File: handlers.py

package info (click to toggle)
jupyter-notebook 4.2.3-4~bpo8%2B1
  • links: PTS, VCS
  • area: main
  • in suites: jessie-backports
  • size: 7,804 kB
  • sloc: python: 8,698; makefile: 240; sh: 74
file content (615 lines) | stat: -rw-r--r-- 20,750 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
"""Base Tornado handlers for the notebook server."""

# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.

import functools
import json
import os
import re
import sys
import traceback
try:
    # py3
    from http.client import responses
except ImportError:
    from httplib import responses
try:
    from urllib.parse import urlparse # Py 3
except ImportError:
    from urlparse import urlparse # Py 2

from jinja2 import TemplateNotFound
from tornado import web

from tornado import gen, escape
from tornado.log import app_log

from notebook._sysinfo import get_sys_info

from traitlets.config import Application
from ipython_genutils.path import filefind
from ipython_genutils.py3compat import string_types

import notebook
from notebook.utils import is_hidden, url_path_join, url_is_absolute, url_escape
from notebook.services.security import csp_report_uri

#-----------------------------------------------------------------------------
# Top-level handlers
#-----------------------------------------------------------------------------
non_alphanum = re.compile(r'[^A-Za-z0-9]')

sys_info = json.dumps(get_sys_info())

class AuthenticatedHandler(web.RequestHandler):
    """A RequestHandler with an authenticated user."""
    
    @property
    def content_security_policy(self):
        """The default Content-Security-Policy header
        
        Can be overridden by defining Content-Security-Policy in settings['headers']
        """
        return '; '.join([
            "frame-ancestors 'self'",
            # Make sure the report-uri is relative to the base_url
            "report-uri " + url_path_join(self.base_url, csp_report_uri),
        ])

    def set_default_headers(self):
        headers = self.settings.get('headers', {})

        if "Content-Security-Policy" not in headers:
            headers["Content-Security-Policy"] = self.content_security_policy

        # Allow for overriding headers
        for header_name,value in headers.items() :
            try:
                self.set_header(header_name, value)
            except Exception as e:
                # tornado raise Exception (not a subclass)
                # if method is unsupported (websocket and Access-Control-Allow-Origin
                # for example, so just ignore)
                self.log.debug(e)
    
    def clear_login_cookie(self):
        self.clear_cookie(self.cookie_name)
    
    def get_current_user(self):
        if self.login_handler is None:
            return 'anonymous'
        return self.login_handler.get_user(self)

    @property
    def cookie_name(self):
        default_cookie_name = non_alphanum.sub('-', 'username-{}'.format(
            self.request.host
        ))
        return self.settings.get('cookie_name', default_cookie_name)
    
    @property
    def logged_in(self):
        """Is a user currently logged in?"""
        user = self.get_current_user()
        return (user and not user == 'anonymous')

    @property
    def login_handler(self):
        """Return the login handler for this application, if any."""
        return self.settings.get('login_handler_class', None)

    @property
    def login_available(self):
        """May a user proceed to log in?

        This returns True if login capability is available, irrespective of
        whether the user is already logged in or not.

        """
        if self.login_handler is None:
            return False
        return bool(self.login_handler.login_available(self.settings))


class IPythonHandler(AuthenticatedHandler):
    """IPython-specific extensions to authenticated handling
    
    Mostly property shortcuts to IPython-specific settings.
    """


    @property
    def ignore_minified_js(self):
        """Wether to user bundle in template. (*.min files)
        
        Mainly use for development and avoid file recompilation
        """
        return self.settings.get('ignore_minified_js', False)

    @property
    def config(self):
        return self.settings.get('config', None)
    
    @property
    def log(self):
        """use the IPython log by default, falling back on tornado's logger"""
        if Application.initialized():
            return Application.instance().log
        else:
            return app_log

    @property
    def jinja_template_vars(self):
        """User-supplied values to supply to jinja templates."""
        return self.settings.get('jinja_template_vars', {})
    
    #---------------------------------------------------------------
    # URLs
    #---------------------------------------------------------------
    
    @property
    def version_hash(self):
        """The version hash to use for cache hints for static files"""
        return self.settings.get('version_hash', '')
    
    @property
    def mathjax_url(self):
        url = self.settings.get('mathjax_url', '')
        if not url or url_is_absolute(url):
            return url
        return url_path_join(self.base_url, url)
    
