textproc/py-feedparser: update to 6.0.2
This update require adding the missing sgmllib for python3 versions and makes the license dual contributed by James French. Also update the test target and switch to github. PR: 250380 Submitted by: jbeich MFH: 2021Q2
This commit is contained in:
Sofian Brabez
parent
b1ca09de5c
commit
d950078a61
@ -1,31 +1,43 @@
|
||||
# Created by: ijliao
|
||||
|
||||
PORTNAME= feedparser
|
||||
PORTVERSION= 5.2.1
|
||||
PORTVERSION= 6.0.2
|
||||
CATEGORIES= textproc python
|
||||
MASTER_SITES= CHEESESHOP
|
||||
PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX}
|
||||
|
||||
MAINTAINER= sbz@FreeBSD.org
|
||||
COMMENT= Universal feed parser written in Python
|
||||
|
||||
LICENSE= BSD2CLAUSE
|
||||
LICENSE= BSD2CLAUSE PSFL
|
||||
LICENSE_COMB= multi
|
||||
LICENSE_FILE= ${WRKSRC}/LICENSE
|
||||
|
||||
USES= python:3.6+ tar:bzip2
|
||||
USE_PYTHON= distutils autoplist
|
||||
USE_PYTHON= autoplist distutils
|
||||
USE_GITHUB= yes
|
||||
|
||||
GH_ACCOUNT= kurtmckee
|
||||
|
||||
NO_ARCH= yes
|
||||
|
||||
OPTIONS_DEFINE= DOCS
|
||||
|
||||
PORTDOCS= NEWS README.rst
|
||||
|
||||
OPTIONS_DEFINE= DOCS
|
||||
|
||||
.include <bsd.port.pre.mk>
|
||||
|
||||
.if ${PYTHON_REL} > 3700
|
||||
PLIST_FILES+= ${PYTHON_SITELIBDIR}/sgmllib.py
|
||||
|
||||
post-install:
|
||||
${INSTALL_DATA} ${FILESDIR}/sgmllib.py ${STAGEDIR}/${PYTHON_SITELIBDIR}/sgmllib.py
|
||||
.endif
|
||||
|
||||
post-install-DOCS-on:
|
||||
${MKDIR} ${STAGEDIR}${DOCSDIR}
|
||||
@${MKDIR} ${STAGEDIR}${DOCSDIR}
|
||||
${INSTALL_DATA} ${PORTDOCS:S,^,${WRKSRC}/,} ${STAGEDIR}${DOCSDIR}
|
||||
|
||||
do-test:
|
||||
@(cd ${WRKSRC}/${PORTNAME}; ${PYTHON_CMD} ${PORTNAME}test.py)
|
||||
@(cd ${WRKSRC}; ${PYTHON_CMD} tests/runtests.py)
|
||||
|
||||
.include <bsd.port.mk>
|
||||
.include <bsd.port.post.mk>
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
TIMESTAMP = 1464128973
|
||||
SHA256 (feedparser-5.2.1.tar.bz2) = ce875495c90ebd74b179855449040003a1beb40cd13d5f037a0654251e260b02
|
||||
SIZE (feedparser-5.2.1.tar.bz2) = 192328
|
||||
TIMESTAMP = 1618343573
|
||||
SHA256 (kurtmckee-feedparser-6.0.2_GH0.tar.gz) = b211cfb80c4daefca64b773ade77340727187564fad9c2c94b37da8e1f03788f
|
||||
SIZE (kurtmckee-feedparser-6.0.2_GH0.tar.gz) = 251508
|
||||
|
||||
547
textproc/py-feedparser/files/sgmllib.py
Normal file
547
textproc/py-feedparser/files/sgmllib.py
Normal file
@ -0,0 +1,547 @@
|
||||
"""A parser for SGML, using the derived class as a static DTD."""
