Merge branch 'jc/mailinfo-scissors'

* jc/mailinfo-scissors:
  mailinfo.scissors: new configuration
  am/mailinfo: Disable scissors processing by default
  Documentation: describe the scissors mark support of "git am"
  Teach mailinfo to ignore everything before -- >8 -- mark
  builtin-mailinfo.c: fix confusing internal API to mailinfo()

12 files changed, 395 insertions, 27 deletions

diff --git a/Documentation/git-am.txt b/Documentation/git-am.txt
index fcacc9465..87781f4a7 100644
--- a/Documentation/git-am.txt
+++ b/Documentation/git-am.txt
@@ -13,7 +13,7 @@ SYNOPSIS
 	 [--3way] [--interactive] [--committer-date-is-author-date]
 	 [--ignore-date] [--ignore-space-change | --ignore-whitespace]
 	 [--whitespace=<option>] [-C<n>] [-p<n>] [--directory=<dir>]
-	 [--reject] [-q | --quiet]
+	 [--reject] [-q | --quiet] [--scissors]
 	 [<mbox> | <Maildir>...]
 'git am' (--skip | --resolved | --abort)
 
@@ -39,6 +39,11 @@ OPTIONS
 --keep::
 	Pass `-k` flag to 'git-mailinfo' (see linkgit:git-mailinfo[1]).
 
+-c::
+--scissors::
+	Remove everything in body before a scissors line (see
+	linkgit:git-mailinfo[1]).
+
 -q::
 --quiet::
 	Be quiet. Only print error messages.
@@ -128,10 +133,8 @@ the commit, after stripping common prefix "[PATCH <anything>]".
 The "Subject: " line is supposed to concisely describe what the
 commit is about in one line of text.
 
-"From: " and "Subject: " lines starting the body (the rest of the
-message after the blank line terminating the RFC2822 headers)
-override the respective commit author name and title values taken
-from the headers.
+"From: " and "Subject: " lines starting the body override the respective
+commit author name and title values taken from the headers.
 
 The commit message is formed by the title taken from the
 "Subject: ", a blank line and the body of the message up to
diff --git a/Documentation/git-mailinfo.txt b/Documentation/git-mailinfo.txt
index 8d95aaa30..823ab82b5 100644
--- a/Documentation/git-mailinfo.txt
+++ b/Documentation/git-mailinfo.txt
@@ -8,7 +8,7 @@ git-mailinfo - Extracts patch and authorship from a single e-mail message
 
 SYNOPSIS
 --------
-'git mailinfo' [-k] [-u | --encoding=<encoding> | -n] <msg> <patch>
+'git mailinfo' [-k] [-u | --encoding=<encoding> | -n] [--scissors] <msg> <patch>
 
 
 DESCRIPTION
@@ -49,6 +49,20 @@ conversion, even with this flag.
 -n::
 	Disable all charset re-coding of the metadata.
 
+--scissors::
+	Remove everything in body before a scissors line.  A line that
+	mainly consists of scissors (either ">8" or "8<") and perforation
+	(dash "-") marks is called a scissors line, and is used to request
+	the reader to cut the message at that line.  If such a line
+	appears in the body of the message before the patch, everything
+	before it (including the scissors line itself) is ignored when
+	this option is used.
++
+This is useful if you want to begin your message in a discussion thread
+with comments and suggestions on the message you are responding to, and to
+conclude it with a patch submission, separating the discussion and the
+beginning of the proposed commit log message with a scissors line.
+
 <msg>::
 	The commit log message extracted from e-mail, usually
 	except the title line which comes from e-mail Subject.
diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
index b0b5d8f6c..03cbcad1f 100644
--- a/builtin-mailinfo.c
+++ b/builtin-mailinfo.c
@@ -25,6 +25,7 @@ static enum  {
 static struct strbuf charset = STRBUF_INIT;
 static int patch_lines;
 static struct strbuf **p_hdr_data, **s_hdr_data;
+static int use_scissors;
 
 #define MAX_HDR_PARSED 10
 #define MAX_BOUNDARIES 5
@@ -712,6 +713,56 @@ static inline int patchbreak(const struct strbuf *line)
 	return 0;
 }
 
