view tests/test-flagprocessor.t @ 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

# Create server
  $ hg init server
  $ cd server
  $ cat >> .hg/hgrc << EOF
  > [extensions]
  > extension=$TESTDIR/flagprocessorext.py
  > EOF
  $ cd ../

# Clone server and enable extensions
  $ hg clone -q server client
  $ cd client
  $ cat >> .hg/hgrc << EOF
  > [extensions]
  > extension=$TESTDIR/flagprocessorext.py
  > EOF

# Commit file that will trigger the noop extension
  $ echo '[NOOP]' > noop
  $ hg commit -Aqm "noop"

# Commit file that will trigger the base64 extension
  $ echo '[BASE64]' > base64
  $ hg commit -Aqm 'base64'

# Commit file that will trigger the gzip extension
  $ echo '[GZIP]' > gzip
  $ hg commit -Aqm 'gzip'

# Commit file that will trigger noop and base64
  $ echo '[NOOP][BASE64]' > noop-base64
  $ hg commit -Aqm 'noop+base64'

# Commit file that will trigger noop and gzip
  $ echo '[NOOP][GZIP]' > noop-gzip
  $ hg commit -Aqm 'noop+gzip'

# Commit file that will trigger base64 and gzip
  $ echo '[BASE64][GZIP]' > base64-gzip
  $ hg commit -Aqm 'base64+gzip'

# Commit file that will trigger base64, gzip and noop
  $ echo '[BASE64][GZIP][NOOP]' > base64-gzip-noop
  $ hg commit -Aqm 'base64+gzip+noop'

# TEST: ensure the revision data is consistent
  $ hg cat noop
  [NOOP]
  $ hg debugdata noop 0
  [NOOP]

  $ hg cat -r . base64
  [BASE64]
  $ hg debugdata base64 0
  W0JBU0U2NF0K (no-eol)

  $ hg cat -r . gzip
  [GZIP]
  $ hg debugdata gzip 0
  x\x9c\x8bv\x8f\xf2\x0c\x88\xe5\x02\x00\x08\xc8\x01\xfd (no-eol) (esc)

  $ hg cat -r . noop-base64
  [NOOP][BASE64]
  $ hg debugdata noop-base64 0
  W05PT1BdW0JBU0U2NF0K (no-eol)

  $ hg cat -r . noop-gzip
  [NOOP][GZIP]
  $ hg debugdata noop-gzip 0
  x\x9c\x8b\xf6\xf3\xf7\x0f\x88\x8dv\x8f\xf2\x0c\x88\xe5\x02\x00\x1dH\x03\xf1 (no-eol) (esc)

  $ hg cat -r . base64-gzip
  [BASE64][GZIP]
  $ hg debugdata base64-gzip 0
  eJyLdnIMdjUziY12j/IMiOUCACLBBDo= (no-eol)

  $ hg cat -r . base64-gzip-noop
  [BASE64][GZIP][NOOP]
  $ hg debugdata base64-gzip-noop 0
  eJyLdnIMdjUziY12j/IMiI328/cPiOUCAESjBi4= (no-eol)

# Push to the server
  $ hg push
  pushing to $TESTTMP/server
  searching for changes
  adding changesets
  adding manifests
  adding file changes
  added 7 changesets with 7 changes to 7 files

Ensure the data got to the server OK

  $ cd ../server
  $ hg cat -r 6e48f4215d24 noop
  [NOOP]
  $ hg debugdata noop 0
  [NOOP]

  $ hg cat -r 6e48f4215d24 base64
  [BASE64]
  $ hg debugdata base64 0
  W0JBU0U2NF0K (no-eol)

  $ hg cat -r 6e48f4215d24 gzip
  [GZIP]
  $ hg debugdata gzip 0
  x\x9c\x8bv\x8f\xf2\x0c\x88\xe5\x02\x00\x08\xc8\x01\xfd (no-eol) (esc)

  $ hg cat -r 6e48f4215d24 noop-base64
  [NOOP][BASE64]
  $ hg debugdata noop-base64 0
  W05PT1BdW0JBU0U2NF0K (no-eol)

  $ hg cat -r 6e48f4215d24 noop-gzip
  [NOOP][GZIP]
  $ hg debugdata noop-gzip 0
  x\x9c\x8b\xf6\xf3\xf7\x0f\x88\x8dv\x8f\xf2\x0c\x88\xe5\x02\x00\x1dH\x03\xf1 (no-eol) (esc)

  $ hg cat -r 6e48f4215d24 base64-gzip
  [BASE64][GZIP]
  $ hg debugdata base64-gzip 0
  eJyLdnIMdjUziY12j/IMiOUCACLBBDo= (no-eol)

  $ hg cat -r 6e48f4215d24 base64-gzip-noop
  [BASE64][GZIP][NOOP]
  $ hg debugdata base64-gzip-noop 0
  eJyLdnIMdjUziY12j/IMiI328/cPiOUCAESjBi4= (no-eol)

# Initialize new client (not cloning) and setup extension
  $ cd ..
  $ hg init client2
  $ cd client2
  $ cat >> .hg/hgrc << EOF
  > [paths]
  > default = $TESTTMP/server
  > [extensions]
  > extension=$TESTDIR/flagprocessorext.py
  > EOF

# Pull from server and update to latest revision
  $ hg pull default
  pulling from $TESTTMP/server
  requesting all changes
  adding changesets
  adding manifests
  adding file changes
  added 7 changesets with 7 changes to 7 files
  new changesets 07b1b9442c5b:6e48f4215d24
  (run 'hg update' to get a working copy)
  $ hg update
  7 files updated, 0 files merged, 0 files removed, 0 files unresolved

# TEST: ensure the revision data is consistent
  $ hg cat noop
  [NOOP]
  $ hg debugdata noop 0
  [NOOP]

  $ hg cat -r . base64
  [BASE64]
  $ hg debugdata base64 0
  W0JBU0U2NF0K (no-eol)

  $ hg cat -r . gzip
  [GZIP]
  $ hg debugdata gzip 0
  x\x9c\x8bv\x8f\xf2\x0c\x88\xe5\x02\x00\x08\xc8\x01\xfd (no-eol) (esc)

  $ hg cat -r . noop-base64
  [NOOP][BASE64]
  $ hg debugdata noop-base64 0
  W05PT1BdW0JBU0U2NF0K (no-eol)

  $ hg cat -r . noop-gzip
  [NOOP][GZIP]
  $ hg debugdata noop-gzip 0
  x\x9c\x8b\xf6\xf3\xf7\x0f\x88\x8dv\x8f\xf2\x0c\x88\xe5\x02\x00\x1dH\x03\xf1 (no-eol) (esc)

  $ hg cat -r . base64-gzip
  [BASE64][GZIP]
  $ hg debugdata base64-gzip 0
  eJyLdnIMdjUziY12j/IMiOUCACLBBDo= (no-eol)

  $ hg cat -r . base64-gzip-noop
  [BASE64][GZIP][NOOP]
  $ hg debugdata base64-gzip-noop 0
  eJyLdnIMdjUziY12j/IMiI328/cPiOUCAESjBi4= (no-eol)

# TEST: ensure a missing processor is handled
  $ echo '[FAIL][BASE64][GZIP][NOOP]' > fail-base64-gzip-noop
  $ hg commit -Aqm 'fail+base64+gzip+noop'
  abort: missing processor for flag '0x1'!
  [255]
  $ rm fail-base64-gzip-noop

# TEST: ensure we cannot register several flag processors on the same flag
  $ cat >> .hg/hgrc << EOF
  > [extensions]
  > extension=$TESTDIR/flagprocessorext.py
  > duplicate=$TESTDIR/flagprocessorext.py
  > EOF
  $ hg debugrebuilddirstate
  Traceback (most recent call last):
    File "*/mercurial/extensions.py", line *, in _runextsetup (glob)
      extsetup(ui)
    File "*/tests/flagprocessorext.py", line *, in extsetup (glob)
      validatehash,
    File "*/mercurial/revlog.py", line *, in addflagprocessor (glob)
      _insertflagprocessor(flag, processor, _flagprocessors)
    File "*/mercurial/revlog.py", line *, in _insertflagprocessor (glob)
      raise error.Abort(msg)
  mercurial.error.Abort: b"cannot register multiple processors on flag '0x8'." (py3 !)
  Abort: cannot register multiple processors on flag '0x8'. (no-py3 !)
  *** failed to set up extension duplicate: cannot register multiple processors on flag '0x8'.
  $ hg st 2>&1 | egrep 'cannot register multiple processors|flagprocessorext'
    File "*/tests/flagprocessorext.py", line *, in extsetup (glob)
  mercurial.error.Abort: b"cannot register multiple processors on flag '0x8'." (py3 !)
  Abort: cannot register multiple processors on flag '0x8'. (no-py3 !)
  *** failed to set up extension duplicate: cannot register multiple processors on flag '0x8'.
    File "*/tests/flagprocessorext.py", line *, in b64decode (glob)

  $ cd ..

# TEST: bundle repo
  $ hg init bundletest
  $ cd bundletest

  $ cat >> .hg/hgrc << EOF
  > [extensions]
  > flagprocessor=$TESTDIR/flagprocessorext.py
  > EOF

  $ for i in 0 single two three 4; do
  >   echo '[BASE64]a-bit-longer-'$i > base64
  >   hg commit -m base64-$i -A base64
  > done

  $ hg update 2 -q
  $ echo '[BASE64]a-bit-longer-branching' > base64
  $ hg commit -q -m branching

#if repobundlerepo
  $ hg bundle --base 1 bundle.hg
  4 changesets found
  $ hg --config extensions.strip= strip -r 2 --no-backup --force -q
  $ hg -R bundle.hg log --stat -T '{rev} {desc}\n' base64
  5 branching
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  4 base64-4
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  3 base64-three
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  2 base64-two
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  1 base64-single
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  0 base64-0
   base64 |  1 +
   1 files changed, 1 insertions(+), 0 deletions(-)
  

  $ hg bundle -R bundle.hg --base 1 bundle-again.hg -q
  $ hg -R bundle-again.hg log --stat -T '{rev} {desc}\n' base64
  5 branching
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  4 base64-4
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  3 base64-three
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  2 base64-two
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  1 base64-single
   base64 |  2 +-
   1 files changed, 1 insertions(+), 1 deletions(-)
  
  0 base64-0
   base64 |  1 +
   1 files changed, 1 insertions(+), 0 deletions(-)
  
  $ rm bundle.hg bundle-again.hg
#endif

# TEST: hg status

  $ hg status
  $ hg diff