Merge branch 'bc/master-diff-hunk-header-fix'

* bc/master-diff-hunk-header-fix:
  Clarify commit error message for unmerged files
  Use strchrnul() instead of strchr() plus manual workaround
  Use remove_path from dir.c instead of own implementation
  Add remove_path: a function to remove as much as possible of a path
  git-submodule: Fix "Unable to checkout" for the initial 'update'
  Clarify how the user can satisfy stash's 'dirty state' check.
  t4018-diff-funcname: test syntax of builtin xfuncname patterns
  t4018-diff-funcname: test syntax of builtin xfuncname patterns
  make "git remote" report multiple URLs
  diff hunk pattern: fix misconverted "\{" tex macro introducers
  diff: fix "multiple regexp" semantics to find hunk header comment
  diff: use extended regexp to find hunk headers
  diff: use extended regexp to find hunk headers
  diff.*.xfuncname which uses "extended" regex's for hunk header selection
  diff.c: associate a flag with each pattern and use it for compiling regex
  diff.c: return pattern entry pointer rather than just the hunk header pattern

Conflicts:
	builtin-merge-recursive.c
	t/t7201-co.sh
	xdiff-interface.h

Documentation/gitattributes.txt

@@ -288,13 +288,13 @@ for paths.
 *.tex	diff=tex
 ------------------------
 
-Then, you would define a "diff.tex.funcname" configuration to
+Then, you would define a "diff.tex.xfuncname" configuration to
 specify a regular expression that matches a line that you would
 want to appear as the hunk header "TEXT", like this:
 
 ------------------------
 [diff "tex"]
-	funcname = "^\\(\\\\\\(sub\\)*section{.*\\)$"
+	xfuncname = "^(\\\\(sub)*section\\{.*)$"
 ------------------------
 
 Note.  A single level of backslashes are eaten by the

builtin-apply.c

@@ -13,6 +13,7 @@
 #include "delta.h"
 #include "builtin.h"
 #include "string-list.h"
+#include "dir.h"
 
 /*
  *  --check turns on checking that the working tree matches the
@@ -2735,15 +2736,7 @@ static void remove_file(struct patch *patch, int rmdir_empty)
 				warning("unable to remove submodule %s",
 					patch->old_name);
 		} else if (!unlink(patch->old_name) && rmdir_empty) {
-			char *name = xstrdup(patch->old_name);
-			char *end = strrchr(name, '/');
-			while (end) {
-				*end = 0;
-				if (rmdir(name))
-					break;
-				end = strrchr(name, '/');
-			}
-			free(name);
+			remove_path(patch->old_name);
 		}
 	}
 }

builtin-commit.c

@@ -639,7 +639,7 @@ static int prepare_to_commit(const char *index_file, const char *prefix)
 		active_cache_tree = cache_tree();
 	if (cache_tree_update(active_cache_tree,
 			      active_cache, active_nr, 0, 0) < 0) {
-		error("Error building trees");
+		error("Error building trees; the index is unmerged?");
 		return 0;
 	}
 

builtin-for-each-ref.c

@@ -320,9 +320,7 @@ static const char *find_wholine(const char *who, int wholen, const char *buf, un
 
 static const char *copy_line(const char *buf)
 {
-	const char *eol = strchr(buf, '\n');
-	if (!eol) // simulate strchrnul()
-		eol = buf + strlen(buf);
+	const char *eol = strchrnul(buf, '\n');
 	return xmemdupz(buf, eol - buf);
 }
 

builtin-remote.c

@@ -650,10 +650,13 @@ static int get_one_entry(struct remote *remote, void *priv)
 {
 	struct string_list *list = priv;
 
