Re: git-fast-export is returning streams with source code inside

From: Jeff King <peff@peff.net>
Date: Aug 5, 2011, 10:30 UTC
Message-ID: <20110805103016.GA19648@sigill.intra.peff.net>
In-Reply-To: <CAFC9htzzPQWFLGCpAP2WHhDQajfknwz1KUu6K0gvyhCVX5gyaQ@mail.gmail.com>

On Fri, Aug 05, 2011 at 10:54:29AM +0100, James Gregory wrote:

Show 15 quoted lines

> Thanks for the feedback. I've just looked at the commit on gitweb, and
> this could be the problem!
> 
> ---
> fixed dodgy filename
> spec/blueprints/sjt_blueprint.rb	[moved from
> spec/blueprints/sjt_blueprint.rb\n lead_in\n scenario\n answers {
> Sham.answers_object }\n justification_selected\n
> justification_unselected\n mark_scheme {
> Sham.single_mark_scheme_object }\nend\nmcq_blueprint.rb with 100%
> similarity]
> ---
> 
> I'm guessing that is where the problem lies... somehow the git
> transaction has got corrupt(?)

Ah, OK. That makes sense. I can replicate your problem easily with:

  $ touch 'file with
    newline'
  $ git init
  $ git add .
  $ git commit -m foo
  $ git fast-export HEAD | git fast-import
  fatal: Unsupported command: newline

According to the fast-import manpage, fast-export should be quoting the embedded line-feed. It looks like it isn't doing any quoting at all of pathnames right now, which is just wrong.

Does the patch below fix your issue?

---

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 9247871..bd27f08 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -16,6 +16,7 @@
 #include "string-list.h"
 #include "utf8.h"
 #include "parse-options.h"
+#include "quote.h"
 
 static const char *fast_export_usage[] = {
 	"git fast-export [rev-list-opts]",
@@ -167,6 +168,15 @@ static int depth_first(const void *a_, const void *b_)
 	return (a->status == 'R') - (b->status == 'R');
 }
 
+static void print_path(const char *path)
+{
+	int need_quote = quote_c_style(path, NULL, NULL, 0);
+	if (need_quote)
+		quote_c_style(path, NULL, stdout, 0);
+	else
+		printf("%s", path);
+}
+
 static void show_filemodify(struct diff_queue_struct *q,
 			    struct diff_options *options, void *data)
 {
@@ -184,13 +194,18 @@ static void show_filemodify(struct diff_queue_struct *q,
 
 		switch (q->queue[i]->status) {
 		case DIFF_STATUS_DELETED:
-			printf("D %s\n", spec->path);
+			printf("D ");
+			print_path(spec->path);
+			putchar('\n');
 			break;
 
 		case DIFF_STATUS_COPIED:
 		case DIFF_STATUS_RENAMED:
-			printf("%c \"%s\" \"%s\"\n", q->queue[i]->status,
-			       ospec->path, spec->path);
+			printf("%c ", q->queue[i]->status);
+			print_path(ospec->path);
+			putchar(' ');
+			print_path(spec->path);
+			putchar('\n');
 
 			if (!hashcmp(ospec->sha1, spec->sha1) &&
 			    ospec->mode == spec->mode)
@@ -205,13 +220,15 @@ static void show_filemodify(struct diff_queue_struct *q,
 			 * output the SHA-1 verbatim.
 			 */
 			if (no_data || S_ISGITLINK(spec->mode))
-				printf("M %06o %s %s\n", spec->mode,
-				       sha1_to_hex(spec->sha1), spec->path);
+				printf("M %06o %s ", spec->mode,
+				       sha1_to_hex(spec->sha1));
 			else {
 				struct object *object = lookup_object(spec->sha1);
-				printf("M %06o :%d %s\n", spec->mode,
-				       get_object_mark(object), spec->path);
+				printf("M %06o :%d ", spec->mode,
+				       get_object_mark(object));
 			}
+			print_path(spec->path);
+			putchar('\n');
 			break;
 
 		default: