Merge branch 'ab/grep-preparatory-cleanup'

The internal implementation of "git grep" has seen some clean-up.

* ab/grep-preparatory-cleanup: (31 commits)
  grep: assert that threading is enabled when calling grep_{lock,unlock}
  grep: given --threads with NO_PTHREADS=YesPlease, warn
  pack-objects: fix buggy warning about threads
  pack-objects & index-pack: add test for --threads warning
  test-lib: add a PTHREADS prerequisite
  grep: move is_fixed() earlier to avoid forward declaration
  grep: change internal *pcre* variable & function names to be *pcre1*
  grep: change the internal PCRE macro names to be PCRE1
  grep: factor test for \0 in grep patterns into a function
  grep: remove redundant regflags assignments
  grep: catch a missing enum in switch statement
  perf: add a comparison test of log --grep regex engines with -F
  perf: add a comparison test of log --grep regex engines
  perf: add a comparison test of grep regex engines with -F
  perf: add a comparison test of grep regex engines
  perf: emit progress output when unpacking & building
  perf: add a GIT_PERF_MAKE_COMMAND for when *_MAKE_OPTS won't do
  grep: add tests to fix blind spots with \0 patterns
  grep: prepare for testing binary regexes containing rx metacharacters
  grep: add a test helper function for less verbose -f \0 tests
  ...

Author: gitster

Documentation/git-grep.txt

@@ -161,8 +161,11 @@ OPTIONS
 
 -P::
 --perl-regexp::
-	Use Perl-compatible regexp for patterns. Requires libpcre to be
-	compiled in.
+	Use Perl-compatible regular expressions for patterns.
++
+Support for these types of regular expressions is an optional
+compile-time dependency. If Git wasn't compiled with support for them
+providing this option will cause it to die.
 
 -F::
 --fixed-strings::

Documentation/rev-list-options.txt

@@ -92,8 +92,12 @@ endif::git-rev-list[]
 	pattern as a regular expression).
 
 --perl-regexp::
-	Consider the limiting patterns to be Perl-compatible regular expressions.
-	Requires libpcre to be compiled in.
+	Consider the limiting patterns to be Perl-compatible regular
+	expressions.
++
+Support for these types of regular expressions is an optional
+compile-time dependency. If Git wasn't compiled with support for them
+providing this option will cause it to die.
 
 --remove-empty::
 	Stop when a given path disappears from the tree.

Makefile

@@ -24,8 +24,10 @@ 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 USE_LIBPCRE if you have and want to use libpcre. Various
+# commands such as log and grep offer runtime options to use
+# Perl-compatible regular expressions instead of standard or extended
+# POSIX regular expressions.
 #
 # Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in
 # /foo/bar/include and /foo/bar/lib directories.
@@ -1087,7 +1089,7 @@ ifdef NO_LIBGEN_H
 endif
 
 ifdef USE_LIBPCRE
-	BASIC_CFLAGS += -DUSE_LIBPCRE
+	BASIC_CFLAGS += -DUSE_LIBPCRE1
 	ifdef LIBPCREDIR
 		BASIC_CFLAGS += -I$(LIBPCREDIR)/include
 		EXTLIBS += -L$(LIBPCREDIR)/$(lib) $(CC_LD_DYNPATH)$(LIBPCREDIR)/$(lib)
@@ -2239,8 +2241,9 @@ GIT-BUILD-OPTIONS: FORCE
 	@echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@+
 	@echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@+
 	@echo NO_EXPAT=\''$(subst ','\'',$(subst ','\'',$(NO_EXPAT)))'\' >>$@+
-	@echo USE_LIBPCRE=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE)))'\' >>$@+
+	@echo USE_LIBPCRE1=\''$(subst ','\'',$(subst ','\'',$(USE_LIBPCRE)))'\' >>$@+
 	@echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@+
+	@echo NO_PTHREADS=\''$(subst ','\'',$(subst ','\'',$(NO_PTHREADS)))'\' >>$@+
 	@echo NO_PYTHON=\''$(subst ','\'',$(subst ','\'',$(NO_PYTHON)))'\' >>$@+
 	@echo NO_UNIX_SOCKETS=\''$(subst ','\'',$(subst ','\'',$(NO_UNIX_SOCKETS)))'\' >>$@+
 	@echo PAGER_ENV=\''$(subst ','\'',$(subst ','\'',$(PAGER_ENV)))'\' >>$@+
@@ -2271,6 +2274,9 @@ endif
 ifdef GIT_PERF_MAKE_OPTS
 	@echo GIT_PERF_MAKE_OPTS=\''$(subst ','\'',$(subst ','\'',$(GIT_PERF_MAKE_OPTS)))'\' >>$@+
 endif
+ifdef GIT_PERF_MAKE_COMMAND
+	@echo GIT_PERF_MAKE_COMMAND=\''$(subst ','\'',$(subst ','\'',$(GIT_PERF_MAKE_COMMAND)))'\' >>$@+
+endif
 ifdef GIT_INTEROP_MAKE_OPTS
 	@echo GIT_INTEROP_MAKE_OPTS=\''$(subst ','\'',$(subst ','\'',$(GIT_INTEROP_MAKE_OPTS)))'\' >>$@+
 endif

