view mercurial/hgweb/protocol.py @ 7180:a42d27bc809d

hgweb: be sure to drain request data even in early error conditions

Thanks to Mads Kiilerich with noticing this. The hg client can only read data
after all the sent data has been read, so we have to read all the request data
even if we're not going to do anything with it (in error conditions). This
is not easy to fix in the client, because we're using Python's httplib, which
is strictly stateful. Abstracted the draining into a separate method.

#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.

import cStringIO, zlib, tempfile, errno, os, sys
from mercurial import util, streamclone
from mercurial.node import bin, hex
from mercurial import changegroup as changegroupmod
from common import HTTP_OK, HTTP_NOT_FOUND, HTTP_SERVER_ERROR

# __all__ is populated with the allowed commands. Be sure to add to it if
# you're adding a new command, or the new command won't work.

__all__ = [
   'lookup', 'heads', 'branches', 'between', 'changegroup',
   'changegroupsubset', 'capabilities', 'unbundle', 'stream_out',
]

HGTYPE = 'application/mercurial-0.1'

def lookup(repo, req):
    try:
        r = hex(repo.lookup(req.form['key'][0]))
        success = 1
    except Exception,inst:
        r = str(inst)
        success = 0
    resp = "%s %s\n" % (success, r)
    req.respond(HTTP_OK, HGTYPE, length=len(resp))
    yield resp

def heads(repo, req):
    resp = " ".join(map(hex, repo.heads())) + "\n"
    req.respond(HTTP_OK, HGTYPE, length=len(resp))
    yield resp

def branches(repo, req):
    nodes = []
    if 'nodes' in req.form:
        nodes = map(bin, req.form['nodes'][0].split(" "))
    resp = cStringIO.StringIO()
    for b in repo.branches(nodes):
        resp.write(" ".join(map(hex, b)) + "\n")
    resp = resp.getvalue()
    req.respond(HTTP_OK, HGTYPE, length=len(resp))
    yield resp

def between(repo, req):
    if 'pairs' in req.form:
        pairs = [map(bin, p.split("-"))
                 for p in req.form['pairs'][0].split(" ")]
    resp = cStringIO.StringIO()
    for b in repo.between(pairs):
        resp.write(" ".join(map(hex, b)) + "\n")
    resp = resp.getvalue()
    req.respond(HTTP_OK, HGTYPE, length=len(resp))
    yield resp

def changegroup(repo, req):
    req.respond(HTTP_OK, HGTYPE)
    nodes = []

    if 'roots' in req.form:
        nodes = map(bin, req.form['roots'][0].split(" "))

    z = zlib.compressobj()
    f = repo.changegroup(nodes, 'serve')
    while 1:
        chunk = f.read(4096)
        if not chunk:
            break
        yield z.compress(chunk)

    yield z.flush()

def changegroupsubset(repo, req):
    req.respond(HTTP_OK, HGTYPE)
    bases = []
    heads = []

    if 'bases' in req.form:
        bases = [bin(x) for x in req.form['bases'][0].split(' ')]
    if 'heads' in req.form:
        heads = [bin(x) for x in req.form['heads'][0].split(' ')]

    z = zlib.compressobj()
    f = repo.changegroupsubset(bases, heads, 'serve')
    while 1:
        chunk = f.read(4096)
        if not chunk:
            break
        yield z.compress(chunk)

    yield z.flush()

def capabilities(repo, req):
    caps = ['lookup', 'changegroupsubset']
    if repo.ui.configbool('server', 'uncompressed', untrusted=True):
        caps.append('stream=%d' % repo.changelog.version)
    if changegroupmod.bundlepriority:
        caps.append('unbundle=%s' % ','.join(changegroupmod.bundlepriority))
    rsp = ' '.join(caps)
    req.respond(HTTP_OK, HGTYPE, length=len(rsp))
    yield rsp

def unbundle(repo, req):

    proto = req.env.get('wsgi.url_scheme') or 'http'
    their_heads = req.form['heads'][0].split(' ')

    def check_heads():
        heads = map(hex, repo.heads())
        return their_heads == [hex('force')] or their_heads == heads

    # fail early if possible
    if not check_heads():
        req.drain()
        raise ErrorResponse(HTTP_OK, 'unsynced changes')

    # do not lock repo until all changegroup data is
    # streamed. save to temporary file.

    fd, tempname = tempfile.mkstemp(prefix='hg-unbundle-')
    fp = os.fdopen(fd, 'wb+')
    try:
        length = int(req.env['CONTENT_LENGTH'])
        for s in util.filechunkiter(req, limit=length):
            fp.write(s)

        try:
            lock = repo.lock()
            try:
                if not check_heads():
                    raise ErrorResponse(HTTP_OK, 'unsynced changes')

                fp.seek(0)
                header = fp.read(6)
                if header.startswith('HG') and not header.startswith('HG10'):
                    raise ValueError('unknown bundle version')
                elif header not in changegroupmod.bundletypes:
                    raise ValueError('unknown bundle compression type')
                gen = changegroupmod.unbundle(header, fp)

                # send addchangegroup output to client

                oldio = sys.stdout, sys.stderr
                sys.stderr = sys.stdout = cStringIO.StringIO()

                try:
                    url = 'remote:%s:%s' % (proto,
                                            req.env.get('REMOTE_HOST', ''))
                    try:
                        ret = repo.addchangegroup(gen, 'serve', url)
                    except util.Abort, inst:
                        sys.stdout.write("abort: %s\n" % inst)
                        ret = 0
                finally:
                    val = sys.stdout.getvalue()
                    sys.stdout, sys.stderr = oldio
                req.respond(HTTP_OK, HGTYPE)
                return '%d\n%s' % (ret, val),
            finally:
                del lock
        except ValueError, inst:
            raise ErrorResponse(HTTP_OK, inst)
        except (OSError, IOError), inst:
            filename = getattr(inst, 'filename', '')
            # Don't send our filesystem layout to the client
            if filename.startswith(repo.root):
                filename = filename[len(repo.root)+1:]
            else:
                filename = ''
            error = getattr(inst, 'strerror', 'Unknown error')
            if inst.errno == errno.ENOENT:
                code = HTTP_NOT_FOUND
            else:
                code = HTTP_SERVER_ERROR
            raise ErrorResponse(code, '%s: %s' % (error, filename))
    finally:
        fp.close()
        os.unlink(tempname)

def stream_out(repo, req):
    req.respond(HTTP_OK, HGTYPE)
    try:
        for chunk in streamclone.stream_out(repo, untrusted=True):
            yield chunk
    except streamclone.StreamException, inst:
        yield str(inst)