Source code for tornado.web

#!/usr/bin/env python
#
# Copyright 2009 Facebook
#
# Licensed under the Apache License, Version 2.0 (the "License"); you may
# not use this file except in compliance with the License. You may obtain
# a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations
# under the License.

"""``tornado.web`` provides a simple web framework with asynchronous
features that allow it to scale to large numbers of open connections,
making it ideal for `long polling
<http://en.wikipedia.org/wiki/Push_technology#Long_polling>`_.

Here is a simple "Hello, world" example app::

    import tornado.ioloop
    import tornado.web

    class MainHandler(tornado.web.RequestHandler):
        def get(self):
            self.write("Hello, world")

    if __name__ == "__main__":
        application = tornado.web.Application([
            (r"/", MainHandler),
        ])
        application.listen(8888)
        tornado.ioloop.IOLoop.instance().start()

See the :doc:`Tornado overview <overview>` for more details and a good getting
started guide.

Thread-safety notes
-------------------

In general, methods on `RequestHandler` and elsewhere in Tornado are
not thread-safe.  In particular, methods such as
`~RequestHandler.write()`, `~RequestHandler.finish()`, and
`~RequestHandler.flush()` must only be called from the main thread.  If
you use multiple threads it is important to use `.IOLoop.add_callback`
to transfer control back to the main thread before finishing the
request.
"""

from __future__ import absolute_import, division, print_function, with_statement


import base64
import binascii
import datetime
import email.utils
import functools
import gzip
import hashlib
import hmac
import mimetypes
import numbers
import os.path
import re
import stat
import sys
import threading
import time
import tornado
import traceback
import types
import uuid

from tornado.concurrent import Future
from tornado import escape
from tornado import httputil
from tornado import locale
from tornado.log import access_log, app_log, gen_log
from tornado import stack_context
from tornado import template
from tornado.escape import utf8, _unicode
from tornado.util import bytes_type, import_object, ObjectDict, raise_exc_info, unicode_type

try:
    from io import BytesIO  # python 3
except ImportError:
    from cStringIO import StringIO as BytesIO  # python 2

try:
    import Cookie  # py2
except ImportError:
    import http.cookies as Cookie  # py3

try:
    import urlparse  # py2
except ImportError:
    import urllib.parse as urlparse  # py3

try:
    from urllib import urlencode  # py2
except ImportError:
    from urllib.parse import urlencode  # py3


