def _set_pid(self, pid):
parent_dir = os.path.abspath(os.path.join(self._pidfile, os.pardir))
if not os.path.isdir(parent_dir):
fileutils.makedirs(parent_dir, exist_ok=True)
with open(self._pidfile, 'w') as pid_file:
pid_file.write(str(pid))
def _start_kafka(self, log, port=9092, zookeeper_port=2181):
kdata = os.path.abspath(os.path.join(self._data, 'kdata'))
if not os.path.isdir(kdata):
fileutils.makedirs(kdata, exist_ok=True)
config = os.path.join(self._data, 'kafka.properties')
with open(config, 'w') as cout:
cout.write('broker.id=0\n')
cout.write(
'listeners=PLAINTEXT://0.0.0.0:{port}\n'.format(port=port))
cout.write('log.dirs={data}\n'.format(data=kdata))
cout.write('num.partitions=1\n')
cout.write('log.retention.hours=8760000\n')
cout.write('zookeeper.connect=localhost:{port}\n'.format(
port=zookeeper_port))
command = [self._kafka_bin, config]
kafka = subprocess.Popen(command, stdout=log, stderr=log,
shell=False).pid
for i in range(1, 5):
with open(log.name, 'r') as rlog:
for line in rlog:
if 'INFO [Kafka Server 0], started (kafka.server.KafkaServer)' in line:
return kafka
time.sleep(1)
daemon.kill(kafka)
return None
def _start_process(self):
if not os.path.isdir(self.engine.get_runtime_path()):
fileutils.makedirs(self.engine.get_runtime_path(), exist_ok=True)
self._log_file = self.engine.get_logfile(ClusterNode.__LOG_FILENAME, ensure=True)
args = ['-e', self.engine.name, '-p', str(self._cluster_ports[0]), str(self._cluster_ports[1]),
'--status-file', self._status_file]
if self._start_rest_server:
args.append('-a')
args.append(str(self._api_port))
if self._verbosity is not None:
args.append('-v')
args.append(str(self._verbosity))
if self._sibling is not None:
args.append('--member')
args.append(str(self._sibling))
command = mmt_javamain('eu.modernmt.cli.ClusterNodeMain', args,
hserr_path=os.path.abspath(os.path.join(self._log_file, os.pardir)))
log = open(self._log_file, 'wa')
if os.path.isfile(self._status_file):
os.remove(self._status_file)
return subprocess.Popen(command, stdout=open(os.devnull), stderr=log, shell=False)
def generate(self, bilingual_corpora, monolingual_corpora, output, log_file=None):
fileutils.makedirs(self._model, exist_ok=True)
args = ['--db', os.path.join(self._model, 'domains.db'), '-l', self._source_lang, '-c']
source_paths = set([corpus.get_folder() for corpus in bilingual_corpora])
for source_path in source_paths:
args.append(source_path)
command = cli.mmt_javamain(self._java_mainclass, args)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'w')
stdout, _ = shell.execute(command, stderr=log)
domains = {}
for domain, name in [line.rstrip('\n').split('\t', 2) for line in stdout.splitlines()]:
domains[name] = domain
return self._make_training_folder(bilingual_corpora, monolingual_corpora, domains, output)
finally:
if log_file is not None:
log.close()
def _start_zookeeper(self, log, port=2181):
zdata = os.path.abspath(os.path.join(self._data, 'zdata'))
if not os.path.isdir(zdata):
fileutils.makedirs(zdata, exist_ok=True)
config = os.path.join(self._data, 'zookeeper.properties')
with open(config, 'w') as cout:
cout.write('dataDir={data}\n'.format(data=zdata))
cout.write('clientPort={port}\n'.format(port=port))
cout.write('maxClientCnxns=0\n')
command = [self._zookeeper_bin, config]
zookeeper = subprocess.Popen(command,
stdout=log,
stderr=log,
shell=False).pid
for i in range(1, 5):
try:
msg = fileutils.netcat('127.0.0.1', port, 'ruok', timeout=2)
except:
msg = None
if 'imok' == msg:
return zookeeper
else:
time.sleep(1)
daemon.kill(zookeeper)
return None
def _start_zookeeper(self, log, port=2181):
zdata = os.path.abspath(os.path.join(self._data, 'zdata'))
if not os.path.isdir(zdata):
fileutils.makedirs(zdata, exist_ok=True)
config = os.path.join(self._data, 'zookeeper.properties')
with open(config, 'w') as cout:
cout.write('dataDir={data}\n'.format(data=zdata))
cout.write('clientPort={port}\n'.format(port=port))
cout.write('maxClientCnxns=0\n')
command = [self._zookeeper_bin, config]
zookeeper = subprocess.Popen(command, stdout=log, stderr=log, shell=False).pid
for i in range(1, 5):
try:
msg = fileutils.netcat('127.0.0.1', port, 'ruok', timeout=2)
except:
msg = None
if 'imok' == msg:
return zookeeper
else:
time.sleep(1)
daemon.kill(zookeeper)
return None
def train(self, corpora, aligner, working_dir='.', log=None):
if log is None:
log = shell.DEVNULL
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
train_corpora = [] # Prepare training folder
for corpus in corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, working_dir,
(self._source_lang, self._target_lang))
source_file = corpus.get_file(self._source_lang)
target_file = corpus.get_file(self._target_lang)
os.symlink(source_file, dest_corpus.get_file(self._source_lang))
os.symlink(target_file, dest_corpus.get_file(self._target_lang))
train_corpora.append(dest_corpus)
# Align corpora
aligner.align(train_corpora, working_dir, log=log)
# Build models
command = [self._build_bin, '--input', working_dir, '--model', self._model,
'-s', self._source_lang, '-t', self._target_lang]
shell.execute(command, stdout=log, stderr=log)
def train(self, corpora, aligner, working_dir='.', log=None):
if log is None:
log = shell.DEVNULL
shutil.rmtree(self._model, ignore_errors=True)
fileutils.makedirs(self._model, exist_ok=True)
train_corpora_path = os.path.join(working_dir, 'corpora')
lex_model_path = os.path.join(working_dir, 'model.tlex')
if not os.path.isdir(train_corpora_path):
fileutils.makedirs(train_corpora_path, exist_ok=True)
train_corpora = [] # Prepare training folder
for corpus in corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, train_corpora_path,
(self._source_lang, self._target_lang))
source_file = corpus.get_file(self._source_lang)
target_file = corpus.get_file(self._target_lang)
os.symlink(source_file, dest_corpus.get_file(self._source_lang))
os.symlink(target_file, dest_corpus.get_file(self._target_lang))
train_corpora.append(dest_corpus)
# Align corpora
aligner.align(train_corpora, train_corpora_path, log=log)
aligner.export(lex_model_path)
# Build models
command = [self._build_bin, '--lex', lex_model_path, '--input', train_corpora_path, '--model', self._model,
'-s', self._source_lang, '-t', self._target_lang, '-v', self._vb.model]
shell.execute(command, stdout=log, stderr=log)
def build(self, corpora, working_dir='.', log=None):
if log is None:
log = shell.DEVNULL
shutil.rmtree(self._model, ignore_errors=True)
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
merged_corpus = BilingualCorpus.make_parallel(
'merge', working_dir, (self._source_lang, self._target_lang))
fileutils.merge(
[corpus.get_file(self._source_lang) for corpus in corpora],
merged_corpus.get_file(self._source_lang))
fileutils.merge(
[corpus.get_file(self._target_lang) for corpus in corpora],
merged_corpus.get_file(self._target_lang))
command = [
self._build_bin, '-s',
merged_corpus.get_file(self._source_lang), '-t',
merged_corpus.get_file(self._target_lang), '-m', self._model, '-I',
'4'
]
shell.execute(command, stdout=log, stderr=log)
def train(self, corpora, aligner, working_dir='.', log_file=None):
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Prepare training folder
for corpus in corpora:
dest_corpus = BilingualCorpus.make_parallel(corpus.name, working_dir,
(self._source_lang, self._target_lang))
source_file = corpus.get_file(self._source_lang)
target_file = corpus.get_file(self._target_lang)
os.symlink(source_file, dest_corpus.get_file(self._source_lang))
os.symlink(target_file, dest_corpus.get_file(self._target_lang))
aligner.align(corpus, os.path.join(working_dir, corpus.name + '.align'))
# Build models
command = [self._build_bin, '--input', working_dir, '--model', self._model,
'-s', self._source_lang, '-t', self._target_lang]
shell.execute(command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def build(self, corpora, working_dir='.', log_file=None):
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
merged_corpus = BilingualCorpus.make_parallel(
'merge', working_dir, (self._source_lang, self._target_lang))
fileutils.merge(
[corpus.get_file(self._source_lang) for corpus in corpora],
merged_corpus.get_file(self._source_lang))
fileutils.merge(
[corpus.get_file(self._target_lang) for corpus in corpora],
merged_corpus.get_file(self._target_lang))
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Train model
command = [
self._build_bin, '-s',
merged_corpus.get_file(self._source_lang), '-t',
merged_corpus.get_file(self._target_lang), '-m', self._model,
'-I', '4'
]
shell.execute(command, stderr=log)
finally:
if log_file is not None:
log.close()
def _start_cassandra(self, log):
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
# create a runtime version of the configuration file
config = os.path.join(self._runtime, 'cassandra.yaml')
self._yaml_transform(config)
env = {"CASSANDRA_JMX_PORT": str(netutils.get_free_tcp_port())}
# launch cassandra -d _runtime
command = [
self._cassandra_bin, '-R', '-Dcassandra.config=file:///' + config,
"-f"
]
