postgres.git / summary / log / commit / refs
commit 9ca3dfba7989ab62e172cfd611d8acdfd56606ac
Author: Andrew Dunstan <andrew@dunslane.net>
Date: Sat Aug 22 21:45:54 2026 +0000
Provide a C-ctype variant expected file for test_regex_utf8
test_regex_utf8 decides whether to run by looking at the database
encoding alone, but two of its cases, [[:graph:]] and [[:print:]] over
E'xᔀሷ', depend on the ctype as well. In a database with encoding
UTF8 and locale C they match just the x, because isgraph() and isprint()
are false for anything outside ASCII, and the file fails.
No buildfarm animal builds such a cluster, which is why this went
unnoticed. A pending buildfarm client change will let an
animal be configured that way.
Fix by providing a second expected file holding the C-ctype answers, in
the manner of json_encoding.sql, which carries expected files for UTF8
and for SQL_ASCII. The .sql needs no change.
This applies to releases 15 and 16 only. A better solution is available
for release 17 and up.
Backpatch to v15, v16 only.
.../test_regex/expected/test_regex_utf8_2.out | 206 +++++++++++++++++++++
1 file changed, 206 insertions(+)
diff --git a/src/test/modules/test_regex/expected/test_regex_utf8_2.out b/src/test/modules/test_regex/expected/test_regex_utf8_2.out
new file mode 100644
index 00000000000..46693c8b74f
--- /dev/null
+++ b/src/test/modules/test_regex/expected/test_regex_utf8_2.out
@@ -0,0 +1,206 @@
+/*
+ * This test must be run in a database with UTF-8 encoding,
+ * because other encodings don't support all the characters used.
+ */
+SELECT getdatabaseencoding() <> 'UTF8'
+ AS skip_test \gset
+\if :skip_test
+\quit
+\endif
+set client_encoding = utf8;
+set standard_conforming_strings = on;
+-- Run the Tcl test cases that require Unicode
+-- expectMatch 9.44 EMP* {a[\u00fe-\u0507][\u00ff-\u0300]b} \
+-- "a\u0102\u02ffb" "a\u0102\u02ffb"
+select * from test_regex('a[\u00fe-\u0507][\u00ff-\u0300]b', E'a\u0102\u02ffb', 'EMP*');
+ test_regex
+----------------------------------------
+ {0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT}
+ {aĂ˿b}
+(2 rows)
+
+-- expectMatch 13.27 P "a\\U00001234x" "a\u1234x" "a\u1234x"
+select * from test_regex('a\U00001234x', E'a\u1234x', 'P');
+ test_regex
+-------------------
+ {0,REG_UNONPOSIX}
+ {aሴx}
+(2 rows)
+
+-- expectMatch 13.28 P {a\U00001234x} "a\u1234x" "a\u1234x"
+select * from test_regex('a\U00001234x', E'a\u1234x', 'P');
+ test_regex
+-------------------
+ {0,REG_UNONPOSIX}
+ {aሴx}
+(2 rows)
+
+-- expectMatch 13.29 P "a\\U0001234x" "a\u1234x" "a\u1234x"
+-- Tcl has relaxed their code to allow 1-8 hex digits, but Postgres hasn't
+select * from test_regex('a\U0001234x', E'a\u1234x', 'P');
+ERROR: invalid regular expression: invalid escape \ sequence
+-- expectMatch 13.30 P {a\U0001234x} "a\u1234x" "a\u1234x"
+-- Tcl has relaxed their code to allow 1-8 hex digits, but Postgres hasn't
+select * from test_regex('a\U0001234x', E'a\u1234x', 'P');
+ERROR: invalid regular expression: invalid escape \ sequence
+-- expectMatch 13.31 P "a\\U000012345x" "a\u12345x" "a\u12345x"
+select * from test_regex('a\U000012345x', E'a\u12345x', 'P');
+ test_regex
+-------------------
+ {0,REG_UNONPOSIX}
+ {aሴ5x}
+(2 rows)
+
+-- expectMatch 13.32 P {a\U000012345x} "a\u12345x" "a\u12345x"
+select * from test_regex('a\U000012345x', E'a\u12345x', 'P');
+ test_regex
+-------------------
+ {0,REG_UNONPOSIX}
