summaryrefslogtreecommitdiff
path: root/src/pip/_vendor/packaging/requirements.py
blob: f9d1c65991a7bff155386acf185c23adbe78316a (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
# This file is dual licensed under the terms of the Apache License, Version
# 2.0, and the BSD License. See the LICENSE file in the root of this repository
# for complete details.
from __future__ import absolute_import, division, print_function

import string
import re
import sys

from pip._vendor.pyparsing import stringStart, stringEnd, originalTextFor, ParseException
from pip._vendor.pyparsing import ZeroOrMore, Word, Optional, Regex, Combine
from pip._vendor.pyparsing import Literal as L  # noqa

from ._typing import TYPE_CHECKING
from .markers import MARKER_EXPR, Marker
from .specifiers import LegacySpecifier, Specifier, SpecifierSet

if sys.version_info[0] >= 3:
    from urllib import parse as urlparse  # pragma: no cover
else:  # pragma: no cover
    import urlparse


if TYPE_CHECKING:  # pragma: no cover
    from typing import List


class InvalidRequirement(ValueError):
    """
    An invalid requirement was found, users should refer to PEP 508.
    """


ALPHANUM = Word(string.ascii_letters + string.digits)

LBRACKET = L("[").suppress()
RBRACKET = L("]").suppress()
LPAREN = L("(").suppress()
RPAREN = L(")").suppress()
COMMA = L(",").suppress()
SEMICOLON = L(";").suppress()
AT = L("@").suppress()

PUNCTUATION = Word("-_.")
IDENTIFIER_END = ALPHANUM | (ZeroOrMore(PUNCTUATION) + ALPHANUM)
IDENTIFIER = Combine(ALPHANUM + ZeroOrMore(IDENTIFIER_END))

NAME = IDENTIFIER("name")
EXTRA = IDENTIFIER

URI = Regex(r"[^ ]+")("url")
URL = AT + URI

EXTRAS_LIST = EXTRA + ZeroOrMore(COMMA + EXTRA)
EXTRAS = (LBRACKET + Optional(EXTRAS_LIST) + RBRACKET)("extras")

VERSION_PEP440 = Regex(Specifier._regex_str, re.VERBOSE | re.IGNORECASE)
VERSION_LEGACY = Regex(LegacySpecifier._regex_str, re.VERBOSE | re.IGNORECASE)

VERSION_ONE = VERSION_PEP440 ^ VERSION_LEGACY
VERSION_MANY = Combine(
    VERSION_ONE + ZeroOrMore(COMMA + VERSION_ONE), joinString=",", adjacent=False
)("_raw_spec")
_VERSION_SPEC = Optional(((LPAREN + VERSION_MANY + RPAREN) | VERSION_MANY))
_VERSION_SPEC.setParseAction(lambda s, l, t: t._raw_spec or "")

VERSION_SPEC = originalTextFor(_VERSION_SPEC)("specifier")
VERSION_SPEC.setParseAction(lambda s, l, t: t[1])

MARKER_EXPR = originalTextFor(MARKER_EXPR())("marker")
MARKER_EXPR.setParseAction(
    lambda s, l, t: Marker(s[t._original_start : t._original_end])
)
MARKER_SEPARATOR = SEMICOLON
MARKER = MARKER_SEPARATOR + MARKER_EXPR

VERSION_AND_MARKER = VERSION_SPEC + Optional(MARKER)
URL_AND_MARKER = URL + Optional(MARKER)

NAMED_REQUIREMENT = NAME + Optional(EXTRAS) + (URL_AND_MARKER | VERSION_AND_MARKER)

REQUIREMENT = stringStart + NAMED_REQUIREMENT + stringEnd
# pyparsing isn't thread safe during initialization, so we do it eagerly, see
# issue #104
REQUIREMENT.parseString("x[]")


class Requirement(object):
    """Parse a requirement.

    Parse a given requirement string into its parts, such as name, specifier,
    URL, and extras. Raises InvalidRequirement on a badly-formed requirement
    string.
    """

    # TODO: Can we test whether something is contained within a requirement?
    #       If so how do we do that? Do we need to test against the _name_ of
    #       the thing as well as the version? What about the markers?
    # TODO: Can we normalize the name and extra name?

    def __init__(self, requirement_string):
        # type: (str) -> None
        try:
            req = REQUIREMENT.parseString(requirement_string)
        except ParseException as e:
            raise InvalidRequirement(
                'Parse error at "{0!r}": {1}'.format(
                    requirement_string[e.loc : e.loc + 8], e.msg
                )
            )

        self.name = req.name
        if req.url:
            parsed_url = urlparse.urlparse(req.url)
            if parsed_url.scheme == "file":
                if urlparse.urlunparse(parsed_url) != req.url:
                    raise InvalidRequirement("Invalid URL given")
            elif not (parsed_url.scheme and parsed_url.netloc) or (
                not parsed_url.scheme and not parsed_url.netloc
            ):
                raise InvalidRequirement("Invalid URL: {0}".format(req.url))
            self.url = req.url
        else:
            self.url = None
        self.extras = set(req.extras.asList() if req.extras else [])
        self.specifier = SpecifierSet(req.specifier)
        self.marker = req.marker if req.marker else None

    def __str__(self):
        # type: () -> str
        parts = [self.name]  # type: List[str]

        if self.extras:
            parts.append("[{0}]".format(",".join(sorted(self.extras))))

        if self.specifier:
            parts.append(str(self.specifier))

        if self.url:
            parts.append("@ {0}".format(self.url))
            if self.marker:
                parts.append(" ")

        if self.marker:
            parts.append("; {0}".format(self.marker))

        return "".join(parts)

    def __repr__(self):
        # type: () -> str
        return "<Requirement({0!r})>".format(str(self))