cassandra = subprocess.Popen(command,
stdout=log,
stderr=log,
shell=False,
env=env).pid
# If Starting listening for CQL clients is not in the rlog
# in the first 80 seconds
# kill Cassandra and return none?
for i in range(1, 100):
with open(log.name, 'r') as rlog:
for line in rlog:
if 'Starting listening for CQL clients' in line:
return cassandra
time.sleep(1)
return None
def build(self, corpora, working_dir='.', log_file=None):
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
merged_corpus = BilingualCorpus.make_parallel('merge', working_dir, (self._source_lang, self._target_lang))
fileutils.merge([corpus.get_file(self._source_lang) for corpus in corpora],
merged_corpus.get_file(self._source_lang))
fileutils.merge([corpus.get_file(self._target_lang) for corpus in corpora],
merged_corpus.get_file(self._target_lang))
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Train model
command = [self._build_bin,
'-s', merged_corpus.get_file(self._source_lang), '-t', merged_corpus.get_file(self._target_lang),
'-m', self._model, '-I', '4']
shell.execute(command, stderr=log)
finally:
if log_file is not None:
log.close()
def _set_pid(self, pid):
parent_dir = os.path.abspath(os.path.join(self._pidfile, os.pardir))
if not os.path.isdir(parent_dir):
fileutils.makedirs(parent_dir, exist_ok=True)
with open(self._pidfile, 'w') as pid_file:
pid_file.write(str(pid))
def generate(self, bilingual_corpora, monolingual_corpora, output, log_file=None):
fileutils.makedirs(self._model, exist_ok=True)
args = ['--db', os.path.join(self._model, 'domains.db'), '-l', self._source_lang, '-c']
source_paths = set([corpus.get_folder() for corpus in bilingual_corpora])
for source_path in source_paths:
args.append(source_path)
command = cli.mmt_javamain(self._java_mainclass, args)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'w')
stdout, _ = shell.execute(command, stderr=log)
domains = {}
for domain, name in [line.rstrip('\n').split('\t', 2) for line in stdout.splitlines()]:
domains[name] = domain
return self._make_training_folder(bilingual_corpora, monolingual_corpora, domains, output)
finally:
if log_file is not None:
log.close()
def _get_tempdir(self, name, delete_if_exists=False):
path = os.path.join(self._temp_dir, name)
if delete_if_exists:
shutil.rmtree(path, ignore_errors=True)
if not os.path.isdir(path):
fileutils.makedirs(path, exist_ok=True)
return path
def _start_kafka(self, log, port=9092, zookeeper_port=2181):
kdata = os.path.abspath(os.path.join(self._data, 'kdata'))
if not os.path.isdir(kdata):
fileutils.makedirs(kdata, exist_ok=True)
config = os.path.join(self._data, 'kafka.properties')
with open(config, 'w') as cout:
cout.write('broker.id=0\n')
cout.write('listeners=PLAINTEXT://0.0.0.0:{port}\n'.format(port=port))
cout.write('log.dirs={data}\n'.format(data=kdata))
cout.write('num.partitions=1\n')
cout.write('log.retention.hours=8760000\n')
cout.write('zookeeper.connect=localhost:{port}\n'.format(port=zookeeper_port))
command = [self._kafka_bin, config]
kafka = subprocess.Popen(command, stdout=log, stderr=log, shell=False).pid
for i in range(1, 5):
with open(log.name, 'r') as rlog:
for line in rlog:
if 'INFO [Kafka Server 0], started (kafka.server.KafkaServer)' in line:
return kafka
time.sleep(1)
daemon.kill(kafka)
return None
def __process_file(self, source, dest, lang, print_tags=True, print_placeholders=False, original_spacing=False):
command = self.__get_command(lang, print_tags, print_placeholders, original_spacing)
if not os.path.isdir(dest.get_folder()):
fileutils.makedirs(dest.get_folder(), exist_ok=True)
with open(source) as input_stream:
with open(dest.get_file(lang), 'w') as output_stream:
shell.execute(command, stdin=input_stream, stdout=output_stream, stderr=shell.DEVNULL)
def train(self, corpora, lang, working_dir='.', log=None):
if log is None:
log = shell.DEVNULL
bicorpora = []
for corpus in corpora:
if len(corpus.langs) > 1:
bicorpora.append(corpus)
shutil.rmtree(self._model, ignore_errors=True)
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
# Train static LM
static_lm_model = os.path.join(self._model, 'background.slm')
static_lm_wdir = os.path.join(working_dir, 'slm.temp')
fileutils.makedirs(static_lm_wdir, exist_ok=True)
merged_corpus = os.path.join(working_dir, 'merged_corpus')
fileutils.merge([corpus.get_file(lang) for corpus in corpora],
merged_corpus)
command = [
self._create_slm_bin, '--discount-fallback', '-o',
str(self._order), '-a',
str(self._compression), '-q',
str(self._quantization), '--type', 'trie', '--model',
static_lm_model, '-T', static_lm_wdir
]
if self._order > 2 and self._prune:
command += ['--prune', '0', '1', '2']
with open(merged_corpus) as stdin:
shell.execute(command, stdin=stdin, stdout=log, stderr=log)
# Create AdaptiveLM training folder
alm_train_folder = os.path.join(working_dir, 'alm_train')
fileutils.makedirs(alm_train_folder, exist_ok=True)
for corpus in bicorpora:
os.symlink(
corpus.get_file(lang),
os.path.join(alm_train_folder, corpus.name + '.' + lang))
# Train adaptive LM
adaptive_lm_model = os.path.join(self._model, 'foreground.alm')
fileutils.makedirs(adaptive_lm_model, exist_ok=True)
command = [
self._create_alm_bin, '-m', adaptive_lm_model, '-i',
alm_train_folder, '-b', '50000000'
]
shell.execute(command, stdout=log, stderr=log)
def train(self, corpora, lang, working_dir='.', log_file=None):
if os.path.isfile(self._model):
raise Exception('Model already exists at ' + self._model)
parent_dir = os.path.abspath(os.path.join(self._model, os.pardir))
if not os.path.isdir(parent_dir):
fileutils.makedirs(parent_dir, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
def train(self, corpora, lang, working_dir='.', log_file=None):
if os.path.isfile(self._model):
raise Exception('Model already exists at ' + self._model)
parent_dir = os.path.abspath(os.path.join(self._model, os.pardir))
if not os.path.isdir(parent_dir):
fileutils.makedirs(parent_dir, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
def _clean_file(self, source, dest_folder, langs):
if not os.path.isdir(dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
input_folder = os.path.join(source.get_folder(), source.name)
output_folder = os.path.join(dest_folder, source.name)
command = ['perl', self._cleaner_script, '-ratio', str(self._ratio), input_folder, langs[0], langs[1],
output_folder, str(self._min), str(self._max)]
shell.execute(command, stdout=shell.DEVNULL, stderr=shell.DEVNULL)
def get_logfile(self, name, ensure=True):
if ensure and not os.path.isdir(self._logs_path):
fileutils.makedirs(self._logs_path, exist_ok=True)
logfile = os.path.join(self._logs_path, name + '.log')
if ensure and os.path.isfile(logfile):
os.remove(logfile)
return logfile
def _clean_file(self, source, dest_folder, langs):
if not os.path.isdir(dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
input_folder = os.path.join(source.get_folder(), source.name)
output_folder = os.path.join(dest_folder, source.name)
command = ['perl', self._cleaner_script, '-ratio', str(self._ratio), input_folder, langs[0], langs[1],
output_folder, str(self._min), str(self._max)]
shell.execute(command, stdout=shell.DEVNULL, stderr=shell.DEVNULL)
def get_logfile(self, name, ensure=True, append=False):
if ensure and not os.path.isdir(self.logs_path):
fileutils.makedirs(self.logs_path, exist_ok=True)
logfile = os.path.join(self.logs_path, name + '.log')
if not append and ensure and os.path.isfile(logfile):
os.remove(logfile)
return logfile
def get_tempdir(self, name, ensure=True):
if ensure and not os.path.isdir(self._temp_path):
fileutils.makedirs(self._temp_path, exist_ok=True)
folder = os.path.join(self._temp_path, name)
if ensure:
shutil.rmtree(folder, ignore_errors=True)
os.makedirs(folder)
return folder
def get_tempdir(self, name, ensure=True):
if ensure and not os.path.isdir(self.temp_path):
fileutils.makedirs(self.temp_path, exist_ok=True)
folder = os.path.join(self.temp_path, name)
if ensure:
shutil.rmtree(folder, ignore_errors=True)
os.makedirs(folder)
return folder
def process_corpora(self, corpora, dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang])
self.process_file(source, dest, lang)
return BilingualCorpus.list(dest_folder)
def process_corpora(self, corpora, dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang])
self.process_file(source, dest, lang)
return BilingualCorpus.list(dest_folder)
def encode(self, corpora, dest_folder):
if not os.path.isdir(dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest_file = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang]).get_file(lang)
self.encode_file(source, dest_file, delete_nl=True)
return BilingualCorpus.list(dest_folder)
def encode(self, corpora, dest_folder):
if not os.path.isdir(dest_folder):
fileutils.makedirs(dest_folder, exist_ok=True)
for corpus in corpora:
for lang in corpus.langs:
source = corpus.get_file(lang)
dest_file = BilingualCorpus.make_parallel(corpus.name, dest_folder, [lang]).get_file(lang)
self.encode_file(source, dest_file, delete_nl=True)
return BilingualCorpus.list(dest_folder)
def process_corpora(self, corpora, output_folder):
fileutils.makedirs(output_folder, exist_ok=True)
for corpus in corpora:
output_corpus = BilingualCorpus.make_parallel(
corpus.name, output_folder, corpus.langs)
for lang in corpus.langs:
input_path = corpus.get_file(lang)
output_path = output_corpus.get_file(lang)
self.process_file(input_path, output_path, lang)
return BilingualCorpus.list(output_folder)
def train(self, corpora, lang, working_dir='.', log_file=None):
LanguageModel.train(self, corpora, lang, working_dir, log_file)
bicorpora = []
for corpus in corpora:
if len(corpus.langs) > 1:
bicorpora.append(corpus)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'w')
fileutils.makedirs(self._model, exist_ok=True)
# Train static LM
static_lm_model = os.path.join(self._model, 'background.slm')
static_lm_wdir = os.path.join(working_dir, 'slm.temp')
fileutils.makedirs(static_lm_wdir, exist_ok=True)
merged_corpus = os.path.join(working_dir, 'merged_corpus')
fileutils.merge([corpus.get_file(lang) for corpus in corpora],
merged_corpus)
command = [
self._create_slm_bin, '--discount_fallback', '-o',
str(self._order), '--model', static_lm_model, '-S',
str(KenLM.get_mem_percent()) + '%', '-T', static_lm_wdir
]
if self._order > 2 and self.prune:
command += ['--prune', '0', '0', '1']
with open(merged_corpus) as stdin:
shell.execute(command, stdin=stdin, stdout=log, stderr=log)
# Create AdaptiveLM training folder
alm_train_folder = os.path.join(working_dir, 'alm_train')
fileutils.makedirs(alm_train_folder, exist_ok=True)
for corpus in bicorpora:
os.symlink(
corpus.get_file(lang),
os.path.join(alm_train_folder, corpus.name + '.' + lang))
# Train adaptive LM
adaptive_lm_model = os.path.join(self._model, 'foreground.alm')
fileutils.makedirs(adaptive_lm_model, exist_ok=True)
command = [
self._create_alm_bin, '-m', adaptive_lm_model, '-i',
alm_train_folder, '-b', '100000000'
