django1/django/utils/http.py

import base64
import calendar
import datetime
import re
import unicodedata
import warnings
from binascii import Error as BinasciiError
from email.utils import formatdate
from urllib.parse import (
    quote, quote_plus, unquote, unquote_plus, urlencode as original_urlencode,
    urlparse,
)

from django.core.exceptions import TooManyFieldsSent
from django.utils.datastructures import MultiValueDict
from django.utils.deprecation import RemovedInDjango21Warning
from django.utils.encoding import force_bytes
from django.utils.functional import keep_lazy_text

# based on RFC 7232, Appendix C
ETAG_MATCH = re.compile(r'''
    \A(      # start of string and capture group
    (?:W/)?  # optional weak indicator
    "        # opening quote
    [^"]*    # any sequence of non-quote characters
    "        # end quote
    )\Z      # end of string and capture group
''', re.X)

MONTHS = 'jan feb mar apr may jun jul aug sep oct nov dec'.split()
__D = r'(?P<day>\d{2})'
__D2 = r'(?P<day>[ \d]\d)'
__M = r'(?P<mon>\w{3})'
__Y = r'(?P<year>\d{4})'
__Y2 = r'(?P<year>\d{2})'
__T = r'(?P<hour>\d{2}):(?P<min>\d{2}):(?P<sec>\d{2})'
RFC1123_DATE = re.compile(r'^\w{3}, %s %s %s %s GMT$' % (__D, __M, __Y, __T))
RFC850_DATE = re.compile(r'^\w{6,9}, %s-%s-%s %s GMT$' % (__D, __M, __Y2, __T))
ASCTIME_DATE = re.compile(r'^\w{3} %s %s %s %s$' % (__M, __D2, __T, __Y))

RFC3986_GENDELIMS = ":/?#[]@"
RFC3986_SUBDELIMS = "!$&'()*+,;="

FIELDS_MATCH = re.compile('[&;]')


@keep_lazy_text
def urlquote(url, safe='/'):
    """
    A legacy compatibility wrapper to Python's urllib.parse.quote() function.
    (was used for unicode handling on Python 2)
    """
    return quote(url, safe)


@keep_lazy_text
def urlquote_plus(url, safe=''):
    """
    A legacy compatibility wrapper to Python's urllib.parse.quote_plus()
    function. (was used for unicode handling on Python 2)
    """
    return quote_plus(url, safe)


@keep_lazy_text
def urlunquote(quoted_url):
    """
    A legacy compatibility wrapper to Python's urllib.parse.unquote() function.
    (was used for unicode handling on Python 2)
    """
    return unquote(quoted_url)


@keep_lazy_text
def urlunquote_plus(quoted_url):
    """
    A legacy compatibility wrapper to Python's urllib.parse.unquote_plus()
    function. (was used for unicode handling on Python 2)
    """
    return unquote_plus(quoted_url)


def urlencode(query, doseq=False):
    """
    A version of Python's urllib.parse.urlencode() function that can operate on
    MultiValueDict and non-string values.
    """
    if isinstance(query, MultiValueDict):
        query = query.lists()
    elif hasattr(query, 'items'):
        query = query.items()
    return original_urlencode(
        [(k, [str(i) for i in v] if isinstance(v, (list, tuple)) else str(v))
         for k, v in query],
        doseq
    )


def cookie_date(epoch_seconds=None):
    """
    Format the time to ensure compatibility with Netscape's cookie standard.

    `epoch_seconds` is a floating point number expressed in seconds since the
    epoch, in UTC - such as that outputted by time.time(). If set to None, it
    defaults to the current time.

    Output a string in the format 'Wdy, DD-Mon-YYYY HH:MM:SS GMT'.
    """
    rfcdate = formatdate(epoch_seconds)
    return '%s-%s-%s GMT' % (rfcdate[:7], rfcdate[8:11], rfcdate[12:25])


def http_date(epoch_seconds=None):
    """
    Format the time to match the RFC1123 date format as specified by HTTP
    RFC7231 section 7.1.1.1.

    `epoch_seconds` is a floating point number expressed in seconds since the
    epoch, in UTC - such as that outputted by time.time(). If set to None, it
    defaults to the current time.

