agora inbox for pgsql-hackers@postgresql.orghelp / color / mirror / Atom feed
[PATCH v9 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. 22+ messages / 2 participants [nested] [flat]
* [PATCH v9 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-08 22:15 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-08 22:15 UTC (permalink / raw) Need catversion bumped? --- src/backend/utils/adt/genfile.c | 51 ++++++++++++++++++++++++++------- src/include/catalog/pg_proc.dat | 6 ++++ 2 files changed, 47 insertions(+), 10 deletions(-) diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 897b11a77d..4699aea568 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -524,7 +524,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) /* Generic function to return a directory listing of files */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok, bool dir_ok) { FuncCallContext *funcctx; struct dirent *de; @@ -540,13 +540,17 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) fctx = palloc(sizeof(directory_fctx)); - tupdesc = CreateTemplateTupleDesc(3); + tupdesc = CreateTemplateTupleDesc(dir_ok ? 4:3); TupleDescInitEntry(tupdesc, (AttrNumber) 1, "name", TEXTOID, -1, 0); TupleDescInitEntry(tupdesc, (AttrNumber) 2, "size", INT8OID, -1, 0); TupleDescInitEntry(tupdesc, (AttrNumber) 3, "modification", TIMESTAMPTZOID, -1, 0); + if (dir_ok) + TupleDescInitEntry(tupdesc, (AttrNumber) 4, "isdir", + BOOLOID, -1, 0); + funcctx->tuple_desc = BlessTupleDesc(tupdesc); fctx->location = pstrdup(dir); @@ -575,8 +579,8 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) while ((de = ReadDir(fctx->dirdesc, fctx->location)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; HeapTuple tuple; @@ -592,13 +596,21 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) (errcode_for_file_access(), errmsg("could not stat file \"%s\": %m", path))); - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) + if (S_ISDIR(attrib.st_mode)) + { + if (!dir_ok) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + /* Ignore anything but regular files */ continue; values[0] = CStringGetTextDatum(de->d_name); values[1] = Int64GetDatum((int64) attrib.st_size); values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (dir_ok) + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); + memset(nulls, 0, sizeof(nulls)); tuple = heap_form_tuple(funcctx->tuple_desc, values, nulls); @@ -613,14 +625,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, false, false); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, false, false); } /* @@ -638,7 +650,7 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, true, false); } /* @@ -667,5 +679,24 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true, false); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + bool missing_ok = false; + bool include_dot_dirs = false; + + if (!PG_ARGISNULL(1)) + missing_ok = PG_GETARG_BOOL(1); + if (!PG_ARGISNULL(2)) + /* XXX: Not implemented */ + include_dot_dirs = PG_GETARG_BOOL(2); + + return pg_ls_dir_files(fcinfo, dirname, missing_ok, true); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 7fb574f9dc..0a1859f709 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10741,6 +10741,12 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '5032', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool bool', + proallargtypes => '{text,bool,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,dir_ok,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', -- 2.17.0 --32u276st3Jlj2kUU Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v9-0005-Add-tests-exercizing-pg_ls_tmpdir.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v9 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-08 22:15 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-08 22:15 UTC (permalink / raw) Need catversion bumped? --- src/backend/utils/adt/genfile.c | 51 ++++++++++++++++++++++++++------- src/include/catalog/pg_proc.dat | 6 ++++ 2 files changed, 47 insertions(+), 10 deletions(-) diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 897b11a77d..4699aea568 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -524,7 +524,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) /* Generic function to return a directory listing of files */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok, bool dir_ok) { FuncCallContext *funcctx; struct dirent *de; @@ -540,13 +540,17 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) fctx = palloc(sizeof(directory_fctx)); - tupdesc = CreateTemplateTupleDesc(3); + tupdesc = CreateTemplateTupleDesc(dir_ok ? 4:3); TupleDescInitEntry(tupdesc, (AttrNumber) 1, "name", TEXTOID, -1, 0); TupleDescInitEntry(tupdesc, (AttrNumber) 2, "size", INT8OID, -1, 0); TupleDescInitEntry(tupdesc, (AttrNumber) 3, "modification", TIMESTAMPTZOID, -1, 0); + if (dir_ok) + TupleDescInitEntry(tupdesc, (AttrNumber) 4, "isdir", + BOOLOID, -1, 0); + funcctx->tuple_desc = BlessTupleDesc(tupdesc); fctx->location = pstrdup(dir); @@ -575,8 +579,8 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) while ((de = ReadDir(fctx->dirdesc, fctx->location)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; HeapTuple tuple; @@ -592,13 +596,21 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) (errcode_for_file_access(), errmsg("could not stat file \"%s\": %m", path))); - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) + if (S_ISDIR(attrib.st_mode)) + { + if (!dir_ok) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + /* Ignore anything but regular files */ continue; values[0] = CStringGetTextDatum(de->d_name); values[1] = Int64GetDatum((int64) attrib.st_size); values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (dir_ok) + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); + memset(nulls, 0, sizeof(nulls)); tuple = heap_form_tuple(funcctx->tuple_desc, values, nulls); @@ -613,14 +625,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, false, false); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, false, false); } /* @@ -638,7 +650,7 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, true, false); } /* @@ -667,5 +679,24 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true, false); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + bool missing_ok = false; + bool include_dot_dirs = false; + + if (!PG_ARGISNULL(1)) + missing_ok = PG_GETARG_BOOL(1); + if (!PG_ARGISNULL(2)) + /* XXX: Not implemented */ + include_dot_dirs = PG_GETARG_BOOL(2); + + return pg_ls_dir_files(fcinfo, dirname, missing_ok, true); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 7fb574f9dc..0a1859f709 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10741,6 +10741,12 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '5032', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool bool', + proallargtypes => '{text,bool,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,dir_ok,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', -- 2.17.0 --32u276st3Jlj2kUU Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v9-0005-Add-tests-exercizing-pg_ls_tmpdir.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v15 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir XXX: Change to use lstat() to allow pg_ls_dir_recurse to avoid infinite recursion. That means: - links to dirs are NOT SHOWN (was: shown with isdir=false;) - NO: timestamps shown are those of the link; - changed pg_stat_file for consistency; Need catversion bumped? --- doc/src/sgml/func.sgml | 17 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 227 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 214 insertions(+), 91 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 630f03d7dd..ed8e1977ba 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -21372,6 +21372,15 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); List the contents of a directory. Restricted to superusers by default, but other users can be granted EXECUTE to run the function. </entry> </row> + <row> + <entry> + <literal><function>pg_ls_dir_metadata(<parameter>dirname</parameter> <type>text</type> [, <parameter>missing_ok</parameter> <type>boolean</type>, <parameter>include_dot_dirs</parameter> <type>boolean</type>])</function></literal> + </entry> + <entry><type>setof text</type></entry> + <entry> + For each file in a directory, list the file and its metadata. Restricted to superusers by default, but other users can be granted EXECUTE to run the function. + </entry> + </row> <row> <entry> <literal><function>pg_ls_logdir()</function></literal> @@ -21472,6 +21481,14 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); empty directory from an non-existent directory. </para> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <para> + <function>pg_ls_dir_metadata</function> lists the files in the specified + directory along with the file's metadata. + </para> + <indexterm> <primary>pg_ls_logdir</primary> </indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 83d00c6cde..4511f9d658 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1436,6 +1436,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 219ac160f8..eaa7c548e0 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata. + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS|LS_DIR_SKIP_HIDDEN|LS_DIR_SKIP_SPECIAL|LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -413,6 +428,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -440,79 +460,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -525,7 +475,9 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -535,7 +487,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -544,6 +496,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -558,8 +536,18 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } else { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -578,20 +566,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags&LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -606,13 +601,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -626,14 +642,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -651,7 +667,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -680,5 +697,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index a6a708cca9..e8846e1522 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10801,6 +10801,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '5032', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '5033', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 2e87c548eb..7930909f02 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -219,6 +219,30 @@ select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false ERROR: could not open directory "does not exist": No such file or directory +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + name | isdir +------+------- + . | t +(1 row) + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + name | isdir +------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + name | size | modification | isdir +------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index f6857ad177..372345720d 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -65,6 +65,17 @@ select * from (select pg_ls_dir('.', false, false) as name) as ls where ls.name= select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --8w3uRX/HFJGApMzv Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v15-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v37 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 205 ++++++++++++------- src/include/catalog/pg_proc.dat | 12 ++ src/test/regress/expected/misc_functions.out | 24 +++ src/test/regress/expected/tablespace.out | 8 + src/test/regress/sql/misc_functions.sql | 11 + src/test/regress/sql/tablespace.sql | 5 + 8 files changed, 217 insertions(+), 70 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index d958c3e74ac..a80d794a43a 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25900,6 +25900,27 @@ LOG: Grand total: 1651920 bytes in 201 blocks; 622360 free (88 chunks); 1029560 </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index 30a048f6b09..b77b83017cb 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -704,6 +704,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index ab6f67f8747..c041c7630c8 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything beginning with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -516,6 +531,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -543,54 +563,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - DIR *dirdesc; - struct dirent *de; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - InitMaterializedSRF(fcinfo, MAT_SRF_USE_EXPECTED_DESC); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, - values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -603,23 +578,55 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; DIR *dirdesc; struct dirent *de; - InitMaterializedSRF(fcinfo, 0); + /* isdir depends on metadata */ + Assert(!(flags & LS_DIR_ISDIR) || (flags & LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags & LS_DIR_ISDIR) || !(flags & LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + /* missing_ok */ + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + /* include_dot_dirs */ + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } + + if (flags & LS_DIR_METADATA) + InitMaterializedSRF(fcinfo, 0); + else + InitMaterializedSRF(fcinfo, MAT_SRF_USE_EXPECTED_DESC); /* * Now walk the directory. Note that we must do this within a single SRF @@ -630,20 +637,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -658,13 +672,35 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); + else +#endif + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -678,14 +714,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -703,7 +739,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -732,7 +769,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -741,7 +806,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -750,7 +815,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -775,5 +840,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 20f5aa56eab..89892647808 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11758,6 +11758,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 77d285ecc85..a656f9ad07e 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -539,6 +539,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/expected/tablespace.out b/src/test/regress/expected/tablespace.out index c52cf1cfcf9..8159c9f18f1 100644 --- a/src/test/regress/expected/tablespace.out +++ b/src/test/regress/expected/tablespace.out @@ -33,6 +33,14 @@ SELECT regexp_replace(pg_tablespace_location(oid), '(pg_tblspc)/(\d+)', '\1/NNN' pg_tblspc/NNN (1 row) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index d299f3d8949..f808555382d 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -181,6 +181,17 @@ select * from pg_ls_tmpdir() limit 0; select * from pg_ls_waldir() limit 0; select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/sql/tablespace.sql b/src/test/regress/sql/tablespace.sql index 21db433f2a8..cf683c3bf3a 100644 --- a/src/test/regress/sql/tablespace.sql +++ b/src/test/regress/sql/tablespace.sql @@ -27,6 +27,11 @@ CREATE TABLESPACE regress_tblspace LOCATION ''; SELECT regexp_replace(pg_tablespace_location(oid), '(pg_tblspc)/(\d+)', '\1/NNN') FROM pg_tablespace WHERE spcname = 'regress_tblspace'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail -- 2.25.1 --Pk/CTwBz1VvfPIDp Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v37-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v36 3/7] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 205 ++++++++++++------- src/include/catalog/pg_proc.dat | 12 ++ src/test/regress/expected/misc_functions.out | 24 +++ src/test/regress/expected/tablespace.out | 8 + src/test/regress/sql/misc_functions.sql | 11 + src/test/regress/sql/tablespace.sql | 5 + 8 files changed, 217 insertions(+), 70 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 933118203f4..ba30faa8441 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25940,6 +25940,27 @@ SELECT collation for ('foo' COLLATE "de_DE"); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index 73da687d5dd..3fa6f9af0a8 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -700,6 +700,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 2bf52192567..c7322ed405a 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything beginning with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -446,6 +461,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -473,54 +493,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - DIR *dirdesc; - struct dirent *de; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - SetSingleFuncCall(fcinfo, SRF_SINGLE_USE_EXPECTED); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, - values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -533,23 +508,55 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; DIR *dirdesc; struct dirent *de; - SetSingleFuncCall(fcinfo, 0); + /* isdir depends on metadata */ + Assert(!(flags & LS_DIR_ISDIR) || (flags & LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags & LS_DIR_ISDIR) || !(flags & LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + /* missing_ok */ + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + /* include_dot_dirs */ + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } + + if (flags & LS_DIR_METADATA) + SetSingleFuncCall(fcinfo, 0); + else + SetSingleFuncCall(fcinfo, SRF_SINGLE_USE_EXPECTED); /* * Now walk the directory. Note that we must do this within a single SRF @@ -560,20 +567,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -588,13 +602,35 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); + else +#endif + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -608,14 +644,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -633,7 +669,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -662,7 +699,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -671,7 +736,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -680,7 +745,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -705,5 +770,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 87aa571a331..0e5c977e69f 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11815,6 +11815,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 45544469af5..e54e38f54ad 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -475,6 +475,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/expected/tablespace.out b/src/test/regress/expected/tablespace.out index c52cf1cfcf9..8159c9f18f1 100644 --- a/src/test/regress/expected/tablespace.out +++ b/src/test/regress/expected/tablespace.out @@ -33,6 +33,14 @@ SELECT regexp_replace(pg_tablespace_location(oid), '(pg_tblspc)/(\d+)', '\1/NNN' pg_tblspc/NNN (1 row) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index 59d6e517503..fcb456f434d 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -155,6 +155,17 @@ select * from pg_ls_tmpdir() limit 0; select * from pg_ls_waldir() limit 0; select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/sql/tablespace.sql b/src/test/regress/sql/tablespace.sql index 21db433f2a8..cf683c3bf3a 100644 --- a/src/test/regress/sql/tablespace.sql +++ b/src/test/regress/sql/tablespace.sql @@ -27,6 +27,11 @@ CREATE TABLESPACE regress_tblspace LOCATION ''; SELECT regexp_replace(pg_tablespace_location(oid), '(pg_tblspc)/(\d+)', '\1/NNN') FROM pg_tablespace WHERE spcname = 'regress_tblspace'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail -- 2.17.1 --4ybNbZnZ8tziJ7D6 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v36-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v34 03/15] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 203 ++++++++++++------- src/include/catalog/pg_proc.dat | 12 ++ src/test/regress/expected/misc_functions.out | 24 +++ src/test/regress/expected/tablespace.out | 8 + src/test/regress/sql/misc_functions.sql | 11 + src/test/regress/sql/tablespace.sql | 5 + 8 files changed, 215 insertions(+), 70 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 0be4743e3ed..c2ff924d021 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25976,6 +25976,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index 81bac6f5812..b4d3609cce7 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -700,6 +700,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 1ed01620a1b..1878bac7eb3 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything beginning with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -446,6 +461,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -473,54 +493,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - DIR *dirdesc; - struct dirent *de; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - SetSingleFuncCall(fcinfo, SRF_SINGLE_USE_EXPECTED); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, - values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -533,23 +508,53 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; DIR *dirdesc; struct dirent *de; - SetSingleFuncCall(fcinfo, 0); + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } + + if (flags & LS_DIR_METADATA) + SetSingleFuncCall(fcinfo, 0); + else + SetSingleFuncCall(fcinfo, SRF_SINGLE_USE_EXPECTED); /* * Now walk the directory. Note that we must do this within a single SRF @@ -560,20 +565,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -588,13 +600,35 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); + else +#endif + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -608,14 +642,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -633,7 +667,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -662,7 +697,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -671,7 +734,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -680,7 +743,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -705,5 +768,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index d8e8715ed1c..43ee0cdc454 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11677,6 +11677,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index b08e7c4a6d0..d18f401248a 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -452,6 +452,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/expected/tablespace.out b/src/test/regress/expected/tablespace.out index 2dfbcfdebe1..c6b9074ab02 100644 --- a/src/test/regress/expected/tablespace.out +++ b/src/test/regress/expected/tablespace.out @@ -24,6 +24,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION ''; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index ebb0352ac68..05794e1ae45 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -147,6 +147,17 @@ select * from pg_ls_tmpdir() limit 0; select * from pg_ls_waldir() limit 0; select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/sql/tablespace.sql b/src/test/regress/sql/tablespace.sql index 896f05cea32..3aadac8b611 100644 --- a/src/test/regress/sql/tablespace.sql +++ b/src/test/regress/sql/tablespace.sql @@ -23,6 +23,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION ''; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail -- 2.17.1 --smOfPzt+Qjm5bNGJ Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v34-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v35 3/7] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 205 ++++++++++++------- src/include/catalog/pg_proc.dat | 12 ++ src/test/regress/expected/misc_functions.out | 24 +++ src/test/regress/expected/tablespace.out | 8 + src/test/regress/sql/misc_functions.sql | 11 + src/test/regress/sql/tablespace.sql | 5 + 8 files changed, 217 insertions(+), 70 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index d01aeec9f88..d2a455a3e27 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25987,6 +25987,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index 81bac6f5812..b4d3609cce7 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -700,6 +700,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 88f279d1b31..75b7bf99849 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything beginning with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -446,6 +461,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -473,54 +493,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - DIR *dirdesc; - struct dirent *de; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - SetSingleFuncCall(fcinfo, SRF_SINGLE_USE_EXPECTED); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, - values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -533,23 +508,55 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; DIR *dirdesc; struct dirent *de; - SetSingleFuncCall(fcinfo, 0); + /* isdir depends on metadata */ + Assert(!(flags & LS_DIR_ISDIR) || (flags & LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags & LS_DIR_ISDIR) || !(flags & LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + /* missing_ok */ + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + /* include_dot_dirs */ + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } + + if (flags & LS_DIR_METADATA) + SetSingleFuncCall(fcinfo, 0); + else + SetSingleFuncCall(fcinfo, SRF_SINGLE_USE_EXPECTED); /* * Now walk the directory. Note that we must do this within a single SRF @@ -560,20 +567,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -588,13 +602,35 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); + else +#endif + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls); @@ -608,14 +644,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -633,7 +669,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -662,7 +699,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -671,7 +736,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -680,7 +745,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -705,5 +770,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 25304430f44..7307f44f371 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11769,6 +11769,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 45544469af5..e54e38f54ad 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -475,6 +475,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/expected/tablespace.out b/src/test/regress/expected/tablespace.out index c52cf1cfcf9..8159c9f18f1 100644 --- a/src/test/regress/expected/tablespace.out +++ b/src/test/regress/expected/tablespace.out @@ -33,6 +33,14 @@ SELECT regexp_replace(pg_tablespace_location(oid), '(pg_tblspc)/(\d+)', '\1/NNN' pg_tblspc/NNN (1 row) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index 59d6e517503..fcb456f434d 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -155,6 +155,17 @@ select * from pg_ls_tmpdir() limit 0; select * from pg_ls_waldir() limit 0; select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/sql/tablespace.sql b/src/test/regress/sql/tablespace.sql index 21db433f2a8..cf683c3bf3a 100644 --- a/src/test/regress/sql/tablespace.sql +++ b/src/test/regress/sql/tablespace.sql @@ -27,6 +27,11 @@ CREATE TABLESPACE regress_tblspace LOCATION ''; SELECT regexp_replace(pg_tablespace_location(oid), '(pg_tblspc)/(\d+)', '\1/NNN') FROM pg_tablespace WHERE spcname = 'regress_tblspace'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail -- 2.17.1 --olLTNZSltDMg5Vbm Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v35-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v32 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 239 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/expected/tablespace.out | 8 + src/test/regress/sql/misc_functions.sql | 11 + src/test/regress/sql/tablespace.sql | 5 + 8 files changed, 225 insertions(+), 96 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index b5c1befe627..7948e6ec06c 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25945,6 +25945,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index 3a4fa9091b1..5eb6cc8572c 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -702,6 +702,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 027ed864001..0728547ec2b 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -452,6 +467,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -479,79 +499,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -564,17 +514,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -583,6 +535,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -597,8 +575,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -617,20 +607,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -645,13 +642,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -665,14 +683,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -690,7 +708,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -719,7 +738,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -728,7 +775,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -737,7 +784,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -762,5 +809,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 4d992dc2241..c99e1633bbf 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11645,6 +11645,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 830de507e7c..b3a9d11b5c0 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -267,6 +267,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/expected/tablespace.out b/src/test/regress/expected/tablespace.out index 864f4b6e208..21f7f19b67f 100644 --- a/src/test/regress/expected/tablespace.out +++ b/src/test/regress/expected/tablespace.out @@ -16,6 +16,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION :'testtablespace'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index 422a1369aeb..ca946d08bde 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -99,6 +99,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/sql/tablespace.sql b/src/test/regress/sql/tablespace.sql index 92076db9a13..291ca029c14 100644 --- a/src/test/regress/sql/tablespace.sql +++ b/src/test/regress/sql/tablespace.sql @@ -16,6 +16,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION :'testtablespace'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail -- 2.17.0 --Bne5rrxQd65beI7a Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v32-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v31 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 239 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 225 insertions(+), 96 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index