From 4f51429dd7f194e36af32b557ecdce555b5ab51b Mon Sep 17 00:00:00 2001
From: Thomas Munro <tmunro@postgresql.org>
Date: Sat, 8 Apr 2023 21:54:45 +1200
Subject: [PATCH] Update tsearch regex memory management.

Now that our regex engine uses palloc(), it's not necessary to set up a
special memory context callback to free compiled regexes.  The regex has
no resources other than the memory that is already going to be freed in
bulk.

Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Discussion: https://postgr.es/m/CA%2BhUKGK3PGKwcKqzoosamn36YW-fsuTdOPPF1i_rtEO%3DnEYKSg%40mail.gmail.com
---
 src/backend/tsearch/spell.c       | 34 +++++++------------------------
 src/include/tsearch/dicts/spell.h | 18 ++++++----------
 2 files changed, 13 insertions(+), 39 deletions(-)

diff --git a/src/backend/tsearch/spell.c b/src/backend/tsearch/spell.c
index 8d48cad251..fe4fd3a929 100644
--- a/src/backend/tsearch/spell.c
+++ b/src/backend/tsearch/spell.c
@@ -655,17 +655,6 @@ FindWord(IspellDict *Conf, const char *word, const char *affixflag, int flag)
 	return 0;
 }
 
-/*
- * Context reset/delete callback for a regular expression used in an affix
- */
-static void
-regex_affix_deletion_callback(void *arg)
-{
-	aff_regex_struct *pregex = (aff_regex_struct *) arg;
-
-	pg_regfree(&(pregex->regex));
-}
-
 /*
  * Adds a new affix rule to the Affix field.
  *
@@ -728,7 +717,6 @@ NIAddAffix(IspellDict *Conf, const char *flag, char flagflags, const char *mask,
 		int			err;
 		pg_wchar   *wmask;
 		char	   *tmask;
-		aff_regex_struct *pregex;
 
 		Affix->issimple = 0;
 		Affix->isregis = 0;
@@ -743,31 +731,23 @@ NIAddAffix(IspellDict *Conf, const char *flag, char flagflags, const char *mask,
 		wmasklen = pg_mb2wchar_with_len(tmask, wmask, masklen);
 
 		/*
-		 * The regex engine stores its stuff using malloc not palloc, so we
-		 * must arrange to explicitly clean up the regex when the dictionary's
-		 * context is cleared.  That means the regex_t has to stay in a fixed
-		 * location within the context; we can't keep it directly in the AFFIX
-		 * struct, since we may sort and resize the array of AFFIXes.
+		 * The regex and all internal state created by pg_regcomp are
+		 * allocated in the dictionary's memory context, and will be freed
+		 * automatically when it is destroyed.
 		 */
-		Affix->reg.pregex = pregex = palloc(sizeof(aff_regex_struct));
-
-		err = pg_regcomp(&(pregex->regex), wmask, wmasklen,
+		Affix->reg.pregex = palloc(sizeof(regex_t));
+		err = pg_regcomp(Affix->reg.pregex, wmask, wmasklen,
 						 REG_ADVANCED | REG_NOSUB,
 						 DEFAULT_COLLATION_OID);
 		if (err)
 		{
 			char		errstr[100];
 
-			pg_regerror(err, &(pregex->regex), errstr, sizeof(errstr));
+			pg_regerror(err, Affix->reg.pregex, errstr, sizeof(errstr));
 			ereport(ERROR,
 					(errcode(ERRCODE_INVALID_REGULAR_EXPRESSION),
 					 errmsg("invalid regular expression: %s", errstr)));
 		}
-
-		pregex->mcallback.func = regex_affix_deletion_callback;
-		pregex->mcallback.arg = (void *) pregex;
-		MemoryContextRegisterResetCallback(CurrentMemoryContext,
-										   &pregex->mcallback);
 	}
 
 	Affix->flagflags = flagflags;
@@ -2161,7 +2141,7 @@ CheckAffix(const char *word, size_t len, AFFIX *Affix, int flagflags, char *neww
 		data = (pg_wchar *) palloc((newword_len + 1) * sizeof(pg_wchar));
 		data_len = pg_mb2wchar_with_len(newword, data, newword_len);
 
-		if (pg_regexec(&(Affix->reg.pregex->regex), data, data_len,
+		if (pg_regexec(Affix->reg.pregex, data, data_len,
 					   0, NULL, 0, NULL, 0) == REG_OKAY)
 		{
 			pfree(data);
diff --git a/src/include/tsearch/dicts/spell.h b/src/include/tsearch/dicts/spell.h
index 5c30af6ac6..0763f9ffe7 100644
--- a/src/include/tsearch/dicts/spell.h
+++ b/src/include/tsearch/dicts/spell.h
@@ -81,17 +81,6 @@ typedef struct spell_struct
 
 #define SPELLHDRSZ	(offsetof(SPELL, word))
 
-/*
- * If an affix uses a regex, we have to store that separately in a struct
- * that won't move around when arrays of affixes are enlarged or sorted.
- * This is so that it can be found to be cleaned up at context destruction.
- */
-typedef struct aff_regex_struct
-{
-	regex_t		regex;
-	MemoryContextCallback mcallback;
-} aff_regex_struct;
-
 /*
  * Represents an entry in an affix list.
  */
@@ -108,7 +97,12 @@ typedef struct aff_struct
 	char	   *repl;
 	union
 	{
-		aff_regex_struct *pregex;
+		/*
+		 * Arrays of AFFIX are moved and sorted.  We'll use a pointer to
+		 * regex_t to keep this struct small, and avoid assuming that regex_t
+		 * is movable.
+		 */
+		regex_t    *pregex;
 		Regis		regis;
 	}			reg;
 } AFFIX;