storageutil: move metadata parsing and packing from revlog (API)

Parsing and writing of revision text metadata is likely identical
across storage backends. Let's move the code out of revlog so we
don't need to import the revlog module in order to use it.

Differential Revision: https://phab.mercurial-scm.org/D4754

hgext/lfs/wrapper.py

@@ -20,6 +20,7 from mercurial import (
 )
 
 from mercurial.utils import (
+    storageutil,
     stringutil,
 )
 
@@ -76,13 +77,13 def readfromstore(self, text):
             name = k[len('x-hg-'):]
             hgmeta[name] = p[k]
     if hgmeta or text.startswith('\1\n'):
-        text = revlog.packmeta(hgmeta, text)
+        text = storageutil.packmeta(hgmeta, text)
 
     return (text, True)
 
 def writetostore(self, text):
     # hg filelog metadata (includes rename, etc)
-    hgmeta, offset = revlog.parsemeta(text)
+    hgmeta, offset = storageutil.parsemeta(text)
     if offset and offset > 0:
         # lfs blob does not contain hg filelog metadata
         text = text[offset:]
@@ -132,7 +133,7 def filelogaddrevision(orig, self, text,
     if lfstrack:
         textlen = len(text)
         # exclude hg rename meta from file size
-        meta, offset = revlog.parsemeta(text)
+        meta, offset = storageutil.parsemeta(text)
         if offset:
             textlen -= offset
 

mercurial/filelog.py

@@ -14,6 +14,7 from . import (
 )
 from .utils import (
     interfaceutil,
+    storageutil,
 )
 
 @interfaceutil.implementer(repository.ifilestorage)
@@ -120,14 +121,14 class filelog(object):
 
     def add(self, text, meta, transaction, link, p1=None, p2=None):
         if meta or text.startswith('\1\n'):
-            text = revlog.packmeta(meta, text)
+            text = storageutil.packmeta(meta, text)
         return self.addrevision(text, transaction, link, p1, p2)
 
     def renamed(self, node):
         if self.parents(node)[0] != revlog.nullid:
             return False
         t = self.revision(node)
-        m = revlog.parsemeta(t)[0]
+        m = storageutil.parsemeta(t)[0]
         # copy and copyrev occur in pairs. In rare cases due to bugs,
         # one can occur without the other.
         if m and "copy" in m and "copyrev" in m:

mercurial/revlog.py

@@ -17,7 +17,6 import collections
 import contextlib
 import errno
 import os
-import re
 import struct
 import zlib
 
@@ -127,27 +126,8 ellipsisprocessor = (
     ellipsisrawprocessor,
 )
 
-_mdre = re.compile('\1\n')
-def parsemeta(text):
-    """return (metadatadict, metadatasize)"""
-    # text can be buffer, so we can't use .startswith or .index
-    if text[:2] != '\1\n':
-        return None, None
-    s = _mdre.search(text, 2).start()
-    mtext = text[2:s]
-    meta = {}
-    for l in mtext.splitlines():
-        k, v = l.split(": ", 1)
-        meta[k] = v
-    return meta, (s + 2)
-
-def packmeta(meta, text):
-    keys = sorted(meta)
-    metatext = "".join("%s: %s\n" % (k, meta[k]) for k in keys)
-    return "\1\n%s\1\n%s" % (metatext, text)
-
 def _censoredtext(text):
-    m, offs = parsemeta(text)
+    m, offs = storageutil.parsemeta(text)
     return m and "censored" in m
 
 def addflagprocessor(flag, processor):
@@ -2516,7 +2496,7 class revlog(object):
                                     self.version)
 
         rev = self.rev(node)
-        tombstone = packmeta({b'censored': tombstone}, b'')
+        tombstone = storageutil.packmeta({b'censored': tombstone}, b'')
 
         if len(tombstone) > self.rawsize(rev):
             raise error.Abort(_('censor tombstone must be no longer than '

mercurial/testing/storage.py

@@ -19,6 +19,9 from .. import (
     mdiff,
     revlog,
 )
+from ..utils import (
+    storageutil,
+)
 
 class basetestcase(unittest.TestCase):
     if not getattr(unittest.TestCase, r'assertRaisesRegex', False):
@@ -882,7 +885,7 class ifiledatatests(basetestcase):
     def testcensored(self):
         f = self._makefilefn()
 
-        stored1 = revlog.packmeta({
+        stored1 = storageutil.packmeta({
             b'censored': b'tombstone',
         }, b'')
 

mercurial/utils/storageutil.py

@@ -8,6 +8,7
 from __future__ import absolute_import
 
 import hashlib
+import re
 
 from ..node import (
     nullid,
@@ -39,3 +40,28 def hashrevisionsha1(text, p1, p2):
         s.update(b)
     s.update(text)
     return s.digest()
+
+METADATA_RE = re.compile(b'\x01\n')
+
+def parsemeta(text):
+    """Parse metadata header from revision data.
+
+    Returns a 2-tuple of (metadata, offset), where both can be None if there
+    is no metadata.
+    """
+    # text can be buffer, so we can't use .startswith or .index
+    if text[:2] != b'\x01\n':
+        return None, None
+    s = METADATA_RE.search(text, 2).start()
+    mtext = text[2:s]
+    meta = {}
+    for l in mtext.splitlines():
+        k, v = l.split(b': ', 1)
+        meta[k] = v
+    return meta, s + 2
+
+def packmeta(meta, text):
+    """Add metadata to fulltext to produce revision text."""
+    keys = sorted(meta)
+    metatext = b''.join(b'%s: %s\n' % (k, meta[k]) for k in keys)
+    return b'\x01\n%s\x01\n%s' % (metatext, text)

tests/simplestorerepo.py

@@ -326,7 +326,7 class filestorage(object):
             return False
 
         fulltext = self.revision(node)
-        m = revlog.parsemeta(fulltext)[0]
+        m = storageutil.parsemeta(fulltext)[0]
 
         if m and 'copy' in m:
             return m['copy'], bin(m['copyrev'])
@@ -411,7 +411,7 class filestorage(object):
 
     def add(self, text, meta, transaction, linkrev, p1, p2):
         if meta or text.startswith(b'\1\n'):
-            text = revlog.packmeta(meta, text)
+            text = storageutil.packmeta(meta, text)
 
         return self.addrevision(text, transaction, linkrev, p1, p2)