##// END OF EJS Templates
revset: introduce new operator "##" to concatenate strings/symbols at runtime...
revset: introduce new operator "##" to concatenate strings/symbols at runtime Before this patch, there is no way to concatenate strings at runtime. For example, to search for the issue ID "1234" in descriptions against all of "issue 1234", "issue:1234", issue1234" and "bug(1234)" patterns, the revset below should be written fully from scratch for each issue ID. grep(r"\bissue[ :]?1234\b|\bbug\(1234\)") This patch introduces new infix operator "##" to concatenate strings/symbols at runtime. Operator symbol "##" comes from the same one of C pre-processor. This concatenation allows parametrizing a part of strings in revset queries. In the case of example above, the definition of the revset alias using operator "##" below can search issue ID "1234" in complicated patterns by "issue(1234)" simply: issue($1) = grep(r"\bissue[ :]?" ## $1 ## r"\b|\bbug\(" ## $1 ## r"\)") "##" operator does: - concatenate not only strings but also symbols into the string Exact distinction between strings and symbols seems not to be convenience, because it is tiresome for users (and "revset.getstring" treats both similarly) For example of revset alias "issue()", "issue(1234)" is easier than "issue('1234')". - have higher priority than any other prefix, infix and postfix operators (like as "##" of C pre-processor) This patch (re-)assigns the priority 20 to "##", and 21 to "(", because priority 19 is already assigned to "-" as prefix "negate".

File last commit:

r23091:8d43c6bb stable
r23742:3a4d8a6c default
Show More
churn.py
200 lines | 6.7 KiB | text/x-python | PythonLexer
# churn.py - create a graph of revisions count grouped by template
#
# Copyright 2006 Josef "Jeff" Sipek <jeffpc@josefsipek.net>
# Copyright 2008 Alexander Solovyov <piranha@piranha.org.ua>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
'''command to display statistics about repository history'''
from mercurial.i18n import _
from mercurial import patch, cmdutil, scmutil, util, templater, commands
from mercurial import encoding
import os
import time, datetime
cmdtable = {}
command = cmdutil.command(cmdtable)
testedwith = 'internal'
def maketemplater(ui, repo, tmpl):
tmpl = templater.parsestring(tmpl, quoted=False)
try:
t = cmdutil.changeset_templater(ui, repo, False, None, tmpl,
None, False)
except SyntaxError, inst:
raise util.Abort(inst.args[0])
return t
def changedlines(ui, repo, ctx1, ctx2, fns):
added, removed = 0, 0
fmatch = scmutil.matchfiles(repo, fns)
diff = ''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
for l in diff.split('\n'):
if l.startswith("+") and not l.startswith("+++ "):
added += 1
elif l.startswith("-") and not l.startswith("--- "):
removed += 1
return (added, removed)
def countrate(ui, repo, amap, *pats, **opts):
"""Calculate stats"""
if opts.get('dateformat'):
def getkey(ctx):
t, tz = ctx.date()
date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
return date.strftime(opts['dateformat'])
else:
tmpl = opts.get('template', '{author|email}')
tmpl = maketemplater(ui, repo, tmpl)
def getkey(ctx):
ui.pushbuffer()
tmpl.show(ctx)
return ui.popbuffer()
state = {'count': 0}
rate = {}
df = False
if opts.get('date'):
df = util.matchdate(opts['date'])
m = scmutil.match(repo[None], pats, opts)
def prep(ctx, fns):
rev = ctx.rev()
if df and not df(ctx.date()[0]): # doesn't match date format
return
key = getkey(ctx).strip()
key = amap.get(key, key) # alias remap
if opts.get('changesets'):
rate[key] = (rate.get(key, (0,))[0] + 1, 0)
else:
parents = ctx.parents()
if len(parents) > 1:
ui.note(_('revision %d is a merge, ignoring...\n') % (rev,))
return
ctx1 = parents[0]
lines = changedlines(ui, repo, ctx1, ctx, fns)
rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]
state['count'] += 1
ui.progress(_('analyzing'), state['count'], total=len(repo))
for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
continue
ui.progress(_('analyzing'), None)
return rate
@command('churn',
[('r', 'rev', [],
_('count rate for the specified revision or revset'), _('REV')),
('d', 'date', '',
_('count rate for revisions matching date spec'), _('DATE')),
('t', 'template', '{author|email}',
_('template to group changesets'), _('TEMPLATE')),
('f', 'dateformat', '',
_('strftime-compatible format for grouping by date'), _('FORMAT')),
('c', 'changesets', False, _('count rate by number of changesets')),
('s', 'sort', False, _('sort by key (default: sort by count)')),
('', 'diffstat', False, _('display added/removed lines separately')),
('', 'aliases', '', _('file with email aliases'), _('FILE')),
] + commands.walkopts,
_("hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]"),
inferrepo=True)
def churn(ui, repo, *pats, **opts):
'''histogram of changes to the repository
This command will display a histogram representing the number
of changed lines or revisions, grouped according to the given
template. The default template will group changes by author.
The --dateformat option may be used to group the results by
date instead.
Statistics are based on the number of changed lines, or
alternatively the number of matching revisions if the
--changesets option is specified.
Examples::
# display count of changed lines for every committer
hg churn -t "{author|email}"
# display daily activity graph
hg churn -f "%H" -s -c
# display activity of developers by month
hg churn -f "%Y-%m" -s -c
# display count of lines changed in every year
hg churn -f "%Y" -s
It is possible to map alternate email addresses to a main address
by providing a file using the following format::
<alias email> = <actual email>
Such a file may be specified with the --aliases option, otherwise
a .hgchurn file will be looked for in the working directory root.
Aliases will be split from the rightmost "=".
'''
def pad(s, l):
return s + " " * (l - encoding.colwidth(s))
amap = {}
aliases = opts.get('aliases')
if not aliases and os.path.exists(repo.wjoin('.hgchurn')):
aliases = repo.wjoin('.hgchurn')
if aliases:
for l in open(aliases, "r"):
try:
alias, actual = l.rsplit('=' in l and '=' or None, 1)
amap[alias.strip()] = actual.strip()
except ValueError:
l = l.strip()
if l:
ui.warn(_("skipping malformed alias: %s\n") % l)
continue
rate = countrate(ui, repo, amap, *pats, **opts).items()
if not rate:
return
if opts.get('sort'):
rate.sort()
else:
rate.sort(key=lambda x: (-sum(x[1]), x))
# Be careful not to have a zero maxcount (issue833)
maxcount = float(max(sum(v) for k, v in rate)) or 1.0
maxname = max(len(k) for k, v in rate)
ttywidth = ui.termwidth()
ui.debug("assuming %i character terminal\n" % ttywidth)
width = ttywidth - maxname - 2 - 2 - 2
if opts.get('diffstat'):
width -= 15
def format(name, diffstat):
added, removed = diffstat
return "%s %15s %s%s\n" % (pad(name, maxname),
'+%d/-%d' % (added, removed),
ui.label('+' * charnum(added),
'diffstat.inserted'),
ui.label('-' * charnum(removed),
'diffstat.deleted'))
else:
width -= 6
def format(name, count):
return "%s %6d %s\n" % (pad(name, maxname), sum(count),
'*' * charnum(sum(count)))
def charnum(count):
return int(round(count * width / maxcount))
for name, count in rate:
ui.write(format(name, count))