Spaces:
Build error
Build error
File size: 4,260 Bytes
e62781a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 |
#!/usr/bin/env python3
# Copyright 2017-present, Facebook, Inc.
# All rights reserved.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
"""Base tokenizer/tokens classes and utilities."""
import copy
class Tokens(object):
"""A class to represent a list of tokenized text."""
TEXT = 0
TEXT_WS = 1
SPAN = 2
POS = 3
LEMMA = 4
NER = 5
def __init__(self, data, annotators, opts=None):
self.data = data
self.annotators = annotators
self.opts = opts or {}
def __len__(self):
"""The number of tokens."""
return len(self.data)
def slice(self, i=None, j=None):
"""Return a view of the list of tokens from [i, j)."""
new_tokens = copy.copy(self)
new_tokens.data = self.data[i: j]
return new_tokens
def untokenize(self):
"""Returns the original text (with whitespace reinserted)."""
return ''.join([t[self.TEXT_WS] for t in self.data]).strip()
def words(self, uncased=False):
"""Returns a list of the text of each token
Args:
uncased: lower cases text
"""
if uncased:
return [t[self.TEXT].lower() for t in self.data]
else:
return [t[self.TEXT] for t in self.data]
def offsets(self):
"""Returns a list of [start, end) character offsets of each token."""
return [t[self.SPAN] for t in self.data]
def pos(self):
"""Returns a list of part-of-speech tags of each token.
Returns None if this annotation was not included.
"""
if 'pos' not in self.annotators:
return None
return [t[self.POS] for t in self.data]
def lemmas(self):
"""Returns a list of the lemmatized text of each token.
Returns None if this annotation was not included.
"""
if 'lemma' not in self.annotators:
return None
return [t[self.LEMMA] for t in self.data]
def entities(self):
"""Returns a list of named-entity-recognition tags of each token.
Returns None if this annotation was not included.
"""
if 'ner' not in self.annotators:
return None
return [t[self.NER] for t in self.data]
def ngrams(self, n=1, uncased=False, filter_fn=None, as_strings=True):
"""Returns a list of all ngrams from length 1 to n.
Args:
n: upper limit of ngram length
uncased: lower cases text
filter_fn: user function that takes in an ngram list and returns
True or False to keep or not keep the ngram
as_string: return the ngram as a string vs list
"""
def _skip(gram):
if not filter_fn:
return False
return filter_fn(gram)
words = self.words(uncased)
ngrams = [(s, e + 1)
for s in range(len(words))
for e in range(s, min(s + n, len(words)))
if not _skip(words[s:e + 1])]
# Concatenate into strings
if as_strings:
ngrams = ['{}'.format(' '.join(words[s:e])) for (s, e) in ngrams]
return ngrams
def entity_groups(self):
"""Group consecutive entity tokens with the same NER tag."""
entities = self.entities()
if not entities:
return None
non_ent = self.opts.get('non_ent', 'O')
groups = []
idx = 0
while idx < len(entities):
ner_tag = entities[idx]
# Check for entity tag
if ner_tag != non_ent:
# Chomp the sequence
start = idx
while (idx < len(entities) and entities[idx] == ner_tag):
idx += 1
groups.append((self.slice(start, idx).untokenize(), ner_tag))
else:
idx += 1
return groups
class Tokenizer(object):
"""Base tokenizer class.
Tokenizers implement tokenize, which should return a Tokens class.
"""
def tokenize(self, text):
raise NotImplementedError
def shutdown(self):
pass
def __del__(self):
self.shutdown()
|