view hgext/win32text.py @ 22506:6e1fbcb18a75 stable

hgweb: fail if an invalid command was supplied in url path (issue4071)

Traditionally, the way to specify a command for hgweb was to use url query
arguments (e.g. "?cmd=batch"). If the command is unknown to hgweb, it gives an
error (e.g. "400 no such method: badcmd").

But there's also another way to specify a command: as a url path fragment (e.g.
"/graph"). Before, hgweb was made forgiving (looks like it was made in
44c5157474e7) and user could put any unknown command in the url. If hgweb
couldn't understand it, it would just silently fall back to the default
command, which depends on the actual style (e.g. for paper it's shortlog, for
monoblue it's summary). This was inconsistent and was breaking some tools that
rely on http status codes (as noted in the issue4071). So this patch changes
that behavior to the more consistent one, i.e. hgweb will now return "400 no
such method: badcmd".

So if some tool was relying on having an invalid command return http status
code 200 and also have some information, then it will stop working. That is, if
somebody typed foobar when they really meant shortlog (and the user was lucky
enough to choose a style where the default command is shortlog too), that fact
will now be revealed.

Code-wise, the changed if block is only relevant when there's no "?cmd" query
parameter (i.e. only when command is specified as a url path fragment), and
looks like the removed else branch was there only for falling back to default
command. With that removed, the rest of the code works as expected: it looks at
the command, and if it's not known, raises a proper ErrorResponse exception
with an appropriate message.

Evidently, there were no tests that required the old behavior. But, frankly, I
don't know any way to tell if anyone actually exploited such forgiving behavior
in some in-house tool.

# win32text.py - LF <-> CRLF/CR translation utilities for Windows/Mac users
#
#  Copyright 2005, 2007-2009 Matt Mackall <[e-mail]> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''perform automatic newline conversion (DEPRECATED)

  Deprecation: The win32text extension requires each user to configure
  the extension again and again for each clone since the configuration
  is not copied when cloning.

  We have therefore made the ``eol`` as an alternative. The ``eol``
  uses a version controlled file for its configuration and each clone
  will therefore use the right settings from the start.

To perform automatic newline conversion, use::

  [extensions]
  win32text =
  [encode]
  ** = cleverencode:
  # or ** = macencode:

  [decode]
  ** = cleverdecode:
  # or ** = macdecode:

If not doing conversion, to make sure you do not commit CRLF/CR by accident::

  [hooks]
  pretxncommit.crlf = python:hgext.win32text.forbidcrlf
  # or pretxncommit.cr = python:hgext.win32text.forbidcr

To do the same check on a server to prevent CRLF/CR from being
pushed or pulled::

  [hooks]
  pretxnchangegroup.crlf = python:hgext.win32text.forbidcrlf
  # or pretxnchangegroup.cr = python:hgext.win32text.forbidcr
'''

from mercurial.i18n import _
from mercurial.node import short
from mercurial import util
import re

testedwith = 'internal'

# regexp for single LF without CR preceding.
re_single_lf = re.compile('(^|[^\r])\n', re.MULTILINE)

newlinestr = {'\r\n': 'CRLF', '\r': 'CR'}
filterstr = {'\r\n': 'clever', '\r': 'mac'}

def checknewline(s, newline, ui=None, repo=None, filename=None):
    # warn if already has 'newline' in repository.
    # it might cause unexpected eol conversion.
    # see issue 302:
    #   http://mercurial.selenic.com/bts/issue302
    if newline in s and ui and filename and repo:
        ui.warn(_('WARNING: %s already has %s line endings\n'
                  'and does not need EOL conversion by the win32text plugin.\n'
                  'Before your next commit, please reconsider your '
                  'encode/decode settings in \nMercurial.ini or %s.\n') %
                (filename, newlinestr[newline], repo.join('hgrc')))

def dumbdecode(s, cmd, **kwargs):
    checknewline(s, '\r\n', **kwargs)
    # replace single LF to CRLF
    return re_single_lf.sub('\\1\r\n', s)

def dumbencode(s, cmd):
    return s.replace('\r\n', '\n')

def macdumbdecode(s, cmd, **kwargs):
    checknewline(s, '\r', **kwargs)
    return s.replace('\n', '\r')

def macdumbencode(s, cmd):
    return s.replace('\r', '\n')

def cleverdecode(s, cmd, **kwargs):
    if not util.binary(s):
        return dumbdecode(s, cmd, **kwargs)
    return s

def cleverencode(s, cmd):
    if not util.binary(s):
        return dumbencode(s, cmd)
    return s

def macdecode(s, cmd, **kwargs):
    if not util.binary(s):
        return macdumbdecode(s, cmd, **kwargs)
    return s

def macencode(s, cmd):
    if not util.binary(s):
        return macdumbencode(s, cmd)
    return s

_filters = {
    'dumbdecode:': dumbdecode,
    'dumbencode:': dumbencode,
    'cleverdecode:': cleverdecode,
    'cleverencode:': cleverencode,
    'macdumbdecode:': macdumbdecode,
    'macdumbencode:': macdumbencode,
    'macdecode:': macdecode,
    'macencode:': macencode,
    }

def forbidnewline(ui, repo, hooktype, node, newline, **kwargs):
    halt = False
    seen = set()
    # we try to walk changesets in reverse order from newest to
    # oldest, so that if we see a file multiple times, we take the
    # newest version as canonical. this prevents us from blocking a
    # changegroup that contains an unacceptable commit followed later
    # by a commit that fixes the problem.
    tip = repo['tip']
    for rev in xrange(len(repo) - 1, repo[node].rev() - 1, -1):
        c = repo[rev]
        for f in c.files():
            if f in seen or f not in tip or f not in c:
                continue
            seen.add(f)
            data = c[f].data()
            if not util.binary(data) and newline in data:
                if not halt:
                    ui.warn(_('attempt to commit or push text file(s) '
                              'using %s line endings\n') %
                              newlinestr[newline])
                ui.warn(_('in %s: %s\n') % (short(c.node()), f))
                halt = True
    if halt and hooktype == 'pretxnchangegroup':
        crlf = newlinestr[newline].lower()
        filter = filterstr[newline]
        ui.warn(_('\nTo prevent this mistake in your local repository,\n'
                  'add to Mercurial.ini or .hg/hgrc:\n'
                  '\n'
                  '[hooks]\n'
                  'pretxncommit.%s = python:hgext.win32text.forbid%s\n'
                  '\n'
                  'and also consider adding:\n'
                  '\n'
                  '[extensions]\n'
                  'win32text =\n'
                  '[encode]\n'
                  '** = %sencode:\n'
                  '[decode]\n'
                  '** = %sdecode:\n') % (crlf, crlf, filter, filter))
    return halt

def forbidcrlf(ui, repo, hooktype, node, **kwargs):
    return forbidnewline(ui, repo, hooktype, node, '\r\n', **kwargs)

def forbidcr(ui, repo, hooktype, node, **kwargs):
    return forbidnewline(ui, repo, hooktype, node, '\r', **kwargs)

def reposetup(ui, repo):
    if not repo.local():
        return
    for name, fn in _filters.iteritems():
        repo.adddatafilter(name, fn)

def extsetup(ui):
    if ui.configbool('win32text', 'warn', True):
        ui.warn(_("win32text is deprecated: "
                  "http://mercurial.selenic.com/wiki/Win32TextExtension\n"))