def __init__(self, path_to_jar=None, path_to_models_jar=None, path_to_ejml_jar=None, model_path='edu/stanford/nlp/models/parser/lexparser/englishPCFG.ser.gz', encoding='utf8', verbose=False, java_options='-mx3G'):
""""""
self._stanford_jar = find_jar(
self._JAR, path_to_jar,
env_vars=('STANFORD_PARSER',),
searchpath=(), url=_stanford_url,
verbose=verbose)
# find the most recent model
self._model_jar=max(
find_jar_iter(
self._MODEL_JAR_PATTERN, path_to_models_jar,
env_vars=('STANFORD_MODELS',),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True),
key=lambda model_name: re.match(self._MODEL_JAR_PATTERN, model_name))
# find the most recent ejml
self._ejml_jar=max(
find_jar_iter(
self._EJML_JAR_PATTERN, path_to_ejml_jar,
env_vars=('STANFORD_EJML',),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True),
key=lambda ejml_name: re.match(self._EJML_JAR_PATTERN, ejml_name))
self.model_path = model_path
self._encoding = encoding
self.java_options = java_options
def __init__(self, path_to_jar=None, path_to_models_jar=None,
model_path='edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz',
encoding='utf8', verbose=False,
java_options='-mx1000m', corenlp_options=''):
# find the most recent code and model jar
stanford_jar = max(
find_jar_iter(
self._JAR, path_to_jar,
env_vars=('STANFORD_PARSER', 'STANFORD_CORENLP'),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True
),
key=lambda model_name: re.match(self._JAR, model_name)
)
model_jar=max(
find_jar_iter(
self._MODEL_JAR_PATTERN, path_to_models_jar,
env_vars=('STANFORD_MODELS', 'STANFORD_CORENLP'),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True
),
key=lambda model_name: re.match(self._MODEL_JAR_PATTERN, model_name)
)
self._classpath = (stanford_jar, model_jar)
self.model_path = model_path
self._encoding = encoding
self.corenlp_options = corenlp_options
self.java_options = java_options
def __init__(self, path_to_jar=None, path_to_models_jar=None,
model_path='edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz',
encoding='utf8', verbose=False,
java_options='-mx1000m', corenlp_options=''):
# find the most recent code and model jar
stanford_jar = max(
find_jar_iter(
self._JAR, path_to_jar,
env_vars=('STANFORD_PARSER', 'STANFORD_CORENLP'),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True
),
key=lambda model_name: re.match(self._JAR, model_name)
)
model_jar=max(
find_jar_iter(
self._MODEL_JAR_PATTERN, path_to_models_jar,
env_vars=('STANFORD_MODELS', 'STANFORD_CORENLP'),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True
),
key=lambda model_name: re.match(self._MODEL_JAR_PATTERN, model_name)
)
self._classpath = (stanford_jar, model_jar)
self.model_path = model_path
self._encoding = encoding
self.corenlp_options = corenlp_options
self.java_options = java_options
def __init__(
self,
path_to_jar=None,
path_to_models_jar=None,
verbose=False,
java_options=None,
corenlp_options=None,
port=None,
):
if corenlp_options is None:
corenlp_options = [
'-preload',
'tokenize,ssplit,pos,lemma,parse,depparse',
]
jars = list(
find_jar_iter(
self._JAR,
path_to_jar,
env_vars=('CORENLP', ),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
))
# find the most recent code and model jar
stanford_jar = max(
jars, key=lambda model_name: re.match(self._JAR, model_name))
if port is None:
try:
port = try_port(9000)
except socket.error:
port = try_port()
corenlp_options.append(str(port))
else:
try_port(port)
self.url = 'http://localhost:{}'.format(port)
model_jar = max(find_jar_iter(
self._MODEL_JAR_PATTERN,
path_to_models_jar,
env_vars=('CORENLP_MODELS', ),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_name: re.match(
self._MODEL_JAR_PATTERN, model_name))
self.verbose = verbose
self._classpath = stanford_jar, model_jar
self.corenlp_options = corenlp_options
self.java_options = java_options or ['-mx2g']
def __init__(self, path_to_jar=None, path_to_models_jar=None, path_to_ejml_jar=None, model_path='edu/stanford/nlp/models/parser/lexparser/englishPCFG.ser.gz', encoding='utf8', verbose=False, java_options='-mx3G'):
""""""
self._stanford_jar = find_jar(
self._JAR, path_to_jar,
env_vars=('STANFORD_PARSER',),
searchpath=(), url=_stanford_url,
verbose=verbose)
# find the most recent model
self._model_jar=max(
find_jar_iter(
self._MODEL_JAR_PATTERN, path_to_models_jar,
env_vars=('STANFORD_MODELS',),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True),
key=lambda model_name: re.match(self._MODEL_JAR_PATTERN, model_name))
# find the most recent ejml
self._ejml_jar=max(
find_jar_iter(
self._EJML_JAR_PATTERN, path_to_ejml_jar,
env_vars=('STANFORD_EJML',),
searchpath=(), url=_stanford_url,
verbose=verbose, is_regex=True),
key=lambda ejml_name: re.match(self._EJML_JAR_PATTERN, ejml_name))
self.model_path = model_path
