Python nltk.internals.find_jars_within_path() Examples

def find_maltparser(parser_dirname):
    """
    A module to find MaltParser .jar file and its dependencies.
    """
    if os.path.exists(parser_dirname): # If a full path is given.
        _malt_dir = parser_dirname
    else: # Try to find path to maltparser directory in environment variables.
        _malt_dir = find_dir(parser_dirname, env_vars=('MALT_PARSER',))
    # Checks that that the found directory contains all the necessary .jar
    malt_dependencies = ['','','']
    _malt_jars = set(find_jars_within_path(_malt_dir))
    _jars = set(jar.rpartition('/')[2] for jar in _malt_jars)
    malt_dependencies = set(['log4j.jar', 'libsvm.jar', 'liblinear-1.8.jar'])

    assert malt_dependencies.issubset(_jars)
    assert any(filter(lambda i: i.startswith('maltparser-') and i.endswith('.jar'), _jars))
    return list(_malt_jars) 

def __init__(self, model_filename, path_to_jar=None, encoding='utf8', verbose=False, java_options='-mx1000m'):
        if not self._JAR:
            warnings.warn('The StanfordTagger class is not meant to be '
                          'instantiated directly. Did you mean StanfordPOSTagger or StanfordNERTagger?')
        self._stanford_jar = find_jar(
            self._JAR, path_to_jar,
            searchpath=(), url=_stanford_url,
            verbose=verbose)

        self._stanford_model = find_file(model_filename,
                                         env_vars=('STANFORD_MODELS',), verbose=verbose)

        # Adding logging jar files to classpath
        stanford_dir = os.path.split(self._stanford_jar)[0]
        self._stanford_jar = tuple(find_jars_within_path(stanford_dir))

        self._encoding = encoding
        self.java_options = java_options 

def find_maltparser(parser_dirname):
    """
    A module to find MaltParser .jar file and its dependencies.
    """
    if os.path.exists(parser_dirname):  # If a full path is given.
        _malt_dir = parser_dirname
    else:  # Try to find path to maltparser directory in environment variables.
        _malt_dir = find_dir(parser_dirname, env_vars=('MALT_PARSER',))
    # Checks that that the found directory contains all the necessary .jar
    malt_dependencies = ['', '', '']
    _malt_jars = set(find_jars_within_path(_malt_dir))
    _jars = set(os.path.split(jar)[1] for jar in _malt_jars)
    malt_dependencies = set(['log4j.jar', 'libsvm.jar', 'liblinear-1.8.jar'])

    assert malt_dependencies.issubset(_jars)
    assert any(
        filter(lambda i: i.startswith('maltparser-') and i.endswith('.jar'), _jars)
    )
    return list(_malt_jars) 

def get_postag_with_record(records, pairs):
    path = os.path.dirname(__file__)
    path = path[:path.rfind(os.sep, 0, len(path)-10)+1] + 'stanford-postagger/'
    print(path)
    # jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
    jar = path + '/stanford-postagger.jar'
    model = path + '/models/english-bidirectional-distsim.tagger'
    pos_tagger = StanfordPOSTagger(model, jar)
    # model = '/Users/memray/Project/stanford/stanford-postagger/models/english-left3words-distsim.tagger'
    # model = '/Users/memray/Project/stanford/stanford-postagger/models/english-bidirectional-distsim.tagger'

    stanford_dir = jar.rpartition('/')[0]
    stanford_jars = find_jars_within_path(stanford_dir)
    pos_tagger._stanford_jar = ':'.join(stanford_jars)

    tagged_source = []
    # Predict on testing data
    for idx, (record, pair) in enumerate(zip(records, pairs)):  # len(test_data_plain)
        print('*' * 100)
        print('File: '  + record['name'])
        print('Input: ' + str(pair[0]))
        text = pos_tagger.tag(pair[0])
        print('[%d/%d][%d] : %s' % (idx, len(records) , len(pair[0]), str(text)))
        tagged_source.append(text)

    return tagged_source 

def get_postag_with_index(sources, idx2word, word2idx):
    path = os.path.dirname(__file__)
    path = path[:path.rfind(os.sep, 0, len(path)-10)+1] + 'stanford-postagger/'
    print(path)
    # jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
    jar = path + '/stanford-postagger.jar'
    model = path + '/models/english-bidirectional-distsim.tagger'
    pos_tagger = StanfordPOSTagger(model, jar)
    # model = '/Users/memray/Project/stanford/stanford-postagger/models/english-left3words-distsim.tagger'
    # model = '/Users/memray/Project/stanford/stanford-postagger/models/english-bidirectional-distsim.tagger'

    stanford_dir = jar.rpartition('/')[0]
    stanford_jars = find_jars_within_path(stanford_dir)
    pos_tagger._stanford_jar = ':'.join(stanford_jars)

    tagged_source = []
    # Predict on testing data
    for idx in xrange(len(sources)):  # len(test_data_plain)
        test_s_o = sources[idx]
        source_text = keyphrase_utils.cut_zero(test_s_o, idx2word)
        text = pos_tagger.tag(source_text)
        print('[%d/%d] : %s' % (idx, len(sources), str(text)))

        tagged_source.append(text)

    return tagged_source 

def load_pos_tagger():
    path = os.path.dirname(__file__)
    path =  os.path.join(file_dir[: file_dir.rfind('pykp') + 4], 'stanford-postagger')
    print(path)
    # jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
    jar = path + '/stanford-postagger.jar'
    model = path + '/models/english-bidirectional-distsim.tagger'
    pos_tagger = StanfordPOSTagger(model, jar)

    stanford_dir = jar.rpartition('/')[0]
    stanford_jars = find_jars_within_path(stanford_dir)
    pos_tagger._stanford_jar = ':'.join(stanford_jars)

    return pos_tagger 

def __init__(self):
        self.parser = StanfordParser(
            model_path='edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz')
        stanford_dir = self.parser._classpath[0].rpartition('/')[0]
        self.parser._classpath = tuple(find_jars_within_path(stanford_dir)) 

def load_pos_tagger():
    path = os.path.dirname(__file__)
    path =  os.path.join(file_dir[: file_dir.rfind('pykp') + 4], 'stanford-postagger')
    print(path)
    # jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
    jar = path + '/stanford-postagger.jar'
    model = path + '/models/english-bidirectional-distsim.tagger'
    pos_tagger = StanfordPOSTagger(model, jar)

    stanford_dir = jar.rpartition('/')[0]
    stanford_jars = find_jars_within_path(stanford_dir)
    pos_tagger._stanford_jar = ':'.join(stanford_jars)

    return pos_tagger 

def load_pos_tagger(stanford_base_dir):
    # path = os.path.dirname(__file__)
    # path = os.path.join(file_dir[: file_dir.rfind('pykp') + 4], 'stanford-postagger')
    # print(path)
    # jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
    jar = stanford_base_dir + '/stanford-postagger.jar'
    model = stanford_base_dir + '/models/english-bidirectional-distsim.tagger'
    pos_tagger = StanfordPOSTagger(model_filename=model, path_to_jar=jar)

    stanford_base_dir = jar.rpartition('/')[0]
    stanford_jars = find_jars_within_path(stanford_base_dir)
    pos_tagger._stanford_jar = ':'.join(stanford_jars)

    return pos_tagger 

def check_postag(config):
    train_set, validation_set, test_set, idx2word, word2idx = deserialize_from_file(config['dataset'])

    path = os.path.dirname(__file__)
    path = path[:path.rfind(os.sep, 0, len(path)-10)+1] + 'stanford-postagger/'
    jar = path + '/stanford-postagger.jar'
    model = path + '/models/english-bidirectional-distsim.tagger'
    pos_tagger = StanfordPOSTagger(model, jar)

    for dataset_name in config['testing_datasets']:
        # override the original test_set
        # test_set = load_testing_data(dataset_name, kwargs=dict(basedir=config['path']))(idx2word, word2idx, config['preprocess_type'])

        test_sets = load_additional_testing_data(config['testing_datasets'], idx2word, word2idx, config)
        test_set = test_sets[dataset_name]

        # print(dataset_name)
        # print('Avg length=%d, Max length=%d' % (np.average([len(s) for s in test_set['source']]), np.max([len(s) for s in test_set['source']])))
        test_data_plain = zip(*(test_set['source'], test_set['target']))

        test_size = len(test_data_plain)

        # Alternatively to setting the CLASSPATH add the jar and model via their path:
        jar = '/Users/memray/Project/stanford/stanford-postagger/stanford-postagger.jar'
        # model = '/Users/memray/Project/stanford/stanford-postagger/models/english-left3words-distsim.tagger'
        model = '/Users/memray/Project/stanford/stanford-postagger/models/english-bidirectional-distsim.tagger'
        pos_tagger = StanfordPOSTagger(model, jar)

        for idx in xrange(len(test_data_plain)):  # len(test_data_plain)
            test_s_o, test_t_o = test_data_plain[idx]

            source = keyphrase_utils.cut_zero(test_s_o, idx2word)

            print(source)

            # Add other jars from Stanford directory
            stanford_dir = jar.rpartition('/')[0]
            stanford_jars = find_jars_within_path(stanford_dir)
            pos_tagger._stanford_jar = ':'.join(stanford_jars)

            text = pos_tagger.tag(source)
            print(text)