diff mercurial/manifest.py @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801)

Previously, removed files would simply be marked by overwriting the first byte
with NUL and dropping their entry in `self.position`.  But no effort was made to
ignore them when compacting the dictionary into text form.  This allowed them to
slip into the manifest revision, since the code seems to be trying to minimize
the string operations by copying as large a chunk as possible.  As part of this,
compact() walks the existing text based on entries in the `positions` list, and
consumed everything up to the next position entry.   This typically resulted in
a ValueError complaining about unsorted manifest entries.

Sometimes it seems that files do get dropped in large repos- it seems to
correspond to there being a new entry that would take the same slot.  A much
more trivial problem is that if the only changes were removals, `_compact()`
didn't even run because `__delitem__` doesn't add anything to `self.extradata`.
Now there's an explicit variable to flag this, both to allow `_compact()` to
run, and to avoid searching the manifest in cases where there are no removals.

In practice, this behavior was mostly obscured by the check in fastdelta() which
takes a different path that explicitly drops removed files if there are fewer
than 1000 changes.  However, timeless has a repo where after rebasing tens of
commits, a totally different path[1] is taken that bypasses the change count
check and hits this problem.

[1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511

--- a/mercurial/manifest.py	Thu May 23 21:39:19 2019 -0400
+++ b/mercurial/manifest.py	Thu May 23 21:54:24 2019 -0400
@@ -126,17 +126,20 @@
     return (a > b) - (a < b)
 
 class _lazymanifest(object):
-    def __init__(self, data, positions=None, extrainfo=None, extradata=None):
+    def __init__(self, data, positions=None, extrainfo=None, extradata=None,
+                 hasremovals=False):
         if positions is None:
             self.positions = self.findlines(data)
             self.extrainfo = [0] * len(self.positions)
             self.data = data
             self.extradata = []
+            self.hasremovals = False
         else:
             self.positions = positions[:]
             self.extrainfo = extrainfo[:]
             self.extradata = extradata[:]
             self.data = data
+            self.hasremovals = hasremovals
 
     def findlines(self, data):
         if not data:
@@ -244,6 +247,7 @@
         self.extrainfo = self.extrainfo[:needle] + self.extrainfo[needle + 1:]
         if cur >= 0:
             self.data = self.data[:cur] + '\x00' + self.data[cur + 1:]
+            self.hasremovals = True
 
     def __setitem__(self, key, value):
         if not isinstance(key, bytes):
@@ -279,11 +283,11 @@
     def copy(self):
         # XXX call _compact like in C?
         return _lazymanifest(self.data, self.positions, self.extrainfo,
-            self.extradata)
+            self.extradata, self.hasremovals)
 
     def _compact(self):
         # hopefully not called TOO often
-        if len(self.extradata) == 0:
+        if len(self.extradata) == 0 and not self.hasremovals:
             return
         l = []
         i = 0
@@ -298,6 +302,16 @@
                     i += 1
                     if i == len(self.positions) or self.positions[i] < 0:
                         break
+
+                    # A removed file has no positions[] entry, but does have an
+                    # overwritten first byte.  Break out and find the end of the
+                    # current good entry/entries if there is a removed file
+                    # before the next position.
+                    if (self.hasremovals
+                        and self.data.find('\n\x00', cur,
+                                           self.positions[i]) != -1):
+                        break
+
                     offset += self.positions[i] - cur
                     cur = self.positions[i]
                 end_cut = self.data.find('\n', cur)
@@ -316,6 +330,7 @@
                     offset += len(l[-1])
                     i += 1
         self.data = ''.join(l)
+        self.hasremovals = False
         self.extradata = []
 
     def _pack(self, d):