view mercurial/filelog.py @ 23834:bf07c19b4c82

https: support tls sni (server name indication) for https urls (issue3090)

SNI is a common way of sharing servers across multiple domains using separate
SSL certificates. As of Python 2.7.9 SSLContext has been backported from
Python 3. This patch changes sslutil's ssl_wrap_socket to use SSLContext and
take a server hostname as and argument. It also changes the url module to make
use of this argument.

The new code for 2.7.9 achieves it's task by attempting to get the SSLContext
object from the ssl module. If this fails the try/except goes back to what was
there before with the exception that the ssl_wrap_socket functions take a
server_hostname argument that doesn't get used. Assuming the SSLContext
exists, the arguments to wrap_socket at the module level are emulated on the
SSLContext. The SSLContext is initialized with the specified ssl_version. If
certfile is not None load_cert_chain is called with certfile and keyfile.
keyfile being None is not a problem, load_cert_chain will simply expect the
private key to be in the certificate file. verify_mode is set to cert_reqs. If
ca_certs is not None load_verify_locations is called with ca_certs as the
cafile. Finally the wrap_socket method of the SSLContext is called with the
socket and server hostname.

Finally, this fails test-check-commit-hg.t because the "new" function
ssl_wrap_socket has underscores in its names and underscores in its arguments.
All the underscore identifiers are taken from the other functions and as such
can't be changed to match naming conventions.

# filelog.py - file history class for mercurial
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

import error, revlog
import re

_mdre = re.compile('\1\n')
def parsemeta(text):
    """return (metadatadict, keylist, metadatasize)"""
    # text can be buffer, so we can't use .startswith or .index
    if text[:2] != '\1\n':
        return None, None
    s = _mdre.search(text, 2).start()
    mtext = text[2:s]
    meta = {}
    for l in mtext.splitlines():
        k, v = l.split(": ", 1)
        meta[k] = v
    return meta, (s + 2)

def packmeta(meta, text):
    keys = sorted(meta.iterkeys())
    metatext = "".join("%s: %s\n" % (k, meta[k]) for k in keys)
    return "\1\n%s\1\n%s" % (metatext, text)

def _censoredtext(text):
    m, offs = parsemeta(text)
    return m and "censored" in m and not text[offs:]

class filelog(revlog.revlog):
    def __init__(self, opener, path):
        super(filelog, self).__init__(opener,
                        "/".join(("data", path + ".i")))

    def read(self, node):
        t = self.revision(node)
        if not t.startswith('\1\n'):
            return t
        s = t.index('\1\n', 2)
        return t[s + 2:]

    def add(self, text, meta, transaction, link, p1=None, p2=None):
        if meta or text.startswith('\1\n'):
            text = packmeta(meta, text)
        return self.addrevision(text, transaction, link, p1, p2)

    def renamed(self, node):
        if self.parents(node)[0] != revlog.nullid:
            return False
        t = self.revision(node)
        m = parsemeta(t)[0]
        if m and "copy" in m:
            return (m["copy"], revlog.bin(m["copyrev"]))
        return False

    def size(self, rev):
        """return the size of a given revision"""

        # for revisions with renames, we have to go the slow way
        node = self.node(rev)
        if self.renamed(node):
            return len(self.read(node))
        if self._iscensored(rev):
            return 0

        # XXX if self.read(node).startswith("\1\n"), this returns (size+4)
        return super(filelog, self).size(rev)

    def cmp(self, node, text):
        """compare text with a given file revision

        returns True if text is different than what is stored.
        """

        t = text
        if text.startswith('\1\n'):
            t = '\1\n\1\n' + text

        samehashes = not super(filelog, self).cmp(node, t)
        if samehashes:
            return False

        # censored files compare against the empty file
        if self._iscensored(node):
            return text != ''

        # renaming a file produces a different hash, even if the data
        # remains unchanged. Check if it's the case (slow):
        if self.renamed(node):
            t2 = self.read(node)
            return t2 != text

        return True

    def checkhash(self, text, p1, p2, node, rev=None):
        try:
            super(filelog, self).checkhash(text, p1, p2, node, rev=rev)
        except error.RevlogError:
            if _censoredtext(text):
                raise error.CensoredNodeError(self.indexfile, node)
            raise

    def _file(self, f):
        return filelog(self.opener, f)

    def _iscensored(self, revornode):
        """Check if a file revision is censored."""
        try:
            self.revision(revornode)
            return False
        except error.CensoredNodeError:
            return True