view contrib/check-commit @ 39632:c1aacb0d76ff

wireprotov2: add phases to "changesetdata" command

This commit teaches the "changesetdata" wire protocol command
to emit the phase state for each changeset.

This is a different approach from existing phase transfer in a
few ways. Previously, if there are no new revisions (or we're
not using bundle2), we perform a "listkeys" request to retrieve
phase heads. And when revision data is being transferred
with bundle2, phases data is encoded in a standalone bundle2 part.
In both cases, phases data is logically decoupled from the changeset
data and is encountered/applied after changeset revision data
is received.

The new wire protocol purposefully tries to more tightly associate
changeset metadata (phases, bookmarks, obsolescence markers, etc)
with the changeset revision and index data itself, rather than
have it live as a separate entity that must be fetched and
processed separately. I reckon that one reason we didn't do this
before was it was difficult to add new data types/fields without
breaking existing consumers. By using CBOR maps to transfer
changeset data and putting clients in control of what fields are
requested / present in those maps, we can easily add additional
changeset data while maintaining backwards compatibility. I believe
this to be a superior approach to the problem.

That being said, for performance reasons, we may need to resort
to alternative mechanisms for transferring data like phases. But
for now, I think giving the wire protocol the ability to transfer
changeset metadata next to the changeset itself is a powerful feature
because it is a raw, changeset-centric data API. And if you build
simple APIs for accessing the fundamental units of repository data,
you enable client-side experimentation (partial clone, etc). If it
turns out that we need specialized APIs or mechanisms for transferring
data like phases, we can build in those APIs later. For now, I'd
like to see how far we can get on simple APIs.

It's worth noting that when phase data is being requested, the
server will also emit changeset records for nodes in the bases
specified by the "noderange" argument. This is to ensure that
phase-only updates for nodes the client has are available to the
client, even if no new changesets will be transferred.

Differential Revision: https://phab.mercurial-scm.org/D4483

#!/usr/bin/env python
#
# Copyright 2014 Matt Mackall <[e-mail]>
#
# A tool/hook to run basic sanity checks on commits/patches for
# submission to Mercurial. Install by adding the following to your
# .hg/hgrc:
#
# [hooks]
# pretxncommit = contrib/check-commit
#
# The hook can be temporarily bypassed with:
#
# $ BYPASS= hg commit
#
# See also: https://mercurial-scm.org/wiki/ContributingChanges

from __future__ import absolute_import, print_function

import os
import re
import sys

commitheader = r"^(?:# [^\n]*\n)*"
afterheader = commitheader + r"(?!#)"
beforepatch = afterheader + r"(?!\n(?!@@))"

errors = [
    (beforepatch + r".*[(]bc[)]", "(BC) needs to be uppercase"),
    (beforepatch + r".*[(]issue \d\d\d",
     "no space allowed between issue and number"),
    (beforepatch + r".*[(]bug(\d|\s)", "use (issueDDDD) instead of bug"),
    (commitheader + r"# User [^@\n]+\n", "username is not an email address"),
    (commitheader + r"(?!merge with )[^#]\S+[^:] ",
     "summary line doesn't start with 'topic: '"),
    (afterheader + r"[A-Z][a-z]\S+", "don't capitalize summary lines"),
    (afterheader + r"[^\n]*: *[A-Z][a-z]\S+", "don't capitalize summary lines"),
    (afterheader + r"\S*[^A-Za-z0-9-_]\S*: ",
     "summary keyword should be most user-relevant one-word command or topic"),
    (afterheader + r".*\.\s*\n", "don't add trailing period on summary line"),
    (afterheader + r".{79,}", "summary line too long (limit is 78)"),
    (r"\n\+\n( |\+)\n", "adds double empty line"),
    (r"\n \n\+\n", "adds double empty line"),
    # Forbid "_" in function name.
    #
    # We skip the check for cffi related functions. They use names mapping the
    # name of the C function. C function names may contain "_".
    (r"\n\+[ \t]+def (?!cffi)[a-z]+_[a-z]",
     "adds a function with foo_bar naming"),
]

word = re.compile('\S')
def nonempty(first, second):
    if word.search(first):
        return first
    return second

def checkcommit(commit, node=None):
    exitcode = 0
    printed = node is None
    hits = []
    signtag = (afterheader +
          r'Added (tag [^ ]+|signature) for changeset [a-f0-9]{12}')
    if re.search(signtag, commit):
        return 0
    for exp, msg in errors:
        for m in re.finditer(exp, commit):
            end = m.end()
            trailing = re.search(r'(\\n)+$', exp)
            if trailing:
                end -= len(trailing.group()) / 2
            hits.append((end, exp, msg))
    if hits:
        hits.sort()
        pos = 0
        last = ''
        for n, l in enumerate(commit.splitlines(True)):
            pos += len(l)
            while len(hits):
                end, exp, msg = hits[0]
                if pos < end:
                    break
                if not printed:
                    printed = True
                    print("node: %s" % node)
                print("%d: %s" % (n, msg))
                print(" %s" % nonempty(l, last)[:-1])
                if "BYPASS" not in os.environ:
                    exitcode = 1
                del hits[0]
            last = nonempty(l, last)

    return exitcode

def readcommit(node):
    return os.popen("hg export %s" % node).read()

if __name__ == "__main__":
    exitcode = 0
    node = os.environ.get("HG_NODE")

    if node:
        commit = readcommit(node)
        exitcode = checkcommit(commit)
    elif sys.argv[1:]:
        for node in sys.argv[1:]:
            exitcode |= checkcommit(readcommit(node), node)
    else:
        commit = sys.stdin.read()
        exitcode = checkcommit(commit)
    sys.exit(exitcode)