def endElement(self, elem):
elem = self.lowerizeInput(elem)
e = XmlParser.endElement(self, elem)
currentElem, elemsToReopen = e.onElementEnd(elem)
# Determine the tag to dump
startTag, endTag = currentElem.getOdfTags(e)
if currentElem.isConflictual:
# Compute the start tag, with potential styles applied
startTag = e.getTags((currentElem,), start=True)
if currentElem.isConflictual and e.res.endswith(startTag):
# We will not dump it, it would constitute a silly empty tag.
e.res = e.res[:-len(startTag)]
else:
# Dump the end tag. But dump some additional stuff if required.
if elem in XHTML_LISTS:
if len(e.currentLists) >= 1:
# We were in an inner list. So we must close the list-item
# tag that surrounds it.
endTag = '%s</%s:list-item>' % (endTag, e.textNs)
if endTag:
e.dumpString(endTag)
if elem in IGNORABLE_TAGS:
e.ignore = False
if elemsToReopen:
e.dumpString(e.getTags(elemsToReopen, start=True))
def endElement(self, elem):
elem = self.lowerizeInput(elem)
e = XmlParser.endElement(self, elem)
elemsToReopen = e.onElementEnd(elem)
if HTML_2_ODT.has_key(elem):
# For "div" elements, we put append a carriage return.
if elem == 'div':
e.dumpString('<%s:line-break/>' % e.textNs)
e.dumpString('</%s:%s>' % (e.textNs, HTML_2_ODT[elem]))
elif elem == 'a':
e.dumpString('</%s:a>' % e.textNs)
elif elem in XHTML_LISTS:
epilogue = ''
if len(e.currentLists) >= 1:
# We were in an inner list. So we must close the list-item tag
# that surrounds it.
epilogue = '</%s:list-item>' % e.textNs
e.dumpString('</%s:list>%s' % (e.textNs, epilogue))
elif elem == 'li':
e.dumpString('</%s:list-item>' % e.textNs)
elif elem == 'table':
e.dumpString('</%s:table>' % e.tableNs)
elif elem == 'thead':
e.dumpString('</%s:table-header-rows>' % e.tableNs)
elif elem == 'tr':
e.dumpString('</%s:table-row>' % e.tableNs)
elif elem in TABLE_CELL_TAGS:
e.dumpString('</%s:table-cell>' % e.tableNs)
elif elem in IGNORABLE_TAGS:
e.ignore = False
if elemsToReopen:
e.dumpTags(elemsToReopen)
def startElement(self, elem, attrs):
elem, attrs = self.lowerizeInput(elem, attrs)
e = XmlParser.startElement(self, elem, attrs)
currentElem = e.onElementStart(elem, attrs)
odfTag = currentElem.getOdfTag(e)
if HTML_2_ODT.has_key(elem):
e.dumpStyledElement(currentElem, odfTag, attrs)
elif elem == 'a':
e.dumpString('<%s %s:type="simple"' % (odfTag, e.linkNs))
if attrs.has_key('href'):
e.dumpString(' %s:href="%s"' % (e.linkNs, attrs['href']))
e.dumpString('>')
elif elem in XHTML_LISTS:
prologue = ''
if len(e.currentLists) >= 2:
# It is a list into another list. In this case the inner list
# must be surrounded by a list-item element.
prologue = '<%s:list-item>' % e.textNs
e.dumpString('%s<%s %s:style-name="%s">' % (
prologue, odfTag, e.textNs, e.listStyles[elem]))
elif elem in ('li', 'thead', 'tr'):
e.dumpString('<%s>' % odfTag)
elif elem == 'table':
# Here we must call "dumpString" only once
e.dumpString('<%s %s:style-name="podTable">' % (odfTag, e.tableNs))
elif elem in TABLE_CELL_TAGS:
e.dumpString('<%s %s:style-name="%s"' % \
(odfTag, e.tableNs, DEFAULT_ODT_STYLES[elem]))
if attrs.has_key('colspan'):
e.dumpString(' %s:number-columns-spanned="%s"' % \
(e.tableNs, attrs['colspan']))
e.dumpString('>')
elif elem in IGNORABLE_TAGS:
e.ignore = True
def endElement(self, elem):
elem = self.lowerizeInput(elem)
e = XmlParser.endElement(self, elem)
currentElem, elemsToReopen = e.onElementEnd(elem)
# Determine the tag to dump
startTag, endTag = currentElem.getOdfTags(e)
if currentElem.isConflictual:
# Compute the start tag, with potential styles applied
startTag = e.getTags((currentElem, ), start=True)
if currentElem.isConflictual and e.res.endswith(startTag):
# We will not dump it, it would constitute a silly empty tag.
e.res = e.res[:-len(startTag)]
else:
# Dump the end tag. But dump some additional stuff if required.
if elem in XHTML_LISTS:
if len(e.currentLists) >= 1:
# We were in an inner list. So we must close the list-item
# tag that surrounds it.
endTag = '%s</%s:list-item>' % (endTag, e.textNs)
if endTag:
e.dumpString(endTag)
if elem in IGNORABLE_TAGS:
e.ignore = False
if elemsToReopen:
e.dumpString(e.getTags(elemsToReopen, start=True))
def startElement(self, elem, attrs):
elem, attrs = self.lowerizeInput(elem, attrs)
e = XmlParser.startElement(self, elem, attrs)
currentElem = e.onElementStart(elem, attrs)
odfTag = currentElem.getOdfTag(e)
if HTML_2_ODT.has_key(elem):
e.dumpStyledElement(currentElem, odfTag, attrs)
elif elem == 'a':
e.dumpString('<%s %s:type="simple"' % (odfTag, e.linkNs))
if attrs.has_key('href'):
e.dumpString(' %s:href="%s"' %
(e.linkNs, escapeXml(attrs['href'])))
e.dumpString('>')
elif elem in XHTML_LISTS:
prologue = ''
if len(e.currentLists) >= 2:
# It is a list into another list. In this case the inner list
# must be surrounded by a list-item element.
prologue = '<%s:list-item>' % e.textNs
numbering = ''
if elem == 'ol':
numbering = ' %s:continue-numbering="false"' % e.textNs
e.dumpString(
'%s<%s %s:style-name="%s"%s>' %
(prologue, odfTag, e.textNs, e.listStyles[elem], numbering))
elif elem in ('li', 'thead', 'tr'):
e.dumpString('<%s>' % odfTag)
elif elem == 'table':
# Here we must call "dumpString" only once
table = e.currentTables[-1]
e.dumpString('<%s %s:name="%s" %s:style-name="podTable">' % \
(odfTag, e.tableNs, table.name, e.tableNs))
elif elem in TABLE_CELL_TAGS:
e.dumpString('<%s %s:style-name="%s"' % \
(odfTag, e.tableNs, DEFAULT_ODT_STYLES[elem]))
if attrs.has_key('colspan'):
e.dumpString(' %s:number-columns-spanned="%s"' % \
(e.tableNs, attrs['colspan']))
e.dumpString('>')
elif elem == 'img':
style = None
if attrs.has_key('style'): style = attrs['style']
imgCode = e.renderer.importDocument(at=attrs['src'],
wrapInPara=False,
style=style)
e.dumpString(imgCode)
elif elem in IGNORABLE_TAGS:
e.ignore = True
def startElement(self, elem, attrs):
elem, attrs = self.lowerizeInput(elem, attrs)
e = XmlParser.startElement(self, elem, attrs)
currentElem = e.onElementStart(elem, attrs)
odfTag = currentElem.getOdfTag(e)
if HTML_2_ODT.has_key(elem):
e.dumpStyledElement(currentElem, odfTag, attrs)
elif elem == 'a':
e.dumpString('<%s %s:type="simple"' % (odfTag, e.linkNs))
if attrs.has_key('href'):
e.dumpString(' %s:href="%s"' % (e.linkNs,
escapeXml(attrs['href'])))
e.dumpString('>')
elif elem in XHTML_LISTS:
prologue = ''
if len(e.currentLists) >= 2:
# It is a list into another list. In this case the inner list
# must be surrounded by a list-item element.
prologue = '<%s:list-item>' % e.textNs
numbering = ''
if elem == 'ol':
numbering = ' %s:continue-numbering="false"' % e.textNs
e.dumpString('%s<%s %s:style-name="%s"%s>' % (
prologue, odfTag, e.textNs, e.listStyles[elem], numbering))
elif elem in ('li', 'thead', 'tr'):
e.dumpString('<%s>' % odfTag)
elif elem == 'table':
# Here we must call "dumpString" only once
table = e.currentTables[-1]
e.dumpString('<%s %s:name="%s" %s:style-name="podTable">' % \
(odfTag, e.tableNs, table.name, e.tableNs))
elif elem in TABLE_CELL_TAGS:
e.dumpString('<%s %s:style-name="%s"' % \
(odfTag, e.tableNs, DEFAULT_ODT_STYLES[elem]))
if attrs.has_key('colspan'):
e.dumpString(' %s:number-columns-spanned="%s"' % \
(e.tableNs, attrs['colspan']))
e.dumpString('>')
elif elem == 'img':
style = None
if attrs.has_key('style'): style = attrs['style']
imgCode = e.renderer.importDocument(at=attrs['src'],
wrapInPara=False, style=style)
e.dumpString(imgCode)
elif elem in IGNORABLE_TAGS:
e.ignore = True
def __init__(self, env, caller=None):
XmlParser.__init__(self, env, caller)
def __init__(self, env=None, caller=None):
if not env: env = OdfEnvironment()
XmlParser.__init__(self, env, caller)
def characters(self, content):
e = XmlParser.characters(self, content)
if not e.ignore:
e.currentContent += content
def characters(self, content):
e = XmlParser.characters(self, content)
if not e.ignore:
e.currentContent += content
def __init__(self, env, caller=None):
XmlParser.__init__(self, env, caller)
def endDocument(self):
self.res = ' '.join(self.res)
return XmlParser.endDocument(self)
def startDocument(self):
XmlParser.startDocument(self)
self.res = []
def endDocument(self):
self.res = ' '.join(self.res)
return XmlParser.endDocument(self)
def startDocument(self):
XmlParser.startDocument(self)
self.res = []
def characters(self, content):
e = XmlParser.characters(self, content)
if e.ignore: return
e.currentContent += WhitespaceCruncher.crunch(content, e.currentContent)
