/usr/share/khmerconverter/modules/unicodeConvertOdt.py is in khmerconverter 1.4-1.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | #!/usr/bin/python
# -*- coding: utf8 -*-
# Khmer Legacy fonts to Khmer Unicode Conversion
# (c) 2006 The WordForge Foundation, all rights reserved.
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public License
# as published by the Free Software Foundation; either version 2.1
# of the License, or (at your option) any later version.
#
# See the LICENSE file for more details.
#
# Developed by:
# Hok Kakada (hokkakada@khmeros.info)
# Keo Sophon (keosophon@khmeros.info)
# San Titvirak (titvirak@khmeros.info)
# Seth Chanratha (sethchanratha@khmeros.info)
#
# This module convertes an *.odt file from legacy Khmer to Unicode format
from xml.dom import minidom
from FontDataXML import FontData
import zipfile
import unicodeProcess
import unicodeReorder
import unittest
from zlib import DEFLATED
class unicodeConvertOdt:
def __init__(self):
self.CONTENTXML = 'content.xml'
self.STYLESXML = 'styles.xml'
self.convertibleStyle = {}
self.fd = FontData()
self.outputFont = "Khmer OS"
self.outputFontSize = None
def convertOdtFile(self, inputFileName, outputFileName, outputFont = None, outputFontSize = None):
"""This function convert OpenOffice.Org writer file
inputFileName: the name of file you want to convert.
outputFileName: the result file name. Default value is converted-inputFileName
outputFont: font name to override. default value is Khmer OS.
outputFontSize: a value to override font size in odt file, value = None to ignore."""
self.outputFont = outputFont
if (outputFontSize):
self.outputFontSize = str(outputFontSize) + 'pt'
if (inputFileName == outputFileName):
raise TypeError('input file and output file must be different!')
try:
# read zip file (.odt)
zipIn = zipfile.ZipFile(inputFileName, "r")
except IOError:
raise IOError('Cannot open file "' + inputFileName + '" for reading!')
if (not (self.CONTENTXML and self.STYLESXML) in zipIn.namelist()):
raise TypeError('Input file' + inputFileName + 'is not an odt file!')
try:
# create new zip file (.odt)
zipOut = zipfile.ZipFile(outputFileName, "w", DEFLATED)
except IOError:
raise IOError('Cannot open file "' + outputFileName + '" for writing!')
zipOut.debug = 3
for file in zipIn.namelist():
fdata = zipIn.read(file)
if (file == self.CONTENTXML):
# read data to contentXml for later processing.
contentXml = fdata
continue
elif (file == self.STYLESXML):
fdata = self.processStyle(fdata)
zipOut.writestr(file, fdata)
# process the content.xml only after already read the styles.xml.
fdata = self.processContent(contentXml)
zipOut.writestr(self.CONTENTXML, fdata)
zipOut.close()
zipIn.close()
def processContent(self, xmldata):
"""change font name and size, convert data to unicode in xmldata
@param xmldata: xml string to parse."""
self.xmldoc = minidom.parseString(xmldata)
officeNode = self.xmldoc.getElementsByTagName('office:text')
officeDocContentNode = self.xmldoc.getElementsByTagName('office:document-content')
# go through node, replace font, and convert data to unicode.
self.goThru(officeDocContentNode, self.replaceFont)
self.goThru(officeNode, self.convertIfLegacy)
return self.xmldoc.toxml('utf-8')
def processStyle(self, xmldata):
"""change font name and size, convert data to unicode in xmldata
@param xmldata: xml string to parse."""
self.xmldoc = minidom.parseString(xmldata)
officeDocStylesNode = self.xmldoc.getElementsByTagName('office:document-styles')
# go through node, replace font, and convert data to unicode.
self.goThru(officeDocStylesNode, self.replaceFont)
self.goThru(officeDocStylesNode, self.convertIfLegacy)
return self.xmldoc.toxml('utf-8')
def goThru (self, nodelist, function):
"""go through nodelist and call function with child node as argument.
@param nodelist: dom's node list.
