test-lib: introduce test_commit_bulk

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 78fc67b03aad7ede3e796d61a52fc4a194270c76..c22cef3b2faff945148029197a32253540c24f73 100644 (file)
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -33,11 +33,13 @@ static const char *fast_export_usage[] = {
 static int progress;
 static enum { SIGNED_TAG_ABORT, VERBATIM, WARN, WARN_STRIP, STRIP } signed_tag_mode = SIGNED_TAG_ABORT;
 static enum { TAG_FILTERING_ABORT, DROP, REWRITE } tag_of_filtered_mode = TAG_FILTERING_ABORT;
+static enum { REENCODE_ABORT, REENCODE_YES, REENCODE_NO } reencode_mode = REENCODE_ABORT;
 static int fake_missing_tagger;
 static int use_done_feature;
 static int no_data;
 static int full_tree;
 static int reference_excluded_commits;
+static int show_original_ids;
 static struct string_list extra_refs = STRING_LIST_INIT_NODUP;
 static struct string_list tag_refs = STRING_LIST_INIT_NODUP;
 static struct refspec refspecs = REFSPEC_INIT_FETCH;
@@ -76,6 +78,31 @@ static int parse_opt_tag_of_filtered_mode(const struct option *opt,
        return 0;
 }
 
+static int parse_opt_reencode_mode(const struct option *opt,
+                                  const char *arg, int unset)
+{
+       if (unset) {
+               reencode_mode = REENCODE_ABORT;
+               return 0;
+       }
+
+       switch (git_parse_maybe_bool(arg)) {
+       case 0:
+               reencode_mode = REENCODE_NO;
+               break;
+       case 1:
+               reencode_mode = REENCODE_YES;
+               break;
+       default:
+               if (!strcasecmp(arg, "abort"))
+                       reencode_mode = REENCODE_ABORT;
+               else
+                       return error("Unknown reencoding mode: %s", arg);
+       }
+
+       return 0;
+}
+
 static struct decoration idnums;
 static uint32_t last_idnum;
 
@@ -271,7 +298,10 @@ static void export_blob(const struct object_id *oid)
 
        mark_next_object(object);
 
-       printf("blob\nmark :%"PRIu32"\ndata %lu\n", last_idnum, size);
+       printf("blob\nmark :%"PRIu32"\n", last_idnum);
+       if (show_original_ids)
+               printf("original-oid %s\n", oid_to_hex(oid));
+       printf("data %"PRIuMAX"\n", (uintmax_t)size);
        if (size && fwrite(buf, size, 1, stdout) != 1)
                die_errno("could not write blob '%s'", oid_to_hex(oid));
        printf("\n");
@@ -449,7 +479,7 @@ static const char *find_encoding(const char *begin, const char *end)
        bol = memmem(begin, end ? end - begin : strlen(begin),
                     needle, strlen(needle));
        if (!bol)
-               return git_commit_encoding;
+               return NULL;
        bol += strlen(needle);
        eol = strchrnul(bol, '\n');
        *eol = '\0';
@@ -629,16 +659,32 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
        }
 
        mark_next_object(&commit->object);
-       if (anonymize)
+       if (anonymize) {
                reencoded = anonymize_commit_message(message);
-       else if (!is_encoding_utf8(encoding))
-               reencoded = reencode_string(message, "UTF-8", encoding);
+       } else if (encoding) {
+               switch(reencode_mode) {
+               case REENCODE_YES:
+                       reencoded = reencode_string(message, "UTF-8", encoding);
+                       break;
+               case REENCODE_NO:
+                       break;
+               case REENCODE_ABORT:
+                       die("Encountered commit-specific encoding %s in commit "
+                           "%s; use --reencode=[yes|no] to handle it",
+                           encoding, oid_to_hex(&commit->object.oid));
+               }
+       }
        if (!commit->parents)
                printf("reset %s\n", refname);
-       printf("commit %s\nmark :%"PRIu32"\n%.*s\n%.*s\ndata %u\n%s",
-              refname, last_idnum,
+       printf("commit %s\nmark :%"PRIu32"\n", refname, last_idnum);
+       if (show_original_ids)
+               printf("original-oid %s\n", oid_to_hex(&commit->object.oid));
+       printf("%.*s\n%.*s\n",
               (int)(author_end - author), author,
-              (int)(committer_end - committer), committer,
+              (int)(committer_end - committer), committer);
+       if (!reencoded && encoding)
+               printf("encoding %s\n", encoding);
+       printf("data %u\n%s",
               (unsigned)(reencoded
                          ? strlen(reencoded) : message
                          ? strlen(message) : 0),
@@ -814,8 +860,10 @@ static void handle_tag(const char *name, struct tag *tag)
 
        if (starts_with(name, "refs/tags/"))
                name += 10;
-       printf("tag %s\nfrom :%d\n%.*s%sdata %d\n%.*s\n",
-              name, tagged_mark,
+       printf("tag %s\nfrom :%d\n", name, tagged_mark);
+       if (show_original_ids)
+               printf("original-oid %s\n", oid_to_hex(&tag->object.oid));
+       printf("%.*s%sdata %d\n%.*s\n",
               (int)(tagger_end - tagger), tagger,
               tagger == tagger_end ? "" : "\n",
               (int)message_size, (int)message_size, message ? message : "");
@@ -1080,6 +1128,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
                OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, N_("mode"),
                             N_("select handling of tags that tag filtered objects"),
                             parse_opt_tag_of_filtered_mode),
+               OPT_CALLBACK(0, "reencode", &reencode_mode, N_("mode"),
+                            N_("select handling of commit messages in an alternate encoding"),
+                            parse_opt_reencode_mode),
                OPT_STRING(0, "export-marks", &export_filename, N_("file"),
                             N_("Dump marks to this file")),
                OPT_STRING(0, "import-marks", &import_filename, N_("file"),
@@ -1096,6 +1147,8 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
                OPT_BOOL(0, "anonymize", &anonymize, N_("anonymize output")),
                OPT_BOOL(0, "reference-excluded-parents",
                         &reference_excluded_commits, N_("Reference parents which are not in fast-export stream by object id")),
+               OPT_BOOL(0, "show-original-ids", &show_original_ids,
+                           N_("Show original object ids of blobs/commits")),
 
                OPT_END()
        };