[docs]class RequestHandler(object): """Subclass this class and define `get()` or `post()` to make a handler. If you want to support more methods than the standard GET/HEAD/POST, you should override the class variable ``SUPPORTED_METHODS`` in your `RequestHandler` subclass. """ SUPPORTED_METHODS = ("GET", "HEAD", "POST", "DELETE", "PATCH", "PUT", "OPTIONS") _template_loaders = {} # {path: template.BaseLoader} _template_loader_lock = threading.Lock() _remove_control_chars_regex = re.compile(r"[\x00-\x08\x0e-\x1f]") def __init__(self, application, request, **kwargs): super(RequestHandler, self).__init__() self.application = application self.request = request self._headers_written = False self._finished = False self._auto_finish = True self._transforms = None # will be set in _execute self.path_args = None self.path_kwargs = None self.ui = ObjectDict((n, self._ui_method(m)) for n, m in application.ui_methods.items()) # UIModules are available as both `modules` and `_tt_modules` in the # template namespace. Historically only `modules` was available # but could be clobbered by user additions to the namespace. # The template {% module %} directive looks in `_tt_modules` to avoid # possible conflicts. self.ui["_tt_modules"] = _UIModuleNamespace(self, application.ui_modules) self.ui["modules"] = self.ui["_tt_modules"] self.clear() # Check since connection is not available in WSGI if getattr(self.request, "connection", None): self.request.connection.set_close_callback( self.on_connection_close) self.initialize(**kwargs)
[docs] def initialize(self): """Hook for subclass initialization. A dictionary passed as the third argument of a url spec will be supplied as keyword arguments to initialize(). Example:: class ProfileHandler(RequestHandler): def initialize(self, database): self.database = database def get(self, username): ... app = Application([ (r'/user/(.*)', ProfileHandler, dict(database=database)), ]) """ pass
@property
[docs] def settings(self): """An alias for `self.application.settings <Application.settings>`.""" return self.application.settings
[docs] def head(self, *args, **kwargs): raise HTTPError(405)
[docs] def get(self, *args, **kwargs): raise HTTPError(405)
[docs] def post(self, *args, **kwargs): raise HTTPError(405)
[docs] def delete(self, *args, **kwargs): raise HTTPError(405)
def patch(self, *args, **kwargs): raise HTTPError(405)
[docs] def put(self, *args, **kwargs): raise HTTPError(405)
[docs] def options(self, *args, **kwargs): raise HTTPError(405)
[docs] def prepare(self): """Called at the beginning of a request before `get`/`post`/etc. Override this method to perform common initialization regardless of the request method. Asynchronous support: Decorate this method with `.gen.coroutine` or `.return_future` to make it asynchronous (the `asynchronous` decorator cannot be used on `prepare`). If this method returns a `.Future` execution will not proceed until the `.Future` is done. .. versionadded:: 3.1 Asynchronous support. """ pass
[docs] def on_finish(self): """Called after the end of a request. Override this method to perform cleanup, logging, etc. This method is a counterpart to `prepare`. ``on_finish`` may not produce any output, as it is called after the response has been sent to the client. """ pass
[docs] def on_connection_close(self): """Called in async handlers if the client closed the connection. Override this to clean up resources associated with long-lived connections. Note that this method is called only if the connection was closed during asynchronous processing; if you need to do cleanup after every request override `on_finish` instead. Proxies may keep a connection open for a time (perhaps indefinitely) after the client has gone away, so this method may not be called promptly after the end user closes their connection. """ pass
[docs] def clear(self): """Resets all headers and content for this response.""" self._headers = httputil.HTTPHeaders({ "Server": "TornadoServer/%s" % tornado.version, "Content-Type": "text/html; charset=UTF-8", "Date": httputil.format_timestamp(time.time()), }) self.set_default_headers() if (not self.request.supports_http_1_1() and getattr(self.request, 'connection', None) and not self.request.connection.no_keep_alive): conn_header = self.request.headers.get("Connection") if conn_header and (conn_header.lower() == "keep-alive"): self._headers["Connection"] = "Keep-Alive" self._write_buffer = [] self._status_code = 200 self._reason = httputil.responses[200]
[docs] def set_default_headers(self): """Override this to set HTTP headers at the beginning of the request. For example, this is the place to set a custom ``Server`` header. Note that setting such headers in the normal flow of request processing may not do what you want, since headers may be reset during error handling. """ pass
[docs] def set_status(self, status_code, reason=None): """Sets the status code for our response. :arg int status_code: Response status code. If ``reason`` is ``None``, it must be present in `httplib.responses <http.client.responses>`. :arg string reason: Human-readable reason phrase describing the status code. If ``None``, it will be filled in from `httplib.responses <http.client.responses>`. """ self._status_code = status_code if reason is not None: self._reason = escape.native_str(reason) else: try: self._reason = httputil.responses[status_code] except KeyError: raise ValueError("unknown status code %d", status_code)
[docs] def get_status(self): """Returns the status code for our response.""" return self._status_code
[docs] def set_header(self, name, value): """Sets the given response header name and value. If a datetime is given, we automatically format it according to the HTTP specification. If the value is not a string, we convert it to a string. All header values are then encoded as UTF-8. """ self._headers[name] = self._convert_header_value(value)
[docs] def add_header(self, name, value): """Adds the given response header and value. Unlike `set_header`, `add_header` may be called multiple times to return multiple values for the same header. """ self._headers.add(name, self._convert_header_value(value))
[docs] def clear_header(self, name): """Clears an outgoing header, undoing a previous `set_header` call. Note that this method does not apply to multi-valued headers set by `add_header`. """ if name in self._headers: del self._headers[name]
_INVALID_HEADER_CHAR_RE = re.compile(br"[\x00-\x1f]") def _convert_header_value(self, value): if isinstance(value, bytes_type): pass elif isinstance(value, unicode_type): value = value.encode('utf-8') elif isinstance(value, numbers.Integral): # return immediately since we know the converted value will be safe return str(value) elif isinstance(value, datetime.datetime): return httputil.format_timestamp(value) else: raise TypeError("Unsupported header value %r" % value) # If \n is allowed into the header, it is possible to inject # additional headers or split the request. Also cap length to # prevent obviously erroneous values. if (len(value) > 4000 or RequestHandler._INVALID_HEADER_CHAR_RE.search(value)): raise ValueError("Unsafe header value %r", value) return value _ARG_DEFAULT = []
[docs] def get_argument(self, name, default=_ARG_DEFAULT, strip=True): """Returns the value of the argument with the given name. If default is not provided, the argument is considered to be required, and we raise a `MissingArgumentError` if it is missing. If the argument appears in the url more than once, we return the last value. The returned value is always unicode. """ return self._get_argument(name, default, self.request.arguments, strip)
[docs] def get_arguments(self, name, strip=True): """Returns a list of the arguments with the given name. If the argument is not present, returns an empty list. The returned values are always unicode. """ return self._get_arguments(name, self.request.arguments, strip)
[docs] def get_body_argument(self, name, default=_ARG_DEFAULT, strip=True): """Returns the value of the argument with the given name from the request body. If default is not provided, the argument is considered to be required, and we raise a `MissingArgumentError` if it is missing. If the argument appears in the url more than once, we return the last value. The returned value is always unicode. .. versionadded:: 3.2 """ return self._get_argument(name, default, self.request.body_arguments, strip)
[docs] def get_body_arguments(self, name, strip=True): """Returns a list of the body arguments with the given name. If the argument is not present, returns an empty list. The returned values are always unicode. .. versionadded:: 3.2 """ return self._get_arguments(name, self.request.body_arguments, strip)
[docs] def get_query_argument(self, name, default=_ARG_DEFAULT, strip=True): """Returns the value of the argument with the given name from the request query string. If default is not provided, the argument is considered to be required, and we raise a `MissingArgumentError` if it is missing. If the argument appears in the url more than once, we return the last value. The returned value is always unicode. .. versionadded:: 3.2 """ return self._get_argument(name, default, self.request.query_arguments, strip)
[docs] def get_query_arguments(self, name, strip=True): """Returns a list of the query arguments with the given name. If the argument is not present, returns an empty list. The returned values are always unicode. .. versionadded:: 3.2 """ return self._get_arguments(name, self.request.query_arguments, strip)
def _get_argument(self, name, default, source, strip=True): args = self._get_arguments(name, source, strip=strip) if not args: if default is self._ARG_DEFAULT: raise MissingArgumentError(name) return default return args[-1] def _get_arguments(self, name, source, strip=True): values = [] for v in source.get(name, []): v = self.decode_argument(v, name=name) if isinstance(v, unicode_type): # Get rid of any weird control chars (unless decoding gave # us bytes, in which case leave it alone) v = RequestHandler._remove_control_chars_regex.sub(" ", v) if strip: v = v.strip() values.append(v) return values
[docs] def decode_argument(self, value, name=None): """Decodes an argument from the request. The argument has been percent-decoded and is now a byte string. By default, this method decodes the argument as utf-8 and returns a unicode string, but this may be overridden in subclasses. This method is used as a filter for both `get_argument()` and for values extracted from the url and passed to `get()`/`post()`/etc. The name of the argument is provided if known, but may be None (e.g. for unnamed groups in the url regex). """ try: return _unicode(value) except UnicodeDecodeError: raise HTTPError(400, "Invalid unicode in %s: %r" % (name or "url", value[:40]))
@property
[docs] def cookies(self): """An alias for `self.request.cookies <.httpserver.HTTPRequest.cookies>`.""" return self.request.cookies
[docs] def clear_all_cookies(self, path="/", domain=None): """Deletes all the cookies the user sent with this request. See `clear_cookie` for more information on the path and domain parameters. .. versionchanged:: 3.2 Added the ``path`` and ``domain`` parameters. """ for name in self.request.cookies: self.clear_cookie(name, path=path, domain=domain)
