cldrDict_sconscript

###
#This file is a part of the NVDA project.
#URL: http://www.nvda-project.org/
#Copyright 2018 NV Access Limited, Babbage B.V.
#This program is free software: you can redistribute it and/or modify
#it under the terms of the GNU General Public License version 2.0, as published by
#the Free Software Foundation.
#This program is distributed in the hope that it will be useful,
#but WITHOUT ANY WARRANTY; without even the implied warranty of
#MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
#This license can be found at:
#http://www.gnu.org/licenses/old-licenses/gpl-2.0.html
###

Import(
	'env', 'sourceDir', 
)

def createCLDRAnnotationsDict(sources, dest):
	import codecs
	from xml.etree import ElementTree
	from collections import OrderedDict	
	cldrDict = OrderedDict()
	for source in sources:
		tree = ElementTree.parse(source)
		for element in tree.iter("annotation"):
			if element.attrib.get("type") == "tts":
				cldrDict[element.attrib['cp']] = element.text.replace(":","")
	assert cldrDict, "cldrDict is empty"
	with codecs.open(dest, "w", "utf_8_sig", errors="replace") as dictFile:
		dictFile.write(u"symbols:\r\n")
		for pattern, description in cldrDict.iteritems():
			dictFile.write(u"{pattern}\t{description}\tsome\r\n".format(
				pattern=pattern,
				description=description
			))

cldrDictAction=env.Action(
	lambda target,source,env: createCLDRAnnotationsDict([src.path for src in source], target[0].path),
	lambda target,source,env: 'Generating %s'%target[0],
)
cldrDictBuilder=env.Builder(
	action=cldrDictAction,
	suffix='.dic',
	src_suffix='.xml',
)
env['BUILDERS']['cldrDict']=cldrDictBuilder

NVDAToCLDRLocales = {
	"af_ZA":("af",),
	"am":("am",),
	#"an":(),
	"ar":("ar",),
	"as":("as",),
	"bg":("bg",),
	"bn":("bn",),
	"ca":("ca",),
	#"ckb":(),
	"cs":("cs",),
	"da":("da",),
	"de":("de",),
	"de_CH":("de_CH",),
	"el":("el",),
	"en":("en_001","en"),
	"es":("es",),
	#"es_CO":(),
	"fa":("fa",),
	"fi":("fi",),
	"fr":("fr",),
	"ga":("ga",),
	"gl":("gl",),
	"gu":("gu",),
	"he":("he",),
	"hi":("hi",),
	"hr":("hr",),
	"hu":("hu",),
	"id":("id",),
	"is":("is",),
	"it":("it",),
	"ja":("ja",),
	"ka":("ka",),
	#"kmr":(),
	"kn":("kn",),
	"ko":("ko",),
	#"kok":(),
	"ky":("ky",),
	"lt":("lt",),
	"mk":("mk",),
	"ml":("ml",),
	"mn":("mn",),
	#"mni":(),
	"my":("my",),
	"nb_NO":("nb",),
	"ne":("ne",),
	"nl":("nl",),
	"nn_NO":("nn",),
	"pa":("pa",),
	"pl":("pl",),
	"pt_BR":("pt",),
	"pt_pt":("pt","pt_PT"),
	"ro":("ro",),
	"ru":("ru",),
	"sk":("sk",),
	"sl":("sl",),
	#"so":(),
	"sq":("sq",),
	"sr":("sr",),
	"sv":("sv",),
	"ta":("ta",),
	"te":("te",),
	"th":("th",),
	"tr":("tr",),
	"uk":("uk",),
	"vi":("vi",),
	"zh_cn":("zh",),
	"zh_hk":("zh","zh_Hant_HK"),
	"zh_tw":("zh","zh_Hant"),
}

annotationsDir = env.Dir("include/cldr-emoji-annotation/annotations")
annotationsDerivedDir = env.Dir("include/cldr-emoji-annotation/annotationsDerived")
for destLocale, sourceLocales in NVDAToCLDRLocales.iteritems():
	cldrSources = []
	# First add all annotations, then the derived ones.
	for sourceLocale in sourceLocales:
		cldrSources.append(annotationsDir.File("%s.xml" % sourceLocale))
	for sourceLocale in sourceLocales:
		cldrSources.append(annotationsDerivedDir.File("%s.xml" % sourceLocale))
	env.cldrDict(sourceDir.Dir("locale/%s" % destLocale).File("cldr.dic"), cldrSources)