]
shell.execute(command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def _start_process(self, api_port, cluster_port, datastream_port, db_port,
leader, verbosity):
if not os.path.isdir(self.engine.runtime_path):
fileutils.makedirs(self.engine.runtime_path, exist_ok=True)
logs_folder = os.path.abspath(os.path.join(self._log_file, os.pardir))
args = [
'-e', self.engine.name, '--status-file', self._status_file,
'--logs', logs_folder
]
if cluster_port is not None:
args.append('--cluster-port')
args.append(str(cluster_port))
if api_port is not None:
args.append('--api-port')
args.append(str(api_port))
if datastream_port is not None:
args.append('--datastream-port')
args.append(str(datastream_port))
if db_port is not None:
args.append('--db-port')
args.append(str(db_port))
if verbosity is not None:
args.append('-v')
args.append(str(verbosity))
if leader is not None:
args.append('--leader')
args.append(leader)
command = mmt_javamain('eu.modernmt.cli.ClusterNodeMain',
args,
hserr_path=logs_folder)
if os.path.isfile(self._status_file):
os.remove(self._status_file)
return subprocess.Popen(command,
stdout=shell.DEVNULL,
stderr=shell.DEVNULL,
shell=False)
def start(self):
if self.is_running():
raise IllegalStateException(
'Cannot start Kafka process. Kafka process is already running')
if not netutils.is_free(self.port):
raise IllegalStateException(
'port %d is already in use, please specify another port with --datastream-port'
% self.port)
self._log_file = self._engine.get_logfile('embedded-kafka',
ensure=True)
shutil.rmtree(self._runtime, ignore_errors=True)
fileutils.makedirs(self._runtime, exist_ok=True)
success = False
zpid, kpid = 0, 0
log = open(self._log_file, 'w')
try:
zookeeper_port = netutils.get_free_tcp_port()
zpid = self._start_zookeeper(log, zookeeper_port)
if zpid is None:
raise IllegalStateException(
'failed to start zookeeper, check log file for more details: '
+ self._log_file)
kpid = self._start_kafka(log, zookeeper_port)
if kpid is None:
raise IllegalStateException(
'failed to start kafka, check log file for more details: '
+ self._log_file)
self._set_pids(kpid, zpid)
success = True
except:
if not success:
daemon.kill(kpid)
daemon.kill(zpid)
log.close()
raise
def create_index(self, corpora, log=None):
if log is None:
log = shell.DEVNULL
source_paths = set()
for corpus in corpora:
source_paths.add(corpus.get_folder())
shutil.rmtree(self._index, ignore_errors=True)
fileutils.makedirs(self._index, exist_ok=True)
args = ['-s', self._source_lang, '-t', self._target_lang, '-i', self._index, '-c']
for source_path in source_paths:
args.append(source_path)
command = mmt_javamain(self._java_mainclass, args)
shell.execute(command, stdout=log, stderr=log)
def generate(self,
bilingual_corpora,
monolingual_corpora,
output,
log=None):
if log is None:
log = shell.DEVNULL
fileutils.makedirs(self._model, exist_ok=True)
args = [
'--db',
os.path.join(self._model, 'domains.db'), '-s', self._source_lang,
'-t', self._target_lang, '-c'
]
source_paths = set(
[corpus.get_folder() for corpus in bilingual_corpora])
for source_path in source_paths:
args.append(source_path)
command = cli.mmt_javamain(self._java_mainclass, args)
stdout, _ = shell.execute(command, stderr=log)
domains = {}
for domain, name in [
line.rstrip('\n').split('\t', 2)
for line in stdout.splitlines()
]:
domains[name] = domain
bilingual_corpora = [
corpus.symlink(output, name=domains[corpus.name])
for corpus in bilingual_corpora
]
monolingual_corpora = [
corpus.symlink(output) for corpus in monolingual_corpora
]
return bilingual_corpora, monolingual_corpora
def train(self, corpora, aligner, working_dir='.', log_file=None):
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Prepare training folder
for corpus in corpora:
dest_corpus = BilingualCorpus.make_parallel(
corpus.name, working_dir,
(self._source_lang, self._target_lang))
source_file = corpus.get_file(self._source_lang)
target_file = corpus.get_file(self._target_lang)
os.symlink(source_file,
dest_corpus.get_file(self._source_lang))
os.symlink(target_file,
dest_corpus.get_file(self._target_lang))
aligner.align(
corpus, os.path.join(working_dir, corpus.name + '.align'))
# Build models
command = [
self._build_bin, '--input', working_dir, '--model',
self._model, '-s', self._source_lang, '-t', self._target_lang
]
shell.execute(command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def _start_process(self):
if not os.path.isdir(self.engine.get_runtime_path()):
fileutils.makedirs(self.engine.get_runtime_path(), exist_ok=True)
self._log_file = self.engine.get_logfile(ClusterNode.__LOG_FILENAME,
ensure=True)
args = [
'-e', self.engine.name, '-p',
str(self._cluster_ports[0]),
str(self._cluster_ports[1]), '--status-file', self._status_file
]
if self._start_rest_server:
args.append('-a')
args.append(str(self._api_port))
if self._verbosity is not None:
args.append('-v')
args.append(str(self._verbosity))
if self._sibling is not None:
args.append('--member')
args.append(str(self._sibling))
command = mmt_javamain('eu.modernmt.cli.ClusterNodeMain',
args,
hserr_path=os.path.abspath(
os.path.join(self._log_file, os.pardir)))
log = open(self._log_file, 'wa')
if os.path.isfile(self._status_file):
os.remove(self._status_file)
return subprocess.Popen(command,
stdout=open(os.devnull),
stderr=log,
shell=False)
def create_index(self, corpora, lang, log_file=None):
source_paths = set()
for corpus in corpora:
source_paths.add(corpus.get_folder())
