Merge branch 'bc/mailsplit-cr-at-eol'

* bc/mailsplit-cr-at-eol:
  Allow mailsplit (and hence git-am) to handle mails with CRLF line-endings
  builtin-mailsplit.c: remove read_line_with_nul() since it is no longer used
  builtin-mailinfo,builtin-mailsplit: use strbufs
  strbuf: add new function strbuf_getwholeline()

7 files changed, 61 insertions, 43 deletions

diff --git a/builtin-mailinfo.c b/builtin-mailinfo.c
index 92637ac0ba..b0b5d8f6cb 100644
--- a/builtin-mailinfo.c
+++ b/builtin-mailinfo.c
@@ -765,7 +765,6 @@ static void handle_filter(struct strbuf *line)
 
 static void handle_body(void)
 {
-	int len = 0;
 	struct strbuf prev = STRBUF_INIT;
 
 	/* Skip up to the first boundary */
@@ -775,8 +774,6 @@ static void handle_body(void)
 	}
 
 	do {
-		strbuf_setlen(&line, line.len + len);
-
 		/* process any boundary lines */
 		if (*content_top && is_multipart_boundary(&line)) {
 			/* flush any leftover */
@@ -832,10 +829,7 @@ static void handle_body(void)
 			handle_filter(&line);
 		}
 
-		strbuf_reset(&line);
-		if (strbuf_avail(&line) < 100)
-			strbuf_grow(&line, 100);
-	} while ((len = read_line_with_nul(line.buf, strbuf_avail(&line), fin)));
+	} while (!strbuf_getwholeline(&line, fin, '\n'));
 
 handle_body_out:
 	strbuf_release(&prev);
diff --git a/builtin-mailsplit.c b/builtin-mailsplit.c
index ad5f6b593d..ee6ca0ebcd 100644
--- a/builtin-mailsplit.c
+++ b/builtin-mailsplit.c
@@ -7,6 +7,7 @@
 #include "cache.h"
 #include "builtin.h"
 #include "string-list.h"
+#include "strbuf.h"
 
 static const char git_mailsplit_usage[] =
 "git mailsplit [-d<prec>] [-f<n>] [-b] -o<directory> [<mbox>|<Maildir>...]";
@@ -42,26 +43,8 @@ static int is_from_line(const char *line, int len)
 	return 1;
 }
 
-/* Could be as small as 64, enough to hold a Unix "From " line. */
-static char buf[4096];
-
-/* We cannot use fgets() because our lines can contain NULs */
-int read_line_with_nul(char *buf, int size, FILE *in)
-{
-	int len = 0, c;
-
-	for (;;) {
-		c = getc(in);
-		if (c == EOF)
-			break;
-		buf[len++] = c;
-		if (c == '\n' || len + 1 >= size)
-			break;
-	}
-	buf[len] = '\0';
-
-	return len;
-}
+static struct strbuf buf = STRBUF_INIT;
+static int keep_cr;
 
 /* Called with the first line (potentially partial)
  * already in buf[] -- normally that should begin with
@@ -71,10 +54,9 @@ int read_line_with_nul(char *buf, int size, FILE *in)
 static int split_one(FILE *mbox, const char *name, int allow_bare)
 {
 	FILE *output = NULL;
-	int len = strlen(buf);
 	int fd;
 	int status = 0;
-	int is_bare = !is_from_line(buf, len);
+	int is_bare = !is_from_line(buf.buf, buf.len);
 
 	if (is_bare && !allow_bare)
 		goto corrupt;
@@ -88,20 +70,23 @@ static int split_one(FILE *mbox, const char *name, int allow_bare)
 	 * "From " and having something that looks like a date format.
 	 */
 	for (;;) {
-		int is_partial = len && buf[len-1] != '\n';
+		if (!keep_cr && buf.len > 1 && buf.buf[buf.len-1] == '\n' &&
+			buf.buf[buf.len-2] == '\r') {
+			strbuf_setlen(&buf, buf.len-2);
+			strbuf_addch(&buf, '\n');
+		}
 
-		if (fwrite(buf, 1, len, output) != len)
+		if (fwrite(buf.buf, 1, buf.len, output) != buf.len)
 			die_errno("cannot write output");
 
-		len = read_line_with_nul(buf, sizeof(buf), mbox);
-		if (len == 0) {
+		if (strbuf_getwholeline(&buf, mbox, '\n')) {
 			if (feof(mbox)) {
 				status = 1;
 				break;
 			}
 			die_errno("cannot read mbox");
 		}
-		if (!is_partial && !is_bare && is_from_line(buf, len))
+		if (!is_bare && is_from_line(buf.buf, buf.len))
 			break; /* done with one message */
 	}
 	fclose(output);
@@ -166,7 +151,7 @@ static int split_maildir(const char *maildir, const char *dir,
 			goto out;
 		}
 
-		if (fgets(buf, sizeof(buf), f) == NULL) {
+		if (strbuf_getwholeline(&buf, f, '\n')) {
 			error("cannot read mail %s (%s)", file, strerror(errno));
 			goto out;
 		}
@@ -203,7 +188,7 @@ static int split_mbox(const char *file, const char *dir, int allow_bare,
 	} while (isspace(peek));
 	ungetc(peek, f);
 
