def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
self.res = u''
self.inAnnotation = False # Are we parsing an annotation ?
self.textEncountered = False # Within an annotation, have we already
# met a text ?
self.ignore = False # Must we avoid dumping the current tag/content
def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
self.res = ""
self.inAnnotation = False # Are we parsing an annotation ?
self.textEncountered = False # Within an annotation, have we already
# met a text ?
self.ignore = False # Must we avoid dumping the current tag/content
def endElement(self, elem):
e = self.env
if elem == '%s:annotation' % e.ns(e.NS_OFFICE):
self.inAnnotation = False
self.ignore = False
if not self.ignore:
self.res += '</%s>' % elem
OdfParser.endElement(self, elem)
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
ns = e.onStartElement()
officeNs = ns[e.NS_OFFICE]
textNs = ns[e.NS_TEXT]
if elem in e.ignorableElements:
e.state = e.IGNORING
elif elem == ('%s:annotation' % officeNs):
e.state = e.READING_STATEMENT
elif (elem == ('%s:change-start' % textNs)) or \
(elem == ('%s:conditional-text' % textNs)):
e.state = e.READING_EXPRESSION
e.exprHasStyle = False
else:
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
if elem in e.impactableElements:
if e.mode == e.ADD_IN_SUBBUFFER:
e.addSubBuffer()
e.currentBuffer.addElement(e.currentElem.name)
e.currentBuffer.dumpStartElement(elem, attrs)
elif e.state == e.READING_STATEMENT:
pass
elif e.state == e.READING_EXPRESSION:
if (elem == ('%s:span' % textNs)) and \
not e.currentContent.strip():
e.currentBuffer.dumpStartElement(elem, attrs)
e.exprHasStyle = True
e.manageInserts()
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
ns = e.onStartElement()
officeNs = ns[e.NS_OFFICE]
textNs = ns[e.NS_TEXT]
if elem in e.ignorableElements:
e.state = e.IGNORING
elif elem == ('%s:annotation' % officeNs):
e.state = e.READING_STATEMENT
elif (elem == ('%s:change-start' % textNs)) or \
(elem == ('%s:conditional-text' % textNs)):
e.state = e.READING_EXPRESSION
e.exprHasStyle = False
else:
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
if elem in e.impactableElements:
if e.mode == e.ADD_IN_SUBBUFFER:
e.addSubBuffer()
e.currentBuffer.addElement(e.currentElem.name)
e.currentBuffer.dumpStartElement(elem, attrs)
elif e.state == e.READING_STATEMENT:
pass
elif e.state == e.READING_EXPRESSION:
if (elem == ('%s:span' % textNs)) and \
not e.currentContent.strip():
e.currentBuffer.dumpStartElement(elem, attrs)
e.exprHasStyle = True
e.manageInserts()
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
self.styleTag = '%s:style' % e.ns(e.NS_STYLE)
if elem == self.styleTag:
e.state = PARSING_STYLE
nameAttr = '%s:name' % e.ns(e.NS_STYLE)
familyAttr = '%s:family' % e.ns(e.NS_STYLE)
classAttr = '%s:class' % e.ns(e.NS_STYLE)
displayNameAttr = '%s:display-name' % e.ns(e.NS_STYLE)
# Create the style
style = Style(name=attrs[nameAttr], family=attrs[familyAttr])
if classAttr in attrs:
style.styleClass = attrs[classAttr]
if displayNameAttr in attrs:
style.displayName = attrs[displayNameAttr]
# Record this style in the environment
e.styles[style.name] = style
e.currentStyle = style
levelKey = '%s:default-outline-level' % e.ns(e.NS_STYLE)
if levelKey in attrs and attrs[levelKey].strip():
style.outlineLevel = int(attrs[levelKey])
else:
if e.state == PARSING_STYLE:
