revlog: addgroup checks if incoming deltas add censored revs, sets flag bit

A censored revision stored in a revlog should have the censored revlog index
flag bit set. This implies we must know if a revision is censored before we
add it to the revlog. When adding revisions from exchanged deltas, we would
prefer to determine this flag without decoding every single full text.

This change introduces a heuristic based on assumptions around the Mercurial
delta format and filelog metadata. Since deltas which produce a censored
revision must be full-replacement deltas, we can read the delta's first bytes
to check the filelog metadata. Since "censored" is the alphabetically first
filelog metadata key, censored filelog revisions have a well-known prefix we
can look for.

For more on the design and background of the censorship feature, see:
http://mercurial.selenic.com/wiki/CensorPlan

mercurial/filelog.py

@@ -5,8 +5,8 b''
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
-import error, revlog
-import re
+import error, mdiff, revlog
+import re, struct
 
 _mdre = re.compile('\1\n')
 def parsemeta(text):
@@ -107,3 +107,23 b' class filelog(revlog.revlog):'
     def iscensored(self, rev):
         """Check if a file revision is censored."""
         return self.flags(rev) & revlog.REVIDX_ISCENSORED
+
+    def _peek_iscensored(self, baserev, delta, flush):
+        """Quickly check if a delta produces a censored revision."""
+        # Fragile heuristic: unless new file meta keys are added alphabetically
+        # preceding "censored", all censored revisions are prefixed by
+        # "\1\ncensored:". A delta producing such a censored revision must be a
+        # full-replacement delta, so we inspect the first and only patch in the
+        # delta for this prefix.
+        hlen = struct.calcsize(">lll")
+        if len(delta) <= hlen:
+            return False
+
+        oldlen = self.rawsize(baserev)
+        newlen = len(delta) - hlen
+        if delta[:hlen] != mdiff.replacediffheader(oldlen, newlen):
+            return False
+
+        add = "\1\ncensored:"
+        addlen = len(add)
+        return newlen >= addlen and delta[hlen:hlen + addlen] == add

mercurial/revlog.py

@@ -1386,7 +1386,10 b' class revlog(object):'
             transaction.add(self.indexfile, isize, r)
             transaction.add(self.datafile, end)
             dfh = self.opener(self.datafile, "a")
-
+        def flush():
+            if dfh:
+                dfh.flush()
+            ifh.flush()
         try:
             # loop through our set of deltas
             chain = None
@@ -1430,9 +1433,13 b' class revlog(object):'
                         raise error.CensoredBaseError(self.indexfile,
                                                       self.node(baserev))
 
+                flags = REVIDX_DEFAULT_FLAGS
+                if self._peek_iscensored(baserev, delta, flush):
+                    flags |= REVIDX_ISCENSORED
+
                 chain = self._addrevision(node, None, transaction, link,
-                                          p1, p2, REVIDX_DEFAULT_FLAGS,
-                                          (baserev, delta), ifh, dfh)
+                                          p1, p2, flags, (baserev, delta),
+                                          ifh, dfh)
                 if not dfh and not self._inline:
                     # addrevision switched from inline to conventional
                     # reopen the index
@@ -1450,6 +1457,10 b' class revlog(object):'
         """Check if a file revision is censored."""
         return False
 
+    def _peek_iscensored(self, baserev, delta, flush):
+        """Quickly check if a delta produces a censored revision."""
+        return False
+
     def getstrippoint(self, minlink):
         """find the minimum rev that must be stripped to strip the linkrev