view mercurial/urllibcompat.py @ 35616:706aa203b396

fileset: add a lightweight file filtering language

This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1].  We want a way to specify what
files will be converted to LFS at commit time.  And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs.  I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.

Yuya suggested farming out to fileset.parse(), which added support for more
symbols.  The only fileset element not supported here is 'negate'.  (List isn't
supported by filesets either.)  I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config.  The extension operator was changed from '.'
to '**', to match how recursive path globs are specified.  Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher.  Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2].  We should
probably revisit that, because it's seriously ugly.  But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.

I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.

Sample filter settings:

  all()                        # everything
  size(">20MB")                # larger than 20MB
  !**.txt                      # except for .txt files
  **.zip | **.tar.gz | **.7z   # some types of compressed files
  "path:bin"                   # files under "bin" in the project root

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html

# urllibcompat.py - adapters to ease using urllib2 on Py2 and urllib on Py3
#
# Copyright 2017 Google, Inc.
#
# 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 . import pycompat

_sysstr = pycompat.sysstr

class _pycompatstub(object):
    def __init__(self):
        self._aliases = {}

    def _registeraliases(self, origin, items):
        """Add items that will be populated at the first access"""
        items = map(_sysstr, items)
        self._aliases.update(
            (item.replace(_sysstr('_'), _sysstr('')).lower(), (origin, item))
            for item in items)

    def _registeralias(self, origin, attr, name):
        """Alias ``origin``.``attr`` as ``name``"""
        self._aliases[_sysstr(name)] = (origin, _sysstr(attr))

    def __getattr__(self, name):
        try:
            origin, item = self._aliases[name]
        except KeyError:
            raise AttributeError(name)
        self.__dict__[name] = obj = getattr(origin, item)
        return obj

httpserver = _pycompatstub()
urlreq = _pycompatstub()
urlerr = _pycompatstub()

if pycompat.ispy3:
    import urllib.parse
    urlreq._registeraliases(urllib.parse, (
        "splitattr",
        "splitpasswd",
        "splitport",
        "splituser",
        "urlparse",
        "urlunparse",
    ))
    urlreq._registeralias(urllib.parse, "unquote_to_bytes", "unquote")
    import urllib.request
    urlreq._registeraliases(urllib.request, (
        "AbstractHTTPHandler",
        "BaseHandler",
        "build_opener",
        "FileHandler",
        "FTPHandler",
        "ftpwrapper",
        "HTTPHandler",
        "HTTPSHandler",
        "install_opener",
        "pathname2url",
        "HTTPBasicAuthHandler",
        "HTTPDigestAuthHandler",
        "HTTPPasswordMgrWithDefaultRealm",
        "ProxyHandler",
        "Request",
        "url2pathname",
        "urlopen",
    ))
    import urllib.response
    urlreq._registeraliases(urllib.response, (
        "addclosehook",
        "addinfourl",
    ))
    import urllib.error
    urlerr._registeraliases(urllib.error, (
        "HTTPError",
        "URLError",
    ))
    import http.server
    httpserver._registeraliases(http.server, (
        "HTTPServer",
        "BaseHTTPRequestHandler",
        "SimpleHTTPRequestHandler",
        "CGIHTTPRequestHandler",
    ))

    # urllib.parse.quote() accepts both str and bytes, decodes bytes
    # (if necessary), and returns str. This is wonky. We provide a custom
    # implementation that only accepts bytes and emits bytes.
    def quote(s, safe=r'/'):
        s = urllib.parse.quote_from_bytes(s, safe=safe)
        return s.encode('ascii', 'strict')

    # urllib.parse.urlencode() returns str. We use this function to make
    # sure we return bytes.
    def urlencode(query, doseq=False):
            s = urllib.parse.urlencode(query, doseq=doseq)
            return s.encode('ascii')

    urlreq.quote = quote
    urlreq.urlencode = urlencode

    def getfullurl(req):
        return req.full_url

    def gethost(req):
        return req.host

    def getselector(req):
        return req.selector

    def getdata(req):
        return req.data

    def hasdata(req):
        return req.data is not None
else:
    import BaseHTTPServer
    import CGIHTTPServer
    import SimpleHTTPServer
    import urllib2
    import urllib
    import urlparse
    urlreq._registeraliases(urllib, (
        "addclosehook",
        "addinfourl",
        "ftpwrapper",
        "pathname2url",
        "quote",
        "splitattr",
        "splitpasswd",
        "splitport",
        "splituser",
        "unquote",
        "url2pathname",
        "urlencode",
    ))
    urlreq._registeraliases(urllib2, (
        "AbstractHTTPHandler",
        "BaseHandler",
        "build_opener",
        "FileHandler",
        "FTPHandler",
        "HTTPBasicAuthHandler",
        "HTTPDigestAuthHandler",
        "HTTPHandler",
        "HTTPPasswordMgrWithDefaultRealm",
        "HTTPSHandler",
        "install_opener",
        "ProxyHandler",
        "Request",
        "urlopen",
    ))
    urlreq._registeraliases(urlparse, (
        "urlparse",
        "urlunparse",
    ))
    urlerr._registeraliases(urllib2, (
        "HTTPError",
        "URLError",
    ))
    httpserver._registeraliases(BaseHTTPServer, (
        "HTTPServer",
        "BaseHTTPRequestHandler",
    ))
    httpserver._registeraliases(SimpleHTTPServer, (
        "SimpleHTTPRequestHandler",
    ))
    httpserver._registeraliases(CGIHTTPServer, (
        "CGIHTTPRequestHandler",
    ))

    def gethost(req):
        return req.get_host()

    def getselector(req):
        return req.get_selector()

    def getfullurl(req):
        return req.get_full_url()

    def getdata(req):
        return req.get_data()

    def hasdata(req):
        return req.has_data()