mirror of
https://github.com/gentoo-mirror/gentoo.git
synced 2026-07-29 22:28:08 -07:00
dev-python/feedparser: Clean old versions up
This commit is contained in:
@@ -1,78 +0,0 @@
|
||||
From 812793c07d3202d3f5bc39091aec2e7071d000c8 Mon Sep 17 00:00:00 2001
|
||||
From: Sebastian Pipping <sebastian@pipping.org>
|
||||
Date: Sun, 1 Jan 2012 19:30:57 +0100
|
||||
Subject: [PATCH] Use shipped sgmllib for Python 3.x
|
||||
|
||||
---
|
||||
feedparser/feedparser.py | 19 +++----------------
|
||||
setup.py | 2 +-
|
||||
2 files changed, 4 insertions(+), 17 deletions(-)
|
||||
|
||||
diff --git a/feedparser/feedparser.py b/feedparser/feedparser.py
|
||||
index 8275c29..9a8a053 100644
|
||||
--- a/feedparser/feedparser.py
|
||||
+++ b/feedparser/feedparser.py
|
||||
@@ -204,17 +204,9 @@ else:
|
||||
try:
|
||||
import sgmllib
|
||||
except ImportError:
|
||||
- # This is probably Python 3, which doesn't include sgmllib anymore
|
||||
- _SGML_AVAILABLE = 0
|
||||
+ import _feedparser_sgmllib as sgmllib
|
||||
|
||||
- # Mock sgmllib enough to allow subclassing later on
|
||||
- class sgmllib(object):
|
||||
- class SGMLParser(object):
|
||||
- def goahead(self, i):
|
||||
- pass
|
||||
- def parse_starttag(self, i):
|
||||
- pass
|
||||
-else:
|
||||
+if True:
|
||||
_SGML_AVAILABLE = 1
|
||||
|
||||
# sgmllib defines a number of module-level regular expressions that are
|
||||
@@ -2520,9 +2512,6 @@ class _RelativeURIResolver(_BaseHTMLProcessor):
|
||||
_BaseHTMLProcessor.unknown_starttag(self, tag, attrs)
|
||||
|
||||
def _resolveRelativeURIs(htmlSource, baseURI, encoding, _type):
|
||||
- if not _SGML_AVAILABLE:
|
||||
- return htmlSource
|
||||
-
|
||||
p = _RelativeURIResolver(baseURI, encoding, _type)
|
||||
p.feed(htmlSource)
|
||||
return p.output()
|
||||
@@ -2803,8 +2792,6 @@ class _HTMLSanitizer(_BaseHTMLProcessor):
|
||||
|
||||
|
||||
def _sanitizeHTML(htmlSource, encoding, _type):
|
||||
- if not _SGML_AVAILABLE:
|
||||
- return htmlSource
|
||||
p = _HTMLSanitizer(encoding, _type)
|
||||
htmlSource = htmlSource.replace('<![CDATA[', '<![CDATA[')
|
||||
p.feed(htmlSource)
|
||||
@@ -3890,7 +3877,7 @@ def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, refer
|
||||
result['bozo'] = 1
|
||||
result['bozo_exception'] = feedparser.exc or e
|
||||
use_strict_parser = 0
|
||||
- if not use_strict_parser and _SGML_AVAILABLE:
|
||||
+ if not use_strict_parser:
|
||||
feedparser = _LooseFeedParser(baseuri, baselang, 'utf-8', entities)
|
||||
feedparser.feed(data.decode('utf-8', 'replace'))
|
||||
result['feed'] = feedparser.feeddata
|
||||
diff --git a/setup.py b/setup.py
|
||||
index a4a60fe..8c15451 100644
|
||||
--- a/setup.py
|
||||
+++ b/setup.py
|
||||
@@ -16,7 +16,7 @@ setup(
|
||||
download_url = 'http://code.google.com/p/feedparser/',
|
||||
platforms = ['POSIX', 'Windows'],
|
||||
package_dir = {'': 'feedparser'},
|
||||
- py_modules = ['feedparser'],
|
||||
+ py_modules = ['feedparser', '_feedparser_sgmllib'],
|
||||
keywords = ['atom', 'cdf', 'feed', 'parser', 'rdf', 'rss'],
|
||||
classifiers = [
|
||||
'Development Status :: 5 - Production/Stable',
|
||||
--
|
||||
1.7.8.1
|
||||
|
||||
@@ -1,32 +0,0 @@
|
||||
From 20a32910f4a521788ba93a8c809cf0db702bed5b Mon Sep 17 00:00:00 2001
|
||||
From: Kurt McKee <contactme@kurtmckee.org>
|
||||
Date: Mon, 17 Dec 2012 10:41:13 -0600
|
||||
Subject: [PATCH] Fix chardet support in Python 3
|
||||
|
||||
Fixes issue 384.
|
||||
Thanks to Google user Arfrever.TFA for reporting this!
|
||||
---
|
||||
NEWS | 1 +
|
||||
feedparser/feedparser.py | 6 +++++-
|
||||
2 files changed, 6 insertions(+), 1 deletion(-)
|
||||
|
||||
diff --git a/feedparser/feedparser.py b/feedparser/feedparser.py
|
||||
index c78e6a3..e977ae8 100644
|
||||
--- a/feedparser/feedparser.py
|
||||
+++ b/feedparser/feedparser.py
|
||||
@@ -3766,7 +3766,11 @@ def convert_to_utf8(http_headers, data):
|
||||
chardet_encoding = None
|
||||
tried_encodings = []
|
||||
if chardet:
|
||||
- chardet_encoding = unicode(chardet.detect(data)['encoding'] or '', 'ascii', 'ignore')
|
||||
+ chardet_encoding = chardet.detect(data)['encoding']
|
||||
+ if not chardet_encoding:
|
||||
+ chardet_encoding = ''
|
||||
+ if not isinstance(chardet_encoding, unicode):
|
||||
+ chardet_encoding = unicode(chardet_encoding, 'ascii', 'ignore')
|
||||
# try: HTTP encoding, declared XML encoding, encoding sniffed from BOM
|
||||
for proposed_encoding in (rfc3023_encoding, xml_encoding, bom_encoding,
|
||||
chardet_encoding, u'utf-8', u'windows-1252', u'iso-8859-2'):
|
||||
--
|
||||
1.8.5.5
|
||||
|
||||
Reference in New Issue
Block a user