[docs] def create_signed_value(self, name, value): """Signs and timestamps a string so it cannot be forged. Normally used via set_secure_cookie, but provided as a separate method for non-cookie uses. To decode a value not stored as a cookie use the optional value argument to get_secure_cookie. """ self.require_setting("cookie_secret", "secure cookies") return create_signed_value(self.application.settings["cookie_secret"], name, value)
[docs] def redirect(self, url, permanent=False, status=None): """Sends a redirect to the given (optionally relative) URL. If the ``status`` argument is specified, that value is used as the HTTP status code; otherwise either 301 (permanent) or 302 (temporary) is chosen based on the ``permanent`` argument. The default is 302 (temporary). """ if self._headers_written: raise Exception("Cannot redirect after headers have been written") if status is None: status = 301 if permanent else 302 else: assert isinstance(status, int) and 300 <= status <= 399 self.set_status(status) self.set_header("Location", urlparse.urljoin(utf8(self.request.uri), utf8(url))) self.finish()
[docs] def write(self, chunk): """Writes the given chunk to the output buffer. To write the output to the network, use the flush() method below. If the given chunk is a dictionary, we write it as JSON and set the Content-Type of the response to be ``application/json``. (if you want to send JSON as a different ``Content-Type``, call set_header *after* calling write()). Note that lists are not converted to JSON because of a potential cross-site security vulnerability. All JSON output should be wrapped in a dictionary. More details at http://haacked.com/archive/2008/11/20/anatomy-of-a-subtle-json-vulnerability.aspx """ if self._finished: raise RuntimeError("Cannot write() after finish(). May be caused " "by using async operations without the " "@asynchronous decorator.") if not isinstance(chunk, (bytes_type, unicode_type, dict)): raise TypeError("write() only accepts bytes, unicode, and dict objects") if isinstance(chunk, dict): chunk = escape.json_encode(chunk) self.set_header("Content-Type", "application/json; charset=UTF-8") chunk = utf8(chunk) self._write_buffer.append(chunk)
[docs] def render(self, template_name, **kwargs): """Renders the template with the given arguments as the response.""" html = self.render_string(template_name, **kwargs) # Insert the additional JS and CSS added by the modules on the page js_embed = [] js_files = [] css_embed = [] css_files = [] html_heads = [] html_bodies = [] for module in getattr(self, "_active_modules", {}).values(): embed_part = module.embedded_javascript() if embed_part: js_embed.append(utf8(embed_part)) file_part = module.javascript_files() if file_part: if isinstance(file_part, (unicode_type, bytes_type)): js_files.append(file_part) else: js_files.extend(file_part) embed_part = module.embedded_css() if embed_part: css_embed.append(utf8(embed_part)) file_part = module.css_files() if file_part: if isinstance(file_part, (unicode_type, bytes_type)): css_files.append(file_part) else: css_files.extend(file_part) head_part = module.html_head() if head_part: html_heads.append(utf8(head_part)) body_part = module.html_body() if body_part: html_bodies.append(utf8(body_part)) def is_absolute(path): return any(path.startswith(x) for x in ["/", "http:", "https:"]) if js_files: # Maintain order of JavaScript files given by modules paths = [] unique_paths = set() for path in js_files: if not is_absolute(path): path = self.static_url(path) if path not in unique_paths: paths.append(path) unique_paths.add(path) js = ''.join('<script src="' + escape.xhtml_escape(p) + '" type="text/javascript"></script>' for p in paths) sloc = html.rindex(b'</body>') html = html[:sloc] + utf8(js) + b'\n' + html[sloc:] if js_embed: js = b'<script type="text/javascript">\n//<![CDATA[\n' + \ b'\n'.join(js_embed) + b'\n//]]>\n</script>' sloc = html.rindex(b'</body>') html = html[:sloc] + js + b'\n' + html[sloc:] if css_files: paths = [] unique_paths = set() for path in css_files: if not is_absolute(path): path = self.static_url(path) if path not in unique_paths: paths.append(path) unique_paths.add(path) css = ''.join('<link href="' + escape.xhtml_escape(p) + '" ' 'type="text/css" rel="stylesheet"/>' for p in paths) hloc = html.index(b'</head>') html = html[:hloc] + utf8(css) + b'\n' + html[hloc:] if css_embed: css = b'<style type="text/css">\n' + b'\n'.join(css_embed) + \ b'\n</style>' hloc = html.index(b'</head>') html = html[:hloc] + css + b'\n' + html[hloc:] if html_heads: hloc = html.index(b'</head>') html = html[:hloc] + b''.join(html_heads) + b'\n' + html[hloc:] if html_bodies: hloc = html.index(b'</body>') html = html[:hloc] + b''.join(html_bodies) + b'\n' + html[hloc:] self.finish(html)
[docs] def render_string(self, template_name, **kwargs): """Generate the given template with the given arguments. We return the generated byte string (in utf8). To generate and write a template as a response, use render() above. """ # If no template_path is specified, use the path of the calling file template_path = self.get_template_path() if not template_path: frame = sys._getframe(0) web_file = frame.f_code.co_filename while frame.f_code.co_filename == web_file: frame = frame.f_back template_path = os.path.dirname(frame.f_code.co_filename) with RequestHandler._template_loader_lock: if template_path not in RequestHandler._template_loaders: loader = self.create_template_loader(template_path) RequestHandler._template_loaders[template_path] = loader else: loader = RequestHandler._template_loaders[template_path] t = loader.load(template_name) namespace = self.get_template_namespace() namespace.update(kwargs) return t.generate(**namespace)
[docs] def get_template_namespace(self): """Returns a dictionary to be used as the default template namespace. May be overridden by subclasses to add or modify values. The results of this method will be combined with additional defaults in the `tornado.template` module and keyword arguments to `render` or `render_string`. """ namespace = dict( handler=self, request=self.request, current_user=self.current_user, locale=self.locale, _=self.locale.translate, static_url=self.static_url, xsrf_form_html=self.xsrf_form_html, reverse_url=self.reverse_url ) namespace.update(self.ui) return namespace
[docs] def create_template_loader(self, template_path): """Returns a new template loader for the given path. May be overridden by subclasses. By default returns a directory-based loader on the given path, using the ``autoescape`` application setting. If a ``template_loader`` application setting is supplied, uses that instead. """ settings = self.application.settings if "template_loader" in settings: return settings["template_loader"] kwargs = {} if "autoescape" in settings: # autoescape=None means "no escaping", so we have to be sure # to only pass this kwarg if the user asked for it. kwargs["autoescape"] = settings["autoescape"] return template.Loader(template_path, **kwargs)
[docs] def flush(self, include_footers=False, callback=None): """Flushes the current output buffer to the network. The ``callback`` argument, if given, can be used for flow control: it will be run when all flushed data has been written to the socket. Note that only one flush callback can be outstanding at a time; if another flush occurs before the previous flush's callback has been run, the previous callback will be discarded. """ if self.application._wsgi: # WSGI applications cannot usefully support flush, so just make # it a no-op (and run the callback immediately). if callback is not None: callback() return chunk = b"".join(self._write_buffer) self._write_buffer = [] if not self._headers_written: self._headers_written = True for transform in self._transforms: self._status_code, self._headers, chunk = \ transform.transform_first_chunk( self._status_code, self._headers, chunk, include_footers) headers = self._generate_headers() else: for transform in self._transforms: chunk = transform.transform_chunk(chunk, include_footers) headers = b"" # Ignore the chunk and only write the headers for HEAD requests if self.request.method == "HEAD": if headers: self.request.write(headers, callback=callback) return self.request.write(headers + chunk, callback=callback)
[docs] def finish(self, chunk=None): """Finishes this response, ending the HTTP request.""" if self._finished: raise RuntimeError("finish() called twice. May be caused " "by using async operations without the " "@asynchronous decorator.") if chunk is not None: self.write(chunk) # Automatically support ETags and add the Content-Length header if # we have not flushed any content yet. if not self._headers_written: if (self._status_code == 200 and self.request.method in ("GET", "HEAD") and "Etag" not in self._headers): self.set_etag_header() if self.check_etag_header(): self._write_buffer = [] self.set_status(304) if self._status_code == 304: assert not self._write_buffer, "Cannot send body with 304" self._clear_headers_for_304() elif "Content-Length" not in self._headers: content_length = sum(len(part) for part in self._write_buffer) self.set_header("Content-Length", content_length) if hasattr(self.request, "connection"): # Now that the request is finished, clear the callback we # set on the HTTPConnection (which would otherwise prevent the # garbage collection of the RequestHandler when there # are keepalive connections) self.request.connection.set_close_callback(None) if not self.application._wsgi: self.flush(include_footers=True) self.request.finish() self._log() self._finished = True self.on_finish() # Break up a reference cycle between this handler and the # _ui_module closures to allow for faster GC on CPython. self.ui = None
[docs] def send_error(self, status_code=500, **kwargs): """Sends the given HTTP error code to the browser. If `flush()` has already been called, it is not possible to send an error, so this method will simply terminate the response. If output has been written but not yet flushed, it will be discarded and replaced with the error page. Override `write_error()` to customize the error page that is returned. Additional keyword arguments are passed through to `write_error`. """ if self._headers_written: gen_log.error("Cannot send error response after headers written") if not self._finished: self.finish() return self.clear() reason = None if 'exc_info' in kwargs: exception = kwargs['exc_info'][1] if isinstance(exception, HTTPError) and exception.reason: reason = exception.reason self.set_status(status_code, reason=reason) try: self.write_error(status_code, **kwargs) except Exception: app_log.error("Uncaught exception in write_error", exc_info=True) if not self._finished: self.finish()
