Lib/urllib/parse.py

"""Parse (absolute and relative) URLs.

urlparse module is based upon the following RFC specifications.

RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L.  Masinter, January 2005.

RFC2396:  "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.

RFC2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zwinski, July 1998.

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

RFC1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
McCahill, December 1994

RFC 3986 is considered the current standard and any changes to urlparse module
should conform to this.  urlparse module is not entirely compliant with this.
The defacto scenarios of parsing are considered sometimes and for backward
compatiblity purposes, older RFC uses of parsing are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
"""

import sys
import collections

__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
           "urlsplit", "urlunsplit", "parse_qs", "parse_qsl",
           "quote", "quote_plus", "quote_from_bytes",
           "unquote", "unquote_plus", "unquote_to_bytes"]

# 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', 'nfs',' git', 'git+ssh']
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."""
    _parse_cache.clear()


class ResultMixin(object):
    """Shared methods for the parsed result objects."""

    @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

from collections import namedtuple

class SplitResult(namedtuple('SplitResult', 'scheme netloc path query fragment'), ResultMixin):

    __slots__ = ()

    def geturl(self):
        return urlunsplit(self)


class ParseResult(namedtuple('ParseResult', 'scheme netloc path params query fragment'), ResultMixin):

    __slots__ = ()

    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 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(components):
    """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)."""
    scheme, netloc, url, params, query, fragment = components
    if params:
        url = "%s;%s" % (url, params)
    return urlunsplit((scheme, netloc, url, query, fragment))

def urlunsplit(components):
    """Combine the elements of a tuple as returned by urlsplit() into a
    complete URL as a string. The data argument can be any five-item iterable.
    This may result in a slightly different, but equivalent URL, if the URL that
    was parsed originally had unnecessary delimiters (for example, a ? with an
    empty query; the RFC states that these are equivalent)."""
    scheme, netloc, url, query, fragment = components
    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:
        path = bpath
        if not params:
            params = bparams
        else:
            path = path[:-1]
            return urlunparse((scheme, netloc, path,
                                params, query, fragment))
        if not query:
            query = bquery
        return urlunparse((scheme, netloc, path,
                           params, query, 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, ''

def unquote_to_bytes(string):
    """unquote_to_bytes('abc%20def') -> b'abc def'."""
    # Note: strings are encoded as UTF-8. This is only an issue if it contains
    # unescaped non-ASCII characters, which URIs should not.
    if isinstance(string, str):
        string = string.encode('utf-8')
    res = string.split(b'%')
    res[0] = res[0]
    for i in range(1, len(res)):
        item = res[i]
        try:
            res[i] = bytes([int(item[:2], 16)]) + item[2:]
        except ValueError:
            res[i] = b'%' + item
    return b''.join(res)

def unquote(string, encoding='utf-8', errors='replace'):
    """Replace %xx escapes by their single-character equivalent. The optional
    encoding and errors parameters specify how to decode percent-encoded
    sequences into Unicode characters, as accepted by the bytes.decode()
    method.
    By default, percent-encoded sequences are decoded with UTF-8, and invalid
    sequences are replaced by a placeholder character.

    unquote('abc%20def') -> 'abc def'.
    """
    if encoding is None: encoding = 'utf-8'
    if errors is None: errors = 'replace'
    # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
    # (list of single-byte bytes objects)
    pct_sequence = []
    res = string.split('%')
    for i in range(1, len(res)):
        item = res[i]
        try:
            if not item: raise ValueError
            pct_sequence.append(bytes.fromhex(item[:2]))
            rest = item[2:]
        except ValueError:
            rest = '%' + item
        if not rest:
            # This segment was just a single percent-encoded character.
            # May be part of a sequence of code units, so delay decoding.
            # (Stored in pct_sequence).
            res[i] = ''
        else:
            # Encountered non-percent-encoded characters. Flush the current
            # pct_sequence.
            res[i] = b''.join(pct_sequence).decode(encoding, errors) + rest
            pct_sequence = []
    if pct_sequence:
        # Flush the final pct_sequence
        # res[-1] will always be empty if pct_sequence != []
        assert not res[-1], "string=%r, res=%r" % (string, res)
        res[-1] = b''.join(pct_sequence).decode(encoding, errors)
    return ''.join(res)

def parse_qs(qs, keep_blank_values=False, strict_parsing=False):
    """Parse a query given as a string argument.

