mailinfo: support format=flowed

Add best-effort support for patches sent using format=flowed (RFC 3676).
Remove leading spaces ("unstuff"), remove soft line breaks (indicated
by space + newline), but leave the signature separator (dash dash space
newline) alone.

Warn in git am when encountering a format=flowed patch, because any
trailing spaces would most probably be lost, as the sending MUA is
encouraged to remove them when preparing the email.

Provide a test patch formatted by Mozilla Thunderbird 60 using its
default configuration.  It reuses the contents of the file mailinfo.c
before and after this patch.

Signed-off-by: Rene Scharfe <l.s.r@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/am.c

@@ -1243,6 +1243,10 @@ static int parse_mail(struct am_state *state, const char *mail)
 	fclose(mi.input);
 	fclose(mi.output);
 
+	if (mi.format_flowed)
+		warning(_("Patch sent with format=flowed; "
+			  "space at the end of lines might be lost."));
+
 	/* Extract message and author information */
 	fp = xfopen(am_path(state, "info"), "r");
 	while (!strbuf_getline_lf(&sb, fp)) {

mailinfo.c

@@ -237,11 +237,22 @@ static int slurp_attr(const char *line, const char *name, struct strbuf *attr)
 	return 1;
 }
 
+static int has_attr_value(const char *line, const char *name, const char *value)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int rc = slurp_attr(line, name, &sb) && !strcasecmp(sb.buf, value);
+	strbuf_release(&sb);
+	return rc;
+}
+
 static void handle_content_type(struct mailinfo *mi, struct strbuf *line)
 {
 	struct strbuf *boundary = xmalloc(sizeof(struct strbuf));
 	strbuf_init(boundary, line->len);
 
+	mi->format_flowed = has_attr_value(line->buf, "format=", "flowed");
+	mi->delsp = has_attr_value(line->buf, "delsp=", "yes");
+
 	if (slurp_attr(line->buf, "boundary=", boundary)) {
 		strbuf_insert(boundary, 0, "--", 2);
 		if (++mi->content_top >= &mi->content[MAX_BOUNDARIES]) {
@@ -964,6 +975,52 @@ again:
 	return 1;
 }
 
+static void handle_filter_flowed(struct mailinfo *mi, struct strbuf *line,
+				 struct strbuf *prev)
+{
+	size_t len = line->len;
+	const char *rest;
+
+	if (!mi->format_flowed) {
+		handle_filter(mi, line);
+		return;
+	}
+
+	if (line->buf[len - 1] == '\n') {
+		len--;
+		if (len && line->buf[len - 1] == '\r')
+			len--;
+	}
+
+	/* Keep signature separator as-is. */
+	if (skip_prefix(line->buf, "-- ", &rest) && rest - line->buf == len) {
+		if (prev->len) {
+			handle_filter(mi, prev);
+			strbuf_reset(prev);
+		}
+		handle_filter(mi, line);
+		return;
+	}
+
+	/* Unstuff space-stuffed line. */
+	if (len && line->buf[0] == ' ') {
+		strbuf_remove(line, 0, 1);
+		len--;
+	}
+
+	/* Save flowed line for later, but without the soft line break. */
+	if (len && line->buf[len - 1] == ' ') {
+		strbuf_add(prev, line->buf, len - !!mi->delsp);
+		return;
+	}
+
+	/* Prepend any previous partial lines */
+	strbuf_insert(line, 0, prev->buf, prev->len);
+	strbuf_reset(prev);
+
+	handle_filter(mi, line);
+}
+
 static void handle_body(struct mailinfo *mi, struct strbuf *line)
 {
 	struct strbuf prev = STRBUF_INIT;
@@ -1012,7 +1069,7 @@ static void handle_body(struct mailinfo *mi, struct strbuf *line)
 						strbuf_addbuf(&prev, sb);
 						break;
 					}
-				handle_filter(mi, sb);
+				handle_filter_flowed(mi, sb, &prev);
 			}
 			/*
 			 * The partial chunk is saved in "prev" and will be
@@ -1022,13 +1079,16 @@ static void handle_body(struct mailinfo *mi, struct strbuf *line)
 			break;
 		}
 		default:
-			handle_filter(mi, line);
+			handle_filter_flowed(mi, line, &prev);
 		}
 
 		if (mi->input_error)
 			break;
 	} while (!strbuf_getwholeline(line, mi->input, '\n'));
 
