Merge branch 'ab/pcre-jit-fixes'

A few simplification and bugfixes to PCRE interface.

* ab/pcre-jit-fixes:
  grep: under --debug, show whether PCRE JIT is enabled
  grep: do not enter PCRE2_UTF mode on fixed matching
  grep: stess test PCRE v2 on invalid UTF-8 data
  grep: create a "is_fixed" member in "grep_pat"
  grep: consistently use "p->fixed" in compile_regexp()
  grep: stop using a custom JIT stack with PCRE v1
  grep: stop "using" a custom JIT stack with PCRE v2
  grep: remove overly paranoid BUG(...) code
  grep: use PCRE v2 for optimized fixed-string search
  grep: remove the kwset optimization
  grep: drop support for \0 in --fixed-strings <pattern>
  grep: make the behavior for NUL-byte in patterns sane
  grep tests: move binary pattern tests into their own file
  grep tests: move "grep binary" alongside the rest
  grep: inline the return value of a function call used only once
  t4210: skip more command-line encoding tests on MinGW
  grep: don't use PCRE2?_UTF8 with "log --encoding=<non-utf8>"
  log tests: test regex backends in "--encode=<enc>" tests

Author: gitster

Documentation/git-grep.txt

@@ -271,6 +271,23 @@ providing this option will cause it to die.
 
 -f <file>::
 	Read patterns from <file>, one per line.
++
+Passing the pattern via <file> allows for providing a search pattern
+containing a \0.
++
+Not all pattern types support patterns containing \0. Git will error
+out if a given pattern type can't support such a pattern. The
+`--perl-regexp` pattern type when compiled against the PCRE v2 backend
+has the widest support for these types of patterns.
++
+In versions of Git before 2.23.0 patterns containing \0 would be
+silently considered fixed. This was never documented, there were also
+odd and undocumented interactions between e.g. non-ASCII patterns
+containing \0 and `--ignore-case`.
++
+In future versions we may learn to support patterns containing \0 for
+more search backends, until then we'll die when the pattern type in
+question doesn't support them.
 
 -e::
 	The next parameter is the pattern. This option has to be

grep.c

@@ -368,18 +368,6 @@ static int is_fixed(const char *s, size_t len)
 	return 1;
 }
 
-static int has_null(const char *s, size_t len)
-{
-	/*
-	 * regcomp cannot accept patterns with NULs so when using it
-	 * we consider any pattern containing a NUL fixed.
-	 */
-	if (memchr(s, 0, len))
-		return 1;
-
-	return 0;
-}
-
 #ifdef USE_LIBPCRE1
 static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
 {
@@ -388,11 +376,11 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
 	int options = PCRE_MULTILINE;
 
 	if (opt->ignore_case) {
-		if (has_non_ascii(p->pattern))
+		if (!opt->ignore_locale && has_non_ascii(p->pattern))
 			p->pcre1_tables = pcre_maketables();
 		options |= PCRE_CASELESS;
 	}
-	if (is_utf8_locale() && has_non_ascii(p->pattern))
+	if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern))
 		options |= PCRE_UTF8;
 
 	p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
@@ -406,15 +394,8 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
 
 #ifdef GIT_PCRE1_USE_JIT
 	pcre_config(PCRE_CONFIG_JIT, &p->pcre1_jit_on);
-	if (p->pcre1_jit_on == 1) {
-		p->pcre1_jit_stack = pcre_jit_stack_alloc(1, 1024 * 1024);
-		if (!p->pcre1_jit_stack)
-			die("Couldn't allocate PCRE JIT stack");
-		pcre_assign_jit_stack(p->pcre1_extra_info, NULL, p->pcre1_jit_stack);
-	} else if (p->pcre1_jit_on != 0) {
-		BUG("The pcre1_jit_on variable should be 0 or 1, not %d",
-		    p->pcre1_jit_on);
-	}
+	if (opt->debug)
+		fprintf(stderr, "pcre1_jit_on=%d\n", p->pcre1_jit_on);
 #endif
 }
 
@@ -426,18 +407,9 @@ static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
 	if (eflags & REG_NOTBOL)
 		flags |= PCRE_NOTBOL;
 
