hi there, this is WIP update for py-html5lib that is needed by more and more projects.
it is WIP mostly because thousansds of tests fail, but perhaps fellow pythonistas could give a hand with it... -f -- the current death rate? one per person, of course.
diff -x CVS -urNP /usr/ports/devel/py-html5lib/Makefile /home/f/src/mystuff/devel/py-html5lib/Makefile --- /usr/ports/devel/py-html5lib/Makefile Fri Feb 1 19:07:06 2013 +++ /home/f/src/mystuff/devel/py-html5lib/Makefile Thu Mar 7 22:34:43 2013 @@ -1,29 +1,31 @@ # $OpenBSD: Makefile,v 1.6 2011/09/16 09:24:55 espie Exp $ -COMMENT= HTML parser/tokeniser based for HTML5 +COMMENT = HTML parser/tokeniser based for HTML5 -MODPY_EGG_VERSION= 0.11.1 -DISTNAME= html5lib-${MODPY_EGG_VERSION} -PKGNAME= py-${DISTNAME} -REVISION = 3 -CATEGORIES= devel www textproc -EXTRACT_SUFX= .zip +MODPY_EGG_VERSION = 0.95 +DISTNAME = html5lib-${MODPY_EGG_VERSION} +PKGNAME = py-${DISTNAME} +CATEGORIES = devel www textproc -HOMEPAGE= http://code.google.com/p/html5lib/ -MASTER_SITES= http://html5lib.googlecode.com/files/ +HOMEPAGE = http://code.google.com/p/html5lib/ +MAINTAINER = frantisek holop <min...@obiit.org> -MAINTAINER= Damien Miller <d...@openbsd.org> - # MIT -PERMIT_PACKAGE_CDROM= Yes -PERMIT_PACKAGE_FTP= Yes -PERMIT_DISTFILES_CDROM= Yes -PERMIT_DISTFILES_FTP= Yes +PERMIT_PACKAGE_CDROM = Yes +PERMIT_PACKAGE_FTP = Yes +PERMIT_DISTFILES_FTP = Yes -PKG_ARCH= * -MODULES= lang/python -MODPY_SETUPTOOLS= Yes +MASTER_SITES = ${MASTER_SITE_PYPI:=h/html5lib/} -REGRESS_DEPENDS= devel/py-simplejson +MODULES = lang/python +MODPY_SETUPTOOLS = Yes + +REGRESS_DEPEND = devel/py-nose + +do-regress: fake +# cd ${WRKSRC} && env LC_CTYPE=en_US.UTF-8 \ +# PYTHONPATH=${WRKINST}${MODPY_SITEPKG} ${MODPY_BIN} nosetests -v + cd ${WRKSRC} && ${MAKE_ENV} \ + PYTHONPATH=${WRKINST}${MODPY_SITEPKG} nosetests -v .include <bsd.port.mk> diff -x CVS -urNP /usr/ports/devel/py-html5lib/distinfo /home/f/src/mystuff/devel/py-html5lib/distinfo --- /usr/ports/devel/py-html5lib/distinfo Fri Feb 1 19:07:20 2013 +++ /home/f/src/mystuff/devel/py-html5lib/distinfo Wed Dec 19 16:35:28 2012 @@ -1,5 +1,2 @@ -MD5 (html5lib-0.11.1.zip) = 8JgfzsPWl4nxL1J3nFX6KQ== -RMD160 (html5lib-0.11.1.zip) = rACXXl6osgYGUx5jEnTBqJhREMk= -SHA1 (html5lib-0.11.1.zip) = FXUGMZ5A9dlzwSjl4rgmzRvuRx4= -SHA256 (html5lib-0.11.1.zip) = 5aJste2hEBhx6joRmd5HMR915ykhWD1Be0S8/2D4dG4= -SIZE (html5lib-0.11.1.zip) = 375892 +SHA256 (html5lib-0.95.tar.gz) = pucH2csXyL8eVTcTrRSzEnSoHVwM4PziGwKTbQ79fbs= +SIZE (html5lib-0.95.tar.gz) = 222614 diff -x CVS -urNP /usr/ports/devel/py-html5lib/pkg/DESCR /home/f/src/mystuff/devel/py-html5lib/pkg/DESCR --- /usr/ports/devel/py-html5lib/pkg/DESCR Sun Jan 18 15:03:56 2009 +++ /home/f/src/mystuff/devel/py-html5lib/pkg/DESCR Sat Feb 2 00:12:26 2013 @@ -1,2 +1,9 @@ -A python based HTML parser/tokenizer based on the WHATWG HTML5 -specification for maximum compatibility with major desktop web browsers. +HTML parser designed to follow the HTML5 specification. +The parser is designed to handle all flavours of HTML and +parses invalid documents using well-defined error handling +rules compatible with the behaviour of major desktop web +browsers. + +Output is to a tree structure; the current release supports +output to DOM, ElementTree, lxml and BeautifulSoup tree formats +as well as a simple custom format. diff -x CVS -urNP /usr/ports/devel/py-html5lib/pkg/PLIST /home/f/src/mystuff/devel/py-html5lib/pkg/PLIST --- /usr/ports/devel/py-html5lib/pkg/PLIST Fri Feb 1 19:08:40 2013 +++ /home/f/src/mystuff/devel/py-html5lib/pkg/PLIST Wed Dec 19 16:36:43 2012 @@ -1,4 +1,4 @@ -@comment $OpenBSD: PLIST,v 1.1 2009/01/18 20:03:56 djm Exp $ +@comment $OpenBSD: PLIST,v 1.1.1.1 2009/01/18 20:03:56 djm Exp $ lib/python${MODPY_VERSION}/site-packages/html5lib/ lib/python${MODPY_VERSION}/site-packages/html5lib-${MODPY_EGG_VERSION}-py${MODPY_VERSION}.egg-info/ lib/python${MODPY_VERSION}/site-packages/html5lib-${MODPY_EGG_VERSION}-py${MODPY_VERSION}.egg-info/PKG-INFO @@ -18,28 +18,20 @@ lib/python${MODPY_VERSION}/site-packages/html5lib/filters/formfiller.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/filters/inject_meta_charset.py lib/python${MODPY_VERSION}/site-packages/html5lib/filters/inject_meta_charset.pyc -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/iso639codes.py -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/iso639codes.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/filters/lint.py lib/python${MODPY_VERSION}/site-packages/html5lib/filters/lint.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/filters/optionaltags.py lib/python${MODPY_VERSION}/site-packages/html5lib/filters/optionaltags.pyc -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/rfc2046.py -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/rfc2046.pyc -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/rfc3987.py -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/rfc3987.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/filters/sanitizer.py lib/python${MODPY_VERSION}/site-packages/html5lib/filters/sanitizer.pyc -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/validator.py -lib/python${MODPY_VERSION}/site-packages/html5lib/filters/validator.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/filters/whitespace.py lib/python${MODPY_VERSION}/site-packages/html5lib/filters/whitespace.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/html5parser.py lib/python${MODPY_VERSION}/site-packages/html5lib/html5parser.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/ihatexml.py +lib/python${MODPY_VERSION}/site-packages/html5lib/ihatexml.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/inputstream.py lib/python${MODPY_VERSION}/site-packages/html5lib/inputstream.pyc -lib/python${MODPY_VERSION}/site-packages/html5lib/liberalxmlparser.py -lib/python${MODPY_VERSION}/site-packages/html5lib/liberalxmlparser.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/sanitizer.py lib/python${MODPY_VERSION}/site-packages/html5lib/sanitizer.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/serializer/ @@ -49,6 +41,114 @@ lib/python${MODPY_VERSION}/site-packages/html5lib/serializer/htmlserializer.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/serializer/xhtmlserializer.py lib/python${MODPY_VERSION}/site-packages/html5lib/serializer/xhtmlserializer.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/__init__.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/__init__.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/mockParser.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/mockParser.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/runparsertests.