-	string_list_append(remote->name, list)->util = remote->url_nr ?
-		(void *)remote->url[0] : NULL;
-	if (remote->url_nr > 1)
-		warning("Remote %s has more than one URL", remote->name);
+	if (remote->url_nr > 0) {
+		int i;
+
+		for (i = 0; i < remote->url_nr; i++)
+			string_list_append(remote->name, list)->util = (void *)remote->url[i];
+	} else
+		string_list_append(remote->name, list)->util = NULL;
 
 	return 0;
 }
@@ -669,10 +672,14 @@ static int show_all(void)
 		sort_string_list(&list);
 		for (i = 0; i < list.nr; i++) {
 			struct string_list_item *item = list.items + i;
-			printf("%s%s%s\n", item->string,
-				verbose ? "\t" : "",
-				verbose && item->util ?
-					(const char *)item->util : "");
+			if (verbose)
+				printf("%s\t%s\n", item->string,
+					item->util ? (const char *)item->util : "");
+			else {
+				if (i && !strcmp((item - 1)->string, item->string))
+					continue;
+				printf("%s\n", item->string);
+			}
 		}
 	}
 	return result;

builtin-rm.c

@@ -29,26 +29,6 @@ static void add_list(const char *name)
 	list.name[list.nr++] = name;
 }
 
-static int remove_file(const char *name)
-{
-	int ret;
-	char *slash;
-
-	ret = unlink(name);
-	if (ret && errno == ENOENT)
-		/* The user has removed it from the filesystem by hand */
-		ret = errno = 0;
-
-	if (!ret && (slash = strrchr(name, '/'))) {
-		char *n = xstrdup(name);
-		do {
-			n[slash - name] = 0;
-			name = n;
-		} while (!rmdir(name) && (slash = strrchr(name, '/')));
-	}
-	return ret;
-}
-
 static int check_local_mod(unsigned char *head, int index_only)
 {
 	/* items in list are already sorted in the cache order,
@@ -239,7 +219,7 @@ int cmd_rm(int argc, const char **argv, const char *prefix)
 		int removed = 0;
 		for (i = 0; i < list.nr; i++) {
 			const char *path = list.name[i];
-			if (!remove_file(path)) {
+			if (!remove_path(path)) {
 				removed = 1;
 				continue;
 			}

diff.c

@@ -96,32 +96,37 @@ static int parse_lldiff_command(const char *var, const char *ep, const char *val
  * to define a customized regexp to find the beginning of a function to
  * be used for hunk header lines of "diff -p" style output.
  */
-static struct funcname_pattern {
+struct funcname_pattern_entry {
 	char *name;
 	char *pattern;
-	struct funcname_pattern *next;
+	int cflags;
+};
+static struct funcname_pattern_list {
+	struct funcname_pattern_list *next;
+	struct funcname_pattern_entry e;
 } *funcname_pattern_list;
 
-static int parse_funcname_pattern(const char *var, const char *ep, const char *value)
+static int parse_funcname_pattern(const char *var, const char *ep, const char *value, int cflags)
 {
 	const char *name;
 	int namelen;
-	struct funcname_pattern *pp;
+	struct funcname_pattern_list *pp;
 
 	name = var + 5; /* "diff." */
 	namelen = ep - name;
 
 	for (pp = funcname_pattern_list; pp; pp = pp->next)
-		if (!strncmp(pp->name, name, namelen) && !pp->name[namelen])
+		if (!strncmp(pp->e.name, name, namelen) && !pp->e.name[namelen])
 			break;
 	if (!pp) {
 		pp = xcalloc(1, sizeof(*pp));
-		pp->name = xmemdupz(name, namelen);
+		pp->e.name = xmemdupz(name, namelen);
 		pp->next = funcname_pattern_list;
 		funcname_pattern_list = pp;
 	}
-	free(pp->pattern);
-	pp->pattern = xstrdup(value);
+	free(pp->e.pattern);
+	pp->e.pattern = xstrdup(value);
+	pp->e.cflags = cflags;
 	return 0;
 }
 
@@ -194,7 +199,13 @@ int git_diff_basic_config(const char *var, const char *value, void *cb)
 			if (!strcmp(ep, ".funcname")) {
 				if (!value)
 					return config_error_nonbool(var);
-				return parse_funcname_pattern(var, ep, value);
+				return parse_funcname_pattern(var, ep, value,
+					0);
+			} else if (!strcmp(ep, ".xfuncname")) {
+				if (!value)
+					return config_error_nonbool(var);
+				return parse_funcname_pattern(var, ep, value,
+					REG_EXTENDED);
 			}
 		}
 	}
@@ -1400,42 +1411,45 @@ int diff_filespec_is_binary(struct diff_filespec *one)
 	return one->is_binary;
 }
 