-#ifdef GIT_PCRE1_USE_JIT
-	if (p->pcre1_jit_on) {
-		ret = pcre_jit_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
-				    eol - line, 0, flags, ovector,
-				    ARRAY_SIZE(ovector), p->pcre1_jit_stack);
-	} else
-#endif
-	{
-		ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
-				eol - line, 0, flags, ovector,
-				ARRAY_SIZE(ovector));
-	}
+	ret = pcre_exec(p->pcre1_regexp, p->pcre1_extra_info, line,
+			eol - line, 0, flags, ovector,
+			ARRAY_SIZE(ovector));
 
 	if (ret < 0 && ret != PCRE_ERROR_NOMATCH)
 		die("pcre_exec failed with error code %d", ret);
@@ -454,14 +426,11 @@ static void free_pcre1_regexp(struct grep_pat *p)
 {
 	pcre_free(p->pcre1_regexp);
 #ifdef GIT_PCRE1_USE_JIT
-	if (p->pcre1_jit_on) {
+	if (p->pcre1_jit_on)
 		pcre_free_study(p->pcre1_extra_info);
-		pcre_jit_stack_free(p->pcre1_jit_stack);
-	} else
+	else
 #endif
-	{
 		pcre_free(p->pcre1_extra_info);
-	}
 	pcre_free((void *)p->pcre1_tables);
 }
 #else /* !USE_LIBPCRE1 */
@@ -498,14 +467,15 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
 	p->pcre2_compile_context = NULL;
 
 	if (opt->ignore_case) {
-		if (has_non_ascii(p->pattern)) {
+		if (!opt->ignore_locale && has_non_ascii(p->pattern)) {
 			character_tables = pcre2_maketables(NULL);
 			p->pcre2_compile_context = pcre2_compile_context_create(NULL);
 			pcre2_set_character_tables(p->pcre2_compile_context, character_tables);
 		}
 		options |= PCRE2_CASELESS;
 	}
-	if (is_utf8_locale() && has_non_ascii(p->pattern))
+	if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) &&
+	    !(!opt->ignore_case && (p->fixed || p->is_fixed)))
 		options |= PCRE2_UTF;
 
 	p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
@@ -522,7 +492,9 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
 	}
 
 	pcre2_config(PCRE2_CONFIG_JIT, &p->pcre2_jit_on);
-	if (p->pcre2_jit_on == 1) {
+	if (opt->debug)
+		fprintf(stderr, "pcre2_jit_on=%d\n", p->pcre2_jit_on);
+	if (p->pcre2_jit_on) {
 		jitret = pcre2_jit_compile(p->pcre2_pattern, PCRE2_JIT_COMPLETE);
 		if (jitret)
 			die("Couldn't JIT the PCRE2 pattern '%s', got '%d'\n", p->pattern, jitret);
@@ -547,19 +519,11 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
 			BUG("pcre2_pattern_info() failed: %d", patinforet);
 		if (jitsizearg == 0) {
 			p->pcre2_jit_on = 0;
+			if (opt->debug)
+				fprintf(stderr, "pcre2_jit_on=%d: (*NO_JIT) in regex\n",
+					p->pcre2_jit_on);
 			return;
 		}
-
-		p->pcre2_jit_stack = pcre2_jit_stack_create(1, 1024 * 1024, NULL);
-		if (!p->pcre2_jit_stack)
-			die("Couldn't allocate PCRE2 JIT stack");
-		p->pcre2_match_context = pcre2_match_context_create(NULL);
-		if (!p->pcre2_match_context)
-			die("Couldn't allocate PCRE2 match context");
-		pcre2_jit_stack_assign(p->pcre2_match_context, NULL, p->pcre2_jit_stack);
-	} else if (p->pcre2_jit_on != 0) {
-		BUG("The pcre2_jit_on variable should be 0 or 1, not %d",
-		    p->pcre2_jit_on);
 	}
 }
 