d36479d86d..e0099e77df 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25860,6 +25860,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index f6789025a5..a45bac89ff 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -698,6 +698,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 027ed86400..0728547ec2 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -452,6 +467,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -479,79 +499,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -564,17 +514,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -583,6 +535,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -597,8 +575,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -617,20 +607,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -645,13 +642,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -665,14 +683,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -690,7 +708,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -719,7 +738,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -728,7 +775,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -737,7 +784,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -762,5 +809,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index e934361dc3..39fbaacbc9 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11645,6 +11645,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 830de507e7..b3a9d11b5c 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -267,6 +267,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index cb9774ecc8..e69fa17004 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index e7629d470e..c2f6d64c5c 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index 422a1369ae..ca946d08bd 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -99,6 +99,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- -- 2.17.0 --qZVVwWJgpX9Jzs7f Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v31-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v31 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 239 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 225 insertions(+), 96 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index d36479d86d..e0099e77df 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25860,6 +25860,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index f6789025a5..a45bac89ff 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -698,6 +698,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 027ed86400..0728547ec2 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -452,6 +467,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -479,79 +499,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -564,17 +514,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -583,6 +535,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -597,8 +575,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -617,20 +607,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -645,13 +642,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -665,14 +683,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -690,7 +708,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -719,7 +738,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -728,7 +775,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -737,7 +784,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -762,5 +809,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index e934361dc3..39fbaacbc9 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11645,6 +11645,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 830de507e7..b3a9d11b5c 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -267,6 +267,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index cb9774ecc8..e69fa17004 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index e7629d470e..c2f6d64c5c 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index 422a1369ae..ca946d08bd 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -99,6 +99,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- -- 2.17.0 --qZVVwWJgpX9Jzs7f Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v31-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v30 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 233 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 222 insertions(+), 93 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 7a830f0684..dd9b1afde4 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25848,6 +25848,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index a416e94d37..649a78605a 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -698,6 +698,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index c436d9318b..8efb798b2f 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -451,6 +466,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -478,79 +498,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -563,17 +513,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -582,6 +534,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -596,8 +574,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -616,20 +606,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -644,13 +641,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -664,14 +682,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -689,7 +707,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -718,5 +737,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index fde251fa4f..b405aa341c 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11547,6 +11547,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index ea0fc48dbd..b4112ec298 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -238,6 +238,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index c133e73499..a32212be04 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 1bbe7e0323..5f7ce3d09f 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index eb6ac12ab4..c169e527d9 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -77,6 +77,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --ZwgA9U+XZDXt4+m+ Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v30-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v28 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 233 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 222 insertions(+), 93 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index aa0dcde886..507a6d73f8 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25821,6 +25821,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 451db2ee0a..dd84b0f11a 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1632,6 +1632,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 322152ebd9..f59f853983 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -452,6 +467,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -479,79 +499,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -564,17 +514,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -583,6 +535,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -597,8 +575,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -617,20 +607,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -645,13 +642,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -665,14 +683,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -690,7 +708,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -719,5 +738,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index f4957653ae..550fbf734a 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11534,6 +11534,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index ea0fc48dbd..b4112ec298 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -238,6 +238,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index c133e73499..a32212be04 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 1bbe7e0323..5f7ce3d09f 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index eb6ac12ab4..c169e527d9 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -77,6 +77,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --vk/v8fjDPiDepTtA Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v28-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v25 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 231 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 221 insertions(+), 92 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index df29af6371..226923a134 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25750,6 +25750,27 @@ SELECT pg_size_pretty(sum(pg_relation_size(relid))) AS total_size </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index b140c210bc..93d4f1e4a6 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1506,6 +1506,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 9f4927220b..7351615f8a 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -449,6 +464,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -476,79 +496,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -561,17 +511,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* * Generic function to return a directory listing of files. * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -580,6 +532,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -594,8 +572,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -614,20 +604,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -642,13 +639,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -662,14 +680,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -687,7 +705,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -716,5 +735,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index fc2202b843..8e88c549d9 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10976,6 +10976,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '9979', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '9980', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index edbfd9abc1..fd7c3c791f 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -225,6 +225,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index b32a3a4b74..64d9d70874 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -68,6 +68,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --SBikYMzjhZGK9d4p Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v25-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v24 