        Arguments:

        qs: URL-encoded query string to be parsed

        keep_blank_values: flag indicating whether blank values in
            URL 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.

        strict_parsing: flag indicating what to do with parsing errors.
            If false (the default), errors are silently ignored.
            If true, errors raise a ValueError exception.
    """
    dict = {}
    for name, value in parse_qsl(qs, keep_blank_values, strict_parsing):
        if name in dict:
            dict[name].append(value)
        else:
            dict[name] = [value]
    return dict

def parse_qsl(qs, keep_blank_values=False, strict_parsing=False):
    """Parse a query given as a string argument.

    Arguments:

    qs: URL-encoded query string to be parsed

    keep_blank_values: flag indicating whether blank values in
        URL 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.

    strict_parsing: flag indicating what to do with parsing errors. If
        false (the default), errors are silently ignored. If true,
        errors raise a ValueError exception.

    Returns a list, as G-d intended.
    """
    pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
    r = []
    for name_value in pairs:
        if not name_value and not strict_parsing:
            continue
        nv = name_value.split('=', 1)
        if len(nv) != 2:
            if strict_parsing:
                raise ValueError("bad query field: %r" % (name_value,))
            # 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 = unquote(nv[0].replace('+', ' '))
            value = unquote(nv[1].replace('+', ' '))
            r.append((name, value))

    return r

def unquote_plus(string, encoding='utf-8', errors='replace'):
    """Like unquote(), but also replace plus signs by spaces, as required for
    unquoting HTML form values.

    unquote_plus('%7e/abc+def') -> '~/abc def'
    """
    string = string.replace('+', ' ')
    return unquote(string, encoding, errors)

_ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
                         b'abcdefghijklmnopqrstuvwxyz'
                         b'0123456789'
                         b'_.-')
_safe_quoters= {}

class Quoter(collections.defaultdict):
    """A mapping from bytes (in range(0,256)) to strings.

    String values are percent-encoded byte values, unless the key < 128, and
    in the "safe" set (either the specified safe set, or default set).
    """
    # Keeps a cache internally, using defaultdict, for efficiency (lookups
    # of cached keys don't call Python code at all).
    def __init__(self, safe):
        """safe: bytes object."""
        self.safe = _ALWAYS_SAFE.union(c for c in safe if c < 128)

    def __repr__(self):
        # Without this, will just display as a defaultdict
        return "<Quoter %r>" % dict(self)

    def __missing__(self, b):
        # Handle a cache miss. Store quoted string in cache and return.
        res = b in self.safe and chr(b) or ('%%%02X' % b)
        self[b] = res
        return res

def quote(string, safe='/', encoding=None, errors=None):
    """quote('abc def') -> 'abc%20def'

    Each part of a URL, e.g. the path info, the query, etc., has a
    different set of reserved characters that must be quoted.

    RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
    the following reserved characters.

    reserved    = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
                  "$" | ","

    Each of these characters is reserved in some component of a URL,
    but not necessarily in all of them.

    By default, the quote function is intended for quoting the path
    section of a URL.  Thus, it will not encode '/'.  This character
    is reserved, but in typical usage the quote function is being
    called on a path where the existing slash characters are used as
    reserved characters.

    string and safe may be either str or bytes objects. encoding must
    not be specified if string is a str.

    The optional encoding and errors parameters specify how to deal with
    non-ASCII characters, as accepted by the str.encode method.
    By default, encoding='utf-8' (characters are encoded with UTF-8), and
    errors='strict' (unsupported characters raise a UnicodeEncodeError).
    """
    if isinstance(string, str):
        if encoding is None:
            encoding = 'utf-8'
        if errors is None:
            errors = 'strict'
        string = string.encode(encoding, errors)
    else:
        if encoding is not None:
            raise TypeError("quote() doesn't support 'encoding' for bytes")
        if errors is not None:
            raise TypeError("quote() doesn't support 'errors' for bytes")
    return quote_from_bytes(string, safe)

def quote_plus(string, safe='', encoding=None, errors=None):
    """Like quote(), but also replace ' ' with '+', as required for quoting
    HTML form values. Plus signs in the original string are escaped unless
    they are included in safe. It also does not have safe default to '/'.
    """
    # Check if ' ' in string, where string may either be a str or bytes.  If
    # there are no spaces, the regular quote will produce the right answer.
    if ((isinstance(string, str) and ' ' not in string) or
        (isinstance(string, bytes) and b' ' not in string)):
        return quote(string, safe, encoding, errors)
    if isinstance(safe, str):
        space = ' '
    else:
        space = b' '
    string = quote(string, safe + space, encoding, errors)
    return string.replace(' ', '+')

