# synthrepo.py - repo synthesis

#

# Copyright 2012 Facebook

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

'''synthesize structurally interesting change history

This extension is useful for creating a repository with properties

that are statistically similar to an existing repository. During

analysis, a simple probability table is constructed from the history

of an existing repository.  During synthesis, these properties are

reconstructed.

Properties that are analyzed and synthesized include the following:

- Lines added or removed when an existing file is modified

- Number and sizes of files added

- Number of files removed

- Line lengths

- Topological distance to parent changeset(s)

- Probability of a commit being a merge

- Probability of a newly added file being added to a new directory

- Interarrival time, and time zone, of commits

- Number of files in each directory

A few obvious properties that are not currently handled realistically:

- Merges are treated as regular commits with two parents, which is not

  realistic

- Modifications are not treated as operations on hunks of lines, but

  as insertions and deletions of randomly chosen single lines

- Committer ID (always random)

- Executability of files

- Symlinks and binary files are ignored

'''

from __future__ import absolute_import

import bisect

import collections

import itertools

import json

import os

import random

import sys

import time

from mercurial.i18n import _

from mercurial.node import (

    nullid,

    nullrev,

    short,

)

from mercurial import (

    context,

    diffutil,

    error,

    hg,

    logcmdutil,

    patch,

    pycompat,

    registrar,

)

from mercurial.utils import dateutil

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for

# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should

# be specifying the version(s) of Mercurial they are tested with, or

# leave the attribute unspecified.

testedwith = 'ships-with-hg-core'

cmdtable = {}

command = registrar.command(cmdtable)

newfile = {'new fi', 'rename', 'copy f', 'copy t'}

def zerodict():

    return collections.defaultdict(lambda: 0)

def roundto(x, k):

    if x > k * 2:

        return int(round(x / float(k)) * k)

    return int(round(x))

def parsegitdiff(lines):

    filename, mar, lineadd, lineremove = None, None, zerodict(), 0

    binary = False

    for line in lines:

        start = line[:6]

        if start == 'diff -':

            if filename:

                yield filename, mar, lineadd, lineremove, binary

            mar, lineadd, lineremove, binary = 'm', zerodict(), 0, False

            filename = patch.gitre.match(line).group(1)

        elif start in newfile:

            mar = 'a'

        elif start == 'GIT bi':

            binary = True

        elif start == 'delete':

            mar = 'r'

        elif start:

            s = start[0]

            if s == '-' and not line.startswith('--- '):

                lineremove += 1

            elif s == '+' and not line.startswith('+++ '):

                lineadd[roundto(len(line) - 1, 5)] += 1

    if filename:

        yield filename, mar, lineadd, lineremove, binary

@command(

    'analyze',

    [

        ('o', 'output', '', _('write output to given file'), _('FILE')),

        ('r', 'rev', [], _('analyze specified revisions'), _('REV')),

    ],

    _('hg analyze'),

    optionalrepo=True,

)

def analyze(ui, repo, *revs, **opts):

    """create a simple model of a repository to use for later synthesis

    This command examines every changeset in the given range (or all

    of history if none are specified) and creates a simple statistical

    model of the history of the repository. It also measures the directory

    structure of the repository as checked out.

    The model is written out to a JSON file, and can be used by

    :hg:`synthesize` to create or augment a repository with synthetic

    commits that have a structure that is statistically similar to the

    analyzed repository.

