395 lines
15 KiB
Python
395 lines
15 KiB
Python
# coding=utf-8
|
||
# Copyright 2018 The Open AI Team Authors and The HuggingFace Inc. team.
|
||
#
|
||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||
# you may not use this file except in compliance with the License.
|
||
# You may obtain a copy of the License at
|
||
#
|
||
# http://www.apache.org/licenses/LICENSE-2.0
|
||
#
|
||
# Unless required by applicable law or agreed to in writing, software
|
||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||
# See the License for the specific language governing permissions and
|
||
# limitations under the License.
|
||
"""Tokenization classes for OpenAI GPT."""
|
||
|
||
|
||
import json
|
||
import os
|
||
import re
|
||
import unicodedata
|
||
from typing import Optional, Tuple
|
||
|
||
from ...tokenization_utils import PreTrainedTokenizer, _is_control, _is_punctuation, _is_whitespace
|
||
from ...utils import logging
|
||
|
||
|
||
logger = logging.get_logger(__name__)
|
||
|
||
VOCAB_FILES_NAMES = {
|
||
"vocab_file": "vocab.json",
|
||
"merges_file": "merges.txt",
|
||
}
|
||
|
||
|
||
# Copied from transformers.models.bert.tokenization_bert.whitespace_tokenize
|
||
def whitespace_tokenize(text):
|
||
"""Runs basic whitespace cleaning and splitting on a piece of text."""
|
||
text = text.strip()
|
||
if not text:
|
||
return []
|
||
tokens = text.split()
|
||
return tokens
|
||
|
||
|
||
# Copied from transformers.models.bert.tokenization_bert.BasicTokenizer
|
||
class BasicTokenizer(object):
|
||
"""
|
||
Constructs a BasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).
|
||
|
||
Args:
|
||
do_lower_case (`bool`, *optional*, defaults to `True`):
|
||
Whether or not to lowercase the input when tokenizing.
|
||
never_split (`Iterable`, *optional*):
|
||
Collection of tokens which will never be split during tokenization. Only has an effect when
|
||
`do_basic_tokenize=True`
|
||
tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
|
||
Whether or not to tokenize Chinese characters.
|
||
|
||
This should likely be deactivated for Japanese (see this
|
||
[issue](https://github.com/huggingface/transformers/issues/328)).
|
||
strip_accents (`bool`, *optional*):
|
||
Whether or not to strip all accents. If this option is not specified, then it will be determined by the
|
||
value for `lowercase` (as in the original BERT).
|
||
do_split_on_punc (`bool`, *optional*, defaults to `True`):
|
||
In some instances we want to skip the basic punctuation splitting so that later tokenization can capture
|
||
the full context of the words, such as contractions.
|
||
"""
|
||
|
||
def __init__(
|
||
self,
|
||
do_lower_case=True,
|
||
never_split=None,
|
||
tokenize_chinese_chars=True,
|
||
strip_accents=None,
|
||
do_split_on_punc=True,
|
||
):
|
||
if never_split is None:
|
||
never_split = []
|
||
self.do_lower_case = do_lower_case
|
||
self.never_split = set(never_split)
|
||
self.tokenize_chinese_chars = tokenize_chinese_chars
|
||
self.strip_accents = strip_accents
|
||
self.do_split_on_punc = do_split_on_punc
|
||
|
||
def tokenize(self, text, never_split=None):
|
||
"""
|
||
Basic Tokenization of a piece of text. For sub-word tokenization, see WordPieceTokenizer.
|
||
|
||
Args:
|
||
never_split (`List[str]`, *optional*)
|
||
Kept for backward compatibility purposes. Now implemented directly at the base class level (see
|
||
[`PreTrainedTokenizer.tokenize`]) List of token not to split.