    @property
    def base_url(self):
        return self.settings.get('base_url', '/')

    @property
    def default_url(self):
        return self.settings.get('default_url', '')

    @property
    def ws_url(self):
        return self.settings.get('websocket_url', '')

    @property
    def contents_js_source(self):
        self.log.debug("Using contents: %s", self.settings.get('contents_js_source',
            'services/contents'))
        return self.settings.get('contents_js_source', 'services/contents')
    
    #---------------------------------------------------------------
    # Manager objects
    #---------------------------------------------------------------
    
    @property
    def kernel_manager(self):
        return self.settings['kernel_manager']

    @property
    def contents_manager(self):
        return self.settings['contents_manager']
    
    @property
    def session_manager(self):
        return self.settings['session_manager']
    
    @property
    def terminal_manager(self):
        return self.settings['terminal_manager']
    
    @property
    def kernel_spec_manager(self):
        return self.settings['kernel_spec_manager']

    @property
    def config_manager(self):
        return self.settings['config_manager']

    #---------------------------------------------------------------
    # CORS
    #---------------------------------------------------------------
    
    @property
    def allow_origin(self):
        """Normal Access-Control-Allow-Origin"""
        return self.settings.get('allow_origin', '')
    
    @property
    def allow_origin_pat(self):
        """Regular expression version of allow_origin"""
        return self.settings.get('allow_origin_pat', None)
    
    @property
    def allow_credentials(self):
        """Whether to set Access-Control-Allow-Credentials"""
        return self.settings.get('allow_credentials', False)
    
    def set_default_headers(self):
        """Add CORS headers, if defined"""
        super(IPythonHandler, self).set_default_headers()
        if self.allow_origin:
            self.set_header("Access-Control-Allow-Origin", self.allow_origin)
        elif self.allow_origin_pat:
            origin = self.get_origin()
            if origin and self.allow_origin_pat.match(origin):
                self.set_header("Access-Control-Allow-Origin", origin)
        if self.allow_credentials:
            self.set_header("Access-Control-Allow-Credentials", 'true')
    
    def get_origin(self):
        # Handle WebSocket Origin naming convention differences
        # The difference between version 8 and 13 is that in 8 the
        # client sends a "Sec-Websocket-Origin" header and in 13 it's
        # simply "Origin".
        if "Origin" in self.request.headers:
            origin = self.request.headers.get("Origin")
        else:
            origin = self.request.headers.get("Sec-Websocket-Origin", None)
        return origin

    # origin_to_satisfy_tornado is present because tornado requires
    # check_origin to take an origin argument, but we don't use it
    def check_origin(self, origin_to_satisfy_tornado=""):
        """Check Origin for cross-site API requests, including websockets

        Copied from WebSocket with changes:

        - allow unspecified host/origin (e.g. scripts)
        """
        if self.allow_origin == '*':
            return True

        host = self.request.headers.get("Host")
        origin = self.request.headers.get("Origin")

        # If no header is provided, assume it comes from a script/curl.
        # We are only concerned with cross-site browser stuff here.
        if origin is None or host is None:
            return True

        origin = origin.lower()
        origin_host = urlparse(origin).netloc

        # OK if origin matches host
        if origin_host == host:
            return True

        # Check CORS headers
        if self.allow_origin:
            allow = self.allow_origin == origin
        elif self.allow_origin_pat:
            allow = bool(self.allow_origin_pat.match(origin))
        else:
            # No CORS headers deny the request
            allow = False
        if not allow:
            self.log.warn("Blocking Cross Origin API request.  Origin: %s, Host: %s",
                origin, host,
            )
        return allow
    
    #---------------------------------------------------------------
    # template rendering
    #---------------------------------------------------------------
    
    def get_template(self, name):
        """Return the jinja template object for a given name"""
        return self.settings['jinja2_env'].get_template(name)
    
    def render_template(self, name, **ns):
        ns.update(self.template_namespace)
        template = self.get_template(name)
        return template.render(**ns)
    
