def inspect(self):
if self.textType is not None and os.path.exists(self.pathWidget.value()):
if self.textType == 'csv':
try:
atts, coldelim = inspect_csv(self.pathWidget.value())
except PCTError:
self.columnFrame.updateColumnFrame([])
return
self.columnDelimiterEdit.setText(coldelim.encode('unicode_escape').decode('utf-8'))
self.columnFrame.updateColumnFrame(atts)
else:
if self.textType == 'textgrid':
anno_types = inspect_discourse_textgrid(self.pathWidget.value())
elif self.textType == 'ilg':
anno_types = inspect_discourse_ilg(self.pathWidget.value())
self.lineNumberEdit.setText(str(len(anno_types)))
elif self.textType == 'transcription':
anno_types = inspect_discourse_transcription(self.pathWidget.value())
elif self.textType == 'spelling':
anno_types = inspect_discourse_spelling(self.pathWidget.value())
elif self.textType in ['buckeye','timit']:
anno_types = inspect_discourse_multiple_files(self.pathWidget.value(), self.textType)
self.columnFrame.updateColumnFrame(anno_types)
else:
self.columnFrame.updateColumnFrame([])
def inspect(self):
if self.textType is not None and os.path.exists(
self.pathWidget.value()):
if self.textType == 'csv':
try:
atts, coldelim = inspect_csv(self.pathWidget.value())
except PCTError:
self.columnFrame.updateColumnFrame([])
return
self.columnDelimiterEdit.setText(
coldelim.encode('unicode_escape').decode('utf-8'))
self.columnFrame.updateColumnFrame(atts)
else:
if self.textType == 'textgrid':
anno_types = inspect_discourse_textgrid(
self.pathWidget.value())
elif self.textType == 'ilg':
anno_types = inspect_discourse_ilg(self.pathWidget.value())
self.lineNumberEdit.setText(str(len(anno_types)))
elif self.textType == 'transcription':
anno_types = inspect_discourse_transcription(
self.pathWidget.value())
elif self.textType == 'spelling':
anno_types = inspect_discourse_spelling(
self.pathWidget.value())
elif self.textType in ['buckeye', 'timit']:
anno_types = inspect_discourse_multiple_files(
self.pathWidget.value(), self.textType)
self.columnFrame.updateColumnFrame(anno_types)
else:
self.columnFrame.updateColumnFrame([])
def test_stressed(csv_test_dir):
stressed_path = os.path.join(csv_test_dir, 'stressed.txt')
ats,_ = inspect_csv(stressed_path, coldelim = ',')
print(ats)
ats[1].number_behavior = 'stress'
c = load_corpus_csv('stressed',stressed_path,',', ats)
assert(c.inventory['uw'].symbol == 'uw')
assert(c.inventory.stresses == {'1': set(['uw','iy']),
'0': set(['uw','iy','ah'])})
def test_inspect_example(csv_test_dir):
example_path = os.path.join(csv_test_dir, 'example.txt')
atts, coldelim = inspect_csv(example_path)
assert(coldelim == ',')
for a in atts:
if a.name == 'frequency':
assert(a.attribute.att_type == 'numeric')
elif a.name == 'transcription':
assert(a.attribute.att_type == 'tier')
assert(a.delimiter == '.')
elif a.name == 'spelling':
assert(a.attribute.att_type == 'spelling')
def forceInspect(self, b):
if os.path.exists(self.pathWidget.value()):
if self.textType == 'csv':
colDelim = codecs.getdecoder("unicode_escape")(self.columnDelimiterEdit.text())[0]
if not colDelim:
colDelim = None
atts, coldelim = inspect_csv(self.pathWidget.value(),
coldelim = colDelim)
self.updateColumnFrame(atts)
elif self.textType == 'ilg':
number = self.lineNumberEdit.text()
if number == '':
number = None
else:
try:
number = int(number)
except:
number = None
annotation_types = inspect_discourse_ilg(self.pathWidget.value(), number = number)
self.columnFrame.updateColumnFrame(annotation_types)
def forceInspect(self, b):
if os.path.exists(self.pathWidget.value()):
if self.textType == 'csv':
colDelim = codecs.getdecoder("unicode_escape")(
self.columnDelimiterEdit.text())[0]
if not colDelim:
colDelim = None
atts, coldelim = inspect_csv(self.pathWidget.value(),
coldelim=colDelim)
self.updateColumnFrame(atts)
elif self.textType == 'ilg':
number = self.lineNumberEdit.text()
if number == '':
number = None
else:
try:
number = int(number)
except:
number = None
annotation_types = inspect_discourse_ilg(
self.pathWidget.value(), number=number)
self.columnFrame.updateColumnFrame(annotation_types)
