Merge branch 'mk/grep-pcre'

* mk/grep-pcre:
  git-grep: Fix problems with recently added tests
  git-grep: Update tests (mainly for -P)
  Makefile: Pass USE_LIBPCRE down in GIT-BUILD-OPTIONS
  git-grep: update tests now regexp type is "last one wins"
  git-grep: do not die upon -F/-P when grep.extendedRegexp is set.
  git-grep: Bail out when -P is used with -F or -E
  grep: Add basic tests
  configure: Check for libpcre
  git-grep: Learn PCRE
  grep: Extract compile_regexp_failed() from compile_regexp()
  grep: Fix a typo in a comment
  grep: Put calls to fixmatch() and regmatch() into patmatch()
  contrib/completion: --line-number to git grep
  Documentation: Add --line-number to git-grep synopsis

Documentation/git-grep.txt

@@ -12,7 +12,8 @@ SYNOPSIS
 'git grep' [-a | --text] [-I] [-i | --ignore-case] [-w | --word-regexp]
 	   [-v | --invert-match] [-h|-H] [--full-name]
 	   [-E | --extended-regexp] [-G | --basic-regexp]
-	   [-F | --fixed-strings] [-n]
+	   [-P | --perl-regexp]
+	   [-F | --fixed-strings] [-n | --line-number]
 	   [-l | --files-with-matches] [-L | --files-without-match]
 	   [(-O | --open-files-in-pager) [<pager>]]
 	   [-z | --null]
@@ -97,6 +98,11 @@ OPTIONS
 	Use POSIX extended/basic regexp for patterns.  Default
 	is to use basic regexp.
 
+-P::
+--perl-regexp::
+	Use Perl-compatible regexp for patterns. Requires libpcre to be
+	compiled in.
+
 -F::
 --fixed-strings::
 	Use fixed strings for patterns (don't interpret pattern

Makefile

@@ -24,6 +24,12 @@ all::
 # Define NO_OPENSSL environment variable if you do not have OpenSSL.
 # This also implies BLK_SHA1.
 #
+# Define USE_LIBPCRE if you have and want to use libpcre. git-grep will be
+# able to use Perl-compatible regular expressions.
+#
+# Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in
+# /foo/bar/include and /foo/bar/lib directories.
+#
 # Define NO_CURL if you do not have libcurl installed.  git-http-pull and
 # git-http-push are not built, and you cannot use http:// and https://
 # transports.
@@ -1258,6 +1264,15 @@ ifdef NO_LIBGEN_H
 	COMPAT_OBJS += compat/basename.o
 endif
 
+ifdef USE_LIBPCRE
+	BASIC_CFLAGS += -DUSE_LIBPCRE
+	ifdef LIBPCREDIR
+		BASIC_CFLAGS += -I$(LIBPCREDIR)/include
+		EXTLIBS += -L$(LIBPCREDIR)/$(lib) $(CC_LD_DYNPATH)$(LIBPCREDIR)/$(lib)
+	endif
+	EXTLIBS += -lpcre
+endif
+
 ifdef NO_CURL
 	BASIC_CFLAGS += -DNO_CURL
 	REMOTE_CURL_PRIMARY =
@@ -2089,6 +2104,7 @@ GIT-BUILD-OPTIONS: FORCE
 	@echo PYTHON_PATH=\''$(subst ','\'',$(PYTHON_PATH_SQ))'\' >>$@
 	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@
 	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@
+	@echo USE_LIBPCRE=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE)))'\' >>$@
 	@echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@
 	@echo NO_PYTHON=\''$(subst ','\'',$(subst ','\'',$(NO_PYTHON)))'\' >>$@
 ifdef GIT_TEST_CMP