[docs] def write_error(self, status_code, **kwargs): """Override to implement custom error pages. ``write_error`` may call `write`, `render`, `set_header`, etc to produce output as usual. If this error was caused by an uncaught exception (including HTTPError), an ``exc_info`` triple will be available as ``kwargs["exc_info"]``. Note that this exception may not be the "current" exception for purposes of methods like ``sys.exc_info()`` or ``traceback.format_exc``. For historical reasons, if a method ``get_error_html`` exists, it will be used instead of the default ``write_error`` implementation. ``get_error_html`` returned a string instead of producing output normally, and had different semantics for exception handling. Users of ``get_error_html`` are encouraged to convert their code to override ``write_error`` instead. """ if hasattr(self, 'get_error_html'): if 'exc_info' in kwargs: exc_info = kwargs.pop('exc_info') kwargs['exception'] = exc_info[1] try: # Put the traceback into sys.exc_info() raise_exc_info(exc_info) except Exception: self.finish(self.get_error_html(status_code, **kwargs)) else: self.finish(self.get_error_html(status_code, **kwargs)) return if self.settings.get("serve_traceback") and "exc_info" in kwargs: # in debug mode, try to send a traceback self.set_header('Content-Type', 'text/plain') for line in traceback.format_exception(*kwargs["exc_info"]): self.write(line) self.finish() else: self.finish("<html><title>%(code)d: %(message)s</title>" "<body>%(code)d: %(message)s</body></html>" % { "code": status_code, "message": self._reason, })
@property def locale(self): """The local for the current session. Determined by either `get_user_locale`, which you can override to set the locale based on, e.g., a user preference stored in a database, or `get_browser_locale`, which uses the ``Accept-Language`` header. """ if not hasattr(self, "_locale"): self._locale = self.get_user_locale() if not self._locale: self._locale = self.get_browser_locale() assert self._locale return self._locale
[docs] def get_user_locale(self): """Override to determine the locale from the authenticated user. If None is returned, we fall back to `get_browser_locale()`. This method should return a `tornado.locale.Locale` object, most likely obtained via a call like ``tornado.locale.get("en")`` """ return None
[docs] def get_browser_locale(self, default="en_US"): """Determines the user's locale from ``Accept-Language`` header. See http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.4 """ if "Accept-Language" in self.request.headers: languages = self.request.headers["Accept-Language"].split(",") locales = [] for language in languages: parts = language.strip().split(";") if len(parts) > 1 and parts[1].startswith("q="): try: score = float(parts[1][2:]) except (ValueError, TypeError): score = 0.0 else: score = 1.0 locales.append((parts[0], score)) if locales: locales.sort(key=lambda pair: pair[1], reverse=True) codes = [l[0] for l in locales] return locale.get(*codes) return locale.get(default)
@property def current_user(self): """The authenticated user for this request. This is a cached version of `get_current_user`, which you can override to set the user based on, e.g., a cookie. If that method is not overridden, this method always returns None. We lazy-load the current user the first time this method is called and cache the result after that. """ if not hasattr(self, "_current_user"): self._current_user = self.get_current_user() return self._current_user @current_user.setter def current_user(self, value): self._current_user = value
[docs] def get_current_user(self): """Override to determine the current user from, e.g., a cookie.""" return None
[docs] def get_login_url(self): """Override to customize the login URL based on the request. By default, we use the ``login_url`` application setting. """ self.require_setting("login_url", "@tornado.web.authenticated") return self.application.settings["login_url"]
[docs] def get_template_path(self): """Override to customize template path for each handler. By default, we use the ``template_path`` application setting. Return None to load templates relative to the calling file. """ return self.application.settings.get("template_path")
@property def xsrf_token(self): """The XSRF-prevention token for the current user/session. To prevent cross-site request forgery, we set an '_xsrf' cookie and include the same '_xsrf' value as an argument with all POST requests. If the two do not match, we reject the form submission as a potential forgery. See http://en.wikipedia.org/wiki/Cross-site_request_forgery """ if not hasattr(self, "_xsrf_token"): token = self.get_cookie("_xsrf") if not token: token = binascii.b2a_hex(uuid.uuid4().bytes) expires_days = 30 if self.current_user else None self.set_cookie("_xsrf", token, expires_days=expires_days) self._xsrf_token = token return self._xsrf_token
[docs] def xsrf_form_html(self): """An HTML ``<input/>`` element to be included with all POST forms. It defines the ``_xsrf`` input value, which we check on all POST requests to prevent cross-site request forgery. If you have set the ``xsrf_cookies`` application setting, you must include this HTML within all of your HTML forms. In a template, this method should be called with ``{% module xsrf_form_html() %}`` See `check_xsrf_cookie()` above for more information. """ return '<input type="hidden" name="_xsrf" value="' + \ escape.xhtml_escape(self.xsrf_token) + '"/>'
[docs] def static_url(self, path, include_host=None, **kwargs): """Returns a static URL for the given relative static file path. This method requires you set the ``static_path`` setting in your application (which specifies the root directory of your static files). This method returns a versioned url (by default appending ``?v=<signature>``), which allows the static files to be cached indefinitely. This can be disabled by passing ``include_version=False`` (in the default implementation; other static file implementations are not required to support this, but they may support other options). By default this method returns URLs relative to the current host, but if ``include_host`` is true the URL returned will be absolute. If this handler has an ``include_host`` attribute, that value will be used as the default for all `static_url` calls that do not pass ``include_host`` as a keyword argument. """ self.require_setting("static_path", "static_url") get_url = self.settings.get("static_handler_class", StaticFileHandler).make_static_url if include_host is None: include_host = getattr(self, "include_host", False) if include_host: base = self.request.protocol + "://" + self.request.host else: base = "" return base + get_url(self.settings, path, **kwargs)
[docs] def async_callback(self, callback, *args, **kwargs): """Obsolete - catches exceptions from the wrapped function. This function is unnecessary since Tornado 1.1. """ if callback is None: return None if args or kwargs: callback = functools.partial(callback, *args, **kwargs) def wrapper(*args, **kwargs): try: return callback(*args, **kwargs) except Exception as e: if self._headers_written: app_log.error("Exception after headers written", exc_info=True) else: self._handle_request_exception(e) return wrapper
[docs] def require_setting(self, name, feature="this feature"): """Raises an exception if the given app setting is not defined.""" if not self.application.settings.get(name): raise Exception("You must define the '%s' setting in your " "application to use %s" % (name, feature))
[docs] def reverse_url(self, name, *args): """Alias for `Application.reverse_url`.""" return self.application.reverse_url(name, *args)
[docs] def compute_etag(self): """Computes the etag header to be used for this request. By default uses a hash of the content written so far. May be overridden to provide custom etag implementations, or may return None to disable tornado's default etag support. """ hasher = hashlib.sha1() for part in self._write_buffer: hasher.update(part) return '"%s"' % hasher.hexdigest()
[docs] def set_etag_header(self): """Sets the response's Etag header using ``self.compute_etag()``. Note: no header will be set if ``compute_etag()`` returns ``None``. This method is called automatically when the request is finished. """ etag = self.compute_etag() if etag is not None: self.set_header("Etag", etag)
[docs] def check_etag_header(self): """Checks the ``Etag`` header against requests's ``If-None-Match``. Returns ``True`` if the request's Etag matches and a 304 should be returned. For example:: self.set_etag_header() if self.check_etag_header(): self.set_status(304) return This method is called automatically when the request is finished, but may be called earlier for applications that override `compute_etag` and want to do an early check for ``If-None-Match`` before completing the request. The ``Etag`` header should be set (perhaps with `set_etag_header`) before calling this method. """ etag = self._headers.get("Etag") inm = utf8(self.request.headers.get("If-None-Match", "")) return bool(etag and inm and inm.find(etag) >= 0)
def _stack_context_handle_exception(self, type, value, traceback): try: # For historical reasons _handle_request_exception only takes # the exception value instead of the full triple, # so re-raise the exception to ensure that it's in # sys.exc_info() raise_exc_info((type, value, traceback)) except Exception: self._handle_request_exception(value) return True def _execute(self, transforms, *args, **kwargs): """Executes this request with the given output transforms.""" self._transforms = transforms try: if self.request.method not in self.SUPPORTED_METHODS: raise HTTPError(405) self.path_args = [self.decode_argument(arg) for arg in args] self.path_kwargs = dict((k, self.decode_argument(v, name=k)) for (k, v) in kwargs.items()) # If XSRF cookies are turned on, reject form submissions without # the proper cookie if self.request.method not in ("GET", "HEAD", "OPTIONS") and \ self.application.settings.get("xsrf_cookies"): self.check_xsrf_cookie() self._when_complete(self.prepare(), self._execute_method) except Exception as e: self._handle_request_exception(e) def _when_complete(self, result, callback): try: if result is None: callback() elif isinstance(result, Future): if result.done(): if result.result() is not None: raise ValueError('Expected None, got %r' % result.result()) callback() else: # Delayed import of IOLoop because it's not available # on app engine from tornado.ioloop import IOLoop IOLoop.current().add_future( result, functools.partial(self._when_complete, callback=callback)) else: raise ValueError("Expected Future or None, got %r" % result) except Exception as e: self._handle_request_exception(e) def _execute_method(self): if not self._finished: method = getattr(self, self.request.method.lower()) self._when_complete(method(*self.path_args, **self.path_kwargs), self._execute_finish) def _execute_finish(self): if self._auto_finish and not self._finished: self.finish() def _generate_headers(self): reason = self._reason lines = [utf8(self.request.version + " " + str(self._status_code) + " " + reason)] lines.extend([utf8(n) + b": " + utf8(v) for n, v in self._headers.get_all()]) if hasattr(self, "_new_cookie"): for cookie in self._new_cookie.values(): lines.append(utf8("Set-Cookie: " + cookie.OutputString(None))) return b"\r\n".join(lines) + b"\r\n\r\n" def _log(self): """Logs the current request. Sort of deprecated since this functionality was moved to the Application, but left in place for the benefit of existing apps that have overridden this method. """ self.application.log_request(self) def _request_summary(self): return self.request.method + " " + self.request.uri + \ " (" + self.request.remote_ip + ")" def _handle_request_exception(self, e): self.log_exception(*sys.exc_info()) if self._finished: # Extra errors after the request has been finished should # be logged, but there is no reason to continue to try and # send a response. return if isinstance(e, HTTPError): if e.status_code not in httputil.responses and not e.reason: gen_log.error("Bad HTTP status code: %d", e.status_code) self.send_error(500, exc_info=sys.exc_info()) else: self.send_error(e.status_code, exc_info=sys.exc_info()) else: self.send_error(500, exc_info=sys.exc_info())
