view tests/test-convert-bzr-directories.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

#require bzr

  $ . "$TESTDIR/bzr-definitions"

empty directory

  $ mkdir test-empty
  $ cd test-empty
  $ bzr init -q source
  $ cd source
  $ echo content > a
  $ bzr add -q a
  $ bzr commit -q -m 'Initial add'
  $ mkdir empty
  $ bzr add -q empty
  $ bzr commit -q -m 'Empty directory added'
  $ echo content > empty/something
  $ bzr add -q empty/something
  $ bzr commit -q -m 'Added file into directory'
  $ cd ..
  $ hg convert source source-hg
  initializing destination source-hg repository
  scanning source...
  sorting...
  converting...
  2 Initial add
  1 Empty directory added
  0 Added file into directory
  $ manifest source-hg 1
  % manifest of 1
  644   a
  $ manifest source-hg tip
  % manifest of tip
  644   a
  644   empty/something
  $ cd ..

directory renames

  $ mkdir test-dir-rename
  $ cd test-dir-rename
  $ bzr init -q source
  $ cd source
  $ mkdir tpyo
  $ echo content > tpyo/something
  $ bzr add -q tpyo
  $ bzr commit -q -m 'Added directory'
  $ bzr mv tpyo typo
  tpyo => typo
  $ bzr commit -q -m 'Oops, typo'
  $ cd ..
  $ hg convert source source-hg
  initializing destination source-hg repository
  scanning source...
  sorting...
  converting...
  1 Added directory
  0 Oops, typo
  $ manifest source-hg 0
  % manifest of 0
  644   tpyo/something
  $ manifest source-hg tip
  % manifest of tip
  644   typo/something
  $ cd ..

nested directory renames

  $ mkdir test-nested-dir-rename
  $ cd test-nested-dir-rename
  $ bzr init -q source
  $ cd source
  $ mkdir -p firstlevel/secondlevel/thirdlevel
  $ echo content > firstlevel/secondlevel/file
  $ echo this_needs_to_be_there_too > firstlevel/secondlevel/thirdlevel/stuff
  $ bzr add -q firstlevel
  $ bzr commit -q -m 'Added nested directories'
  $ bzr mv firstlevel/secondlevel secondlevel
  firstlevel/secondlevel => secondlevel
  $ bzr commit -q -m 'Moved secondlevel one level up'
  $ cd ..
  $ hg convert source source-hg
  initializing destination source-hg repository
  scanning source...
  sorting...
  converting...
  1 Added nested directories
  0 Moved secondlevel one level up
  $ manifest source-hg tip
  % manifest of tip
  644   secondlevel/file
  644   secondlevel/thirdlevel/stuff
  $ cd ..

directory remove

  $ mkdir test-dir-remove
  $ cd test-dir-remove
  $ bzr init -q source
  $ cd source
  $ mkdir src
  $ echo content > src/sourcecode
  $ bzr add -q src
  $ bzr commit -q -m 'Added directory'
  $ bzr rm -q src
  $ bzr commit -q -m 'Removed directory'
  $ cd ..
  $ hg convert source source-hg
  initializing destination source-hg repository
  scanning source...
  sorting...
  converting...
  1 Added directory
  0 Removed directory
  $ manifest source-hg 0
  % manifest of 0
  644   src/sourcecode
  $ manifest source-hg tip
  % manifest of tip
  $ cd ..

directory replace

  $ mkdir test-dir-replace
  $ cd test-dir-replace
  $ bzr init -q source
  $ cd source
  $ mkdir first second
  $ echo content > first/file
  $ echo morecontent > first/dummy
  $ echo othercontent > second/something
  $ bzr add -q first second
  $ bzr commit -q -m 'Initial layout'
  $ bzr mv first/file second/file
  first/file => second/file
  $ bzr mv first third
  first => third
  $ bzr commit -q -m 'Some conflicting moves'
  $ cd ..
  $ hg convert source source-hg
  initializing destination source-hg repository
  scanning source...
  sorting...
  converting...
  1 Initial layout
  0 Some conflicting moves
  $ manifest source-hg tip
  % manifest of tip
  644   second/file
  644   second/something
  644   third/dummy
  $ cd ..

divergent nested renames (issue3089)

  $ mkdir test-divergent-renames
  $ cd test-divergent-renames
  $ bzr init -q source
  $ cd source
  $ mkdir -p a/c
  $ echo a > a/fa
  $ echo c > a/c/fc
  $ bzr add -q a
  $ bzr commit -q -m 'Initial layout'
  $ bzr mv a b
  a => b
  $ mkdir a
  $ bzr add a
  add(ed|ing) a (re)
  $ bzr mv b/c a/c
  b/c => a/c
  $ bzr status
  added:
    a/
  renamed:
    a/? => b/? (re)
    a/c/? => a/c/? (re)
  $ bzr commit -q -m 'Divergent renames'
  $ cd ..
  $ hg convert source source-hg
  initializing destination source-hg repository
  scanning source...
  sorting...
  converting...
  1 Initial layout
  0 Divergent renames
  $ hg -R source-hg st -C --change 1
  A b/fa
    a/fa
  R a/fa
  $ hg -R source-hg manifest -r 1
  a/c/fc
  b/fa
  $ cd ..