fast-export: quote paths in output

Many pathnames in a fast-import stream need to be quoted. In
particular:

  1. Pathnames at the end of an "M" or "D" line need quoting
     if they contain a LF or start with double-quote.

  2. Pathnames on a "C" or "R" line need quoting as above,
     but also if they contain spaces.

For (1), we weren't quoting at all. For (2), we put
double-quotes around the paths to handle spaces, but ignored
the possibility that they would need further quoting.

This patch checks whether each pathname needs c-style
quoting, and uses it. This is slightly overkill for (1),
which doesn't actually need to quote many characters that
vanilla c-style quoting does. However, it shouldn't hurt, as
any implementation needs to be ready to handle quoted
strings anyway.

In addition to adding a test, we have to tweak a test which
blindly assumed that case (2) would always use
double-quotes, whether it needed to or not.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index c8fd46b872780b27b09ad70316fa164d855f3220..e5035675b9514d5bf5ec894aeccbaa6af1d762e6 100644 (file)
--- 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]",
@@ -178,6 +179,15 @@ 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)
 {
@@ -195,13 +205,18 @@ 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)
@@ -216,13 +231,15 @@ 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:

diff --git a/t/t9350-fast-export.sh b/t/t9350-fast-export.sh
index 8c8e679468f4b191f93ca68a973d4d58fa1b72d2..d90a4136cf111cc0a0792db2a8f48e5ef07b1fb1 100755 (executable)
--- a/t/t9350-fast-export.sh
+++ b/t/t9350-fast-export.sh
@@ -228,7 +228,7 @@ test_expect_success 'fast-export -C -C | fast-import' '
        mkdir new &&
        git --git-dir=new/.git init &&
        git fast-export -C -C --signed-tags=strip --all > output &&
-       grep "^C \"file6\" \"file7\"\$" output &&
+       grep "^C file6 file7\$" output &&
        cat output |
        (cd new &&
         git fast-import &&
@@ -414,4 +414,30 @@ test_expect_success SYMLINKS 'directory becomes symlink'        '
        (cd result && git show master:foo)
 '
 
+test_expect_success 'fast-export quotes pathnames' '
+       git init crazy-paths &&
+       (cd crazy-paths &&
+        blob=`echo foo | git hash-object -w --stdin` &&
+        git update-index --add \
+               --cacheinfo 100644 $blob "$(printf "path with\\nnewline")" \
+               --cacheinfo 100644 $blob "path with \"quote\"" \
+               --cacheinfo 100644 $blob "path with \\backslash" \
+               --cacheinfo 100644 $blob "path with space" &&
+        git commit -m addition &&
+        git ls-files -z -s | perl -0pe "s{\\t}{$&subdir/}" >index &&
+        git read-tree --empty &&
+        git update-index -z --index-info <index &&
+        git commit -m rename &&
+        git read-tree --empty &&
+        git commit -m deletion &&
+        git fast-export HEAD >export.out &&
+        git rev-list HEAD >expect &&
+        git init result &&
+        cd result &&
+        git fast-import <../export.out &&
+        git rev-list HEAD >actual &&
+        test_cmp ../expect actual
+       )
+'
+
 test_done