+static int is_scissors_line(const struct strbuf *line)
+{
+	size_t i, len = line->len;
+	int scissors = 0, gap = 0;
+	int first_nonblank = -1;
+	int last_nonblank = 0, visible, perforation = 0, in_perforation = 0;
+	const char *buf = line->buf;
+
+	for (i = 0; i < len; i++) {
+		if (isspace(buf[i])) {
+			if (in_perforation) {
+				perforation++;
+				gap++;
+			}
+			continue;
+		}
+		last_nonblank = i;
+		if (first_nonblank < 0)
+			first_nonblank = i;
+		if (buf[i] == '-') {
+			in_perforation = 1;
+			perforation++;
+			continue;
+		}
+		if (i + 1 < len &&
+		    (!memcmp(buf + i, ">8", 2) || !memcmp(buf + i, "8<", 2))) {
+			in_perforation = 1;
+			perforation += 2;
+			scissors += 2;
+			i++;
+			continue;
+		}
+		in_perforation = 0;
+	}
+
+	/*
+	 * The mark must be at least 8 bytes long (e.g. "-- >8 --").
+	 * Even though there can be arbitrary cruft on the same line
+	 * (e.g. "cut here"), in order to avoid misidentification, the
+	 * perforation must occupy more than a third of the visible
+	 * width of the line, and dashes and scissors must occupy more
+	 * than half of the perforation.
+	 */
+
+	visible = last_nonblank - first_nonblank + 1;
+	return (scissors && 8 <= visible &&
+		visible < perforation * 3 &&
+		gap * 2 < perforation);
+}
+
 static int handle_commit_msg(struct strbuf *line)
 {
 	static int still_looking = 1;
@@ -723,7 +774,8 @@ static int handle_commit_msg(struct strbuf *line)
 		strbuf_ltrim(line);
 		if (!line->len)
 			return 0;
-		if ((still_looking = check_header(line, s_hdr_data, 0)) != 0)
+		still_looking = check_header(line, s_hdr_data, 0);
+		if (still_looking)
 			return 0;
 	}
 
@@ -731,6 +783,24 @@ static int handle_commit_msg(struct strbuf *line)
 	if (metainfo_charset)
 		convert_to_utf8(line, charset.buf);
 
+	if (use_scissors && is_scissors_line(line)) {
+		int i;
+		rewind(cmitmsg);
+		ftruncate(fileno(cmitmsg), 0);
+		still_looking = 1;
+
+		/*
+		 * We may have already read "secondary headers"; purge
+		 * them to give ourselves a clean restart.
+		 */
+		for (i = 0; header[i]; i++) {
+			if (s_hdr_data[i])
+				strbuf_release(s_hdr_data[i]);
+			s_hdr_data[i] = NULL;
+		}
+		return 0;
+	}
+
 	if (patchbreak(line)) {
 		fclose(cmitmsg);
 		cmitmsg = NULL;
@@ -885,12 +955,9 @@ static void handle_info(void)
 	fprintf(fout, "\n");
 }
 
-static int mailinfo(FILE *in, FILE *out, int ks, const char *encoding,
-		    const char *msg, const char *patch)
+static int mailinfo(FILE *in, FILE *out, const char *msg, const char *patch)
 {
 	int peek;
-	keep_subject = ks;
-	metainfo_charset = encoding;
 	fin = in;
 	fout = out;
 
@@ -924,6 +991,18 @@ static int mailinfo(FILE *in, FILE *out, int ks, const char *encoding,
 	return 0;
 }
 
+static int git_mailinfo_config(const char *var, const char *value, void *unused)
+{
+	if (prefixcmp(var, "mailinfo."))
+		return git_default_config(var, value, unused);
+	if (!strcmp(var, "mailinfo.scissors")) {
+		use_scissors = git_config_bool(var, value);
+		return 0;
+	}
+	/* perhaps others here */
+	return 0;
+}
+
 static const char mailinfo_usage[] =
 	"git mailinfo [-k] [-u | --encoding=<encoding> | -n] msg patch <mail >info";
 
