hgext/fastannotate/formatter.py

git: skeleton of a new extension to _directly_ operate on git repos

This is based in part of work I did years ago in hgit, but it's mostly
new code since I'm using pygit2 instead of dulwich and the hg storage
interfaces have improved. Some cleanup of old hgit code by Pulkit,
which I greatly appreciate.

test-git-interop.t does not cover a whole lot of cases, but it
passes. It includes status, diff, making a new commit, and `hg annotate`
working on the git repository.

This is _not_ (yet) production quality code: this is an
experiment. Known technical debt lurking in this implementation:

 * Writing bookmarks just totally ignores transactions.
 * The way progress is threaded down into the gitstore is awful.
 * Ideally we'd find a way to incrementally reindex DAGs. I'm not sure
   how to do that efficiently, so we might need a "known only fast-forwards"
   mode on the DAG indexer for use on `hg commit` and friends.
 * We don't even _try_ to do anything reasonable for `hg pull` or `hg push`.
 * Mercurial need an interface for the changelog type.

Tests currently require git 2.24 as far as I'm aware: `git status` has
some changed output that I didn't try and handle in a compatible way.

This patch has produced some interesting cleanups, most recently on
the manifest type. I expect continuing down this road will produce
other meritorious cleanups throughout our code.

Differential Revision: https://phab.mercurial-scm.org/D6734

# Copyright 2016-present Facebook. All Rights Reserved.
#
# format: defines the format used to output annotate result
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import

from mercurial import (
    encoding,
    node,
    pycompat,
    templatefilters,
    util,
)
from mercurial.utils import dateutil

# imitating mercurial.commands.annotate, not using the vanilla formatter since
# the data structures are a bit different, and we have some fast paths.
class defaultformatter(object):
    """the default formatter that does leftpad and support some common flags"""

    def __init__(self, ui, repo, opts):
        self.ui = ui
        self.opts = opts

        if ui.quiet:
            datefunc = dateutil.shortdate
        else:
            datefunc = dateutil.datestr
        datefunc = util.cachefunc(datefunc)
        getctx = util.cachefunc(lambda x: repo[x[0]])
        hexfunc = self._hexfunc

        # special handling working copy "changeset" and "rev" functions
        if self.opts.get(b'rev') == b'wdir()':
            orig = hexfunc
            hexfunc = lambda x: None if x is None else orig(x)
            wnode = hexfunc(repo[b'.'].node()) + b'+'
            wrev = b'%d' % repo[b'.'].rev()
            wrevpad = b''
            if not opts.get(b'changeset'):  # only show + if changeset is hidden
                wrev += b'+'
                wrevpad = b' '
            revenc = lambda x: wrev if x is None else (b'%d' % x) + wrevpad

            def csetenc(x):
                if x is None:
                    return wnode
                return pycompat.bytestr(x) + b' '

        else:
            revenc = csetenc = pycompat.bytestr

        # opt name, separator, raw value (for json/plain), encoder (for plain)
        opmap = [
            (b'user', b' ', lambda x: getctx(x).user(), ui.shortuser),
            (b'number', b' ', lambda x: getctx(x).rev(), revenc),
            (b'changeset', b' ', lambda x: hexfunc(x[0]), csetenc),
            (b'date', b' ', lambda x: getctx(x).date(), datefunc),
            (b'file', b' ', lambda x: x[2], pycompat.bytestr),
            (b'line_number', b':', lambda x: x[1] + 1, pycompat.bytestr),
        ]
        fieldnamemap = {b'number': b'rev', b'changeset': b'node'}
        funcmap = [
            (get, sep, fieldnamemap.get(op, op), enc)
            for op, sep, get, enc in opmap
            if opts.get(op)
        ]
        # no separator for first column
        funcmap[0] = list(funcmap[0])
        funcmap[0][1] = b''
        self.funcmap = funcmap

    def write(self, annotatedresult, lines=None, existinglines=None):
        """(annotateresult, [str], set([rev, linenum])) -> None. write output.
        annotateresult can be [(node, linenum, path)], or [(node, linenum)]
        """
        pieces = []  # [[str]]
        maxwidths = []  # [int]

        # calculate padding
        for f, sep, name, enc in self.funcmap:
            l = [enc(f(x)) for x in annotatedresult]
            pieces.append(l)
            if name in [b'node', b'date']:  # node and date has fixed size
                l = l[:1]
            widths = pycompat.maplist(encoding.colwidth, set(l))
            maxwidth = max(widths) if widths else 0
            maxwidths.append(maxwidth)

        # buffered output
        result = b''
        for i in pycompat.xrange(len(annotatedresult)):
            for j, p in enumerate(pieces):
                sep = self.funcmap[j][1]
                padding = b' ' * (maxwidths[j] - len(p[i]))
                result += sep + padding + p[i]
            if lines:
                if existinglines is None:
                    result += b': ' + lines[i]
                else:  # extra formatting showing whether a line exists
                    key = (annotatedresult[i][0], annotatedresult[i][1])
                    if key in existinglines:
                        result += b':  ' + lines[i]
                    else:
                        result += b': ' + self.ui.label(
                            b'-' + lines[i], b'diff.deleted'
                        )

            if result[-1:] != b'\n':
                result += b'\n'

        self.ui.write(result)

    @util.propertycache
    def _hexfunc(self):
        if self.ui.debugflag or self.opts.get(b'long_hash'):
            return node.hex
        else:
            return node.short

    def end(self):
        pass


class jsonformatter(defaultformatter):
    def __init__(self, ui, repo, opts):
        super(jsonformatter, self).__init__(ui, repo, opts)
        self.ui.write(b'[')
        self.needcomma = False

    def write(self, annotatedresult, lines=None, existinglines=None):
        if annotatedresult:
            self._writecomma()

        pieces = [
            (name, pycompat.maplist(f, annotatedresult))
            for f, sep, name, enc in self.funcmap
        ]
        if lines is not None:
            pieces.append((b'line', lines))
        pieces.sort()

        seps = [b','] * len(pieces[:-1]) + [b'']

        result = b''
        lasti = len(annotatedresult) - 1
        for i in pycompat.xrange(len(annotatedresult)):
            result += b'\n {\n'
            for j, p in enumerate(pieces):
                k, vs = p
                result += b'  "%s": %s%s\n' % (
                    k,
                    templatefilters.json(vs[i], paranoid=False),
                    seps[j],
                )
            result += b' }%s' % (b'' if i == lasti else b',')
        if lasti >= 0:
            self.needcomma = True

        self.ui.write(result)

    def _writecomma(self):
        if self.needcomma:
            self.ui.write(b',')
            self.needcomma = False

    @util.propertycache
    def _hexfunc(self):
        return node.hex

    def end(self):
        self.ui.write(b'\n]\n')