view tests/tinyproxy.py @ 23923:ab6fd3205dad stable

largefiles: fix commit of a directory with no largefile changes (issue4330)

When a directory is named in the commit file list, the previous behavior was to
walk the list, and if no normal files in the directory were also named, add the
corresponding standin for each largefile in that directory.  The directory is
then dropped from the list, so that committing a directory with no normal file
changes works.  It then added the corresponding standin directory for the first
largefile seen, by prefixing it with '.hglf/'.

The latter is unnecessary since each affected largefile is explicitly referenced
by its standin in the list.  It also caused an abort if there were no changed
largefiles in the directory, because none of its standins changed:

    abort: .hglf/foo/bar: no match under directory!

This list of files is used to tweak a matcher in lfutil.updatestandinsbymatch(),
which is what is passed to commit().

The status() call that is ultimately done in the commit code with this matcher
seems to have some OS specific differences.  It is not necessary to append '.'
for Windows to run the largefiles tests cleanly.  But if '.' is not added to the
list, the match function isn't called on Linux, so status() would miss any
normal files that were also in a named directory.  The commit then proceeds
without those normal files, or says "nothing changed" if there were no changed
largefiles in the directory.  This is not filesystem specific, as VFAT on Linux
had the same behavior as when run on ext4.  It is also not an issue with
lfilesrepo.status(), since that only calls the overridden implementation when
paths are passed to commit.  I dont have access to an OS X machine ATM to test
there.

Maybe there's a better way to do this.  But since the standin directory for the
first largefile was previously being added, and that caused the same walk in
status(), there's no preformance change to this.  There is no danger of
erroneously committing files in '.', because the original match function is
called, and if it fails, the lfutil.updatestandinsbymatch() tweaked matcher only
indicates a match if the file is in the list of standins- and '.' never is.  The
added tests confirm this.

#!/usr/bin/env python

__doc__ = """Tiny HTTP Proxy.

This module implements GET, HEAD, POST, PUT and DELETE methods
on BaseHTTPServer, and behaves as an HTTP proxy.  The CONNECT
method is also implemented experimentally, but has not been
tested yet.

Any help will be greatly appreciated.           SUZUKI Hisao
"""

__version__ = "0.2.1"

import BaseHTTPServer, select, socket, SocketServer, urlparse, os

class ProxyHandler (BaseHTTPServer.BaseHTTPRequestHandler):
    __base = BaseHTTPServer.BaseHTTPRequestHandler
    __base_handle = __base.handle

    server_version = "TinyHTTPProxy/" + __version__
    rbufsize = 0                        # self.rfile Be unbuffered

    def handle(self):
        (ip, port) =  self.client_address
        allowed = getattr(self, 'allowed_clients', None)
        if allowed is not None and ip not in allowed:
            self.raw_requestline = self.rfile.readline()
            if self.parse_request():
                self.send_error(403)
        else:
            self.__base_handle()

    def log_request(self, code='-', size='-'):
        xheaders = [h for h in self.headers.items() if h[0].startswith('x-')]
        self.log_message('"%s" %s %s%s',
                         self.requestline, str(code), str(size),
                         ''.join([' %s:%s' % h for h in sorted(xheaders)]))

    def _connect_to(self, netloc, soc):
        i = netloc.find(':')
        if i >= 0:
            host_port = netloc[:i], int(netloc[i + 1:])
        else:
            host_port = netloc, 80
        print "\t" "connect to %s:%d" % host_port
        try: soc.connect(host_port)
        except socket.error, arg:
            try: msg = arg[1]
            except (IndexError, TypeError): msg = arg
            self.send_error(404, msg)
            return 0
        return 1

    def do_CONNECT(self):
        soc = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        try:
            if self._connect_to(self.path, soc):
                self.log_request(200)
                self.wfile.write(self.protocol_version +
                                 " 200 Connection established\r\n")
                self.wfile.write("Proxy-agent: %s\r\n" % self.version_string())
                self.wfile.write("\r\n")
                self._read_write(soc, 300)
        finally:
            print "\t" "bye"
            soc.close()
            self.connection.close()

    def do_GET(self):
        (scm, netloc, path, params, query, fragment) = urlparse.urlparse(
            self.path, 'http')
        if scm != 'http' or fragment or not netloc:
            self.send_error(400, "bad url %s" % self.path)
            return
        soc = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        try:
            if self._connect_to(netloc, soc):
                self.log_request()
                soc.send("%s %s %s\r\n" % (
                    self.command,
                    urlparse.urlunparse(('', '', path, params, query, '')),
                    self.request_version))
                self.headers['Connection'] = 'close'
                del self.headers['Proxy-Connection']
                for key_val in self.headers.items():
                    soc.send("%s: %s\r\n" % key_val)
                soc.send("\r\n")
                self._read_write(soc)
        finally:
            print "\t" "bye"
            soc.close()
            self.connection.close()

    def _read_write(self, soc, max_idling=20):
        iw = [self.connection, soc]
        ow = []
        count = 0
        while True:
            count += 1
            (ins, _, exs) = select.select(iw, ow, iw, 3)
            if exs:
                break
            if ins:
                for i in ins:
                    if i is soc:
                        out = self.connection
                    else:
                        out = soc
                    try:
                        data = i.recv(8192)
                    except socket.error:
                        break
                    if data:
                        out.send(data)
                        count = 0
            else:
                print "\t" "idle", count
            if count == max_idling:
                break

    do_HEAD = do_GET
    do_POST = do_GET
    do_PUT  = do_GET
    do_DELETE = do_GET

class ThreadingHTTPServer (SocketServer.ThreadingMixIn,
                           BaseHTTPServer.HTTPServer):
    def __init__(self, *args, **kwargs):
        BaseHTTPServer.HTTPServer.__init__(self, *args, **kwargs)
        a = open("proxy.pid", "w")
        a.write(str(os.getpid()) + "\n")
        a.close()

if __name__ == '__main__':
    from sys import argv
    if argv[1:] and argv[1] in ('-h', '--help'):
        print argv[0], "[port [allowed_client_name ...]]"
    else:
        if argv[2:]:
            allowed = []
            for name in argv[2:]:
                client = socket.gethostbyname(name)
                allowed.append(client)
                print "Accept: %s (%s)" % (client, name)
            ProxyHandler.allowed_clients = allowed
            del argv[2:]
        else:
            print "Any clients will be served..."
        BaseHTTPServer.test(ProxyHandler, ThreadingHTTPServer)