aboutsummaryrefslogtreecommitdiff
path: root/t/t9351-fast-export-anonymize.sh
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2014-08-27 13:01:28 -0400
committerJunio C Hamano <gitster@pobox.com>2014-08-27 10:42:16 -0700
commita8722750985a53cc502a66ae3d68a9e42c7fdb98 (patch)
tree31892a12522ed3f217be7a3ce96c4e5d2c3173be /t/t9351-fast-export-anonymize.sh
parent6c4ab27f2378ce67940b4496365043119d7ffff2 (diff)
downloadgit-a8722750985a53cc502a66ae3d68a9e42c7fdb98.tar.gz
git-a8722750985a53cc502a66ae3d68a9e42c7fdb98.tar.xz
teach fast-export an --anonymize option
Sometimes users want to report a bug they experience on their repository, but they are not at liberty to share the contents of the repository. It would be useful if they could produce a repository that has a similar shape to its history and tree, but without leaking any information. This "anonymized" repository could then be shared with developers (assuming it still replicates the original problem). This patch implements an "--anonymize" option to fast-export, which generates a stream that can recreate such a repository. Producing a single stream makes it easy for the caller to verify that they are not leaking any useful information. You can get an overview of what will be shared by running a command like: git fast-export --anonymize --all | perl -pe 's/\d+/X/g' | sort -u | less which will show every unique line we generate, modulo any numbers (each anonymized token is assigned a number, like "User 0", and we replace it consistently in the output). In addition to anonymizing, this produces test cases that are relatively small (compared to the original repository) and fast to generate (compared to using filter-branch, or modifying the output of fast-export yourself). Here are numbers for git.git: $ time git fast-export --anonymize --all \ --tag-of-filtered-object=drop >output real 0m2.883s user 0m2.828s sys 0m0.052s $ gzip output $ ls -lh output.gz | awk '{print $5}' 2.9M Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 't/t9351-fast-export-anonymize.sh')
-rwxr-xr-xt/t9351-fast-export-anonymize.sh112
1 files changed, 112 insertions, 0 deletions
diff --git a/t/t9351-fast-export-anonymize.sh b/t/t9351-fast-export-anonymize.sh
new file mode 100755
index 000000000..897dc5090
--- /dev/null
+++ b/t/t9351-fast-export-anonymize.sh
@@ -0,0 +1,112 @@
+#!/bin/sh
+
+test_description='basic tests for fast-export --anonymize'
+. ./test-lib.sh
+
+test_expect_success 'setup simple repo' '
+ test_commit base &&
+ test_commit foo &&
+ git checkout -b other HEAD^ &&
+ mkdir subdir &&
+ test_commit subdir/bar &&
+ test_commit subdir/xyzzy &&
+ git tag -m "annotated tag" mytag
+'
+
+test_expect_success 'export anonymized stream' '
+ git fast-export --anonymize --all >stream
+'
+
+# this also covers commit messages
+test_expect_success 'stream omits path names' '
+ ! grep base stream &&
+ ! grep foo stream &&
+ ! grep subdir stream &&
+ ! grep bar stream &&
+ ! grep xyzzy stream
+'
+
+test_expect_success 'stream allows master as refname' '
+ grep master stream
+'
+
+test_expect_success 'stream omits other refnames' '
+ ! grep other stream &&
+ ! grep mytag stream
+'
+
+test_expect_success 'stream omits identities' '
+ ! grep "$GIT_COMMITTER_NAME" stream &&
+ ! grep "$GIT_COMMITTER_EMAIL" stream &&
+ ! grep "$GIT_AUTHOR_NAME" stream &&
+ ! grep "$GIT_AUTHOR_EMAIL" stream
+'
+
+test_expect_success 'stream omits tag message' '
+ ! grep "annotated tag" stream
+'
+
+# NOTE: we chdir to the new, anonymized repository
+# after this. All further tests should assume this.
+test_expect_success 'import stream to new repository' '
+ git init new &&
+ cd new &&
+ git fast-import <../stream
+'
+
+test_expect_success 'result has two branches' '
+ git for-each-ref --format="%(refname)" refs/heads >branches &&
+ test_line_count = 2 branches &&
+ other_branch=$(grep -v refs/heads/master branches)
+'
+
+test_expect_success 'repo has original shape and timestamps' '
+ shape () {
+ git log --format="%m %ct" --left-right --boundary "$@"
+ } &&
+ (cd .. && shape master...other) >expect &&
+ shape master...$other_branch >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'root tree has original shape' '
+ # the output entries are not necessarily in the same
+ # order, but we know at least that we will have one tree
+ # and one blob, so just check the sorted order
+ cat >expect <<-\EOF &&
+ blob
+ tree
+ EOF
+ git ls-tree $other_branch >root &&
+ cut -d" " -f2 <root | sort >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'paths in subdir ended up in one tree' '
+ cat >expect <<-\EOF &&
+ blob
+ blob
+ EOF
+ tree=$(grep tree root | cut -f2) &&
+ git ls-tree $other_branch:$tree >tree &&
+ cut -d" " -f2 <tree >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'tag points to branch tip' '
+ git rev-parse $other_branch >expect &&
+ git for-each-ref --format="%(*objectname)" | grep . >actual &&
+ test_cmp expect actual
+'
+
+test_expect_success 'idents are shared' '
+ git log --all --format="%an <%ae>" >authors &&
+ sort -u authors >unique &&
+ test_line_count = 1 unique &&
+ git log --all --format="%cn <%ce>" >committers &&
+ sort -u committers >unique &&
+ test_line_count = 1 unique &&
+ ! test_cmp authors committers
+'
+
+test_done