view tests/tinyproxy.py @ 24545:9e0c67e84896

json: implement {tags} template

Tags is pretty easy to implement. Let's start there.

The output is slightly different from `hg tags -Tjson`. For reference,
the CLI has the following output:

  [
   {
    "node": "e2049974f9a23176c2addb61d8f5b86e0d620490",
    "rev": 29880,
    "tag": "tip",
    "type": ""
   },
   ...
  ]

Our output has the format:

  {
    "node": "0aeb19ea57a6d223bacddda3871cb78f24b06510",
    "tags": [
      {
        "node": "e2049974f9a23176c2addb61d8f5b86e0d620490",
        "tag": "tag1",
        "date": [1427775457.0, 25200]
      },
      ...
    ]
  }

"rev" is omitted because it isn't a reliable identifier. We shouldn't
be exposing them in web APIs and giving the impression it remotely
resembles a stable identifier. Perhaps we could one day hide this behind
a config option (it might be useful to expose when running servers
locally).

The "type" of the tag isn't defined because this information isn't yet
exposed to the hgweb templater (it could be in a follow-up) and because
it is questionable whether different types should be exposed at all.
(Should the web interface really be exposing "local" tags?)

We use an object for the outer type instead of Array for a few reasons.
First, it is extensible. If we ever need to throw more global properties
into the output, we can do that without breaking backwards compatibility
(property additions should be backwards compatible). Second, uniformity
in web APIs is nice. Having everything return objects seems much saner than
a mix of array and object. Third, there are security issues with arrays
in older browsers. The JSON web services world almost never uses arrays
as the main type for this reason.

Another possibly controversial part about this patch is how dates are
defined. While JSON has a Date type, it is based on the JavaScript Date
type, which is widely considered a pile of garbage. It is a non-starter
for this reason.

Many of Mercurial's built-in date filters drop seconds resolution. So
that's a non-starter as well, since we want the API to be lossless where
possible. rfc3339date, rfc822date, isodatesec, and date are all lossless.
However, they each require the client to perform string parsing on top of
JSON decoding. While date parsing libraries are pretty ubiquitous, some
languages don't have them out of the box. However, pretty much every
programming language can deal with UNIX timestamps (which are just
integers or floats). So, we choose to use Mercurial's internal date
representation, which in JSON is modeled as float seconds since UNIX
epoch and an integer timezone offset from UTC (keep in mind
JavaScript/JSON models all "Numbers" as double prevision floating point
numbers, so there isn't a difference between ints and floats in JSON).

#!/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)