self._encoding = encoding
self.java_options = java_options
def __init__(
self, path_to_jar=None, path_to_models_jar=None, verbose=False,
java_options=None, corenlp_options=None, port=None,
):
if corenlp_options is None:
corenlp_options = [
'-preload', 'tokenize,ssplit,pos,lemma,parse,depparse',
]
jars = list(find_jar_iter(
self._JAR,
path_to_jar,
env_vars=('CORENLP', ),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
))
# find the most recent code and model jar
stanford_jar = max(
jars,
key=lambda model_name: re.match(self._JAR, model_name)
)
if port is None:
try:
port = try_port(9000)
except socket.error:
port = try_port()
corenlp_options.append(str(port))
else:
try_port(port)
self.url = 'http://localhost:{}'.format(port)
model_jar = max(
find_jar_iter(
self._MODEL_JAR_PATTERN,
path_to_models_jar,
env_vars=('CORENLP_MODELS', ),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_name: re.match(self._MODEL_JAR_PATTERN, model_name)
)
self.verbose = verbose
self._classpath = stanford_jar, model_jar
self.corenlp_options = corenlp_options
self.java_options = java_options or ['-mx2g']
def __init__(
self,
path_to_jar=None,
path_to_models_jar=None,
verbose=False,
java_options=None,
corenlp_options=None,
port=4466,
):
'''
if corenlp_options is None:
corenlp_options = ['-preload']
'''
jars = list(
find_jar_iter(
self._JAR,
path_to_jar,
env_vars=('CORENLP', ),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
))
# find the most recent code and model jar
stanford_jar = max(
jars, key=lambda model_name: re.match(self._JAR, model_name))
port = try_port()
corenlp_options.extend(['-port', str(port)])
self.host = 'localhost'
self.port = port
model_jar = max(
find_jar_iter(
self._MODEL_JAR_PATTERN,
path_to_models_jar,
env_vars=('CORENLP_MODELS', ),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_name: re.match(self._MODEL_JAR_PATTERN, model_name
),
)
self.verbose = verbose
self._classpath = stanford_jar, model_jar
self.corenlp_options = corenlp_options
self.java_options = java_options or ['-mx2g']
def __init__(
self,
path_to_jar=None,
path_to_models_jar=None,
model_path='edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz',
encoding='utf8',
verbose=False,
java_options='-mx4g',
corenlp_options='',
):
# find the most recent code and model jar
stanford_jar = max(
find_jar_iter(
self._JAR,
path_to_jar,
env_vars=('STANFORD_PARSER', 'STANFORD_CORENLP'),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_path: os.path.dirname(model_path),
)
model_jar = max(
find_jar_iter(
self._MODEL_JAR_PATTERN,
path_to_models_jar,
env_vars=('STANFORD_MODELS', 'STANFORD_CORENLP'),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_path: os.path.dirname(model_path),
)
# self._classpath = (stanford_jar, model_jar)
# Adding logging jar files to classpath
stanford_dir = os.path.split(stanford_jar)[0]
self._classpath = tuple([model_jar] +
find_jars_within_path(stanford_dir))
self.model_path = model_path
self._encoding = encoding
self.corenlp_options = corenlp_options
self.java_options = java_options
def __init__(
self,
path_to_jar=None,
path_to_models_jar=None,
model_path='edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz',
encoding='utf8',
verbose=False,
java_options='-mx4g',
corenlp_options='',
):
# find the most recent code and model jar
stanford_jar = max(
find_jar_iter(
self._JAR,
path_to_jar,
env_vars=('STANFORD_PARSER', 'STANFORD_CORENLP'),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_path: os.path.dirname(model_path),
)
model_jar = max(
find_jar_iter(
self._MODEL_JAR_PATTERN,
path_to_models_jar,
env_vars=('STANFORD_MODELS', 'STANFORD_CORENLP'),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_path: os.path.dirname(model_path),
)
# self._classpath = (stanford_jar, model_jar)
# Adding logging jar files to classpath
stanford_dir = os.path.split(stanford_jar)[0]
self._classpath = tuple([model_jar] + find_jars_within_path(stanford_dir))
self.model_path = model_path
self._encoding = encoding
self.corenlp_options = corenlp_options
self.java_options = java_options
def __init__(
self,
path_to_jar=None,
path_to_models_jar=None,
model_path="edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz",
encoding="UTF-8",
verbose=False,
java_options="-mx1000m",
):
self._stanford_jar = find_jar(
self._JAR, path_to_jar, env_vars=("STANFORD_PARSER",), searchpath=(), url=_stanford_url, verbose=verbose
)
# find the most recent model
self._model_jar = max(
find_jar_iter(
self._MODEL_JAR_PATTERN,
path_to_models_jar,
env_vars=("STANFORD_MODELS",),
searchpath=(),
url=_stanford_url,
verbose=verbose,
is_regex=True,
),
key=lambda model_name: re.match(self._MODEL_JAR_PATTERN, model_name),
)
self.model_path = model_path
self._encoding = encoding
self.java_options = java_options