[git] Be more specific when looking for llvm-svn

Summary:
A commit may, for some reason, have `llvm-svn:` in it multiple times. It may even take up the whole line and look identical to what gets added automatically when svn commits land in github.

To workaround this, make changes to both lookups:

1) When doing the git -> svn lookup, make sure to go through the whole message, and:
 a) Only look for llvm-svn starting at the beginning of the line (excluding the whitespace that `git log` adds).
 b) Take the last one (at the end of the commit message), if there are multiple matches.

2) When doing the svn -> git lookup, look through a sizeable but still reasonably small number of git commits (10k, about 4-5 months right now), and:
 a) Only consider commits with the '^llvm-svn: NNNNNN' we expect, and
 b) Only consider those that also follow the same git -> svn matching above. (Error if it's not exactly one commit).

Reviewers: jyknight

Reviewed By: jyknight

Subscribers: llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D60017

llvm-svn: 361532

diff --git a/llvm/utils/git-svn/git-llvm b/llvm/utils/git-svn/git-llvm
index 28a0a9bbf4d16101bc255bdc2a6c6f84583b73b3..53abc538ccaf38f750700c9102430f51dde1be79 100755 (executable)
--- a/llvm/utils/git-svn/git-llvm
+++ b/llvm/utils/git-svn/git-llvm
@@ -413,12 +413,22 @@ def cmd_push(args):
 
 
 def lookup_llvm_svn_id(git_commit_hash):
-    commit_msg = git('log', '-1', git_commit_hash, ignore_errors=True)
+    # Use --format=%b to get the raw commit message, without any extra
+    # whitespace.
+    commit_msg = git('log', '-1', '--format=%b', git_commit_hash,
+                     ignore_errors=True)
     if len(commit_msg) == 0:
       die("Can't find git commit " + git_commit_hash)
-    svn_match = re.search('llvm-svn: (\d{5,7})$', commit_msg)
+    # If a commit has multiple "llvm-svn:" lines (e.g. if the commit is
+    # reverting/quoting a previous commit), choose the last one, which should
+    # be the authoritative one.
+    svn_match_iter = re.finditer('^llvm-svn: (\d{5,7})$', commit_msg,
+                                 re.MULTILINE)
+    svn_match = None
+    for m in svn_match_iter:
+      svn_match = m.group(1)
     if svn_match:
-      return int(svn_match.group(1))
+      return int(svn_match)
     die("Can't find svn revision in git commit " + git_commit_hash)
 
 
@@ -437,6 +447,28 @@ def cmd_svn_lookup(args):
     log('r' + str(lookup_llvm_svn_id(args.git_commit_hash)))
 
 
+def git_hash_by_svn_rev(svn_rev):
+    '''Find the git hash for a given svn revision.
+
+    This check is paranoid: 'llvm-svn: NNNNNN' could exist on its own line
+    somewhere else in the commit message. Look in the full log message to see
+    if it's actually on the last line.
+
+    Since this check is expensive (we're searching every single commit), limit
+    to the past 10k commits (about 5 months).
+    '''
+    possible_hashes = git(
+        'log', '--format=%H', '--grep', '^llvm-svn: %d$' % svn_rev,
+        'HEAD~10000...HEAD').split('\n')
+    matching_hashes = [h for h in possible_hashes
+                       if lookup_llvm_svn_id(h) == svn_rev]
+    if len(matching_hashes) > 1:
+      die("svn revision r%d has ambiguous commits: %s" % (
+          svn_rev, ', '.join(matching_hashes)))
+    elif len(matching_hashes) < 1:
+      die("svn revision r%d matches no commits" % svn_rev)
+    return matching_hashes[0]
+
 def cmd_revert(args):
     '''Revert a commit by either SVN id (rNNNNNN) or git hash. This also
     populates the git commit message with both the SVN revision and git hash of
@@ -459,24 +491,28 @@ def cmd_revert(args):
     # the git commit.
     svn_match = re.match('^r(\d{5,7})$', args.revision)
     if svn_match:
-      svn_rev = svn_match.group(1)
+      # If the revision looks like rNNNNNN, use that as the svn revision, and
+      # grep through git commits to find which one corresponds to that svn
+      # revision.
+      svn_rev = int(svn_match.group(1))
+      git_hash = git_hash_by_svn_rev(svn_rev)
     else:
-      svn_rev = str(lookup_llvm_svn_id(args.revision))
+      # Otherwise, this looks like a git hash, so we just need to grab the svn
+      # revision from the end of the commit message.
+      # Get the actual git hash in case the revision is something like "HEAD~1"
+      git_hash = git('rev-parse', '--verify', args.revision + '^{commit}')
+      svn_rev = lookup_llvm_svn_id(git_hash)
 
-    oneline = git('log', '--all',  '-1', '--format=%H %s', '--grep',
-                  'llvm-svn: ' + svn_rev)
-    if len(oneline) == 0:
-      die("Can't find svn revision r" + svn_rev)
-    (git_hash, msg) = oneline.split(' ', 1)
+    msg = git('log', '-1', '--format=%s', git_hash)
 
-    log_verbose('Ready to revert r%s/%s: "%s"' % (svn_rev, git_hash, msg))
+    log_verbose('Ready to revert r%d (%s): "%s"' % (svn_rev, git_hash, msg))
 
     revert_args = ['revert', '--no-commit', git_hash]
     # TODO: Running --edit doesn't seem to work, with errors that stdin is not
     # a tty.
     commit_args = [
         'commit', '-m', 'Revert ' + msg,
-        '-m', 'This reverts r%s (git commit %s)' % (svn_rev, git_hash)]
+        '-m', 'This reverts r%d (git commit %s)' % (svn_rev, git_hash)]
     if args.dry_run:
       log("Would have run the following commands, if this weren't a dry run:\n"
           '1) git %s\n2) git %s' % (
@@ -487,7 +523,7 @@ def cmd_revert(args):
     git(*revert_args)
     commit_log = git(*commit_args)
 
-    log('Created revert of r%s: %s' % (svn_rev, commit_log))
+    log('Created revert of r%d: %s' % (svn_rev, commit_log))
     log("Run 'git llvm push -n' to inspect your changes and "
         "run 'git llvm push' when ready")