+	if (prev.len)
+		handle_filter(mi, &prev);
+
 	flush_inbody_header_accum(mi);
 
 handle_body_out:

mailinfo.h

@@ -20,6 +20,8 @@ struct mailinfo {
 	struct strbuf *content[MAX_BOUNDARIES];
 	struct strbuf **content_top;
 	struct strbuf charset;
+	unsigned int format_flowed:1;
+	unsigned int delsp:1;
 	char *message_id;
 	enum  {
 		TE_DONTCARE, TE_QP, TE_BASE64

t/t4256-am-format-flowed.sh

@@ -0,0 +1,19 @@
+#!/bin/sh
+
+test_description='test format=flowed support of git am'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	cp "$TEST_DIRECTORY/t4256/1/mailinfo.c.orig" mailinfo.c &&
+	git add mailinfo.c &&
+	git commit -m initial
+'
+
+test_expect_success 'am with format=flowed' '
+	git am <"$TEST_DIRECTORY/t4256/1/patch" >stdout 2>stderr &&
+	test_i18ngrep "warning: Patch sent with format=flowed" stderr &&
+	test_cmp "$TEST_DIRECTORY/t4256/1/mailinfo.c" mailinfo.c
+'
+
+test_done

t/t4256/1/patch

@@ -0,0 +1,129 @@
+From: A <author@example.com>
+Subject: [PATCH] mailinfo: support format=flowed
+Message-ID: <aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa@example.com>
+Date: Sat, 25 Aug 2018 22:04:50 +0200
+User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:60.0) Gecko/20100101
+ Thunderbird/60.0
+MIME-Version: 1.0
+Content-Type: text/plain; charset=utf-8; format=flowed
+Content-Language: en-US
+Content-Transfer-Encoding: 7bit
+
+---
+  mailinfo.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++++--
+  1 file changed, 62 insertions(+), 2 deletions(-)
+
+diff --git a/mailinfo.c b/mailinfo.c
+index 3281a37d51..b395adbdf2 100644
+--- a/mailinfo.c
++++ b/mailinfo.c
+@@ -237,11 +237,22 @@ static int slurp_attr(const char *line, const char 
+*name, struct strbuf *attr)
+  	return 1;
+  }
+
++static int has_attr_value(const char *line, const char *name, const 
+char *value)
++{
++	struct strbuf sb = STRBUF_INIT;
++	int rc = slurp_attr(line, name, &sb) && !strcasecmp(sb.buf, value);
++	strbuf_release(&sb);
++	return rc;
++}
++
+  static void handle_content_type(struct mailinfo *mi, struct strbuf *line)
+  {
+  	struct strbuf *boundary = xmalloc(sizeof(struct strbuf));
+  	strbuf_init(boundary, line->len);
+
++	mi->format_flowed = has_attr_value(line->buf, "format=", "flowed");
++	mi->delsp = has_attr_value(line->buf, "delsp=", "yes");
++
+  	if (slurp_attr(line->buf, "boundary=", boundary)) {
+  		strbuf_insert(boundary, 0, "--", 2);
+  		if (++mi->content_top >= &mi->content[MAX_BOUNDARIES]) {
+@@ -964,6 +975,52 @@ static int handle_boundary(struct mailinfo *mi, 
+struct strbuf *line)
+  	return 1;
+  }
+
++static void handle_filter_flowed(struct mailinfo *mi, struct strbuf *line,
++				 struct strbuf *prev)
++{
++	size_t len = line->len;
++	const char *rest;
++
++	if (!mi->format_flowed) {
++		handle_filter(mi, line);
++		return;
++	}
++
++	if (line->buf[len - 1] == '\n') {
++		len--;
++		if (len && line->buf[len - 1] == '\r')
++			len--;
++	}
++
++	/* Keep signature separator as-is. */
++	if (skip_prefix(line->buf, "-- ", &rest) && rest - line->buf == len) {
++		if (prev->len) {
++			handle_filter(mi, prev);
++			strbuf_reset(prev);
++		}
++		handle_filter(mi, line);
++		return;
++	}
++
++	/* Unstuff space-stuffed line. */
++	if (len && line->buf[0] == ' ') {
++		strbuf_remove(line, 0, 1);
++		len--;
++	}
++
++	/* Save flowed line for later, but without the soft line break. */
++	if (len && line->buf[len - 1] == ' ') {
++		strbuf_add(prev, line->buf, len - !!mi->delsp);
++		return;
++	}
++
++	/* Prepend any previous partial lines */
++	strbuf_insert(line, 0, prev->buf, prev->len);
++	strbuf_reset(prev);
++
++	handle_filter(mi, line);
++}
++
+  static void handle_body(struct mailinfo *mi, struct strbuf *line)
+  {
+  	struct strbuf prev = STRBUF_INIT;
+@@ -1012,7 +1069,7 @@ static void handle_body(struct mailinfo *mi, 
+struct strbuf *line)
+  						strbuf_addbuf(&prev, sb);
+  						break;
+  					}
+-				handle_filter(mi, sb);
++				handle_filter_flowed(mi, sb, &prev);
+  			}
+  			/*
+  			 * The partial chunk is saved in "prev" and will be
+@@ -1022,13 +1079,16 @@ static void handle_body(struct mailinfo *mi, 
+struct strbuf *line)
+  			break;
+  		}
+  		default:
+-			handle_filter(mi, line);
++			handle_filter_flowed(mi, line, &prev);
+  		}
+
+  		if (mi->input_error)
+  			break;
+  	} while (!strbuf_getwholeline(line, mi->input, '\n'));
+
++	if (prev.len)
++		handle_filter(mi, &prev);
++
+  	flush_inbody_header_accum(mi);
+
+  handle_body_out:
+-- 
+2.18.0