1 files changed, 235 insertions, 64 deletions

diff --git a/grep.c b/grep.c
index 9c5e1cd..190139c 100644
--- a/grep.c
+++ b/grep.c
@@ -168,15 +168,10 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 		p->fixed = 0;
 
 	if (p->fixed) {
-		if (opt->regflags & REG_ICASE || p->ignore_case) {
-			static char trans[256];
-			int i;
-			for (i = 0; i < 256; i++)
-				trans[i] = tolower(i);
-			p->kws = kwsalloc(trans);
-		} else {
+		if (opt->regflags & REG_ICASE || p->ignore_case)
+			p->kws = kwsalloc(tolower_trans_tbl);
+		else
 			p->kws = kwsalloc(NULL);
-		}
 		kwsincr(p->kws, p->pattern, p->patternlen);
 		kwsprep(p->kws);
 		return;
@@ -806,10 +801,51 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol,
 	opt->output(opt, "\n", 1);
 }
 
-static int match_funcname(struct grep_opt *opt, char *bol, char *eol)
+#ifndef NO_PTHREADS
+int grep_use_locks;
+
+/*
+ * This lock protects access to the gitattributes machinery, which is
+ * not thread-safe.
+ */
+pthread_mutex_t grep_attr_mutex;
+
+static inline void grep_attr_lock(void)
+{
+	if (grep_use_locks)
+		pthread_mutex_lock(&grep_attr_mutex);
+}
+
+static inline void grep_attr_unlock(void)
+{
+	if (grep_use_locks)
+		pthread_mutex_unlock(&grep_attr_mutex);
+}
+
+/*
+ * Same as git_attr_mutex, but protecting the thread-unsafe object db access.
+ */
+pthread_mutex_t grep_read_mutex;
+
+#else
+#define grep_attr_lock()
+#define grep_attr_unlock()
+#endif
+
+static int match_funcname(struct grep_opt *opt, struct grep_source *gs, char *bol, char *eol)
 {
 	xdemitconf_t *xecfg = opt->priv;
-	if (xecfg && xecfg->find_func) {
+	if (xecfg && !xecfg->find_func) {
+		grep_source_load_driver(gs);
+		if (gs->driver->funcname.pattern) {
+			const struct userdiff_funcname *pe = &gs->driver->funcname;
+			xdiff_set_find_func(xecfg, pe->pattern, pe->cflags);
+		} else {
+			xecfg = opt->priv = NULL;
+		}
+	}
+
+	if (xecfg) {
 		char buf[1];
 		return xecfg->find_func(bol, eol - bol, buf, 1,
 					xecfg->find_func_priv) >= 0;
@@ -822,33 +858,33 @@ static int match_funcname(struct grep_opt *opt, char *bol, char *eol)
 	return 0;
 }
 
-static void show_funcname_line(struct grep_opt *opt, const char *name,
-			       char *buf, char *bol, unsigned lno)
+static void show_funcname_line(struct grep_opt *opt, struct grep_source *gs,
+			       char *bol, unsigned lno)
 {
-	while (bol > buf) {
+	while (bol > gs->buf) {
 		char *eol = --bol;
 
-		while (bol > buf && bol[-1] != '\n')
+		while (bol > gs->buf && bol[-1] != '\n')
 			bol--;
 		lno--;
 
 		if (lno <= opt->last_shown)
 			break;
 
-		if (match_funcname(opt, bol, eol)) {
-			show_line(opt, bol, eol, name, lno, '=');
+		if (match_funcname(opt, gs, bol, eol)) {
+			show_line(opt, bol, eol, gs->name, lno, '=');
 			break;
 		}
 	}
 }
 
-static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
+static void show_pre_context(struct grep_opt *opt, struct grep_source *gs,
 			     char *bol, char *end, unsigned lno)
 {
 	unsigned cur = lno, from = 1, funcname_lno = 0;
 	int funcname_needed = !!opt->funcname;
 
