Merge branch 'rs/xdiff-hunk-with-func-line' into maint

"git show -W" (extend hunks to cover the entire function, delimited
by lines that match the "funcname" pattern) used to show the entire
file when a change added an entire function at the end of the file,
which has been fixed.

* rs/xdiff-hunk-with-func-line:
  xdiff: fix merging of appended hunk with -W
  grep: -W: don't extend context to trailing empty lines
  t7810: add test for grep -W and trailing empty context lines
  xdiff: don't trim common tail with -W
  xdiff: -W: don't include common trailing empty lines in context
  xdiff: ignore empty lines before added functions with -W
  xdiff: handle appended chunks better with -W
  xdiff: factor out match_func_rec()
  t4051: rewrite, add more tests

7 files changed, 278 insertions, 77 deletions

diff --git a/t/t4051-diff-function-context.sh b/t/t4051-diff-function-context.sh
index 001d678e0..b79b87790 100755
--- a/t/t4051-diff-function-context.sh
+++ b/t/t4051-diff-function-context.sh
@@ -3,90 +3,180 @@
 test_description='diff function context'
 
 . ./test-lib.sh
-. "$TEST_DIRECTORY"/diff-lib.sh
 
+dir="$TEST_DIRECTORY/t4051"
 
-cat <<\EOF >hello.c
-#include <stdio.h>
-
-static int a(void)
-{
-	/*
-	 * Dummy.
-	 */
+commit_and_tag () {
+	tag=$1 &&
+	shift &&
+	git add "$@" &&
+	test_tick &&
+	git commit -m "$tag" &&
+	git tag "$tag"
 }
 
-static int hello_world(void)
-{
-	/* Classic. */
-	printf("Hello world.\n");
-
-	/* Success! */
-	return 0;
+first_context_line () {
+	awk '
+		found {print; exit}
+		/^@@/ {found = 1}
+	'
 }
-static int b(void)
-{
-	/*
-	 * Dummy, too.
-	 */
+
+last_context_line () {
+	sed -ne \$p
 }
 
-int main(int argc, char **argv)
-{
-	a();
-	b();
-	return hello_world();
+check_diff () {
+	name=$1
+	desc=$2
+	options="-W $3"
+
+	test_expect_success "$desc" '
+		git diff $options "$name^" "$name" >"$name.diff"
+	'
+
+	test_expect_success ' diff applies' '
+		test_when_finished "git reset --hard" &&
+		git checkout --detach "$name^" &&
+		git apply --index "$name.diff" &&
+		git diff --exit-code "$name"
+	'
 }
-EOF
 
