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_load_spelling_ignore(text_test_dir):
spelling_path = os.path.join(text_test_dir, 'test_text_spelling.txt')
a = inspect_discourse_spelling(spelling_path)
a[0].ignored_characters = set(["'",'.'])
c = load_discourse_spelling('test',spelling_path, a)
assert(c.lexicon['ab'].frequency == 3)
assert(c.lexicon['cabd'].frequency == 1)
def test_load_spelling_ignore(text_test_dir):
spelling_path = os.path.join(text_test_dir, 'test_text_spelling.txt')
a = inspect_discourse_spelling(spelling_path)
a[0].ignored_characters = set(["'", '.'])
c = load_discourse_spelling('test', spelling_path, a)
assert (c.lexicon['ab'].frequency == 3)
assert (c.lexicon['cabd'].frequency == 1)