fileutils.makedirs(self._index, exist_ok=True)
args = ['-l', lang, '-i', self._index, '-c']
for source_path in source_paths:
args.append(source_path)
command = mmt_javamain(self._java_mainclass, args)
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'w')
shell.execute(command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def start(self):
if self.is_running():
raise IllegalStateException(
'Cannot start Cassandra process. Cassandra process is already running'
)
if not netutils.is_free(self.port):
raise IllegalStateException(
'port %d is already in use, please specify another port with --db-port'
% self.port)
self._log_file = self._engine.get_logfile('embedded-cassandra',
ensure=True)
shutil.rmtree(self._runtime, ignore_errors=True)
fileutils.makedirs(self._runtime, exist_ok=True)
success = False
cpid = 0
log = open(self._log_file, 'w')
try:
cpid = self._start_cassandra(log)
if cpid is None:
raise IllegalStateException(
'failed to start Cassandra, check log file for more details: '
+ self._log_file)
self._set_pid(cpid)
success = True
except:
if not success:
daemon.kill(cpid)
log.close()
raise
def _start_process(self):
if not os.path.isdir(self.engine.runtime_path):
fileutils.makedirs(self.engine.runtime_path, exist_ok=True)
logs_folder = os.path.abspath(os.path.join(self._log_file, os.pardir))
args = [
'-e', self.engine.name, '-p',
str(self._cluster_ports[0]),
str(self._cluster_ports[1]), '--datastream-port',
str(self._datastream_port), '--status-file', self._status_file,
'--logs', logs_folder
]
if self._start_rest_server:
args.append('-a')
args.append(str(self._api_port))
if self._verbosity is not None:
args.append('-v')
args.append(str(self._verbosity))
if self._sibling is not None:
args.append('--member')
args.append(str(self._sibling))
command = mmt_javamain('eu.modernmt.cli.ClusterNodeMain',
args,
hserr_path=logs_folder)
if os.path.isfile(self._status_file):
os.remove(self._status_file)
return subprocess.Popen(command,
stdout=shell.DEVNULL,
stderr=shell.DEVNULL,
shell=False)
def align(self, corpus, langs, model_dir, working_dir='.', log_file=None):
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
def _get_tempdir(self, name):
path = os.path.join(self._temp_dir, name)
if not os.path.isdir(path):
fileutils.makedirs(path, exist_ok=True)
return path
def train(self, corpora, aligner, working_dir='.', log_file=None):
if os.path.isdir(self._model) and len(os.listdir(self._model)) > 0:
raise Exception('Model already exists at ' + self._model)
if not os.path.isdir(self._model):
fileutils.makedirs(self._model, exist_ok=True)
if not os.path.isdir(working_dir):
fileutils.makedirs(working_dir, exist_ok=True)
l1 = self._source_lang
l2 = self._target_lang
langs = (l1, l2)
langs_suffix = l1 + '-' + l2
mct_base = self._get_model_basename()
dmp_file = mct_base + '.dmp'
mam_file = mct_base + '.' + langs_suffix + '.mam'
lex_file = mct_base + '.' + langs_suffix + '.lex'
log = shell.DEVNULL
try:
if log_file is not None:
log = open(log_file, 'a')
# Clean corpus for training
clean_output = os.path.join(working_dir, 'clean_corpora')
fileutils.makedirs(clean_output, exist_ok=True)
corpora = self._cleaner.clean(corpora, clean_output, (self._source_lang, self._target_lang))
# Create merged corpus and domains list file (dmp)
merged_corpus = BilingualCorpus.make_parallel(os.path.basename(mct_base), working_dir, langs)
fileutils.merge([corpus.get_file(l1) for corpus in corpora], merged_corpus.get_file(l1))
fileutils.merge([corpus.get_file(l2) for corpus in corpora], merged_corpus.get_file(l2))
with open(dmp_file, 'w') as dmp:
for corpus in corpora:
dmp.write(str(corpus.name) + ' ' + str(corpus.count_lines()) + '\n')
# Create alignments in 'bal' file and symmetrize
bal_file = aligner.align(merged_corpus, langs, self._model, working_dir, log_file)
symal_file = os.path.join(working_dir, 'alignments.' + langs_suffix + '.symal')
symal_command = [self._symal_bin, '-a=g', '-d=yes', '-f=yes', '-b=yes']
with open(bal_file) as stdin:
with open(symal_file, 'w') as stdout:
shell.execute(symal_command, stdin=stdin, stdout=stdout, stderr=log)
# Execute mtt-build
mttbuild_command = self._get_mttbuild_command(mct_base, dmp_file, l1)
with open(merged_corpus.get_file(l1)) as stdin:
shell.execute(mttbuild_command, stdin=stdin, stdout=log, stderr=log)
mttbuild_command = self._get_mttbuild_command(mct_base, dmp_file, l2)
with open(merged_corpus.get_file(l2)) as stdin:
shell.execute(mttbuild_command, stdin=stdin, stdout=log, stderr=log)
# Create 'mam' file
mam_command = [self._symal2mam_bin, mam_file]
with open(symal_file) as stdin:
shell.execute(mam_command, stdin=stdin, stdout=log, stderr=log)
# Create 'lex' file
lex_command = [self._mmlexbuild_bin, mct_base + '.', l1, l2, '-o', lex_file]
shell.execute(lex_command, stdout=log, stderr=log)
finally:
if log_file is not None:
log.close()
def tune(self,
corpora=None,
debug=False,
context_enabled=True,
random_seeds=False,
max_iterations=25,
early_stopping_value=None):
if corpora is None:
corpora = BilingualCorpus.list(
os.path.join(self.engine.data_path,
TrainingPreprocessor.DEV_FOLDER_NAME))
target_lang = self.engine.target_lang
source_lang = self.engine.source_lang
corpora = [
corpus for corpus in corpora
if source_lang in corpus.langs and target_lang in corpus.langs
]
if len(corpora) == 0:
raise IllegalArgumentException(
'No %s > %s corpora found into specified path' %
(source_lang, target_lang))
source_corpora = [
BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(),
