def format_lexc_xml(wordmap):
analysis = xml_escape(wordmap['lemma'])
analysis = analysis.replace('|', '<s mcs="wb"/>').replace('_', '<s mcs="mb"/>')
analysis += '<s mcs="' + wordmap['pos'] + '"/>'
if wordmap['is_proper']:
analysis += '<s mcs="proper"/>'
if wordmap['is_suffix']:
analysis = "<s mcs='suffix'/>" + analysis
if wordmap['is_prefix']:
analysis += "<s mcs='prefix'/>"
stub = xml_escape(wordmap['stub'])
stub = stub.replace('|', '<s mcs="wb"/>').replace('_', '<s mcs="mb"/>')
return (' <e><a>%s</a><i>%s</i><cont lexica="%s"/></e>' %
(analysis, stub, " ".join(wordmap['new_paras'])))
def format_continuation_lexicon_xml(tsvparts):
xmlstring = ' <e>'
if tsvparts[1] != '':
xmlstring += '<a>'
for anal in tsvparts[1].split('|'):
if anal in stuff2ftb3:
anal = make_xmlid(anal)
xmlstring += '<s mcs="' + anal + '"/>'
else:
xmlstring += xml_escape(anal)
xmlstring += '</a>'
else:
xmlstring += '<a/>'
xmlstring += "<i>" + xml_escape(tsvparts[2]) + "</i>"
xmlstring += '<cont lexica="' + " ".join(tsvparts[3:]).replace("#", "_END") + '"/></e>\n'
return xmlstring
def format_multichars_lexc_xml():
multichars = " <Multichar_Symbols>\n"
for key, value in stuff2ftb3.items():
key = make_xmlid(key)
if key != '':
if value != '':
multichars += " <mcs id='" + key + "'>" + xml_escape(value) + "</mcs>\n"
else:
multichars += " <mcs id='" + key + "'>" + key + "</mcs>\n"
else:
pass
multichars += """<!-- Following specials exist in all versions of omorfi -->
<mcs id="hyph">{hyph?}</mcs>
<mcs id="deriv">ยป</mcs>
<mcs id="infl">></mcs>
<mcs id="wb">|</mcs>
"""
multichars += " <mcs id='VERSION'>" + version_id_easter_egg + '</mcs>\n'
multichars += " </Multichar_Symbols>"
return multichars
htmltags = dict([(n, XmlElementProto(n, False))
for n in _non_empty_html_tags] +
[(n, XmlElementProto(n, True))
for n in _maybe_empty_html_tags] +
[('script', XmlElementProto('script', element_class=Script))])
# I have a separate module that defines the html entity refs. Email
# me if you would like a copy.
################################################################################
# 6: Visitors for the xml/html elements, etc.
xml_default_visitors_map = default_visitors_map.copy()
# o = obj_to_be_walked, w = walker (aka serializer)
xml_default_visitors_map.update({
unicode: (lambda o, w: w.emit(xml_escape(o))),
XmlName: (lambda o, w: w.emit(unicode(o))),
XmlAttributes: (lambda o, w: [w.walk(i) for i in o]),
XmlElementProto: (lambda o, w: (w.emit(
safe_unicode('<%s />' % o.name)
if o.can_be_empty else safe_unicode('<%s></%s>' % (o.name, o.name))))),
XmlEntityRef: (lambda o, w: w.emit(safe_unicode('&%s;' % o.alpha))),
})
@xml_default_visitors_map.register(XmlElement)
def visit_xml_element(elem, walker):
walker.emit_many(('<', elem.name))
walker.walk(elem.attrs)
walker.emit('>')
walker.walk(elem.children)
htmltags = dict(
[(n, XmlElementProto(n, False)) for n in _non_empty_html_tags]
+ [(n, XmlElementProto(n, True)) for n in _maybe_empty_html_tags]
+ [('script', XmlElementProto('script', element_class=Script))])
# I have a separate module that defines the html entity refs. Email
# me if you would like a copy.
################################################################################
# 6: Visitors for the xml/html elements, etc.
xml_default_visitors_map = default_visitors_map.copy()
# o = obj_to_be_walked, w = walker (aka serializer)
xml_default_visitors_map.update({
unicode: (lambda o, w: w.emit(xml_escape(o))),
XmlName: (lambda o, w: w.emit(unicode(o))),
XmlAttributes: (lambda o, w: [w.walk(i) for i in o]),
XmlElementProto: (lambda o, w: (
w.emit(safe_unicode('<%s />'%o.name)
if o.can_be_empty
else safe_unicode('<%s></%s>'%(o.name, o.name))))),
XmlEntityRef: (lambda o, w: w.emit(safe_unicode('&%s;'%o.alpha))),
})
@xml_default_visitors_map.register(XmlElement)
def visit_xml_element(elem, walker):
walker.emit_many(('<', elem.name))
walker.walk(elem.attrs)
walker.emit('>')
walker.walk(elem.children)
def convertFile (inputFile, outputFile):
outputFile.write(header)
lineno = 0
inItem = False
questionText = ""
questionType = ""
questionTitle = ""
questionno = 0
for line in inputFile:
line = line.strip()
lineno += 1
if line == "" and inItem: # End of item -> prepare, print & reset
questionno+=1
# Prepare question
questionText = xml_escape(questionText, quote=True)
questionTitle = xml_escape(questionTitle, quote=True)
print id + " " + questionType + " " + questionTitle # TEST !!!
itempresentationelems, itemfeedbackelems, itemresprocessingelems = createQuestion (questionType, questionText)
# Print
if (itempresentationelems != None):
outputFile.write( itemopen % (id, questionTitle) )
outputFile.write( itemmetadata % questionType )
outputFile.write( itempresentationopen % (questionTitle) )
outputFile.write( itempresentationelems )
outputFile.write( itempresentationclose )
outputFile.write( itemresprocessingopen )
outputFile.write( itemresprocessingelems )
outputFile.write( itemresprocessingclose )
outputFile.write( itemfeedbackelems )
outputFile.write( itemclose )
# Reset
questionText = ""
questionType = ""
title = ""
inItem = False
continue
if line == "" and not inItem: # Ignore empty lines
continue
if line[0] == "#": # Ignore comments
continue
if line[0:3] == "[t]": # Have title -> create new question
inItem = True
id = "il_0_qst_" + str(lineno) # id comes from line number
# Type
if line[3:6] == "[s]": # multiple choice, single answer
questionType = questionTypeMCSingle
if line[3:6] == "[m]": # multiple choice, multiple answers
questionType = questionTypeMCMulti
elif line[3:6] == "[g]": # gap question
questionType = questionTypeGap
# Title
questionTitle = line[6:].strip()
continue
# Have (maybe several lines) of question text
# Just add this to what I have had before
if questionText == "":
questionText = line
else:
questionText = questionText + "<br/>" + line
outputFile.write(footer)
print "Found %d questions.\n" % (questionno)
