SUMMARY="Fast C based HTML 5 parsing for python"
DESCRIPTION="A fast implementation of the HTML 5 parsing spec for Python. \
Parsing is done in C using a variant of the gumbo parser. The gumbo parse \
tree is then transformed into an lxml tree, also in C, yielding parse times \
that can be a thirtieth of the html5lib parse times. That is a speedup of \
30x. This differs, for instance, from the gumbo python bindings, where the \
initial parsing is done in C but the transformation into the final tree \
is done in python."
HOMEPAGE="https://html5-parser.readthedocs.io/
https://pypi.python.org/pypi/html5-parser/"
COPYRIGHT="2017 Kovid Goyal
2010, 2011 Google Inc.
2015-2016 Kevin B. Hendricks, Stratford Ontario
2008-2009 Bjoern Hoehrmann"
LICENSE="Apache v2"
REVISION="1"
SOURCE_URI="https://files.pythonhosted.org/packages/source/h/html5-parser/html5-parser-$portVersion.tar.gz"
CHECKSUM_SHA256="b1ead2784c69cee5d481eb6d75587cc5ea08fc292b127ae08afe7771a6fba101"
SOURCE_DIR="html5-parser-$portVersion"
ARCHITECTURES="!x86_gcc2 x86 x86_64"
SECONDARY_ARCHITECTURES="x86"
PROVIDES="
html5_parser$secondaryArchSuffix = $portVersion
"
REQUIRES="
haiku$secondaryArchSuffix
"
BUILD_REQUIRES="
haiku${secondaryArchSuffix}_devel
devel:libxml2$secondaryArchSuffix
"
BUILD_PREREQUIRES="
cmd:gcc$secondaryArchSuffix
cmd:pkg_config$secondaryArchSuffix
"
PYTHON_PACKAGES=()
PYTHON_VERSIONS=()
PYTHON_LIBSUFFIXES=()
# We don't have python2 for secondaryArch
if [ -z "$secondaryArchSuffix" ]; then
PYTHON_PACKAGES+=(python)
PYTHON_VERSIONS+=(2.7)
PYTHON_LIBSUFFIXES+=("")
BUILD_REQUIRES+="
setuptools_python
"
BUILD_PREREQUIRES+="
cmd:python2
"
fi
# gcc2 does not support the flags passed by python3
if [ "$effectiveTargetArchitecture" != x86_gcc2 ]; then
PYTHON_PACKAGES+=(python3)
PYTHON_VERSIONS+=(3.7)
PYTHON_LIBSUFFIXES+=(m)
BUILD_REQUIRES+="
setuptools_python3
"
BUILD_PREREQUIRES+="
cmd:python3
"
fi
for i in "${!PYTHON_PACKAGES[@]}"; do
pythonPackage=${PYTHON_PACKAGES[i]}
pythonVersion=${PYTHON_VERSIONS[$i]}
pythonLibSuffix=${PYTHON_LIBSUFFIXES[$i]}
eval "PROVIDES_$pythonPackage=\"
${portName}_$pythonPackage = $portVersion
\""
eval "REQUIRES_$pythonPackage=\"
haiku$secondaryArchSuffix
chardet_$pythonPackage
lxml${secondaryArchSuffix}_$pythonPackage
lib:libpython$pythonVersion$pythonLibSuffix$secondaryArchSuffix
\""
TEST_REQUIRES+="
${portName}_$pythonPackage
beautifulsoup_$pythonPackage
chardet_$pythonPackage
lxml${secondaryArchSuffix}_$pythonPackage
"
done
if [ "$targetArchitecture" = x86_gcc2 -a -n "$secondaryArchSuffix" ]; then
PROVIDES_python3+="
html5_parser_python3 = $portVersion
"
fi
BUILD()
{
for i in "${!PYTHON_PACKAGES[@]}"; do
pythonPackage=${PYTHON_PACKAGES[i]}
pythonVersion=${PYTHON_VERSIONS[$i]}
rm -rf "$sourceDir"-$pythonPackage
cp -a "$sourceDir" "$sourceDir"-$pythonPackage
cd "$sourceDir"-$pythonPackage
python=python$pythonVersion
$python setup.py build
done
}
INSTALL()
{
for i in "${!PYTHON_PACKAGES[@]}"; do
pythonPackage=${PYTHON_PACKAGES[i]}
pythonVersion=${PYTHON_VERSIONS[$i]}
cd "$sourceDir"-$pythonPackage
python=python$pythonVersion
installLocation=$prefix/lib/$python/vendor-packages
export PYTHONPATH=$installLocation
mkdir -p "$installLocation"
$python setup.py install \
--root=/ --prefix="$prefix"
packageEntries $pythonPackage \
"$prefix"/lib/$python
done
cd "$sourceDir"
install -m 755 -d "$docDir"
install -m 644 -t "$docDir" README.rst
}
TEST()
{
for i in "${!PYTHON_PACKAGES[@]}"; do
pythonPackage=${PYTHON_PACKAGES[i]}
pythonVersion=${PYTHON_VERSIONS[$i]}
cd "$sourceDir"-$pythonPackage
python=python$pythonVersion
$python run_tests.py
done
}