builtin/grep.c

@@ -753,6 +753,15 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	int i;
 	int dummy;
 	int use_index = 1;
+	enum {
+		pattern_type_unspecified = 0,
+		pattern_type_bre,
+		pattern_type_ere,
+		pattern_type_fixed,
+		pattern_type_pcre,
+	};
+	int pattern_type = pattern_type_unspecified;
+
 	struct option options[] = {
 		OPT_BOOLEAN(0, "cached", &cached,
 			"search in index instead of in the work tree"),
@@ -774,13 +783,18 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			"descend at most <depth> levels", PARSE_OPT_NONEG,
 			NULL, 1 },
 		OPT_GROUP(""),
-		OPT_BIT('E', "extended-regexp", &opt.regflags,
-			"use extended POSIX regular expressions", REG_EXTENDED),
-		OPT_NEGBIT('G', "basic-regexp", &opt.regflags,
-			"use basic POSIX regular expressions (default)",
-			REG_EXTENDED),
-		OPT_BOOLEAN('F', "fixed-strings", &opt.fixed,
-			"interpret patterns as fixed strings"),
+		OPT_SET_INT('E', "extended-regexp", &pattern_type,
+			    "use extended POSIX regular expressions",
+			    pattern_type_ere),
+		OPT_SET_INT('G', "basic-regexp", &pattern_type,
+			    "use basic POSIX regular expressions (default)",
+			    pattern_type_bre),
+		OPT_SET_INT('F', "fixed-strings", &pattern_type,
+			    "interpret patterns as fixed strings",
+			    pattern_type_fixed),
+		OPT_SET_INT('P', "perl-regexp", &pattern_type,
+			    "use Perl-compatible regular expressions",
+			    pattern_type_pcre),
 		OPT_GROUP(""),
 		OPT_BOOLEAN('n', "line-number", &opt.linenum, "show line numbers"),
 		OPT_NEGBIT('h', NULL, &opt.pathname, "don't show filenames", 1),
@@ -886,6 +900,28 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			     PARSE_OPT_KEEP_DASHDASH |
 			     PARSE_OPT_STOP_AT_NON_OPTION |
 			     PARSE_OPT_NO_INTERNAL_HELP);
+	switch (pattern_type) {
+	case pattern_type_fixed:
+		opt.fixed = 1;
+		opt.pcre = 0;
+		break;
+	case pattern_type_bre:
+		opt.fixed = 0;
+		opt.pcre = 0;
+		opt.regflags &= ~REG_EXTENDED;
+		break;
+	case pattern_type_ere:
+		opt.fixed = 0;
+		opt.pcre = 0;
+		opt.regflags |= REG_EXTENDED;
+		break;
+	case pattern_type_pcre:
+		opt.fixed = 0;
+		opt.pcre = 1;
+		break;
+	default:
+		break; /* nothing */
+	}
 
 	if (use_index && !startup_info->have_repository)
 		/* die the same way as if we did it at the beginning */
@@ -925,8 +961,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		die(_("no pattern given."));
 	if (!opt.fixed && opt.ignore_case)
 		opt.regflags |= REG_ICASE;
-	if ((opt.regflags != REG_NEWLINE) && opt.fixed)
-		die(_("cannot mix --fixed-strings and regexp"));
 
 #ifndef NO_PTHREADS
 	if (online_cpus() == 1 || !grep_threads_ok(&opt))

config.mak.in

@@ -61,6 +61,7 @@ NO_INET_PTON=@NO_INET_PTON@
 NO_ICONV=@NO_ICONV@
 OLD_ICONV=@OLD_ICONV@
 NO_REGEX=@NO_REGEX@
+USE_LIBPCRE=@USE_LIBPCRE@
 NO_DEFLATE_BOUND=@NO_DEFLATE_BOUND@
 INLINE=@INLINE@
 SOCKLEN_T=@SOCKLEN_T@

configure.ac

@@ -220,6 +220,27 @@ AS_HELP_STRING([--with-openssl],[use OpenSSL library (default is YES)])
 AS_HELP_STRING([],              [ARG can be prefix for openssl library and headers]),\
 GIT_PARSE_WITH(openssl))
 #
+# Define USE_LIBPCRE if you have and want to use libpcre. git-grep will be
+# able to use Perl-compatible regular expressions.
+#
+# Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in
+# /foo/bar/include and /foo/bar/lib directories.
+#
+AC_ARG_WITH(libpcre,
+AS_HELP_STRING([--with-libpcre],[support Perl-compatible regexes (default is NO)])
+AS_HELP_STRING([],           [ARG can be also prefix for libpcre library and headers]),
+if test "$withval" = "no"; then \
+	USE_LIBPCRE=; \
+elif test "$withval" = "yes"; then \
+	USE_LIBPCRE=YesPlease; \
+else
+	USE_LIBPCRE=YesPlease; \
+	LIBPCREDIR=$withval; \
+	AC_MSG_NOTICE([Setting LIBPCREDIR to $withval]); \
+	GIT_CONF_APPEND_LINE(LIBPCREDIR=$withval); \
+fi \
+)
+#
 # Define NO_CURL if you do not have curl installed.  git-http-pull and
 # git-http-push are not built, and you cannot use http:// and https://
 # transports.
@@ -434,6 +455,25 @@ GIT_UNSTASH_FLAGS($OPENSSLDIR)
 AC_SUBST(NEEDS_SSL_WITH_CRYPTO)
 AC_SUBST(NO_OPENSSL)
 
+#
+# Define USE_LIBPCRE if you have and want to use libpcre. git-grep will be
+# able to use Perl-compatible regular expressions.
+#
+
+if test -n "$USE_LIBPCRE"; then
+
+GIT_STASH_FLAGS($LIBPCREDIR)
+
+AC_CHECK_LIB([pcre], [pcre_version],
+[USE_LIBPCRE=YesPlease],
+[USE_LIBPCRE=])
+
+GIT_UNSTASH_FLAGS($LIBPCREDIR)
+
+AC_SUBST(USE_LIBPCRE)
+
+fi
+
 #
 # Define NO_CURL if you do not have libcurl installed.  git-http-pull and
 # git-http-push are not built, and you cannot use http:// and https://

contrib/completion/git-completion.bash

@@ -1441,8 +1441,9 @@ _git_grep ()
 		__gitcomp "
 			--cached
 			--text --ignore-case --word-regexp --invert-match
-			--full-name
+			--full-name --line-number
 			--extended-regexp --basic-regexp --fixed-strings
+			--perl-regexp
 			--files-with-matches --name-only
 			--files-without-match
 			--max-depth

grep.c

@@ -59,6 +59,84 @@ struct grep_opt *grep_opt_dup(const struct grep_opt *opt)
 	return ret;
 }
 
+static NORETURN void compile_regexp_failed(const struct grep_pat *p,
+		const char *error)
+{
+	char where[1024];
+
+	if (p->no)
+		sprintf(where, "In '%s' at %d, ", p->origin, p->no);
+	else if (p->origin)
+		sprintf(where, "%s, ", p->origin);
+	else
+		where[0] = 0;
+
+	die("%s'%s': %s", where, p->pattern, error);
+}
+
+#ifdef USE_LIBPCRE
+static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
+{
+	const char *error;
+	int erroffset;
+	int options = 0;
+
+	if (opt->ignore_case)
+		options |= PCRE_CASELESS;
+
+	p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
+			NULL);
+	if (!p->pcre_regexp)
+		compile_regexp_failed(p, error);
+
+	p->pcre_extra_info = pcre_study(p->pcre_regexp, 0, &error);
+	if (!p->pcre_extra_info && error)
+		die("%s", error);
+}
+
+static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
+		regmatch_t *match, int eflags)
+{
+	int ovector[30], ret, flags = 0;
+
+	if (eflags & REG_NOTBOL)
+		flags |= PCRE_NOTBOL;
+
+	ret = pcre_exec(p->pcre_regexp, p->pcre_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);
+	if (ret > 0) {
+		ret = 0;
+		match->rm_so = ovector[0];
+		match->rm_eo = ovector[1];
+	}
+
+	return ret;
+}
+
+static void free_pcre_regexp(struct grep_pat *p)
+{
+	pcre_free(p->pcre_regexp);
+	pcre_free(p->pcre_extra_info);
+}
+#else /* !USE_LIBPCRE */
+static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
+{
+	die("cannot use Perl-compatible regexes when not compiled with USE_LIBPCRE");
+}
+
+static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
+		regmatch_t *match, int eflags)
+{
+	return 1;
+}
+
+static void free_pcre_regexp(struct grep_pat *p)
+{
+}
+#endif /* !USE_LIBPCRE */
+
 static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
 	int err;
@@ -70,20 +148,17 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 	if (p->fixed)
 		return;
 
+	if (opt->pcre) {
+		compile_pcre_regexp(p, opt);
+		return;
+	}
+
 	err = regcomp(&p->regexp, p->pattern, opt->regflags);
 	if (err) {
 		char errbuf[1024];
-		char where[1024];
-		if (p->no)
-			sprintf(where, "In '%s' at %d, ",
-				p->origin, p->no);
-		else if (p->origin)
-			sprintf(where, "%s, ", p->origin);
-		else
-			where[0] = 0;
 		regerror(err, &p->regexp, errbuf, 1024);
 		regfree(&p->regexp);
-		die("%s'%s': %s", where, p->pattern, errbuf);
+		compile_regexp_failed(p, errbuf);
 	}
 }
 
@@ -320,7 +395,10 @@ void free_grep_patterns(struct grep_opt *opt)
 		case GREP_PATTERN: /* atom */
 		case GREP_PATTERN_HEAD:
 		case GREP_PATTERN_BODY:
-			regfree(&p->regexp);
+			if (p->pcre_regexp)
+				free_pcre_regexp(p);
+			else
+				regfree(&p->regexp);
 			break;
 		default:
 			break;
@@ -412,6 +490,21 @@ static int regmatch(const regex_t *preg, char *line, char *eol,
 	return regexec(preg, line, 1, match, eflags);
 }
 
+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->pcre_regexp)
+		hit = !pcrematch(p, line, eol, match, eflags);
+	else
+		hit = !regmatch(&p->regexp, line, eol, match, eflags);
+
+	return hit;
+}
+
 static int strip_timestamp(char *bol, char **eol_p)
 {
 	char *eol = *eol_p;
@@ -461,10 +554,7 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
 	}
 
  again:
-	if (p->fixed)
-		hit = !fixmatch(p, bol, eol, pmatch);
-	else
-		hit = !regmatch(&p->regexp, bol, eol, pmatch, eflags);
+	hit = patmatch(p, bol, eol, pmatch, eflags);
 
 	if (hit && p->word_regexp) {
 		if ((pmatch[0].rm_so < 0) ||
@@ -791,10 +881,7 @@ static int look_ahead(struct grep_opt *opt,
 		int hit;
 		regmatch_t m;
 
-		if (p->fixed)
-			hit = !fixmatch(p, bol, bol + *left_p, &m);
-		else
-			hit = !regmatch(&p->regexp, bol, bol + *left_p, &m, 0);
+		hit = patmatch(p, bol, bol + *left_p, &m, 0);
 		if (!hit || m.rm_so < 0 || m.rm_eo < 0)
 			continue;
 		if (earliest < 0 || m.rm_so < earliest)
@@ -891,7 +978,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 		int hit;
 
 		/*
-		 * look_ahead() skips quicly to the line that possibly
+		 * look_ahead() skips quickly to the line that possibly
 		 * has the next hit; don't call it if we need to do
 		 * something more than just skipping the current line
 		 * in response to an unmatch for the current line.  E.g.

grep.h

 #ifndef GREP_H
 #define GREP_H
 #include "color.h"
+#ifdef USE_LIBPCRE
+#include <pcre.h>
+#else
+typedef int pcre;
+typedef int pcre_extra;
+#endif
 
 enum grep_pat_token {
 	GREP_PATTERN,
@@ -33,6 +39,8 @@ struct grep_pat {
 	size_t patternlen;
 	enum grep_header_field field;
 	regex_t regexp;
+	pcre *pcre_regexp;
+	pcre_extra *pcre_extra_info;
 	unsigned fixed:1;
 	unsigned ignore_case:1;
 	unsigned word_regexp:1;
@@ -83,6 +91,7 @@ struct grep_opt {
 #define GREP_BINARY_TEXT	2
 	int binary;
 	int extended;
+	int pcre;
 	int relative;
 	int pathname;
 	int null_following_name;

t/README

@@ -588,6 +588,11 @@ use these, and "test_set_prereq" for how to define your own.
    Test is not run by root user, and an attempt to write to an
    unwritable file is expected to fail correctly.
 
+ - LIBPCRE
+
+   Git was compiled with USE_LIBPCRE=YesPlease. Wrap any tests
+   that use git-grep --perl-regexp or git-grep -P in these.
+
 Tips for Writing Tests
 ----------------------
 

t/t7810-grep.sh

@@ -26,6 +26,17 @@ test_expect_success setup '
 		echo foo mmap bar_mmap
 		echo foo_mmap bar mmap baz
 	} >file &&
+	{
+		echo Hello world
+		echo HeLLo world
+		echo Hello_world
+		echo HeLLo_world
+	} >hello_world &&
+	{
+		echo "a+b*c"
+		echo "a+bc"
+		echo "abc"
+	} >ab &&
 	echo vvv >v &&
 	echo ww w >w &&
 	echo x x xx x >x &&
@@ -221,7 +232,17 @@ do
 		git grep --max-depth 0 -n -e vvv $H -- t . >actual &&
 		test_cmp expected actual
 	'
+	test_expect_success "grep $L with grep.extendedRegexp=false" '
+		echo "ab:a+bc" >expected &&
+		git -c grep.extendedRegexp=false grep "a+b*c" ab >actual &&
+		test_cmp expected actual
+	'
 
+	test_expect_success "grep $L with grep.extendedRegexp=true" '
+		echo "ab:abc" >expected &&
+		git -c grep.extendedRegexp=true grep "a+b*c" ab >actual &&
+		test_cmp expected actual
+	'
 done
 
 cat >expected <<EOF
@@ -599,4 +620,100 @@ test_expect_success 'grep -e -- -- path' '
 	test_cmp expected actual
 '
 
+cat >expected <<EOF
+hello.c:int main(int argc, const char **argv)
+hello.c:	printf("Hello world.\n");
+EOF
+
+test_expect_success LIBPCRE 'grep --perl-regexp pattern' '
+	git grep --perl-regexp "\p{Ps}.*?\p{Pe}" hello.c >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success LIBPCRE 'grep -P pattern' '
+	git grep -P "\p{Ps}.*?\p{Pe}" hello.c >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep pattern with grep.extendedRegexp=true' '
+	>empty &&
+	test_must_fail git -c grep.extendedregexp=true \
+		grep "\p{Ps}.*?\p{Pe}" hello.c >actual &&
+	test_cmp empty actual
+'
+
+test_expect_success LIBPCRE 'grep -P pattern with grep.extendedRegexp=true' '
+	git -c grep.extendedregexp=true \
+		grep -P "\p{Ps}.*?\p{Pe}" hello.c >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success LIBPCRE 'grep -P -v pattern' '
+	{
+		echo "ab:a+b*c"
+		echo "ab:a+bc"
+	} >expected &&
+	git grep -P -v "abc" ab >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success LIBPCRE 'grep -P -i pattern' '
+	{
+		echo "hello.c:	printf(\"Hello world.\n\");"
+	} >expected &&
+	git grep -P -i "PRINTF\([^\d]+\)" hello.c >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success LIBPCRE 'grep -P -w pattern' '
+	{
+		echo "hello_world:Hello world"
+		echo "hello_world:HeLLo world"
+	} >expected &&
+	git grep -P -w "He((?i)ll)o" hello_world >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep -G invalidpattern properly dies ' '
+	test_must_fail git grep -G "a["
+'
+
+test_expect_success 'grep -E invalidpattern properly dies ' '
+	test_must_fail git grep -E "a["
+'
+
+test_expect_success LIBPCRE 'grep -P invalidpattern properly dies ' '
+	test_must_fail git grep -P "a["
+'
+
+test_expect_success 'grep -G -E -F pattern' '
+	echo "ab:a+b*c" >expected &&
+	git grep -G -E -F "a+b*c" ab >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep -E -F -G pattern' '
+	echo "ab:a+bc" >expected &&
+	git grep -E -F -G "a+b*c" ab >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep -F -G -E pattern' '
+	echo "ab:abc" >expected &&
+	git grep -F -G -E "a+b*c" ab >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep -G -F -P -E pattern' '
+	>empty &&
+	test_must_fail git grep -G -F -P -E "a\x{2b}b\x{2a}c" ab >actual &&
+	test_cmp empty actual
+'
+
+test_expect_success LIBPCRE 'grep -G -F -E -P pattern' '
+	echo "ab:a+b*c" >expected &&
+	git grep -G -F -E -P "a\x{2b}b\x{2a}c" ab >actual &&
+	test_cmp expected actual
+'
+
 test_done

t/test-lib.sh

@@ -1071,6 +1071,7 @@ esac
 
 test -z "$NO_PERL" && test_set_prereq PERL
 test -z "$NO_PYTHON" && test_set_prereq PYTHON
+test -n "$USE_LIBPCRE" && test_set_prereq LIBPCRE
 
 # Can we rely on git's output in the C locale?
 if test -n "$GETTEXT_POISON"