-static const char *funcname_pattern(const char *ident)
+static const struct funcname_pattern_entry *funcname_pattern(const char *ident)
 {
-	struct funcname_pattern *pp;
+	struct funcname_pattern_list *pp;
 
 	for (pp = funcname_pattern_list; pp; pp = pp->next)
-		if (!strcmp(ident, pp->name))
-			return pp->pattern;
+		if (!strcmp(ident, pp->e.name))
+			return &pp->e;
 	return NULL;
 }
 
-static struct builtin_funcname_pattern {
-	const char *name;
-	const char *pattern;
-} builtin_funcname_pattern[] = {
-	{ "bibtex", "\\(@[a-zA-Z]\\{1,\\}[ \t]*{\\{0,1\\}[ \t]*[^ \t\"@',\\#}{~%]*\\).*$" },
-	{ "html", "^\\s*\\(<[Hh][1-6]\\s.*>.*\\)$" },
-	{ "java", "!^[ 	]*\\(catch\\|do\\|for\\|if\\|instanceof\\|"
-			"new\\|return\\|switch\\|throw\\|while\\)\n"
-			"^[ 	]*\\(\\([ 	]*"
-			"[A-Za-z_][A-Za-z_0-9]*\\)\\{2,\\}"
-			"[ 	]*([^;]*\\)$" },
-	{ "pascal", "^\\(\\(procedure\\|function\\|constructor\\|"
-			"destructor\\|interface\\|implementation\\|"
-			"initialization\\|finalization\\)[ \t]*.*\\)$"
-			"\\|"
-			"^\\(.*=[ \t]*\\(class\\|record\\).*\\)$"
-			},
-	{ "php", "^[\t ]*\\(\\(function\\|class\\).*\\)" },
-	{ "python", "^\\s*\\(\\(class\\|def\\)\\s.*\\)$" },
-	{ "ruby", "^\\s*\\(\\(class\\|module\\|def\\)\\s.*\\)$" },
-	{ "tex", "^\\(\\\\\\(\\(sub\\)*section\\|chapter\\|part\\)\\*\\{0,1\\}{.*\\)$" },
+static const struct funcname_pattern_entry builtin_funcname_pattern[] = {
+	{ "bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
+	  REG_EXTENDED },
+	{ "html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$", REG_EXTENDED },
+	{ "java",
+	  "!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
+	  "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$",
+	  REG_EXTENDED },
+	{ "pascal",
+	  "^((procedure|function|constructor|destructor|interface|"
+		"implementation|initialization|finalization)[ \t]*.*)$"
+	  "\n"
+	  "^(.*=[ \t]*(class|record).*)$",
+	  REG_EXTENDED },
+	{ "php", "^[\t ]*((function|class).*)", REG_EXTENDED },
+	{ "python", "^[ \t]*((class|def)[ \t].*)$", REG_EXTENDED },
+	{ "ruby", "^[ \t]*((class|module|def)[ \t].*)$",
+	  REG_EXTENDED },
+	{ "bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
+	  REG_EXTENDED },
+	{ "tex",
+	  "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
+	  REG_EXTENDED },
 };
 
-static const char *diff_funcname_pattern(struct diff_filespec *one)
+static const struct funcname_pattern_entry *diff_funcname_pattern(struct diff_filespec *one)
 {
-	const char *ident, *pattern;
+	const char *ident;
+	const struct funcname_pattern_entry *pe;
 	int i;
 
 	diff_filespec_check_attr(one);
@@ -1450,9 +1464,9 @@ static const char *diff_funcname_pattern(struct diff_filespec *one)
 		return funcname_pattern("default");
 
 	/* Look up custom "funcname.$ident" regexp from config. */
-	pattern = funcname_pattern(ident);
-	if (pattern)
-		return pattern;
+	pe = funcname_pattern(ident);
+	if (pe)
+		return pe;
 
