Validate ispell dictionaries more carefully.

Using incorrect, or just mismatched, dictionary and affix files
could result in a crash, due to failure to cross-check offsets
obtained from the file.  Add necessary validation, as well as
some Asserts for future-proofing.

Per bug #16050 from Alexander Lakhin.  Back-patch to 9.6 where the
problem was introduced.

Arthur Zakirov, per initial investigation by Tomas Vondra

Discussion: https://postgr.es/m/16050-024ae722464ab604@postgresql.org
Discussion: https://postgr.es/m/20191013012610.2p2fp3zzpoav7jzf@development

src/backend/tsearch/spell.c

@@ -458,6 +458,8 @@ IsAffixFlagInUse(IspellDict *Conf, int affix, const char *affixflag)
 	if (*affixflag == 0)
 		return true;
 
+	Assert(affix < Conf->nAffixData);
+
 	flagcur = Conf->AffixData[affix];
 
 	while (*flagcur)
@@ -1160,13 +1162,17 @@ getAffixFlagSet(IspellDict *Conf, char *s)
 					(errcode(ERRCODE_CONFIG_FILE_ERROR),
 					 errmsg("invalid affix alias \"%s\"", s)));
 
-		if (curaffix > 0 && curaffix <= Conf->nAffixData)
+		if (curaffix > 0 && curaffix < Conf->nAffixData)
 
 			/*
 			 * Do not subtract 1 from curaffix because empty string was added
 			 * in NIImportOOAffixes
 			 */
 			return Conf->AffixData[curaffix];
+		else if (curaffix > Conf->nAffixData)
+			ereport(ERROR,
+					(errcode(ERRCODE_CONFIG_FILE_ERROR),
+					 errmsg("invalid affix alias \"%s\"", s)));
 		else
 			return VoidString;
 	}
@@ -1561,6 +1567,8 @@ MergeAffix(IspellDict *Conf, int a1, int a2)
 {
 	char	  **ptr;
 
+	Assert(a1 < Conf->nAffixData && a2 < Conf->nAffixData);
+
 	/* Do not merge affix flags if one of affix flags is empty */
 	if (*Conf->AffixData[a1] == '\0')
 		return a2;
@@ -1603,9 +1611,10 @@ MergeAffix(IspellDict *Conf, int a1, int a2)
 static uint32
 makeCompoundFlags(IspellDict *Conf, int affix)
 {
-	char	   *str = Conf->AffixData[affix];
+	Assert(affix < Conf->nAffixData);
 
-	return (getCompoundAffixFlagValue(Conf, str) & FF_COMPOUNDFLAGMASK);
+	return (getCompoundAffixFlagValue(Conf, Conf->AffixData[affix]) &
+			FF_COMPOUNDFLAGMASK);
 }
 
 /*
@@ -1725,6 +1734,16 @@ NISortDictionary(IspellDict *Conf)
 							(errcode(ERRCODE_CONFIG_FILE_ERROR),
 							 errmsg("invalid affix alias \"%s\"",
 									Conf->Spell[i]->p.flag)));
+				if (curaffix < 0 || curaffix >= Conf->nAffixData)
+					ereport(ERROR,
+							(errcode(ERRCODE_CONFIG_FILE_ERROR),
+							 errmsg("invalid affix alias \"%s\"",
+									Conf->Spell[i]->p.flag)));
+				if (*end != '\0' && !t_isdigit(end) && !t_isspace(end))
+					ereport(ERROR,
+							(errcode(ERRCODE_CONFIG_FILE_ERROR),
+							 errmsg("invalid affix alias \"%s\"",
+									Conf->Spell[i]->p.flag)));
 			}
 			else
 			{

src/test/regress/expected/tsdicts.out

@@ -413,6 +413,40 @@ SELECT ts_lexize('hunspell_num', 'footballyklubber');
  {foot,ball,klubber}
 (1 row)
 
+-- Test suitability of affix and dict files
+CREATE TEXT SEARCH DICTIONARY hunspell_err (
+						Template=ispell,
+						DictFile=ispell_sample,
+						AffFile=hunspell_sample_long
+);
+ERROR:  invalid affix alias "GJUS"
+CREATE TEXT SEARCH DICTIONARY hunspell_err (
+						Template=ispell,
+						DictFile=ispell_sample,
+						AffFile=hunspell_sample_num
+);
+ERROR:  invalid affix flag "SZ\"
+CREATE TEXT SEARCH DICTIONARY hunspell_invalid_1 (
+						Template=ispell,
+						DictFile=hunspell_sample_long,
+						AffFile=ispell_sample
+);
+CREATE TEXT SEARCH DICTIONARY hunspell_invalid_2 (
+						Template=ispell,
+						DictFile=hunspell_sample_long,
+						AffFile=hunspell_sample_num
+);
+CREATE TEXT SEARCH DICTIONARY hunspell_invalid_3 (
+						Template=ispell,
+						DictFile=hunspell_sample_num,
+						AffFile=ispell_sample
+);
+CREATE TEXT SEARCH DICTIONARY hunspell_err (
+						Template=ispell,
+						DictFile=hunspell_sample_num,
+						AffFile=hunspell_sample_long
+);
+ERROR:  invalid affix alias "302,301,202,303"
 -- Synonym dictionary
 CREATE TEXT SEARCH DICTIONARY synonym (
 						Template=synonym,

src/test/regress/sql/tsdicts.sql

@@ -101,6 +101,43 @@ SELECT ts_lexize('hunspell_num', 'footballklubber');
 SELECT ts_lexize('hunspell_num', 'ballyklubber');
 SELECT ts_lexize('hunspell_num', 'footballyklubber');
 
+-- Test suitability of affix and dict files
+CREATE TEXT SEARCH DICTIONARY hunspell_err (
+						Template=ispell,
+						DictFile=ispell_sample,
+						AffFile=hunspell_sample_long
+);
+
+CREATE TEXT SEARCH DICTIONARY hunspell_err (
+						Template=ispell,
+						DictFile=ispell_sample,
+						AffFile=hunspell_sample_num
+);
+
+CREATE TEXT SEARCH DICTIONARY hunspell_invalid_1 (
+						Template=ispell,
+						DictFile=hunspell_sample_long,
+						AffFile=ispell_sample
+);
+
+CREATE TEXT SEARCH DICTIONARY hunspell_invalid_2 (
+						Template=ispell,
+						DictFile=hunspell_sample_long,
+						AffFile=hunspell_sample_num
+);
+
+CREATE TEXT SEARCH DICTIONARY hunspell_invalid_3 (
+						Template=ispell,
+						DictFile=hunspell_sample_num,
+						AffFile=ispell_sample
+);
+
+CREATE TEXT SEARCH DICTIONARY hunspell_err (
+						Template=ispell,
+						DictFile=hunspell_sample_num,
+						AffFile=hunspell_sample_long
+);
+
 -- Synonym dictionary
 CREATE TEXT SEARCH DICTIONARY synonym (
 						Template=synonym,