Add assorted new regexp_xxx SQL functions.

This patch adds new functions regexp_count(), regexp_instr(),
regexp_like(), and regexp_substr(), and extends regexp_replace()
with some new optional arguments.  All these functions follow
the definitions used in Oracle, although there are small differences
in the regexp language due to using our own regexp engine -- most
notably, that the default newline-matching behavior is different.
Similar functions appear in DB2 and elsewhere, too.  Aside from
easing portability, these functions are easier to use for certain
tasks than our existing regexp_match[es] functions.

Gilles Darold, heavily revised by me

Discussion: https://postgr.es/m/fc160ee0-c843-b024-29bb-97b5da61971f@darold.net

Author: tglsfdc

doc/src/sgml/func.sgml

@@ -4496,23 +4496,28 @@ appendStringInfoRegexpSubstr(StringInfo str, text *replace_text,
 /*
  * replace_text_regexp
  *
- * replace text that matches to regexp in src_text to replace_text.
+ * replace substring(s) in src_text that match regexp with replace_text.
+ *
+ * search_start: the character (not byte) offset in src_text at which to
+ * begin searching.
+ * n: if 0, replace all matches; if > 0, replace only the N'th match.
  *
  * Note: to avoid having to include regex.h in builtins.h, we declare
  * the regexp argument as void *, but really it's regex_t *.
  */
 text *
 replace_text_regexp(text *src_text, void *regexp,
-					text *replace_text, bool glob)
+					text *replace_text,
+					int search_start, int n)
 {
 	text	   *ret_text;
 	regex_t    *re = (regex_t *) regexp;
 	int			src_text_len = VARSIZE_ANY_EXHDR(src_text);
+	int			nmatches = 0;
 	StringInfoData buf;
 	regmatch_t	pmatch[REGEXP_REPLACE_BACKREF_CNT];
 	pg_wchar   *data;
 	size_t		data_len;
-	int			search_start;
 	int			data_pos;
 	char	   *start_ptr;
 	bool		have_escape;
@@ -4530,7 +4535,6 @@ replace_text_regexp(text *src_text, void *regexp,
 	start_ptr = (char *) VARDATA_ANY(src_text);
 	data_pos = 0;
 
-	search_start = 0;
 	while (search_start <= data_len)
 	{
 		int			regexec_result;
@@ -4560,6 +4564,23 @@ replace_text_regexp(text *src_text, void *regexp,
 					 errmsg("regular expression failed: %s", errMsg)));
 		}
 
+		/*
+		 * Count matches, and decide whether to replace this match.
+		 */
+		nmatches++;
+		if (n > 0 && nmatches != n)
+		{
+			/*
+			 * No, so advance search_start, but not start_ptr/data_pos. (Thus,
+			 * we treat the matched text as if it weren't matched, and copy it
+			 * to the output later.)
+			 */
+			search_start = pmatch[0].rm_eo;
+			if (pmatch[0].rm_so == pmatch[0].rm_eo)
+				search_start++;
+			continue;
+		}
+
 		/*
 		 * Copy the text to the left of the match position.  Note we are given
 		 * character not byte indexes.
@@ -4596,9 +4617,9 @@ replace_text_regexp(text *src_text, void *regexp,
 		data_pos = pmatch[0].rm_eo;
 
 		/*
-		 * When global option is off, replace the first instance only.
+		 * If we only want to replace one occurrence, we're done.
 		 */
-		if (!glob)
+		if (n > 0)
 			break;
 
 		/*

src/backend/utils/adt/regexp.c

@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	202107261
+#define CATALOG_VERSION_NO	202108031
 