[docs] def log_exception(self, typ, value, tb): """Override to customize logging of uncaught exceptions. By default logs instances of `HTTPError` as warnings without stack traces (on the ``tornado.general`` logger), and all other exceptions as errors with stack traces (on the ``tornado.application`` logger). .. versionadded:: 3.1 """ if isinstance(value, HTTPError): if value.log_message: format = "%d %s: " + value.log_message args = ([value.status_code, self._request_summary()] + list(value.args)) gen_log.warning(format, *args) else: app_log.error("Uncaught exception %s\n%r", self._request_summary(), self.request, exc_info=(typ, value, tb))
def _ui_module(self, name, module): def render(*args, **kwargs): if not hasattr(self, "_active_modules"): self._active_modules = {} if name not in self._active_modules: self._active_modules[name] = module(self) rendered = self._active_modules[name].render(*args, **kwargs) return rendered return render def _ui_method(self, method): return lambda *args, **kwargs: method(self, *args, **kwargs) def _clear_headers_for_304(self): # 304 responses should not contain entity headers (defined in # http://www.w3.org/Protocols/rfc2616/rfc2616-sec7.html#sec7.1) # not explicitly allowed by # http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.5 headers = ["Allow", "Content-Encoding", "Content-Language", "Content-Length", "Content-MD5", "Content-Range", "Content-Type", "Last-Modified"] for h in headers: self.clear_header(h)
[docs]def asynchronous(method): """Wrap request handler methods with this if they are asynchronous. This decorator is unnecessary if the method is also decorated with ``@gen.coroutine`` (it is legal but unnecessary to use the two decorators together, in which case ``@asynchronous`` must be first). This decorator should only be applied to the :ref:`HTTP verb methods <verbs>`; its behavior is undefined for any other method. This decorator does not *make* a method asynchronous; it tells the framework that the method *is* asynchronous. For this decorator to be useful the method must (at least sometimes) do something asynchronous. If this decorator is given, the response is not finished when the method returns. It is up to the request handler to call `self.finish() <RequestHandler.finish>` to finish the HTTP request. Without this decorator, the request is automatically finished when the ``get()`` or ``post()`` method returns. Example:: class MyRequestHandler(web.RequestHandler): @web.asynchronous def get(self): http = httpclient.AsyncHTTPClient() http.fetch("http://friendfeed.com/", self._on_download) def _on_download(self, response): self.write("Downloaded!") self.finish() .. versionadded:: 3.1 The ability to use ``@gen.coroutine`` without ``@asynchronous``. """ # Delay the IOLoop import because it's not available on app engine. from tornado.ioloop import IOLoop @functools.wraps(method) def wrapper(self, *args, **kwargs): if self.application._wsgi: raise Exception("@asynchronous is not supported for WSGI apps") self._auto_finish = False with stack_context.ExceptionStackContext( self._stack_context_handle_exception): result = method(self, *args, **kwargs) if isinstance(result, Future): # If @asynchronous is used with @gen.coroutine, (but # not @gen.engine), we can automatically finish the # request when the future resolves. Additionally, # the Future will swallow any exceptions so we need # to throw them back out to the stack context to finish # the request. def future_complete(f): f.result() if not self._finished: self.finish() IOLoop.current().add_future(result, future_complete) # Once we have done this, hide the Future from our # caller (i.e. RequestHandler._when_complete), which # would otherwise set up its own callback and # exception handler (resulting in exceptions being # logged twice). return None return result return wrapper
[docs]def removeslash(method): """Use this decorator to remove trailing slashes from the request path. For example, a request to ``/foo/`` would redirect to ``/foo`` with this decorator. Your request handler mapping should use a regular expression like ``r'/foo/*'`` in conjunction with using the decorator. """ @functools.wraps(method) def wrapper(self, *args, **kwargs): if self.request.path.endswith("/"): if self.request.method in ("GET", "HEAD"): uri = self.request.path.rstrip("/") if uri: # don't try to redirect '/' to '' if self.request.query: uri += "?" + self.request.query self.redirect(uri, permanent=True) return else: raise HTTPError(404) return method(self, *args, **kwargs) return wrapper
[docs]def addslash(method): """Use this decorator to add a missing trailing slash to the request path. For example, a request to ``/foo`` would redirect to ``/foo/`` with this decorator. Your request handler mapping should use a regular expression like ``r'/foo/?'`` in conjunction with using the decorator. """ @functools.wraps(method) def wrapper(self, *args, **kwargs): if not self.request.path.endswith("/"): if self.request.method in ("GET", "HEAD"): uri = self.request.path + "/" if self.request.query: uri += "?" + self.request.query self.redirect(uri, permanent=True) return raise HTTPError(404) return method(self, *args, **kwargs) return wrapper
[docs]class Application(object): """A collection of request handlers that make up a web application. Instances of this class are callable and can be passed directly to HTTPServer to serve the application:: application = web.Application([ (r"/", MainPageHandler), ]) http_server = httpserver.HTTPServer(application) http_server.listen(8080) ioloop.IOLoop.instance().start() The constructor for this class takes in a list of `URLSpec` objects or (regexp, request_class) tuples. When we receive requests, we iterate over the list in order and instantiate an instance of the first request class whose regexp matches the request path. The request class can be specified as either a class object or a (fully-qualified) name. Each tuple can contain additional elements, which correspond to the arguments to the `URLSpec` constructor. (Prior to Tornado 3.2, this only tuples of two or three elements were allowed). A dictionary may be passed as the third element of the tuple, which will be used as keyword arguments to the handler's constructor and `~RequestHandler.initialize` method. This pattern is used for the `StaticFileHandler` in this example (note that a `StaticFileHandler` can be installed automatically with the static_path setting described below):: application = web.Application([ (r"/static/(.*)", web.StaticFileHandler, {"path": "/var/www"}), ]) We support virtual hosts with the `add_handlers` method, which takes in a host regular expression as the first argument:: application.add_handlers(r"www\.myhost\.com", [ (r"/article/([0-9]+)", ArticleHandler), ]) You can serve static files by sending the ``static_path`` setting as a keyword argument. We will serve those files from the ``/static/`` URI (this is configurable with the ``static_url_prefix`` setting), and we will serve ``/favicon.ico`` and ``/robots.txt`` from the same directory. A custom subclass of `StaticFileHandler` can be specified with the ``static_handler_class`` setting. """ def __init__(self, handlers=None, default_host="", transforms=None, wsgi=False, **settings): if transforms is None: self.transforms = [] if settings.get("gzip"): self.transforms.append(GZipContentEncoding) self.transforms.append(ChunkedTransferEncoding) else: self.transforms = transforms self.handlers = [] self.named_handlers = {} self.default_host = default_host self.settings = settings self.ui_modules = {'linkify': _linkify, 'xsrf_form_html': _xsrf_form_html, 'Template': TemplateModule, } self.ui_methods = {} self._wsgi = wsgi self._load_ui_modules(settings.get("ui_modules", {})) self._load_ui_methods(settings.get("ui_methods", {})) if self.settings.get("static_path"): path = self.settings["static_path"] handlers = list(handlers or []) static_url_prefix = settings.get("static_url_prefix", "/static/") static_handler_class = settings.get("static_handler_class", StaticFileHandler) static_handler_args = settings.get("static_handler_args", {}) static_handler_args['path'] = path for pattern in [re.escape(static_url_prefix) + r"(.*)", r"/(favicon\.ico)", r"/(robots\.txt)"]: handlers.insert(0, (pattern, static_handler_class, static_handler_args)) if handlers: self.add_handlers(".*$", handlers) if self.settings.get('debug'): self.settings.setdefault('autoreload', True) self.settings.setdefault('compiled_template_cache', False) self.settings.setdefault('static_hash_cache', False) self.settings.setdefault('serve_traceback', True) # Automatically reload modified modules if self.settings.get('autoreload') and not wsgi: from tornado import autoreload autoreload.start()
[docs] def listen(self, port, address="", **kwargs): """Starts an HTTP server for this application on the given port. This is a convenience alias for creating an `.HTTPServer` object and calling its listen method. Keyword arguments not supported by `HTTPServer.listen <.TCPServer.listen>` are passed to the `.HTTPServer` constructor. For advanced uses (e.g. multi-process mode), do not use this method; create an `.HTTPServer` and call its `.TCPServer.bind`/`.TCPServer.start` methods directly. Note that after calling this method you still need to call ``IOLoop.instance().start()`` to start the server. """ # import is here rather than top level because HTTPServer # is not importable on appengine from tornado.httpserver import HTTPServer server = HTTPServer(self, **kwargs) server.listen(port, address)
[docs] def add_handlers(self, host_pattern, host_handlers): """Appends the given handlers to our handler list. Host patterns are processed sequentially in the order they were added. All matching patterns will be considered. """ if not host_pattern.endswith("$"): host_pattern += "$" handlers = [] # The handlers with the wildcard host_pattern are a special # case - they're added in the constructor but should have lower # precedence than the more-precise handlers added later. # If a wildcard handler group exists, it should always be last # in the list, so insert new groups just before it. if self.handlers and self.handlers[-1][0].pattern == '.*$': self.handlers.insert(-1, (re.compile(host_pattern), handlers)) else: self.handlers.append((re.compile(host_pattern), handlers)) for spec in host_handlers: if isinstance(spec, (tuple, list)): assert len(spec) in (2, 3, 4) spec = URLSpec(*spec) handlers.append(spec) if spec.name: if spec.name in self.named_handlers: app_log.warning( "Multiple handlers named %s; replacing previous value", spec.name) self.named_handlers[spec.name] = spec