 test_expect_success 'setup' '
-	git add hello.c &&
-	test_tick &&
-	git commit -m initial &&
-
-	grep -v Classic <hello.c >hello.c.new &&
-	mv hello.c.new hello.c
-'
-
-cat <<\EOF >expected
-diff --git a/hello.c b/hello.c
---- a/hello.c
-+++ b/hello.c
-@@ -10,8 +10,7 @@ static int a(void)
- static int hello_world(void)
- {
--	/* Classic. */
- 	printf("Hello world.\n");
- 
- 	/* Success! */
- 	return 0;
- }
-EOF
-
-test_expect_success 'diff -U0 -W' '
-	git diff -U0 -W >actual &&
-	compare_diff_patch actual expected
-'
-
-cat <<\EOF >expected
-diff --git a/hello.c b/hello.c
---- a/hello.c
-+++ b/hello.c
-@@ -9,9 +9,8 @@ static int a(void)
- 
- static int hello_world(void)
- {
--	/* Classic. */
- 	printf("Hello world.\n");
- 
- 	/* Success! */
- 	return 0;
- }
-EOF
-
-test_expect_success 'diff -W' '
-	git diff -W >actual &&
-	compare_diff_patch actual expected
+	cat "$dir/includes.c" "$dir/dummy.c" "$dir/dummy.c" "$dir/hello.c" \
+		"$dir/dummy.c" "$dir/dummy.c" >file.c &&
+	commit_and_tag initial file.c &&
+
+	grep -v "delete me from hello" <file.c >file.c.new &&
+	mv file.c.new file.c &&
+	commit_and_tag changed_hello file.c &&
+
+	grep -v "delete me from includes" <file.c >file.c.new &&
+	mv file.c.new file.c &&
+	commit_and_tag changed_includes file.c &&
+
+	cat "$dir/appended1.c" >>file.c &&
+	commit_and_tag appended file.c &&
+
+	cat "$dir/appended2.c" >>file.c &&
+	commit_and_tag extended file.c &&
+
+	grep -v "Begin of second part" <file.c >file.c.new &&
+	mv file.c.new file.c &&
+	commit_and_tag long_common_tail file.c &&
+
+	git checkout initial &&
+	grep -v "delete me from hello" <file.c >file.c.new &&
+	mv file.c.new file.c &&
+	cat "$dir/appended1.c" >>file.c &&
+	commit_and_tag changed_hello_appended file.c
+'
+
+check_diff changed_hello 'changed function'
+
+test_expect_success ' context includes begin' '
+	grep "^ .*Begin of hello" changed_hello.diff
+'
+
+test_expect_success ' context includes end' '
+	grep "^ .*End of hello" changed_hello.diff
+'
+
+test_expect_success ' context does not include other functions' '
+	test $(grep -c "^[ +-].*Begin" changed_hello.diff) -le 1
+'
+
+test_expect_success ' context does not include preceding empty lines' '
+	test "$(first_context_line <changed_hello.diff)" != " "
+'
+
+test_expect_success ' context does not include trailing empty lines' '
+	test "$(last_context_line <changed_hello.diff)" != " "
+'
+
+check_diff changed_includes 'changed includes'
+
+test_expect_success ' context includes begin' '
+	grep "^ .*Begin.h" changed_includes.diff
+'
+
+test_expect_success ' context includes end' '
+	grep "^ .*End.h" changed_includes.diff
+'
+
+test_expect_success ' context does not include other functions' '
+	test $(grep -c "^[ +-].*Begin" changed_includes.diff) -le 1
+'
+
+test_expect_success ' context does not include trailing empty lines' '
+	test "$(last_context_line <changed_includes.diff)" != " "
+'
+
+check_diff appended 'appended function'
+
+test_expect_success ' context includes begin' '
+	grep "^[+].*Begin of first part" appended.diff
+'
+
+test_expect_success ' context includes end' '
+	grep "^[+].*End of first part" appended.diff
+'
+
+test_expect_success ' context does not include other functions' '
+	test $(grep -c "^[ +-].*Begin" appended.diff) -le 1
+'
+
+check_diff extended 'appended function part'
+
+test_expect_success ' context includes begin' '
+	grep "^ .*Begin of first part" extended.diff
+'
+
+test_expect_success ' context includes end' '
+	grep "^[+].*End of second part" extended.diff
+'
+
+test_expect_success ' context does not include other functions' '
+	test $(grep -c "^[ +-].*Begin" extended.diff) -le 2
+'
+
+test_expect_success ' context does not include preceding empty lines' '
+	test "$(first_context_line <extended.diff)" != " "
+'
+
+check_diff long_common_tail 'change with long common tail and no context' -U0
+
+test_expect_success ' context includes begin' '
+	grep "^ .*Begin of first part" long_common_tail.diff
+'
+
+test_expect_success ' context includes end' '
+	grep "^ .*End of second part" long_common_tail.diff
+'
+
+test_expect_success ' context does not include other functions' '
+	test $(grep -c "^[ +-].*Begin" long_common_tail.diff) -le 2
+'
+
+test_expect_success ' context does not include preceding empty lines' '
+	test "$(first_context_line <long_common_tail.diff.diff)" != " "
+'
+
+check_diff changed_hello_appended 'changed function plus appended function'
+
+test_expect_success ' context includes begin' '
+	grep "^ .*Begin of hello" changed_hello_appended.diff &&
+	grep "^[+].*Begin of first part" changed_hello_appended.diff
+'
+
+test_expect_success ' context includes end' '
+	grep "^ .*End of hello" changed_hello_appended.diff &&
+	grep "^[+].*End of first part" changed_hello_appended.diff
+'
+
+test_expect_success ' context does not include other functions' '
+	test $(grep -c "^[ +-].*Begin" changed_hello_appended.diff) -le 2
 '
 