-	if (opt->funcbody && !match_funcname(opt, bol, end))
+	if (opt->funcbody && !match_funcname(opt, gs, bol, end))
 		funcname_needed = 2;
 
 	if (opt->pre_context < lno)
@@ -857,14 +893,14 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
 		from = opt->last_shown + 1;
 
 	/* Rewind. */
-	while (bol > buf &&
+	while (bol > gs->buf &&
 	       cur > (funcname_needed == 2 ? opt->last_shown + 1 : from)) {
 		char *eol = --bol;
 
-		while (bol > buf && bol[-1] != '\n')
+		while (bol > gs->buf && bol[-1] != '\n')
 			bol--;
 		cur--;
-		if (funcname_needed && match_funcname(opt, bol, eol)) {
+		if (funcname_needed && match_funcname(opt, gs, bol, eol)) {
 			funcname_lno = cur;
 			funcname_needed = 0;
 		}
@@ -872,7 +908,7 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
 
 	/* We need to look even further back to find a function signature. */
 	if (opt->funcname && funcname_needed)
-		show_funcname_line(opt, name, buf, bol, cur);
+		show_funcname_line(opt, gs, bol, cur);
 
 	/* Back forward. */
 	while (cur < lno) {
@@ -880,7 +916,7 @@ static void show_pre_context(struct grep_opt *opt, const char *name, char *buf,
 
 		while (*eol != '\n')
 			eol++;
-		show_line(opt, bol, eol, name, cur, sign);
+		show_line(opt, bol, eol, gs->name, cur, sign);
 		bol = eol + 1;
 		cur++;
 	}
@@ -942,29 +978,15 @@ static int look_ahead(struct grep_opt *opt,
 	return 0;
 }
 
-int grep_threads_ok(const struct grep_opt *opt)
-{
-	/* If this condition is true, then we may use the attribute
-	 * machinery in grep_buffer_1. The attribute code is not
-	 * thread safe, so we disable the use of threads.
-	 */
-	if (opt->funcname && !opt->unmatch_name_only && !opt->status_only &&
-	    !opt->name_only)
-		return 0;
-
-	return 1;
-}
-
 static void std_output(struct grep_opt *opt, const void *buf, size_t size)
 {
 	fwrite(buf, size, 1, stdout);
 }
 
-static int grep_buffer_1(struct grep_opt *opt, const char *name,
-			 char *buf, unsigned long size, int collect_hits)
+static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int collect_hits)
 {
-	char *bol = buf;
-	unsigned long left = size;
+	char *bol;
+	unsigned long left;
 	unsigned lno = 1;
 	unsigned last_hit = 0;
 	int binary_match_only = 0;
@@ -994,11 +1016,11 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 
 	switch (opt->binary) {
 	case GREP_BINARY_DEFAULT:
-		if (buffer_is_binary(buf, size))
+		if (grep_source_is_binary(gs))
 			binary_match_only = 1;
 		break;
 	case GREP_BINARY_NOMATCH:
-		if (buffer_is_binary(buf, size))
+		if (grep_source_is_binary(gs))
 			return 0; /* Assume unmatch */
 		break;
 	case GREP_BINARY_TEXT:
@@ -1008,17 +1030,15 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 	}
 
 	memset(&xecfg, 0, sizeof(xecfg));
-	if (opt->funcname && !opt->unmatch_name_only && !opt->status_only &&
-	    !opt->name_only && !binary_match_only && !collect_hits) {
-		struct userdiff_driver *drv = userdiff_find_by_path(name);
-		if (drv && drv->funcname.pattern) {
-			const struct userdiff_funcname *pe = &drv->funcname;
-			xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
-			opt->priv = &xecfg;
-		}
-	}
+	opt->priv = &xecfg;
+
 	try_lookahead = should_lookahead(opt);
 