|
||
"""
|
||
# union() returns a new set by concatenating the two sets.
|
||
never_split = self.never_split.union(set(never_split)) if never_split else self.never_split
|
||
text = self._clean_text(text)
|
||
|
||
# This was added on November 1st, 2018 for the multilingual and Chinese
|
||
# models. This is also applied to the English models now, but it doesn't
|
||
# matter since the English models were not trained on any Chinese data
|
||
# and generally don't have any Chinese data in them (there are Chinese
|
||
# characters in the vocabulary because Wikipedia does have some Chinese
|
||
# words in the English Wikipedia.).
|
||
if self.tokenize_chinese_chars:
|
||
text = self._tokenize_chinese_chars(text)
|
||
# prevents treating the same character with different unicode codepoints as different characters
|
||
unicode_normalized_text = unicodedata.normalize("NFC", text)
|
||
orig_tokens = whitespace_tokenize(unicode_normalized_text)
|
||
split_tokens = []
|
||
for token in orig_tokens:
|
||
if token not in never_split:
|
||
if self.do_lower_case:
|
||
token = token.lower()
|
||
if self.strip_accents is not False:
|
||
token = self._run_strip_accents(token)
|
||
elif self.strip_accents:
|
||
token = self._run_strip_accents(token)
|
||
split_tokens.extend(self._run_split_on_punc(token, never_split))
|
||
|
||
output_tokens = whitespace_tokenize(" ".join(split_tokens))
|
||
return output_tokens
|
||
|
||
def _run_strip_accents(self, text):
|
||
"""Strips accents from a piece of text."""
|
||
text = unicodedata.normalize("NFD", text)
|
||
output = []
|
||
for char in text:
|
||
cat = unicodedata.category(char)
|
||
if cat == "Mn":
|
||
continue
|
||
output.append(char)
|
||
return "".join(output)
|
||
|
||
def _run_split_on_punc(self, text, never_split=None):
|
||
"""Splits punctuation on a piece of text."""
|
||
if not self.do_split_on_punc or (never_split is not None and text in never_split):
|
||
return [text]
|
||
chars = list(text)
|
||
i = 0
|
||
start_new_word = True
|
||
output = []
|
||
while i < len(chars):
|
||
char = chars[i]
|
||
if _is_punctuation(char):
|
||
output.append([char])
|
||
start_new_word = True
|
||
else:
|
||
if start_new_word:
|
||
output.append([])
|
||
start_new_word = False
|
||
output[-1].append(char)
|
||
i += 1
|
||
|
||
return ["".join(x) for x in output]
|
||
|
||
def _tokenize_chinese_chars(self, text):
|
||
"""Adds whitespace around any CJK character."""
|
||
output = []
|
||
for char in text:
|
||
cp = ord(char)
|
||
if self._is_chinese_char(cp):
|
||
output.append(" ")
|
||
output.append(char)
|
||
output.append(" ")
|
||
else:
|
||
output.append(char)
|
||
return "".join(output)
|
||
|
||
def _is_chinese_char(self, cp):
|
||
"""Checks whether CP is the codepoint of a CJK character."""
|
||
# This defines a "chinese character" as anything in the CJK Unicode block:
|
||
# https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
|
||
#
|
||
# Note that the CJK Unicode block is NOT all Japanese and Korean characters,
|
||
# despite its name. The modern Korean Hangul alphabet is a different block,
|
||
# as is Japanese Hiragana and Katakana. Those alphabets are used to write
|
||
# space-separated words, so they are not treated specially and handled
|
||
# like the all of the other languages.
|
||
if (
|
||
(cp >= 0x4E00 and cp <= 0x9FFF)
|
||
or (cp >= 0x3400 and cp <= 0x4DBF) #
|
||
or (cp >= 0x20000 and cp <= 0x2A6DF) #
|
||
or (cp >= 0x2A700 and cp <= 0x2B73F) #
|
||
or (cp >= 0x2B740 and cp <= 0x2B81F) #
|
||
or (cp >= 0x2B820 and cp <= 0x2CEAF) #
|
||
or (cp >= 0xF900 and cp <= 0xFAFF)
|
||
or (cp >= 0x2F800 and cp <= 0x2FA1F) #
|
||
): #
|
||
return True
|
||
|
||
return False
|
||
|
||
def _clean_text(self, text):
|
||
"""Performs invalid character removal and whitespace cleanup on text."""