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 231 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 221 insertions(+), 92 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 507bc1a668..5e267c4f8d 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25757,6 +25757,27 @@ SELECT pg_size_pretty(sum(pg_relation_size(relid))) AS total_size </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 2e4aa1c4b6..e7647787cf 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1503,6 +1503,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 9f4927220b..7351615f8a 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -449,6 +464,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -476,79 +496,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -561,17 +511,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* * Generic function to return a directory listing of files. * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -580,6 +532,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -594,8 +572,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -614,20 +604,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -642,13 +639,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -662,14 +680,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -687,7 +705,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -716,5 +735,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index e7fbda9f81..f35a684dcf 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10975,6 +10975,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '9979', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '9980', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index edbfd9abc1..fd7c3c791f 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -225,6 +225,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index b32a3a4b74..64d9d70874 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -68,6 +68,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --mPTHnM80CEnHQ2WJ Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v24-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v22 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 229 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 220 insertions(+), 91 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 7ef2ec9972..34c92903d8 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25747,6 +25747,27 @@ SELECT pg_size_pretty(sum(pg_relation_size(relid))) AS total_size </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type>] </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>name</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index c6dd084fbc..169602c1b6 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1509,6 +1509,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 9f4927220b..054b8d4b1a 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata. + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -449,6 +464,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -476,79 +496,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -561,7 +511,9 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -571,7 +523,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -580,6 +532,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -594,8 +572,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -614,20 +604,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -642,13 +639,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -662,14 +680,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -687,7 +705,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -716,5 +735,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 24ec2cfed6..02b1436d83 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10964,6 +10964,18 @@ proallargtypes => '{regclass,text,text,int8}', proargmodes => '{i,i,o,o}', proargnames => '{relation,fork,path,failed_block_num}', prosrc => 'pg_relation_check_pages' }, +{ oid => '9979', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '9980', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 2e87c548eb..20bfe71822 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -219,6 +219,30 @@ select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false ERROR: could not open directory "does not exist": No such file or directory +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index f6857ad177..68e2bc6586 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -65,6 +65,17 @@ select * from (select pg_ls_dir('.', false, false) as name) as ls where ls.name= select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --d6Gm4EdcadzBjdND Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v22-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v20 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 229 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 220 insertions(+), 91 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 959f6a1c2f..eead88419f 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25741,6 +25741,27 @@ SELECT pg_size_pretty(sum(pg_relation_size(relid))) AS total_size </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type>] </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>name</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index b6d35c2d11..360b6bda26 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1478,6 +1478,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 46d0977c2e..3324ffe16a 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata. + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS|LS_DIR_SKIP_HIDDEN|LS_DIR_SKIP_SPECIAL|LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -449,6 +464,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -476,79 +496,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -561,7 +511,9 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -571,7 +523,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -580,6 +532,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -594,8 +572,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -614,20 +604,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -642,13 +639,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -662,14 +680,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -687,7 +705,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -716,5 +735,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 95604e988a..186ced4a35 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10919,6 +10919,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '9979', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '9980', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 2e87c548eb..7930909f02 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -219,6 +219,30 @@ select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false ERROR: could not open directory "does not exist": No such file or directory +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + name | isdir +------+------- + . | t +(1 row) + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + name | isdir +------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + name | size | modification | isdir +------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index f6857ad177..372345720d 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -65,6 +65,17 @@ select * from (select pg_ls_dir('.', false, false) as name) as ls where ls.name= select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --Z1Z8UV8BNhgCynIS Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v20-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v21 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 229 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 220 insertions(+), 91 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 959f6a1c2f..eead88419f 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25741,6 +25741,27 @@ SELECT pg_size_pretty(sum(pg_relation_size(relid))) AS total_size </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type>] </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>name</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 8625cbeab6..b9b2a6aa20 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1478,6 +1478,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 9f4927220b..24d858d1bc 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata. + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS|LS_DIR_SKIP_HIDDEN|LS_DIR_SKIP_SPECIAL|LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -449,6 +464,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -476,79 +496,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -561,7 +511,9 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -571,7 +523,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -580,6 +532,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -594,8 +572,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -614,20 +604,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -642,13 +639,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -662,14 +680,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -687,7 +705,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -716,5 +735,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 95604e988a..83927b510a 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10919,6 +10919,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '9979', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '9980', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 2e87c548eb..20bfe71822 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -219,6 +219,30 @@ select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false ERROR: could not open directory "does not exist": No such file or directory +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index f6857ad177..68e2bc6586 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -65,6 +65,17 @@ select * from (select pg_ls_dir('.', false, false) as name) as ls where ls.name= select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --Tcb1KvpfnM4LxW2s Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v21-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v19 