def add_transform(self, transform_class): self.transforms.append(transform_class) def _get_host_handlers(self, request): host = request.host.lower().split(':')[0] matches = [] for pattern, handlers in self.handlers: if pattern.match(host): matches.extend(handlers) # Look for default host if not behind load balancer (for debugging) if not matches and "X-Real-Ip" not in request.headers: for pattern, handlers in self.handlers: if pattern.match(self.default_host): matches.extend(handlers) return matches or None def _load_ui_methods(self, methods): if isinstance(methods, types.ModuleType): self._load_ui_methods(dict((n, getattr(methods, n)) for n in dir(methods))) elif isinstance(methods, list): for m in methods: self._load_ui_methods(m) else: for name, fn in methods.items(): if not name.startswith("_") and hasattr(fn, "__call__") \ and name[0].lower() == name[0]: self.ui_methods[name] = fn def _load_ui_modules(self, modules): if isinstance(modules, types.ModuleType): self._load_ui_modules(dict((n, getattr(modules, n)) for n in dir(modules))) elif isinstance(modules, list): for m in modules: self._load_ui_modules(m) else: assert isinstance(modules, dict) for name, cls in modules.items(): try: if issubclass(cls, UIModule): self.ui_modules[name] = cls except TypeError: pass def __call__(self, request): """Called by HTTPServer to execute the request.""" transforms = [t(request) for t in self.transforms] handler = None args = [] kwargs = {} handlers = self._get_host_handlers(request) if not handlers: handler = RedirectHandler( self, request, url="http://" + self.default_host + "/") else: for spec in handlers: match = spec.regex.match(request.path) if match: handler = spec.handler_class(self, request, **spec.kwargs) if spec.regex.groups: # None-safe wrapper around url_unescape to handle # unmatched optional groups correctly def unquote(s): if s is None: return s return escape.url_unescape(s, encoding=None, plus=False) # Pass matched groups to the handler. Since # match.groups() includes both named and unnamed groups, # we want to use either groups or groupdict but not both. # Note that args are passed as bytes so the handler can # decide what encoding to use. if spec.regex.groupindex: kwargs = dict( (str(k), unquote(v)) for (k, v) in match.groupdict().items()) else: args = [unquote(s) for s in match.groups()] break if not handler: if self.settings.get('default_handler_class'): handler_class = self.settings['default_handler_class'] handler_args = self.settings.get( 'default_handler_args', {}) else: handler_class = ErrorHandler handler_args = dict(status_code=404) handler = handler_class(self, request, **handler_args) # If template cache is disabled (usually in the debug mode), # re-compile templates and reload static files on every # request so you don't need to restart to see changes if not self.settings.get("compiled_template_cache", True): with RequestHandler._template_loader_lock: for loader in RequestHandler._template_loaders.values(): loader.reset() if not self.settings.get('static_hash_cache', True): StaticFileHandler.reset() handler._execute(transforms, *args, **kwargs) return handler
[docs] def reverse_url(self, name, *args): """Returns a URL path for handler named ``name`` The handler must be added to the application as a named `URLSpec`. Args will be substituted for capturing groups in the `URLSpec` regex. They will be converted to strings if necessary, encoded as utf8, and url-escaped. """ if name in self.named_handlers: return self.named_handlers[name].reverse(*args) raise KeyError("%s not found in named urls" % name)
[docs] def log_request(self, handler): """Writes a completed HTTP request to the logs. By default writes to the python root logger. To change this behavior either subclass Application and override this method, or pass a function in the application settings dictionary as ``log_function``. """ if "log_function" in self.settings: self.settings["log_function"](handler) return if handler.get_status() < 400: log_method = access_log.info elif handler.get_status() < 500: log_method = access_log.warning else: log_method = access_log.error request_time = 1000.0 * handler.request.request_time() log_method("%d %s %.2fms", handler.get_status(), handler._request_summary(), request_time)
[docs]class HTTPError(Exception): """An exception that will turn into an HTTP error response. Raising an `HTTPError` is a convenient alternative to calling `RequestHandler.send_error` since it automatically ends the current function. :arg int status_code: HTTP status code. Must be listed in `httplib.responses <http.client.responses>` unless the ``reason`` keyword argument is given. :arg string log_message: Message to be written to the log for this error (will not be shown to the user unless the `Application` is in debug mode). May contain ``%s``-style placeholders, which will be filled in with remaining positional parameters. :arg string reason: Keyword-only argument. The HTTP "reason" phrase to pass in the status line along with ``status_code``. Normally determined automatically from ``status_code``, but can be used to use a non-standard numeric code. """ def __init__(self, status_code, log_message=None, *args, **kwargs): self.status_code = status_code self.log_message = log_message self.args = args self.reason = kwargs.get('reason', None) def __str__(self): message = "HTTP %d: %s" % ( self.status_code, self.reason or httputil.responses.get(self.status_code, 'Unknown')) if self.log_message: return message + " (" + (self.log_message % self.args) + ")" else: return message
[docs]class MissingArgumentError(HTTPError): """Exception raised by `RequestHandler.get_argument`. This is a subclass of `HTTPError`, so if it is uncaught a 400 response code will be used instead of 500 (and a stack trace will not be logged). .. versionadded:: 3.1 """ def __init__(self, arg_name): super(MissingArgumentError, self).__init__( 400, 'Missing argument %s' % arg_name) self.arg_name = arg_name
[docs]class ErrorHandler(RequestHandler): """Generates an error response with ``status_code`` for all requests.""" def initialize(self, status_code): self.set_status(status_code) def prepare(self): raise HTTPError(self._status_code) def check_xsrf_cookie(self): # POSTs to an ErrorHandler don't actually have side effects, # so we don't need to check the xsrf token. This allows POSTs # to the wrong url to return a 404 instead of 403. pass
[docs]class RedirectHandler(RequestHandler): """Redirects the client to the given URL for all GET requests. You should provide the keyword argument ``url`` to the handler, e.g.:: application = web.Application([ (r"/oldpath", web.RedirectHandler, {"url": "/newpath"}), ]) """ def initialize(self, url, permanent=True): self._url = url self._permanent = permanent def get(self): self.redirect(self._url, permanent=self._permanent)
[docs]class StaticFileHandler(RequestHandler): """A simple handler that can serve static content from a directory. A `StaticFileHandler` is configured automatically if you pass the ``static_path`` keyword argument to `Application`. This handler can be customized with the ``static_url_prefix``, ``static_handler_class``, and ``static_handler_args`` settings. To map an additional path to this handler for a static data directory you would add a line to your application like:: application = web.Application([ (r"/content/(.*)", web.StaticFileHandler, {"path": "/var/www"}), ]) The handler constructor requires a ``path`` argument, which specifies the local root directory of the content to be served. Note that a capture group in the regex is required to parse the value for the ``path`` argument to the get() method (different than the constructor argument above); see `URLSpec` for details. To maximize the effectiveness of browser caching, this class supports versioned urls (by default using the argument ``?v=``). If a version is given, we instruct the browser to cache this file indefinitely. `make_static_url` (also available as `RequestHandler.static_url`) can be used to construct a versioned url. This handler is intended primarily for use in development and light-duty file serving; for heavy traffic it will be more efficient to use a dedicated static file server (such as nginx or Apache). We support the HTTP ``Accept-Ranges`` mechanism to return partial content (because some browsers require this functionality to be present to seek in HTML5 audio or video), but this handler should not be used with files that are too large to fit comfortably in memory. **Subclassing notes** This class is designed to be extensible by subclassing, but because of the way static urls are generated with class methods rather than instance methods, the inheritance patterns are somewhat unusual. Be sure to use the ``@classmethod`` decorator when overriding a class method. Instance methods may use the attributes ``self.path`` ``self.absolute_path``, and ``self.modified``. Subclasses should only override methods discussed in this section; overriding other methods is error-prone. Overriding ``StaticFileHandler.get`` is particularly problematic due to the tight coupling with ``compute_etag`` and other methods. To change the way static urls are generated (e.g. to match the behavior of another server or CDN), override `make_static_url`, `parse_url_path`, `get_cache_time`, and/or `get_version`. To replace all interaction with the filesystem (e.g. to serve static content from a database), override `get_content`, `get_content_size`, `get_modified_time`, `get_absolute_path`, and `validate_absolute_path`. .. versionchanged:: 3.1 Many of the methods for subclasses were added in Tornado 3.1. """ CACHE_MAX_AGE = 86400 * 365 * 10 # 10 years _static_hashes = {} _lock = threading.Lock() # protects _static_hashes def initialize(self, path, default_filename=None): self.root = path self.default_filename = default_filename @classmethod def reset(cls): with cls._lock: cls._static_hashes = {} def head(self, path): self.get(path, include_body=False) def get(self, path, include_body=True): # Set up our path instance variables. self.path = self.parse_url_path(path) del path # make sure we don't refer to path instead of self.path again absolute_path = self.get_absolute_path(self.root, self.path) self.absolute_path = self.validate_absolute_path( self.root, absolute_path) if self.absolute_path is None: return self.modified = self.get_modified_time() self.set_headers() if self.should_return_304(): self.set_status(304) return request_range = None range_header = self.request.headers.get("Range") if range_header: # As per RFC 2616 14.16, if an invalid Range header is specified, # the request will be treated as if the header didn't exist. request_range = httputil._parse_request_range(range_header) if request_range: start, end = request_range size = self.get_content_size() if (start is not None and start >= size) or end == 0: # As per RFC 2616 14.35.1, a range is not satisfiable only: if # the first requested byte is equal to or greater than the # content, or when a suffix with length 0 is specified self.set_status(416) # Range Not Satisfiable self.set_header("Content-Type", "text/plain") self.set_header("Content-Range", "bytes */%s" % (size, )) return if start is not None and start < 0: start += size if end is not None and end > size: # Clients sometimes blindly use a large range to limit their # download size; cap the endpoint at the actual file size. end = size # Note: only return HTTP 206 if less than the entire range has been # requested. Not only is this semantically correct, but Chrome # refuses to play audio if it gets an HTTP 206 in response to # ``Range: bytes=0-``. if size != (end or size) - (start or 0): self.set_status(206) # Partial Content self.set_header("Content-Range", httputil._get_content_range(start, end, size)) else: start = end = None content = self.get_content(self.absolute_path, start, end) if isinstance(content, bytes_type): content = [content] content_length = 0 for chunk in content: if include_body: self.write(chunk) else: content_length += len(chunk) if not include_body: assert self.request.method == "HEAD" self.set_header("Content-Length", content_length)
