view contrib/hgclient.py @ 39862:5a9ab91e0a45

revlog: new API to emit revision data

I recently refactored changegroup generation code to make it more
storage agnostic. I made significant progress. But there is still
a bit of work to be done. Specifically:

* Changegroup code is looking at low-level storage attributes to
  influence sorting. Sorting should be done at the storage layer.
* The linknode lookup and sorting code for ellipsis is very
  complicated.
* Linknodes are just generally wonky because e.g. file storage doesn't
  know how to translate a linkrev to a changelog node.
* We regressed performance when introducing the request-response
  objects.

Having thought about this problem a bit, I think I've come up with
a better interface for emitting revision deltas.

This commit defines and implements that interface. See the docstring
in repository.py for more info.

This API adds 3 notable features over the previous one.

First, it defers node ordering to the storage implementation in
the common case but allows overriding as necessary. We have a
facility for requesting an exact ordering (used in ellipsis
mode). We have another facility for storage order (used for changelog).

Second, we have an argument specifying assumptions about parents
revisions. This can be used to force a fulltext revision when we
don't know the receiver has a parent revision to delta against.

Third, we can control whether revision data is emitted. This makes
the API suitable as a generic "index data retrieval" API as well
as for producing revision deltas - possibly in the same operation!

The new API is much simpler: we no longer need a complicated "request"
object to encapsulate the delta generation request. I'm optimistic
this will restore performance loss associated with
emitrevisiondeltas().

Storage unit tests for the new API have been implemented.

Future commits will port existing consumers of emitrevisiondeltas()
to the new API then remove emitrevisiondeltas().

Differential Revision: https://phab.mercurial-scm.org/D4722

# A minimal client for Mercurial's command server

from __future__ import absolute_import, print_function
import os
import signal
import socket
import struct
import subprocess
import sys
import time

try:
    import cStringIO as io
    stringio = io.StringIO
except ImportError:
    import io
    stringio = io.StringIO

def connectpipe(path=None):
    cmdline = ['hg', 'serve', '--cmdserver', 'pipe']
    if path:
        cmdline += ['-R', path]

    server = subprocess.Popen(cmdline, stdin=subprocess.PIPE,
                              stdout=subprocess.PIPE)

    return server

class unixconnection(object):
    def __init__(self, sockpath):
        self.sock = sock = socket.socket(socket.AF_UNIX)
        sock.connect(sockpath)
        self.stdin = sock.makefile('wb')
        self.stdout = sock.makefile('rb')

    def wait(self):
        self.stdin.close()
        self.stdout.close()
        self.sock.close()

class unixserver(object):
    def __init__(self, sockpath, logpath=None, repopath=None):
        self.sockpath = sockpath
        cmdline = ['hg', 'serve', '--cmdserver', 'unix', '-a', sockpath]
        if repopath:
            cmdline += ['-R', repopath]
        if logpath:
            stdout = open(logpath, 'a')
            stderr = subprocess.STDOUT
        else:
            stdout = stderr = None
        self.server = subprocess.Popen(cmdline, stdout=stdout, stderr=stderr)
        # wait for listen()
        while self.server.poll() is None:
            if os.path.exists(sockpath):
                break
            time.sleep(0.1)

    def connect(self):
        return unixconnection(self.sockpath)

    def shutdown(self):
        os.kill(self.server.pid, signal.SIGTERM)
        self.server.wait()

def writeblock(server, data):
    server.stdin.write(struct.pack('>I', len(data)))
    server.stdin.write(data)
    server.stdin.flush()

def readchannel(server):
    data = server.stdout.read(5)
    if not data:
        raise EOFError
    channel, length = struct.unpack('>cI', data)
    if channel in 'IL':
        return channel, length
    else:
        return channel, server.stdout.read(length)

def sep(text):
    return text.replace('\\', '/')

def runcommand(server, args, output=sys.stdout, error=sys.stderr, input=None,
               outfilter=lambda x: x):
    print('*** runcommand', ' '.join(args))
    sys.stdout.flush()
    server.stdin.write('runcommand\n')
    writeblock(server, '\0'.join(args))

    if not input:
        input = stringio()

    while True:
        ch, data = readchannel(server)
        if ch == 'o':
            output.write(outfilter(data))
            output.flush()
        elif ch == 'e':
            error.write(data)
            error.flush()
        elif ch == 'I':
            writeblock(server, input.read(data))
        elif ch == 'L':
            writeblock(server, input.readline(data))
        elif ch == 'r':
            ret, = struct.unpack('>i', data)
            if ret != 0:
                print(' [%d]' % ret)
            return ret
        else:
            print("unexpected channel %c: %r" % (ch, data))
            if ch.isupper():
                return

def check(func, connect=connectpipe):
    sys.stdout.flush()
    server = connect()
    try:
        return func(server)
    finally:
        server.stdin.close()
        server.wait()