@@ -934,7 +1013,7 @@ int cmd_mailinfo(int argc, const char **argv, const char *prefix)
 	/* NEEDSWORK: might want to do the optional .git/ directory
 	 * discovery
 	 */
-	git_config(git_default_config, NULL);
+	git_config(git_mailinfo_config, NULL);
 
 	def_charset = (git_commit_encoding ? git_commit_encoding : "UTF-8");
 	metainfo_charset = def_charset;
@@ -948,6 +1027,10 @@ int cmd_mailinfo(int argc, const char **argv, const char *prefix)
 			metainfo_charset = NULL;
 		else if (!prefixcmp(argv[1], "--encoding="))
 			metainfo_charset = argv[1] + 11;
+		else if (!strcmp(argv[1], "--scissors"))
+			use_scissors = 1;
+		else if (!strcmp(argv[1], "--no-scissors"))
+			use_scissors = 0;
 		else
 			usage(mailinfo_usage);
 		argc--; argv++;
@@ -956,5 +1039,5 @@ int cmd_mailinfo(int argc, const char **argv, const char *prefix)
 	if (argc != 3)
 		usage(mailinfo_usage);
 
-	return !!mailinfo(stdin, stdout, keep_subject, metainfo_charset, argv[1], argv[2]);
+	return !!mailinfo(stdin, stdout, argv[1], argv[2]);
 }
diff --git a/git-am.sh b/git-am.sh
index 3c03f3e0d..26ffe702e 100755
--- a/git-am.sh
+++ b/git-am.sh
@@ -15,6 +15,7 @@ q,quiet         be quiet
 s,signoff       add a Signed-off-by line to the commit message
 u,utf8          recode into utf8 (default)
 k,keep          pass -k flag to git-mailinfo
+c,scissors      strip everything before a scissors line
 whitespace=     pass it through git-apply
 ignore-space-change pass it through git-apply
 ignore-whitespace pass it through git-apply
@@ -288,7 +289,7 @@ split_patches () {
 prec=4
 dotest="$GIT_DIR/rebase-apply"
 sign= utf8=t keep= skip= interactive= resolved= rebasing= abort=
-resolvemsg= resume=
+resolvemsg= resume= scissors=
 git_apply_opt=
 committer_date_is_author_date=
 ignore_date=
@@ -310,6 +311,10 @@ do
 		utf8= ;;
 	-k|--keep)
 		keep=t ;;
+	-c|--scissors)
+		scissors=t ;;
+	--no-scissors)
+		scissors=f ;;
 	-r|--resolved)
 		resolved=t ;;
 	--skip)
@@ -317,7 +322,7 @@ do
 	--abort)
 		abort=t ;;
 	--rebasing)
-		rebasing=t threeway=t keep=t ;;
+		rebasing=t threeway=t keep=t scissors=f ;;
 	-d|--dotest)
 		die "-d option is no longer supported.  Do not use."
 		;;
@@ -435,14 +440,14 @@ else
 
 	split_patches "$@"
 
-	# -s, -u, -k, --whitespace, -3, -C, -q and -p flags are kept
-	# for the resuming session after a patch failure.
-	# -i can and must be given when resuming.
+	# -i can and must be given when resuming; everything
+	# else is kept
 	echo " $git_apply_opt" >"$dotest/apply-opt"
 	echo "$threeway" >"$dotest/threeway"
 	echo "$sign" >"$dotest/sign"
 	echo "$utf8" >"$dotest/utf8"
 	echo "$keep" >"$dotest/keep"
+	echo "$scissors" >"$dotest/scissors"
 	echo "$GIT_QUIET" >"$dotest/quiet"
 	echo 1 >"$dotest/next"
 	if test -n "$rebasing"
@@ -484,6 +489,12 @@ if test "$(cat "$dotest/keep")" = t
 then
 	keep=-k
 fi
+case "$(cat "$dotest/scissors")" in
+t)
+	scissors=--scissors ;;
+f)
+	scissors=--no-scissors ;;
+esac
 if test "$(cat "$dotest/quiet")" = t
 then
 	GIT_QUIET=t
@@ -538,7 +549,7 @@ do
 	# by the user, or the user can tell us to do so by --resolved flag.
 	case "$resume" in
 	'')
-		git mailinfo $keep $utf8 "$dotest/msg" "$dotest/patch" \
+		git mailinfo $keep $scissors $utf8 "$dotest/msg" "$dotest/patch" \
 			<"$dotest/$msgnum" >"$dotest/info" ||
 			stop_here $this
 