-	if (fgets(buf, sizeof(buf), f) == NULL) {
+	if (strbuf_getwholeline(&buf, f, '\n')) {
 		/* empty stdin is OK */
 		if (f != stdin) {
 			error("cannot read mbox %s", file);
@@ -248,6 +233,8 @@ int cmd_mailsplit(int argc, const char **argv, const char *prefix)
 			nr = strtol(arg+2, NULL, 10);
 		} else if ( arg[1] == 'b' && !arg[2] ) {
 			allow_bare = 1;
+		} else if (!strcmp(arg, "--keep-cr")) {
+			keep_cr = 1;
 		} else if ( arg[1] == 'o' && arg[2] ) {
 			dir = arg+2;
 		} else if ( arg[1] == '-' && !arg[2] ) {
diff --git a/builtin.h b/builtin.h
index 20427d2963..9993dfcf99 100644
--- a/builtin.h
+++ b/builtin.h
@@ -13,7 +13,6 @@ extern const char git_more_info_string[];
 extern void list_common_cmds_help(void);
 extern const char *help_unknown_cmd(const char *cmd);
 extern void prune_packed_objects(int);
-extern int read_line_with_nul(char *buf, int size, FILE *file);
 extern int fmt_merge_msg(int merge_summary, struct strbuf *in,
 	struct strbuf *out);
 extern int commit_tree(const char *msg, unsigned char *tree,
diff --git a/git-am.sh b/git-am.sh
index f719f6e654..5396be2279 100755
--- a/git-am.sh
+++ b/git-am.sh
@@ -211,7 +211,13 @@ check_patch_format () {
 split_patches () {
 	case "$patch_format" in
 	mbox)
-		git mailsplit -d"$prec" -o"$dotest" -b -- "$@" > "$dotest/last" ||
+		case "$rebasing" in
+		'')
+			keep_cr= ;;
+		?*)
+			keep_cr=--keep-cr ;;
+		esac
+		git mailsplit -d"$prec" -o"$dotest" -b $keep_cr -- "$@" > "$dotest/last" ||
 		clean_abort
 		;;
 	stgit-series)
diff --git a/strbuf.c b/strbuf.c
index f03d11702b..a6153dca27 100644
--- a/strbuf.c
+++ b/strbuf.c
@@ -322,7 +322,7 @@ int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint)
 	return -1;
 }
 
-int strbuf_getline(struct strbuf *sb, FILE *fp, int term)
+int strbuf_getwholeline(struct strbuf *sb, FILE *fp, int term)
 {
 	int ch;
 
@@ -332,10 +332,10 @@ int strbuf_getline(struct strbuf *sb, FILE *fp, int term)
 
 	strbuf_reset(sb);
 	while ((ch = fgetc(fp)) != EOF) {
-		if (ch == term)
-			break;
 		strbuf_grow(sb, 1);
 		sb->buf[sb->len++] = ch;
+		if (ch == term)
+			break;
 	}
 	if (ch == EOF && sb->len == 0)
 		return EOF;
@@ -344,6 +344,15 @@ int strbuf_getline(struct strbuf *sb, FILE *fp, int term)
 	return 0;
 }
 
+int strbuf_getline(struct strbuf *sb, FILE *fp, int term)
+{
+	if (strbuf_getwholeline(sb, fp, term))
+		return EOF;
+	if (sb->buf[sb->len-1] == term)
+		strbuf_setlen(sb, sb->len-1);
+	return 0;
+}
+
 int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint)
 {
 	int fd, len;
diff --git a/strbuf.h b/strbuf.h
index eaa8704d5f..d05e056dd3 100644
--- a/strbuf.h
+++ b/strbuf.h
@@ -126,6 +126,7 @@ extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint);
 extern int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint);
 extern int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint);
 
+extern int strbuf_getwholeline(struct strbuf *, FILE *, int);
 extern int strbuf_getline(struct strbuf *, FILE *, int);
 
 extern void stripspace(struct strbuf *buf, int skip_comments);
diff --git a/t/t3400-rebase.sh b/t/t3400-rebase.sh
index c5c29ccc4f..4e6a44b623 100755
--- a/t/t3400-rebase.sh
+++ b/t/t3400-rebase.sh
@@ -3,9 +3,10 @@
 # Copyright (c) 2005 Amos Waterland
 #
 
-test_description='git rebase should not destroy author information
+test_description='git rebase assorted tests
 
-This test runs git rebase and checks that the author information is not lost.
+This test runs git rebase and checks that the author information is not lost
+among other things.
 '
 . ./test-lib.sh
 
@@ -133,4 +134,25 @@ test_expect_success 'rebase -q is quiet' '
      test ! -s output.out
 '
 
+q_to_cr () {
+	tr Q '\015'
+}
+
+test_expect_success 'Rebase a commit that sprinkles CRs in' '
+	(
+		echo "One"
+		echo "TwoQ"
+		echo "Three"
+		echo "FQur"
+		echo "Five"
+	) | q_to_cr >CR &&
+	git add CR &&
+	test_tick &&
+	git commit -a -m "A file with a line with CR" &&
+	git tag file-with-cr &&
+	git checkout HEAD^0 &&
+	git rebase --onto HEAD^^ HEAD^ &&
+	git diff --exit-code file-with-cr:CR HEAD:CR
+'
+
 test_done