+	if (grep_source_load(gs) < 0)
+		return 0;
+
+	bol = gs->buf;
+	left = gs->size;
 	while (left) {
 		char *eol, ch;
 		int hit;
@@ -1067,14 +1087,14 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 			if (opt->status_only)
 				return 1;
 			if (opt->name_only) {
-				show_name(opt, name);
+				show_name(opt, gs->name);
 				return 1;
 			}
 			if (opt->count)
 				goto next_line;
 			if (binary_match_only) {
 				opt->output(opt, "Binary file ", 12);
-				output_color(opt, name, strlen(name),
+				output_color(opt, gs->name, strlen(gs->name),
 					     opt->color_filename);
 				opt->output(opt, " matches\n", 9);
 				return 1;
@@ -1083,23 +1103,23 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 			 * pre-context lines, we would need to show them.
 			 */
 			if (opt->pre_context || opt->funcbody)
-				show_pre_context(opt, name, buf, bol, eol, lno);
+				show_pre_context(opt, gs, bol, eol, lno);
 			else if (opt->funcname)
-				show_funcname_line(opt, name, buf, bol, lno);
-			show_line(opt, bol, eol, name, lno, ':');
+				show_funcname_line(opt, gs, bol, lno);
+			show_line(opt, bol, eol, gs->name, lno, ':');
 			last_hit = lno;
 			if (opt->funcbody)
 				show_function = 1;
 			goto next_line;
 		}
-		if (show_function && match_funcname(opt, bol, eol))
+		if (show_function && match_funcname(opt, gs, bol, eol))
 			show_function = 0;
 		if (show_function ||
 		    (last_hit && lno <= last_hit + opt->post_context)) {
 			/* If the last hit is within the post context,
 			 * we need to show this line.
 			 */
-			show_line(opt, bol, eol, name, lno, '-');
+			show_line(opt, bol, eol, gs->name, lno, '-');
 		}
 
 	next_line:
@@ -1117,7 +1137,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 		return 0;
 	if (opt->unmatch_name_only) {
 		/* We did not see any hit, so we want to show this */
-		show_name(opt, name);
+		show_name(opt, gs->name);
 		return 1;
 	}
 
@@ -1131,7 +1151,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 	 */
 	if (opt->count && count) {
 		char buf[32];
-		output_color(opt, name, strlen(name), opt->color_filename);
+		output_color(opt, gs->name, strlen(gs->name), opt->color_filename);
 		output_sep(opt, ':');
 		snprintf(buf, sizeof(buf), "%u\n", count);
 		opt->output(opt, buf, strlen(buf));
@@ -1166,23 +1186,174 @@ static int chk_hit_marker(struct grep_expr *x)
 	}
 }
 
-int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size)
+int grep_source(struct grep_opt *opt, struct grep_source *gs)
 {
 	/*
 	 * we do not have to do the two-pass grep when we do not check
 	 * buffer-wide "all-match".
 	 */
 	if (!opt->all_match)
-		return grep_buffer_1(opt, name, buf, size, 0);
+		return grep_source_1(opt, gs, 0);
 
 	/* Otherwise the toplevel "or" terms hit a bit differently.
 	 * We first clear hit markers from them.
 	 */
 	clr_hit_marker(opt->pattern_expression);
-	grep_buffer_1(opt, name, buf, size, 1);
+	grep_source_1(opt, gs, 1);
 
 	if (!chk_hit_marker(opt->pattern_expression))
 		return 0;
 
