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.

2 files changed, 65 insertions, 0 deletions

diff --git a/src/test/regress/expected/strings.out b/src/test/regress/expected/strings.out
index 281c69528aa..19708c32fdd 100644
--- a/src/test/regress/expected/strings.out
+++ b/src/test/regress/expected/strings.out
@@ -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"
diff --git a/src/test/regress/sql/strings.sql b/src/test/regress/sql/strings.sql
index e7841aa20d7..f9cfaeb44ac 100644
--- a/src/test/regress/sql/strings.sql
+++ b/src/test/regress/sql/strings.sql
@@ -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$re$);