Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/urllib3/util/url.py: 29%

1from __future__ import annotations

3import re

4import typing

6from ..exceptions import LocationParseError

7from .util import to_str

9# We only want to normalize urls with an HTTP(S) scheme.

10# urllib3 infers URLs without a scheme (None) to be http.

11_NORMALIZABLE_SCHEMES = ("http", "https", None)

13# Almost all of these patterns were derived from the

14# 'rfc3986' module: https://github.com/python-hyper/rfc3986

15_PERCENT_RE = re.compile(r"%[a-fA-F0-9]{2}")

16_SCHEME_RE = re.compile(r"^(?:[a-zA-Z][a-zA-Z0-9+-]*:|/)")

17_URI_RE = re.compile(

18 r"^(?:([a-zA-Z][a-zA-Z0-9+.-]*):)?"

19 r"(?://([^\\/?#]*))?"

20 r"([^?#]*)"

21 r"(?:\?([^#]*))?"

22 r"(?:#(.*))?$",

23 re.UNICODE | re.DOTALL,

24)

26_IPV4_PAT = r"(?:[0-9]{1,3}\.){3}[0-9]{1,3}"

27_HEX_PAT = "[0-9A-Fa-f]{1,4}"

28_LS32_PAT = "(?:{hex}:{hex}|{ipv4})".format(hex=_HEX_PAT, ipv4=_IPV4_PAT)

29_subs = {"hex": _HEX_PAT, "ls32": _LS32_PAT}

30_variations = [

31 # 6( h16 ":" ) ls32

32 "(?:%(hex)s:){6}%(ls32)s",

33 # "::" 5( h16 ":" ) ls32

34 "::(?:%(hex)s:){5}%(ls32)s",

35 # [ h16 ] "::" 4( h16 ":" ) ls32

36 "(?:%(hex)s)?::(?:%(hex)s:){4}%(ls32)s",

37 # [ *1( h16 ":" ) h16 ] "::" 3( h16 ":" ) ls32

38 "(?:(?:%(hex)s:)?%(hex)s)?::(?:%(hex)s:){3}%(ls32)s",

39 # [ *2( h16 ":" ) h16 ] "::" 2( h16 ":" ) ls32

40 "(?:(?:%(hex)s:){0,2}%(hex)s)?::(?:%(hex)s:){2}%(ls32)s",

41 # [ *3( h16 ":" ) h16 ] "::" h16 ":" ls32

42 "(?:(?:%(hex)s:){0,3}%(hex)s)?::%(hex)s:%(ls32)s",

43 # [ *4( h16 ":" ) h16 ] "::" ls32

44 "(?:(?:%(hex)s:){0,4}%(hex)s)?::%(ls32)s",

45 # [ *5( h16 ":" ) h16 ] "::" h16

46 "(?:(?:%(hex)s:){0,5}%(hex)s)?::%(hex)s",

47 # [ *6( h16 ":" ) h16 ] "::"

48 "(?:(?:%(hex)s:){0,6}%(hex)s)?::",

49]

51_UNRESERVED_PAT = r"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._\-~"

52_IPV6_PAT = "(?:" + "|".join([x % _subs for x in _variations]) + ")"

53_ZONE_ID_PAT = "(?:%25|%)(?:[" + _UNRESERVED_PAT + "]|%[a-fA-F0-9]{2})+"

54_IPV6_ADDRZ_PAT = r"\[" + _IPV6_PAT + r"(?:" + _ZONE_ID_PAT + r")?\]"

55_REG_NAME_PAT = r"(?:[^\[\]%:/?#]|%[a-fA-F0-9]{2})*"

56_TARGET_RE = re.compile(r"^(/[^?#]*)(?:\?([^#]*))?(?:#.*)?$")

58_IPV4_RE = re.compile("^" + _IPV4_PAT + "$")

59_IPV6_RE = re.compile("^" + _IPV6_PAT + "$")

60_IPV6_ADDRZ_RE = re.compile("^" + _IPV6_ADDRZ_PAT + "$")

61_BRACELESS_IPV6_ADDRZ_RE = re.compile("^" + _IPV6_ADDRZ_PAT[2:-2] + "$")

62_ZONE_ID_RE = re.compile("(" + _ZONE_ID_PAT + r")\]$")

64_HOST_PORT_PAT = ("^(%s|%s|%s)(?::0*?(|0|[1-9][0-9]{0,4}))?$") % (

65 _REG_NAME_PAT,

66 _IPV4_PAT,

67 _IPV6_ADDRZ_PAT,

68)

69_HOST_PORT_RE = re.compile(_HOST_PORT_PAT, re.UNICODE | re.DOTALL)

71_UNRESERVED_CHARS = set(

72 "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789._-~"

73)

74_SUB_DELIM_CHARS = set("!$&'()*+,;=")

75_USERINFO_CHARS = _UNRESERVED_CHARS | _SUB_DELIM_CHARS | {":"}

76_PATH_CHARS = _USERINFO_CHARS | {"@", "/"}

77_QUERY_CHARS = _FRAGMENT_CHARS = _PATH_CHARS | {"?"}

80class Url(

81 typing.NamedTuple(

82 "Url",

83 [

84 ("scheme", typing.Optional[str]),

85 ("auth", typing.Optional[str]),

86 ("host", typing.Optional[str]),

87 ("port", typing.Optional[int]),

88 ("path", typing.Optional[str]),

89 ("query", typing.Optional[str]),

90 ("fragment", typing.Optional[str]),

91 ],

92 )

93):

94 """

95 Data structure for representing an HTTP URL. Used as a return value for

96 :func:`parse_url`. Both the scheme and host are normalized as they are

97 both case-insensitive according to RFC 3986.

98 """

100 def __new__( # type: ignore[no-untyped-def]

101 cls,

102 scheme: str | None = None,

103 auth: str | None = None,

104 host: str | None = None,

105 port: int | None = None,

106 path: str | None = None,

107 query: str | None = None,

108 fragment: str | None = None,

109 ):

110 if path and not path.startswith("/"):

111 path = "/" + path

112 if scheme is not None:

113 scheme = scheme.lower()

114 return super().__new__(cls, scheme, auth, host, port, path, query, fragment)

115

116 @property

117 def hostname(self) -> str | None:

118 """For backwards-compatibility with urlparse. We're nice like that."""

119 return self.host

120

121 @property

122 def request_uri(self) -> str:

123 """Absolute path including the query string."""

124 uri = self.path or "/"

125

126 if self.query is not None:

127 uri += "?" + self.query

128

129 return uri

130

131 @property

132 def authority(self) -> str | None:

133 """

134 Authority component as defined in RFC 3986 3.2.

135 This includes userinfo (auth), host and port.

136

137 i.e.

138 userinfo@host:port

139 """

140 userinfo = self.auth

141 netloc = self.netloc

142 if netloc is None or userinfo is None:

143 return netloc

144 else:

145 return f"{userinfo}@{netloc}"

146

147 @property

148 def netloc(self) -> str | None:

149 """

150 Network location including host and port.

151

152 If you need the equivalent of urllib.parse's ``netloc``,

153 use the ``authority`` property instead.

154 """

155 if self.host is None:

156 return None

157 if self.port:

158 return f"{self.host}:{self.port}"

159 return self.host

160

161 @property

162 def url(self) -> str:

163 """

164 Convert self into a url

165

166 This function should more or less round-trip with :func:`.parse_url`. The

167 returned url may not be exactly the same as the url inputted to

168 :func:`.parse_url`, but it should be equivalent by the RFC (e.g., urls

169 with a blank port will have : removed).

170

171 Example:

172

173 .. code-block:: python

174

175 import urllib3

176

177 U = urllib3.util.parse_url("https://google.com/mail/")

178

179 print(U.url)

180 # "https://google.com/mail/"

181

182 print( urllib3.util.Url("https", "username:password",

183 "host.com", 80, "/path", "query", "fragment"

184 ).url

185 )

186 # "https://username:password@host.com:80/path?query#fragment"

187 """

188 scheme, auth, host, port, path, query, fragment = self

189 url = ""

190

191 # We use "is not None" we want things to happen with empty strings (or 0 port)

192 if scheme is not None:

193 url += scheme + "://"

194 if auth is not None:

195 url += auth + "@"

196 if host is not None:

197 url += host

198 if port is not None:

199 url += ":" + str(port)

200 if path is not None:

201 url += path

202 if query is not None:

203 url += "?" + query

204 if fragment is not None:

205 url += "#" + fragment

206

207 return url

208

209 def __str__(self) -> str:

210 return self.url

211

212

213@typing.overload

214def _encode_invalid_chars(

215 component: str, allowed_chars: typing.Container[str]

216) -> str: # Abstract

217 ...

