Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/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@typing.overload

298def _normalize_host(host: str, scheme: str | None) -> str: ...

299

300

301def _normalize_host(host: str | None, scheme: str | None) -> str | None:

302 if host:

303 if scheme in _NORMALIZABLE_SCHEMES:

304 is_ipv6 = _IPV6_ADDRZ_RE.match(host)

305 if is_ipv6:

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

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

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

309 match = _ZONE_ID_RE.search(host)

310 if match:

311 start, end = match.span(1)

312 zone_id = host[start:end]

313

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

315 zone_id = zone_id[3:]

316 else:

317 zone_id = zone_id[1:]

318 zone_id = _encode_invalid_chars(zone_id, _UNRESERVED_CHARS)

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

320 else:

321 return host.lower()

322 elif not _IPV4_RE.match(host):

323 return to_str(

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

325 "ascii",

326 )

327 return host

328

329

330def _idna_encode(name: str) -> bytes:

331 if not name.isascii():

332 try:

333 import idna

334 except ImportError:

335 raise LocationParseError(

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

337 ) from None

338

339 try:

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

341 except idna.IDNAError:

342 raise LocationParseError(

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

344 ) from None

345

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

347

348

349def _encode_target(target: str) -> str:

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

351

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

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

354 """

355 match = _TARGET_RE.match(target)

356 if not match: # Defensive:

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

358

359 path, query = match.groups()

360 encoded_target = _encode_invalid_chars(path, _PATH_CHARS)

361 if query is not None:

362 query = _encode_invalid_chars(query, _QUERY_CHARS)

363 encoded_target += "?" + query

364 return encoded_target

365

366

367def parse_url(url: str) -> Url:

368 """

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

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

371 This parser is RFC 3986 and RFC 6874 compliant.

372

373 The parser logic and helper functions are based heavily on

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

375

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

377

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

379

380 Example:

381

382 .. code-block:: python

383

384 import urllib3

385

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

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

388

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

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

391

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

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

394 """

395 if not url:

396 # Empty

397 return Url()

398

399 source_url = url

400 if not _SCHEME_RE.search(url):

401 url = "//" + url

402

403 scheme: str | None

404 authority: str | None

405 auth: str | None

406 host: str | None

407 port: str | None

408 port_int: int | None

409 path: str | None

410 query: str | None

411 fragment: str | None

412

413 try:

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

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

416

417 if scheme:

418 scheme = scheme.lower()

419

420 if authority:

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

422 auth = auth or None

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

424 if auth and normalize_uri:

425 auth = _encode_invalid_chars(auth, _USERINFO_CHARS)

426 if port == "":

427 port = None

428 else:

429 auth, host, port = None, None, None

430

431 if port is not None:

432 port_int = int(port)

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

434 raise LocationParseError(url)

435 else:

436 port_int = None

437

438 host = _normalize_host(host, scheme)

439

440 if normalize_uri and path:

441 path = _remove_path_dot_segments(path)

442 path = _encode_invalid_chars(path, _PATH_CHARS)

443 if normalize_uri and query:

444 query = _encode_invalid_chars(query, _QUERY_CHARS)

445 if normalize_uri and fragment:

446 fragment = _encode_invalid_chars(fragment, _FRAGMENT_CHARS)

447

448 except (ValueError, AttributeError) as e:

449 raise LocationParseError(source_url) from e

450

451 # For the sake of backwards compatibility we put empty

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

453 # beyond the path in the URL.

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

455 if not path:

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

457 path = ""

458 else:

459 path = None

460

461 return Url(

462 scheme=scheme,

463 auth=auth,

464 host=host,

465 port=port_int,

466 path=path,

467 query=query,

468 fragment=fragment,

469 )