builtin/grep.c

@@ -73,14 +73,14 @@ static pthread_mutex_t grep_mutex;
 
 static inline void grep_lock(void)
 {
-	if (num_threads)
-		pthread_mutex_lock(&grep_mutex);
+	assert(num_threads);
+	pthread_mutex_lock(&grep_mutex);
 }
 
 static inline void grep_unlock(void)
 {
-	if (num_threads)
-		pthread_mutex_unlock(&grep_mutex);
+	assert(num_threads);
+	pthread_mutex_unlock(&grep_mutex);
 }
 
 /* Signalled when a new work_item is added to todo. */
@@ -289,6 +289,17 @@ static int grep_cmd_config(const char *var, const char *value, void *cb)
 		if (num_threads < 0)
 			die(_("invalid number of threads specified (%d) for %s"),
 			    num_threads, var);
+#ifdef NO_PTHREADS
+		else if (num_threads && num_threads != 1) {
+			/*
+			 * TRANSLATORS: %s is the configuration
+			 * variable for tweaking threads, currently
+			 * grep.threads
+			 */
+			warning(_("no threads support, ignoring %s"), var);
+			num_threads = 0;
+		}
+#endif
 	}
 
 	return st;
@@ -495,6 +506,8 @@ static void compile_submodule_options(const struct grep_opt *opt,
 		break;
 	case GREP_PATTERN_TYPE_UNSPECIFIED:
 		break;
+	default:
+		die("BUG: Added a new grep pattern type without updating switch statement");
 	}
 
 	for (pattern = opt->pattern_list; pattern != NULL;
@@ -1229,6 +1242,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	else if (num_threads < 0)
 		die(_("invalid number of threads specified (%d)"), num_threads);
 #else
+	if (num_threads)
+		warning(_("no threads support, ignoring --threads"));
 	num_threads = 0;
 #endif
 

builtin/pack-objects.c

@@ -2483,8 +2483,10 @@ static int git_pack_config(const char *k, const char *v, void *cb)
 			die("invalid number of threads specified (%d)",
 			    delta_search_threads);
 #ifdef NO_PTHREADS
-		if (delta_search_threads != 1)
+		if (delta_search_threads != 1) {
 			warning("no threads support, ignoring %s", k);
+			delta_search_threads = 0;
+		}
 #endif
 		return 0;
 	}

configure.ac

@@ -250,8 +250,10 @@ 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 USE_LIBPCRE if you have and want to use libpcre. Various
+# commands such as log and grep offer runtime options to use
+# Perl-compatible regular expressions instead of standard or extended
+# POSIX regular expressions.
 #
 # Define LIBPCREDIR=/foo/bar if your libpcre header and library files are in
 # /foo/bar/include and /foo/bar/lib directories.
@@ -499,8 +501,10 @@ GIT_CONF_SUBST([NEEDS_SSL_WITH_CRYPTO])
 GIT_CONF_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.
+# Define USE_LIBPCRE if you have and want to use libpcre. Various
+# commands such as log and grep offer runtime options to use
+# Perl-compatible regular expressions instead of standard or extended
+# POSIX regular expressions.
 #
 
 if test -n "$USE_LIBPCRE"; then

grep.c

@@ -178,26 +178,23 @@ static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, st
 
 	case GREP_PATTERN_TYPE_BRE:
 		opt->fixed = 0;
-		opt->pcre = 0;
-		opt->regflags &= ~REG_EXTENDED;
+		opt->pcre1 = 0;
 		break;
 
 	case GREP_PATTERN_TYPE_ERE:
 		opt->fixed = 0;
-		opt->pcre = 0;
+		opt->pcre1 = 0;
 		opt->regflags |= REG_EXTENDED;
 		break;
 
 	case GREP_PATTERN_TYPE_FIXED:
 		opt->fixed = 1;
-		opt->pcre = 0;
-		opt->regflags &= ~REG_EXTENDED;
+		opt->pcre1 = 0;
 		break;
 
 	case GREP_PATTERN_TYPE_PCRE:
 		opt->fixed = 0;
-		opt->pcre = 1;
-		opt->regflags &= ~REG_EXTENDED;
+		opt->pcre1 = 1;
 		break;
 	}
 }
@@ -324,40 +321,64 @@ static NORETURN void compile_regexp_failed(const struct grep_pat *p,
 	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)
+static int is_fixed(const char *s, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (is_regex_special(s[i]))
+			return 0;
+	}
+
+	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)
 {
 	const char *error;
 	int erroffset;
 	int options = PCRE_MULTILINE;
 
 	if (opt->ignore_case) {
 		if (has_non_ascii(p->pattern))
-			p->pcre_tables = pcre_maketables();
+			p->pcre1_tables = pcre_maketables();
 		options |= PCRE_CASELESS;
 	}
 	if (is_utf8_locale() && has_non_ascii(p->pattern))
 		options |= PCRE_UTF8;
 
