From: Justin Pryzby Date: Mon, 9 Mar 2020 22:40:24 -0500 Subject: [PATCH v36 3/7] Add pg_ls_dir_metadata to list a dir with file metadata.. 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"); + + + + pg_ls_dir_metadata + + pg_ls_dir_metadata ( dirname text + , missing_ok boolean, + include_dot_dirs boolean ) + setof record + ( filename text, + size bigint, + modification timestamp with time zone ) + + + 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. + + + 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"