|
||
output = []
|
||
for char in text:
|
||
cp = ord(char)
|
||
if cp == 0 or cp == 0xFFFD or _is_control(char):
|
||
continue
|
||
if _is_whitespace(char):
|
||
output.append(" ")
|
||
else:
|
||
output.append(char)
|
||
return "".join(output)
|
||
|
||
|
||
def get_pairs(word):
|
||
"""
|
||
Return set of symbol pairs in a word. word is represented as tuple of symbols (symbols being variable-length
|
||
strings)
|
||
"""
|
||
pairs = set()
|
||
prev_char = word[0]
|
||
for char in word[1:]:
|
||
pairs.add((prev_char, char))
|
||
prev_char = char
|
||
return pairs
|
||
|
||
|
||
def text_standardize(text):
|
||
"""
|
||
fixes some issues the spacy tokenizer had on books corpus also does some whitespace standardization
|
||
"""
|
||
text = text.replace("—", "-")
|
||
text = text.replace("–", "-")
|
||
text = text.replace("―", "-")
|
||
text = text.replace("…", "...")
|
||
text = text.replace("´", "'")
|
||
text = re.sub(r"""(-+|~+|!+|"+|;+|\?+|\++|,+|\)+|\(+|\\+|\/+|\*+|\[+|\]+|}+|{+|\|+|_+)""", r" \1 ", text)
|
||
text = re.sub(r"\s*\n\s*", " \n ", text)
|
||
text = re.sub(r"[^\S\n]+", " ", text)
|
||
return text.strip()
|
||
|
||
|
||
class OpenAIGPTTokenizer(PreTrainedTokenizer):
|
||
"""
|
||
Construct a GPT Tokenizer. Based on Byte-Pair-Encoding with the following peculiarities:
|
||
|
||
- lowercases all inputs,
|
||
- uses `SpaCy` tokenizer and `ftfy` for pre-BPE tokenization if they are installed, fallback to BERT's
|
||
`BasicTokenizer` if not.
|
||
|
||
This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
|
||
this superclass for more information regarding those methods.
|
||
|
||
Args:
|
||
vocab_file (`str`):
|
||
Path to the vocabulary file.
|
||
merges_file (`str`):
|
||
Path to the merges file.
|
||
unk_token (`str`, *optional*, defaults to `"<unk>"`):
|
||
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
|
||
token instead.
|
||
"""
|
||
|
||
vocab_files_names = VOCAB_FILES_NAMES
|
||
model_input_names = ["input_ids", "attention_mask"]
|
||
|
||
def __init__(self, vocab_file, merges_file, unk_token="<unk>", **kwargs):
|
||
try:
|
||
import ftfy
|
||
from spacy.lang.en import English
|
||
|
||
_nlp = English()
|
||
self.nlp = _nlp.tokenizer
|
||
self.fix_text = ftfy.fix_text
|
||
except ImportError:
|
||
logger.warning("ftfy or spacy is not installed using BERT BasicTokenizer instead of SpaCy & ftfy.")