[source_lang]) for corpus in corpora
]
reference_corpora = [
BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(),
[target_lang]) for corpus in corpora
]
cmdlogger = _tuning_logger(4)
cmdlogger.start(self, corpora)
working_dir = self.engine.get_tempdir('tuning')
mert_wd = os.path.join(working_dir, 'mert')
try:
# Tokenization
tokenizer = Tokenizer(target_lang)
tokenized_output = os.path.join(working_dir, 'reference_corpora')
fileutils.makedirs(tokenized_output, exist_ok=True)
with cmdlogger.step('Corpora tokenization') as _:
reference_corpora = tokenizer.process_corpora(
reference_corpora, tokenized_output)
# Create merged corpus
with cmdlogger.step('Merging corpus') as _:
# source
source_merged_corpus = os.path.join(working_dir,
'corpus.' + source_lang)
with open(source_merged_corpus, 'wb') as out:
for corpus in source_corpora:
out.write(corpus.get_file(source_lang) + '\n')
# target
target_merged_corpus = os.path.join(working_dir,
'corpus.' + target_lang)
fileutils.merge([
corpus.get_file(target_lang)
for corpus in reference_corpora
], target_merged_corpus)
# Run MERT algorithm
with cmdlogger.step('Tuning') as _:
# Start MERT
decoder_flags = ['--port', str(self.api.port)]
if self.api.root is not None:
decoder_flags += ['--root', self.api.root]
if not context_enabled:
decoder_flags.append('--skip-context-analysis')
decoder_flags.append('1')
fileutils.makedirs(mert_wd, exist_ok=True)
with tempfile.NamedTemporaryFile() as runtime_moses_ini:
command = [
self._mert_script, source_merged_corpus,
target_merged_corpus, self._mert_i_script,
runtime_moses_ini.name, '--threads',
str(multiprocessing.cpu_count()), '--mertdir',
cli.BIN_DIR, '--mertargs',
'\'--binary --sctype BLEU\'', '--working-dir', mert_wd,
'--nbest', '100', '--decoder-flags',
'"' + ' '.join(decoder_flags) + '"', '--nonorm',
'--closest', '--no-filter-phrase-table'
]
if early_stopping_value is not None:
command += [
'--bleuscorer', self._scorer_script,
'--bleuscorer-flags "-nt" --early-stopping-value %d'
% early_stopping_value
]
if not random_seeds:
command.append('--predictable-seeds')
if max_iterations > 0:
command.append('--maximum-iterations={num}'.format(
num=max_iterations))
with open(self.engine.get_logfile('mert'), 'wb') as log:
shell.execute(' '.join(command),
stdout=log,
stderr=log)
# Read optimized configuration
with cmdlogger.step('Applying changes') as _:
bleu_score = 0
weights = {}
found_weights = False
with open(os.path.join(mert_wd, 'moses.ini')) as moses_ini:
for line in moses_ini:
line = line.strip()
if len(line) == 0:
continue
elif found_weights:
tokens = line.split()
weights[tokens[0].rstrip('=')] = [
float(val) for val in tokens[1:]
]
elif line.startswith('# BLEU'):
bleu_score = float(line.split()[2])
elif line == '[weight]':
found_weights = True
_ = self.api.update_features(weights)
cmdlogger.completed(bleu_score)
finally:
if not debug:
self.engine.clear_tempdir("tuning")
def evaluate(self, corpora, heval_output=None, debug=False):
if len(corpora) == 0:
raise IllegalArgumentException('empty corpora')
if heval_output is not None:
fileutils.makedirs(heval_output, exist_ok=True)
target_lang = self._engine.target_lang
source_lang = self._engine.source_lang
logger = _evaluate_logger()
logger.start(corpora)
working_dir = self._engine.get_tempdir('evaluation')
try:
results = []
# Process references
with logger.step('Preparing corpora') as _:
corpora_path = os.path.join(working_dir, 'corpora')
corpora = self._xmlencoder.encode(corpora, corpora_path)
reference = os.path.join(working_dir, 'reference.' + target_lang)
source = os.path.join(working_dir, 'source.' + source_lang)
fileutils.merge([corpus.get_file(target_lang) for corpus in corpora], reference)
fileutils.merge([corpus.get_file(source_lang) for corpus in corpora], source)
if heval_output is not None:
self._heval_outputter.write(lang=target_lang, input_file=reference,
output_file=os.path.join(heval_output, 'reference.' + target_lang))
self._heval_outputter.write(lang=source_lang, input_file=source,
output_file=os.path.join(heval_output, 'source.' + source_lang))
# Translate
for translator in self._translators:
name = translator.name()
with logger.step('Translating with %s' % name) as _:
result = _EvaluationResult(translator)
results.append(result)
translations_path = os.path.join(working_dir, 'translations', result.id + '.raw')
xmltranslations_path = os.path.join(working_dir, 'translations', result.id)
fileutils.makedirs(translations_path, exist_ok=True)
try:
translated, mtt, parallelism = translator.translate(corpora, translations_path)
filename = result.id + '.' + target_lang
result.mtt = mtt
result.parallelism = parallelism
result.translated_corpora = self._xmlencoder.encode(translated, xmltranslations_path)
result.merge = os.path.join(working_dir, filename)
fileutils.merge([corpus.get_file(target_lang)
for corpus in result.translated_corpora], result.merge)
if heval_output is not None:
self._heval_outputter.write(lang=target_lang, input_file=result.merge,
output_file=os.path.join(heval_output, filename))
except TranslateError as e:
result.error = e
except Exception as e:
result.error = TranslateError('Unexpected ERROR: ' + str(e.message))
# Check corpora length
reference_lines = fileutils.linecount(reference)
for result in results:
if result.error is not None:
continue
lines = fileutils.linecount(result.merge)
if lines != reference_lines:
raise TranslateError('Invalid line count for translator %s: expected %d, found %d.'
% (result.translator.name(), reference_lines, lines))
# Scoring
scorers = [(MatecatScore(), 'pes'), (BLEUScore(), 'bleu')]
for scorer, field in scorers:
with logger.step('Calculating %s' % scorer.name()) as _:
for result in results:
if result.error is not None:
continue
setattr(result, field, scorer.calculate(result.merge, reference))
logger.completed(results, scorers)
return results
finally:
if not debug:
self._engine.clear_tempdir('evaluation')
def get_tempfile(self, name, ensure=True):
if ensure and not os.path.isdir(self.temp_path):
fileutils.makedirs(self.temp_path, exist_ok=True)
return os.path.join(self.temp_path, name)
def tune(self, corpora=None, debug=False, context_enabled=True, random_seeds=False, max_iterations=25):
if corpora is None:
corpora = BilingualCorpus.list(os.path.join(self.engine.data_path, TrainingPreprocessor.DEV_FOLDER_NAME))
if len(corpora) == 0:
raise IllegalArgumentException('empty corpora')
if not self.is_running():
raise IllegalStateException('No MMT Server running, start the engine first')
tokenizer = Tokenizer()
target_lang = self.engine.target_lang
source_lang = self.engine.source_lang
source_corpora = [BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(), [source_lang])
for corpus in corpora]
reference_corpora = [BilingualCorpus.make_parallel(corpus.name, corpus.get_folder(), [target_lang])
for corpus in corpora]
cmdlogger = _tuning_logger(4)
cmdlogger.start(self, corpora)
working_dir = self.engine.get_tempdir('tuning')
mert_wd = os.path.join(working_dir, 'mert')
try:
# Tokenization
tokenized_output = os.path.join(working_dir, 'reference_corpora')
fileutils.makedirs(tokenized_output, exist_ok=True)
with cmdlogger.step('Corpora tokenization') as _:
reference_corpora = tokenizer.process_corpora(reference_corpora, tokenized_output)
# Create merged corpus
with cmdlogger.step('Merging corpus') as _:
# source
source_merged_corpus = os.path.join(working_dir, 'corpus.' + source_lang)
with open(source_merged_corpus, 'wb') as out:
for corpus in source_corpora:
out.write(corpus.get_file(source_lang) + '\n')
# target
target_merged_corpus = os.path.join(working_dir, 'corpus.' + target_lang)
fileutils.merge([corpus.get_file(target_lang) for corpus in reference_corpora], target_merged_corpus)
# Run MERT algorithm
with cmdlogger.step('Tuning') as _:
# Start MERT
decoder_flags = ['--port', str(self.api.port)]
if not context_enabled:
decoder_flags.append('--skip-context-analysis')
decoder_flags.append('1')
fileutils.makedirs(mert_wd, exist_ok=True)
with tempfile.NamedTemporaryFile() as runtime_moses_ini:
command = [self._mert_script, source_merged_corpus, target_merged_corpus,
self._mert_i_script, runtime_moses_ini.name, '--threads',
str(multiprocessing.cpu_count()), '--mertdir', cli.BIN_DIR,
'--mertargs', '\'--binary --sctype BLEU\'', '--working-dir', mert_wd, '--nbest', '100',
'--decoder-flags', '"' + ' '.join(decoder_flags) + '"', '--nonorm', '--closest',
'--no-filter-phrase-table']
if not random_seeds:
command.append('--predictable-seeds')
if max_iterations > 0:
command.append('--maximum-iterations={num}'.format(num=max_iterations))
with open(self.engine.get_logfile('mert'), 'wb') as log:
shell.execute(' '.join(command), stdout=log, stderr=log)
# Read optimized configuration
with cmdlogger.step('Applying changes') as _:
bleu_score = 0
weights = {}
found_weights = False
with open(os.path.join(mert_wd, 'moses.ini')) as moses_ini:
for line in moses_ini:
line = line.strip()
if len(line) == 0:
continue
elif found_weights:
tokens = line.split()
weights[tokens[0].rstrip('=')] = [float(val) for val in tokens[1:]]
elif line.startswith('# BLEU'):
bleu_score = float(line.split()[2])
elif line == '[weight]':
found_weights = True
_ = self.api.update_features(weights)
cmdlogger.completed(bleu_score)
finally:
if not debug:
self.engine.clear_tempdir()
def translate(self, corpora, dest_path=None, debug=False):
if len(corpora) == 0:
raise IllegalArgumentException('empty corpora')
if dest_path:
fileutils.makedirs(dest_path, exist_ok=True)
target_lang = self._engine.target_lang
source_lang = self._engine.source_lang
working_dir = self._engine.get_tempdir('evaluation')
have_references = False
try:
results = []
# Process references
corpora_path = os.path.join(working_dir, 'corpora')
corpora = self._xmlencoder.encode(corpora, corpora_path)
reference = os.path.join(working_dir, 'reference.' + target_lang)
source = os.path.join(working_dir, 'source.' + source_lang)
refs = [corpus.get_file(target_lang) for corpus in corpora if corpus.get_file(target_lang)]
have_references = len(refs) > 0
fileutils.merge(refs, reference) # tolerates missing reference
fileutils.merge([corpus.get_file(source_lang) for corpus in corpora], source)
if dest_path:
for corpus in corpora:
corpus.copy(dest_path, suffixes={source_lang: '.src', target_lang: '.ref', 'tmx': '.src'})
# Translate
translator = self._translator
name = translator.name()
result = _EvaluationResult(translator)
results.append(result)
translations_path = os.path.join(working_dir, 'translations', result.id + '.raw')
xmltranslations_path = os.path.join(working_dir, 'translations', result.id)
fileutils.makedirs(translations_path, exist_ok=True)
try:
translated, mtt, parallelism = translator.translate(corpora, translations_path)
filename = result.id + '.' + target_lang
result.mtt = mtt
result.parallelism = parallelism
result.translated_corpora = self._xmlencoder.encode(translated, xmltranslations_path)
result.merge = os.path.join(working_dir, filename)
fileutils.merge([corpus.get_file(target_lang)
for corpus in result.translated_corpora], result.merge)
if dest_path:
for corpus in result.translated_corpora:
corpus.copy(dest_path, suffixes={target_lang: '.hyp', 'tmx': '.hyp'})
except TranslateError as e:
result.error = e
except Exception as e:
result.error = TranslateError('Unexpected ERROR: ' + str(e.message))
if result.error is None:
if have_references:
scorer = BLEUScore()
# bleu in range [0;1)
bleu = scorer.calculate(result.merge, reference)
return bleu
else:
return True
else:
print(result.error)
return None
finally:
if not debug:
self._engine.clear_tempdir('evaluation')
