def _get_participants(self, fileid):
# multidimensional dicts
def dictOfDicts():
return defaultdict(dictOfDicts)
xmldoc = ElementTree.parse(fileid).getroot()
# getting participants' data
pat = dictOfDicts()
for participant in xmldoc.findall('.//{%s}Participants/{%s}participant' % (NS,NS)):
for (key,value) in participant.items():
pat[participant.get('id')][key] = value
return pat
def _get_age(self, fileid, month):
xmldoc = ElementTree.parse(fileid).getroot()
for pat in xmldoc.findall('.//{%s}Participants/{%s}participant' % (NS,NS)):
try:
if pat.get('id') == 'CHI':
age = pat.get('age')
if month:
age = self._convert_age(age)
return age
# some files don't have age data
except (TypeError, AttributeError), e:
return None
def _get_age(self, fileid, month):
xmldoc = ElementTree.parse(fileid).getroot()
for pat in xmldoc.findall('.//{%s}Participants/{%s}participant' %
(NS, NS)):
try:
if pat.get('id') == 'CHI':
age = pat.get('age')
if month:
age = _convert_age(age)
return age
# some files don't have age data
except (TypeError, AttributeError), e:
return None
def _get_participants(self, fileid):
# multidimensional dicts
def dictOfDicts():
return defaultdict(dictOfDicts)
xmldoc = ElementTree.parse(fileid).getroot()
# getting participants' data
pat = dictOfDicts()
for participant in xmldoc.findall(
'.//{%s}Participants/{%s}participant' % (NS, NS)):
for (key, value) in participant.items():
pat[participant.get('id')][key] = value
return pat
def _get_words(self, fileid, speaker, sent, stem, relation, pos,
strip_space, replace):
xmldoc = ElementTree.parse(fileid).getroot()
# processing each xml doc
results = []
for xmlsent in xmldoc.findall('.//{%s}u' % NS):
sents = []
# select speakers
if speaker == 'ALL' or xmlsent.get('who') in speaker:
for xmlword in xmlsent.findall('.//{%s}w' % NS):
infl = None ; suffixStem = None
# getting replaced words
if replace and xmlsent.find('.//{%s}w/{%s}replacement' % (NS,NS)):
xmlword = xmlsent.find('.//{%s}w/{%s}replacement/{%s}w' % (NS,NS,NS))
elif replace and xmlsent.find('.//{%s}w/{%s}wk' % (NS,NS)):
xmlword = xmlsent.find('.//{%s}w/{%s}wk' % (NS,NS))
# get text
if xmlword.text:
word = xmlword.text
else:
word = ''
# strip tailing space
if strip_space:
word = word.strip()
# stem
if relation or stem:
try:
xmlstem = xmlword.find('.//{%s}stem' % NS)
word = xmlstem.text
except AttributeError, e:
pass
# if there is an inflection
try:
xmlinfl = xmlword.find('.//{%s}mor/{%s}mw/{%s}mk' % (NS,NS,NS))
word += '-' + xmlinfl.text
except:
pass
# if there is a suffix
try:
xmlsuffix = xmlword.find('.//{%s}mor/{%s}mor-post/{%s}mw/{%s}stem' % (NS,NS,NS,NS))
suffixStem = xmlsuffix.text
except AttributeError:
suffixStem = ""
# pos
if relation or pos:
try:
xmlpos = xmlword.findall(".//{%s}c" % NS)
word = (word,xmlpos[0].text)
if len(xmlpos) != 1 and suffixStem:
suffixStem = (suffixStem,xmlpos[1].text)
except (AttributeError,IndexError), e:
word = (word,None)
if suffixStem:
suffixStem = (suffixStem,None)
# relational
# the gold standard is stored in <mor></mor><mor type="trn"><gra type="grt">
if relation == True:
for xmlstem_rel in xmlword.findall('.//{%s}mor/{%s}gra' % (NS,NS)):
if not xmlstem_rel.get('type') == 'grt':
word = (word[0],word[1],xmlstem_rel.get('index')+"|"+xmlstem_rel.get('head')+
"|"+xmlstem_rel.get('relation'))
else:
word = (word[0],word[1],word[2],word[0],word[1],xmlstem_rel.get('index')+"|"+
xmlstem_rel.get('head')+"|"+xmlstem_rel.get('relation'))
try:
for xmlpost_rel in xmlword.findall('.//{%s}mor/{%s}mor-post/{%s}gra' % (NS,NS,NS)):