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 229 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 220 insertions(+), 91 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index b7c450ea29..2931f9d7d5 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25711,6 +25711,27 @@ SELECT pg_size_pretty(sum(pg_relation_size(relid))) AS total_size </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type>] </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>name</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 5314e9348f..f5217a0d93 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1481,6 +1481,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 219ac160f8..4824a55480 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata. + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS|LS_DIR_SKIP_HIDDEN|LS_DIR_SKIP_SPECIAL|LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -413,6 +428,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -440,79 +460,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -525,7 +475,9 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -535,7 +487,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -544,6 +496,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -558,8 +536,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -578,20 +568,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -606,13 +603,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -626,14 +644,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -651,7 +669,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -680,5 +699,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 61f2c2f5b4..5b0147ee2d 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10902,6 +10902,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '9979', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '9980', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 2e87c548eb..7930909f02 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -219,6 +219,30 @@ select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false ERROR: could not open directory "does not exist": No such file or directory +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + name | isdir +------+------- + . | t +(1 row) + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + name | isdir +------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + name | size | modification | isdir +------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index f6857ad177..372345720d 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -65,6 +65,17 @@ select * from (select pg_ls_dir('.', false, false) as name) as ls where ls.name= select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --S0GG+JvAI2G0KxBG Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v19-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v15 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir XXX: Change to use lstat() to allow pg_ls_dir_recurse to avoid infinite recursion. That means: - links to dirs are NOT SHOWN (was: shown with isdir=false;) - NO: timestamps shown are those of the link; - changed pg_stat_file for consistency; Need catversion bumped? --- doc/src/sgml/func.sgml | 17 ++ src/backend/catalog/system_views.sql | 1 + src/backend/utils/adt/genfile.c | 227 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 214 insertions(+), 91 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 630f03d7dd..ed8e1977ba 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -21372,6 +21372,15 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); List the contents of a directory. Restricted to superusers by default, but other users can be granted EXECUTE to run the function. </entry> </row> + <row> + <entry> + <literal><function>pg_ls_dir_metadata(<parameter>dirname</parameter> <type>text</type> [, <parameter>missing_ok</parameter> <type>boolean</type>, <parameter>include_dot_dirs</parameter> <type>boolean</type>])</function></literal> + </entry> + <entry><type>setof text</type></entry> + <entry> + For each file in a directory, list the file and its metadata. Restricted to superusers by default, but other users can be granted EXECUTE to run the function. + </entry> + </row> <row> <entry> <literal><function>pg_ls_logdir()</function></literal> @@ -21472,6 +21481,14 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); empty directory from an non-existent directory. </para> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <para> + <function>pg_ls_dir_metadata</function> lists the files in the specified + directory along with the file's metadata. + </para> + <indexterm> <primary>pg_ls_logdir</primary> </indexterm> diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index 83d00c6cde..4511f9d658 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1436,6 +1436,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 219ac160f8..eaa7c548e0 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata. + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS|LS_DIR_SKIP_HIDDEN|LS_DIR_SKIP_SPECIAL|LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -413,6 +428,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -440,79 +460,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -525,7 +475,9 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -535,7 +487,7 @@ pg_ls_dir_1arg(PG_FUNCTION_ARGS) * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -544,6 +496,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -558,8 +536,18 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } else { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -578,20 +566,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags&LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -606,13 +601,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -626,14 +642,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -651,7 +667,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -680,5 +697,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Function to return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index a6a708cca9..e8846e1522 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -10801,6 +10801,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '5032', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '5033', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,name,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index 2e87c548eb..7930909f02 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -219,6 +219,30 @@ select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false ERROR: could not open directory "does not exist": No such file or directory +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + name | isdir +------+------- + . | t +(1 row) + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + name | isdir +------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + name | size | modification | isdir +------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index a5f61a35dc..0b9cfe615e 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 162b591b31..a42714bf40 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index f6857ad177..372345720d 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -65,6 +65,17 @@ select * from (select pg_ls_dir('.', false, false) as name) as ls where ls.name= select pg_ls_dir('does not exist', true, false); -- ok with missingok=true select pg_ls_dir('does not exist'); -- fails with missingok=false +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select name, isdir from pg_ls_dir_metadata('.') where name='.'; + +select name, isdir from pg_ls_dir_metadata('.', false, false) where name='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --8w3uRX/HFJGApMzv Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v15-0005-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v33 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 240 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/expected/tablespace.out | 8 + src/test/regress/sql/misc_functions.sql | 11 + src/test/regress/sql/tablespace.sql | 5 + 8 files changed, 226 insertions(+), 96 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index d32b414e04f..14b8fba3123 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25958,6 +25958,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index fd1421788e6..2ffc2f9d1a6 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -702,6 +702,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_log_backend_memory_contexts(integer) FROM PUBLIC; diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index 542bbacaa24..3921723fda6 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -37,6 +37,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -452,6 +467,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -479,79 +499,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -564,17 +514,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -583,6 +535,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -597,8 +575,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -617,20 +607,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -645,13 +642,35 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); + else +#endif + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -665,14 +684,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -690,7 +709,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -719,7 +739,35 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } /* @@ -728,7 +776,7 @@ pg_ls_archive_statusdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", false); + return pg_ls_dir_files(fcinfo, "pg_logical/snapshots", LS_DIR_HISTORIC); } /* @@ -737,7 +785,7 @@ pg_ls_logicalsnapdir(PG_FUNCTION_ARGS) Datum pg_ls_logicalmapdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, "pg_logical/mappings", false); + return pg_ls_dir_files(fcinfo, "pg_logical/mappings", LS_DIR_HISTORIC); } /* @@ -762,5 +810,5 @@ pg_ls_replslotdir(PG_FUNCTION_ARGS) slotname))); snprintf(path, sizeof(path), "pg_replslot/%s", slotname); - return