annotate mercurial/filelog.py @ 20172:181108726ea5

http: reuse authentication info after the first failed request (issue3567)

Context: mercurial access to repository server with http access, and this
server is protected by basic auth.

Before patch:

* mercurial try an anonymous access to server, server return 401 response and
  mercurial resend request with login / password information

After patch:

* mercurial try an anonymous access to server, server return 401
  response. For all subsequent requests, mercurial keep in memory this
  information (this server need basic auth information).

This patch reduce the number of http access against mercurial server.

Example, before patch :

10.10.168.170 - - [25/Oct/2013:15:44:51 +0200] "GET /hg/testagt?cmd=capabilities
HTTP/1.1" 401 260 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:44:52 +0200] "GET /hg/testagt?cmd=capabilities
HTTP/1.1" 200 147 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:00 +0200] "GET /hg/testagt?cmd=capabilities
HTTP/1.1" 401 260 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:01 +0200] "GET /hg/testagt?cmd=capabilities
HTTP/1.1" 200 147 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:03 +0200] "GET /hg/testagt?cmd=batch
HTTP/1.1" 401 260 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:04 +0200] "GET /hg/testagt?cmd=batch
HTTP/1.1" 200 42 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:06 +0200] "GET /hg/testagt?cmd=getbundle
HTTP/1.1" 401 260 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:07 +0200] "GET /hg/testagt?cmd=getbundle
HTTP/1.1" 200 61184 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:09 +0200] "GET /hg/testagt?cmd=listkeys
HTTP/1.1" 401 260 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:10 +0200] "GET /hg/testagt?cmd=listkeys
HTTP/1.1" 200 15 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:12 +0200] "GET /hg/testagt?cmd=listkeys
HTTP/1.1" 401 260 "-" "mercurial/proto-1.0"
10.10.168.170 - - [25/Oct/2013:15:45:12 +0200] "GET /hg/testagt?cmd=listkeys
HTTP/1.1" 200 - "-" "mercurial/proto-1.0"

Example after patch :

10.10.168.170 - - [28/Oct/2013:11:49:14 +0100] "GET /hg/testagt?cmd=capabilities
HTTP/1.1" 401 260 "-" "mercurial/proto-1.0"
10.10.168.170 - - [28/Oct/2013:11:49:15 +0100] "GET /hg/testagt?cmd=capabilities
HTTP/1.1" 200 147 "-" "mercurial/proto-1.0"
10.10.168.170 - - [28/Oct/2013:11:49:17 +0100] "GET /hg/testagt?cmd=batch
HTTP/1.1" 200 42 "-" "mercurial/proto-1.0"
10.10.168.170 - - [28/Oct/2013:11:49:19 +0100] "GET /hg/testagt?cmd=getbundle
HTTP/1.1" 200 61184 "-" "mercurial/proto-1.0"
10.10.168.170 - - [28/Oct/2013:11:49:22 +0100] "GET /hg/testagt?cmd=listkeys
HTTP/1.1" 200 15 "-" "mercurial/proto-1.0"
10.10.168.170 - - [28/Oct/2013:11:49:24 +0100] "GET /hg/testagt?cmd=listkeys
HTTP/1.1" 200 - "-" "mercurial/proto-1.0"

In this last example, you can see only one 401 response.

# 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 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, None
    s = _mdre.search(text, 2).start()
    mtext = text[2:s]
    meta = {}
    keys = []
    for l in mtext.splitlines():
        k, v = l.split(": ", 1)
        meta[k] = v
        keys.append(k)
    return meta, keys, (s + 2)

def _packmeta(meta, keys=None):
    if not keys:
        keys = sorted(meta.iterkeys())
    return "".join("%s: %s\n" % (k, meta[k]) for k in keys)

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 = "\1\n%s\1\n%s" % (_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))

        # 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

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