grep: skip UTF8 checks explicitly

carenas · gitster · commit ad7c543e3b0f · 2019-09-09T11:50:08.000-07:00
18547aa ("grep/pcre: support utf-8", 2016-06-25) that was released with git 2.10 added the PCRE_UTF8 flag to PCRE1 matching including a call to has_non_ascii() to try to avoid breakage if there was non-utf8 encoded content in the haystack. Usually PCRE is compiled with JIT support (even if is not the default), and therefore the codepath used includes calling pcre_jit_exec, which skips UTF-8 validation by design (which might result in crashes or hangs) but when JIT support wasn't compiled we use pcre_exec instead with the posibility that grep might be aborted if invalid UTF-8 is found in the haystack. PCRE1 provides a flag since Mar 5, 2007 that could be used to skip the checks explicitly so use that to make both codepaths equivalent (the flag is ignored by pcre1_jit_exec) this fix is only implemented for PCRE1 because PCRE2 is likely to have a better solution (without the risks) instead in the future Helped-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Suggested-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Carlo Marcelo Arenas Belón <carenas@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/grep.c b/grep.c
@@ -421,7 +421,7 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
 static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
 		regmatch_t *match, int eflags)
 {
-	int ovector[30], ret, flags = 0;
+	int ovector[30], ret, flags = PCRE_NO_UTF8_CHECK;
 
 	if (eflags & REG_NOTBOL)
 		flags |= PCRE_NOTBOL;
diff --git a/grep.h b/grep.h
@@ -3,6 +3,9 @@
 #include "color.h"
 #ifdef USE_LIBPCRE1
 #include <pcre.h>
+#ifndef PCRE_NO_UTF8_CHECK
+#define PCRE_NO_UTF8_CHECK 0
+#endif
 #ifdef PCRE_CONFIG_JIT
 #if PCRE_MAJOR >= 8 && PCRE_MINOR >= 32
 #ifndef NO_LIBPCRE1_JIT

Original file line number	Diff line number	Diff line change
`@@ -421,7 +421,7 @@ static void compile_pcre1_regexp(struct grep_pat p, const struct grep_opt opt)`
`421`	`421`	`static int pcre1match(struct grep_pat p, const char line, const char *eol,`
`422`	`422`	`regmatch_t *match, int eflags)`
`423`	`423`	`{`
`424`		`- int ovector[30], ret, flags = 0;`
	`424`	`+ int ovector[30], ret, flags = PCRE_NO_UTF8_CHECK;`
`425`	`425`
`426`	`426`	`if (eflags & REG_NOTBOL)`
`427`	`427`	`flags \|= PCRE_NOTBOL;`