pg_ls_dir_files(fcinfo, path, false); + return pg_ls_dir_files(fcinfo, path, LS_DIR_HISTORIC); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 0859dc81cac..b58987b713c 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11661,6 +11661,18 @@ proargmodes => '{i,o,o,o}', proargnames => '{slot_name,name,size,modification}', prosrc => 'pg_ls_replslotdir' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index b7264af3ecb..a627839bc28 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -309,6 +309,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/expected/tablespace.out b/src/test/regress/expected/tablespace.out index 2dfbcfdebe1..c6b9074ab02 100644 --- a/src/test/regress/expected/tablespace.out +++ b/src/test/regress/expected/tablespace.out @@ -24,6 +24,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION ''; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index 169f66416c3..bfa8e309e9a 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -109,6 +109,17 @@ select * from pg_ls_tmpdir() limit 0; select * from pg_ls_waldir() limit 0; select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test replication slot directory functions -- diff --git a/src/test/regress/sql/tablespace.sql b/src/test/regress/sql/tablespace.sql index 896f05cea32..3aadac8b611 100644 --- a/src/test/regress/sql/tablespace.sql +++ b/src/test/regress/sql/tablespace.sql @@ -23,6 +23,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION ''; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail -- 2.17.1 --9CzcV6dAFIr7O1Ie Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v33-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH v30 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. @ 2020-03-10 03:40 Justin Pryzby <pryzbyj@telsasoft.com> 0 siblings, 0 replies; 22+ messages in thread From: Justin Pryzby @ 2020-03-10 03:40 UTC (permalink / raw) Generalize pg_ls_dir_files and retire pg_ls_dir Need catversion bumped? --- doc/src/sgml/func.sgml | 21 ++ src/backend/catalog/system_functions.sql | 1 + src/backend/utils/adt/genfile.c | 233 +++++++++++-------- src/include/catalog/pg_proc.dat | 12 + src/test/regress/expected/misc_functions.out | 24 ++ src/test/regress/input/tablespace.source | 5 + src/test/regress/output/tablespace.source | 8 + src/test/regress/sql/misc_functions.sql | 11 + 8 files changed, 222 insertions(+), 93 deletions(-) diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 7a830f0684..dd9b1afde4 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25848,6 +25848,27 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup()); </para></entry> </row> + <row> + <entry role="func_table_entry"><para role="func_signature"> + <indexterm> + <primary>pg_ls_dir_metadata</primary> + </indexterm> + <function>pg_ls_dir_metadata</function> ( <parameter>dirname</parameter> <type>text</type> + <optional>, <parameter>missing_ok</parameter> <type>boolean</type>, + <parameter>include_dot_dirs</parameter> <type>boolean</type> </optional> ) + <returnvalue>setof record</returnvalue> + ( <parameter>filename</parameter> <type>text</type>, + <parameter>size</parameter> <type>bigint</type>, + <parameter>modification</parameter> <type>timestamp with time zone</type> ) + </para> + <para> + For each file in the specified directory, list the file and its + metadata. + Restricted to superusers by default, but other users can be granted + EXECUTE to run the function. + </para></entry> + </row> + <row> <entry role="func_table_entry"><para role="func_signature"> <indexterm> diff --git a/src/backend/catalog/system_functions.sql b/src/backend/catalog/system_functions.sql index a416e94d37..649a78605a 100644 --- a/src/backend/catalog/system_functions.sql +++ b/src/backend/catalog/system_functions.sql @@ -698,6 +698,7 @@ REVOKE EXECUTE ON FUNCTION pg_stat_file(text,boolean) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text) FROM public; REVOKE EXECUTE ON FUNCTION pg_ls_dir(text,boolean,boolean) FROM public; +REVOKE EXECUTE ON FUNCTION pg_ls_dir_metadata(text,boolean,boolean) FROM public; -- -- We also set up some things as accessible to standard roles. diff --git a/src/backend/utils/adt/genfile.c b/src/backend/utils/adt/genfile.c index c436d9318b..8efb798b2f 100644 --- a/src/backend/utils/adt/genfile.c +++ b/src/backend/utils/adt/genfile.c @@ -36,6 +36,21 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +static Datum pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags); + +#define LS_DIR_ISDIR (1<<0) /* Show column: isdir */ +#define LS_DIR_METADATA (1<<1) /* Show columns: mtime, size */ +#define LS_DIR_MISSING_OK (1<<2) /* Ignore ENOENT if the toplevel dir is missing */ +#define LS_DIR_SKIP_DOT_DIRS (1<<3) /* Do not show . or .. */ +#define LS_DIR_SKIP_HIDDEN (1<<4) /* Do not show anything begining with . */ +#define LS_DIR_SKIP_DIRS (1<<5) /* Do not show directories */ +#define LS_DIR_SKIP_SPECIAL (1<<6) /* Do not show special file types */ + +/* + * Shortcut for the historic behavior of the pg_ls_* functions (not including + * pg_ls_dir, which skips different files and doesn't show metadata). + */ +#define LS_DIR_HISTORIC (LS_DIR_SKIP_DIRS | LS_DIR_SKIP_HIDDEN | LS_DIR_SKIP_SPECIAL | LS_DIR_METADATA) /* * Convert a "text" filename argument to C string, and check it's allowable. @@ -451,6 +466,11 @@ pg_stat_file(PG_FUNCTION_ARGS) values[4] = TimestampTzGetDatum(time_t_to_timestamptz(fst.st_ctime)); #endif values[5] = BoolGetDatum(S_ISDIR(fst.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(filename)) + values[5] = BoolGetDatum(false); +#endif tuple = heap_form_tuple(tupdesc, values, isnull); @@ -478,79 +498,9 @@ pg_stat_file_1arg(PG_FUNCTION_ARGS) Datum pg_ls_dir(PG_FUNCTION_ARGS) { - ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; - char *location; - bool missing_ok = false; - bool include_dot_dirs = false; - bool randomAccess; - TupleDesc tupdesc; - Tuplestorestate *tupstore; - DIR *dirdesc; - struct dirent *de; - MemoryContext oldcontext; - - location = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); - - /* check the optional arguments */ - if (PG_NARGS() == 3) - { - if (!PG_ARGISNULL(1)) - missing_ok = PG_GETARG_BOOL(1); - if (!PG_ARGISNULL(2)) - include_dot_dirs = PG_GETARG_BOOL(2); - } - - /* check to see if caller supports us returning a tuplestore */ - if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("set-valued function called in context that cannot accept a set"))); - if (!(rsinfo->allowedModes & SFRM_Materialize)) - ereport(ERROR, - (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("materialize mode required, but it is not allowed in this context"))); - - /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ - oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - - tupdesc = CreateTemplateTupleDesc(1); - TupleDescInitEntry(tupdesc, (AttrNumber) 1, "pg_ls_dir", TEXTOID, -1, 0); - - randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; - tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); - rsinfo->returnMode = SFRM_Materialize; - rsinfo->setResult = tupstore; - rsinfo->setDesc = tupdesc; - - MemoryContextSwitchTo(oldcontext); - - dirdesc = AllocateDir(location); - if (!dirdesc) - { - /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) - return (Datum) 0; - /* Otherwise, we can let ReadDir() throw the error */ - } - - while ((de = ReadDir(dirdesc, location)) != NULL) - { - Datum values[1]; - bool nulls[1]; - - if (!include_dot_dirs && - (strcmp(de->d_name, ".") == 0 || - strcmp(de->d_name, "..") == 0)) - continue; - - values[0] = CStringGetTextDatum(de->d_name); - nulls[0] = false; - - tuplestore_putvalues(tupstore, tupdesc, values, nulls); - } - - FreeDir(dirdesc); - return (Datum) 0; + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* @@ -563,17 +513,19 @@ pg_ls_dir(PG_FUNCTION_ARGS) Datum pg_ls_dir_1arg(PG_FUNCTION_ARGS) { - return pg_ls_dir(fcinfo); + text *filename_t = PG_GETARG_TEXT_PP(0); + char *filename = convert_and_check_filename(filename_t); + return pg_ls_dir_files(fcinfo, filename, LS_DIR_SKIP_DOT_DIRS); } /* - * Generic function to return a directory listing of files. + * Generic function to return a directory listing of files (and optionally dirs). * - * If the directory isn't there, silently return an empty set if missing_ok. + * If the directory isn't there, silently return an empty set if MISSING_OK. * Other unreadable-directory cases throw an error. */ static Datum -pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) +pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, int flags) { ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo; bool randomAccess; @@ -582,6 +534,32 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) DIR *dirdesc; struct dirent *de; MemoryContext oldcontext; + TypeFuncClass tuptype ; + + /* isdir depends on metadata */ + Assert(!(flags&LS_DIR_ISDIR) || (flags&LS_DIR_METADATA)); + /* Unreasonable to show isdir and skip dirs */ + Assert(!(flags&LS_DIR_ISDIR) || !