 	/*
 	 * And define built-in fallback patterns here.  Note that
@@ -1460,7 +1474,7 @@ static const char *diff_funcname_pattern(struct diff_filespec *one)
 	 */
 	for (i = 0; i < ARRAY_SIZE(builtin_funcname_pattern); i++)
 		if (!strcmp(ident, builtin_funcname_pattern[i].name))
-			return builtin_funcname_pattern[i].pattern;
+			return &builtin_funcname_pattern[i];
 
 	return NULL;
 }
@@ -1556,11 +1570,11 @@ static void builtin_diff(const char *name_a,
 		xdemitconf_t xecfg;
 		xdemitcb_t ecb;
 		struct emit_callback ecbdata;
-		const char *funcname_pattern;
+		const struct funcname_pattern_entry *pe;
 
-		funcname_pattern = diff_funcname_pattern(one);
-		if (!funcname_pattern)
-			funcname_pattern = diff_funcname_pattern(two);
+		pe = diff_funcname_pattern(one);
+		if (!pe)
+			pe = diff_funcname_pattern(two);
 
 		memset(&xecfg, 0, sizeof(xecfg));
 		memset(&ecbdata, 0, sizeof(ecbdata));
@@ -1572,8 +1586,8 @@ static void builtin_diff(const char *name_a,
 		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
 		xecfg.ctxlen = o->context;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
-		if (funcname_pattern)
-			xdiff_set_find_func(&xecfg, funcname_pattern);
+		if (pe)
+			xdiff_set_find_func(&xecfg, pe->pattern, pe->cflags);
 		if (!diffopts)
 			;
 		else if (!prefixcmp(diffopts, "--unified="))

dir.c

@@ -831,3 +831,23 @@ void setup_standard_excludes(struct dir_struct *dir)
 	if (excludes_file && !access(excludes_file, R_OK))
 		add_excludes_from_file(dir, excludes_file);
 }
+
+int remove_path(const char *name)
+{
+	char *slash;
+
+	if (unlink(name) && errno != ENOENT)
+		return -1;
+
+	slash = strrchr(name, '/');
+	if (slash) {
+		char *dirs = xstrdup(name);
+		slash = dirs + (slash - name);
+		do {
+			*slash = '\0';
+		} while (rmdir(dirs) && (slash = strrchr(dirs, '/')));
+		free(dirs);
+	}
+	return 0;
+}
+

dir.h

@@ -81,4 +81,7 @@ extern int is_inside_dir(const char *dir);
 extern void setup_standard_excludes(struct dir_struct *dir);
 extern int remove_dir_recursively(struct strbuf *path, int only_empty);
 
+/* tries to remove the path with empty directories along it, ignores ENOENT */
+extern int remove_path(const char *path);
+
 #endif

git-stash.sh

@@ -161,7 +161,7 @@ show_stash () {
 apply_stash () {
 	git update-index -q --refresh &&
 	git diff-files --quiet --ignore-submodules ||
-		die 'Cannot restore on top of a dirty state'
+		die 'Cannot apply to a dirty working tree, please stage your changes'
 
 	unstash_index=
 	case "$1" in

git-submodule.sh

@@ -194,7 +194,7 @@ cmd_add()
 	else
 
 		module_clone "$path" "$realrepo" || exit
-		(unset GIT_DIR; cd "$path" && git checkout -q ${branch:+-b "$branch" "origin/$branch"}) ||
+		(unset GIT_DIR; cd "$path" && git checkout -f -q ${branch:+-b "$branch" "origin/$branch"}) ||
 		die "Unable to checkout submodule '$path'"
 	fi
 
@@ -340,8 +340,13 @@ cmd_update()
 
 		if test "$subsha1" != "$sha1"
 		then
+			force=
+			if test -z "$subsha1"
+			then
+				force="-f"
+			fi
 			(unset GIT_DIR; cd "$path" && git-fetch &&
-				git-checkout -q "$sha1") ||
+				git-checkout $force -q "$sha1") ||
 			die "Unable to checkout '$sha1' in submodule path '$path'"
 
 			say "Submodule path '$path': checked out '$sha1'"

merge-recursive.c

@@ -19,6 +19,7 @@
 #include "interpolate.h"
 #include "attr.h"
 #include "merge-recursive.h"
+#include "dir.h"
 
 static struct tree *shift_tree_object(struct tree *one, struct tree *two)
 {
@@ -392,22 +393,6 @@ static int update_stages(const char *path, struct diff_filespec *o,
 	return 0;
 }
 