@param function: function to call, child argument will be provided by goThru."""
for node in nodelist:
if node.hasChildNodes():
for child in node.childNodes:
function(child)
self.goThru (node.childNodes, function)
def replaceFont(self, node):
"""look for node which has "style:font-name" attribute and change its value to fontName."""
if (not hasattr(node, "getAttribute")):
return
fontName = node.getAttribute('style:font-name')
fontType = None
if (fontName):
try:
fontType = self.fd.typeForFontname(fontName)
except:
pass
if (fontType and hasattr(node.parentNode, "getAttribute")):
# add name to convertible list
self.convertibleStyle[unicode(node.parentNode.getAttribute('style:name'))] = fontType
node.removeAttribute('style:font-name')
node.setAttribute('style:font-name-complex', self.outputFont)
if (self.outputFontSize):
node.setAttribute('style:font-size-complex', self.outputFontSize)
styleName = node.getAttribute('style:name')
if (styleName):
# if node's parent style is also convertible, node is also convertible.
# search in child if child also has style:font-name (which will override parent)
# then will not add to convertible list.
if node.hasChildNodes():
for child in node.childNodes:
if (child.hasAttribute('style:font-name')) and (hasattr(child, "getAttribute")):
fontName = child.getAttribute('style:font-name')
try:
fontType = self.fd.typeForFontname(fontName)
except:
return
parentStyleName = node.getAttribute('style:parent-style-name')
if self.convertibleStyle.has_key(parentStyleName):
# add to convertible style
self.convertibleStyle[styleName] = self.convertibleStyle[parentStyleName]
try:
fontType = self.fd.typeForFontname(styleName)
except:
return
self.convertibleStyle[styleName] = fontType
node.setAttribute('style:name', self.outputFont)
node.setAttribute('svg:font-family', self.outputFont)
def convertIfLegacy(self, node):
"""look the node for information of legacy font and convert to unicode, otherwise return False.
@param node: node to look to and convert if necessary."""
if (not node.nodeValue):
return False
if (not (hasattr(node, "parentNode") or
hasattr(node.parentNode, "getAttribute") or
hasattr(node.parentNode, "parentNode") or
hasattr(node.parentNode.parentNode, "getAttribute"))):
return False
# if node don have font specified, but it's under parent that in convertible list
# do also convert node.
styleName = node.parentNode.getAttribute(u'text:style-name')
parentStyleName = node.parentNode.parentNode.getAttribute(u'text:style-name')
if (styleName in self.convertibleStyle):
style = styleName
elif (parentStyleName in self.convertibleStyle):
style = parentStyleName
else:
return False
# legacy font data's referal.
fontname = self.convertibleStyle[style]
sin = node.data
try:
sin = sin.encode('cp1252')
except UnicodeEncodeError:
result = u''
part = ''
for char in sin:
try:
tmpChar = char.encode('cp1252')
except UnicodeEncodeError:
if (part):
part = unicodeProcess.process(part, self.fd.legacyData(fontname))
result += unicodeReorder.reorder(part)
part = ''
result += char
else:
part += tmpChar
if (part):
part = unicodeProcess.process(part, self.fd.legacyData(fontname))
result += unicodeReorder.reorder(part)
sin = result
else:
sin = unicodeProcess.process(sin, self.fd.legacyData(fontname))
sin = unicodeReorder.reorder(sin)
newtext = self.xmldoc.createTextNode(sin) # create text of Node
node.parentNode.replaceChild(newtext, node)
class TestConvertOdt(unittest.TestCase):
def testSameFile(self):
# same file raise error
self.assertRaises(TypeError, unicodeConvertOdt().convertOdtFile, 'file1', 'file1')
def testUnreadable(self):
# assert error if file is unreadable
self.assertRaises(IOError, unicodeConvertOdt().convertOdtFile, '!@#$%^&', 'file2')
def testModifyStyle(self):
xmldata = """<?xml version="1.0" encoding="utf-8"?><office:document-styles office:version="1.0" xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0"><office:font-face-decls><style:font-face style:font-pitch="variable" style:name="Limon S1" svg:font-family="Limon S1"/></office:font-face-decls></office:document-styles>"""
modxmldata = xmldata.replace("Limon S1", "Khmer OS")
self.assertEqual(unicodeConvertOdt().processStyle(xmldata), modxmldata)
if __name__ == '__main__':
unittest.main()
|