(flags&LS_DIR_SKIP_DIRS)); + + /* check the optional arguments */ + if (PG_NARGS() == 3) + { + if (!PG_ARGISNULL(1)) + { + if (PG_GETARG_BOOL(1)) + flags |= LS_DIR_MISSING_OK; + else + flags &= ~LS_DIR_MISSING_OK; + } + + if (!PG_ARGISNULL(2)) + { + if (PG_GETARG_BOOL(2)) + flags &= ~LS_DIR_SKIP_DOT_DIRS; + else + flags |= LS_DIR_SKIP_DOT_DIRS; + } + } /* check to see if caller supports us returning a tuplestore */ if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo)) @@ -596,8 +574,20 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) /* The tupdesc and tuplestore must be created in ecxt_per_query_memory */ oldcontext = MemoryContextSwitchTo(rsinfo->econtext->ecxt_per_query_memory); - if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE) - elog(ERROR, "return type must be a row type"); + tuptype = get_call_result_type(fcinfo, NULL, &tupdesc); + if (flags & LS_DIR_METADATA) + { + if (tuptype != TYPEFUNC_COMPOSITE) + elog(ERROR, "return type must be a row type"); + } + else + { + /* pg_ls_dir returns a simple scalar */ + if (tuptype != TYPEFUNC_SCALAR) + elog(ERROR, "return type must be a scalar type"); + tupdesc = CreateTemplateTupleDesc(1); + TupleDescInitEntry(tupdesc, (AttrNumber) 1, "column", TEXTOID, -1, 0); + } randomAccess = (rsinfo->allowedModes & SFRM_Materialize_Random) != 0; tupstore = tuplestore_begin_heap(randomAccess, false, work_mem); @@ -616,20 +606,27 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) if (!dirdesc) { /* Return empty tuplestore if appropriate */ - if (missing_ok && errno == ENOENT) + if (flags & LS_DIR_MISSING_OK && errno == ENOENT) return (Datum) 0; /* Otherwise, we can let ReadDir() throw the error */ } while ((de = ReadDir(dirdesc, dir)) != NULL) { - Datum values[3]; - bool nulls[3]; + Datum values[4]; + bool nulls[4]; char path[MAXPGPATH * 2]; struct stat attrib; - /* Skip hidden files */ - if (de->d_name[0] == '.') + /* Skip dot dirs? */ + if (flags & LS_DIR_SKIP_DOT_DIRS && + (strcmp(de->d_name, ".") == 0 || + strcmp(de->d_name, "..") == 0)) + continue; + + /* Skip hidden files? */ + if (flags & LS_DIR_SKIP_HIDDEN && + de->d_name[0] == '.') continue; /* Get the file info */ @@ -644,13 +641,34 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) errmsg("could not stat file \"%s\": %m", path))); } - /* Ignore anything but regular files */ - if (!S_ISREG(attrib.st_mode)) - continue; + /* Skip dirs or special files? */ + if (S_ISDIR(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_DIRS) + continue; + } + else if (!S_ISREG(attrib.st_mode)) + { + if (flags & LS_DIR_SKIP_SPECIAL) + continue; + } values[0] = CStringGetTextDatum(de->d_name); - values[1] = Int64GetDatum((int64) attrib.st_size); - values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_METADATA) + { + values[1] = Int64GetDatum((int64) attrib.st_size); + values[2] = TimestampTzGetDatum(time_t_to_timestamptz(attrib.st_mtime)); + if (flags & LS_DIR_ISDIR) + { + values[3] = BoolGetDatum(S_ISDIR(attrib.st_mode)); +#ifdef WIN32 + /* Links should have isdir=false */ + if (pgwin32_is_junction(path)) + values[3] = BoolGetDatum(false); +#endif + } + } + memset(nulls, 0, sizeof(nulls)); tuplestore_putvalues(tupstore, tupdesc, values, nulls); @@ -664,14 +682,14 @@ pg_ls_dir_files(FunctionCallInfo fcinfo, const char *dir, bool missing_ok) Datum pg_ls_logdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, Log_directory, false); + return pg_ls_dir_files(fcinfo, Log_directory, LS_DIR_HISTORIC); } /* Function to return the list of files in the WAL directory */ Datum pg_ls_waldir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR, false); + return pg_ls_dir_files(fcinfo, XLOGDIR, LS_DIR_HISTORIC); } /* @@ -689,7 +707,8 @@ pg_ls_tmpdir(FunctionCallInfo fcinfo, Oid tblspc) tblspc))); TempTablespacePath(path, tblspc); - return pg_ls_dir_files(fcinfo, path, true); + return pg_ls_dir_files(fcinfo, path, + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); } /* @@ -718,5 +737,33 @@ pg_ls_tmpdir_1arg(PG_FUNCTION_ARGS) Datum pg_ls_archive_statusdir(PG_FUNCTION_ARGS) { - return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", true); + return pg_ls_dir_files(fcinfo, XLOGDIR "/archive_status", + LS_DIR_HISTORIC | LS_DIR_MISSING_OK); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + */ +Datum +pg_ls_dir_metadata(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); +} + +/* + * Return the list of files and metadata in an arbitrary directory. + * note: this wrapper is necessary to pass the sanity check in opr_sanity, + * which checks that all built-in functions that share the implementing C + * function take the same number of arguments. + */ +Datum +pg_ls_dir_metadata_1arg(PG_FUNCTION_ARGS) +{ + char *dirname = convert_and_check_filename(PG_GETARG_TEXT_PP(0)); + + return pg_ls_dir_files(fcinfo, dirname, + LS_DIR_METADATA | LS_DIR_SKIP_SPECIAL | LS_DIR_ISDIR); } diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index fde251fa4f..b405aa341c 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -11547,6 +11547,18 @@ proallargtypes => '{oid,text,int8,timestamptz}', proargmodes => '{i,o,o,o}', proargnames => '{tablespace,name,size,modification}', prosrc => 'pg_ls_tmpdir_1arg' }, +{ oid => '8450', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text bool bool', + proallargtypes => '{text,bool,bool,text,int8,timestamptz,bool}', proargmodes => '{i,i,i,o,o,o,o}', + proargnames => '{dirname,missing_ok,include_dot_dirs,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata' }, +{ oid => '8451', descr => 'list directory with metadata', + proname => 'pg_ls_dir_metadata', procost => '10', prorows => '20', proretset => 't', + provolatile => 'v', prorettype => 'record', proargtypes => 'text', + proallargtypes => '{text,text,int8,timestamptz,bool}', proargmodes => '{i,o,o,o,o}', + proargnames => '{dirname,filename,size,modification,isdir}', + prosrc => 'pg_ls_dir_metadata_1arg' }, # hash partitioning constraint function { oid => '5028', descr => 'hash partition CHECK constraint', diff --git a/src/test/regress/expected/misc_functions.out b/src/test/regress/expected/misc_functions.out index ea0fc48dbd..b4112ec298 100644 --- a/src/test/regress/expected/misc_functions.out +++ b/src/test/regress/expected/misc_functions.out @@ -238,6 +238,30 @@ select * from pg_stat_file('.') limit 0; ------+--------+--------------+--------+----------+------- (0 rows) +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + filename | isdir +----------+------- + . | t +(1 row) + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + filename | isdir +----------+------- +(0 rows) + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + filename | size | modification | isdir +----------+------+--------------+------- +(0 rows) + -- -- Test adding a support function to a subject function -- diff --git a/src/test/regress/input/tablespace.source b/src/test/regress/input/tablespace.source index c133e73499..a32212be04 100644 --- a/src/test/regress/input/tablespace.source +++ b/src/test/regress/input/tablespace.source @@ -11,6 +11,11 @@ DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/output/tablespace.source b/src/test/regress/output/tablespace.source index 1bbe7e0323..5f7ce3d09f 100644 --- a/src/test/regress/output/tablespace.source +++ b/src/test/regress/output/tablespace.source @@ -13,6 +13,14 @@ SELECT spcoptions FROM pg_tablespace WHERE spcname = 'regress_tblspacewith'; DROP TABLESPACE regress_tblspacewith; -- create a tablespace we can use CREATE TABLESPACE regress_tblspace LOCATION '@testtablespace@'; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +-- The query is written to ERROR if the tablespace doesn't exist, rather than silently failing to call pg_ls_tmpdir() +SELECT c.* FROM (SELECT oid FROM pg_tablespace b WHERE b.spcname='regress_tblspace' UNION SELECT 0 ORDER BY 1 DESC LIMIT 1) AS b , pg_ls_tmpdir(oid) AS c WHERE c.name='Does not exist'; + name | size | modification +------+------+-------------- +(0 rows) + -- try setting and resetting some properties for the new tablespace ALTER TABLESPACE regress_tblspace SET (random_page_cost = 1.0, seq_page_cost = 1.1); ALTER TABLESPACE regress_tblspace SET (some_nonexistent_parameter = true); -- fail diff --git a/src/test/regress/sql/misc_functions.sql b/src/test/regress/sql/misc_functions.sql index eb6ac12ab4..c169e527d9 100644 --- a/src/test/regress/sql/misc_functions.sql +++ b/src/test/regress/sql/misc_functions.sql @@ -77,6 +77,17 @@ select pg_ls_dir('does not exist'); -- fails with missingok=false -- Check that expected columns are present select * from pg_stat_file('.') limit 0; +-- This tests the missing_ok parameter, which causes pg_ls_tmpdir to succeed even if the tmpdir doesn't exist yet +-- The name='' condition is never true, so the function runs to completion but returns zero rows. +select * from pg_ls_tmpdir() where name='Does not exist'; + +select filename, isdir from pg_ls_dir_metadata('.') where filename='.'; + +select filename, isdir from pg_ls_dir_metadata('.', false, false) where filename='.'; -- include_dot_dirs=false + +-- Check that expected columns are present +select * from pg_ls_dir_metadata('.') limit 0; + -- -- Test adding a support function to a subject function -- -- 2.17.0 --ZwgA9U+XZDXt4+m+ Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v30-0004-pg_ls_tmpdir-to-show-directories-and-isdir-argum.patch" ^ permalink raw reply [nested|flat] 22+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <ah@cybertec.at> 0 siblings, 0 replies; 22+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 22+ messages in thread
end of thread, other threads:[~2026-02-27 18:01 UTC | newest] Thread overview: 22+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-03-08 22:15 [PATCH v9 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-08 22:15 [PATCH v9 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v31 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v22 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v37 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v36 3/7] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v34 03/15] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v32 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v31 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v25 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v28 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v30 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v20 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v15 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v33 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v35 3/7] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v30 03/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v24 04/11] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v21 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v19 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2020-03-10 03:40 [PATCH v15 04/10] Add pg_ls_dir_metadata to list a dir with file metadata.. Justin Pryzby <pryzbyj@telsasoft.com> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <ah@cybertec.at>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox