summaryrefslogtreecommitdiffstats
path: root/Lib/urlparse.py
blob: 7a2e6ce746141c21b908a1209770a5e1c07b60af (plain)
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
"""Parse (absolute and relative) URLs.

See RFC 1808: "Relative Uniform Resource Locators", by R. Fielding,
UC Irvine, June 1995.
"""

__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
           "urlsplit", "urlunsplit"]

# A classification of schemes ('' means apply by default)
uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap',
                 'wais', 'file', 'https', 'shttp', 'mms',
                 'prospero', 'rtsp', 'rtspu', '', 'sftp']
uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet',
               'imap', 'wais', 'file', 'mms', 'https', 'shttp',
               'snews', 'prospero', 'rtsp', 'rtspu', 'rsync', '',
               'svn', 'svn+ssh', 'sftp']
non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',
                    'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']
uses_params = ['ftp', 'hdl', 'prospero', 'http', 'imap',
               'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips',
               'mms', '', 'sftp']
uses_query = ['http', 'wais', 'imap', 'https', 'shttp', 'mms',
              'gopher', 'rtsp', 'rtspu', 'sip', 'sips', '']
uses_fragment = ['ftp', 'hdl', 'http', 'gopher', 'news',
                 'nntp', 'wais', 'https', 'shttp', 'snews',
                 'file', 'prospero', '']

# Characters valid in scheme names
scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
                'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
                '0123456789'
                '+-.')

MAX_CACHE_SIZE = 20
_parse_cache = {}

def clear_cache():
    """Clear the parse cache."""
    global _parse_cache
    _parse_cache = {}


class BaseResult(tuple):
    """Base class for the parsed result objects.

    This provides the attributes shared by the two derived result
    objects as read-only properties.  The derived classes are
    responsible for checking the right number of arguments were
    supplied to the constructor.

    """

    __slots__ = ()

    # Attributes that access the basic components of the URL:

    @property
    def scheme(self):
        return self[0]

    @property
    def netloc(self):
        return self[1]

    @property
    def path(self):
        return self[2]

    @property
    def query(self):
        return self[-2]

    @property
    def fragment(self):
        return self[-1]

    # Additional attributes that provide access to parsed-out portions
    # of the netloc:

    @property
    def username(self):
        netloc = self.netloc
        if "@" in netloc:
            userinfo = netloc.rsplit("@", 1)[0]
            if ":" in userinfo:
                userinfo = userinfo.split(":", 1)[0]
            return userinfo
        return None

    @property
    def password(self):
        netloc = self.netloc
        if "@" in netloc:
            userinfo = netloc.rsplit("@", 1)[0]
            if ":" in userinfo:
                return userinfo.split(":", 1)[1]
        return None

    @property
    def hostname(self):
        netloc = self.netloc
        if "@" in netloc:
            netloc = netloc.rsplit("@", 1)[1]
        if ":" in netloc:
            netloc = netloc.split(":", 1)[0]
        return netloc.lower() or None

    @property
    def port(self):
        netloc = self.netloc
        if "@" in netloc:
            netloc = netloc.rsplit("@", 1)[1]
        if ":" in netloc:
            port = netloc.split(":", 1)[1]
            return int(port, 10)
        return None


class SplitResult(BaseResult):

    __slots__ = ()

    def __new__(cls, scheme, netloc, path, query, fragment):
        return BaseResult.__new__(
            cls, (scheme, netloc, path, query, fragment))

    def geturl(self):
        return urlunsplit(self)


class ParseResult(BaseResult):

    __slots__ = ()

    def __new__(cls, scheme, netloc, path, params, query, fragment):
        return BaseResult.__new__(
            cls, (scheme, netloc, path, params, query, fragment))