[docs] def compute_etag(self): """Sets the ``Etag`` header based on static url version. This allows efficient ``If-None-Match`` checks against cached versions, and sends the correct ``Etag`` for a partial response (i.e. the same ``Etag`` as the full file). .. versionadded:: 3.1 """ version_hash = self._get_cached_version(self.absolute_path) if not version_hash: return None return '"%s"' % (version_hash, )
[docs] def set_headers(self): """Sets the content and caching headers on the response. .. versionadded:: 3.1 """ self.set_header("Accept-Ranges", "bytes") self.set_etag_header() if self.modified is not None: self.set_header("Last-Modified", self.modified) content_type = self.get_content_type() if content_type: self.set_header("Content-Type", content_type) cache_time = self.get_cache_time(self.path, self.modified, content_type) if cache_time > 0: self.set_header("Expires", datetime.datetime.utcnow() + datetime.timedelta(seconds=cache_time)) self.set_header("Cache-Control", "max-age=" + str(cache_time)) self.set_extra_headers(self.path)
[docs] def should_return_304(self): """Returns True if the headers indicate that we should return 304. .. versionadded:: 3.1 """ if self.check_etag_header(): return True # Check the If-Modified-Since, and don't send the result if the # content has not been modified ims_value = self.request.headers.get("If-Modified-Since") if ims_value is not None: date_tuple = email.utils.parsedate(ims_value) if date_tuple is not None: if_since = datetime.datetime(*date_tuple[:6]) if if_since >= self.modified: return True return False
@classmethod
[docs] def get_absolute_path(cls, root, path): """Returns the absolute location of ``path`` relative to ``root``. ``root`` is the path configured for this `StaticFileHandler` (in most cases the ``static_path`` `Application` setting). This class method may be overridden in subclasses. By default it returns a filesystem path, but other strings may be used as long as they are unique and understood by the subclass's overridden `get_content`. .. versionadded:: 3.1 """ abspath = os.path.abspath(os.path.join(root, path)) return abspath
[docs] def validate_absolute_path(self, root, absolute_path): """Validate and return the absolute path. ``root`` is the configured path for the `StaticFileHandler`, and ``path`` is the result of `get_absolute_path` This is an instance method called during request processing, so it may raise `HTTPError` or use methods like `RequestHandler.redirect` (return None after redirecting to halt further processing). This is where 404 errors for missing files are generated. This method may modify the path before returning it, but note that any such modifications will not be understood by `make_static_url`. In instance methods, this method's result is available as ``self.absolute_path``. .. versionadded:: 3.1 """ root = os.path.abspath(root) # os.path.abspath strips a trailing / # it needs to be temporarily added back for requests to root/ if not (absolute_path + os.path.sep).startswith(root): raise HTTPError(403, "%s is not in root static directory", self.path) if (os.path.isdir(absolute_path) and self.default_filename is not None): # need to look at the request.path here for when path is empty # but there is some prefix to the path that was already # trimmed by the routing if not self.request.path.endswith("/"): self.redirect(self.request.path + "/", permanent=True) return absolute_path = os.path.join(absolute_path, self.default_filename) if not os.path.exists(absolute_path): raise HTTPError(404) if not os.path.isfile(absolute_path): raise HTTPError(403, "%s is not a file", self.path) return absolute_path
@classmethod
[docs] def get_content(cls, abspath, start=None, end=None): """Retrieve the content of the requested resource which is located at the given absolute path. This class method may be overridden by subclasses. Note that its signature is different from other overridable class methods (no ``settings`` argument); this is deliberate to ensure that ``abspath`` is able to stand on its own as a cache key. This method should either return a byte string or an iterator of byte strings. The latter is preferred for large files as it helps reduce memory fragmentation. .. versionadded:: 3.1 """ with open(abspath, "rb") as file: if start is not None: file.seek(start) if end is not None: remaining = end - (start or 0) else: remaining = None while True: chunk_size = 64 * 1024 if remaining is not None and remaining < chunk_size: chunk_size = remaining chunk = file.read(chunk_size) if chunk: if remaining is not None: remaining -= len(chunk) yield chunk else: if remaining is not None: assert remaining == 0 return
@classmethod
[docs] def get_content_version(cls, abspath): """Returns a version string for the resource at the given path. This class method may be overridden by subclasses. The default implementation is a hash of the file's contents. .. versionadded:: 3.1 """ data = cls.get_content(abspath) hasher = hashlib.md5() if isinstance(data, bytes_type): hasher.update(data) else: for chunk in data: hasher.update(chunk) return hasher.hexdigest()
def _stat(self): if not hasattr(self, '_stat_result'): self._stat_result = os.stat(self.absolute_path) return self._stat_result
[docs] def get_content_size(self): """Retrieve the total size of the resource at the given path. This method may be overridden by subclasses. It will only be called if a partial result is requested from `get_content` .. versionadded:: 3.1 """ stat_result = self._stat() return stat_result[stat.ST_SIZE]
[docs] def get_modified_time(self): """Returns the time that ``self.absolute_path`` was last modified. May be overridden in subclasses. Should return a `~datetime.datetime` object or None. .. versionadded:: 3.1 """ stat_result = self._stat() modified = datetime.datetime.utcfromtimestamp(stat_result[stat.ST_MTIME]) return modified
[docs] def get_content_type(self): """Returns the ``Content-Type`` header to be used for this request. .. versionadded:: 3.1 """ mime_type, encoding = mimetypes.guess_type(self.absolute_path) return mime_type
[docs] def set_extra_headers(self, path): """For subclass to add extra headers to the response""" pass
[docs] def get_cache_time(self, path, modified, mime_type): """Override to customize cache control behavior. Return a positive number of seconds to make the result cacheable for that amount of time or 0 to mark resource as cacheable for an unspecified amount of time (subject to browser heuristics). By default returns cache expiry of 10 years for resources requested with ``v`` argument. """ return self.CACHE_MAX_AGE if "v" in self.request.arguments else 0
@classmethod
[docs] def make_static_url(cls, settings, path, include_version=True): """Constructs a versioned url for the given path. This method may be overridden in subclasses (but note that it is a class method rather than an instance method). Subclasses are only required to implement the signature ``make_static_url(cls, settings, path)``; other keyword arguments may be passed through `~RequestHandler.static_url` but are not standard. ``settings`` is the `Application.settings` dictionary. ``path`` is the static path being requested. The url returned should be relative to the current host. ``include_version`` determines whether the generated URL should include the query string containing the version hash of the file corresponding to the given ``path``. """ url = settings.get('static_url_prefix', '/static/') + path if not include_version: return url version_hash = cls.get_version(settings, path) if not version_hash: return url return '%s?v=%s' % (url, version_hash)
[docs] def parse_url_path(self, url_path): """Converts a static URL path into a filesystem path. ``url_path`` is the path component of the URL with ``static_url_prefix`` removed. The return value should be filesystem path relative to ``static_path``. This is the inverse of `make_static_url`. """ if os.path.sep != "/": url_path = url_path.replace("/", os.path.sep) return url_path
@classmethod
[docs] def get_version(cls, settings, path): """Generate the version string to be used in static URLs. ``settings`` is the `Application.settings` dictionary and ``path`` is the relative location of the requested asset on the filesystem. The returned value should be a string, or ``None`` if no version could be determined. .. versionchanged:: 3.1 This method was previously recommended for subclasses to override; `get_content_version` is now preferred as it allows the base class to handle caching of the result. """ abs_path = cls.get_absolute_path(settings['static_path'], path) return cls._get_cached_version(abs_path)
@classmethod def _get_cached_version(cls, abs_path): with cls._lock: hashes = cls._static_hashes if abs_path not in hashes: try: hashes[abs_path] = cls.get_content_version(abs_path) except Exception: gen_log.error("Could not open static file %r", abs_path) hashes[abs_path] = None hsh = hashes.get(abs_path) if hsh: return hsh return None
[docs]class FallbackHandler(RequestHandler): """A `RequestHandler` that wraps another HTTP server callback. The fallback is a callable object that accepts an `~.httpserver.HTTPRequest`, such as an `Application` or `tornado.wsgi.WSGIContainer`. This is most useful to use both Tornado ``RequestHandlers`` and WSGI in the same server. Typical usage:: wsgi_app = tornado.wsgi.WSGIContainer( django.core.handlers.wsgi.WSGIHandler()) application = tornado.web.Application([ (r"/foo", FooHandler), (r".*", FallbackHandler, dict(fallback=wsgi_app), ]) """ def initialize(self, fallback): self.fallback = fallback def prepare(self): self.fallback(self.request) self._finished = True
