changeset 25410:eee88912db0a

revlog: raise an exception earlier if an entry is too large (issue4675)

Before we were relying on _pack to error out when trying to pass an
integer that was too large for the "i" format specifier. Now we check
this earlier so we can form a better error message.

The error message unfortunately must exclude the filename at this
level of the call stack. The problem is that this name is not
available here, and the error can be triggered by a large manifest or
by a large file itself. Although perhaps we could provide the name of
a revlog index file (from the revlog object, instead of the revlogio
object), this seems like too much leakage of internal data structures.
It's not ideal already that an error message even mentions revlogs,
but this does seem unavoidable here.

--- a/mercurial/revlog.py	Wed Jun 03 14:31:19 2015 -0500
+++ b/mercurial/revlog.py	Tue Jun 02 15:04:39 2015 -0400
@@ -153,6 +153,10 @@
 ngshaoffset = 32
 versionformat = ">I"
 
+# corresponds to uncompressed length of indexformatng (2 gigs, 4-byte
+# signed integer)
+_maxentrysize = 0x7fffffff
+
 class revlogio(object):
     def __init__(self):
         self.size = struct.calcsize(indexformatng)
@@ -163,6 +167,12 @@
         return index, getattr(index, 'nodemap', None), cache
 
     def packentry(self, entry, node, version, rev):
+        uncompressedlength = entry[2]
+        if uncompressedlength > _maxentrysize:
+            raise RevlogError(
+                _("size of %d bytes exceeds maximum revlog storage of 2GiB")
+                % uncompressedlength)
+
         p = _pack(indexformatng, *entry)
         if rev == 0:
             p = _pack(versionformat, version) + p[4:]