import re
import shutil
import stat
+import zipfile
+import zlib
+import ctypes
try:
from subprocess import CalledProcessError
path = os.getcwd()
os.environ['PWD'] = path
+def calcDiskFree():
+ """Return free space in bytes on the disk of the given dirname."""
+ if platform.system() == 'Windows':
+ free_bytes = ctypes.c_ulonglong(0)
+ ctypes.windll.kernel32.GetDiskFreeSpaceExW(ctypes.c_wchar_p(os.getcwd()), None, None, ctypes.pointer(free_bytes))
+ return free_bytes.value
+ else:
+ st = os.statvfs(os.getcwd())
+ return st.f_bavail * st.f_frsize
+
def die(msg):
if verbose:
raise Exception(msg)
def p4_delete(f):
p4_system(["delete", wildcard_encode(f)])
-def p4_edit(f):
- p4_system(["edit", wildcard_encode(f)])
+def p4_edit(f, *options):
+ p4_system(["edit"] + list(options) + [wildcard_encode(f)])
def p4_revert(f):
p4_system(["revert", wildcard_encode(f)])
_gitConfig = {}
-def gitConfig(key):
+def gitConfig(key, typeSpecifier=None):
if not _gitConfig.has_key(key):
- cmd = [ "git", "config", key ]
+ cmd = [ "git", "config" ]
+ if typeSpecifier:
+ cmd += [ typeSpecifier ]
+ cmd += [ key ]
s = read_pipe(cmd, ignore_error=True)
_gitConfig[key] = s.strip()
return _gitConfig[key]
in the config."""
if not _gitConfig.has_key(key):
- cmd = [ "git", "config", "--bool", key ]
+ _gitConfig[key] = gitConfig(key, '--bool') == "true"
+ return _gitConfig[key]
+
+def gitConfigInt(key):
+ if not _gitConfig.has_key(key):
+ cmd = [ "git", "config", "--int", key ]
s = read_pipe(cmd, ignore_error=True)
v = s.strip()
- _gitConfig[key] = v == "true"
+ try:
+ _gitConfig[key] = int(gitConfig(key, '--int'))
+ except ValueError:
+ _gitConfig[key] = None
return _gitConfig[key]
def gitConfigList(key):
if not _gitConfig.has_key(key):
s = read_pipe(["git", "config", "--get-all", key], ignore_error=True)
_gitConfig[key] = s.strip().split(os.linesep)
+ if _gitConfig[key] == ['']:
+ _gitConfig[key] = []
return _gitConfig[key]
def p4BranchesInGit(branchesAreInRemotes=True):
die("cannot use --changes-block-size with non-numeric revisions")
block_size = None
- # Accumulate change numbers in a dictionary to avoid duplicates
- changes = {}
+ changes = []
- for p in depotPaths:
- # Retrieve changes a block at a time, to prevent running
- # into a MaxResults/MaxScanRows error from the server.
+ # Retrieve changes a block at a time, to prevent running
+ # into a MaxResults/MaxScanRows error from the server.
- while True:
- cmd = ['changes']
+ while True:
+ cmd = ['changes']
- if block_size:
- end = min(changeEnd, changeStart + block_size)
- revisionRange = "%d,%d" % (changeStart, end)
- else:
- revisionRange = "%s,%s" % (changeStart, changeEnd)
+ if block_size:
+ end = min(changeEnd, changeStart + block_size)
+ revisionRange = "%d,%d" % (changeStart, end)
+ else:
+ revisionRange = "%s,%s" % (changeStart, changeEnd)
+ for p in depotPaths:
cmd += ["%s...@%s" % (p, revisionRange)]
- for line in p4_read_pipe_lines(cmd):
- changeNum = int(line.split(" ")[1])
- changes[changeNum] = True
+ # Insert changes in chronological order
+ for line in reversed(p4_read_pipe_lines(cmd)):
+ changes.append(int(line.split(" ")[1]))
- if not block_size:
- break
+ if not block_size:
+ break
- if end >= changeEnd:
- break
+ if end >= changeEnd:
+ break
- changeStart = end + 1
+ changeStart = end + 1
- changelist = changes.keys()
- changelist.sort()
- return changelist
+ changes = sorted(changes)
+ return changes
def p4PathStartsWith(path, prefix):
# This method tries to remedy a potential mixed-case issue:
m = re.search("[*#@%]", path)
return m is not None
+class LargeFileSystem(object):
+ """Base class for large file system support."""
