diff options
Diffstat (limited to 'src/test/regress/sql/regex.sql')
| -rw-r--r-- | src/test/regress/sql/regex.sql | 158 |
1 files changed, 158 insertions, 0 deletions
diff --git a/src/test/regress/sql/regex.sql b/src/test/regress/sql/regex.sql new file mode 100644 index 0000000..5621710 --- /dev/null +++ b/src/test/regress/sql/regex.sql @@ -0,0 +1,158 @@ +-- +-- Regular expression tests +-- + +-- Don't want to have to double backslashes in regexes +set standard_conforming_strings = on; + +-- Test simple quantified backrefs +select 'bbbbb' ~ '^([bc])\1*$' as t; +select 'ccc' ~ '^([bc])\1*$' as t; +select 'xxx' ~ '^([bc])\1*$' as f; +select 'bbc' ~ '^([bc])\1*$' as f; +select 'b' ~ '^([bc])\1*$' as t; + +-- Test quantified backref within a larger expression +select 'abc abc abc' ~ '^(\w+)( \1)+$' as t; +select 'abc abd abc' ~ '^(\w+)( \1)+$' as f; +select 'abc abc abd' ~ '^(\w+)( \1)+$' as f; +select 'abc abc abc' ~ '^(.+)( \1)+$' as t; +select 'abc abd abc' ~ '^(.+)( \1)+$' as f; +select 'abc abc abd' ~ '^(.+)( \1)+$' as f; + +-- Test some cases that crashed in 9.2beta1 due to pmatch[] array overrun +select substring('asd TO foo' from ' TO (([a-z0-9._]+|"([^"]+|"")+")+)'); +select substring('a' from '((a))+'); +select substring('a' from '((a)+)'); + +-- Test regexp_match() +select regexp_match('abc', ''); +select regexp_match('abc', 'bc'); +select regexp_match('abc', 'd') is null; +select regexp_match('abc', '(B)(c)', 'i'); +select regexp_match('abc', 'Bd', 'ig'); -- error + +-- Test lookahead constraints +select regexp_matches('ab', 'a(?=b)b*'); +select regexp_matches('a', 'a(?=b)b*'); +select regexp_matches('abc', 'a(?=b)b*(?=c)c*'); +select regexp_matches('ab', 'a(?=b)b*(?=c)c*'); +select regexp_matches('ab', 'a(?!b)b*'); +select regexp_matches('a', 'a(?!b)b*'); +select regexp_matches('b', '(?=b)b'); +select regexp_matches('a', '(?=b)b'); + +-- Test lookbehind constraints +select regexp_matches('abb', '(?<=a)b*'); +select regexp_matches('a', 'a(?<=a)b*'); +select regexp_matches('abc', 'a(?<=a)b*(?<=b)c*'); +select regexp_matches('ab', 'a(?<=a)b*(?<=b)c*'); +select regexp_matches('ab', 'a*(?<!a)b*'); +select regexp_matches('ab', 'a*(?<!a)b+'); +select regexp_matches('b', 'a*(?<!a)b+'); +select regexp_matches('a', 'a(?<!a)b*'); +select regexp_matches('b', '(?<=b)b'); +select regexp_matches('foobar', '(?<=f)b+'); +select regexp_matches('foobar', '(?<=foo)b+'); +select regexp_matches('foobar', '(?<=oo)b+'); + +-- Test optimization of single-chr-or-bracket-expression lookaround constraints +select 'xz' ~ 'x(?=[xy])'; +select 'xy' ~ 'x(?=[xy])'; +select 'xz' ~ 'x(?![xy])'; +select 'xy' ~ 'x(?![xy])'; +select 'x' ~ 'x(?![xy])'; +select 'xyy' ~ '(?<=[xy])yy+'; +select 'zyy' ~ '(?<=[xy])yy+'; +select 'xyy' ~ '(?<![xy])yy+'; +select 'zyy' ~ '(?<![xy])yy+'; + +-- Test conversion of regex patterns to indexable conditions +explain (costs off) select * from pg_proc where proname ~ 'abc'; +explain (costs off) select * from pg_proc where proname ~ '^abc'; +explain (costs off) select * from pg_proc where proname ~ '^abc$'; +explain (costs off) select * from pg_proc where proname ~ '^abcd*e'; +explain (costs off) select * from pg_proc where proname ~ '^abc+d'; +explain (costs off) select * from pg_proc where proname ~ '^(abc)(def)'; +explain (costs off) select * from pg_proc where proname ~ '^(abc)$'; +explain (costs off) select * from pg_proc where proname ~ '^(abc)?d'; +explain (costs off) select * from pg_proc where proname ~ '^abcd(x|(?