def parse_run(params):
sys.stdout.write("\nINPUT FILE: " + params.input_file)
sys.stdout.write("\nOUTPUT FILE: " + params.output_file)
sys.stdout.write("\nMODELS FILE: " + params.models + "\n")
sys.stdout.flush()
components = params.run.split(",")
tokenize = True if "tokenizer" in components else False
compound = True if "compound" in components else False
lemmatize = True if "lemmatizer" in components else False
tag = True if "tagger" in components else False
parse = True if "parser" in components else False
# common elements load
sys.stdout.write("\nLoading embeddings : " + params.embeddings + " ...\n")
embeddings = WordEmbeddings()
embeddings.read_from_file(params.embeddings, None)
encodings = None
if tokenize == True:
if not os.path.isfile(
os.path.join(params.models, "tokenizer-tok.bestAcc")):
sys.stdout.write(
"\n\tTokenizer model not found! (" +
os.path.join(params.models, "tokenizer-tok.bestAcc") + ")")
sys.stdout.flush()
sys.exit(1)
sys.stdout.write("\n\tTokenization enabled.\n")
tokenizer_encodings = Encodings(verbose=False)
tokenizer_encodings.load(
os.path.join(params.models, "tokenizer.encodings"))
if compound == True:
if not os.path.isfile(os.path.join(params.models, "compound.bestAcc")):
sys.stdout.write("\n\tCompound word expander model not found!")
sys.stdout.flush()
sys.exit(1)
sys.stdout.write("\n\tCompound word expander enabled.\n")
if encodings == None:
encodings = Encodings(verbose=False)
encodings.load(os.path.join(params.models, "lemmatizer.encodings"))
if lemmatize == True:
if not os.path.isfile(os.path.join(params.models,
"lemmatizer.bestACC")):
sys.stdout.write("\n\tLemmatization model not found!")
sys.stdout.flush()
sys.exit(1)
sys.stdout.write("\n\tLemmatization enabled.\n")
if encodings == None:
encodings = Encodings(verbose=False)
encodings.load(os.path.join(params.models, "lemmatizer.encodings"))
if tag == True:
if not os.path.isfile(os.path.join(params.models,
"tagger.bestOVERALL")):
sys.stdout.write("\n\tTagger model not found!")
sys.stdout.flush()
sys.exit(1)
sys.stdout.write("\n\tTagger enabled.\n")
if encodings == None:
encodings = Encodings(verbose=False)
encodings.load(os.path.join(params.models, "tagger.encodings"))
if parse == True:
if not os.path.isfile(os.path.join(params.models, "parser.bestUAS")):
sys.stdout.write("\n\tParser model not found!")
sys.stdout.flush()
sys.exit(1)
sys.stdout.write("\n\tParser enabled.\n")
if encodings == None:
encodings = Encodings(verbose=False)
encodings.load(os.path.join(params.models, "parser.encodings"))
sequences = None
if tokenize:
sys.stdout.write("\nTokenizing " + params.input_file + " ... \n\t")
sys.stdout.flush()
from io_utils.config import TieredTokenizerConfig
from generic_networks.tokenizers import TieredTokenizer
config = TieredTokenizerConfig(
os.path.join(params.models, "tokenizer.conf"))
tokenizer_object = TieredTokenizer(config,
tokenizer_encodings,
embeddings,
runtime=True)
tokenizer_object.load(os.path.join(params.models, "tokenizer"))
with open(params.input_file, 'r') as file:
lines = file.readlines()
# analyze use of spaces in first part of the file
test = ""
useSpaces = " "
cnt = 0
while True:
test = test + lines[cnt]
# print(lines[cnt])
if cnt >= len(lines) or cnt > 5:
break
cnt += 1
if float(test.count(' ')) / float(len(test)) < 0.02:
useSpaces = ""
# print (str(float(test.count(' '))/float(len(test))))
i = -1
input_string = ""
sequences = []
while i < len(lines) - 1:
i += 1
input_string = input_string + lines[i].replace("\r", "").replace(
"\n", "").strip() + useSpaces
if lines[i].strip() == "" or i == len(lines) - 1: # end of block
if input_string.strip() != "":
sequences += tokenizer_object.tokenize(input_string)
input_string = ""
del tokenizer_object # free memory
else:
ds = Dataset(params.input_file)
sequences = ds.sequences
sys.stdout.write(" done\n")
sys.stdout.flush()
if compound:
sys.stdout.write("\nCompound word expanding " + params.input_file +
" ... \n\t")
sys.stdout.flush()
from generic_networks.token_expanders import CompoundWordExpander
from io_utils.config import CompoundWordConfig
config = CompoundWordConfig(