    """

    root = repo.root

    if not root.endswith(os.path.sep):

        root += os.path.sep

    revs = list(revs)

    revs.extend(opts['rev'])

    if not revs:

        revs = [':']

    output = opts['output']

    if not output:

        output = os.path.basename(root) + '.json'

    if output == '-':

        fp = sys.stdout

    else:

        fp = open(output, 'w')

    # Always obtain file counts of each directory in the given root directory.

    def onerror(e):

        ui.warn(_('error walking directory structure: %s\n') % e)

    dirs = {}

    rootprefixlen = len(root)

    for dirpath, dirnames, filenames in os.walk(root, onerror=onerror):

        dirpathfromroot = dirpath[rootprefixlen:]

        dirs[dirpathfromroot] = len(filenames)

        if '.hg' in dirnames:

            dirnames.remove('.hg')

    lineschanged = zerodict()

    children = zerodict()

    p1distance = zerodict()

    p2distance = zerodict()

    linesinfilesadded = zerodict()

    fileschanged = zerodict()

    filesadded = zerodict()

    filesremoved = zerodict()

    linelengths = zerodict()

    interarrival = zerodict()

    parents = zerodict()

    dirsadded = zerodict()

    tzoffset = zerodict()

    # If a mercurial repo is available, also model the commit history.

    if repo:

        revs = logcmdutil.revrange(repo, revs)

        revs.sort()

        progress = ui.makeprogress(

            _('analyzing'), unit=_('changesets'), total=len(revs)

        )

        for i, rev in enumerate(revs):

            progress.update(i)

            ctx = repo[rev]

            pl = ctx.parents()

            pctx = pl[0]

            prev = pctx.rev()

            children[prev] += 1

            p1distance[rev - prev] += 1

            parents[len(pl)] += 1

            tzoffset[ctx.date()[1]] += 1

            if len(pl) > 1:

                p2distance[rev - pl[1].rev()] += 1

            if prev == rev - 1:

                lastctx = pctx

            else:

                lastctx = repo[rev - 1]

            if lastctx.rev() != nullrev:

                timedelta = ctx.date()[0] - lastctx.date()[0]

                interarrival[roundto(timedelta, 300)] += 1

            diffopts = diffutil.diffallopts(ui, {'git': True})

            diff = sum(

                (d.splitlines() for d in ctx.diff(pctx, opts=diffopts)), []

            )

            fileadds, diradds, fileremoves, filechanges = 0, 0, 0, 0

            for filename, mar, lineadd, lineremove, isbin in parsegitdiff(diff):

                if isbin:

                    continue

                added = sum(pycompat.itervalues(lineadd), 0)

                if mar == 'm':

                    if added and lineremove:

                        lineschanged[

                            roundto(added, 5), roundto(lineremove, 5)

                        ] += 1

                        filechanges += 1

                elif mar == 'a':

                    fileadds += 1

                    if '/' in filename:

                        filedir = filename.rsplit('/', 1)[0]

                        if filedir not in pctx.dirs():

                            diradds += 1

                    linesinfilesadded[roundto(added, 5)] += 1

                elif mar == 'r':

                    fileremoves += 1

                for length, count in lineadd.iteritems():

                    linelengths[length] += count

            fileschanged[filechanges] += 1

            filesadded[fileadds] += 1

            dirsadded[diradds] += 1

            filesremoved[fileremoves] += 1

        progress.complete()

    invchildren = zerodict()

    for rev, count in children.iteritems():

        invchildren[count] += 1

    if output != '-':

        ui.status(_('writing output to %s\n') % output)

    def pronk(d):

        return sorted(d.iteritems(), key=lambda x: x[1], reverse=True)

    json.dump(

        {

            'revs': len(revs),

            'initdirs': pronk(dirs),

            'lineschanged': pronk(lineschanged),

            'children': pronk(invchildren),

            'fileschanged': pronk(fileschanged),

            'filesadded': pronk(filesadded),

            'linesinfilesadded': pronk(linesinfilesadded),

            'dirsadded': pronk(dirsadded),

            'filesremoved': pronk(filesremoved),

            'linelengths': pronk(linelengths),

            'parents': pronk(parents),

            'p1distance': pronk(p1distance),

            'p2distance': pronk(p2distance),

            'interarrival': pronk(interarrival),

            'tzoffset': pronk(tzoffset),

        },

        fp,

    )

    fp.close()