if not xmlpost_rel.get('type') == 'grt':
suffixStem = (suffixStem[0],suffixStem[1],xmlpost_rel.get('index')+"|"+xmlpost_rel.get('head')+
"|"+xmlpost_rel.get('relation'))
else:
suffixStem = (suffixStem[0],suffixStem[1],suffixStem[2],suffixStem[0],suffixStem[1],xmlpost_rel.get('index')+"|"+xmlpost_rel.get('head')+
"|"+xmlpost_rel.get('relation'))
except:
pass
sents.append(word)
if suffixStem:
sents.append(suffixStem)
if sent or relation:
results.append(sents)
else:
results.extend(sents)
def _get_corpus(self, fileid):
results = dict()
xmldoc = ElementTree.parse(fileid).getroot()
for key, value in xmldoc.items():
results[key] = value
return results
def _get_words(self, fileid, speaker, sent, stem, relation, pos,
strip_space, replace):
xmldoc = ElementTree.parse(fileid).getroot()
# processing each xml doc
results = []
for xmlsent in xmldoc.findall('.//{%s}u' % NS):
sents = []
# select speakers
if speaker == 'ALL' or xmlsent.get('who') == speaker:
for xmlword in xmlsent.findall('.//{%s}w' % NS):
infl = None
suffixStem = None
# getting replaced words
if replace and xmlsent.find('.//{%s}w/{%s}replacement' %
(NS, NS)):
xmlword = xmlsent.find(
'.//{%s}w/{%s}replacement/{%s}w' % (NS, NS, NS))
elif replace and xmlsent.find('.//{%s}w/{%s}wk' %
(NS, NS)):
xmlword = xmlsent.find('.//{%s}w/{%s}wk' % (NS, NS))
# get text
if xmlword.text:
word = xmlword.text
else:
word = ''
# strip tailing space
if strip_space:
word = word.strip()
# stem
if relation or stem:
try:
xmlstem = xmlword.find('.//{%s}stem' % NS)
word = xmlstem.text
except AttributeError, e:
pass
# if there is an inflection
try:
xmlinfl = xmlword.find('.//{%s}mor/{%s}mw/{%s}mk' %
(NS, NS, NS))
word += '-' + xmlinfl.text
except:
pass
# if there is a suffix
try:
xmlsuffix = xmlword.find(
'.//{%s}mor/{%s}mor-post/{%s}mw/{%s}stem' %
(NS, NS, NS, NS))
suffixStem = xmlsuffix.text
except AttributeError:
suffixStem = ""
# pos
if relation or pos:
try:
xmlpos = xmlword.findall(".//{%s}c" % NS)
word = (word, xmlpos[0].text)
if len(xmlpos) != 1 and suffixStem:
suffixStem = (suffixStem, xmlpos[1].text)
except (AttributeError, IndexError), e:
word = (word, None)
if suffixStem:
suffixStem = (suffixStem, None)
# relational
# the gold standard is stored in <mor></mor><mor type="trn"><gra type="grt">
if relation == True:
for xmlstem_rel in xmlword.findall(
'.//{%s}mor/{%s}gra' % (NS, NS)):
if not xmlstem_rel.get('type') == 'grt':
word = (word[0], word[1],
xmlstem_rel.get('index') + "|" +
xmlstem_rel.get('head') + "|" +
xmlstem_rel.get('relation'))
else:
word = (word[0], word[1], word[2], word[0],
word[1], xmlstem_rel.get('index') +
"|" + xmlstem_rel.get('head') + "|" +
xmlstem_rel.get('relation'))
try:
for xmlpost_rel in xmlword.findall(
'.//{%s}mor/{%s}mor-post/{%s}gra' %
(NS, NS, NS)):
if not xmlpost_rel.get('type') == 'grt':
suffixStem = (suffixStem[0], suffixStem[1],
xmlpost_rel.get('index') +
"|" +
xmlpost_rel.get('head') +
"|" +
xmlpost_rel.get('relation'))
else:
suffixStem = (suffixStem[0], suffixStem[1],
suffixStem[2], suffixStem[0],
suffixStem[1],
xmlpost_rel.get('index') +
"|" +
xmlpost_rel.get('head') +
"|" +
xmlpost_rel.get('relation'))
except:
pass
sents.append(word)
if suffixStem:
sents.append(suffixStem)
if sent or relation:
results.append(sents)
else:
results.extend(sents)
def _get_corpus(self, fileid):
results = dict()
xmldoc = ElementTree.parse(fileid).getroot()
for key, value in xmldoc.items():
results[key] = value
return results