+ {aሴ5x}
+(2 rows)
+
+-- expectMatch 13.33 P "a\\U1000000x" "a\ufffd0x" "a\ufffd0x"
+-- Tcl allows this as a standalone character, but Postgres doesn't
+select * from test_regex('a\U1000000x', E'a\ufffd0x', 'P');
+ERROR: invalid regular expression: invalid escape \ sequence
+-- expectMatch 13.34 P {a\U1000000x} "a\ufffd0x" "a\ufffd0x"
+-- Tcl allows this as a standalone character, but Postgres doesn't
+select * from test_regex('a\U1000000x', E'a\ufffd0x', 'P');
+ERROR: invalid regular expression: invalid escape \ sequence
+-- Additional tests, not derived from Tcl
+-- Exercise logic around high character ranges a bit more
+select * from test_regex('a
+ [\u1000-\u1100]*
+ [\u3000-\u3100]*
+ [\u1234-\u25ff]+
+ [\u2000-\u35ff]*
+ [\u2600-\u2f00]*
+ \u1236\u1236x',
+ E'a\u1234\u1236\u1236x', 'xEMP');
+ test_regex
+----------------------------------------
+ {0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT}
+ {aሴሶሶx}
+(2 rows)
+
+select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
+ E'\u1500\u1237', 'ELMP');
+ test_regex
+----------------------------------------------------
+ {0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT,REG_ULOCALE}
+ {ᔀሷ}
+(2 rows)
+
+select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
+ E'A\u1239', 'ELMP');
+ test_regex
+----------------------------------------------------
+ {0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT,REG_ULOCALE}
+(1 row)
+
+select * from test_regex('[[:alnum:]]*[[:upper:]]*[\u1000-\u2000]*\u1237',
+ E'\u1500\u1237', 'iELMP');
+ test_regex
+----------------------------------------------------
+ {0,REG_UBBS,REG_UNONPOSIX,REG_UUNPORT,REG_ULOCALE}
+ {ᔀሷ}
+(2 rows)
+
+-- systematically test char classes
+select * from test_regex('[[:alnum:]]+', E'x*\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {x}
+(2 rows)
+
+select * from test_regex('[[:alpha:]]+', E'x*\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {x}
+(2 rows)
+
+select * from test_regex('[[:ascii:]]+', E'x\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {x}
+(2 rows)
+
+select * from test_regex('[[:blank:]]+', E'x \t\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {" "}
+(2 rows)
+
+select * from test_regex('[[:cntrl:]]+', E'x\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+(1 row)
+
+select * from test_regex('[[:digit:]]+', E'x9\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {9}
+(2 rows)
+
+select * from test_regex('[[:graph:]]+', E'x\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {x}
+(2 rows)
+
+select * from test_regex('[[:lower:]]+', E'x\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {x}
+(2 rows)
+
+select * from test_regex('[[:print:]]+', E'x\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {x}
+(2 rows)
+
+select * from test_regex('[[:punct:]]+', E'x.\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {.}
+(2 rows)
+
+select * from test_regex('[[:space:]]+', E'x \t\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {" "}
+(2 rows)
+
+select * from test_regex('[[:upper:]]+', E'xX\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {X}
+(2 rows)
+
+select * from test_regex('[[:xdigit:]]+', E'xa9\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {a9}
+(2 rows)
+
+select * from test_regex('[[:word:]]+', E'x_*\u1500\u1237', 'L');
+ test_regex
+-----------------
+ {0,REG_ULOCALE}
+ {x_}
+(2 rows)
+
[parent: ea3227bf2162]