+
+ def __init__(self, writeToGitStream):
+ self.largeFiles = set()
+ self.writeToGitStream = writeToGitStream
+
+ def generatePointer(self, cloneDestination, contentFile):
+ """Return the content of a pointer file that is stored in Git instead of
+ the actual content."""
+ assert False, "Method 'generatePointer' required in " + self.__class__.__name__
+
+ def pushFile(self, localLargeFile):
+ """Push the actual content which is not stored in the Git repository to
+ a server."""
+ assert False, "Method 'pushFile' required in " + self.__class__.__name__
+
+ def hasLargeFileExtension(self, relPath):
+ return reduce(
+ lambda a, b: a or b,
+ [relPath.endswith('.' + e) for e in gitConfigList('git-p4.largeFileExtensions')],
+ False
+ )
+
+ def generateTempFile(self, contents):
+ contentFile = tempfile.NamedTemporaryFile(prefix='git-p4-large-file', delete=False)
+ for d in contents:
+ contentFile.write(d)
+ contentFile.close()
+ return contentFile.name
+
+ def exceedsLargeFileThreshold(self, relPath, contents):
+ if gitConfigInt('git-p4.largeFileThreshold'):
+ contentsSize = sum(len(d) for d in contents)
+ if contentsSize > gitConfigInt('git-p4.largeFileThreshold'):
+ return True
+ if gitConfigInt('git-p4.largeFileCompressedThreshold'):
+ contentsSize = sum(len(d) for d in contents)
+ if contentsSize <= gitConfigInt('git-p4.largeFileCompressedThreshold'):
+ return False
+ contentTempFile = self.generateTempFile(contents)
+ compressedContentFile = tempfile.NamedTemporaryFile(prefix='git-p4-large-file', delete=False)
+ zf = zipfile.ZipFile(compressedContentFile.name, mode='w')
+ zf.write(contentTempFile, compress_type=zipfile.ZIP_DEFLATED)
+ zf.close()
+ compressedContentsSize = zf.infolist()[0].compress_size
+ os.remove(contentTempFile)
+ os.remove(compressedContentFile.name)
+ if compressedContentsSize > gitConfigInt('git-p4.largeFileCompressedThreshold'):
+ return True
+ return False
+
+ def addLargeFile(self, relPath):
+ self.largeFiles.add(relPath)
+
+ def removeLargeFile(self, relPath):
+ self.largeFiles.remove(relPath)
+
+ def isLargeFile(self, relPath):
+ return relPath in self.largeFiles
+
+ def processContent(self, git_mode, relPath, contents):
+ """Processes the content of git fast import. This method decides if a
+ file is stored in the large file system and handles all necessary
+ steps."""
+ if self.exceedsLargeFileThreshold(relPath, contents) or self.hasLargeFileExtension(relPath):
+ contentTempFile = self.generateTempFile(contents)
+ (git_mode, contents, localLargeFile) = self.generatePointer(contentTempFile)
+
+ # Move temp file to final location in large file system
+ largeFileDir = os.path.dirname(localLargeFile)
+ if not os.path.isdir(largeFileDir):
+ os.makedirs(largeFileDir)
+ shutil.move(contentTempFile, localLargeFile)
+ self.addLargeFile(relPath)
+ if gitConfigBool('git-p4.largeFilePush'):
+ self.pushFile(localLargeFile)
+ if verbose:
+ sys.stderr.write("%s moved to large file system (%s)\n" % (relPath, localLargeFile))
+ return (git_mode, contents)
+
+class MockLFS(LargeFileSystem):
+ """Mock large file system for testing."""
+
+ def generatePointer(self, contentFile):
+ """The pointer content is the original content prefixed with "pointer-".
+ The local filename of the large file storage is derived from the file content.
+ """
+ with open(contentFile, 'r') as f:
+ content = next(f)
+ gitMode = '100644'
+ pointerContents = 'pointer-' + content
+ localLargeFile = os.path.join(os.getcwd(), '.git', 'mock-storage', 'local', content[:-1])
+ return (gitMode, pointerContents, localLargeFile)
+
+ def pushFile(self, localLargeFile):
+ """The remote filename of the large file storage is the same as the local
+ one but in a different directory.