# I am parsing tags within the style.
if elem == ('%s:text-properties' % e.ns(e.NS_STYLE)):
fontSizeKey = '%s:font-size' % e.ns(e.NS_FO)
if fontSizeKey in attrs:
e.currentStyle.setFontSize(attrs[fontSizeKey])
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
self.styleTag = '%s:style' % e.ns(e.NS_STYLE)
if elem == self.styleTag:
e.state = PARSING_STYLE
nameAttr = '%s:name' % e.ns(e.NS_STYLE)
familyAttr = '%s:family' % e.ns(e.NS_STYLE)
classAttr = '%s:class' % e.ns(e.NS_STYLE)
displayNameAttr = '%s:display-name' % e.ns(e.NS_STYLE)
# Create the style
style = Style(name=attrs[nameAttr], family=attrs[familyAttr])
if attrs.has_key(classAttr):
style.styleClass = attrs[classAttr]
if attrs.has_key(displayNameAttr):
style.displayName = attrs[displayNameAttr]
# Record this style in the environment
e.styles[style.name] = style
e.currentStyle = style
levelKey = '%s:default-outline-level' % e.ns(e.NS_STYLE)
if attrs.has_key(levelKey) and attrs[levelKey].strip():
style.outlineLevel = int(attrs[levelKey])
else:
if e.state == PARSING_STYLE:
# I am parsing tags within the style.
if elem == ('%s:text-properties' % e.ns(e.NS_STYLE)):
fontSizeKey = '%s:font-size' % e.ns(e.NS_FO)
if attrs.has_key(fontSizeKey):
e.currentStyle.setFontSize(attrs[fontSizeKey])
def endElement(self, elem):
e = OdfParser.endElement(self, elem)
if elem == "%s:annotation" % e.ns(e.NS_OFFICE):
self.inAnnotation = False
self.ignore = False
if not self.ignore:
self.res += "</%s>" % elem
def characters(self, content):
e = OdfParser.characters(self, content)
if not self.ignore:
for c in content:
if XML_SPECIAL_CHARS.has_key(c):
self.res += XML_SPECIAL_CHARS[c]
else:
self.res += c
def characters(self, content):
e = OdfParser.characters(self, content)
if not self.ignore:
for c in content:
if XML_SPECIAL_CHARS.has_key(c):
self.res += XML_SPECIAL_CHARS[c]
else:
self.res += c
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
ns = e.onStartElement()
officeNs = ns[e.NS_OFFICE]
textNs = ns[e.NS_TEXT]
tableNs = ns[e.NS_TABLE]
if elem in e.ignorableElements:
e.state = e.IGNORING
elif elem == e.tags['annotation']:
# Be it in an ODT or ODS template, an annotation is considered to
# contain a POD statement.
e.state = e.READING_STATEMENT
elif elem in (e.tags['change-start'], e.tags['conditional-text']):
# In an ODT template, any text in track-changes or any conditional
# field is considered to contain a POD expression.
e.state = e.READING_EXPRESSION
e.exprHasStyle = False
elif (elem == e.tags['table-cell']) and \
attrs.has_key(e.tags['formula']) and \
attrs.has_key(e.tags['value-type']) and \
(attrs[e.tags['value-type']] == 'string') and \
attrs[e.tags['formula']].startswith('of:="'):
# In an ODS template, any cell containing a formula of type "string"
# and whose content is expressed as a string between double quotes
# (="...") is considered to contain a POD expression. But here it
# is a special case: we need to dump the cell; the expression is not
# directly contained within this cell; the expression will be
# contained in the next inner paragraph. So we must here dump the
# cell, but without some attributes, because the "formula" will be
# converted to the result of evaluating the POD expression.
if e.mode == e.ADD_IN_SUBBUFFER:
e.addSubBuffer()
e.currentBuffer.addElement(e.currentElem.name)
hook = e.currentBuffer.dumpStartElement(
elem,
attrs,
ignoreAttrs=(e.tags['formula'], e.tags['string-value'],
e.tags['value-type']),
hook=True)
# We already have the POD expression: remember it on the env.
e.currentOdsExpression = attrs[e.tags['string-value']]
e.currentOdsHook = hook
else:
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
if elem in e.impactableElements:
if e.mode == e.ADD_IN_SUBBUFFER:
e.addSubBuffer()
e.currentBuffer.addElement(e.currentElem.name)
e.currentBuffer.dumpStartElement(elem, attrs)
elif e.state == e.READING_STATEMENT:
pass
elif e.state == e.READING_EXPRESSION:
if (elem == (e.tags['span'])) and not e.currentContent.strip():
e.currentBuffer.dumpStartElement(elem, attrs)
e.exprHasStyle = True
e.manageInserts()
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
ns = e.onStartElement()
officeNs = ns[e.NS_OFFICE]
textNs = ns[e.NS_TEXT]
tableNs = ns[e.NS_TABLE]
if elem in e.ignorableElems:
e.state = e.IGNORING
elif elem == e.tags['annotation']:
# Be it in an ODT or ODS template, an annotation is considered to
# contain a POD statement.
e.state = e.READING_STATEMENT
elif elem in e.exprStartElems:
# Any track-changed text or being in a conditional or input field is
# considered to be a POD expression.
e.state = e.READING_EXPRESSION
e.exprHasStyle = False
elif (elem == e.tags['table-cell']) and \
attrs.has_key(e.tags['formula']) and \
attrs.has_key(e.tags['value-type']) and \
(attrs[e.tags['value-type']] == 'string') and \
attrs[e.tags['formula']].startswith('of:="'):
# In an ODS template, any cell containing a formula of type "string"
# and whose content is expressed as a string between double quotes
# (="...") is considered to contain a POD expression. But here it
# is a special case: we need to dump the cell; the expression is not
# directly contained within this cell; the expression will be
# contained in the next inner paragraph. So we must here dump the
# cell, but without some attributes, because the "formula" will be
# converted to the result of evaluating the POD expression.
if e.mode == e.ADD_IN_SUBBUFFER:
e.addSubBuffer()
e.currentBuffer.addElement(e.currentElem.name)
hook = e.currentBuffer.dumpStartElement(elem, attrs,
ignoreAttrs=(e.tags['formula'], e.tags['string-value'],
e.tags['value-type']),
hook=True)
# We already have the POD expression: remember it on the env.
e.currentOdsExpression = attrs[e.tags['string-value']]
e.currentOdsHook = hook
else:
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
if elem in e.impactableElems:
if e.mode == e.ADD_IN_SUBBUFFER:
e.addSubBuffer()
e.currentBuffer.addElement(e.currentElem.name)
e.currentBuffer.dumpStartElement(elem, attrs)
elif e.state == e.READING_STATEMENT:
pass
elif e.state == e.READING_EXPRESSION:
if (elem == (e.tags['span'])) and not e.currentContent.strip():
e.currentBuffer.dumpStartElement(elem, attrs)
e.exprHasStyle = True
e.manageInserts()
def endElement(self, elem):
e = OdfParser.endElement(self, elem)
if elem == e.tags['style']:
e.state = READING
e.currentStyle = None
elif elem == e.tags['page-layout']:
e.state = READING
e.currentPageLayout = None
elif elem == e.tags['master-styles']:
e.state = READING
def characters(self, content):
e = OdfParser.characters(self, content)
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
e.currentBuffer.dumpContent(content)
elif e.state == e.READING_STATEMENT:
if e.currentElem.elem.startswith(e.namespaces[e.NS_TEXT]):
e.currentContent += content
elif e.state == e.READING_EXPRESSION:
e.currentContent += content
def characters(self, content):
e = OdfParser.characters(self, content)
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
e.currentBuffer.dumpContent(content)
elif e.state == e.READING_STATEMENT:
if e.currentElem.elem.startswith(e.namespaces[e.NS_TEXT]):
e.currentContent += content
elif e.state == e.READING_EXPRESSION:
e.currentContent += content
def characters(self, content):
e = OdfParser.characters(self, content)
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
if e.currentOdsExpression:
# Do not write content if we have encountered an ODS expression:
# we will replace this content with the expression's result.
pass
else:
e.currentBuffer.dumpContent(content)
elif e.state == e.READING_STATEMENT:
if e.currentElem.elem.startswith(e.namespaces[e.NS_TEXT]):
e.currentContent += content
elif e.state == e.READING_EXPRESSION:
e.currentContent += content
def characters(self, content):
e = OdfParser.characters(self, content)
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
if e.currentOdsExpression:
# Do not write content if we have encountered an ODS expression:
# we will replace this content with the expression's result.
pass
else:
e.currentBuffer.dumpContent(content)
elif e.state == e.READING_STATEMENT:
if e.currentElem.elem.startswith(e.namespaces[e.NS_TEXT]):
e.currentContent += content
elif e.state == e.READING_EXPRESSION:
e.currentContent += content
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
ns = e.onStartElement()
if elem == e.tags['style']:
e.state = PARSING_STYLE
# Create the style
style = Style(name=attrs[e.tags['name']],
family=attrs[e.tags['family']])
classAttr = e.tags['class']
if attrs.has_key(classAttr): style.styleClass = attrs[classAttr]
dnAttr = e.tags['display-name']
if attrs.has_key(dnAttr): style.displayName = attrs[dnAttr]
dolAttr = e.tags['default-outline-level']
if attrs.has_key(dolAttr) and attrs[dolAttr].strip():
style.outlineLevel = int(attrs[dolAttr])
# Record this style in the environment
e.styles[style.name] = style
e.currentStyle = style
elif elem == e.tags['page-layout']:
e.state = PARSING_PAGE_LAYOUT
pageLayout = PageLayout(attrs[e.tags['name']])
# Record this page layout in the environment
e.pageLayouts[pageLayout.name] = pageLayout
e.currentPageLayout = pageLayout
elif elem == e.tags['master-styles']:
e.state = PARSING_MASTER_STYLES
elif e.state == PARSING_STYLE:
# Find properties within this style definition
if elem == e.tags['text-properties']:
fontSizeAttr = e.tags['font-size']
if attrs.has_key(fontSizeAttr):
e.currentStyle.setFontSize(attrs[fontSizeAttr])
elif e.state == PARSING_PAGE_LAYOUT:
# Find properties within this page layout definition
if elem == e.tags['page-layout-properties']:
e.currentPageLayout.setProperties(e, attrs)
elif e.state == PARSING_MASTER_STYLES:
# I am parsing section "master-styles"
if elem == e.tags['master-page']:
plnAttr = e.tags['page-layout-name']
if attrs.has_key(plnAttr):
e.masterLayoutName = attrs[plnAttr]
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
# Do we enter into an annotation ?
if elem == "%s:annotation" % e.ns(e.NS_OFFICE):
self.inAnnotation = True
self.textEncountered = False
elif elem == "%s:p" % e.ns(e.NS_TEXT):
if self.inAnnotation:
if not self.textEncountered:
self.textEncountered = True
else:
self.ignore = True
if not self.ignore:
self.res += "<%s" % elem
for attrName, attrValue in list(attrs.items()):
self.res += ' %s="%s"' % (attrName, attrValue)
self.res += ">"
def startElement(self, elem, attrs):
e = OdfParser.startElement(self, elem, attrs)
# Do we enter into an annotation ?
if elem == '%s:annotation' % e.ns(e.NS_OFFICE):
self.inAnnotation = True
self.textEncountered = False
elif elem == '%s:p' % e.ns(e.NS_TEXT):
if self.inAnnotation:
if not self.textEncountered:
self.textEncountered = True
else:
self.ignore = True
if not self.ignore:
self.res += '<%s' % elem
for attrName, attrValue in attrs.items():
self.res += ' %s="%s"' % (attrName, attrValue)
self.res += '>'
def characters(self, content):
e = OdfParser.characters(self, content)
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
if e.currentOdsExpression:
# Do not write content if we have encountered an ODS expression:
# we will replace this content with the expression's result.
pass
else:
e.currentBuffer.dumpContent(content)
elif e.state == e.READING_STATEMENT:
# Ignore note meta-data: creator, date, sender-initials.
if e.currentElem.elem in e.NOTE_TAGS:
e.currentContent += content
elif e.state == e.READING_EXPRESSION:
e.currentContent += content
def endDocument(self):
e = OdfParser.endDocument(self)
self.caller.styles = e.styles
def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
self.styleTag = None
def endElement(self, elem):
e = OdfParser.endElement(self, elem)
if elem == self.styleTag:
e.state = READING
e.currentStyle = None
def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
env.raiseOnError = caller.raiseOnError
def endDocument(self):
e = OdfParser.endDocument(self)
self.caller.styles = e.styles
def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
self.styleTag = None
def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
def endElement(self, elem):
e = OdfParser.endElement(self, elem)
ns = e.onEndElement()
officeNs = ns[e.NS_OFFICE]
textNs = ns[e.NS_TEXT]
if elem in e.ignorableElements:
e.state = e.READING_CONTENT
elif elem == e.tags['annotation']:
# Manage statement
oldCb = e.currentBuffer
actionElemIndex = oldCb.createAction(e.currentStatement)
e.currentStatement = []
if actionElemIndex != -1:
e.currentBuffer = oldCb.\
transferActionIndependentContent(actionElemIndex)
if e.currentBuffer == oldCb:
e.mode = e.ADD_IN_SUBBUFFER
else:
e.mode = e.ADD_IN_BUFFER
e.state = e.READING_CONTENT
else:
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
# Dump the ODS POD expression if any
if e.currentOdsExpression:
e.currentBuffer.addExpression(e.currentOdsExpression,
tiedHook=e.currentOdsHook)
e.currentOdsExpression = None
e.currentOdsHook = None
# Dump the ending tag
e.currentBuffer.dumpEndElement(elem)
if elem in e.impactableElements:
if isinstance(e.currentBuffer, MemoryBuffer):
isMainElement = e.currentBuffer.isMainElement(elem)
# Unreference the element among the 'elements' attribute
e.currentBuffer.unreferenceElement(elem)
if isMainElement:
parent = e.currentBuffer.parent
if not e.currentBuffer.action:
# Delete this buffer and transfer content to
# parent.
e.currentBuffer.transferAllContent()
parent.removeLastSubBuffer()
e.currentBuffer = parent
else:
if isinstance(parent, FileBuffer):
# Execute buffer action and delete the
# buffer.
e.currentBuffer.action.execute()
parent.removeLastSubBuffer()
e.currentBuffer = parent
e.mode = e.ADD_IN_SUBBUFFER
elif e.state == e.READING_STATEMENT:
if e.currentElem.elem == Text.OD.elem:
statementLine = e.currentContent.strip()
if statementLine:
e.currentStatement.append(statementLine)
e.currentContent = ''
elif e.state == e.READING_EXPRESSION:
if (elem == e.tags['change-end']) or \
(elem == e.tags['conditional-text']):
expression = e.currentContent.strip()
e.currentContent = ''
# Manage expression
e.currentBuffer.addExpression(expression)
if e.exprHasStyle:
e.currentBuffer.dumpEndElement(e.tags['span'])
e.state = e.READING_CONTENT
def endDocument(self):
e = OdfParser.endDocument(self)
self.caller.styles = e.styles
self.caller.pageLayout = e.pageLayouts[e.masterLayoutName]
def endElement(self, elem):
e = OdfParser.endElement(self, elem)
ns = e.onEndElement()
officeNs = ns[e.NS_OFFICE]
textNs = ns[e.NS_TEXT]
if elem in e.ignorableElements:
e.state = e.READING_CONTENT
elif elem == e.tags['annotation']:
# Manage statement
oldCb = e.currentBuffer
actionElemIndex = oldCb.createAction(e.currentStatement)
e.currentStatement = []
if actionElemIndex != -1:
e.currentBuffer = oldCb.\
transferActionIndependentContent(actionElemIndex)
if e.currentBuffer == oldCb:
e.mode = e.ADD_IN_SUBBUFFER
else:
e.mode = e.ADD_IN_BUFFER
e.state = e.READING_CONTENT
else:
if e.state == e.IGNORING:
pass
elif e.state == e.READING_CONTENT:
# Dump the ODS POD expression if any
if e.currentOdsExpression:
e.currentBuffer.addExpression(e.currentOdsExpression,
tiedHook=e.currentOdsHook)
e.currentOdsExpression = None
e.currentOdsHook = None
# Dump the ending tag
e.currentBuffer.dumpEndElement(elem)
if elem in e.impactableElements:
if isinstance(e.currentBuffer, MemoryBuffer):
isMainElement = e.currentBuffer.isMainElement(elem)
# Unreference the element among the 'elements' attribute
e.currentBuffer.unreferenceElement(elem)
if isMainElement:
parent = e.currentBuffer.parent
if not e.currentBuffer.action:
# Delete this buffer and transfer content to
# parent.
e.currentBuffer.transferAllContent()
parent.removeLastSubBuffer()
e.currentBuffer = parent
else:
if isinstance(parent, FileBuffer):
# Execute buffer action and delete the
# buffer.
e.currentBuffer.action.execute()
parent.removeLastSubBuffer()
e.currentBuffer = parent
e.mode = e.ADD_IN_SUBBUFFER
elif e.state == e.READING_STATEMENT:
if e.currentElem.elem == Text.OD.elem:
statementLine = e.currentContent.strip()
if statementLine:
e.currentStatement.append(statementLine)
e.currentContent = ''
elif e.state == e.READING_EXPRESSION:
if (elem == e.tags['change-end']) or \
(elem == e.tags['conditional-text']):
expression = e.currentContent.strip()
e.currentContent = ''
# Manage expression
e.currentBuffer.addExpression(expression)
if e.exprHasStyle:
e.currentBuffer.dumpEndElement(e.tags['span'])
e.state = e.READING_CONTENT
def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
def characters(self, content):
e = OdfParser.characters(self, content)
if not self.ignore:
self.res += escapeXml(content)
def characters(self, content):
e = OdfParser.characters(self, content)
if not self.ignore: self.res += escapeXml(content)
def endElement(self, elem):
e = OdfParser.endElement(self, elem)
if elem == self.styleTag:
e.state = READING
e.currentStyle = None
def __init__(self, env, caller):
OdfParser.__init__(self, env, caller)
env.raiseOnError = caller.raiseOnError