    @property
    def params(self):
        return self[3]

    def geturl(self):
        return urlunparse(self)


def urlparse(url, scheme='', allow_fragments=True):
    """Parse a URL into 6 components:
    <scheme>://<netloc>/<path>;<params>?<query>#<fragment>
    Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
    Note that we don't break the components up in smaller bits
    (e.g. netloc is a single string) and we don't expand % escapes."""
    tuple = urlsplit(url, scheme, allow_fragments)
    scheme, netloc, url, query, fragment = tuple
    if scheme in uses_params and ';' in url:
        url, params = _splitparams(url)
    else:
        params = ''
    return ParseResult(scheme, netloc, url, params, query, fragment)

def _splitparams(url):
    if '/'  in url:
        i = url.find(';', url.rfind('/'))
        if i < 0:
            return url, ''
    else:
        i = url.find(';')
    return url[:i], url[i+1:]

def _splitnetloc(url, start=0):
    delim = len(url)   # position of end of domain part of url, default is end
    for c in '/?#':    # look for delimiters; the order is NOT important
        wdelim = url.find(c, start)        # find first of this delim
        if wdelim >= 0:                    # if found
            delim = min(delim, wdelim)     # use earliest delim position
    return url[start:delim], url[delim:]   # return (domain, rest)

def urlsplit(url, scheme='', allow_fragments=True):
    """Parse a URL into 5 components:
    <scheme>://<netloc>/<path>?<query>#<fragment>
    Return a 5-tuple: (scheme, netloc, path, query, fragment).
    Note that we don't break the components up in smaller bits
    (e.g. netloc is a single string) and we don't expand % escapes."""
    allow_fragments = bool(allow_fragments)
    key = url, scheme, allow_fragments, type(url), type(scheme)
    cached = _parse_cache.get(key, None)
    if cached:
        return cached
    if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
        clear_cache()
    netloc = query = fragment = ''
    i = url.find(':')
    if i > 0:
        if url[:i] == 'http': # optimize the common case
            scheme = url[:i].lower()
            url = url[i+1:]
            if url[:2] == '//':
                netloc, url = _splitnetloc(url, 2)
            if allow_fragments and '#' in url:
                url, fragment = url.split('#', 1)
            if '?' in url:
                url, query = url.split('?', 1)
            v = SplitResult(scheme, netloc, url, query, fragment)
            _parse_cache[key] = v
            return v
        for c in url[:i]:
            if c not in scheme_chars:
                break
        else:
            scheme, url = url[:i].lower(), url[i+1:]
    if scheme in uses_netloc and url[:2] == '//':
        netloc, url = _splitnetloc(url, 2)
    if allow_fragments and scheme in uses_fragment and '#' in url:
        url, fragment = url.split('#', 1)
    if scheme in uses_query and '?' in url:
        url, query = url.split('?', 1)
    v = SplitResult(scheme, netloc, url, query, fragment)
    _parse_cache[key] = v
    return v

def urlunparse((scheme, netloc, url, params, query, fragment)):
    """Put a parsed URL back together again.  This may result in a
    slightly different, but equivalent URL, if the URL that was parsed
    originally had redundant delimiters, e.g. a ? with an empty query
    (the draft states that these are equivalent)."""
    if params:
        url = "%s;%s" % (url, params)
    return urlunsplit((scheme, netloc, url, query, fragment))

def urlunsplit((scheme, netloc, url, query, fragment)):
    if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
        if url and url[:1] != '/': url = '/' + url
        url = '//' + (netloc or '') + url
    if scheme:
        url = scheme + ':' + url
    if query:
        url = url + '?' + query
    if fragment:
        url = url + '#' + fragment
    return url