+ """
+ remotePath = os.path.join(os.path.dirname(localLargeFile), '..', 'remote')
+ if not os.path.exists(remotePath):
+ os.makedirs(remotePath)
+ shutil.copyfile(localLargeFile, os.path.join(remotePath, os.path.basename(localLargeFile)))
+
+class GitLFS(LargeFileSystem):
+ """Git LFS as backend for the git-p4 large file system.
+ See https://git-lfs.github.com/ for details."""
+
+ def __init__(self, *args):
+ LargeFileSystem.__init__(self, *args)
+ self.baseGitAttributes = []
+
+ def generatePointer(self, contentFile):
+ """Generate a Git LFS pointer for the content. Return LFS Pointer file
+ mode and content which is stored in the Git repository instead of
+ the actual content. Return also the new location of the actual
+ content.
+ """
+ pointerProcess = subprocess.Popen(
+ ['git', 'lfs', 'pointer', '--file=' + contentFile],
+ stdout=subprocess.PIPE
+ )
+ pointerFile = pointerProcess.stdout.read()
+ if pointerProcess.wait():
+ os.remove(contentFile)
+ die('git-lfs pointer command failed. Did you install the extension?')
+
+ # Git LFS removed the preamble in the output of the 'pointer' command
+ # starting from version 1.2.0. Check for the preamble here to support
+ # earlier versions.
+ # c.f. https://github.com/github/git-lfs/commit/da2935d9a739592bc775c98d8ef4df9c72ea3b43
+ if pointerFile.startswith('Git LFS pointer for'):
+ pointerFile = re.sub(r'Git LFS pointer for.*\n\n', '', pointerFile)
+
+ oid = re.search(r'^oid \w+:(\w+)', pointerFile, re.MULTILINE).group(1)
+ localLargeFile = os.path.join(
+ os.getcwd(),
+ '.git', 'lfs', 'objects', oid[:2], oid[2:4],
+ oid,
+ )
+ # LFS Spec states that pointer files should not have the executable bit set.
+ gitMode = '100644'
+ return (gitMode, pointerFile, localLargeFile)
+
+ def pushFile(self, localLargeFile):
+ uploadProcess = subprocess.Popen(
+ ['git', 'lfs', 'push', '--object-id', 'origin', os.path.basename(localLargeFile)]
+ )
+ if uploadProcess.wait():
+ die('git-lfs push command failed. Did you define a remote?')
+
+ def generateGitAttributes(self):
+ return (
+ self.baseGitAttributes +
+ [
+ '\n',
+ '#\n',
+ '# Git LFS (see https://git-lfs.github.com/)\n',
+ '#\n',
+ ] +
+ ['*.' + f.replace(' ', '[[:space:]]') + ' filter=lfs -text\n'
+ for f in sorted(gitConfigList('git-p4.largeFileExtensions'))
+ ] +
+ ['/' + f.replace(' ', '[[:space:]]') + ' filter=lfs -text\n'
+ for f in sorted(self.largeFiles) if not self.hasLargeFileExtension(f)
+ ]
+ )
+
+ def addLargeFile(self, relPath):
+ LargeFileSystem.addLargeFile(self, relPath)
+ self.writeToGitStream('100644', '.gitattributes', self.generateGitAttributes())
+
+ def removeLargeFile(self, relPath):
+ LargeFileSystem.removeLargeFile(self, relPath)
+ self.writeToGitStream('100644', '.gitattributes', self.generateGitAttributes())
+
+ def processContent(self, git_mode, relPath, contents):
+ if relPath == '.gitattributes':
+ self.baseGitAttributes = contents
+ return (git_mode, self.generateGitAttributes())
+ else:
+ return LargeFileSystem.processContent(self, git_mode, relPath, contents)
+
class Command:
def __init__(self):
self.usage = "usage: %prog [options]"
self.users[output["User"]] = output["FullName"] + " <" + output["Email"] + ">"
self.emails[output["Email"]] = output["User"]
+ mapUserConfigRegex = re.compile(r"^\s*(\S+)\s*=\s*(.+)\s*<(\S+)>\s*$", re.VERBOSE)
+ for mapUserConfig in gitConfigList("git-p4.mapUser"):
+ mapUser = mapUserConfigRegex.findall(mapUserConfig)
+ if mapUser and len(mapUser[0]) == 3:
+ user = mapUser[0][0]
+ fullname = mapUser[0][1]
+ email = mapUser[0][2]
+ self.users[user] = fullname + " <" + email + ">"
+ self.emails[email] = user
s = ''
for (key, val) in self.users.items():
self.p4HasMoveCommand = p4_has_move_command()
self.branch = None
+ if gitConfig('git-p4.largeFileSystem'):
+ die("Large file system not supported for git-p4 submit command. Please remove it from config.")