    @property
    def template_namespace(self):
        return dict(
            base_url=self.base_url,
            default_url=self.default_url,
            ws_url=self.ws_url,
            logged_in=self.logged_in,
            login_available=self.login_available,
            static_url=self.static_url,
            sys_info=sys_info,
            contents_js_source=self.contents_js_source,
            version_hash=self.version_hash,
            ignore_minified_js=self.ignore_minified_js,
            **self.jinja_template_vars
        )
    
    def get_json_body(self):
        """Return the body of the request as JSON data."""
        if not self.request.body:
            return None
        # Do we need to call body.decode('utf-8') here?
        body = self.request.body.strip().decode(u'utf-8')
        try:
            model = json.loads(body)
        except Exception:
            self.log.debug("Bad JSON: %r", body)
            self.log.error("Couldn't parse JSON", exc_info=True)
            raise web.HTTPError(400, u'Invalid JSON in body of request')
        return model

    def write_error(self, status_code, **kwargs):
        """render custom error pages"""
        exc_info = kwargs.get('exc_info')
        message = ''
        status_message = responses.get(status_code, 'Unknown HTTP Error')
        if exc_info:
            exception = exc_info[1]
            # get the custom message, if defined
            try:
                message = exception.log_message % exception.args
            except Exception:
                pass
            
            # construct the custom reason, if defined
            reason = getattr(exception, 'reason', '')
            if reason:
                status_message = reason
        
        # build template namespace
        ns = dict(
            status_code=status_code,
            status_message=status_message,
            message=message,
            exception=exception,
        )
        
        self.set_header('Content-Type', 'text/html')
        # render the template
        try:
            html = self.render_template('%s.html' % status_code, **ns)
        except TemplateNotFound:
            self.log.debug("No template for %d", status_code)
            html = self.render_template('error.html', **ns)
        
        self.write(html)


class APIHandler(IPythonHandler):
    """Base class for API handlers"""

    def prepare(self):
        if not self.check_origin():
            raise web.HTTPError(404)
        return super(APIHandler, self).prepare()

    @property
    def content_security_policy(self):
        csp = '; '.join([
                super(APIHandler, self).content_security_policy,
                "default-src 'none'",
            ])
        return csp
    
    def finish(self, *args, **kwargs):
        self.set_header('Content-Type', 'application/json')
        return super(APIHandler, self).finish(*args, **kwargs)

    def options(self, *args, **kwargs):
        self.set_header('Access-Control-Allow-Headers', 'accept, content-type')
        self.set_header('Access-Control-Allow-Methods',
                        'GET, PUT, POST, PATCH, DELETE, OPTIONS')
        self.finish()


class Template404(IPythonHandler):
    """Render our 404 template"""
    def prepare(self):
        raise web.HTTPError(404)


class AuthenticatedFileHandler(IPythonHandler, web.StaticFileHandler):
    """static files should only be accessible when logged in"""

    @web.authenticated
    def get(self, path):
        if os.path.splitext(path)[1] == '.ipynb':
            name = path.rsplit('/', 1)[-1]
            self.set_header('Content-Type', 'application/json')
            self.set_header('Content-Disposition','attachment; filename="%s"' % escape.url_escape(name))
        
        return web.StaticFileHandler.get(self, path)
    
    def set_headers(self):
        super(AuthenticatedFileHandler, self).set_headers()
        # disable browser caching, rely on 304 replies for savings
        if "v" not in self.request.arguments:
            self.add_header("Cache-Control", "no-cache")
    
    def compute_etag(self):
        return None
    
    def validate_absolute_path(self, root, absolute_path):
        """Validate and return the absolute path.
        
        Requires tornado 3.1
        
        Adding to tornado's own handling, forbids the serving of hidden files.
        """
        abs_path = super(AuthenticatedFileHandler, self).validate_absolute_path(root, absolute_path)
        abs_root = os.path.abspath(root)
        if is_hidden(abs_path, abs_root):
            self.log.info("Refusing to serve hidden file, via 404 Error")
            raise web.HTTPError(404)
        return abs_path


def json_errors(method):
    """Decorate methods with this to return GitHub style JSON errors.
    
    This should be used on any JSON API on any handler method that can raise HTTPErrors.
    