-static int remove_path(const char *name)
-{
-	char *slash, *dirs;
-
-	if (unlink(name))
-		return -1;
-	dirs = xstrdup(name);
-	while ((slash = strrchr(name, '/'))) {
-		*slash = '\0';
-		if (rmdir(name) != 0)
-			break;
-	}
-	free(dirs);
-	return 0;
-}
-
 static int remove_file(struct merge_options *o, int clean,
 		       const char *path, int no_wd)
 {

t/t4018-diff-funcname.sh

@@ -32,7 +32,18 @@ EOF
 
 sed 's/beer\\/beer,\\/' < Beer.java > Beer-correct.java
 
+builtin_patterns="bibtex html java pascal php python ruby tex"
+for p in $builtin_patterns
+do
+	test_expect_success "builtin $p pattern compiles" '
+		echo "*.java diff=$p" > .gitattributes &&
+		! ( git diff --no-index Beer.java Beer-correct.java 2>&1 |
+			grep "fatal" > /dev/null )
+	'
+done
+
 test_expect_success 'default behaviour' '
+	rm -f .gitattributes &&
 	git diff --no-index Beer.java Beer-correct.java |
 	grep "^@@.*@@ public class Beer"
 '
@@ -58,7 +69,7 @@ test_expect_success 'last regexp must not be negated' '
 '
 
 test_expect_success 'alternation in pattern' '
-	git config diff.java.funcname "^[ 	]*\\(\\(public\\|static\\).*\\)$"
+	git config diff.java.xfuncname "^[ 	]*((public|static).*)$" &&
 	git diff --no-index Beer.java Beer-correct.java |
 	grep "^@@.*@@ public static void main("
 '

xdiff-interface.c

@@ -194,31 +194,34 @@ static long ff_regexp(const char *line, long len,
 	char *line_buffer = xstrndup(line, len); /* make NUL terminated */
 	struct ff_regs *regs = priv;
 	regmatch_t pmatch[2];
-	int result = 0, i;
+	int i;
+	int result = -1;
 
 	for (i = 0; i < regs->nr; i++) {
 		struct ff_reg *reg = regs->array + i;
-		if (reg->negate ^ !!regexec(&reg->re,
-					line_buffer, 2, pmatch, 0)) {
-			free(line_buffer);
-			return -1;
+		if (!regexec(&reg->re, line_buffer, 2, pmatch, 0)) {
+			if (reg->negate)
+				goto fail;
+			break;
 		}
 	}
+	if (regs->nr <= i)
+		goto fail;
 	i = pmatch[1].rm_so >= 0 ? 1 : 0;
 	line += pmatch[i].rm_so;
 	result = pmatch[i].rm_eo - pmatch[i].rm_so;
 	if (result > buffer_size)
 		result = buffer_size;
 	else
-		while (result > 0 && (isspace(line[result - 1]) ||
-					line[result - 1] == '\n'))
+		while (result > 0 && (isspace(line[result - 1])))
 			result--;
 	memcpy(buffer, line, result);
+ fail:
 	free(line_buffer);
 	return result;
 }
 
-void xdiff_set_find_func(xdemitconf_t *xecfg, const char *value)
+void xdiff_set_find_func(xdemitconf_t *xecfg, const char *value, int cflags)
 {
 	int i;
 	struct ff_regs *regs;
@@ -243,7 +246,7 @@ void xdiff_set_find_func(xdemitconf_t *xecfg, const char *value)
 			expression = buffer = xstrndup(value, ep - value);
 		else
 			expression = value;
-		if (regcomp(&reg->re, expression, 0))
+		if (regcomp(&reg->re, expression, cflags))
 			die("Invalid regexp to look for hunk header: %s", expression);
 		free(buffer);
 		value = ep + 1;

xdiff-interface.h

@@ -16,7 +16,7 @@ int parse_hunk_header(char *line, int len,
 int read_mmfile(mmfile_t *ptr, const char *filename);
 int buffer_is_binary(const char *ptr, unsigned long size);
 
-extern void xdiff_set_find_func(xdemitconf_t *xecfg, const char *line);
+extern void xdiff_set_find_func(xdemitconf_t *xecfg, const char *line, int cflags);
 extern int git_xmerge_config(const char *var, const char *value, void *cb);
 extern int git_xmerge_style;