rdelaage
/
postgresql
mirror of https://git.postgresql.org/git/postgresql.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix regexp_matches() handling of zero-length matches. 

We'd find the same match twice if it was of zero length and not immediately
adjacent to the previous match.  replace_text_regexp() got similar cases
right, so adjust this search logic to match that.  Note that even though
the regexp_split_to_xxx() functions share this code, they did not display
equivalent misbehavior, because the second match would be considered
degenerate and ignored.

Jeevan Chalke, with some cosmetic changes by me.
This commit is contained in:
Tom Lane 2013-07-31 11:31:22 -04:00
parent c876fb4241
commit d074b4e50d
4 changed files with 75 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/backend/utils/adt/regexp.c
View File

@ -957,14 +957,13 @@ setup_regexp_matches(text *orig_str, text *pattern, text *flags,
break;
/*
* Advance search position. Normally we start just after the end of
* the previous match, but always advance at least one character (the
* special case can occur if the pattern matches zero characters just
* after the prior match or at the end of the string).
* Advance search position. Normally we start the next search at the
* end of the previous match; but if the match was of zero length, we
* have to advance by one character, or we'd just find the same match
* again.
*/
if (start_search < pmatch[0].rm_eo)
start_search = pmatch[0].rm_eo;
else
start_search = prev_match_end;
if (pmatch[0].rm_so == pmatch[0].rm_eo)
start_search++;
if (start_search > wide_len)
break;

5
src/backend/utils/adt/varlena.c
View File

@ -3083,7 +3083,10 @@ replace_text_regexp(text *src_text, void *regexp,
break;
/*
* Search from next character when the matching text is zero width.
* Advance search position. Normally we start the next search at the
* end of the previous match; but if the match was of zero length, we
* have to advance by one character, or we'd just find the same match
* again.
*/
search_start = data_pos;
if (pmatch[0].rm_so == pmatch[0].rm_eo)

58
src/test/regress/expected/strings.out
View File

@ -440,6 +440,64 @@ SELECT regexp_matches('foobarbequebaz', $re$barbeque$re$);
{barbeque}
(1 row)
-- start/end-of-line matches are of zero length
SELECT regexp_matches('foo' || chr(10) || 'bar' || chr(10) || 'bequq' || chr(10) || 'baz', '^', 'mg');
regexp_matches
----------------
{""}
{""}
{""}
{""}
(4 rows)
SELECT regexp_matches('foo' || chr(10) || 'bar' || chr(10) || 'bequq' || chr(10) || 'baz', '$', 'mg');
regexp_matches
----------------
{""}
{""}
{""}
{""}
(4 rows)
SELECT regexp_matches('1' || chr(10) || '2' || chr(10) || '3' || chr(10) || '4' || chr(10), '^.?', 'mg');
regexp_matches
----------------
{1}
{2}
{3}
{4}
{""}
(5 rows)
SELECT regexp_matches(chr(10) || '1' || chr(10) || '2' || chr(10) || '3' || chr(10) || '4' || chr(10), '.?$', 'mg');
regexp_matches
----------------
{""}
{1}
{""}
{2}
{""}
{3}
{""}
{4}
{""}
{""}
(10 rows)
SELECT regexp_matches(chr(10) || '1' || chr(10) || '2' || chr(10) || '3' || chr(10) || '4', '.?$', 'mg');
regexp_matches
----------------
{""}
{1}
{""}
{2}
{""}
{3}
{""}
{4}
{""}
(9 rows)
-- give me errors
SELECT regexp_matches('foobarbequebaz', $re$(bar)(beque)$re$, 'gz');
ERROR: invalid regexp option: "z"

7
src/test/regress/sql/strings.sql
View File

@ -158,6 +158,13 @@ SELECT regexp_matches('foobarbequebaz', $re$(bar)(.+)?(beque)$re$);
-- no capture groups
SELECT regexp_matches('foobarbequebaz', $re$barbeque$re$);
-- start/end-of-line matches are of zero length
SELECT regexp_matches('foo' || chr(10) || 'bar' || chr(10) || 'bequq' || chr(10) || 'baz', '^', 'mg');
SELECT regexp_matches('foo' || chr(10) || 'bar' || chr(10) || 'bequq' || chr(10) || 'baz', '$', 'mg');
SELECT regexp_matches('1' || chr(10) || '2' || chr(10) || '3' || chr(10) || '4' || chr(10), '^.?', 'mg');
SELECT regexp_matches(chr(10) || '1' || chr(10) || '2' || chr(10) || '3' || chr(10) || '4' || chr(10), '.?$', 'mg');
SELECT regexp_matches(chr(10) || '1' || chr(10) || '2' || chr(10) || '3' || chr(10) || '4', '.?$', 'mg');
-- give me errors
SELECT regexp_matches('foobarbequebaz', $re$(bar)(beque)$re$, 'gz');
SELECT regexp_matches('foobarbequebaz', $re$(barbeque$re$);