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/runparsertests.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/runtests.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/runtests.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/support.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/support.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_encoding.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_encoding.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_formfiller.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_formfiller.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_parser.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_parser.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_parser2.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_parser2.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_sanitizer.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_sanitizer.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_serializer.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_serializer.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_stream.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_stream.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_tokenizer.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_tokenizer.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_treewalkers.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_treewalkers.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_whitespace_filter.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/test_whitespace_filter.pyc +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/encoding/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/encoding/test-yahoo-jp.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/encoding/tests1.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/encoding/tests2.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/sanitizer/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/sanitizer/tests1.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/serializer/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/serializer/core.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/serializer/injectmeta.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/serializer/optionaltags.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/serializer/options.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/serializer/whitespace.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/sniffer/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/sniffer/htmlOrFeed.json +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/contentModelFlags.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/domjs.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/entities.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/escapeFlag.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/namedEntities.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/numericEntities.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/pendingSpecChanges.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/test1.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/test2.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/test3.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/test4.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/unicodeChars.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/unicodeCharsProblematic.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tokenizer/xmlViolation.test +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/ +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/adoption01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/adoption02.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/comments01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/doctype01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/domjs-unsafe.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/entities01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/entities02.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/html5test-com.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/inbody01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/isindex.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/pending-spec-changes-plain-text-unsafe.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/pending-spec-changes.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/plain-text-unsafe.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/scriptdata01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tables01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests1.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests10.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests11.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests12.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests14.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests15.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests16.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests17.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests18.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests19.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests2.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests20.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests21.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests22.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests23.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests24.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests25.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests26.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests3.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests4.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests5.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests6.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests7.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests8.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests9.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tests_innerHTML_1.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/tricky01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/webkit01.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/testdata/tree-construction/webkit02.dat +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/tokenizertotree.py +lib/python${MODPY_VERSION}/site-packages/html5lib/tests/tokenizertotree.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/tokenizer.py lib/python${MODPY_VERSION}/site-packages/html5lib/tokenizer.pyc lib/python${MODPY_VERSION}/site-packages/html5lib/treebuilders/