Cope with more than 64K phrases in a thesaurus dictionary.

tglsfdc · tglsfdc · commit 07668808414a · 2014-11-06T20:53:02.000-05:00
dict_thesaurus stored phrase IDs in uint16 fields, so it would get confused
and even crash if there were more than 64K entries in the configuration
file.  It turns out to be basically free to widen the phrase IDs to uint32,
so let's just do so.

This was complained of some time ago by David Boutin (in bug #7793);
he later submitted an informal patch but it was never acted on.
We now have another complaint (bug #11901 from Luc Ouellette) so it's
time to make something happen.

This is basically Boutin's patch, but for future-proofing I also added a
defense against too many words per phrase.  Note that we don't need any
explicit defense against overflow of the uint32 counters, since before that
happens we'd hit array allocation sizes that repalloc rejects.

Back-patch to all supported branches because of the crash risk.
diff --git a/src/backend/tsearch/dict_thesaurus.c b/src/backend/tsearch/dict_thesaurus.c
@@ -29,7 +29,7 @@
 
 typedef struct LexemeInfo
 {
-	uint16		idsubst;		/* entry's number in DictThesaurus->subst */
+	uint32		idsubst;		/* entry's number in DictThesaurus->subst */
 	uint16		posinsubst;		/* pos info in entry */
 	uint16		tnvariant;		/* total num lexemes in one variant */
 	struct LexemeInfo *nextentry;
@@ -69,7 +69,7 @@ typedef struct
 
 
 static void
-newLexeme(DictThesaurus *d, char *b, char *e, uint16 idsubst, uint16 posinsubst)
+newLexeme(DictThesaurus *d, char *b, char *e, uint32 idsubst, uint16 posinsubst)
 {
 	TheLexeme  *ptr;
 
@@ -103,7 +103,7 @@ newLexeme(DictThesaurus *d, char *b, char *e, uint16 idsubst, uint16 posinsubst)
 }
 
 static void
-addWrd(DictThesaurus *d, char *b, char *e, uint16 idsubst, uint16 nwrd, uint16 posinsubst, bool useasis)
+addWrd(DictThesaurus *d, char *b, char *e, uint32 idsubst, uint16 nwrd, uint16 posinsubst, bool useasis)
 {
 	static int	nres = 0;
 	static int	ntres = 0;
@@ -144,7 +144,6 @@ addWrd(DictThesaurus *d, char *b, char *e, uint16 idsubst, uint16 nwrd, uint16 p
 			ntres *= 2;
 			ptr->res = (TSLexeme *) repalloc(ptr->res, sizeof(TSLexeme) * ntres);
 		}
-
 	}
 
 	ptr->res[nres].lexeme = palloc(e - b + 1);
@@ -169,7 +168,7 @@ static void
 thesaurusRead(char *filename, DictThesaurus *d)
 {
 	tsearch_readline_state trst;
-	uint16		idsubst = 0;
+	uint32		idsubst = 0;
 	bool		useasis = false;
 	char	   *line;
 
@@ -185,8 +184,8 @@ thesaurusRead(char *filename, DictThesaurus *d)
 		char	   *ptr;
 		int			state = TR_WAITLEX;
 		char	   *beginwrd = NULL;
-		uint16		posinsubst = 0;
-		uint16		nwrd = 0;
+		uint32		posinsubst = 0;
+		uint32		nwrd = 0;
 
 		ptr = line;
 
@@ -287,6 +286,16 @@ thesaurusRead(char *filename, DictThesaurus *d)
 					(errcode(ERRCODE_CONFIG_FILE_ERROR),
 					 errmsg("unexpected end of line")));
 
+		/*
+		 * Note: currently, tsearch_readline can't return lines exceeding 4KB,
+		 * so overflow of the word counts is impossible.  But that may not
+		 * always be true, so let's check.
+		 */
+		if (nwrd != (uint16) nwrd || posinsubst != (uint16) posinsubst)
+			ereport(ERROR,
+					(errcode(ERRCODE_CONFIG_FILE_ERROR),
+					 errmsg("too many lexemes in thesaurus entry")));
+
 		pfree(line);
 	}
 
@@ -671,7 +680,7 @@ findTheLexeme(DictThesaurus *d, char *lexeme)
 }
 
 static bool
-matchIdSubst(LexemeInfo *stored, uint16 idsubst)
+matchIdSubst(LexemeInfo *stored, uint32 idsubst)
 {
 	bool		res = true;
 