    This will grab the latest HTTPError exception using sys.exc_info
    and then:
    
    1. Set the HTTP status code based on the HTTPError
    2. Create and return a JSON body with a message field describing
       the error in a human readable form.
    """
    @functools.wraps(method)
    @gen.coroutine
    def wrapper(self, *args, **kwargs):
        try:
            result = yield gen.maybe_future(method(self, *args, **kwargs))
        except web.HTTPError as e:
            self.set_header('Content-Type', 'application/json')
            status = e.status_code
            message = e.log_message
            self.log.warn(message)
            self.set_status(e.status_code)
            reply = dict(message=message, reason=e.reason)
            self.finish(json.dumps(reply))
        except Exception:
            self.set_header('Content-Type', 'application/json')
            self.log.error("Unhandled error in API request", exc_info=True)
            status = 500
            message = "Unknown server error"
            t, value, tb = sys.exc_info()
            self.set_status(status)
            tb_text = ''.join(traceback.format_exception(t, value, tb))
            reply = dict(message=message, reason=None, traceback=tb_text)
            self.finish(json.dumps(reply))
        else:
            # FIXME: can use regular return in generators in py3
            raise gen.Return(result)
    return wrapper



#-----------------------------------------------------------------------------
# File handler
#-----------------------------------------------------------------------------

# to minimize subclass changes:
HTTPError = web.HTTPError

class FileFindHandler(IPythonHandler, web.StaticFileHandler):
    """subclass of StaticFileHandler for serving files from a search path"""
    
    # cache search results, don't search for files more than once
    _static_paths = {}
    
    def set_headers(self):
        super(FileFindHandler, self).set_headers()
        # disable browser caching, rely on 304 replies for savings
        if "v" not in self.request.arguments or \
                any(self.request.path.startswith(path) for path in self.no_cache_paths):
            self.set_header("Cache-Control", "no-cache")
    
    def initialize(self, path, default_filename=None, no_cache_paths=None):
        self.no_cache_paths = no_cache_paths or []
        
        if isinstance(path, string_types):
            path = [path]
        
        self.root = tuple(
            os.path.abspath(os.path.expanduser(p)) + os.sep for p in path
        )
        self.default_filename = default_filename
    
    def compute_etag(self):
        return None
    
    @classmethod
    def get_absolute_path(cls, roots, path):
        """locate a file to serve on our static file search path"""
        with cls._lock:
            if path in cls._static_paths:
                return cls._static_paths[path]
            try:
                abspath = os.path.abspath(filefind(path, roots))
            except IOError:
                # IOError means not found
                return ''
            
            cls._static_paths[path] = abspath
            return abspath
    
    def validate_absolute_path(self, root, absolute_path):
        """check if the file should be served (raises 404, 403, etc.)"""
        if absolute_path == '':
            raise web.HTTPError(404)
        
        for root in self.root:
            if (absolute_path + os.sep).startswith(root):
                break
        
        return super(FileFindHandler, self).validate_absolute_path(root, absolute_path)


class APIVersionHandler(APIHandler):

    @json_errors
    def get(self):
        # not authenticated, so give as few info as possible
        self.finish(json.dumps({"version":notebook.__version__}))


class TrailingSlashHandler(web.RequestHandler):
    """Simple redirect handler that strips trailing slashes
    
    This should be the first, highest priority handler.
    """
    
    def get(self):
        self.redirect(self.request.uri.rstrip('/'))
    
    post = put = get


class FilesRedirectHandler(IPythonHandler):
    """Handler for redirecting relative URLs to the /files/ handler"""
    
    @staticmethod
    def redirect_to_files(self, path):
        """make redirect logic a reusable static method
        
        so it can be called from other handlers.
        """
        cm = self.contents_manager
        if cm.dir_exists(path):
            # it's a *directory*, redirect to /tree
            url = url_path_join(self.base_url, 'tree', url_escape(path))
        else:
            orig_path = path
            # otherwise, redirect to /files
            parts = path.split('/')

            if not cm.file_exists(path=path) and 'files' in parts:
                # redirect without files/ iff it would 404
                # this preserves pre-2.0-style 'files/' links
                self.log.warn("Deprecated files/ URL: %s", orig_path)
                parts.remove('files')
                path = '/'.join(parts)

            if not cm.file_exists(path=path):
                raise web.HTTPError(404)

            url = url_path_join(self.base_url, 'files', url_escape(path))
        self.log.debug("Redirecting %s to %s", self.request.path, url)
        self.redirect(url)
    
    def get(self, path=''):
        return self.redirect_to_files(self, path)


#-----------------------------------------------------------------------------
# URL pattern fragments for re-use
#-----------------------------------------------------------------------------

# path matches any number of `/foo[/bar...]` or just `/` or ''
path_regex = r"(?P<path>(?:(?:/[^/]+)+|/?))"

#-----------------------------------------------------------------------------
# URL to handler mappings
#-----------------------------------------------------------------------------


default_handlers = [
    (r".*/", TrailingSlashHandler),
    (r"api", APIVersionHandler)
]