+
def check(self):
if len(p4CmdList("opened ...")) > 0:
die("You have files opened with perforce! Close them before starting the sync.")
Remove lines in the Files section that show changes to files
outside the depot path we're committing into."""
+ [upstream, settings] = findUpstreamBranchPoint()
+
template = ""
inFilesSection = False
for line in p4_read_pipe_lines(['change', '-o']):
lastTab = path.rfind("\t")
if lastTab != -1:
path = path[:lastTab]
- if not p4PathStartsWith(path, self.depotPath):
- continue
+ if settings.has_key('depot-paths'):
+ if not [p for p in settings['depot-paths']
+ if p4PathStartsWith(path, p)]:
+ continue
+ else:
+ if not p4PathStartsWith(path, self.depotPath):
+ continue
else:
inFilesSection = False
else:
diff = read_pipe_lines("git diff-tree -r %s \"%s^\" \"%s\"" % (self.diffOpts, id, id))
filesToAdd = set()
+ filesToChangeType = set()
filesToDelete = set()
editedFiles = set()
pureRenameCopy = set()
os.unlink(dest)
filesToDelete.add(src)
editedFiles.add(dest)
+ elif modifier == "T":
+ filesToChangeType.add(path)
else:
die("unknown modifier %s for %s" % (modifier, path))
#
system(applyPatchCmd)
+ for f in filesToChangeType:
+ p4_edit(f, "-t", "auto")
for f in filesToAdd:
p4_add(f)
for f in filesToDelete:
if self.useClientSpec:
self.clientSpecDirs = getClientSpec()
- # Check for the existance of P4 branches
+ # Check for the existence of P4 branches
branchesDetected = (len(p4BranchesInGit().keys()) > 1)
if self.useClientSpec and not branchesDetected:
self.useClientSpec_from_options = False
self.clientSpecDirs = None
self.tempBranches = []
- self.tempBranchLocation = "git-p4-tmp"
+ self.tempBranchLocation = "refs/git-p4-tmp"
+ self.largeFileSystem = None
+
+ if gitConfig('git-p4.largeFileSystem'):
+ largeFileSystemConstructor = globals()[gitConfig('git-p4.largeFileSystem')]
+ self.largeFileSystem = largeFileSystemConstructor(
+ lambda git_mode, relPath, contents: self.writeToGitStream(git_mode, relPath, contents)
+ )
if gitConfig("git-p4.syncFromOrigin") == "false":
self.syncWithOrigin = False
fnum = fnum + 1
return files
+ def extractJobsFromCommit(self, commit):
+ jobs = []
+ jnum = 0
+ while commit.has_key("job%s" % jnum):
+ job = commit["job%s" % jnum]
+ jobs.append(job)
+ jnum = jnum + 1
+ return jobs
+
def stripRepoPath(self, path, prefixes):
"""When streaming files, this is called to map a p4 depot path
to where it should go in git. The prefixes are either
return branches
+ def writeToGitStream(self, gitMode, relPath, contents):
+ self.gitStream.write('M %s inline %s\n' % (gitMode, relPath))
+ self.gitStream.write('data %d\n' % sum(len(d) for d in contents))
+ for d in contents:
+ self.gitStream.write(d)
+ self.gitStream.write('\n')
+
# output one file from the P4 stream
# - helper for streamP4Files
def streamOneP4File(self, file, contents):
relPath = self.stripRepoPath(file['depotFile'], self.branchPrefixes)
if verbose:
- sys.stderr.write("%s\n" % relPath)
+ size = int(self.stream_file['fileSize'])
+ sys.stdout.write('\r%s --> %s (%i MB)\n' % (file['depotFile'], relPath, size/1024/1024))
+ sys.stdout.flush()
(type_base, type_mods) = split_p4_type(file["type"])
text = regexp.sub(r'$\1$', text)
contents = [ text ]
- self.gitStream.write("M %s inline %s\n" % (git_mode, relPath))
+ try:
+ relPath.decode('ascii')
+ except:
+ encoding = 'utf8'
+ if gitConfig('git-p4.pathEncoding'):
+ encoding = gitConfig('git-p4.pathEncoding')
+ relPath = relPath.decode(encoding, 'replace').encode('utf8', 'replace')
+ if self.verbose:
+ print 'Path with non-ASCII characters detected. Used %s to encode: %s ' % (encoding, relPath)
- # total length...