|
||||
|
||||
# XXX This only supports those SGML features used by HTML.
|
||||
|
||||
# XXX There should be a way to distinguish between PCDATA (parsed
|
||||
# character data -- the normal case), RCDATA (replaceable character
|
||||
# data -- only char and entity references and end tags are special)
|
||||
# and CDATA (character data -- only end tags are special). RCDATA is
|
||||
# not supported at all.
|
||||
|
||||
import _markupbase
|
||||
import re
|
||||
|
||||
__all__ = ["SGMLParser", "SGMLParseError"]
|
||||
|
||||
# Regular expressions used for parsing
|
||||
|
||||
interesting = re.compile('[&<]')
|
||||
incomplete = re.compile('&([a-zA-Z][a-zA-Z0-9]*|#[0-9]*)?|'
|
||||
'<([a-zA-Z][^<>]*|'
|
||||
'/([a-zA-Z][^<>]*)?|'
|
||||
'![^<>]*)?')
|
||||
|
||||
entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
|
||||
charref = re.compile('&#([0-9]+)[^0-9]')
|
||||
|
||||
starttagopen = re.compile('<[>a-zA-Z]')
|
||||
shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
|
||||
shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
|
||||
piclose = re.compile('>')
|
||||
endbracket = re.compile('[<>]')
|
||||
tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*')
|
||||
attrfind = re.compile(
|
||||
r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
|
||||
r'(\'[^\']*\'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*))?')
|
||||
|
||||
|
||||
class SGMLParseError(RuntimeError):
|
||||
"""Exception raised for all parse errors."""
|
||||
pass
|
||||
|
||||
|
||||
# SGML parser base class -- find tags and call handler functions.
|
||||
# Usage: p = SGMLParser(); p.feed(data); ...; p.close().
|
||||
# The dtd is defined by deriving a class which defines methods
|
||||
# with special names to handle tags: start_foo and end_foo to handle
|
||||
# <foo> and </foo>, respectively, or do_foo to handle <foo> by itself.
|
||||
# (Tags are converted to lower case for this purpose.) The data
|
||||
# between tags is passed to the parser by calling self.handle_data()
|
||||
# with some data as argument (the data may be split up in arbitrary
|
||||
# chunks). Entity references are passed by calling
|
||||
# self.handle_entityref() with the entity reference as argument.
|
||||
|
||||
class SGMLParser(_markupbase.ParserBase):
|
||||
# Definition of entities -- derived classes may override
|
||||
entity_or_charref = re.compile('&(?:'
|
||||
'([a-zA-Z][-.a-zA-Z0-9]*)|#([0-9]+)'
|
||||
')(;?)')
|
||||
|
||||
def __init__(self, verbose=0):
|
||||
"""Initialize and reset this instance."""
|
||||
self.verbose = verbose
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
"""Reset this instance. Loses all unprocessed data."""
|
||||
self.__starttag_text = None
|
||||
self.rawdata = ''
|
||||
self.stack = []
|
||||
self.lasttag = '???'
|
||||
self.nomoretags = 0
|
||||
self.literal = 0
|
||||
_markupbase.ParserBase.reset(self)
|
||||
|
||||
def setnomoretags(self):
|
||||
"""Enter literal mode (CDATA) till EOF.
|
||||
|
||||
Intended for derived classes only.
|
||||
"""
|
||||
self.nomoretags = self.literal = 1
|
||||
|
||||
def setliteral(self, *args):
|
||||
"""Enter literal mode (CDATA).
|
||||
|
||||
Intended for derived classes only.
|
||||
"""
|
||||
self.literal = 1
|
||||
|
||||
def feed(self, data):
|
||||
"""Feed some data to the parser.
|
||||
|
||||
Call this as often as you want, with as little or as much text
|
||||
as you want (may include '\n'). (This just saves the text,
|
||||
all the processing is done by goahead().)
|
||||
"""
|
||||
|
||||
self.rawdata = self.rawdata + data
|
||||
self.goahead(0)
|
||||
|
||||
def close(self):
|
||||
"""Handle the remaining data."""
|
||||
self.goahead(1)
|
||||
|
||||
def error(self, message):
|
||||
raise SGMLParseError(message)
|
||||
|
||||
# Internal -- handle data as far as reasonable. May leave state
|
||||
# and data to be processed by a subsequent call. If 'end' is
|
||||
# true, force handling all data as if followed by EOF marker.
|
||||
def goahead(self, end):
|
||||
rawdata = self.rawdata
|
||||
i = 0
|
||||
n = len(rawdata)
|
||||
while i < n:
|
||||
if self.nomoretags:
|
||||
self.handle_data(rawdata[i:n])
|
||||
i = n
|
||||
break
|
||||
match = interesting.search(rawdata, i)
|
||||
if match: j = match.start()
|
||||
else: j = n
|
||||
if i < j:
|
||||
self.handle_data(rawdata[i:j])
|
||||
i = j
|
||||
if i == n: break
|
||||
if rawdata[i] == '<':
|
||||
if starttagopen.match(rawdata, i):
|
||||
if self.literal:
|
||||
self.handle_data(rawdata[i])
|
||||
i = i+1
|
||||
continue
|
||||
k = self.parse_starttag(i)
|
||||
if k < 0: break
|
||||
i = k
|
||||
continue
|
||||
if rawdata.startswith("</", i):
|
||||
k = self.parse_endtag(i)
|
||||
if k < 0: break
|
||||
i = k
|
||||
self.literal = 0
|
||||
continue
|
||||
if self.literal:
|
||||
if n > (i + 1):
|
||||
self.handle_data("<")
|
||||
i = i+1
|
||||
else:
|
||||
# incomplete
|
||||
break
|
||||
continue
|
||||
if rawdata.startswith("<!--", i):
|
||||
# Strictly speaking, a comment is --.*--
|
||||
# within a declaration tag <!...>.
|
||||
# This should be removed,
|
||||
# and comments handled only in parse_declaration.
|
||||
k = self.parse_comment(i)
|
||||
if k < 0: break
|
||||
i = k
|
||||
continue
|
||||
if rawdata.startswith("<?", i):
|
||||
k = self.parse_pi(i)
|
||||
if k < 0: break
|
||||
i = i+k
|
||||
continue
|
||||
if rawdata.startswith("<!", i):
|
||||
# This is some sort of declaration; in "HTML as
|
||||
# deployed," this should only be the document type
|
||||
# declaration ("<!DOCTYPE html...>").
|
||||
k = self.parse_declaration(i)
|
||||
if k < 0: break
|
||||
i = k
|
||||
continue
|
||||
elif rawdata[i] == '&':
|
||||
if self.literal:
|
||||
self.handle_data(rawdata[i])
|
||||
i = i+1
|
||||
continue
|
||||
match = charref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group(1)
|
||||
self.handle_charref(name)
|
||||
i = match.end(0)
|
||||
if rawdata[i-1] != ';': i = i-1
|
||||
continue
|
||||
match = entityref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group(1)
|
||||
self.handle_entityref(name)
|
||||
i = match.end(0)
|
||||
if rawdata[i-1] != ';': i = i-1
|
||||
continue
|
||||
else:
|
||||
self.error('neither < nor & ??')
|
||||
# We get here only if incomplete matches but
|
||||
# nothing else
|
||||
match = incomplete.match(rawdata, i)
|
||||
if not match:
|
||||
self.handle_data(rawdata[i])
|
||||
i = i+1
|
||||
continue
|
||||
j = match.end(0)
|
||||
if j == n:
|
||||
break # Really incomplete
|
||||
self.handle_data(rawdata[i:j])
|
||||
i = j
|
||||
# end while
|
||||
if end and i < n:
|
||||
self.handle_data(rawdata[i:n])
|
||||
i = n
|
||||
self.rawdata = rawdata[i:]
|
||||
# XXX if end: check for empty stack
|
||||
|
||||
# Extensions for the DOCTYPE scanner:
|
||||
_decl_otherchars = '='
|
||||
|
||||
# Internal -- parse processing instr, return length or -1 if not terminated
|
||||
def parse_pi(self, i):
|
||||
rawdata = self.rawdata
|
||||
if rawdata[i:i+2] != '<?':
|
||||
self.error('unexpected call to parse_pi()')
|
||||
match = piclose.search(rawdata, i+2)
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start(0)
|
||||
self.handle_pi(rawdata[i+2: j])
|
||||
j = match.end(0)
|
||||
return j-i
|
||||
|
||||
def get_starttag_text(self):
|
||||
return self.__starttag_text
|
||||
|
||||
# Internal -- handle starttag, return length or -1 if not terminated
|
||||
def parse_starttag(self, i):
|
||||
self.__starttag_text = None
|
||||
start_pos = i
|
||||
rawdata = self.rawdata
|
||||
if shorttagopen.match(rawdata, i):