@@ -603,8 +567,6 @@ static void free_pcre2_pattern(struct grep_pat *p)
 	pcre2_compile_context_free(p->pcre2_compile_context);
 	pcre2_code_free(p->pcre2_pattern);
 	pcre2_match_data_free(p->pcre2_match_data);
-	pcre2_jit_stack_free(p->pcre2_jit_stack);
-	pcre2_match_context_free(p->pcre2_match_context);
 }
 #else /* !USE_LIBPCRE2 */
 static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt)
@@ -626,7 +588,6 @@ static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
 static void free_pcre2_pattern(struct grep_pat *p)
 {
 }
-#endif /* !USE_LIBPCRE2 */
 
 static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
@@ -647,46 +608,66 @@ static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
 		compile_regexp_failed(p, errbuf);
 	}
 }
+#endif /* !USE_LIBPCRE2 */
 
 static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
-	int ascii_only;
 	int err;
 	int regflags = REG_NEWLINE;
 
 	p->word_regexp = opt->word_regexp;
 	p->ignore_case = opt->ignore_case;
-	ascii_only     = !has_non_ascii(p->pattern);
+	p->fixed = opt->fixed;
 
-	/*
-	 * Even when -F (fixed) asks us to do a non-regexp search, we
-	 * may not be able to correctly case-fold when -i
-	 * (ignore-case) is asked (in which case, we'll synthesize a
-	 * regexp to match the pattern that matches regexp special
-	 * characters literally, while ignoring case differences).  On
-	 * the other hand, even without -F, if the pattern does not
-	 * have any regexp special characters and there is no need for
-	 * case-folding search, we can internally turn it into a
-	 * simple string match using kws.  p->fixed tells us if we
-	 * want to use kws.
-	 */
-	if (opt->fixed ||
-	    has_null(p->pattern, p->patternlen) ||
-	    is_fixed(p->pattern, p->patternlen))
-		p->fixed = !p->ignore_case || ascii_only;
-
-	if (p->fixed) {
-		p->kws = kwsalloc(p->ignore_case ? tolower_trans_tbl : NULL);
-		kwsincr(p->kws, p->pattern, p->patternlen);
-		kwsprep(p->kws);
-		return;
-	} else if (opt->fixed) {
-		/*
-		 * We come here when the pattern has the non-ascii
-		 * characters we cannot case-fold, and asked to
-		 * ignore-case.
-		 */
+	if (memchr(p->pattern, 0, p->patternlen) && !opt->pcre2)
+		die(_("given pattern contains NULL byte (via -f <file>). This is only supported with -P under PCRE v2"));
+
+	p->is_fixed = is_fixed(p->pattern, p->patternlen);
+#ifdef USE_LIBPCRE2
+       if (!p->fixed && !p->is_fixed) {
+	       const char *no_jit = "(*NO_JIT)";
+	       const int no_jit_len = strlen(no_jit);
+	       if (starts_with(p->pattern, no_jit) &&
+		   is_fixed(p->pattern + no_jit_len,
+			    p->patternlen - no_jit_len))
+		       p->is_fixed = 1;
+       }
+#endif
+	if (p->fixed || p->is_fixed) {
+#ifdef USE_LIBPCRE2
+		opt->pcre2 = 1;
+		if (p->is_fixed) {
+			compile_pcre2_pattern(p, opt);
+		} else {
+			/*
+			 * E.g. t7811-grep-open.sh relies on the
+			 * pattern being restored.
+			 */
+			char *old_pattern = p->pattern;
+			size_t old_patternlen = p->patternlen;
+			struct strbuf sb = STRBUF_INIT;
+
+			/*
+			 * There is the PCRE2_LITERAL flag, but it's
+			 * only in PCRE v2 10.30 and later. Needing to
+			 * ifdef our way around that and dealing with
+			 * it + PCRE2_MULTILINE being an error is more
+			 * complex than just quoting this ourselves.
+			*/
+			strbuf_add(&sb, "\\Q", 2);
+			strbuf_add(&sb, p->pattern, p->patternlen);
+			strbuf_add(&sb, "\\E", 2);
+
+			p->pattern = sb.buf;
+			p->patternlen = sb.len;
+			compile_pcre2_pattern(p, opt);
+			p->pattern = old_pattern;
+			p->patternlen = old_patternlen;
+			strbuf_release(&sb);
+		}
+#else /* !USE_LIBPCRE2 */
 		compile_fixed_regexp(p, opt);
+#endif /* !USE_LIBPCRE2 */
 		return;
 	}
 
