contrib/churn.py
author Alexis S. L. Carvalho <alexis@cecm.usp.br>
Mon, 16 Apr 2007 20:17:39 -0300
changeset 4359 2e3c54fb79a3
parent 3963 ba45041827a2
child 4937 9bbc0217209b
permissions -rw-r--r--
actually port simplemerge to hg - use bdiff instead of patiencediff; this is a larger change, since bdiff works on 2 multi-line strings, while patiencediff works on 2 lists; - rename the main class from Merge3 to Merge3Text and add a Merge3 class that derives from Merge3Text. This new Merge3 class has the same interface from the original class, so that the tests still work; - Merge3 uses util.binary to detect binary data and raises util.Abort instead of a specific exception; - don't use the @decorator syntax, to keep python2.3 compatibility; - the test uses unittest, which likes to print how long it took to run. This obviously doesn't play too well with hg's test suite, so we override time.time to fool unittest; - one test has a different (but still valid) output because of the different diff algorithm used; - the TestCase class used by bzr has some extras to help debugging. test-merge3.py used 2 of them: - log method to log some data - assertEqualDiff method to ease viewing diffs of diffs We add a dummy log method and use regular assertEquals instead of assertEqualDiff. - make simplemerge executable and add "#!/usr/bin/env python" header

# churn.py - create a graph showing who changed the most lines
#
# Copyright 2006 Josef "Jeff" Sipek <jeffpc@josefsipek.net>
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.
#
#
# Aliases map file format is simple one alias per line in the following
# format:
#
# <alias email> <actual email>

import sys
from mercurial.i18n import gettext as _
from mercurial import hg, mdiff, cmdutil, ui, util, templater, node

def __gather(ui, repo, node1, node2):
    def dirtywork(f, mmap1, mmap2):
        lines = 0

        to = mmap1 and repo.file(f).read(mmap1[f]) or None
        tn = mmap2 and repo.file(f).read(mmap2[f]) or None

        diff = mdiff.unidiff(to, "", tn, "", f).split("\n")

        for line in diff:
            if not line:
                continue # skip EOF
            if line.startswith(" "):
                continue # context line
            if line.startswith("--- ") or line.startswith("+++ "):
                continue # begining of diff
            if line.startswith("@@ "):
                continue # info line

            # changed lines
            lines += 1

        return lines

    ##

    lines = 0

    changes = repo.status(node1, node2, None, util.always)[:5]

    modified, added, removed, deleted, unknown = changes

    who = repo.changelog.read(node2)[1]
    who = templater.email(who) # get the email of the person

    mmap1 = repo.manifest.read(repo.changelog.read(node1)[0])
    mmap2 = repo.manifest.read(repo.changelog.read(node2)[0])
    for f in modified:
        lines += dirtywork(f, mmap1, mmap2)

    for f in added:
        lines += dirtywork(f, None, mmap2)

    for f in removed:
        lines += dirtywork(f, mmap1, None)

    for f in deleted:
        lines += dirtywork(f, mmap1, mmap2)

    for f in unknown:
        lines += dirtywork(f, mmap1, mmap2)

    return (who, lines)

def gather_stats(ui, repo, amap, revs=None, progress=False):
    stats = {}

    cl    = repo.changelog

    if not revs:
        revs = range(0, cl.count())

    nr_revs = len(revs)
    cur_rev = 0

    for rev in revs:
        cur_rev += 1 # next revision

        node2    = cl.node(rev)
        node1    = cl.parents(node2)[0]

        if cl.parents(node2)[1] != node.nullid:
            ui.note(_('Revision %d is a merge, ignoring...\n') % (rev,))
            continue

        who, lines = __gather(ui, repo, node1, node2)

        # remap the owner if possible
        if amap.has_key(who):
            ui.note("using '%s' alias for '%s'\n" % (amap[who], who))
            who = amap[who]

        if not stats.has_key(who):
            stats[who] = 0
        stats[who] += lines

        ui.note("rev %d: %d lines by %s\n" % (rev, lines, who))

        if progress:
            if int(100.0*(cur_rev - 1)/nr_revs) < int(100.0*cur_rev/nr_revs):
                ui.write("%d%%.." % (int(100.0*cur_rev/nr_revs),))
                sys.stdout.flush()

    if progress:
        ui.write("done\n")
        sys.stdout.flush()

    return stats

def churn(ui, repo, **opts):
    "Graphs the number of lines changed"

    def pad(s, l):
        if len(s) < l:
            return s + " " * (l-len(s))
        return s[0:l]

    def graph(n, maximum, width, char):
        n = int(n * width / float(maximum))

        return char * (n)

    def get_aliases(f):
        aliases = {}

        for l in f.readlines():
            l = l.strip()
            alias, actual = l.split(" ")
            aliases[alias] = actual

        return aliases

    amap = {}
    aliases = opts.get('aliases')
    if aliases:
        try:
            f = open(aliases,"r")
        except OSError, e:
            print "Error: " + e
            return

        amap = get_aliases(f)
        f.close()

    revs = [int(r) for r in cmdutil.revrange(repo, opts['rev'])]
    revs.sort()
    stats = gather_stats(ui, repo, amap, revs, opts.get('progress'))

    # make a list of tuples (name, lines) and sort it in descending order
    ordered = stats.items()
    ordered.sort(lambda x, y: cmp(y[1], x[1]))

    maximum = ordered[0][1]

    ui.note("Assuming 80 character terminal\n")
    width = 80 - 1

    for i in ordered:
        person = i[0]
        lines = i[1]
        print "%s %6d %s" % (pad(person, 20), lines,
                graph(lines, maximum, width - 20 - 1 - 6 - 2 - 2, '*'))

cmdtable = {
    "churn":
    (churn,
     [('r', 'rev', [], _('limit statistics to the specified revisions')),
      ('', 'aliases', '', _('file with email aliases')),
      ('', 'progress', None, _('show progress'))],
    'hg churn [-r revision range] [-a file] [--progress]'),
}