@command(

    'synthesize',

    [

        ('c', 'count', 0, _('create given number of commits'), _('COUNT')),

        ('', 'dict', '', _('path to a dictionary of words'), _('FILE')),

        ('', 'initfiles', 0, _('initial file count to create'), _('COUNT')),

    ],

    _('hg synthesize [OPTION].. DESCFILE'),

)

def synthesize(ui, repo, descpath, **opts):

    """synthesize commits based on a model of an existing repository

    The model must have been generated by :hg:`analyze`. Commits will

    be generated randomly according to the probabilities described in

    the model. If --initfiles is set, the repository will be seeded with

    the given number files following the modeled repository's directory

    structure.

    When synthesizing new content, commit descriptions, and user

    names, words will be chosen randomly from a dictionary that is

    presumed to contain one word per line. Use --dict to specify the

    path to an alternate dictionary to use.

    """

    try:

        fp = hg.openpath(ui, descpath)

    except Exception as err:

        raise error.Abort('%s: %s' % (descpath, err[0].strerror))

    desc = json.load(fp)

    fp.close()

    def cdf(l):

        if not l:

            return [], []

        vals, probs = zip(*sorted(l, key=lambda x: x[1], reverse=True))

        t = float(sum(probs, 0))

        s, cdfs = 0, []

        for v in probs:

            s += v

            cdfs.append(s / t)

        return vals, cdfs

    lineschanged = cdf(desc['lineschanged'])

    fileschanged = cdf(desc['fileschanged'])

    filesadded = cdf(desc['filesadded'])

    dirsadded = cdf(desc['dirsadded'])

    filesremoved = cdf(desc['filesremoved'])

    linelengths = cdf(desc['linelengths'])

    parents = cdf(desc['parents'])

    p1distance = cdf(desc['p1distance'])

    p2distance = cdf(desc['p2distance'])

    interarrival = cdf(desc['interarrival'])

    linesinfilesadded = cdf(desc['linesinfilesadded'])

    tzoffset = cdf(desc['tzoffset'])

    dictfile = opts.get('dict') or '/usr/share/dict/words'

    try:

        fp = open(dictfile, 'rU')

    except IOError as err:

        raise error.Abort('%s: %s' % (dictfile, err.strerror))

    words = fp.read().splitlines()

    fp.close()

    initdirs = {}

    if desc['initdirs']:

        for k, v in desc['initdirs']:

            initdirs[k.encode('utf-8').replace('.hg', '_hg')] = v

        initdirs = renamedirs(initdirs, words)

    initdirscdf = cdf(initdirs)

    def pick(cdf):

        return cdf[0][bisect.bisect_left(cdf[1], random.random())]

    def pickpath():

        return os.path.join(pick(initdirscdf), random.choice(words))

    def makeline(minimum=0):

        total = max(minimum, pick(linelengths))

        c, l = 0, []

        while c < total:

            w = random.choice(words)

            c += len(w) + 1

            l.append(w)

        return ' '.join(l)

    wlock = repo.wlock()

    lock = repo.lock()

    nevertouch = {'.hgsub', '.hgignore', '.hgtags'}

    _synthesizing = _('synthesizing')

    _files = _('initial files')

    _changesets = _('changesets')

    # Synthesize a single initial revision adding files to the repo according

    # to the modeled directory structure.

    initcount = int(opts['initfiles'])

    if initcount and initdirs:

        pctx = repo['.']

        dirs = set(pctx.dirs())

        files = {}

        def validpath(path):

            # Don't pick filenames which are already directory names.

            if path in dirs:

                return False

            # Don't pick directories which were used as file names.

            while path:

                if path in files:

                    return False

                path = os.path.dirname(path)

            return True

        progress = ui.makeprogress(_synthesizing, unit=_files, total=initcount)

        for i in pycompat.xrange(0, initcount):

            progress.update(i)