Merge branch 'jn/apply-filename-with-sp'

* jn/apply-filename-with-sp:
  apply: handle traditional patches with space in filename
  tests: exercise "git apply" with weird filenames
  apply: split quoted filename handling into new function

21 files changed, 456 insertions, 41 deletions

diff --git a/builtin/apply.c b/builtin/apply.c
index 470520bde..23c18c573 100644
--- a/builtin/apply.c
+++ b/builtin/apply.c
@@ -416,48 +416,190 @@ static char *squash_slash(char *name)
 	return name;
 }
 
-static char *find_name(const char *line, char *def, int p_value, int terminate)
+static char *find_name_gnu(const char *line, char *def, int p_value)
 {
-	int len;
-	const char *start = NULL;
+	struct strbuf name = STRBUF_INIT;
+	char *cp;
 
-	if (p_value == 0)
-		start = line;
+	/*
+	 * Proposed "new-style" GNU patch/diff format; see
+	 * http://marc.theaimsgroup.com/?l=git&m=112927316408690&w=2
+	 */
+	if (unquote_c_style(&name, line, NULL)) {
+		strbuf_release(&name);
+		return NULL;
+	}
 
-	if (*line == '"') {
-		struct strbuf name = STRBUF_INIT;
+	for (cp = name.buf; p_value; p_value--) {
+		cp = strchr(cp, '/');
+		if (!cp) {
+			strbuf_release(&name);
+			return NULL;
+		}
+		cp++;
+	}
 
-		/*
-		 * Proposed "new-style" GNU patch/diff format; see
-		 * http://marc.theaimsgroup.com/?l=git&m=112927316408690&w=2
-		 */
-		if (!unquote_c_style(&name, line, NULL)) {
-			char *cp;
+	/* name can later be freed, so we need
+	 * to memmove, not just return cp
+	 */
+	strbuf_remove(&name, 0, cp - name.buf);
+	free(def);
+	if (root)
+		strbuf_insert(&name, 0, root, root_len);
+	return squash_slash(strbuf_detach(&name, NULL));
+}
 
-			for (cp = name.buf; p_value; p_value--) {
-				cp = strchr(cp, '/');
-				if (!cp)
-					break;
-				cp++;
-			}
-			if (cp) {
-				/* name can later be freed, so we need
-				 * to memmove, not just return cp
-				 */
-				strbuf_remove(&name, 0, cp - name.buf);
-				free(def);
-				if (root)
-					strbuf_insert(&name, 0, root, root_len);
-				return squash_slash(strbuf_detach(&name, NULL));
-			}
-		}
-		strbuf_release(&name);
+static size_t tz_len(const char *line, size_t len)
+{
+	const char *tz, *p;
+
+	if (len < strlen(" +0500") || line[len-strlen(" +0500")] != ' ')
+		return 0;
+	tz = line + len - strlen(" +0500");
+
+	if (tz[1] != '+' && tz[1] != '-')
+		return 0;
+
+	for (p = tz + 2; p != line + len; p++)
+		if (!isdigit(*p))
+			return 0;
+
+	return line + len - tz;
+}
+
+static size_t date_len(const char *line, size_t len)
+{
+	const char *date, *p;
+
+	if (len < strlen("72-02-05") || line[len-strlen("-05")] != '-')
+		return 0;
+	p = date = line + len - strlen("72-02-05");
+
+	if (!isdigit(*p++) || !isdigit(*p++) || *p++ != '-' ||
+	    !isdigit(*p++) || !isdigit(*p++) || *p++ != '-' ||
+	    !isdigit(*p++) || !isdigit(*p++))	/* Not a date. */
+		return 0;
+
+	if (date - line >= strlen("19") &&
+	    isdigit(date[-1]) && isdigit(date[-2]))	/* 4-digit year */
+		date -= strlen("19");
+
+	return line + len - date;
+}
+
+static size_t short_time_len(const char *line, size_t len)
+{
+	const char *time, *p;
+
+	if (len < strlen(" 07:01:32") || line[len-strlen(":32")] != ':')
+		return 0;
+	p = time = line + len - strlen(" 07:01:32");
+
+	/* Permit 1-digit hours? */
+	if (*p++ != ' ' ||
+	    !isdigit(*p++) || !isdigit(*p++) || *p++ != ':' ||
+	    !isdigit(*p++) || !isdigit(*p++) || *p++ != ':' ||
+	    !isdigit(*p++) || !isdigit(*p++))	/* Not a time. */
+		return 0;
+
+	return line + len - time;
+}
+
+static size_t fractional_time_len(const char *line, size_t len)
+{
+	const char *p;
+	size_t n;
+
+	/* Expected format: 19:41:17.620000023 */
+	if (!len || !isdigit(line[len - 1]))
+		return 0;
+	p = line + len - 1;
+
+	/* Fractional seconds. */
+	while (p > line && isdigit(*p))
+		p--;
+	if (*p != '.')
+		return 0;
+
+	/* Hours, minutes, and whole seconds. */
+	n = short_time_len(line, p - line);
+	if (!n)
+		return 0;
+
+	return line + len - p + n;
+}
+
+static size_t trailing_spaces_len(const char *line, size_t len)
+{
+	const char *p;
+
+	/* Expected format: ' ' x (1 or more)  */
+	if (!len || line[len - 1] != ' ')
+		return 0;
+
+	p = line + len;
+	while (p != line) {
+		p--;
+		if (*p != ' ')
+			return line + len - (p + 1);
 	}
 
-	for (;;) {
+	/* All spaces! */
+	return len;
+}
+
+static size_t diff_timestamp_len(const char *line, size_t len)
+{
+	const char *end = line + len;
+	size_t n;
+
+	/*
+	 * Posix: 2010-07-05 19:41:17
+	 * GNU: 2010-07-05 19:41:17.620000023 -0500
+	 */
+
+	if (!isdigit(end[-1]))
+		return 0;
+
+	n = tz_len(line, end - line);
+	end -= n;
+
+	n = short_time_len(line, end - line);
+	if (!n)
+		n = fractional_time_len(line, end - line);
+	end -= n;
+
+	n = date_len(line, end - line);
+	if (!n)	/* No date.  Too bad. */
+		return 0;
+	end -= n;
+
+	if (end == line)	/* No space before date. */
+		return 0;
+	if (end[-1] == '\t') {	/* Success! */
+		end--;
+		return line + len - end;
+	}
+	if (end[-1] != ' ')	/* No space before date. */
+		return 0;
+
+	/* Whitespace damage. */
+	end -= trailing_spaces_len(line, end - line);
+	return line + len - end;
+}
+
+static char *find_name_common(const char *line, char *def, int p_value,
+				const char *end, int terminate)
+{
+	int len;
+	const char *start = NULL;
+
+	if (p_value == 0)
+		start = line;
+	while (line != end) {
 		char c = *line;
 
-		if (isspace(c)) {
+		if (!end && isspace(c)) {
 			if (c == '\n')
 				break;
 			if (name_terminate(start, line-start, c, terminate))
@@ -497,6 +639,37 @@ static char *find_name(const char *line, char *def, int p_value, int terminate)
 	return squash_slash(xmemdupz(start, len));
 }
 
+static char *find_name(const char *line, char *def, int p_value, int terminate)
+{
+	if (*line == '"') {
+		char *name = find_name_gnu(line, def, p_value);
+		if (name)
+			return name;
+	}
+
+	return find_name_common(line, def, p_value, NULL, terminate);
+}
+
+static char *find_name_traditional(const char *line, char *def, int p_value)
+{
+	size_t len = strlen(line);
+	size_t date_len;
+
+	if (*line == '"') {
+		char *name = find_name_gnu(line, def, p_value);
+		if (name)
+			return name;
+	}
+
+	len = strchrnul(line, '\n') - line;
+	date_len = diff_timestamp_len(line, len);
+	if (!date_len)
+		return find_name_common(line, def, p_value, NULL, TERM_TAB);
+	len -= date_len;
+
+	return find_name_common(line, def, p_value, line + len, 0);
+}
+
 static int count_slashes(const char *cp)
 {
 	int cnt = 0;
@@ -519,7 +692,7 @@ static int guess_p_value(const char *nameline)
 
 	if (is_dev_null(nameline))
 		return -1;
-	name = find_name(nameline, NULL, 0, TERM_SPACE | TERM_TAB);
+	name = find_name_traditional(nameline, NULL, 0);
 	if (!name)
 		return -1;
 	cp = strchr(name, '/');
@@ -638,16 +811,16 @@ static void parse_traditional_patch(const char *first, const char *second, struc
 	if (is_dev_null(first)) {
 		patch->is_new = 1;
 		patch->is_delete = 0;
-		name = find_name(second, NULL, p_value, TERM_SPACE | TERM_TAB);
+		name = find_name_traditional(second, NULL, p_value);
 		patch->new_name = name;
 	} else if (is_dev_null(second)) {
 		patch->is_new = 0;
 		patch->is_delete = 1;
-		name = find_name(first, NULL, p_value, TERM_SPACE | TERM_TAB);
+		name = find_name_traditional(first, NULL, p_value);
 		patch->old_name = name;
 	} else {
-		name = find_name(first, NULL, p_value, TERM_SPACE | TERM_TAB);
-		name = find_name(second, name, p_value, TERM_SPACE | TERM_TAB);
+		name = find_name_traditional(first, NULL, p_value);
+		name = find_name_traditional(second, name, p_value);
 		if (has_epoch_timestamp(first)) {
 			patch->is_new = 1;
 			patch->is_delete = 0;
diff --git a/t/t4120-apply-popt.sh b/t/t4120-apply-popt.sh
index b463b4f05..2b2d00b33 100755
--- a/t/t4120-apply-popt.sh
+++ b/t/t4120-apply-popt.sh
@@ -10,21 +10,50 @@ test_description='git apply -p handling.'
 test_expect_success setup '
 	mkdir sub &&
 	echo A >sub/file1 &&
-	cp sub/file1 file1 &&
+	cp sub/file1 file1.saved &&
 	git add sub/file1 &&
 	echo B >sub/file1 &&
 	git diff >patch.file &&
-	rm sub/file1 &&
-	rmdir sub
+	git checkout -- sub/file1 &&
+	git mv sub süb &&
+	echo B >süb/file1 &&
+	git diff >patch.escaped &&
+	grep "[\]" patch.escaped &&
+	rm süb/file1 &&
+	rmdir süb
 '
 
 test_expect_success 'apply git diff with -p2' '
+	cp file1.saved file1 &&
 	git apply -p2 patch.file
 '
 
 test_expect_success 'apply with too large -p' '
+	cp file1.saved file1 &&
 	test_must_fail git apply --stat -p3 patch.file 2>err &&
 	grep "removing 3 leading" err
 '
 
+test_expect_success 'apply (-p2) traditional diff with funny filenames' '
+	cat >patch.quotes <<-\EOF &&
+	diff -u "a/"sub/file1 "b/"sub/file1
+	--- "a/"sub/file1
+	+++ "b/"sub/file1
+	@@ -1 +1 @@
+	-A
+	+B
+	EOF
+	echo B >expected &&
+
+	cp file1.saved file1 &&
+	git apply -p2 patch.quotes &&
+	test_cmp expected file1
+'
+
+test_expect_success 'apply with too large -p and fancy filename' '
+	cp file1.saved file1 &&
+	test_must_fail git apply --stat -p3 patch.escaped 2>err &&
+	grep "removing 3 leading" err
+'
+
 test_done
diff --git a/t/t4135-apply-weird-filenames.sh b/t/t4135-apply-weird-filenames.sh
new file mode 100755
index 000000000..1e5aad57a
--- /dev/null
+++ b/t/t4135-apply-weird-filenames.sh
@@ -0,0 +1,75 @@
+#!/bin/sh
+
+test_description='git apply with weird postimage filenames'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	vector=$TEST_DIRECTORY/t4135 &&
+
+	test_tick &&
+	git commit --allow-empty -m preimage &&
+	git tag preimage &&
+
+	reset_preimage() {
+		git checkout -f preimage^0 &&
+		git read-tree -u --reset HEAD &&
+		git update-index --refresh
+	} &&
+
+	test_when_finished "rm -f \"tab	embedded.txt\"" &&
+	test_when_finished "rm -f '\''\"quoteembedded\".txt'\''" &&
+	if touch -- "tab	embedded.txt" '\''"quoteembedded".txt'\''
+	then
+		test_set_prereq FUNNYNAMES
+	fi
+'
+
+try_filename() {
+	desc=$1
+	postimage=$2
+	prereq=${3:-}
+	exp1=${4:-success}
+	exp2=${5:-success}
+	exp3=${6:-success}
+
+	test_expect_$exp1 $prereq "$desc, git-style file creation patch" "
+		echo postimage >expected &&
+		reset_preimage &&
+		rm -f '$postimage' &&
+		git apply -v \"\$vector\"/'git-$desc.diff' &&
+		test_cmp expected '$postimage'
+	"
+
+	test_expect_$exp2 $prereq "$desc, traditional patch" "
+		echo postimage >expected &&
+		reset_preimage &&
+		echo preimage >'$postimage' &&
+		git apply -v \"\$vector\"/'diff-$desc.diff' &&
+		test_cmp expected '$postimage'
+	"
+
+	test_expect_$exp3 $prereq "$desc, traditional file creation patch" "
+		echo postimage >expected &&
+		reset_preimage &&
+		rm -f '$postimage' &&
+		git apply -v \"\$vector\"/'add-$desc.diff' &&
+		test_cmp expected '$postimage'
+	"
+}
+
+try_filename 'plain'            'postimage.txt'
+try_filename 'with spaces'      'post image.txt'
+try_filename 'with tab'         'post	image.txt' FUNNYNAMES
+try_filename 'with backslash'   'post\image.txt' BSLASHPSPEC
+try_filename 'with quote'       '"postimage".txt' FUNNYNAMES success failure success
+
+test_expect_success 'whitespace-damaged traditional patch' '
+	echo postimage >expected &&
+	reset_preimage &&
+	rm -f postimage.txt &&
+	git apply -v "$vector/damaged.diff" &&
+	test_cmp expected postimage.txt
+'
+
+test_done
diff --git a/t/t4135/.gitignore b/t/t4135/.gitignore
new file mode 100644
index 000000000..3e58e65f5
--- /dev/null
+++ b/t/t4135/.gitignore
@@ -0,0 +1,3 @@
+/file-creation/
+/trad-creation/
+/trad-modification/
diff --git a/t/t4135/add-plain.diff b/t/t4135/add-plain.diff
new file mode 100644
index 000000000..cf5970a08
--- /dev/null
+++ b/t/t4135/add-plain.diff
@@ -0,0 +1,5 @@
+diff -pruN a/postimage.txt b/postimage.txt
+--- a/postimage.txt	1969-12-31 18:00:00.000000000 -0600
++++ b/postimage.txt	2010-08-18 20:13:31.484002255 -0500
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/add-with backslash.diff b/t/t4135/add-with backslash.diff
new file mode 100644
index 000000000..c6861e196
--- /dev/null
+++ b/t/t4135/add-with backslash.diff
@@ -0,0 +1,5 @@
+diff -pruN a/post\image.txt b/post\image.txt
+--- a/post\image.txt	1969-12-31 18:00:00.000000000 -0600
++++ b/post\image.txt	2010-08-18 20:13:31.692002255 -0500
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/add-with quote.diff b/t/t4135/add-with quote.diff
new file mode 100644
index 000000000..866de78ca
--- /dev/null
+++ b/t/t4135/add-with quote.diff
@@ -0,0 +1,5 @@
+diff -pruN a/"postimage".txt b/"postimage".txt
+--- a/"postimage".txt	1969-12-31 18:00:00.000000000 -0600
++++ b/"postimage".txt	2010-08-18 20:13:31.756002255 -0500
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/add-with spaces.diff b/t/t4135/add-with spaces.diff
new file mode 100644
index 000000000..a9a1212a2
--- /dev/null
+++ b/t/t4135/add-with spaces.diff
@@ -0,0 +1,5 @@
+diff -pruN a/post image.txt b/post image.txt
+--- a/post image.txt	1969-12-31 18:00:00.000000000 -0600
++++ b/post image.txt	2010-08-18 20:13:31.556002255 -0500
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/add-with tab.diff b/t/t4135/add-with tab.diff
new file mode 100644
index 000000000..bb67cb793
--- /dev/null
+++ b/t/t4135/add-with tab.diff
@@ -0,0 +1,5 @@
+diff -pruN a/post	image.txt b/post	image.txt
+--- a/post	image.txt	1969-12-31 18:00:00.000000000 -0600
++++ b/post	image.txt	2010-08-18 20:13:31.628002255 -0500
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/damaged.diff b/t/t4135/damaged.diff
new file mode 100644
index 000000000..68f7ededf
--- /dev/null
+++ b/t/t4135/damaged.diff
@@ -0,0 +1,5 @@
+diff -pruN a/postimage.txt b/postimage.txt
+--- a/postimage.txt     1969-12-31 18:00:00.000000000 -0600
++++ b/postimage.txt     2010-08-18 20:13:31.484002255 -0500
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/diff-plain.diff b/t/t4135/diff-plain.diff
new file mode 100644
index 000000000..acedcfa61
--- /dev/null
+++ b/t/t4135/diff-plain.diff
@@ -0,0 +1,5 @@
+--- postimage.txt.orig	2010-08-18 20:13:31.432002255 -0500
++++ postimage.txt	2010-08-18 20:13:31.432002255 -0500
+@@ -1 +1 @@
+-preimage
++postimage
diff --git a/t/t4135/diff-with backslash.diff b/t/t4135/diff-with backslash.diff
new file mode 100644
index 000000000..9068a61bd
--- /dev/null
+++ b/t/t4135/diff-with backslash.diff
@@ -0,0 +1,5 @@
+--- post\image.txt.orig	2010-08-18 20:13:31.680002255 -0500
++++ post\image.txt	2010-08-18 20:13:31.680002255 -0500
+@@ -1 +1 @@
+-preimage
++postimage
diff --git a/t/t4135/diff-with quote.diff b/t/t4135/diff-with quote.diff
new file mode 100644
index 000000000..c8e8cc1a8
--- /dev/null
+++ b/t/t4135/diff-with quote.diff
@@ -0,0 +1,5 @@
+--- "postimage".txt.orig	2010-08-18 20:13:31.744002255 -0500
++++ "postimage".txt	2010-08-18 20:13:31.744002255 -0500
+@@ -1 +1 @@
+-preimage
++postimage
diff --git a/t/t4135/diff-with spaces.diff b/t/t4135/diff-with spaces.diff
new file mode 100644
index 000000000..3512056f2
--- /dev/null
+++ b/t/t4135/diff-with spaces.diff
@@ -0,0 +1,5 @@
+--- post image.txt.orig	2010-08-18 20:13:31.544002255 -0500
++++ post image.txt	2010-08-18 20:13:31.544002255 -0500
+@@ -1 +1 @@
+-preimage
++postimage
diff --git a/t/t4135/diff-with tab.diff b/t/t4135/diff-with tab.diff
new file mode 100644
index 000000000..4e6d9b294
--- /dev/null
+++ b/t/t4135/diff-with tab.diff
@@ -0,0 +1,5 @@
+--- post	image.txt.orig	2010-08-18 20:13:31.616002255 -0500
++++ post	image.txt	2010-08-18 20:13:31.616002255 -0500
+@@ -1 +1 @@
+-preimage
++postimage
diff --git a/t/t4135/git-plain.diff b/t/t4135/git-plain.diff
new file mode 100644
index 000000000..db47d1a69
--- /dev/null
+++ b/t/t4135/git-plain.diff
@@ -0,0 +1,7 @@
+diff --git a/postimage.txt b/postimage.txt
+new file mode 100644
+index 0000000..eff0c54
+--- /dev/null
++++ b/postimage.txt
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/git-with backslash.diff b/t/t4135/git-with backslash.diff
new file mode 100644
index 000000000..0e84a10e9
--- /dev/null
+++ b/t/t4135/git-with backslash.diff
@@ -0,0 +1,7 @@
+diff --git "a/post\\image.txt" "b/post\\image.txt"
+new file mode 100644
+index 0000000..eff0c54
+--- /dev/null
++++ "b/post\\image.txt"
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/git-with quote.diff b/t/t4135/git-with quote.diff
new file mode 100644
index 000000000..bdbea8af3
--- /dev/null
+++ b/t/t4135/git-with quote.diff
@@ -0,0 +1,7 @@
+diff --git "a/\"postimage\".txt" "b/\"postimage\".txt"
+new file mode 100644
+index 0000000..eff0c54
+--- /dev/null
++++ "b/\"postimage\".txt"
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/git-with spaces.diff b/t/t4135/git-with spaces.diff
new file mode 100644
index 000000000..baaa810de
--- /dev/null
+++ b/t/t4135/git-with spaces.diff
@@ -0,0 +1,7 @@
+diff --git a/post image.txt b/post image.txt
+new file mode 100644
+index 0000000..eff0c54
+--- /dev/null
++++ b/post image.txt	
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/git-with tab.diff b/t/t4135/git-with tab.diff
new file mode 100644
index 000000000..cca3c9287
--- /dev/null
+++ b/t/t4135/git-with tab.diff
@@ -0,0 +1,7 @@
+diff --git "a/post\timage.txt" "b/post\timage.txt"
+new file mode 100644
+index 0000000..eff0c54
+--- /dev/null
++++ "b/post\timage.txt"
+@@ -0,0 +1 @@
++postimage
diff --git a/t/t4135/make-patches b/t/t4135/make-patches
new file mode 100755
index 000000000..f5f45ddd0
--- /dev/null
+++ b/t/t4135/make-patches
@@ -0,0 +1,45 @@
+#!/bin/sh
+
+do_filename() {
+	desc=$1
+	postimage=$2
+
+	rm -fr file-creation &&
+	git init file-creation &&
+	(
+		cd file-creation &&
+		git commit --allow-empty -m init &&
+		echo postimage >"$postimage" &&
+		git add -N "$postimage" &&
+		git diff HEAD >"../git-$desc.diff"
+	) &&
+
+	rm -fr trad-modification &&
+	mkdir trad-modification &&
+	(
+		cd trad-modification &&
+		echo preimage >"$postimage.orig" &&
+		echo postimage >"$postimage" &&
+		! diff -u "$postimage.orig" "$postimage" >"../diff-$desc.diff"
+	) &&
+
+	rm -fr trad-creation &&
+	mkdir trad-creation &&
+	(
+		cd trad-creation &&
+		mkdir a b &&
+		echo postimage >"b/$postimage" &&
+		! diff -pruN a b >"../add-$desc.diff"
+	)
+}
+
+do_filename plain postimage.txt &&
+do_filename 'with spaces' 'post image.txt' &&
+do_filename 'with tab' 'post	image.txt' &&
+do_filename 'with backslash' 'post\image.txt' &&
+do_filename 'with quote' '"postimage".txt' &&
+expand add-plain.diff >damaged.diff ||
+{
+	echo >&2 Failed. &&
+	exit 1
+}