def urljoin(base, url, allow_fragments=True):
    """Join a base URL and a possibly relative URL to form an absolute
    interpretation of the latter."""
    if not base:
        return url
    if not url:
        return base
    bscheme, bnetloc, bpath, bparams, bquery, bfragment = \
            urlparse(base, '', allow_fragments)
    scheme, netloc, path, params, query, fragment = \
            urlparse(url, bscheme, allow_fragments)
    if scheme != bscheme or scheme not in uses_relative:
        return url
    if scheme in uses_netloc:
        if netloc:
            return urlunparse((scheme, netloc, path,
                               params, query, fragment))
        netloc = bnetloc
    if path[:1] == '/':
        return urlunparse((scheme, netloc, path,
                           params, query, fragment))
    if not (path or params or query):
        return urlunparse((scheme, netloc, bpath,
                           bparams, bquery, fragment))
    segments = bpath.split('/')[:-1] + path.split('/')
    # XXX The stuff below is bogus in various ways...
    if segments[-1] == '.':
        segments[-1] = ''
    while '.' in segments:
        segments.remove('.')
    while 1:
        i = 1
        n = len(segments) - 1
        while i < n:
            if (segments[i] == '..'
                and segments[i-1] not in ('', '..')):
                del segments[i-1:i+1]
                break
            i = i+1
        else:
            break
    if segments == ['', '..']:
        segments[-1] = ''
    elif len(segments) >= 2 and segments[-1] == '..':
        segments[-2:] = ['']
    return urlunparse((scheme, netloc, '/'.join(segments),
                       params, query, fragment))

def urldefrag(url):
    """Removes any existing fragment from URL.

    Returns a tuple of the defragmented URL and the fragment.  If
    the URL contained no fragments, the second element is the
    empty string.
    """
    if '#' in url:
        s, n, p, a, q, frag = urlparse(url)
        defrag = urlunparse((s, n, p, a, q, ''))
        return defrag, frag
    else:
        return url, ''


test_input = """
      http://a/b/c/d

      g:h        = <URL:g:h>
      http:g     = <URL:http://a/b/c/g>
      http:      = <URL:http://a/b/c/d>
      g          = <URL:http://a/b/c/g>
      ./g        = <URL:http://a/b/c/g>
      g/         = <URL:http://a/b/c/g/>
      /g         = <URL:http://a/g>
      //g        = <URL:http://g>
      ?y         = <URL:http://a/b/c/d?y>
      g?y        = <URL:http://a/b/c/g?y>
      g?y/./x    = <URL:http://a/b/c/g?y/./x>
      .          = <URL:http://a/b/c/>
      ./         = <URL:http://a/b/c/>
      ..         = <URL:http://a/b/>
      ../        = <URL:http://a/b/>
      ../g       = <URL:http://a/b/g>
      ../..      = <URL:http://a/>
      ../../g    = <URL:http://a/g>
      ../../../g = <URL:http://a/../g>
      ./../g     = <URL:http://a/b/g>
      ./g/.      = <URL:http://a/b/c/g/>
      /./g       = <URL:http://a/./g>
      g/./h      = <URL:http://a/b/c/g/h>
      g/../h     = <URL:http://a/b/c/h>
      http:g     = <URL:http://a/b/c/g>
      http:      = <URL:http://a/b/c/d>
      http:?y         = <URL:http://a/b/c/d?y>
      http:g?y        = <URL:http://a/b/c/g?y>
      http:g?y/./x    = <URL:http://a/b/c/g?y/./x>
"""

def test():
    import sys
    base = ''
    if sys.argv[1:]:
        fn = sys.argv[1]
        if fn == '-':
            fp = sys.stdin
        else:
            fp = open(fn)
    else:
        try:
            from cStringIO import StringIO
        except ImportError:
            from StringIO import StringIO
        fp = StringIO(test_input)
    while 1:
        line = fp.readline()
        if not line: break
        words = line.split()
        if not words:
            continue
        url = words[0]
        parts = urlparse(url)
        print '%-10s : %s' % (url, parts)
        abs = urljoin(base, url)
        if not base:
            base = abs
        wrapped = '<URL:%s>' % abs
        print '%-10s = %s' % (url, wrapped)
        if len(words) == 3 and words[1] == '=':
            if wrapped != words[2]:
                print 'EXPECTED', words[2], '!!!!!!!!!!'

if __name__ == '__main__':
    test()