[PATCH 1 of 3 STABLE] tests: demonstrate broken manifest generation with the pure module

[Matt Harbison]

# HG changeset patch
# User Matt Harbison <matt_harbison at yahoo.com>
# Date 1558661959 14400
#      Thu May 23 21:39:19 2019 -0400
# Branch stable
# Node ID 89c0c8edc9d40ccb707acbeccff25891c5456521
# Parent  2338bdea44744312e42632d68bc00491184c748b
tests: demonstrate broken manifest generation with the pure module

This will be fixed next.  But I don't fully understand how 'b.txt' is actually
removed properly in the second test, given what's broken.  Also, I'm not sure
why 'bb.txt' is flagged as not being in the manifest, when it clearly appears
to be.

diff --git a/mercurial/manifest.py b/mercurial/manifest.py
--- a/mercurial/manifest.py
+++ b/mercurial/manifest.py
@@ -35,6 +35,9 @@ from .utils import (
 parsers = policy.importmod(r'parsers')
 propertycache = util.propertycache
 
+# Allow tests to more easily test the alternate path in manifestdict.fastdelta()
+FASTDELTA_TEXTDIFF_THRESHOLD = 1000
+
 def _parse(data):
     # This method does a little bit of excessive-looking
     # precondition checking. This is so that the behavior of this
@@ -558,7 +561,7 @@ class manifestdict(object):
         addbuf = util.buffer(base)
 
         changes = list(changes)
-        if len(changes) < 1000:
+        if len(changes) < FASTDELTA_TEXTDIFF_THRESHOLD:
             # start with a readonly loop that finds the offset of
             # each line and creates the deltas
             for f, todelete in changes:
diff --git a/tests/test-manifest.t b/tests/test-manifest.t
--- a/tests/test-manifest.t
+++ b/tests/test-manifest.t
@@ -201,3 +201,94 @@ hg update should warm the cache too
   total cache data size 425 bytes, on-disk 425 bytes
   $ hg log -r '0' --debug | grep 'manifest:'
   manifest:    0:fce2a30dedad1eef4da95ca1dc0004157aa527cf
+
+Test file removal (especially with pure).  The tests are crafted such that there
+will be contiguous spans of existing entries to ensure that is handled properly.
+(In this case, a.txt, aa.txt and c.txt, cc.txt, and ccc.txt)
+
+  $ cat > $TESTTMP/manifest.py <<EOF
+  > from mercurial import (
+  >     extensions,
+  >     manifest,
+  > )
+  > def extsetup(ui):
+  >     manifest.FASTDELTA_TEXTDIFF_THRESHOLD = 0
+  > EOF
+  $ cat >> $HGRCPATH <<EOF
+  > [extensions]
+  > manifest = $TESTTMP/manifest.py
+  > EOF
+
+BROKEN: Pure removes should actually remove all dropped entries
+
+  $ hg init repo
+  $ cd repo
+  $ echo a > a.txt
+  $ echo aa > aa.txt
+  $ echo b > b.txt
+  $ echo c > c.txt
+  $ echo c > cc.txt
+  $ echo c > ccc.txt
+  $ echo b > d.txt
+  $ echo c > e.txt
+  $ hg ci -Aqm 'a-e'
+
+  $ hg rm b.txt d.txt
+  $ hg ci -m 'remove b and d'
+
+  $ hg debugdata -m 1
+  a.txt\x00b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3 (esc)
+  aa.txt\x00a4bdc161c8fbb523c9a60409603f8710ff49a571 (esc)
+  \x00.txt\x001e88685f5ddec574a34c70af492f95b6debc8741 (esc) (pure !)
+  c.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+  cc.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+  ccc.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+  \x00.txt\x001e88685f5ddec574a34c70af492f95b6debc8741 (esc) (pure !)
+  e.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+
+  $ hg up -C . 2>&1 | grep ValueError || true
+      raise ValueError("Manifest lines not in sorted order.") (pure !)
+  ValueError: Manifest lines not in sorted order. (pure !)
+
+  $ hg verify || true
+  checking changesets
+  checking manifests
+   manifest at 1: reading delta c1f6b2f803ac: Non-hexadecimal digit found (pure !)
+  crosschecking files in changesets and manifests
+  checking files
+  checked 2 changesets with 8 changes to 8 files
+  1 integrity errors encountered! (pure !)
+  (first damaged changeset appears to be 1) (pure !)
+
+  $ hg rollback -q --config ui.rollback=True
+  $ hg rm b.txt d.txt
+  $ echo bb > bb.txt
+
+BROKEN: A mix of adds and removes should remove all dropped entries.
+
+  $ hg ci -Aqm 'remove b and d; add bb'
+
+  $ hg debugdata -m 1
+  a.txt\x00b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3 (esc)
+  aa.txt\x00a4bdc161c8fbb523c9a60409603f8710ff49a571 (esc)
+  bb.txt\x0004c6faf8a9fdd848a5304dfc1704749a374dff44 (esc)
+  c.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+  cc.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+  ccc.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+  \x00.txt\x001e88685f5ddec574a34c70af492f95b6debc8741 (esc) (pure !)
+  e.txt\x00149da44f2a4e14f488b7bd4157945a9837408c00 (esc)
+
+  $ hg up -C . 2>&1 | grep ValueError || true
+      raise ValueError("Manifest lines not in sorted order.") (pure !)
+  ValueError: Manifest lines not in sorted order. (pure !)
+
+  $ hg verify || true
+  checking changesets
+  checking manifests
+   manifest at 1: reading delta 0a0385480090: Manifest lines not in sorted order. (pure !)
+  crosschecking files in changesets and manifests
+   bb.txt at 1: in changeset but not in manifest (pure !)
+  checking files
+  checked 2 changesets with 9 changes to 9 files
+  2 integrity errors encountered! (pure !)
+  (first damaged changeset appears to be 1) (pure !)