git-p4: Search for parent commit on branch creation

To find out which is its parent the commit of the new branch is compared
sequentially to each blob of the parent branch from the newest to the
oldest. The first blob which results in a zero diff is considered the
parent commit. If none is found, then the commit is applied to the top
of the parent branch.

A fast-import "checkpoint" call is required because diff-tree is only
able to work with blobs on disk. But most of these commits will not be
part of the final imported tree, making fast-import fail. To avoid this,
the temporary branches are tracked and then removed at the end of the
import process.

Signed-off-by: Vitor Antunes <vitor.hda@gmail.com>
Acked-by: Pete Wyckoff <pw@padd.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 45 insertions, 1 deletions

diff --git a/contrib/fast-import/git-p4 b/contrib/fast-import/git-p4
index bcb0e6cd2..0bf262507 100755
--- a/contrib/fast-import/git-p4
+++ b/contrib/fast-import/git-p4
@@ -1429,6 +1429,8 @@ class P4Sync(Command, P4UserMap):
         self.cloneExclude = []
         self.useClientSpec = False
         self.clientSpecDirs = None
+        self.tempBranches = []
+        self.tempBranchLocation = "git-p4-tmp"
 
         if gitConfig("git-p4.syncFromOrigin") == "false":
             self.syncWithOrigin = False
@@ -1450,6 +1452,14 @@ class P4Sync(Command, P4UserMap):
                    .replace("%25", "%")
         return path
 
+    # Force a checkpoint in fast-import and wait for it to finish
+    def checkpoint(self):
+        self.gitStream.write("checkpoint\n\n")
+        self.gitStream.write("progress checkpoint\n\n")
+        out = self.gitOutput.readline()
+        if self.verbose:
+            print "checkpoint finished: " + out
+
     def extractFilesFromCommit(self, commit):
         self.cloneExclude = [re.sub(r"\.\.\.$", "", path)
                              for path in self.cloneExclude]
@@ -1957,6 +1967,20 @@ class P4Sync(Command, P4UserMap):
         self.importChanges(changes)
         return True
 
+    def searchParent(self, parent, branch, target):
+        parentFound = False
+        for blob in read_pipe_lines(["git", "rev-list", "--reverse", "--no-merges", parent]):
+            blob = blob.strip()
+            if len(read_pipe(["git", "diff-tree", blob, target])) == 0:
+                parentFound = True
+                if self.verbose:
+                    print "Found parent of %s in commit %s" % (branch, blob)
+                break
+        if parentFound:
+            return blob
+        else:
+            return None
+
     def importChanges(self, changes):
         cnt = 1
         for change in changes:
@@ -2013,7 +2037,21 @@ class P4Sync(Command, P4UserMap):
                             parent = self.initialParents[branch]
                             del self.initialParents[branch]
 
-                        self.commit(description, filesForCommit, branch, [branchPrefix], parent)
+                        blob = None
+                        if len(parent) > 0:
+                            tempBranch = os.path.join(self.tempBranchLocation, "%d" % (change))
+                            if self.verbose:
+                                print "Creating temporary branch: " + tempBranch
+                            self.commit(description, filesForCommit, tempBranch, [branchPrefix])
+                            self.tempBranches.append(tempBranch)
+                            self.checkpoint()
+                            blob = self.searchParent(parent, branch, tempBranch)
+                        if blob:
+                            self.commit(description, filesForCommit, branch, [branchPrefix], blob)
+                        else:
+                            if self.verbose:
+                                print "Parent of %s not found. Committing into head of %s" % (branch, parent)
+                            self.commit(description, filesForCommit, branch, [branchPrefix], parent)
                 else:
                     files = self.extractFilesFromCommit(description)
                     self.commit(description, files, self.branch, self.depotPaths,
@@ -2348,6 +2386,12 @@ class P4Sync(Command, P4UserMap):
         self.gitOutput.close()
         self.gitError.close()
 
+        # Cleanup temporary branches created during import
+        if self.tempBranches != []:
+            for branch in self.tempBranches:
+                read_pipe("git update-ref -d %s" % branch)
+            os.rmdir(os.path.join(os.environ.get("GIT_DIR", ".git"), self.tempBranchLocation))
+
         return True
 
 class P4Rebase(Command):