    Output a string in the format 'Wdy, DD Mon YYYY HH:MM:SS GMT'.
    """
    return formatdate(epoch_seconds, usegmt=True)


def parse_http_date(date):
    """
    Parse a date format as specified by HTTP RFC7231 section 7.1.1.1.

    The three formats allowed by the RFC are accepted, even if only the first
    one is still in widespread use.

    Return an integer expressed in seconds since the epoch, in UTC.
    """
    # emails.Util.parsedate does the job for RFC1123 dates; unfortunately
    # RFC7231 makes it mandatory to support RFC850 dates too. So we roll
    # our own RFC-compliant parsing.
    for regex in RFC1123_DATE, RFC850_DATE, ASCTIME_DATE:
        m = regex.match(date)
        if m is not None:
            break
    else:
        raise ValueError("%r is not in a valid HTTP date format" % date)
    try:
        year = int(m.group('year'))
        if year < 100:
            if year < 70:
                year += 2000
            else:
                year += 1900
        month = MONTHS.index(m.group('mon').lower()) + 1
        day = int(m.group('day'))
        hour = int(m.group('hour'))
        min = int(m.group('min'))
        sec = int(m.group('sec'))
        result = datetime.datetime(year, month, day, hour, min, sec)
        return calendar.timegm(result.utctimetuple())
    except Exception as exc:
        raise ValueError("%r is not a valid date" % date) from exc


def parse_http_date_safe(date):
    """
    Same as parse_http_date, but return None if the input is invalid.
    """
    try:
        return parse_http_date(date)
    except Exception:
        pass


# Base 36 functions: useful for generating compact URLs

def base36_to_int(s):
    """
    Convert a base 36 string to an int. Raise ValueError if the input won't fit
    into an int.
    """
    # To prevent overconsumption of server resources, reject any
    # base36 string that is longer than 13 base36 digits (13 digits
    # is sufficient to base36-encode any 64-bit integer)
    if len(s) > 13:
        raise ValueError("Base36 input too large")
    return int(s, 36)


def int_to_base36(i):
    """Convert an integer to a base36 string."""
    char_set = '0123456789abcdefghijklmnopqrstuvwxyz'
    if i < 0:
        raise ValueError("Negative base36 conversion input.")
    if i < 36:
        return char_set[i]
    b36 = ''
    while i != 0:
        i, n = divmod(i, 36)
        b36 = char_set[n] + b36
    return b36


def urlsafe_base64_encode(s):
    """
    Encode a bytestring in base64 for use in URLs. Strip any trailing equal
    signs.
    """
    return base64.urlsafe_b64encode(s).rstrip(b'\n=')


def urlsafe_base64_decode(s):
    """
    Decode a base64 encoded string. Add back any trailing equal signs that
    might have been stripped.
    """
    s = force_bytes(s)
    try:
        return base64.urlsafe_b64decode(s.ljust(len(s) + len(s) % 4, b'='))
    except (LookupError, BinasciiError) as e:
        raise ValueError(e)


def parse_etags(etag_str):
    """
    Parse a string of ETags given in an If-None-Match or If-Match header as
    defined by RFC 7232. Return a list of quoted ETags, or ['*'] if all ETags
    should be matched.
    """
    if etag_str.strip() == '*':
        return ['*']
    else:
        # Parse each ETag individually, and return any that are valid.
        etag_matches = (ETAG_MATCH.match(etag.strip()) for etag in etag_str.split(','))
        return [match.group(1) for match in etag_matches if match]


def quote_etag(etag_str):
    """
    If the provided string is already a quoted ETag, return it. Otherwise, wrap
    the string in quotes, making it a strong ETag.
    """
    if ETAG_MATCH.match(etag_str):
        return etag_str
    else:
        return '"%s"' % etag_str


def is_same_domain(host, pattern):
    """
    Return ``True`` if the host is either an exact match or a match
    to the wildcard pattern.

