def url_unparse(components):
"""The reverse operation to :meth:`url_parse`. This accepts arbitrary
as well as :class:`URL` tuples and returns a URL as a string.
:param components: the parsed URL as tuple which should be converted
into a URL string.
"""
scheme, netloc, path, query, fragment = \
normalize_string_tuple(components)
s = make_literal_wrapper(scheme)
url = s('')
# We generally treat file:///x and file:/x the same which is also
# what browsers seem to do. This also allows us to ignore a schema
# register for netloc utilization or having to differenciate between
# empty and missing netloc.
if netloc or (scheme and path.startswith(s('/'))):
if path and path[:1] != s('/'):
path = s('/') + path
url = s('//') + (netloc or s('')) + path
elif path:
url += path
if scheme:
url = scheme + s(':') + url
if query:
url = url + s('?') + query
if fragment:
url = url + s('#') + fragment
return url
def url_unparse(components):
"""The reverse operation to :meth:`url_parse`. This accepts arbitrary
as well as :class:`URL` tuples and returns a URL as a string.
:param components: the parsed URL as tuple which should be converted
into a URL string.
"""
scheme, netloc, path, query, fragment = \
normalize_string_tuple(components)
s = make_literal_wrapper(scheme)
url = s('')
# We generally treat file:///x and file:/x the same which is also
# what browsers seem to do. This also allows us to ignore a schema
# register for netloc utilization or having to differenciate between
# empty and missing netloc.
if netloc or (scheme and path.startswith(s('/'))):
if path and path[:1] != s('/'):
path = s('/') + path
url = s('//') + (netloc or s('')) + path
elif path:
url += path
if scheme:
url = scheme + s(':') + url
if query:
url = url + s('?') + query
if fragment:
url = url + s('#') + fragment
return url
def url_join(base, url, allow_fragments=True):
"""Join a base URL and a possibly relative URL to form an absolute
interpretation of the latter.
:param base: the base URL for the join operation.
:param url: the URL to join.
:param allow_fragments: indicates whether fragments should be allowed.
"""
if isinstance(base, tuple):
base = url_unparse(base)
if isinstance(url, tuple):
url = url_unparse(url)
base, url = normalize_string_tuple((base, url))
s = make_literal_wrapper(base)
if not base:
return url
if not url:
return base
bscheme, bnetloc, bpath, bquery, bfragment = \
url_parse(base, allow_fragments=allow_fragments)
scheme, netloc, path, query, fragment = \
url_parse(url, bscheme, allow_fragments)
if scheme != bscheme:
return url
if netloc:
return url_unparse((scheme, netloc, path, query, fragment))
netloc = bnetloc
if path[:1] == s('/'):
segments = path.split(s('/'))
elif not path:
segments = bpath.split(s('/'))
if not query:
query = bquery
else:
segments = bpath.split(s('/'))[:-1] + path.split(s('/'))
# If the rightmost part is "./" we want to keep the slash but
# remove the dot.
if segments[-1] == s('.'):
segments[-1] = s('')
# Resolve ".." and "."
segments = [segment for segment in segments if segment != s('.')]
while 1:
i = 1
n = len(segments) - 1
while i < n:
if segments[i] == s('..') and \
segments[i - 1] not in (s(''), s('..')):
del segments[i - 1:i + 1]
break
i += 1
else:
break
# Remove trailing ".." if the URL is absolute
unwanted_marker = [s(''), s('..')]
while segments[:2] == unwanted_marker:
del segments[1]
path = s('/').join(segments)
return url_unparse((scheme, netloc, path, query, fragment))
def url_join(base, url, allow_fragments=True):
"""Join a base URL and a possibly relative URL to form an absolute
interpretation of the latter.
:param base: the base URL for the join operation.
:param url: the URL to join.
:param allow_fragments: indicates whether fragments should be allowed.
"""
if isinstance(base, tuple):
base = url_unparse(base)
if isinstance(url, tuple):
url = url_unparse(url)
base, url = normalize_string_tuple((base, url))
s = make_literal_wrapper(base)
if not base:
return url
if not url:
return base
bscheme, bnetloc, bpath, bquery, bfragment = \
url_parse(base, allow_fragments=allow_fragments)
scheme, netloc, path, query, fragment = \
url_parse(url, bscheme, allow_fragments)
if scheme != bscheme:
return url
if netloc:
return url_unparse((scheme, netloc, path, query, fragment))
netloc = bnetloc
if path[:1] == s('/'):
segments = path.split(s('/'))
elif not path:
segments = bpath.split(s('/'))
if not query:
query = bquery
else:
segments = bpath.split(s('/'))[:-1] + path.split(s('/'))
# If the rightmost part is "./" we want to keep the slash but
# remove the dot.
if segments[-1] == s('.'):
segments[-1] = s('')
# Resolve ".." and "."
segments = [segment for segment in segments if segment != s('.')]
while 1:
i = 1
n = len(segments) - 1
while i < n:
if segments[i] == s('..') and \
segments[i - 1] not in (s(''), s('..')):
del segments[i - 1:i + 1]
break
i += 1
else:
break
# Remove trailing ".." if the URL is absolute
unwanted_marker = [s(''), s('..')]
while segments[:2] == unwanted_marker:
del segments[1]
path = s('/').join(segments)
return url_unparse((scheme, netloc, path, query, fragment))