218

219

220@typing.overload

221def _encode_invalid_chars(

222 component: None, allowed_chars: typing.Container[str]

223) -> None: # Abstract

224 ...

225

226

227def _encode_invalid_chars(

228 component: str | None, allowed_chars: typing.Container[str]

229) -> str | None:

230 """Percent-encodes a URI component without reapplying

231 onto an already percent-encoded component.

232 """

233 if component is None:

234 return component

235

236 component = to_str(component)

237

238 # Normalize existing percent-encoded bytes.

239 # Try to see if the component we're encoding is already percent-encoded

240 # so we can skip all '%' characters but still encode all others.

241 component, percent_encodings = _PERCENT_RE.subn(

242 lambda match: match.group(0).upper(), component

243 )

244

245 uri_bytes = component.encode("utf-8", "surrogatepass")

246 is_percent_encoded = percent_encodings == uri_bytes.count(b"%")

247 encoded_component = bytearray()

248

249 for i in range(0, len(uri_bytes)):

250 # Will return a single character bytestring

251 byte = uri_bytes[i : i + 1]

252 byte_ord = ord(byte)

253 if (is_percent_encoded and byte == b"%") or (

254 byte_ord < 128 and byte.decode() in allowed_chars

255 ):

256 encoded_component += byte

257 continue

258 encoded_component.extend(b"%" + (hex(byte_ord)[2:].encode().zfill(2).upper()))

259

260 return encoded_component.decode()

261

262

263def _remove_path_dot_segments(path: str) -> str:

264 # See http://tools.ietf.org/html/rfc3986#section-5.2.4 for pseudo-code

265 segments = path.split("/") # Turn the path into a list of segments

266 output = [] # Initialize the variable to use to store output

267

268 for segment in segments:

269 # '.' is the current directory, so ignore it, it is superfluous

270 if segment == ".":

271 continue

272 # Anything other than '..', should be appended to the output

273 if segment != "..":

274 output.append(segment)

275 # In this case segment == '..', if we can, we should pop the last

276 # element

277 elif output:

278 output.pop()

279

280 # If the path starts with '/' and the output is empty or the first string

281 # is non-empty

282 if path.startswith("/") and (not output or output[0]):

283 output.insert(0, "")

284

285 # If the path starts with '/.' or '/..' ensure we add one more empty

286 # string to add a trailing '/'

287 if path.endswith(("/.", "/..")):

288 output.append("")

289

290 return "/".join(output)

291

292

293@typing.overload

294def _normalize_host(host: None, scheme: str | None) -> None:

295 ...

296

297

298@typing.overload

299def _normalize_host(host: str, scheme: str | None) -> str:

300 ...

301

302

303def _normalize_host(host: str | None, scheme: str | None) -> str | None:

304 if host:

305 if scheme in _NORMALIZABLE_SCHEMES:

306 is_ipv6 = _IPV6_ADDRZ_RE.match(host)

307 if is_ipv6:

308 # IPv6 hosts of the form 'a::b%zone' are encoded in a URL as

309 # such per RFC 6874: 'a::b%25zone'. Unquote the ZoneID

310 # separator as necessary to return a valid RFC 4007 scoped IP.

311 match = _ZONE_ID_RE.search(host)

312 if match:

313 start, end = match.span(1)

314 zone_id = host[start:end]

315

316 if zone_id.startswith("%25") and zone_id != "%25":

317 zone_id = zone_id[3:]

318 else:

319 zone_id = zone_id[1:]

320 zone_id = _encode_invalid_chars(zone_id, _UNRESERVED_CHARS)

321 return f"{host[:start].lower()}%{zone_id}{host[end:]}"

322 else:

323 return host.lower()

324 elif not _IPV4_RE.match(host):

325 return to_str(

326 b".".join([_idna_encode(label) for label in host.split(".")]),

327 "ascii",

328 )

329 return host

330

331

332def _idna_encode(name: str) -> bytes:

333 if not name.isascii():

334 try:

335 import idna

336 except ImportError:

337 raise LocationParseError(

338 "Unable to parse URL without the 'idna' module"

339 ) from None

340

341 try:

342 return idna.encode(name.lower(), strict=True, std3_rules=True)

343 except idna.IDNAError:

344 raise LocationParseError(

345 f"Name '{name}' is not a valid IDNA label"

346 ) from None

347

348 return name.lower().encode("ascii")

349

350

351def _encode_target(target: str) -> str:

352 """Percent-encodes a request target so that there are no invalid characters

353

354 Pre-condition for this function is that 'target' must start with '/'.

355 If that is the case then _TARGET_RE will always produce a match.

356 """

357 match = _TARGET_RE.match(target)

358 if not match: # Defensive:

359 raise LocationParseError(f"{target!r} is not a valid request URI")

360

361 path, query = match.groups()

362 encoded_target = _encode_invalid_chars(path, _PATH_CHARS)

363 if query is not None:

364 query = _encode_invalid_chars(query, _QUERY_CHARS)

365 encoded_target += "?" + query

366 return encoded_target

367

368

369def parse_url(url: str) -> Url:

370 """

371 Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is

372 performed to parse incomplete urls. Fields not provided will be None.

373 This parser is RFC 3986 and RFC 6874 compliant.

374

375 The parser logic and helper functions are based heavily on

376 work done in the ``rfc3986`` module.

377

378 :param str url: URL to parse into a :class:`.Url` namedtuple.

379

380 Partly backwards-compatible with :mod:`urllib.parse`.

381

382 Example:

383

384 .. code-block:: python

385

386 import urllib3

387

388 print( urllib3.util.parse_url('http://google.com/mail/'))

389 # Url(scheme='http', host='google.com', port=None, path='/mail/', ...)

390

391 print( urllib3.util.parse_url('google.com:80'))

392 # Url(scheme=None, host='google.com', port=80, path=None, ...)

393

394 print( urllib3.util.parse_url('/foo?bar'))

395 # Url(scheme=None, host=None, port=None, path='/foo', query='bar', ...)

396 """

397 if not url:

398 # Empty

399 return Url()

400

401 source_url = url

402 if not _SCHEME_RE.search(url):

403 url = "//" + url

404

405 scheme: str | None

406 authority: str | None

407 auth: str | None

408 host: str | None

409 port: str | None

410 port_int: int | None

411 path: str | None

412 query: str | None

413 fragment: str | None

414

415 try:

416 scheme, authority, path, query, fragment = _URI_RE.match(url).groups() # type: ignore[union-attr]

417 normalize_uri = scheme is None or scheme.lower() in _NORMALIZABLE_SCHEMES

418

419 if scheme:

420 scheme = scheme.lower()

421

422 if authority:

423 auth, _, host_port = authority.rpartition("@")

424 auth = auth or None

425 host, port = _HOST_PORT_RE.match(host_port).groups() # type: ignore[union-attr]

426 if auth and normalize_uri:

427 auth = _encode_invalid_chars(auth, _USERINFO_CHARS)

428 if port == "":

429 port = None

430 else:

431 auth, host, port = None, None, None

432

433 if port is not None:

434 port_int = int(port)

435 if not (0 <= port_int <= 65535):

436 raise LocationParseError(url)

437 else:

438 port_int = None

439

440 host = _normalize_host(host, scheme)

441

442 if normalize_uri and path:

443 path = _remove_path_dot_segments(path)

444 path = _encode_invalid_chars(path, _PATH_CHARS)

445 if normalize_uri and query:

446 query = _encode_invalid_chars(query, _QUERY_CHARS)

447 if normalize_uri and fragment:

448 fragment = _encode_invalid_chars(fragment, _FRAGMENT_CHARS)

449

450 except (ValueError, AttributeError) as e:

451 raise LocationParseError(source_url) from e

452

453 # For the sake of backwards compatibility we put empty

454 # string values for path if there are any defined values

455 # beyond the path in the URL.

456 # TODO: Remove this when we break backwards compatibility.

457 if not path:

458 if query is not None or fragment is not None:

459 path = ""

460 else:

461 path = None

462

463 return Url(

464 scheme=scheme,

465 auth=auth,

466 host=host,

467 port=port_int,

468 path=path,

469 query=query,

470 fragment=fragment,

471 )