|
||||
# SGML shorthand: <tag/data/ == <tag>data</tag>
|
||||
# XXX Can data contain &... (entity or char refs)?
|
||||
# XXX Can data contain < or > (tag characters)?
|
||||
# XXX Can there be whitespace before the first /?
|
||||
match = shorttag.match(rawdata, i)
|
||||
if not match:
|
||||
return -1
|
||||
tag, data = match.group(1, 2)
|
||||
self.__starttag_text = '<%s/' % tag
|
||||
tag = tag.lower()
|
||||
k = match.end(0)
|
||||
self.finish_shorttag(tag, data)
|
||||
self.__starttag_text = rawdata[start_pos:match.end(1) + 1]
|
||||
return k
|
||||
# XXX The following should skip matching quotes (' or ")
|
||||
# As a shortcut way to exit, this isn't so bad, but shouldn't
|
||||
# be used to locate the actual end of the start tag since the
|
||||
# < or > characters may be embedded in an attribute value.
|
||||
match = endbracket.search(rawdata, i+1)
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start(0)
|
||||
# Now parse the data between i+1 and j into a tag and attrs
|
||||
attrs = []
|
||||
if rawdata[i:i+2] == '<>':
|
||||
# SGML shorthand: <> == <last open tag seen>
|
||||
k = j
|
||||
tag = self.lasttag
|
||||
else:
|
||||
match = tagfind.match(rawdata, i+1)
|
||||
if not match:
|
||||
self.error('unexpected call to parse_starttag')
|
||||
k = match.end(0)
|
||||
tag = rawdata[i+1:k].lower()
|
||||
self.lasttag = tag
|
||||
while k < j:
|
||||
match = attrfind.match(rawdata, k)
|
||||
if not match: break
|
||||
attrname, rest, attrvalue = match.group(1, 2, 3)
|
||||
if not rest:
|
||||
attrvalue = attrname
|
||||
else:
|
||||
if (attrvalue[:1] == "'" == attrvalue[-1:] or
|
||||
attrvalue[:1] == '"' == attrvalue[-1:]):
|
||||
# strip quotes
|
||||
attrvalue = attrvalue[1:-1]
|
||||
attrvalue = self.entity_or_charref.sub(
|
||||
self._convert_ref, attrvalue)
|
||||
attrs.append((attrname.lower(), attrvalue))
|
||||
k = match.end(0)
|
||||
if rawdata[j] == '>':
|
||||
j = j+1
|
||||
self.__starttag_text = rawdata[start_pos:j]
|
||||
self.finish_starttag(tag, attrs)
|
||||
return j
|
||||
|
||||
# Internal -- convert entity or character reference
|
||||
def _convert_ref(self, match):
|
||||
if match.group(2):
|
||||
return self.convert_charref(match.group(2)) or \
|
||||
'&#%s%s' % match.groups()[1:]
|
||||
elif match.group(3):
|
||||
return self.convert_entityref(match.group(1)) or \
|
||||
'&%s;' % match.group(1)
|
||||
else:
|
||||
return '&%s' % match.group(1)
|
||||
|
||||
# Internal -- parse endtag
|
||||
def parse_endtag(self, i):
|
||||
rawdata = self.rawdata
|
||||
match = endbracket.search(rawdata, i+1)
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start(0)
|
||||
tag = rawdata[i+2:j].strip().lower()
|
||||
if rawdata[j] == '>':
|
||||
j = j+1
|
||||
self.finish_endtag(tag)
|
||||
return j
|
||||
|
||||
# Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
|
||||
def finish_shorttag(self, tag, data):
|
||||
self.finish_starttag(tag, [])
|
||||
self.handle_data(data)
|
||||
self.finish_endtag(tag)
|
||||
|
||||
# Internal -- finish processing of start tag
|
