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="3"
SOURCE_URI="https://files.pythonhosted.org/packages/source/h/html5-parser/html5-parser-$portVersion.tar.gz"
CHECKSUM_SHA256="f9294418c0da95c2d5facc19d3dc32941093a6b8e3b3e4b36cc7b5a1697fbca4"
SOURCE_DIR="html5-parser-$portVersion"

ARCHITECTURES="all !x86_gcc2"
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_VERSIONS=(3.10)

for i in "${!PYTHON_VERSIONS[@]}"; do
	pythonVersion=${PYTHON_VERSIONS[$i]}
	pythonPackage=python${pythonVersion//.}

	eval "PROVIDES_$pythonPackage=\"
		${portName}_$pythonPackage = $portVersion
		\""
	if [ "$targetArchitecture" = "x86_gcc2" ]; then
		eval "PROVIDES_$pythonPackage+=\"
			html5_parser_$pythonPackage = $portVersion
			\""
	fi
	eval "REQUIRES_$pythonPackage=\"
		haiku$secondaryArchSuffix
		chardet_$pythonPackage
		lxml${secondaryArchSuffix}_$pythonPackage
		lib:libpython$pythonVersion$secondaryArchSuffix
		\""

	BUILD_REQUIRES+="
		setuptools_$pythonPackage
		"
	BUILD_PREREQUIRES+="
		cmd:python$pythonVersion
		"
	TEST_REQUIRES+="
		${portName}_$pythonPackage
		beautifulsoup4_$pythonPackage
		chardet_$pythonPackage
		lxml${secondaryArchSuffix}_$pythonPackage
		"
done


BUILD()
{
	for i in "${!PYTHON_VERSIONS[@]}"; do
		pythonVersion=${PYTHON_VERSIONS[$i]}
		pythonPackage=python${pythonVersion//.}

		rm -rf "$sourceDir"-$pythonPackage
		cp -a "$sourceDir" "$sourceDir"-$pythonPackage
		cd "$sourceDir"-$pythonPackage

		python=python$pythonVersion
		$python setup.py build
	done
}


INSTALL()
{
	for i in "${!PYTHON_VERSIONS[@]}"; do
		pythonVersion=${PYTHON_VERSIONS[$i]}
		pythonPackage=python${pythonVersion//.}

		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
}



# Reference results:
# Ran 28 tests in 1.363s
# OK (skipped=1)
TEST()
{
	for i in "${!PYTHON_VERSIONS[@]}"; do
		pythonVersion=${PYTHON_VERSIONS[$i]}
		pythonPackage=python${pythonVersion//.}

		cd "$sourceDir"-$pythonPackage

		python=python$pythonVersion
		$python run_tests.py
	done
}