view contrib/relnotes @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping The performance and memory benefit is much greater if we don't have to copy all the data in memory for each information. So we introduce an option (on by default) to read the data using mmap. This changeset is the last one definition the API for index support nodemap data. (they have to be able to use the mmaping). Below are some benchmark comparing the best we currently have in 5.3 with the final step of this series (using the persistent nodemap implementation in Rust). The benchmark run `hg perfindex` with various revset and the following variants: Before: * do not use the persistent nodemap * use the CPython implementation of the index for nodemap * use mmapping of the changelog index After: * use the MixedIndex Rust code, with the NodeTree object for nodemap access (still in review) * use the persistent nodemap data from disk * access the persistent nodemap data through mmap * use mmapping of the changelog index The persistent nodemap greatly speed up most operation on very large repositories. Some of the previously very fast lookup end up a bit slower because the persistent nodemap has to be setup. However the absolute slowdown is very small and won't matters in the big picture. Here are some numbers (in seconds) for the reference copy of mozilla-try: Revset Before After abs-change speedup -10000: 0.004622 0.005532 0.000910 × 0.83 -10: 0.000050 0.000132 0.000082 × 0.37 tip 0.000052 0.000085 0.000033 × 0.61 0 + (-10000:) 0.028222 0.005337 -0.022885 × 5.29 0 0.023521 0.000084 -0.023437 × 280.01 (-10000:) + 0 0.235539 0.005308 -0.230231 × 44.37 (-10:) + :9 0.232883 0.000180 -0.232703 ×1293.79 (-10000:) + (:99) 0.238735 0.005358 -0.233377 × 44.55 :99 + (-10000:) 0.317942 0.005593 -0.312349 × 56.84 :9 + (-10:) 0.313372 0.000179 -0.313193 ×1750.68 :9 0.316450 0.000143 -0.316307 ×2212.93 On smaller repositories, the cost of nodemap related operation is not as big, so the win is much more modest. Yet it helps shaving a handful of millisecond here and there. Here are some numbers (in seconds) for the reference copy of mercurial: Revset Before After abs-change speedup -10: 0.000065 0.000097 0.000032 × 0.67 tip 0.000063 0.000078 0.000015 × 0.80 0 0.000561 0.000079 -0.000482 × 7.10 -10000: 0.004609 0.003648 -0.000961 × 1.26 0 + (-10000:) 0.005023 0.003715 -0.001307 × 1.35 (-10:) + :9 0.002187 0.000108 -0.002079 ×20.25 (-10000:) + 0 0.006252 0.003716 -0.002536 × 1.68 (-10000:) + (:99) 0.006367 0.003707 -0.002660 × 1.71 :9 + (-10:) 0.003846 0.000110 -0.003736 ×34.96 :9 0.003854 0.000099 -0.003755 ×38.92 :99 + (-10000:) 0.007644 0.003778 -0.003866 × 2.02 Differential Revision: https://phab.mercurial-scm.org/D7894
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents 99e231afc29c
children
line wrap: on
line source

#!/usr/bin/env python3
"""Generate release notes from our commit log.

This uses the relnotes extension directives when they're available,
and falls back to our old pre-relnotes logic that used to live in the
release-tools repo.
"""
import argparse
import re
import subprocess

rules = {
    # keep
    r"\(issue": 100,
    r"\(BC\)": 100,
    r"\(API\)": 100,
    r"\(SEC\)": 100,
    # core commands, bump up
    r"(commit|files|log|pull|push|patch|status|tag|summary)(|s|es):": 20,
    r"(annotate|alias|branch|bookmark|clone|graft|import|verify).*:": 20,
    # extensions, bump up
    r"(mq|shelve|rebase):": 20,
    # newsy
    r": deprecate": 20,
    r": new.*(extension|flag|module)": 10,
    r"( ability|command|feature|option|support)": 10,
    # experimental
    r"hg-experimental": 20,
    r"(from|graduate).*experimental": 15,
    r"(hide|mark).*experimental": -10,
    # bug-like?
    r"(fix|don't break|improve)": 7,
    r"(not|n't|avoid|fix|prevent).*crash": 10,
    r"vulnerab": 10,
    # boring stuff, bump down
    r"^contrib": -5,
    r"debug": -5,
    r"help": -5,
    r"minor": -5,
    r"(doc|metavar|bundle2|obsolete|obsmarker|rpm|setup|debug\S+:)": -15,
    r"(check-code|check-commit|check-config|import-checker)": -20,
    r"(flake8|lintian|pyflakes|pylint)": -20,
    # cleanups and refactoring
    r"(clean ?up|white ?space|spelling|quoting)": -20,
    r"(flatten|dedent|indent|nesting|unnest)": -20,
    r"(typo|hint|note|comment|TODO|FIXME)": -20,
    r"(style:|convention|one-?liner)": -20,
    r"(argument|absolute_import|attribute|assignment|mutable)": -15,
    r"(scope|True|False)": -10,
    r"(unused|useless|unnecessar|superfluous|duplicate|deprecated)": -10,
    r"(redundant|pointless|confusing|uninitialized|meaningless|dead)": -10,
    r": (drop|remove|delete|rip out)": -10,
    r": (inherit|rename|simplify|naming|inline)": -10,
    r"(correct doc|docstring|document .* method)": -20,
    r"(abstract|factor|extract|prepare|split|replace| import)": -20,
    r": add.*(function|method|implementation|example)": -10,
    r": (move|extract) .* (to|into|from|out of)": -20,
    r": implement ": -5,
    r": use .* implementation": -20,
    r": use .* instead of": -20,
    # code
    r"_": -10,
    r"__": -5,
    r"\(\)": -5,
    r"\S\S\S+\.\S\S\S\S+": -5,
    # dumb keywords
    r"\S+/\S+:": -10,
    r"\S+\.\S+:": -10,
    # python compatibility
    r"[Pp]y(|thon) ?[23]": -20,
    r"pycompat": -20,
    r"(coerce|convert|encode) .*to (byte|sys|)(s|str|string)": -20,
    # tests
    r"^test(|s|ing|runner|-\S+):": -20,
    r"^(f|hghave|run-tests):": -20,
    r"add.* tests?": -20,
    r"(buildbot|fuzz|mock|ratchet)": -10,
    # drop
    r"^i18n-": -50,
    r"^i18n:.*(hint|comment)": -50,
    r"perf:": -50,
    r"Added.*for changeset": -50,
    r"^_": -50,
}