||||
# Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
|
||||
def finish_starttag(self, tag, attrs):
|
||||
try:
|
||||
method = getattr(self, 'start_' + tag)
|
||||
except AttributeError:
|
||||
try:
|
||||
method = getattr(self, 'do_' + tag)
|
||||
except AttributeError:
|
||||
self.unknown_starttag(tag, attrs)
|
||||
return -1
|
||||
else:
|
||||
self.handle_starttag(tag, method, attrs)
|
||||
return 0
|
||||
else:
|
||||
self.stack.append(tag)
|
||||
self.handle_starttag(tag, method, attrs)
|
||||
return 1
|
||||
|
||||
# Internal -- finish processing of end tag
|
||||
def finish_endtag(self, tag):
|
||||
if not tag:
|
||||
found = len(self.stack) - 1
|
||||
if found < 0:
|
||||
self.unknown_endtag(tag)
|
||||
return
|
||||
else:
|
||||
if tag not in self.stack:
|
||||
try:
|
||||
method = getattr(self, 'end_' + tag)
|
||||
except AttributeError:
|
||||
self.unknown_endtag(tag)
|
||||
else:
|
||||
self.report_unbalanced(tag)
|
||||
return
|
||||
found = len(self.stack)
|
||||
for i in range(found):
|
||||
if self.stack[i] == tag: found = i
|
||||
while len(self.stack) > found:
|
||||
tag = self.stack[-1]
|
||||
try:
|
||||
method = getattr(self, 'end_' + tag)
|
||||
except AttributeError:
|
||||
method = None
|
||||
if method:
|
||||
self.handle_endtag(tag, method)
|
||||
else:
|
||||
self.unknown_endtag(tag)
|
||||
del self.stack[-1]
|
||||
|
||||
# Overridable -- handle start tag
|
||||
def handle_starttag(self, tag, method, attrs):
|
||||
method(attrs)
|
||||
|
||||
# Overridable -- handle end tag
|
||||
def handle_endtag(self, tag, method):
|
||||
method()
|
||||
|
||||
# Example -- report an unbalanced </...> tag.
|
||||
def report_unbalanced(self, tag):
|
||||
if self.verbose:
|
||||
print('*** Unbalanced </' + tag + '>')
|
||||
print('*** Stack:', self.stack)
|
||||
|
||||
def convert_charref(self, name):
|
||||
"""Convert character reference, may be overridden."""
|
||||
try:
|
||||
n = int(name)
|
||||
except ValueError:
|
||||
return
|
||||
if not 0 <= n <= 127:
|
||||
return
|
||||
return self.convert_codepoint(n)
|
||||
|
||||
def convert_codepoint(self, codepoint):
|
||||
return chr(codepoint)
|
||||
|
||||
def handle_charref(self, name):
|
||||
"""Handle character reference, no need to override."""
|
||||
replacement = self.convert_charref(name)
|
||||
if replacement is None:
|
||||
self.unknown_charref(name)
|
||||
else:
|
||||
self.handle_data(replacement)
|
||||
|
||||
# Definition of entities -- derived classes may override
|
||||
entitydefs = \
|
||||
{'lt': '<', 'gt': '>', 'amp': '&', 'quot': '"', 'apos': '\''}
|
||||
|
||||
def convert_entityref(self, name):
|
||||
"""Convert entity references.
|
||||
|
||||
As an alternative to overriding this method; one can tailor the
|
||||
results by setting up the self.entitydefs mapping appropriately.
|
||||
"""
|
||||
table = self.entitydefs
|
||||
if name in table:
|
||||
return table[name]
|
||||
else:
|
||||
return
|
||||
|
||||
def handle_entityref(self, name):
|
||||
"""Handle entity references, no need to override."""