=\w\w)q)'; + +-- Test for infinite loop in pullback() (CVE-2007-4772) +select 'a' ~ '($|^)*'; + +-- These cases expose a bug in the original fix for CVE-2007-4772 +select 'a' ~ '(^)+^'; +select 'a' ~ '$($$)+'; + +-- More cases of infinite loop in pullback(), not fixed by CVE-2007-4772 fix +select 'a' ~ '($^)+'; +select 'a' ~ '(^$)*'; +select 'aa bb cc' ~ '(^(?!aa))+'; +select 'aa x' ~ '(^(?!aa)(?!bb)(?!cc))+'; +select 'bb x' ~ '(^(?!aa)(?!bb)(?!cc))+'; +select 'cc x' ~ '(^(?!aa)(?!bb)(?!cc))+'; +select 'dd x' ~ '(^(?!aa)(?!bb)(?!cc))+'; + +-- Test for infinite loop in fixempties() (Tcl bugs 3604074, 3606683) +select 'a' ~ '((((((a)*)*)*)*)*)*'; +select 'a' ~ '((((((a+|)+|)+|)+|)+|)+|)'; + +-- These cases used to give too-many-states failures +select 'x' ~ 'abcd(\m)+xyz'; +select 'a' ~ '^abcd*(((((^(a c(e?d)a+|)+|)+|)+|)+|a)+|)'; +select 'x' ~ 'a^(^)bcd*xy(((((($a+|)+|)+|)+$|)+|)+|)^$'; +select 'x' ~ 'xyz(\Y\Y)+'; +select 'x' ~ 'x|(?:\M)+'; + +-- This generates O(N) states but O(N^2) arcs, so it causes problems +-- if arc count is not constrained +select 'x' ~ repeat('x*y*z*', 1000); + +-- Test backref in combination with non-greedy quantifier +-- https://core.tcl.tk/tcl/tktview/6585b21ca8fa6f3678d442b97241fdd43dba2ec0 +select 'Programmer' ~ '(\w).*?\1' as t; +select regexp_matches('Programmer', '(\w)(.*?\1)', 'g'); + +-- Test for proper matching of non-greedy iteration (bug #11478) +select regexp_matches('foo/bar/baz', + '^([^/]+?)(?:/([^/]+?))(?:/([^/]+?))?$', ''); + +-- Test that greediness can be overridden by outer quantifier +select regexp_matches('llmmmfff', '^(l*)(.*)(f*)$'); +select regexp_matches('llmmmfff', '^(l*){1,1}(.*)(f*)$'); +select regexp_matches('llmmmfff', '^(l*){1,1}?(.*)(f*)$'); +select regexp_matches('llmmmfff', '^(l*){1,1}?(.*){1,1}?(f*)$'); +select regexp_matches('llmmmfff', '^(l*?)(.*)(f*)$'); +select regexp_matches('llmmmfff', '^(l*?){1,1}(.*)(f*)$'); +select regexp_matches('llmmmfff', '^(l*?){1,1}?(.*)(f*)$'); +select regexp_matches('llmmmfff', '^(l*?){1,1}?(.*){1,1}?(f*)$'); + +-- Test for infinite loop in cfindloop with zero-length possible match +-- but no actual match (can only happen in the presence of backrefs) +select 'a' ~ '$()|^\1'; +select 'a' ~ '.. ()|\1'; +select 'a' ~ '()*\1'; +select 'a' ~ '()+\1'; + +-- Test incorrect removal of capture groups within {0} +select 'xxx' ~ '(.){0}(\1)' as f; +select 'xxx' ~ '((.)){0}(\2)' as f; +select 'xyz' ~ '((.)){0}(\2){0}' as t; + +-- Test ancient oversight in when to apply zaptreesubs +select 'abcdef' ~ '^(.)\1|\1.' as f; +select 'abadef' ~ '^((.)\2|..)\2' as f; + +-- Add coverage for some cases in checkmatchall +select regexp_match('xy', '.|...'); +select regexp_match('xyz', '.|...'); +select regexp_match('xy', '.*'); +select regexp_match('fooba', '(?:..)*'); +select regexp_match('xyz', repeat('.', 260)); +select regexp_match('foo', '(?:.|){99}'); + +-- Error conditions +select 'xyz' ~ 'x(\w)(?=\1)'; -- no backrefs in LACONs +select 'xyz' ~ 'x(\w)(?=(\1))'; +select 'a' ~ '\x7fffffff'; -- invalid chr code |