cutoff = 10
commits = []

groupings = [
    (r"util|parsers|repo|ctx|context|revlog|filelog|alias|cmdutil", "core"),
    (r"revset|template|ui|dirstate|hook|i18n|transaction|wire|vfs", "core"),
    (r"dispatch|exchange|localrepo|streamclone|color|pager", "core"),
    (r"hgweb|paper|coal|gitweb|monoblue|spartan", "hgweb"),
    (r"pull|push|revert|resolve|annotate|bookmark|branch|clone", "commands"),
    (r"commands|commit|config|files|graft|import|log|merge|patch", "commands"),
    (r"phases|status|summary|amend|tag|help|verify", "commands"),
    (r"rebase|mq|convert|eol|histedit|largefiles", "extensions"),
    (r"shelve|unshelve", "extensions"),
]


def wikify(desc):
    desc = desc.replace("(issue", "(Bts:issue")
    desc = re.sub(r"\b([0-9a-f]{12})\b", r"Cset:\1", desc)
    # stop ParseError from being recognized as a (nonexistent) wiki page
    desc = re.sub(r" ([A-Z][a-z]+[A-Z][a-z]+)\b", r" !\1", desc)
    # prevent wiki markup of magic methods
    desc = re.sub(r"\b(\S*__\S*)\b", r"`\1`", desc)
    return desc


def main():
    desc = "example: %(prog)s 4.7.2 --stoprev 4.8rc0"
    ap = argparse.ArgumentParser(description=desc)
    ap.add_argument(
        "startrev",
        metavar="REV",
        type=str,
        help=(
            "Starting revision for the release notes. This revision "
            "won't be included, but later revisions will."
        ),
    )
    ap.add_argument(
        "--stoprev",
        metavar="REV",
        type=str,
        default="@",
        help=(
            "Stop revision for release notes. This revision will be included,"
            " but no later revisions will. This revision needs to be "
            "a descendant of startrev."
        ),
    )
    args = ap.parse_args()
    fromext = subprocess.check_output(
        [
            "hg",
            "--config",
            "extensions.releasenotes=",
            "releasenotes",
            "-r",
            "only(%s, %s)" % (args.stoprev, args.startrev),
        ]
    ).decode("utf-8")
    # Find all release notes from un-relnotes-flagged commits.
    for entry in sorted(
        subprocess.check_output(
            [
                "hg",
                "log",
                "-r",
                "only(%s, %s) - merge()" % (args.stoprev, args.startrev),
                "-T",
                r"{desc|firstline}\n",
            ]
        )
        .decode("utf-8")
        .splitlines()
    ):
        desc = entry.replace("`", "'")

        score = 0
        for rule, val in rules.items():
            if re.search(rule, desc):
                score += val

        if score >= cutoff:
            commits.append(wikify(desc))
    # Group unflagged notes.
    groups = {}
    bcs = []
    apis = []

    for d in commits:
        if "(BC)" in d:
            bcs.append(d)
        if "(API)" in d:
            apis.append(d)
        for rule, g in groupings:
            if re.match(rule, d):
                groups.setdefault(g, []).append(d)
                break
        else:
            groups.setdefault("unsorted", []).append(d)
    print(fromext)
    # print legacy release notes sections
    for g in sorted(groups):
        print("\n=== %s ===" % g)
        for d in sorted(groups[g]):
            print(" * %s" % d)

    if bcs:
        print("\n=== Behavior Changes ===\n")

    for d in sorted(bcs):
        print(" * %s" % d)

    if apis:
        print("\n=== Internal API Changes ===\n")

    for d in sorted(apis):
        print(" * %s" % d)


if __name__ == "__main__":
    main()