 #endif

src/backend/utils/adt/varlena.c

@@ -3565,6 +3565,18 @@
 { oid => '2285', descr => 'replace text using regexp',
   proname => 'regexp_replace', prorettype => 'text',
   proargtypes => 'text text text text', prosrc => 'textregexreplace' },
+{ oid => '9611', descr => 'replace text using regexp',
+  proname => 'regexp_replace', prorettype => 'text',
+  proargtypes => 'text text text int4 int4 text',
+  prosrc => 'textregexreplace_extended' },
+{ oid => '9612', descr => 'replace text using regexp',
+  proname => 'regexp_replace', prorettype => 'text',
+  proargtypes => 'text text text int4 int4',
+  prosrc => 'textregexreplace_extended_no_flags' },
+{ oid => '9613', descr => 'replace text using regexp',
+  proname => 'regexp_replace', prorettype => 'text',
+  proargtypes => 'text text text int4',
+  prosrc => 'textregexreplace_extended_no_n' },
 { oid => '3396', descr => 'find first match for regexp',
   proname => 'regexp_match', prorettype => '_text', proargtypes => 'text text',
   prosrc => 'regexp_match_no_flags' },
@@ -3579,6 +3591,58 @@
   proname => 'regexp_matches', prorows => '10', proretset => 't',
   prorettype => '_text', proargtypes => 'text text text',
   prosrc => 'regexp_matches' },
+{ oid => '9614', descr => 'count regexp matches',
+  proname => 'regexp_count', prorettype => 'int4', proargtypes => 'text text',
+  prosrc => 'regexp_count_no_start' },
+{ oid => '9615', descr => 'count regexp matches',
+  proname => 'regexp_count', prorettype => 'int4',
+  proargtypes => 'text text int4', prosrc => 'regexp_count_no_flags' },
+{ oid => '9616', descr => 'count regexp matches',
+  proname => 'regexp_count', prorettype => 'int4',
+  proargtypes => 'text text int4 text', prosrc => 'regexp_count' },
+{ oid => '9617', descr => 'position of regexp match',
+  proname => 'regexp_instr', prorettype => 'int4', proargtypes => 'text text',
+  prosrc => 'regexp_instr_no_start' },
+{ oid => '9618', descr => 'position of regexp match',
+  proname => 'regexp_instr', prorettype => 'int4',
+  proargtypes => 'text text int4', prosrc => 'regexp_instr_no_n' },
+{ oid => '9619', descr => 'position of regexp match',
+  proname => 'regexp_instr', prorettype => 'int4',
+  proargtypes => 'text text int4 int4', prosrc => 'regexp_instr_no_endoption' },
+{ oid => '9620', descr => 'position of regexp match',
+  proname => 'regexp_instr', prorettype => 'int4',
+  proargtypes => 'text text int4 int4 int4',
+  prosrc => 'regexp_instr_no_flags' },
+{ oid => '9621', descr => 'position of regexp match',
+  proname => 'regexp_instr', prorettype => 'int4',
+  proargtypes => 'text text int4 int4 int4 text',
+  prosrc => 'regexp_instr_no_subexpr' },
+{ oid => '9622', descr => 'position of regexp match',
+  proname => 'regexp_instr', prorettype => 'int4',
+  proargtypes => 'text text int4 int4 int4 text int4',
+  prosrc => 'regexp_instr' },
+{ oid => '9623', descr => 'test for regexp match',
+  proname => 'regexp_like', prorettype => 'bool', proargtypes => 'text text',
+  prosrc => 'regexp_like_no_flags' },
+{ oid => '9624', descr => 'test for regexp match',
+  proname => 'regexp_like', prorettype => 'bool',
+  proargtypes => 'text text text', prosrc => 'regexp_like' },
+{ oid => '9625', descr => 'extract substring that matches regexp',
+  proname => 'regexp_substr', prorettype => 'text', proargtypes => 'text text',
+  prosrc => 'regexp_substr_no_start' },
+{ oid => '9626', descr => 'extract substring that matches regexp',
+  proname => 'regexp_substr', prorettype => 'text',
+  proargtypes => 'text text int4', prosrc => 'regexp_substr_no_n' },
+{ oid => '9627', descr => 'extract substring that matches regexp',
+  proname => 'regexp_substr', prorettype => 'text',
+  proargtypes => 'text text int4 int4', prosrc => 'regexp_substr_no_flags' },
+{ oid => '9628', descr => 'extract substring that matches regexp',
+  proname => 'regexp_substr', prorettype => 'text',
+  proargtypes => 'text text int4 int4 text',
+  prosrc => 'regexp_substr_no_subexpr' },
+{ oid => '9629', descr => 'extract substring that matches regexp',
+  proname => 'regexp_substr', prorettype => 'text',
+  proargtypes => 'text text int4 int4 text int4', prosrc => 'regexp_substr' },
 { oid => '2088', descr => 'split string by field_sep and return field_num',
   proname => 'split_part', prorettype => 'text',
   proargtypes => 'text text int4', prosrc => 'split_part' },

src/include/catalog/catversion.h

@@ -34,6 +34,7 @@ extern bool SplitDirectoriesString(char *rawstring, char separator,
 extern bool SplitGUCList(char *rawstring, char separator,
 						 List **namelist);
 extern text *replace_text_regexp(text *src_text, void *regexp,
-								 text *replace_text, bool glob);
+								 text *replace_text,
+								 int search_start, int n);
 
 #endif