- length = 0
- for d in contents:
- length = length + len(d)
+ if self.largeFileSystem:
+ (git_mode, contents) = self.largeFileSystem.processContent(git_mode, relPath, contents)
- self.gitStream.write("data %d\n" % length)
- for d in contents:
- self.gitStream.write(d)
- self.gitStream.write("\n")
+ self.writeToGitStream(git_mode, relPath, contents)
def streamOneP4Deletion(self, file):
relPath = self.stripRepoPath(file['path'], self.branchPrefixes)
if verbose:
- sys.stderr.write("delete %s\n" % relPath)
+ sys.stdout.write("delete %s\n" % relPath)
+ sys.stdout.flush()
self.gitStream.write("D %s\n" % relPath)
+ if self.largeFileSystem and self.largeFileSystem.isLargeFile(relPath):
+ self.largeFileSystem.removeLargeFile(relPath)
+
# handle another chunk of streaming data
def streamP4FilesCb(self, marshalled):
if marshalled["code"] == "error":
if "data" in marshalled:
err = marshalled["data"].rstrip()
+
+ if not err and 'fileSize' in self.stream_file:
+ required_bytes = int((4 * int(self.stream_file["fileSize"])) - calcDiskFree())
+ if required_bytes > 0:
+ err = 'Not enough space left on %s! Free at least %i MB.' % (
+ os.getcwd(), required_bytes/1024/1024
+ )
+
if err:
f = None
if self.stream_have_file_info:
# 'data' field we need to append to our array
for k in marshalled.keys():
if k == 'data':
+ if 'streamContentSize' not in self.stream_file:
+ self.stream_file['streamContentSize'] = 0
+ self.stream_file['streamContentSize'] += len(marshalled['data'])
self.stream_contents.append(marshalled['data'])
else:
self.stream_file[k] = marshalled[k]
+ if (verbose and
+ 'streamContentSize' in self.stream_file and
+ 'fileSize' in self.stream_file and
+ 'depotFile' in self.stream_file):
+ size = int(self.stream_file["fileSize"])
+ if size > 0:
+ progress = 100*self.stream_file['streamContentSize']/size
+ sys.stdout.write('\r%s %d%% (%i MB)' % (self.stream_file['depotFile'], progress, int(size/1024/1024)))
+ sys.stdout.flush()
+
self.stream_have_file_info = True
# Stream directly from "p4 files" into "git fast-import"
return True
hasPrefix = [p for p in self.branchPrefixes
if p4PathStartsWith(path, p)]
- if hasPrefix and self.verbose:
+ if not hasPrefix and self.verbose:
print('Ignoring file outside of prefix: {0}'.format(path))
return hasPrefix
def commit(self, details, files, branch, parent = ""):
epoch = details["time"]
author = details["user"]
+ jobs = self.extractJobsFromCommit(details)
if self.verbose:
print('commit into {0}'.format(branch))
self.gitStream.write("data <<EOT\n")
self.gitStream.write(details["desc"])
+ if len(jobs) > 0:
+ self.gitStream.write("\nJobs: %s" % (' '.join(jobs)))
self.gitStream.write("\n[git-p4: depot-paths = \"%s\": change = %s" %
(','.join(self.branchPrefixes), details["change"]))
if len(details['options']) > 0: