annotate mercurial/pure/bdiff.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.

# bdiff.py - Python implementation of bdiff.c
#
# Copyright 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.

import struct, difflib, re

def splitnewlines(text):
    '''like str.splitlines, but only split on newlines.'''
    lines = [l + '\n' for l in text.split('\n')]
    if lines:
        if lines[-1] == '\n':
            lines.pop()
        else:
            lines[-1] = lines[-1][:-1]
    return lines

def _normalizeblocks(a, b, blocks):
    prev = None
    r = []
    for curr in blocks:
        if prev is None:
            prev = curr
            continue
        shift = 0

        a1, b1, l1 = prev
        a1end = a1 + l1
        b1end = b1 + l1

        a2, b2, l2 = curr
        a2end = a2 + l2
        b2end = b2 + l2
        if a1end == a2:
            while (a1end + shift < a2end and
                   a[a1end + shift] == b[b1end + shift]):
                shift += 1
        elif b1end == b2:
            while (b1end + shift < b2end and
                   a[a1end + shift] == b[b1end + shift]):
                shift += 1
        r.append((a1, b1, l1 + shift))
        prev = a2 + shift, b2 + shift, l2 - shift
    r.append(prev)
    return r

def bdiff(a, b):
    a = str(a).splitlines(True)
    b = str(b).splitlines(True)

    if not a:
        s = "".join(b)
        return s and (struct.pack(">lll", 0, 0, len(s)) + s)

    bin = []
    p = [0]
    for i in a: p.append(p[-1] + len(i))

    d = difflib.SequenceMatcher(None, a, b).get_matching_blocks()
    d = _normalizeblocks(a, b, d)
    la = 0
    lb = 0
    for am, bm, size in d:
        s = "".join(b[lb:bm])
        if am > la or s:
            bin.append(struct.pack(">lll", p[la], p[am], len(s)) + s)
        la = am + size
        lb = bm + size

    return "".join(bin)

def blocks(a, b):
    an = splitnewlines(a)
    bn = splitnewlines(b)
    d = difflib.SequenceMatcher(None, an, bn).get_matching_blocks()
    d = _normalizeblocks(an, bn, d)
    return [(i, i + n, j, j + n) for (i, j, n) in d]

def fixws(text, allws):
    if allws:
        text = re.sub('[ \t\r]+', '', text)
    else:
        text = re.sub('[ \t\r]+', ' ', text)
        text = text.replace(' \n', '\n')
    return text