diff options
| -rw-r--r-- | Documentation/git-fast-export.txt | 29 | ||||
| -rw-r--r-- | builtin/fast-export.c | 50 | ||||
| -rwxr-xr-x | t/t9351-fast-export-anonymize.sh | 11 |
3 files changed, 88 insertions, 2 deletions
diff --git a/Documentation/git-fast-export.txt b/Documentation/git-fast-export.txt index e8950de3ba..1978dbdc6a 100644 --- a/Documentation/git-fast-export.txt +++ b/Documentation/git-fast-export.txt @@ -119,6 +119,11 @@ by keeping the marks the same across runs. the shape of the history and stored tree. See the section on `ANONYMIZING` below. +--anonymize-map=<from>[:<to>]:: + Convert token `<from>` to `<to>` in the anonymized output. If + `<to>` is omitted, map `<from>` to itself (i.e., do not + anonymize it). See the section on `ANONYMIZING` below. + --reference-excluded-parents:: By default, running a command such as `git fast-export master~5..master` will not include the commit master{tilde}5 @@ -238,6 +243,30 @@ collapse "User 0", "User 1", etc into "User X"). This produces a much smaller output, and it is usually easy to quickly confirm that there is no private data in the stream. +Reproducing some bugs may require referencing particular commits or +paths, which becomes challenging after refnames and paths have been +anonymized. You can ask for a particular token to be left as-is or +mapped to a new value. For example, if you have a bug which reproduces +with `git rev-list sensitive -- secret.c`, you can run: + +--------------------------------------------------- +$ git fast-export --anonymize --all \ + --anonymize-map=sensitive:foo \ + --anonymize-map=secret.c:bar.c \ + >stream +--------------------------------------------------- + +After importing the stream, you can then run `git rev-list foo -- bar.c` +in the anonymized repository. + +Note that paths and refnames are split into tokens at slash boundaries. +The command above would anonymize `subdir/secret.c` as something like +`path123/bar.c`; you could then search for `bar.c` in the anonymized +repository to determine the final pathname. + +To make referencing the final pathname simpler, you can map each path +component; so if you also anonymize `subdir` to `publicdir`, then the +final pathname would be `publicdir/bar.c`. LIMITATIONS ----------- diff --git a/builtin/fast-export.c b/builtin/fast-export.c index 1cbca5b4b4..b0b09bca30 100644 --- a/builtin/fast-export.c +++ b/builtin/fast-export.c @@ -45,6 +45,7 @@ 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; static int anonymize; +static struct hashmap anonymized_seeds; static struct revision_sources revision_sources; static int parse_opt_signed_tag_mode(const struct option *opt, @@ -168,8 +169,18 @@ static const char *anonymize_str(struct hashmap *map, hashmap_entry_init(&key.hash, memhash(orig, len)); key.orig = orig; key.orig_len = len; - ret = hashmap_get_entry(map, &key, hash, &key); + /* First check if it's a token the user configured manually... */ + if (anonymized_seeds.cmpfn) + ret = hashmap_get_entry(&anonymized_seeds, &key, hash, &key); + else + ret = NULL; + + /* ...otherwise check if we've already seen it in this context... */ + if (!ret) + ret = hashmap_get_entry(map, &key, hash, &key); + + /* ...and finally generate a new mapping if necessary */ if (!ret) { FLEX_ALLOC_MEM(ret, orig, orig, len); hashmap_entry_init(&ret->hash, key.hash.hash); @@ -1147,6 +1158,37 @@ static void handle_deletes(void) } } +static char *anonymize_seed(void *data) +{ + return xstrdup(data); +} + +static int parse_opt_anonymize_map(const struct option *opt, + const char *arg, int unset) +{ + struct hashmap *map = opt->value; + const char *delim, *value; + size_t keylen; + + BUG_ON_OPT_NEG(unset); + + delim = strchr(arg, ':'); + if (delim) { + keylen = delim - arg; + value = delim + 1; + } else { + keylen = strlen(arg); + value = arg; + } + + if (!keylen || !*value) + return error(_("--anonymize-map token cannot be empty")); + + anonymize_str(map, anonymize_seed, arg, keylen, (void *)value); + + return 0; +} + int cmd_fast_export(int argc, const char **argv, const char *prefix) { struct rev_info revs; @@ -1188,6 +1230,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) OPT_STRING_LIST(0, "refspec", &refspecs_list, N_("refspec"), N_("Apply refspec to exported refs")), OPT_BOOL(0, "anonymize", &anonymize, N_("anonymize output")), + OPT_CALLBACK_F(0, "anonymize-map", &anonymized_seeds, N_("from:to"), + N_("convert <from> to <to> in anonymized output"), + PARSE_OPT_NONEG, parse_opt_anonymize_map), 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, @@ -1215,6 +1260,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) if (argc > 1) usage_with_options (fast_export_usage, options); + if (anonymized_seeds.cmpfn && !anonymize) + die(_("--anonymize-map without --anonymize does not make sense")); + if (refspecs_list.nr) { int i; diff --git a/t/t9351-fast-export-anonymize.sh b/t/t9351-fast-export-anonymize.sh index dc5d75cd19..5a21c71568 100755 --- a/t/t9351-fast-export-anonymize.sh +++ b/t/t9351-fast-export-anonymize.sh @@ -6,6 +6,7 @@ test_description='basic tests for fast-export --anonymize' test_expect_success 'setup simple repo' ' test_commit base && test_commit foo && + test_commit retain-me && git checkout -b other HEAD^ && mkdir subdir && test_commit subdir/bar && @@ -18,7 +19,10 @@ test_expect_success 'setup simple repo' ' ' test_expect_success 'export anonymized stream' ' - git fast-export --anonymize --all >stream + git fast-export --anonymize --all \ + --anonymize-map=retain-me \ + --anonymize-map=xyzzy:custom-name \ + >stream ' # this also covers commit messages @@ -30,6 +34,11 @@ test_expect_success 'stream omits path names' ' ! grep xyzzy stream ' +test_expect_success 'stream contains user-specified names' ' + grep retain-me stream && + grep custom-name stream +' + test_expect_success 'stream omits gitlink oids' ' # avoid relying on the whole oid to remain hash-agnostic; this is # plenty to be unique within our test case |