 test_done
diff --git a/t/t4051/appended1.c b/t/t4051/appended1.c
new file mode 100644
index 000000000..a9f56f11d
--- /dev/null
+++ b/t/t4051/appended1.c
@@ -0,0 +1,15 @@
+
+int appended(void) // Begin of first part
+{
+	int i;
+	char *s = "a string";
+
+	printf("%s\n", s);
+
+	for (i = 99;
+	     i >= 0;
+	     i--) {
+		printf("%d bottles of beer on the wall\n", i);
+	}
+
+	printf("End of first part\n");
diff --git a/t/t4051/appended2.c b/t/t4051/appended2.c
new file mode 100644
index 000000000..e651f7147
--- /dev/null
+++ b/t/t4051/appended2.c
@@ -0,0 +1,35 @@
+	printf("Begin of second part\n");
+
+	/*
+	 * Lorem ipsum dolor sit amet, consectetuer sadipscing elitr,
+	 * sed diam nonumy eirmod tempor invidunt ut labore et dolore
+	 * magna aliquyam erat, sed diam voluptua. At vero eos et
+	 * accusam et justo duo dolores et ea rebum. Stet clita kasd
+	 * gubergren, no sea takimata sanctus est Lorem ipsum dolor
+	 * sit amet.
+	 *
+	 * Lorem ipsum dolor sit amet, consectetuer sadipscing elitr,
+	 * sed diam nonumy eirmod tempor invidunt ut labore et dolore
+	 * magna aliquyam erat, sed diam voluptua. At vero eos et
+	 * accusam et justo duo dolores et ea rebum. Stet clita kasd
+	 * gubergren, no sea takimata sanctus est Lorem ipsum dolor
+	 * sit amet.
+	 *
+	 * Lorem ipsum dolor sit amet, consectetuer sadipscing elitr,
+	 * sed diam nonumy eirmod tempor invidunt ut labore et dolore
+	 * magna aliquyam erat, sed diam voluptua. At vero eos et
+	 * accusam et justo duo dolores et ea rebum. Stet clita kasd
+	 * gubergren, no sea takimata sanctus est Lorem ipsum dolor
+	 * sit amet.
+	 *
+	 * Lorem ipsum dolor sit amet, consectetuer sadipscing elitr,
+	 * sed diam nonumy eirmod tempor invidunt ut labore et dolore
+	 * magna aliquyam erat, sed diam voluptua. At vero eos et
+	 * accusam et justo duo dolores et ea rebum. Stet clita kasd
+	 * gubergren, no sea takimata sanctus est Lorem ipsum dolor
+	 * sit amet.
+	 *
+	 */
+
+	return 0;
+}	// End of second part
diff --git a/t/t4051/dummy.c b/t/t4051/dummy.c
new file mode 100644
index 000000000..a43016e87
--- /dev/null
+++ b/t/t4051/dummy.c
@@ -0,0 +1,7 @@
+
+static int dummy(void)	// Begin of dummy
+{
+	int rc = 0;
+
+	return rc;
+}	// End of dummy
diff --git a/t/t4051/hello.c b/t/t4051/hello.c
new file mode 100644
index 000000000..63b1a1e4e
--- /dev/null
+++ b/t/t4051/hello.c
@@ -0,0 +1,21 @@
+
+static void hello(void)	// Begin of hello
+{
+	/*
+	 * Classic.
+	 */
+	putchar('H');
+	putchar('e');
+	putchar('l');
+	putchar('l');
+	putchar('o');
+	putchar(' ');
+	/* delete me from hello */
+	putchar('w');
+	putchar('o');
+	putchar('r');
+	putchar('l');
+	putchar('d');
+	putchar('.');
+	putchar('\n');
+}	// End of hello
diff --git a/t/t4051/includes.c b/t/t4051/includes.c
new file mode 100644
index 000000000..efc68f8bf
--- /dev/null
+++ b/t/t4051/includes.c
@@ -0,0 +1,20 @@
+#include <Begin.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdarg.h>
+/* delete me from includes */
+#include <string.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <sys/time.h>
+#include <time.h>
+#include <signal.h>
+#include <assert.h>
+#include <regex.h>
+#include <utime.h>
+#include <syslog.h>
+#include <End.h>
diff --git a/t/t7810-grep.sh b/t/t7810-grep.sh
index 1e72971a1..960425a4e 100755
--- a/t/t7810-grep.sh
+++ b/t/t7810-grep.sh
@@ -9,7 +9,9 @@ test_description='git grep various.
 . ./test-lib.sh
 
 cat >hello.c <<EOF
+#include <assert.h>
 #include <stdio.h>
+
 int main(int argc, const char **argv)
 {
 	printf("Hello world.\n");
@@ -715,6 +717,7 @@ test_expect_success 'grep -p' '
 
 cat >expected <<EOF
 hello.c-#include <stdio.h>
+hello.c-
 hello.c=int main(int argc, const char **argv)
 hello.c-{
 hello.c-	printf("Hello world.\n");
@@ -741,6 +744,16 @@ test_expect_success 'grep -W' '
 '
 
 cat >expected <<EOF
+hello.c-#include <assert.h>
+hello.c:#include <stdio.h>
+EOF
+
+test_expect_success 'grep -W shows no trailing empty lines' '
+	git grep -W stdio >actual &&
+	test_cmp expected actual
+'
+
+cat >expected <<EOF
 hello.c=	printf("Hello world.\n");
 hello.c:	return 0;
 hello.c-	/* char ?? */
@@ -1232,8 +1245,8 @@ test_expect_success 'grep --heading' '
 
 cat >expected <<EOF
 <BOLD;GREEN>hello.c<RESET>
-2:int main(int argc, const <BLACK;BYELLOW>char<RESET> **argv)
-6:	/* <BLACK;BYELLOW>char<RESET> ?? */
+4:int main(int argc, const <BLACK;BYELLOW>char<RESET> **argv)
+8:	/* <BLACK;BYELLOW>char<RESET> ?? */
 
 <BOLD;GREEN>hello_world<RESET>
 3:Hel<BLACK;BYELLOW>lo_w<RESET>orld
@@ -1340,7 +1353,7 @@ test_expect_success 'grep --color -e A --and --not -e B with context' '
 '
 
 cat >expected <<EOF
-hello.c-#include <stdio.h>
+hello.c-
 hello.c=int main(int argc, const char **argv)
 hello.c-{
 hello.c:	pr<RED>int<RESET>f("<RED>Hello<RESET> world.\n");