|
||||
replacement = self.convert_entityref(name)
|
||||
if replacement is None:
|
||||
self.unknown_entityref(name)
|
||||
else:
|
||||
self.handle_data(replacement)
|
||||
|
||||
# Example -- handle data, should be overridden
|
||||
def handle_data(self, data):
|
||||
pass
|
||||
|
||||
# Example -- handle comment, could be overridden
|
||||
def handle_comment(self, data):
|
||||
pass
|
||||
|
||||
# Example -- handle declaration, could be overridden
|
||||
def handle_decl(self, decl):
|
||||
pass
|
||||
|
||||
# Example -- handle processing instruction, could be overridden
|
||||
def handle_pi(self, data):
|
||||
pass
|
||||
|
||||
# To be overridden -- handlers for unknown objects
|
||||
def unknown_starttag(self, tag, attrs): pass
|
||||
def unknown_endtag(self, tag): pass
|
||||
def unknown_charref(self, ref): pass
|
||||
def unknown_entityref(self, ref): pass
|
||||
|
||||
|
||||
class TestSGMLParser(SGMLParser):
|
||||
|
||||
def __init__(self, verbose=0):
|
||||
self.testdata = ""
|
||||
SGMLParser.__init__(self, verbose)
|
||||
|
||||
def handle_data(self, data):
|
||||
self.testdata = self.testdata + data
|
||||
if len(repr(self.testdata)) >= 70:
|
||||
self.flush()
|
||||
|
||||
def flush(self):
|
||||
data = self.testdata
|
||||
if data:
|
||||
self.testdata = ""
|
||||
print('data:', repr(data))
|
||||
|
||||
def handle_comment(self, data):
|
||||
self.flush()
|
||||
r = repr(data)
|
||||
if len(r) > 68:
|
||||
r = r[:32] + '...' + r[-32:]
|
||||
print('comment:', r)
|
||||
|
||||
def unknown_starttag(self, tag, attrs):
|
||||
self.flush()
|
||||
if not attrs:
|
||||
print('start tag: <' + tag + '>')
|
||||
else:
|
||||
print('start tag: <' + tag, end=' ')
|
||||
for name, value in attrs:
|
||||
print(name + '=' + '"' + value + '"', end=' ')
|
||||
print('>')
|
||||
|
||||
def unknown_endtag(self, tag):
|
||||
self.flush()
|
||||
print('end tag: </' + tag + '>')
|
||||
|
||||
def unknown_entityref(self, ref):
|
||||
self.flush()
|
||||
print('*** unknown entity ref: &' + ref + ';')
|
||||
|
||||
def unknown_charref(self, ref):
|
||||
self.flush()
|
||||
print('*** unknown char ref: &#' + ref + ';')
|
||||
|
||||
def unknown_decl(self, data):
|
||||
self.flush()
|
||||
print('*** unknown decl: [' + data + ']')
|
||||
|
||||
def close(self):
|
||||
SGMLParser.close(self)
|
||||
self.flush()
|
||||
|
||||
|
||||
def test(args = None):
|
||||
import sys
|
||||
|
||||
if args is None:
|
||||
args = sys.argv[1:]
|
||||
|
||||
if args and args[0] == '-s':
|
||||
args = args[1:]
|
||||
klass = SGMLParser
|
||||
else:
|
||||
klass = TestSGMLParser
|
||||
|
||||
if args:
|
||||
file = args[0]
|
||||
else:
|
||||
file = 'test.html'
|
||||
|
||||
if file == '-':
|
||||
f = sys.stdin
|
||||
else:
|
||||
try:
|
||||
f = open(file, 'r')
|
||||
except IOError as msg:
|
||||
print(file, ":", msg)
|
||||
sys.exit(1)
|
||||
|
||||
data = f.read()
|
||||
if f is not sys.stdin:
|
||||
f.close()
|
||||
|
||||
x = klass()
|
||||
for c in data:
|
||||
x.feed(c)
|
||||
x.close()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
test()
|
||||
Loading…
Reference in New Issue
Block a user