    Any pattern beginning with a period matches a domain and all of its
    subdomains. (e.g. ``.example.com`` matches ``example.com`` and
    ``foo.example.com``). Anything else is an exact string match.
    """
    if not pattern:
        return False

    pattern = pattern.lower()
    return (
        pattern[0] == '.' and (host.endswith(pattern) or host == pattern[1:]) or
        pattern == host
    )


def is_safe_url(url, host=None, allowed_hosts=None, require_https=False):
    """
    Return ``True`` if the url is a safe redirection (i.e. it doesn't point to
    a different host and uses a safe scheme).

    Always return ``False`` on an empty url.

    If ``require_https`` is ``True``, only 'https' will be considered a valid
    scheme, as opposed to 'http' and 'https' with the default, ``False``.
    """
    if url is not None:
        url = url.strip()
    if not url:
        return False
    if allowed_hosts is None:
        allowed_hosts = set()
    if host:
        warnings.warn(
            "The host argument is deprecated, use allowed_hosts instead.",
            RemovedInDjango21Warning,
            stacklevel=2,
        )
        # Avoid mutating the passed in allowed_hosts.
        allowed_hosts = allowed_hosts | {host}
    # Chrome treats \ completely as / in paths but it could be part of some
    # basic auth credentials so we need to check both URLs.
    return (_is_safe_url(url, allowed_hosts, require_https=require_https) and
            _is_safe_url(url.replace('\\', '/'), allowed_hosts, require_https=require_https))


def _is_safe_url(url, allowed_hosts, require_https=False):
    # Chrome considers any URL with more than two slashes to be absolute, but
    # urlparse is not so flexible. Treat any url with three slashes as unsafe.
    if url.startswith('///'):
        return False
    url_info = urlparse(url)
    # Forbid URLs like http:///example.com - with a scheme, but without a hostname.
    # In that URL, example.com is not the hostname but, a path component. However,
    # Chrome will still consider example.com to be the hostname, so we must not
    # allow this syntax.
    if not url_info.netloc and url_info.scheme:
        return False
    # Forbid URLs that start with control characters. Some browsers (like
    # Chrome) ignore quite a few control characters at the start of a
    # URL and might consider the URL as scheme relative.
    if unicodedata.category(url[0])[0] == 'C':
        return False
    scheme = url_info.scheme
    # Consider URLs without a scheme (e.g. //example.com/p) to be http.
    if not url_info.scheme and url_info.netloc:
        scheme = 'http'
    valid_schemes = ['https'] if require_https else ['http', 'https']
    return ((not url_info.netloc or url_info.netloc in allowed_hosts) and
            (not scheme or scheme in valid_schemes))


def limited_parse_qsl(qs, keep_blank_values=False, encoding='utf-8',
                      errors='replace', fields_limit=None):
    """
    Return a list of key/value tuples parsed from query string.

    Copied from urlparse with an additional "fields_limit" argument.
    Copyright (C) 2013 Python Software Foundation (see LICENSE.python).

    Arguments:

    qs: percent-encoded query string to be parsed

    keep_blank_values: flag indicating whether blank values in
        percent-encoded queries should be treated as blank strings. A
        true value indicates that blanks should be retained as blank
        strings. The default false value indicates that blank values
        are to be ignored and treated as if they were  not included.

    encoding and errors: specify how to decode percent-encoded sequences
        into Unicode characters, as accepted by the bytes.decode() method.

    fields_limit: maximum number of fields parsed or an exception
        is raised. None means no limit and is the default.
    """
    if fields_limit:
        pairs = FIELDS_MATCH.split(qs, fields_limit)
        if len(pairs) > fields_limit:
            raise TooManyFieldsSent(
                'The number of GET/POST parameters exceeded '
                'settings.DATA_UPLOAD_MAX_NUMBER_FIELDS.'
            )
    else:
        pairs = FIELDS_MATCH.split(qs)
    r = []
    for name_value in pairs:
        if not name_value:
            continue
        nv = name_value.split('=', 1)
        if len(nv) != 2:
            # Handle case of a control-name with no equal sign
            if keep_blank_values:
                nv.append('')
            else:
                continue
        if len(nv[1]) or keep_blank_values:
            name = nv[0].replace('+', ' ')
            name = unquote(name, encoding=encoding, errors=errors)
            value = nv[1].replace('+', ' ')
            value = unquote(value, encoding=encoding, errors=errors)
            r.append((name, value))
    return r