def mlfparametrize(self,
mlf,
inDir=None,
outDir=None,
source_type='normalized',
target_type='decoded',
use_empty=False):
self.setupDirs(inDir, outDir)
foo, new_sen_file = tempfile.mkstemp()
self.logger.info("Reading MLF")
mlf = MLF.readFromFile(mlf)
self.logger.info("Making build directories")
self.makeDirs()
self.logger.info("Getting text from XMLs")
if new_sen_file is None:
fn = os.path.join(self.settings['PDT_WORK_DIR'], 'sen_file')
else:
fn = new_sen_file
fw = codecs.open(fn, 'w', 'utf-8')
try:
for fn in self.getInputXMLs():
dxml = DXML.readFromFile(fn)
acts = dxml.getDialogueActs(source_type)
idx = 0
for utter in acts:
for txt, attrs in utter:
if not txt:
self.logger.info(
"Empty <dialogue_act> in file: %s", fn)
key = "*/%s_%05d" % (os.path.splitext(
os.path.basename(fn))[0], idx)
if key in mlf:
line = mlf[key]
elif not use_empty:
line = [txt + '\n']
else:
line = ['\n']
line = '\n'.join(line)
fw.write(line)
idx += 1
finally:
fw.close()
self.parametrize(target_type, new_sen_file)
os.remove(new_sen_file)
def mlfparametrize(self, mlf, inDir=None, outDir=None,
source_type='normalized', target_type='decoded', use_empty=False):
self.setupDirs(inDir, outDir)
foo, new_sen_file = tempfile.mkstemp()
self.logger.info("Reading MLF")
mlf = MLF.readFromFile(mlf)
self.logger.info("Making build directories")
self.makeDirs()
self.logger.info("Getting text from XMLs")
if new_sen_file is None:
fn = os.path.join(self.settings['PDT_WORK_DIR'], 'sen_file')
else:
fn = new_sen_file
fw = codecs.open(fn, 'w', 'utf-8')
try:
for fn in self.getInputXMLs():
dxml = DXML.readFromFile(fn)
acts = dxml.getDialogueActs(source_type)
idx = 0
for utter in acts:
for txt, attrs in utter:
if not txt:
self.logger.info("Empty <dialogue_act> in file: %s", fn)
key = "*/%s_%05d" % (os.path.splitext(os.path.basename(fn))[0], idx)
if key in mlf:
line = mlf[key]
elif not use_empty:
line = [txt + '\n']
else:
line = ['\n']
line = '\n'.join(line)
fw.write(line)
idx += 1
finally:
fw.close()
self.parametrize(target_type, new_sen_file)
os.remove(new_sen_file)