diff --git a/t/t5100-mailinfo.sh b/t/t5100-mailinfo.sh
index e70ea94a1..0279d07c8 100755
--- a/t/t5100-mailinfo.sh
+++ b/t/t5100-mailinfo.sh
@@ -11,18 +11,26 @@ test_expect_success 'split sample box' \
 	'git mailsplit -o. "$TEST_DIRECTORY"/t5100/sample.mbox >last &&
 	last=`cat last` &&
 	echo total is $last &&
-	test `cat last` = 13'
+	test `cat last` = 14'
+
+check_mailinfo () {
+	mail=$1 opt=$2
+	mo="$mail$opt"
+	git mailinfo -u $opt msg$mo patch$mo <$mail >info$mo &&
+	test_cmp "$TEST_DIRECTORY"/t5100/msg$mo msg$mo &&
+	test_cmp "$TEST_DIRECTORY"/t5100/patch$mo patch$mo &&
+	test_cmp "$TEST_DIRECTORY"/t5100/info$mo info$mo
+}
+
 
 for mail in `echo 00*`
 do
 	test_expect_success "mailinfo $mail" '
-		git mailinfo -u msg$mail patch$mail <$mail >info$mail &&
-		echo msg &&
-		test_cmp "$TEST_DIRECTORY"/t5100/msg$mail msg$mail &&
-		echo patch &&
-		test_cmp "$TEST_DIRECTORY"/t5100/patch$mail patch$mail &&
-		echo info &&
-		test_cmp "$TEST_DIRECTORY"/t5100/info$mail info$mail
+		check_mailinfo $mail "" &&
+		if test -f "$TEST_DIRECTORY"/t5100/msg$mail--scissors
+		then
+			check_mailinfo $mail --scissors
+		fi
 	'
 done
 