def quote_from_bytes(bs, safe='/'):
    """Like quote(), but accepts a bytes object rather than a str, and does
    not perform string-to-bytes encoding.  It always returns an ASCII string.
    quote_from_bytes(b'abc def\xab') -> 'abc%20def%AB'
    """
    if isinstance(safe, str):
        # Normalize 'safe' by converting to bytes and removing non-ASCII chars
        safe = safe.encode('ascii', 'ignore')
    cachekey = bytes(safe)  # In case it was a bytearray
    if not (isinstance(bs, bytes) or isinstance(bs, bytearray)):
        raise TypeError("quote_from_bytes() expected a bytes")
    try:
        quoter = _safe_quoters[cachekey]
    except KeyError:
        quoter = Quoter(safe)
        _safe_quoters[cachekey] = quoter
    return ''.join([quoter[char] for char in bs])

def urlencode(query, doseq=False, safe='', encoding=None, errors=None):
    """Encode a sequence of two-element tuples or dictionary into a URL query string.

    If any values in the query arg are sequences and doseq is true, each
    sequence element is converted to a separate parameter.

    If the query arg is a sequence of two-element tuples, the order of the
    parameters in the output will match the order of parameters in the
    input.

    The query arg may be either a string or a bytes type. When query arg is a
    string, the safe, encoding and error parameters are sent the quote_plus for
    encoding.
    """

    if hasattr(query, "items"):
        query = query.items()
    else:
        # It's a bother at times that strings and string-like objects are
        # sequences.
        try:
            # non-sequence items should not work with len()
            # non-empty strings will fail this
            if len(query) and not isinstance(query[0], tuple):
                raise TypeError
            # Zero-length sequences of all types will get here and succeed,
            # but that's a minor nit.  Since the original implementation
            # allowed empty dicts that type of behavior probably should be
            # preserved for consistency
        except TypeError:
            ty, va, tb = sys.exc_info()
            raise TypeError("not a valid non-string sequence "
                            "or mapping object").with_traceback(tb)

    l = []
    if not doseq:
        for k, v in query:
            if isinstance(k, bytes):
                k = quote_plus(k, safe)
            else:
                k = quote_plus(str(k), safe, encoding, errors)

            if isinstance(v, bytes):
                v = quote_plus(v, safe)
            else:
                v = quote_plus(str(v), safe, encoding, errors)
            l.append(k + '=' + v)
    else:
        for k, v in query:
            if isinstance(k, bytes):
                k = quote_plus(k, safe)
            else:
                k = quote_plus(str(k), safe, encoding, errors)

            if isinstance(v, bytes):
                v = quote_plus(v, safe)
                l.append(k + '=' + v)
            elif isinstance(v, str):
                v = quote_plus(v, safe, encoding, errors)
                l.append(k + '=' + v)
            else:
                try:
                    # Is this a sufficient test for sequence-ness?
                    x = len(v)
                except TypeError:
                    # not a sequence
                    v = quote_plus(str(v), safe, encoding, errors)
                    l.append(k + '=' + v)
                else:
                    # loop over the sequence
                    for elt in v:
                        if isinstance(elt, bytes):
                            elt = quote_plus(elt, safe)
                        else:
                            elt = quote_plus(str(elt), safe, encoding, errors)
                        l.append(k + '=' + elt)
    return '&'.join(l)

# Utilities to parse URLs (most of these return None for missing parts):
# unwrap('<URL:type://host/path>') --> 'type://host/path'
# splittype('type:opaquestring') --> 'type', 'opaquestring'
# splithost('//host[:port]/path') --> 'host[:port]', '/path'
# splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'
# splitpasswd('user:passwd') -> 'user', 'passwd'
# splitport('host:port') --> 'host', 'port'
# splitquery('/path?query') --> '/path', 'query'
# splittag('/path#tag') --> '/path', 'tag'
# splitattr('/path;attr1=value1;attr2=value2;...') ->
#   '/path', ['attr1=value1', 'attr2=value2', ...]
# splitvalue('attr=value') --> 'attr', 'value'
# urllib.parse.unquote('abc%20def') -> 'abc def'
# quote('abc def') -> 'abc%20def')

def to_bytes(url):
    """to_bytes(u"URL") --> 'URL'."""
    # Most URL schemes require ASCII. If that changes, the conversion
    # can be relaxed.
    # XXX get rid of to_bytes()
    if isinstance(url, str):
        try:
            url = url.encode("ASCII").decode()
        except UnicodeError:
            raise UnicodeError("URL " + repr(url) +
                               " contains non-ASCII characters")
    return url

def unwrap(url):
    """unwrap('<URL:type://host/path>') --> 'type://host/path'."""
    url = str(url).strip()
    if url[:1] == '<' and url[-1:] == '>':
        url = url[1:-1].strip()
    if url[:4] == 'URL:': url = url[4:].strip()
    return url