-	return grep_buffer_1(opt, name, buf, size, 0);
+	return grep_source_1(opt, gs, 0);
+}
+
+int grep_buffer(struct grep_opt *opt, char *buf, unsigned long size)
+{
+	struct grep_source gs;
+	int r;
+
+	grep_source_init(&gs, GREP_SOURCE_BUF, NULL, NULL);
+	gs.buf = buf;
+	gs.size = size;
+
+	r = grep_source(opt, &gs);
+
+	grep_source_clear(&gs);
+	return r;
+}
+
+void grep_source_init(struct grep_source *gs, enum grep_source_type type,
+		      const char *name, const void *identifier)
+{
+	gs->type = type;
+	gs->name = name ? xstrdup(name) : NULL;
+	gs->buf = NULL;
+	gs->size = 0;
+	gs->driver = NULL;
+
+	switch (type) {
+	case GREP_SOURCE_FILE:
+		gs->identifier = xstrdup(identifier);
+		break;
+	case GREP_SOURCE_SHA1:
+		gs->identifier = xmalloc(20);
+		memcpy(gs->identifier, identifier, 20);
+		break;
+	case GREP_SOURCE_BUF:
+		gs->identifier = NULL;
+	}
+}
+
+void grep_source_clear(struct grep_source *gs)
+{
+	free(gs->name);
+	gs->name = NULL;
+	free(gs->identifier);
+	gs->identifier = NULL;
+	grep_source_clear_data(gs);
+}
+
+void grep_source_clear_data(struct grep_source *gs)
+{
+	switch (gs->type) {
+	case GREP_SOURCE_FILE:
+	case GREP_SOURCE_SHA1:
+		free(gs->buf);
+		gs->buf = NULL;
+		gs->size = 0;
+		break;
+	case GREP_SOURCE_BUF:
+		/* leave user-provided buf intact */
+		break;
+	}
+}
+
+static int grep_source_load_sha1(struct grep_source *gs)
+{
+	enum object_type type;
+
+	grep_read_lock();
+	gs->buf = read_sha1_file(gs->identifier, &type, &gs->size);
+	grep_read_unlock();
+
+	if (!gs->buf)
+		return error(_("'%s': unable to read %s"),
+			     gs->name,
+			     sha1_to_hex(gs->identifier));
+	return 0;
+}
+
+static int grep_source_load_file(struct grep_source *gs)
+{
+	const char *filename = gs->identifier;
+	struct stat st;
+	char *data;
+	size_t size;
+	int i;
+
+	if (lstat(filename, &st) < 0) {
+	err_ret:
+		if (errno != ENOENT)
+			error(_("'%s': %s"), filename, strerror(errno));
+		return -1;
+	}
+	if (!S_ISREG(st.st_mode))
+		return -1;
+	size = xsize_t(st.st_size);
+	i = open(filename, O_RDONLY);
+	if (i < 0)
+		goto err_ret;
+	data = xmalloc(size + 1);
+	if (st.st_size != read_in_full(i, data, size)) {
+		error(_("'%s': short read %s"), filename, strerror(errno));
+		close(i);
+		free(data);
+		return -1;
+	}
+	close(i);
+	data[size] = 0;
+
+	gs->buf = data;
+	gs->size = size;
+	return 0;
+}
+
+int grep_source_load(struct grep_source *gs)
+{
+	if (gs->buf)
+		return 0;
+
+	switch (gs->type) {
+	case GREP_SOURCE_FILE:
+		return grep_source_load_file(gs);
+	case GREP_SOURCE_SHA1:
+		return grep_source_load_sha1(gs);
+	case GREP_SOURCE_BUF:
+		return gs->buf ? 0 : -1;
+	}
+	die("BUG: invalid grep_source type");
+}
+
+void grep_source_load_driver(struct grep_source *gs)
+{
+	if (gs->driver)
+		return;
+
+	grep_attr_lock();
+	gs->driver = userdiff_find_by_path(gs->name);
+	if (!gs->driver)
+		gs->driver = userdiff_find_by_name("default");
+	grep_attr_unlock();
+}
+
+int grep_source_is_binary(struct grep_source *gs)
+{
+	grep_source_load_driver(gs);
+	if (gs->driver->binary != -1)
+		return gs->driver->binary;
+
+	if (!grep_source_load(gs))
+		return buffer_is_binary(gs->buf, gs->size);
+
+	return 0;
 }