diff --git a/t/t5100/info0014 b/t/t5100/info0014
new file mode 100644
index 000000000..08566b34b
--- /dev/null
+++ b/t/t5100/info0014
@@ -0,0 +1,5 @@
+Author: Junio Hamano
+Email: junkio@cox.net
+Subject: BLAH ONE
+Date: Thu, 20 Aug 2009 17:18:22 -0700
+
diff --git a/t/t5100/info0014--scissors b/t/t5100/info0014--scissors
new file mode 100644
index 000000000..ab9c8d090
--- /dev/null
+++ b/t/t5100/info0014--scissors
@@ -0,0 +1,5 @@
+Author: Junio C Hamano
+Email: gitster@pobox.com
+Subject: Teach mailinfo to ignore everything before -- >8 -- mark
+Date: Thu, 20 Aug 2009 17:18:22 -0700
+
diff --git a/t/t5100/msg0014 b/t/t5100/msg0014
new file mode 100644
index 000000000..62e5cd2ec
--- /dev/null
+++ b/t/t5100/msg0014
@@ -0,0 +1,18 @@
+In real life, we will see a discussion that inspired this patch
+discussing related and unrelated things around >8 scissors mark
+in this part of the message.
+
+Subject: [PATCH] BLAH TWO
+
+And then we will see the scissors.
+
+ This line is not a scissors mark -- >8 -- but talks about it.
+ - - >8 - - please remove everything above this line - - >8 - -
+
+Subject: [PATCH] Teach mailinfo to ignore everything before -- >8 -- mark
+From: Junio C Hamano <gitster@pobox.com>
+
+This teaches mailinfo the scissors -- >8 -- mark; the command ignores
+everything before it in the message body.
+
+Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/t/t5100/msg0014--scissors b/t/t5100/msg0014--scissors
new file mode 100644
index 000000000..259c6a46d
--- /dev/null
+++ b/t/t5100/msg0014--scissors
@@ -0,0 +1,4 @@
+This teaches mailinfo the scissors -- >8 -- mark; the command ignores
+everything before it in the message body.
+
+Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/t/t5100/patch0014 b/t/t5100/patch0014
new file mode 100644
index 000000000..124efd234
--- /dev/null
+++ b/t/t5100/patch0014
@@ -0,0 +1,64 @@
+---
+ builtin-mailinfo.c |   37 ++++++++++++++++++++++++++++++++++++-
+ 1 files changed, 36 insertions(+), 1 deletions(-)
+
+diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
+index b0b5d8f..461c47e 100644
+--- a/builtin-mailinfo.c
++++ b/builtin-mailinfo.c
+@@ -712,6 +712,34 @@ static inline int patchbreak(const struct strbuf *line)
+ 	return 0;
+ }
+ 
++static int scissors(const struct strbuf *line)
++{
++	size_t i, len = line->len;
++	int scissors_dashes_seen = 0;
++	const char *buf = line->buf;
++
++	for (i = 0; i < len; i++) {
++		if (isspace(buf[i]))
++			continue;
++		if (buf[i] == '-') {
++			scissors_dashes_seen |= 02;
++			continue;
++		}
++		if (i + 1 < len && !memcmp(buf + i, ">8", 2)) {
++			scissors_dashes_seen |= 01;
++			i++;
++			continue;
++		}
++		if (i + 7 < len && !memcmp(buf + i, "cut here", 8)) {
++			i += 7;
++			continue;
++		}
++		/* everything else --- not scissors */
++		break;
++	}
++	return scissors_dashes_seen == 03;
++}
++
+ static int handle_commit_msg(struct strbuf *line)
+ {
+ 	static int still_looking = 1;
+@@ -723,10 +751,17 @@ static int handle_commit_msg(struct strbuf *line)
+ 		strbuf_ltrim(line);
+ 		if (!line->len)
+ 			return 0;
+-		if ((still_looking = check_header(line, s_hdr_data, 0)) != 0)
++		still_looking = check_header(line, s_hdr_data, 0);
++		if (still_looking)
+ 			return 0;
+ 	}
+ 
++	if (scissors(line)) {
++		fseek(cmitmsg, 0L, SEEK_SET);
++		still_looking = 1;
++		return 0;
++	}
++
+ 	/* normalize the log message to UTF-8. */
+ 	if (metainfo_charset)
+ 		convert_to_utf8(line, charset.buf);
+-- 
+1.6.4.1
diff --git a/t/t5100/patch0014--scissors b/t/t5100/patch0014--scissors
new file mode 100644
index 000000000..124efd234
--- /dev/null
+++ b/t/t5100/patch0014--scissors
@@ -0,0 +1,64 @@
+---
+ builtin-mailinfo.c |   37 ++++++++++++++++++++++++++++++++++++-
+ 1 files changed, 36 insertions(+), 1 deletions(-)
+
+diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
+index b0b5d8f..461c47e 100644
+--- a/builtin-mailinfo.c
++++ b/builtin-mailinfo.c
+@@ -712,6 +712,34 @@ static inline int patchbreak(const struct strbuf *line)
+ 	return 0;
+ }
+ 
++static int scissors(const struct strbuf *line)
++{
++	size_t i, len = line->len;
++	int scissors_dashes_seen = 0;
++	const char *buf = line->buf;
++
++	for (i = 0; i < len; i++) {
++		if (isspace(buf[i]))
++			continue;
++		if (buf[i] == '-') {
++			scissors_dashes_seen |= 02;
++			continue;
++		}
++		if (i + 1 < len && !memcmp(buf + i, ">8", 2)) {
++			scissors_dashes_seen |= 01;
++			i++;
++			continue;
++		}
++		if (i + 7 < len && !memcmp(buf + i, "cut here", 8)) {
++			i += 7;
++			continue;
++		}
++		/* everything else --- not scissors */
++		break;
++	}
++	return scissors_dashes_seen == 03;
++}
++
+ static int handle_commit_msg(struct strbuf *line)
+ {
+ 	static int still_looking = 1;
+@@ -723,10 +751,17 @@ static int handle_commit_msg(struct strbuf *line)
+ 		strbuf_ltrim(line);
+ 		if (!line->len)
+ 			return 0;
+-		if ((still_looking = check_header(line, s_hdr_data, 0)) != 0)
++		still_looking = check_header(line, s_hdr_data, 0);
++		if (still_looking)
+ 			return 0;
+ 	}
+ 
++	if (scissors(line)) {
++		fseek(cmitmsg, 0L, SEEK_SET);
++		still_looking = 1;
++		return 0;
++	}
++
+ 	/* normalize the log message to UTF-8. */
+ 	if (metainfo_charset)
+ 		convert_to_utf8(line, charset.buf);
+-- 
+1.6.4.1
diff --git a/t/t5100/sample.mbox b/t/t5100/sample.mbox
index c3074ac57..13fa4ae03 100644
--- a/t/t5100/sample.mbox
+++ b/t/t5100/sample.mbox
@@ -561,3 +561,92 @@ From: <a.u.thor@example.com> (A U Thor)
 Date: Fri, 9 Jun 2006 00:44:16 -0700
 Subject: [PATCH] a patch
 