|
||
self.nlp = BasicTokenizer(do_lower_case=True)
|
||
self.fix_text = None
|
||
|
||
with open(vocab_file, encoding="utf-8") as vocab_handle:
|
||
self.encoder = json.load(vocab_handle)
|
||
self.decoder = {v: k for k, v in self.encoder.items()}
|
||
with open(merges_file, encoding="utf-8") as merges_handle:
|
||
merges = merges_handle.read().split("\n")[1:-1]
|
||
merges = [tuple(merge.split()) for merge in merges]
|
||
self.bpe_ranks = dict(zip(merges, range(len(merges))))
|
||
self.cache = {}
|
||
|
||
super().__init__(unk_token=unk_token, **kwargs)
|
||
|
||
@property
|
||
def do_lower_case(self):
|
||
return True
|
||
|
||
@property
|
||
def vocab_size(self):
|
||
return len(self.encoder)
|
||
|
||
def get_vocab(self):
|
||
return dict(self.encoder, **self.added_tokens_encoder)
|
||
|
||
def bpe(self, token):
|
||
word = tuple(token[:-1]) + (token[-1] + "</w>",)
|
||
if token in self.cache:
|
||
return self.cache[token]
|
||
pairs = get_pairs(word)
|
||
|
||
if not pairs:
|
||
return token + "</w>"
|
||
|
||
while True:
|
||
bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
|
||
if bigram not in self.bpe_ranks:
|
||
break
|
||
first, second = bigram
|
||
new_word = []
|
||
i = 0
|
||
while i < len(word):
|
||
try:
|
||
j = word.index(first, i)
|
||
except ValueError:
|
||
new_word.extend(word[i:])
|
||
break
|
||
else:
|
||
new_word.extend(word[i:j])
|
||
i = j
|
||
|
||
if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
|
||
new_word.append(first + second)
|
||
i += 2
|
||
else:
|
||
new_word.append(word[i])
|
||
i += 1
|
||
new_word = tuple(new_word)
|
||
word = new_word
|
||
if len(word) == 1:
|
||
break
|
||
else:
|
||
pairs = get_pairs(word)
|
||
word = " ".join(word)
|
||
if word == "\n </w>":
|
||
word = "\n</w>"
|
||
self.cache[token] = word
|
||
return word
|
||
|
||
def _tokenize(self, text):
|
||
"""Tokenize a string."""
|
||
split_tokens = []
|
||
if self.fix_text is None:
|
||
# Using BERT's BasicTokenizer
|
||
text = self.nlp.tokenize(text)
|
||
for token in text:
|
||
split_tokens.extend(list(self.bpe(token).split(" ")))
|
||
else:
|
||
# Using SpaCy & ftfy (original tokenization process of OpenAI GPT)
|
||
text = self.nlp(text_standardize(self.fix_text(text)))
|
||
for token in text:
|
||
split_tokens.extend(list(self.bpe(token.text.lower()).split(" ")))
|
||
return split_tokens
|
||
|
||
def _convert_token_to_id(self, token):
|
||
"""Converts a token (str) in an id using the vocab."""
|
||
return self.encoder.get(token, self.encoder.get(self.unk_token))
|
||
|
||
def _convert_id_to_token(self, index):
|
||
"""Converts an id in a token (BPE) using the vocab."""
|
||
return self.decoder.get(index, self.unk_token)
|
||
|
||
def convert_tokens_to_string(self, tokens):
|
||
"""Converts a sequence of tokens (string) in a single string."""
|
||
out_string = "".join(tokens).replace("</w>", " ").strip()
|
||
return out_string
|
||
|
||
def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
||
if not os.path.isdir(save_directory):
|
||
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
|
||
return
|
||
vocab_file = os.path.join(
|
||
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
|
||
)
|
||
merge_file = os.path.join(
|
||
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
|
||
)
|
||
|
||
with open(vocab_file, "w", encoding="utf-8") as f:
|
||
f.write(json.dumps(self.encoder, indent=2, sort_keys=True, ensure_ascii=False) + "\n")
|
||
|
||
index = 0
|
||
with open(merge_file, "w", encoding="utf-8") as writer:
|
||
writer.write("#version: 0.2\n")
|
||
for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
|
||
if index != token_index:
|
||
logger.warning(
|
||
f"Saving vocabulary to {merge_file}: BPE merge indices are not consecutive."
|
||
" Please check that the tokenizer is not corrupted!"
|
||
)
|
||
index = token_index
|
||
writer.write(" ".join(bpe_tokens) + "\n")
|
||
index += 1
|
||
|
||
return vocab_file, merge_file
|