Merge branch 'ls/p4-lfs'

Teach "git p4" to send large blobs outside the repository by
talking to Git LFS.

* ls/p4-lfs:
  git-p4: add Git LFS backend for large file system
  git-p4: add support for large file systems
  git-p4: check free space during streaming
  git-p4: add file streaming progress in verbose mode
  git-p4: return an empty list if a list config has no values
  git-p4: add gitConfigInt reader
  git-p4: add optional type specifier to gitConfig reader

1 files changed, 254 insertions, 16 deletions

diff --git a/git-p4.py b/git-p4.py
index 4915e83..daa60c6 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -22,6 +22,8 @@ import platform
 import re
 import shutil
 import stat
+import zipfile
+import zlib
 
 try:
     from subprocess import CalledProcessError
@@ -104,6 +106,16 @@ def chdir(path, is_client_path=False):
         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)
@@ -602,9 +614,12 @@ def gitBranchExists(branch):
 
 _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]
@@ -615,16 +630,26 @@ def gitConfigBool(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):
@@ -907,6 +932,182 @@ def wildcard_present(path):
     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?')
+        pointerContents = [i+'\n' for i in pointerFile.split('\n')[2:][:-1]]
+        oid = pointerContents[1].split(' ')[1].split(':')[1][:-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, pointerContents, 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]"
@@ -1080,6 +1281,9 @@ class P4Submit(Command, P4UserMap):
         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.")
@@ -2030,6 +2234,13 @@ class P4Sync(Command, P4UserMap):
         self.clientSpecDirs = None
         self.tempBranches = []
         self.tempBranchLocation = "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
@@ -2150,13 +2361,22 @@ class P4Sync(Command, P4UserMap):
 
         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"])
 
@@ -2235,24 +2455,21 @@ class P4Sync(Command, P4UserMap):
             if self.verbose:
                 print 'Path with non-ASCII characters detected. Used %s to encode: %s ' % (encoding, relPath)
 
-        self.gitStream.write("M %s inline %s\n" % (git_mode, relPath))
+        if self.largeFileSystem:
+            (git_mode, contents) = self.largeFileSystem.processContent(git_mode, relPath, contents)
 
-        # total length...
-        length = 0
-        for d in contents:
-            length = length + len(d)
-
-        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):
 
@@ -2262,6 +2479,14 @@ class P4Sync(Command, P4UserMap):
             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:
@@ -2290,10 +2515,23 @@ class P4Sync(Command, P4UserMap):
         # '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"