@ -1274,6 +1274,30 @@ CREATE COLLATION ctest_det (provider = icu, locale = '', deterministic = true);
NOTICE: using standard form "und" for ICU locale ""
CREATE COLLATION ctest_nondet (provider = icu, locale = '', deterministic = false);
NOTICE: using standard form "und" for ICU locale ""
SELECT 'abc' LIKE 'abc' COLLATE ctest_det;
?column?
----------
t
(1 row)
SELECT 'abc' LIKE 'a\bc' COLLATE ctest_det;
?column?
----------
t
(1 row)
SELECT 'abc' LIKE 'abc' COLLATE ctest_nondet;
?column?
----------
t
(1 row)
SELECT 'abc' LIKE 'a\bc' COLLATE ctest_nondet;
?column?
----------
t
(1 row)
CREATE TABLE test6 (a int, b text);
-- same string in different normal forms
INSERT INTO test6 VALUES (1, U&'\00E4bc');
@ -1298,6 +1322,19 @@ SELECT * FROM test6 WHERE b = 'äbc' COLLATE ctest_nondet;
2 | ä
(2 rows)
SELECT * FROM test6 WHERE b LIKE 'äbc' COLLATE ctest_det;
a | b
---+-----
1 | äbc
(1 row)
SELECT * FROM test6 WHERE b LIKE 'äbc' COLLATE ctest_nondet;
a | b
---+-----
1 | äbc
2 | ä
(2 rows)
-- same with arrays
CREATE TABLE test6a (a int, b text[]);
INSERT INTO test6a VALUES (1, ARRAY[U&'\00E4bc']);
@ -1514,7 +1551,12 @@ SELECT x FROM test3ci WHERE x <> 'abc';
(2 rows)
SELECT x FROM test3ci WHERE x LIKE 'a%';
ERROR: nondeterministic collations are not supported for LIKE
x
-----
abc
ABC
(2 rows)
SELECT x FROM test3ci WHERE x ILIKE 'a%';
ERROR: nondeterministic collations are not supported for ILIKE
SELECT x FROM test3ci WHERE x SIMILAR TO 'a%';
@ -1632,7 +1674,12 @@ SELECT x FROM test3bpci WHERE x <> 'abc';
(2 rows)
SELECT x FROM test3bpci WHERE x LIKE 'a%';
ERROR: nondeterministic collations are not supported for LIKE
x
-----
abc
ABC
(2 rows)
SELECT x FROM test3bpci WHERE x ILIKE 'a%';
ERROR: nondeterministic collations are not supported for ILIKE
SELECT x FROM test3bpci WHERE x SIMILAR TO 'a%';
@ -1729,7 +1776,7 @@ SELECT string_to_array('ABCDEFGHI'::char(9) COLLATE case_insensitive, NULL, 'b')
-- This tests the issue described in match_pattern_prefix(). In the
-- absence of that check, the case_insensitive tests below would
-- return no rows where they should logically return one.
CREATE TABLE test4c (x text COLLATE "C" );
CREATE TABLE test4c (x text COLLATE case_insensitive );
INSERT INTO test4c VALUES ('abc');
CREATE INDEX ON test4c (x);
SET enable_seqscan = off;
@ -1743,10 +1790,18 @@ SELECT x FROM test4c WHERE x LIKE 'ABC%' COLLATE case_sensitive; -- ok, no rows
---
(0 rows)
SELECT x FROM test4c WHERE x LIKE 'ABC' COLLATE case_insensitive; -- error
ERROR: nondeterministic collations are not supported for LIKE
SELECT x FROM test4c WHERE x LIKE 'ABC%' COLLATE case_insensitive; -- error
ERROR: nondeterministic collations are not supported for LIKE
SELECT x FROM test4c WHERE x LIKE 'ABC' COLLATE case_insensitive; -- ok
x
-----
abc
(1 row)
SELECT x FROM test4c WHERE x LIKE 'ABC%' COLLATE case_insensitive; -- ok
x
-----
abc
(1 row)
RESET enable_seqscan;
-- Unicode special case: different variants of Greek lower case sigma.
-- A naive implementation like citext that just does lower(x) =
@ -1840,6 +1895,126 @@ SELECT * FROM test4 WHERE b = 'Cote' COLLATE case_insensitive;
1 | cote
(1 row)
-- This is a tricky one. A naive implementation would first test
-- \00E4 matches \0061, which is true under ignore_accents, but then
-- the rest of the string won't match anymore. Therefore, the
-- algorithm has to test whether the rest of the string matches, and
-- if not try matching \00E4 against a longer substring like
-- \0061\0308, which will then work out.
SELECT U&'\0061\0308bc' LIKE U&'\00E4_c' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- and in reverse:
SELECT U&'\00E4bc' LIKE U&'\0061\0308_c' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- inner % matches b:
SELECT U&'\0061\0308bc' LIKE U&'\00E4%c' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- inner %% matches b then zero:
SELECT U&'\0061\0308bc' LIKE U&'\00E4%%c' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- inner %% matches b then zero:
SELECT U&'cb\0061\0308' LIKE U&'c%%\00E4' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- trailing _ matches two codepoints that form one grapheme:
SELECT U&'cb\0061\0308' LIKE U&'cb_' COLLATE ignore_accents;
?column?
----------
f
(1 row)
-- trailing __ matches two codepoints that form one grapheme:
SELECT U&'cb\0061\0308' LIKE U&'cb__' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- leading % matches zero:
SELECT U&'\0061\0308bc' LIKE U&'%\00E4bc' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- leading % matches zero (with later %):
SELECT U&'\0061\0308bc' LIKE U&'%\00E4%c' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- trailing % matches zero:
SELECT U&'\0061\0308bc' LIKE U&'\00E4bc%' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- trailing % matches zero (with previous %):
SELECT U&'\0061\0308bc' LIKE U&'\00E4%c%' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- _ versus two codepoints that form one grapheme:
SELECT U&'\0061\0308bc' LIKE U&'_bc' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- (actually this matches because)
SELECT U&'\0308bc' = 'bc' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- __ matches two codepoints that form one grapheme:
SELECT U&'\0061\0308bc' LIKE U&'__bc' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- _ matches one codepoint that forms half a grapheme:
SELECT U&'\0061\0308bc' LIKE U&'_\0308bc' COLLATE ignore_accents;
?column?
----------
t
(1 row)
-- doesn't match because \00e4 doesn't match only \0308
SELECT U&'\0061\0308bc' LIKE U&'_\00e4bc' COLLATE ignore_accents;
?column?
----------
f
(1 row)
-- escape character at end of pattern
SELECT 'foox' LIKE 'foo\' COLLATE ignore_accents;
ERROR: LIKE pattern must not end with escape character
-- foreign keys (mixing different nondeterministic collations not allowed)
CREATE TABLE test10pk (x text COLLATE case_sensitive PRIMARY KEY);
CREATE TABLE test10fk (x text COLLATE case_insensitive REFERENCES test10pk (x) ON UPDATE CASCADE ON DELETE CASCADE); -- error
Peter Eisentraut
1 year ago