_typeprog = None
def splittype(url):
    """splittype('type:opaquestring') --> 'type', 'opaquestring'."""
    global _typeprog
    if _typeprog is None:
        import re
        _typeprog = re.compile('^([^/:]+):')

    match = _typeprog.match(url)
    if match:
        scheme = match.group(1)
        return scheme.lower(), url[len(scheme) + 1:]
    return None, url

_hostprog = None
def splithost(url):
    """splithost('//host[:port]/path') --> 'host[:port]', '/path'."""
    global _hostprog
    if _hostprog is None:
        import re
        _hostprog = re.compile('^//([^/?]*)(.*)$')

    match = _hostprog.match(url)
    if match: return match.group(1, 2)
    return None, url

_userprog = None
def splituser(host):
    """splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'."""
    global _userprog
    if _userprog is None:
        import re
        _userprog = re.compile('^(.*)@(.*)$')

    match = _userprog.match(host)
    if match: return map(unquote, match.group(1, 2))
    return None, host

_passwdprog = None
def splitpasswd(user):
    """splitpasswd('user:passwd') -> 'user', 'passwd'."""
    global _passwdprog
    if _passwdprog is None:
        import re
        _passwdprog = re.compile('^([^:]*):(.*)$',re.S)

    match = _passwdprog.match(user)
    if match: return match.group(1, 2)
    return user, None

# splittag('/path#tag') --> '/path', 'tag'
_portprog = None
def splitport(host):
    """splitport('host:port') --> 'host', 'port'."""
    global _portprog
    if _portprog is None:
        import re
        _portprog = re.compile('^(.*):([0-9]+)$')

    match = _portprog.match(host)
    if match: return match.group(1, 2)
    return host, None

_nportprog = None
def splitnport(host, defport=-1):
    """Split host and port, returning numeric port.
    Return given default port if no ':' found; defaults to -1.
    Return numerical port if a valid number are found after ':'.
    Return None if ':' but not a valid number."""
    global _nportprog
    if _nportprog is None:
        import re
        _nportprog = re.compile('^(.*):(.*)$')

    match = _nportprog.match(host)
    if match:
        host, port = match.group(1, 2)
        try:
            if not port: raise ValueError("no digits")
            nport = int(port)
        except ValueError:
            nport = None
        return host, nport
    return host, defport

_queryprog = None
def splitquery(url):
    """splitquery('/path?query') --> '/path', 'query'."""
    global _queryprog
    if _queryprog is None:
        import re
        _queryprog = re.compile('^(.*)\?([^?]*)$')

    match = _queryprog.match(url)
    if match: return match.group(1, 2)
    return url, None

_tagprog = None
def splittag(url):
    """splittag('/path#tag') --> '/path', 'tag'."""
    global _tagprog
    if _tagprog is None:
        import re
        _tagprog = re.compile('^(.*)#([^#]*)$')

    match = _tagprog.match(url)
    if match: return match.group(1, 2)
    return url, None

def splitattr(url):
    """splitattr('/path;attr1=value1;attr2=value2;...') ->
        '/path', ['attr1=value1', 'attr2=value2', ...]."""
    words = url.split(';')
    return words[0], words[1:]

_valueprog = None
def splitvalue(attr):
    """splitvalue('attr=value') --> 'attr', 'value'."""
    global _valueprog
    if _valueprog is None:
        import re
        _valueprog = re.compile('^([^=]*)=(.*)$')

    match = _valueprog.match(attr)
    if match: return match.group(1, 2)
    return attr, None

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():
    base = ''
    if sys.argv[1:]:
        fn = sys.argv[1]
        if fn == '-':
            fp = sys.stdin
        else:
            fp = open(fn)
    else:
        from io import StringIO
        fp = StringIO(test_input)
    for line in fp:
        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()