os.path.join(params.models, "compound.conf"))
compoundwordexpander_object = CompoundWordExpander(config,
encodings,
embeddings,
runtime=True)
compoundwordexpander_object.load(
os.path.join(params.models, "compound.bestAcc"))
sequences = compoundwordexpander_object.expand_sequences(sequences)
del compoundwordexpander_object # free memory
sys.stdout.write(" done\n")
sys.stdout.flush()
if parse == True:
sys.stdout.write("\nParsing " + params.input_file + " ... \n\t")
sys.stdout.flush()
from io_utils.config import ParserConfig
from generic_networks.parsers import BDRNNParser
config = ParserConfig(os.path.join(params.models, "parser.conf"))
parser_object = BDRNNParser(config,
encodings,
embeddings,
runtime=True)
parser_object.load(os.path.join(params.models, "parser.bestUAS"))
sequences = parser_object.parse_sequences(sequences)
del parser_object # free memory
sys.stdout.write(" done\n")
sys.stdout.flush()
if tag == True:
sys.stdout.write("\nTagging " + params.input_file + " ... \n\t")
sys.stdout.flush()
from io_utils.config import TaggerConfig
from generic_networks.taggers import BDRNNTagger
config = TaggerConfig(os.path.join(params.models, "tagger.conf"))
tagger_object_UPOS = BDRNNTagger(config,
encodings,
embeddings,
runtime=True)
tagger_object_UPOS.load(os.path.join(params.models, "tagger.bestUPOS"))
tagger_object_XPOS = BDRNNTagger(config,
encodings,
embeddings,
runtime=True)
tagger_object_XPOS.load(os.path.join(params.models, "tagger.bestXPOS"))
tagger_object_ATTRS = BDRNNTagger(config,
encodings,
embeddings,
runtime=True)
tagger_object_ATTRS.load(
os.path.join(params.models, "tagger.bestATTRS"))
new_sequences = []
for sequence in sequences:
new_sequence = copy.deepcopy(sequence)
predicted_tags_UPOS = tagger_object_UPOS.tag(new_sequence)
predicted_tags_XPOS = tagger_object_XPOS.tag(new_sequence)
predicted_tags_ATTRS = tagger_object_ATTRS.tag(new_sequence)
for entryIndex in range(len(sequence)):
new_sequence[entryIndex].upos = predicted_tags_UPOS[
entryIndex][0]
new_sequence[entryIndex].xpos = predicted_tags_XPOS[
entryIndex][1]
new_sequence[entryIndex].attrs = predicted_tags_ATTRS[
entryIndex][2]
new_sequences.append(new_sequence)
sequences = copy.deepcopy(new_sequences)
del tagger_object_UPOS # free memory
del tagger_object_XPOS # free memory
del tagger_object_ATTRS # free memory
sys.stdout.write(" done\n")
sys.stdout.flush()
if lemmatize:
sys.stdout.write("\nLemmatizing " + params.input_file + " ... \n\t")
sys.stdout.flush()
from generic_networks.lemmatizers import FSTLemmatizer
from io_utils.config import LemmatizerConfig
config = LemmatizerConfig(
os.path.join(params.models, "lemmatizer.conf"))
lemmatizer_object = FSTLemmatizer(config,
encodings,
embeddings,
runtime=True)
lemmatizer_object.load(
os.path.join(params.models, "lemmatizer.bestACC"))
sequences = lemmatizer_object.lemmatize_sequences(sequences)
del lemmatizer_object # free memory
sys.stdout.write(" done\n")
sys.stdout.flush()
output_dataset = Dataset()
output_dataset.sequences = sequences
output_dataset.write(params.output_file)
new_sequences = []
for sequence in sequences:
new_sequence = copy.deepcopy(sequence)
predicted_tags_UPOS = self.models[PipelineComponents.TAGGER][0].tag(new_sequence)
predicted_tags_XPOS = self.models[PipelineComponents.TAGGER][1].tag(new_sequence)
predicted_tags_ATTRS = self.models[PipelineComponents.TAGGER][2].tag(new_sequence)
for entryIndex in range(len(sequence)):
new_sequence[entryIndex].upos = predicted_tags_UPOS[entryIndex][0]
new_sequence[entryIndex].xpos = predicted_tags_XPOS[entryIndex][1]
new_sequence[entryIndex].attrs = predicted_tags_ATTRS[entryIndex][2]
new_sequences.append(new_sequence)
sequences = new_sequences
if PipelineComponents.LEMMATIZER in pipeline and self.lemmatizer_enabled:
sequences = self.models[PipelineComponents.LEMMATIZER].lemmatize_sequences(sequences)
return sequences
if __name__ == "__main__":
cube = Cube()
cube.load('ro')
sequences = cube.process_text(text="ana are mere dar nu are pere și mănâncă miere.")
sys.stdout.write("\n\n\n")
from io_utils.conll import Dataset
ds = Dataset()
ds.sequences = sequences
ds.write_stdout()