[PATCH V2] verify: add a config option to skip certain flag processors

[Jun Wu]

# HG changeset patch
# User Jun Wu <quark at fb.com>
# Date 1494779886 25200
#      Sun May 14 09:38:06 2017 -0700
# Node ID c3d89aaf46bf50343dd06ff4e59dbadb0563b464
# Parent  78496ac300255e9996b3e282086661afc08af37c
# Available At https://bitbucket.org/quark-zju/hg-draft
#              hg pull https://bitbucket.org/quark-zju/hg-draft -r c3d89aaf46bf
verify: add a config option to skip certain flag processors

Previously, "hg verify" verifies everything, which could be undesirable when
there are expensive flag processor contents.

This patch adds a "verify.skipflags" developer config. A flag processor will
be skipped if (flag & verify.skipflags) == 0.

In the LFS usecase, that means "hg verify --config verify.skipflags=8192"
will not download all LFS blobs, which could be too large to be stored
locally.

Note: "renamed" is also skipped since its default implementation may call
filelog.data() which will trigger the flag processor.

diff --git a/mercurial/verify.py b/mercurial/verify.py
--- a/mercurial/verify.py
+++ b/mercurial/verify.py
@@ -50,4 +50,6 @@ class verifier(object):
         self.refersmf = False
         self.fncachewarned = False
+        # developer config: verify.skipflags
+        self.skipflags = repo.ui.configint('verify', 'skipflags')
 
     def warn(self, msg):
@@ -428,6 +430,10 @@ class verifier(object):
                 #     use either "text" (external), or "rawtext" (in revlog).
                 try:
-                    fl.read(n) # side effect: read content and do checkhash
-                    rp = fl.renamed(n)
+                    skipflags = self.skipflags
+                    if skipflags:
+                        skipflags &= fl.flags(i)
+                    if not skipflags:
+                        fl.read(n) # side effect: read content and do checkhash
+                        rp = fl.renamed(n)
                     # the "L1 == L2" check
                     l1 = fl.rawsize(i)
diff --git a/tests/test-verify.t b/tests/test-verify.t
--- a/tests/test-verify.t
+++ b/tests/test-verify.t
@@ -318,2 +318,46 @@ test revlog format 0
   1 files, 1 changesets, 1 total revisions
   $ cd ..
+
+test flag processor and skipflags
+
+  $ hg init skipflags
+  $ cd skipflags
+  $ cat >> .hg/hgrc <<EOF
+  > [extensions]
+  > flagprocesor=$RUNTESTDIR/flagprocessorext.py
+  > EOF
+  $ echo '[BASE64]content' > base64
+  $ hg commit -Aqm 'flag processor content' base64
+  $ hg verify
+  checking changesets
+  checking manifests
+  crosschecking files in changesets and manifests
+  checking files
+  1 files, 1 changesets, 1 total revisions
+
+  $ cat >> $TESTTMP/break-base64.py <<EOF
+  > from __future__ import absolute_import
+  > import base64
+  > base64.b64decode=lambda x: x
+  > EOF
+  $ cat >> .hg/hgrc <<EOF
+  > breakbase64=$TESTTMP/break-base64.py
+  > EOF
+
+  $ hg verify
+  checking changesets
+  checking manifests
+  crosschecking files in changesets and manifests
+  checking files
+   base64 at 0: unpacking 794cee7777cb: integrity check failed on data/base64.i:0
+  1 files, 1 changesets, 1 total revisions
+  1 integrity errors encountered!
+  (first damaged changeset appears to be 0)
+  [1]
+  $ hg verify --config verify.skipflags=2147483647
+  checking changesets
+  checking manifests
+  crosschecking files in changesets and manifests
+  checking files
+  1 files, 1 changesets, 1 total revisions
+