@@ -1053,9 +1034,7 @@ void free_grep_patterns(struct grep_opt *opt)
 		case GREP_PATTERN: /* atom */
 		case GREP_PATTERN_HEAD:
 		case GREP_PATTERN_BODY:
-			if (p->kws)
-				kwsfree(p->kws);
-			else if (p->pcre1_regexp)
+			if (p->pcre1_regexp)
 				free_pcre1_regexp(p);
 			else if (p->pcre2_pattern)
 				free_pcre2_pattern(p);
@@ -1115,29 +1094,12 @@ static void show_name(struct grep_opt *opt, const char *name)
 	opt->output(opt, opt->null_following_name ? "\0" : "\n", 1);
 }
 
-static int fixmatch(struct grep_pat *p, char *line, char *eol,
-		    regmatch_t *match)
-{
-	struct kwsmatch kwsm;
-	size_t offset = kwsexec(p->kws, line, eol - line, &kwsm);
-	if (offset == -1) {
-		match->rm_so = match->rm_eo = -1;
-		return REG_NOMATCH;
-	} else {
-		match->rm_so = offset;
-		match->rm_eo = match->rm_so + kwsm.size[0];
-		return 0;
-	}
-}
-
 static int patmatch(struct grep_pat *p, char *line, char *eol,
 		    regmatch_t *match, int eflags)
 {
 	int hit;
 
-	if (p->fixed)
-		hit = !fixmatch(p, line, eol, match);
-	else if (p->pcre1_regexp)
+	if (p->pcre1_regexp)
 		hit = !pcre1match(p, line, eol, match, eflags);
 	else if (p->pcre2_pattern)
 		hit = !pcre2match(p, line, eol, match, eflags);

grep.h

@@ -17,13 +17,9 @@
 #ifndef GIT_PCRE_STUDY_JIT_COMPILE
 #define GIT_PCRE_STUDY_JIT_COMPILE 0
 #endif
-#if PCRE_MAJOR <= 8 && PCRE_MINOR < 20
-typedef int pcre_jit_stack;
-#endif
 #else
 typedef int pcre;
 typedef int pcre_extra;
-typedef int pcre_jit_stack;
 #endif
 #ifdef USE_LIBPCRE2
 #define PCRE2_CODE_UNIT_WIDTH 8
@@ -32,10 +28,7 @@ typedef int pcre_jit_stack;
 typedef int pcre2_code;
 typedef int pcre2_match_data;
 typedef int pcre2_compile_context;
-typedef int pcre2_match_context;
-typedef int pcre2_jit_stack;
 #endif
-#include "kwset.h"
 #include "thread-utils.h"
 #include "userdiff.h"
 
@@ -91,17 +84,14 @@ struct grep_pat {
 	regex_t regexp;
 	pcre *pcre1_regexp;
 	pcre_extra *pcre1_extra_info;
-	pcre_jit_stack *pcre1_jit_stack;
 	const unsigned char *pcre1_tables;
 	int pcre1_jit_on;
 	pcre2_code *pcre2_pattern;
 	pcre2_match_data *pcre2_match_data;
 	pcre2_compile_context *pcre2_compile_context;
-	pcre2_match_context *pcre2_match_context;
-	pcre2_jit_stack *pcre2_jit_stack;
 	uint32_t pcre2_jit_on;
-	kwset_t kws;
 	unsigned fixed:1;
+	unsigned is_fixed:1;
 	unsigned ignore_case:1;
 	unsigned word_regexp:1;
 };
@@ -176,6 +166,7 @@ struct grep_opt {
 	int funcbody;
 	int extended_regexp_option;
 	int pattern_type_option;
+	int ignore_locale;
 	char colors[NR_GREP_COLORS][COLOR_MAXLEN];
 	unsigned pre_context;
 	unsigned post_context;

revision.c

@@ -28,6 +28,7 @@
 #include "commit-graph.h"
 #include "prio-queue.h"
 #include "hashmap.h"
+#include "utf8.h"
 
 volatile show_early_output_fn_t show_early_output;
 
@@ -2687,6 +2688,8 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s
 
 	grep_commit_pattern_type(GREP_PATTERN_TYPE_UNSPECIFIED,
 				 &revs->grep_filter);
+	if (!is_encoding_utf8(get_log_output_encoding()))
+		revs->grep_filter.ignore_locale = 1;
 	compile_grep_patterns(&revs->grep_filter);
 
 	if (revs->reverse && revs->reflog_info)