class OutputTransform(object): """A transform modifies the result of an HTTP request (e.g., GZip encoding) A new transform instance is created for every request. See the ChunkedTransferEncoding example below if you want to implement a new Transform. """ def __init__(self, request): pass def transform_first_chunk(self, status_code, headers, chunk, finishing): return status_code, headers, chunk def transform_chunk(self, chunk, finishing): return chunk class GZipContentEncoding(OutputTransform): """Applies the gzip content encoding to the response. See http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.11 """ # Whitelist of compressible mime types (in addition to any types # beginning with "text/"). CONTENT_TYPES = set(["application/javascript", "application/x-javascript", "application/xml", "application/atom+xml", "application/json", "application/xhtml+xml"]) MIN_LENGTH = 5 def __init__(self, request): self._gzipping = request.supports_http_1_1() and \ "gzip" in request.headers.get("Accept-Encoding", "") def _compressible_type(self, ctype): return ctype.startswith('text/') or ctype in self.CONTENT_TYPES def transform_first_chunk(self, status_code, headers, chunk, finishing): if 'Vary' in headers: headers['Vary'] += b', Accept-Encoding' else: headers['Vary'] = b'Accept-Encoding' if self._gzipping: ctype = _unicode(headers.get("Content-Type", "")).split(";")[0] self._gzipping = self._compressible_type(ctype) and \ (not finishing or len(chunk) >= self.MIN_LENGTH) and \ (finishing or "Content-Length" not in headers) and \ ("Content-Encoding" not in headers) if self._gzipping: headers["Content-Encoding"] = "gzip" self._gzip_value = BytesIO() self._gzip_file = gzip.GzipFile(mode="w", fileobj=self._gzip_value) chunk = self.transform_chunk(chunk, finishing) if "Content-Length" in headers: headers["Content-Length"] = str(len(chunk)) return status_code, headers, chunk def transform_chunk(self, chunk, finishing): if self._gzipping: self._gzip_file.write(chunk) if finishing: self._gzip_file.close() else: self._gzip_file.flush() chunk = self._gzip_value.getvalue() self._gzip_value.truncate(0) self._gzip_value.seek(0) return chunk class ChunkedTransferEncoding(OutputTransform): """Applies the chunked transfer encoding to the response. See http://www.w3.org/Protocols/rfc2616/rfc2616-sec3.html#sec3.6.1 """ def __init__(self, request): self._chunking = request.supports_http_1_1() def transform_first_chunk(self, status_code, headers, chunk, finishing): # 304 responses have no body (not even a zero-length body), and so # should not have either Content-Length or Transfer-Encoding headers. if self._chunking and status_code != 304: # No need to chunk the output if a Content-Length is specified if "Content-Length" in headers or "Transfer-Encoding" in headers: self._chunking = False else: headers["Transfer-Encoding"] = "chunked" chunk = self.transform_chunk(chunk, finishing) return status_code, headers, chunk def transform_chunk(self, block, finishing): if self._chunking: # Don't write out empty chunks because that means END-OF-STREAM # with chunked encoding if block: block = utf8("%x" % len(block)) + b"\r\n" + block + b"\r\n" if finishing: block += b"0\r\n\r\n" return block
[docs]def authenticated(method): """Decorate methods with this to require that the user be logged in. If the user is not logged in, they will be redirected to the configured `login url <RequestHandler.get_login_url>`. """ @functools.wraps(method) def wrapper(self, *args, **kwargs): if not self.current_user: if self.request.method in ("GET", "HEAD"): url = self.get_login_url() if "?" not in url: if urlparse.urlsplit(url).scheme: # if login url is absolute, make next absolute too next_url = self.request.full_url() else: next_url = self.request.uri url += "?" + urlencode(dict(next=next_url)) self.redirect(url) return raise HTTPError(403) return method(self, *args, **kwargs) return wrapper
[docs]class UIModule(object): """A re-usable, modular UI unit on a page. UI modules often execute additional queries, and they can include additional CSS and JavaScript that will be included in the output page, which is automatically inserted on page render. """ def __init__(self, handler): self.handler = handler self.request = handler.request self.ui = handler.ui self.locale = handler.locale @property def current_user(self): return self.handler.current_user
[docs] def render(self, *args, **kwargs): """Overridden in subclasses to return this module's output.""" raise NotImplementedError()
[docs] def embedded_javascript(self): """Returns a JavaScript string that will be embedded in the page.""" return None
[docs] def javascript_files(self): """Returns a list of JavaScript files required by this module.""" return None
[docs] def embedded_css(self): """Returns a CSS string that will be embedded in the page.""" return None
[docs] def css_files(self): """Returns a list of CSS files required by this module.""" return None
[docs] def html_head(self): """Returns a CSS string that will be put in the <head/> element""" return None
[docs] def html_body(self): """Returns an HTML string that will be put in the <body/> element""" return None
[docs] def render_string(self, path, **kwargs): """Renders a template and returns it as a string.""" return self.handler.render_string(path, **kwargs)
class _linkify(UIModule): def render(self, text, **kwargs): return escape.linkify(text, **kwargs) class _xsrf_form_html(UIModule): def render(self): return self.handler.xsrf_form_html() class TemplateModule(UIModule): """UIModule that simply renders the given template. {% module Template("foo.html") %} is similar to {% include "foo.html" %}, but the module version gets its own namespace (with kwargs passed to Template()) instead of inheriting the outer template's namespace. Templates rendered through this module also get access to UIModule's automatic javascript/css features. Simply call set_resources inside the template and give it keyword arguments corresponding to the methods on UIModule: {{ set_resources(js_files=static_url("my.js")) }} Note that these resources are output once per template file, not once per instantiation of the template, so they must not depend on any arguments to the template. """ def __init__(self, handler): super(TemplateModule, self).__init__(handler) # keep resources in both a list and a dict to preserve order self._resource_list = [] self._resource_dict = {} def render(self, path, **kwargs): def set_resources(**kwargs): if path not in self._resource_dict: self._resource_list.append(kwargs) self._resource_dict[path] = kwargs else: if self._resource_dict[path] != kwargs: raise ValueError("set_resources called with different " "resources for the same template") return "" return self.render_string(path, set_resources=set_resources, **kwargs) def _get_resources(self, key): return (r[key] for r in self._resource_list if key in r) def embedded_javascript(self): return "\n".join(self._get_resources("embedded_javascript")) def javascript_files(self): result = [] for f in self._get_resources("javascript_files"): if isinstance(f, (unicode_type, bytes_type)): result.append(f) else: result.extend(f) return result def embedded_css(self): return "\n".join(self._get_resources("embedded_css")) def css_files(self): result = [] for f in self._get_resources("css_files"): if isinstance(f, (unicode_type, bytes_type)): result.append(f) else: result.extend(f) return result def html_head(self): return "".join(self._get_resources("html_head")) def html_body(self): return "".join(self._get_resources("html_body")) class _UIModuleNamespace(object): """Lazy namespace which creates UIModule proxies bound to a handler.""" def __init__(self, handler, ui_modules): self.handler = handler self.ui_modules = ui_modules def __getitem__(self, key): return self.handler._ui_module(key, self.ui_modules[key]) def __getattr__(self, key): try: return self[key] except KeyError as e: raise AttributeError(str(e))
[docs]class URLSpec(object): """Specifies mappings between URLs and handlers.""" def __init__(self, pattern, handler, kwargs=None, name=None): """Parameters: * ``pattern``: Regular expression to be matched. Any groups in the regex will be passed in to the handler's get/post/etc methods as arguments. * ``handler_class``: `RequestHandler` subclass to be invoked. * ``kwargs`` (optional): A dictionary of additional arguments to be passed to the handler's constructor. * ``name`` (optional): A name for this handler. Used by `Application.reverse_url`. """ if not pattern.endswith('$'): pattern += '$' self.regex = re.compile(pattern) assert len(self.regex.groupindex) in (0, self.regex.groups), \ ("groups in url regexes must either be all named or all " "positional: %r" % self.regex.pattern) if isinstance(handler, str): # import the Module and instantiate the class # Must be a fully qualified name (module.ClassName) handler = import_object(handler) self.handler_class = handler self.kwargs = kwargs or {} self.name = name self._path, self._group_count = self._find_groups() def __repr__(self): return '%s(%r, %s, kwargs=%r, name=%r)' % \ (self.__class__.__name__, self.regex.pattern, self.handler_class, self.kwargs, self.name) def _find_groups(self): """Returns a tuple (reverse string, group count) for a url. For example: Given the url pattern /([0-9]{4})/([a-z-]+)/, this method would return ('/%s/%s/', 2). """ pattern = self.regex.pattern if pattern.startswith('^'): pattern = pattern[1:] if pattern.endswith('$'): pattern = pattern[:-1] if self.regex.groups != pattern.count('('): # The pattern is too complicated for our simplistic matching, # so we can't support reversing it. return (None, None) pieces = [] for fragment in pattern.split('('): if ')' in fragment: paren_loc = fragment.index(')') if paren_loc >= 0: pieces.append('%s' + fragment[paren_loc + 1:]) else: pieces.append(fragment) return (''.join(pieces), self.regex.groups) def reverse(self, *args): assert self._path is not None, \ "Cannot reverse url regex " + self.regex.pattern assert len(args) == self._group_count, "required number of arguments "\ "not found" if not len(args): return self._path converted_args = [] for a in args: if not isinstance(a, (unicode_type, bytes_type)): a = str(a) converted_args.append(escape.url_escape(utf8(a), plus=False)) return self._path % tuple(converted_args)
url = URLSpec if hasattr(hmac, 'compare_digest'): # python 3.3 _time_independent_equals = hmac.compare_digest else: def _time_independent_equals(a, b): if len(a) != len(b): return False result = 0 if isinstance(a[0], int): # python3 byte strings for x, y in zip(a, b): result |= x ^ y else: # python2 for x, y in zip(a, b): result |= ord(x) ^ ord(y) return result == 0 def create_signed_value(secret, name, value): timestamp = utf8(str(int(time.time()))) value = base64.b64encode(utf8(value)) signature = _create_signature(secret, name, value, timestamp) value = b"|".join([value, timestamp, signature]) return value def decode_signed_value(secret, name, value, max_age_days=31): if not value: return None parts = utf8(value).split(b"|") if len(parts) != 3: return None signature = _create_signature(secret, name, parts[0], parts[1]) if not _time_independent_equals(parts[2], signature): gen_log.warning("Invalid cookie signature %r", value) return None timestamp = int(parts[1]) if timestamp < time.time() - max_age_days * 86400: gen_log.warning("Expired cookie %r", value) return None if timestamp > time.time() + 31 * 86400: # _cookie_signature does not hash a delimiter between the # parts of the cookie, so an attacker could transfer trailing # digits from the payload to the timestamp without altering the # signature. For backwards compatibility, sanity-check timestamp # here instead of modifying _cookie_signature. gen_log.warning("Cookie timestamp in future; possible tampering %r", value) return None if parts[1].startswith(b"0"): gen_log.warning("Tampered cookie %r", value) return None try: return base64.b64decode(parts[0]) except Exception: return None def _create_signature(secret, *parts): hash = hmac.new(utf8(secret), digestmod=hashlib.sha1) for part in parts: hash.update(utf8(part)) return utf8(hash.hexdigest())