+From nobody Mon Sep 17 00:00:00 2001
+From: Junio Hamano <junkio@cox.net>
+Date: Thu, 20 Aug 2009 17:18:22 -0700
+Subject: Why doesn't git-am does not like >8 scissors mark?
+
+Subject: [PATCH] BLAH ONE
+
+In real life, we will see a discussion that inspired this patch
+discussing related and unrelated things around >8 scissors mark
+in this part of the message.
+
+Subject: [PATCH] BLAH TWO
+
+And then we will see the scissors.
+
+ This line is not a scissors mark -- >8 -- but talks about it.
+ - - >8 - - please remove everything above this line - - >8 - -
+
+Subject: [PATCH] Teach mailinfo to ignore everything before -- >8 -- mark
+From: Junio C Hamano <gitster@pobox.com>
+
+This teaches mailinfo the scissors -- >8 -- mark; the command ignores
+everything before it in the message body.
+
+Signed-off-by: Junio C Hamano <gitster@pobox.com>
+---
+ builtin-mailinfo.c |   37 ++++++++++++++++++++++++++++++++++++-
+ 1 files changed, 36 insertions(+), 1 deletions(-)
+
+diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
+index b0b5d8f..461c47e 100644
+--- a/builtin-mailinfo.c
++++ b/builtin-mailinfo.c
+@@ -712,6 +712,34 @@ static inline int patchbreak(const struct strbuf *line)
+ 	return 0;
+ }
+ 
++static int scissors(const struct strbuf *line)
++{
++	size_t i, len = line->len;
++	int scissors_dashes_seen = 0;
++	const char *buf = line->buf;
++
++	for (i = 0; i < len; i++) {
++		if (isspace(buf[i]))
++			continue;
++		if (buf[i] == '-') {
++			scissors_dashes_seen |= 02;
++			continue;
++		}
++		if (i + 1 < len && !memcmp(buf + i, ">8", 2)) {
++			scissors_dashes_seen |= 01;
++			i++;
++			continue;
++		}
++		if (i + 7 < len && !memcmp(buf + i, "cut here", 8)) {
++			i += 7;
++			continue;
++		}
++		/* everything else --- not scissors */
++		break;
++	}
++	return scissors_dashes_seen == 03;
++}
++
+ static int handle_commit_msg(struct strbuf *line)
+ {
+ 	static int still_looking = 1;
+@@ -723,10 +751,17 @@ static int handle_commit_msg(struct strbuf *line)
+ 		strbuf_ltrim(line);
+ 		if (!line->len)
+ 			return 0;
+-		if ((still_looking = check_header(line, s_hdr_data, 0)) != 0)
++		still_looking = check_header(line, s_hdr_data, 0);
++		if (still_looking)
+ 			return 0;
+ 	}
+ 
++	if (scissors(line)) {
++		fseek(cmitmsg, 0L, SEEK_SET);
++		still_looking = 1;
++		return 0;
++	}
++
+ 	/* normalize the log message to UTF-8. */
+ 	if (metainfo_charset)
+ 		convert_to_utf8(line, charset.buf);
+-- 
+1.6.4.1