-	p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
-				      p->pcre_tables);
-	if (!p->pcre_regexp)
+	p->pcre1_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
+				      p->pcre1_tables);
+	if (!p->pcre1_regexp)
 		compile_regexp_failed(p, error);
 
-	p->pcre_extra_info = pcre_study(p->pcre_regexp, 0, &error);
-	if (!p->pcre_extra_info && error)
+	p->pcre1_extra_info = pcre_study(p->pcre1_regexp, 0, &error);
+	if (!p->pcre1_extra_info && error)
 		die("%s", error);
 }
 
-static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
+static int pcre1match(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,
+	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);
@@ -370,55 +391,36 @@ static int pcrematch(struct grep_pat *p, const char *line, const char *eol,
 	return ret;
 }
 
-static void free_pcre_regexp(struct grep_pat *p)
+static void free_pcre1_regexp(struct grep_pat *p)
 {
-	pcre_free(p->pcre_regexp);
-	pcre_free(p->pcre_extra_info);
-	pcre_free((void *)p->pcre_tables);
+	pcre_free(p->pcre1_regexp);
+	pcre_free(p->pcre1_extra_info);
+	pcre_free((void *)p->pcre1_tables);
 }
-#else /* !USE_LIBPCRE */
-static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
+#else /* !USE_LIBPCRE1 */
+static void compile_pcre1_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,
+static int pcre1match(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)
+static void free_pcre1_regexp(struct grep_pat *p)
 {
 }
-#endif /* !USE_LIBPCRE */
-
-static int is_fixed(const char *s, size_t len)
-{
-	size_t i;
-
-	/* regcomp cannot accept patterns with NULs so we
-	 * consider any pattern containing a NUL fixed.
-	 */
-	if (memchr(s, 0, len))
-		return 1;
-
-	for (i = 0; i < len; i++) {
-		if (is_regex_special(s[i]))
-			return 0;
-	}
-
-	return 1;
-}
+#endif /* !USE_LIBPCRE1 */
 
 static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
 	struct strbuf sb = STRBUF_INIT;
 	int err;
-	int regflags;
+	int regflags = opt->regflags;
 
 	basic_regex_quote_buf(&sb, p->pattern);
-	regflags = opt->regflags & ~REG_EXTENDED;
 	if (opt->ignore_case)
 		regflags |= REG_ICASE;
 	err = regcomp(&p->regexp, sb.buf, regflags);
@@ -455,7 +457,9 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 	 * simple string match using kws.  p->fixed tells us if we
 	 * want to use kws.
 	 */
-	if (opt->fixed || is_fixed(p->pattern, p->patternlen))
+	if (opt->fixed ||
+	    has_null(p->pattern, p->patternlen) ||
+	    is_fixed(p->pattern, p->patternlen))
 		p->fixed = !icase || ascii_only;
 	else
 		p->fixed = 0;
@@ -475,8 +479,8 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 		return;
 	}
 
-	if (opt->pcre) {
-		compile_pcre_regexp(p, opt);
+	if (opt->pcre1) {
+		compile_pcre1_regexp(p, opt);
 		return;
 	}
 
@@ -832,8 +836,8 @@ void free_grep_patterns(struct grep_opt *opt)
 		case GREP_PATTERN_BODY:
 			if (p->kws)
 				kwsfree(p->kws);
-			else if (p->pcre_regexp)
-				free_pcre_regexp(p);
+			else if (p->pcre1_regexp)
+				free_pcre1_regexp(p);
 			else
 				regfree(&p->regexp);
 			free(p->pattern);
@@ -912,8 +916,8 @@ static int patmatch(struct grep_pat *p, char *line, char *eol,
 
 	if (p->fixed)
 		hit = !fixmatch(p, line, eol, match);
-	else if (p->pcre_regexp)
-		hit = !pcrematch(p, line, eol, match, eflags);
+	else if (p->pcre1_regexp)
+		hit = !pcre1match(p, line, eol, match, eflags);
 	else
 		hit = !regexec_buf(&p->regexp, line, eol - line, 1, match,
 				   eflags);