tokenization.py

# coding=utf-8
# Copyright 2019 The Google Research Authors.
#
# 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.

# Lint as: python2, python3
# coding=utf-8
"""Tokenization classes."""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import collections
import re
import unicodedata
import six
from six.moves import range
import sentencepiece as spm

SPIECE_UNDERLINE = u"▁".encode("utf-8")


def clean_text(text):
  """Performs invalid character removal and whitespace cleanup on text."""
  text = text.replace(u"“", u'"')\
          .replace(u'”', u'"')\
          .replace(u'‘', "'")\
          .replace(u'’', u"'")\
          .replace(u'—', u'-')

  output = []
  for char in text:
      if _is_control(char):
          continue
      if _is_whitespace(char):
          output.append(" ")
      else:
          output.append(char)
  return "".join(output)


def preprocess_text(inputs, remove_space=True, lower=False):
  """preprocess data by removing extra space and normalize data."""

  outputs = inputs
  if remove_space:
    outputs = " ".join(inputs.strip().split())

  if six.PY2 and isinstance(outputs, str):
    try:
      outputs = six.ensure_text(outputs, "utf-8")
    except UnicodeDecodeError:
      outputs = six.ensure_text(outputs, "latin-1")

  outputs = unicodedata.normalize("NFKD", outputs)
  outputs = "".join([c for c in outputs if not unicodedata.combining(c)])
  if lower:
    outputs = outputs.lower()

  return outputs


def encode_pieces(sp_model, text, return_unicode=True, sample=False):
  """turn sentences into word pieces."""

  text = clean_text(text)

  if six.PY2 and isinstance(text, six.text_type):
    text = six.ensure_binary(text, "utf-8")

  if not sample:
    pieces = sp_model.EncodeAsPieces(text)
  else:
    pieces = sp_model.SampleEncodeAsPieces(text, 64, 0.1)

  new_pieces = []
  for piece in pieces:
    piece = printable_text(piece)
    if len(piece) > 1 and piece[-1] == "," and piece[-2].isdigit():
      cur_pieces = sp_model.EncodeAsPieces(
          six.ensure_binary(piece[:-1]).replace(SPIECE_UNDERLINE, b""))
      if piece[0] != SPIECE_UNDERLINE and cur_pieces[0][0] == SPIECE_UNDERLINE:
        if len(cur_pieces[0]) == 1:
          cur_pieces = cur_pieces[1:]
        else:
          cur_pieces[0] = cur_pieces[0][1:]
      cur_pieces.append(piece[-1])
      new_pieces.extend(cur_pieces)
    else:
      new_pieces.append(piece)

  if six.PY2 and return_unicode:
    ret_pieces = []
    for piece in new_pieces:
      if isinstance(piece, str):
        piece = six.ensure_text(piece, "utf-8")
      ret_pieces.append(piece)
    new_pieces = ret_pieces

  return new_pieces


def encode_ids(sp_model, text, sample=False):
  pieces = encode_pieces(sp_model, text, return_unicode=False, sample=sample)
  ids = [sp_model.PieceToId(piece) for piece in pieces]
  return ids


def convert_to_unicode(text):
  """Converts `text` to Unicode (if it's not already), assuming utf-8 input."""
  if six.PY3:
    if isinstance(text, str):
      return text
    elif isinstance(text, bytes):
      return six.ensure_text(text, "utf-8", "ignore")
    else:
      raise ValueError("Unsupported string type: %s" % (type(text)))
  elif six.PY2:
    if isinstance(text, str):
      return six.ensure_text(text, "utf-8", "ignore")
    elif isinstance(text, six.text_type):
      return text
    else:
      raise ValueError("Unsupported string type: %s" % (type(text)))
  else:
    raise ValueError("Not running on Python2 or Python 3?")


def printable_text(text):
  """Returns text encoded in a way suitable for print or `tf.logging`."""

  # These functions want `str` for both Python2 and Python3, but in one case
  # it's a Unicode string and in the other it's a byte string.
  if six.PY3:
    if isinstance(text, str):
      return text
    elif isinstance(text, bytes):
      return six.ensure_text(text, "utf-8", "ignore")
    else:
      raise ValueError("Unsupported string type: %s" % (type(text)))
  elif six.PY2:
    if isinstance(text, str):
      return text
    elif isinstance(text, six.text_type):
      return six.ensure_binary(text, "utf-8")
    else:
      raise ValueError("Unsupported string type: %s" % (type(text)))
  else:
    raise ValueError("Not running on Python2 or Python 3?")


def load_vocab(vocab_file):
    """Loads a vocabulary file into a dictionary."""
    vocab = collections.OrderedDict()
    fin = open(vocab_file)
    for num, line in enumerate(fin):
        items = convert_to_unicode(line.strip()).split("\t")
        if len(items) > 2:
            break
        token = items[0]
        index = items[1] if len(items) == 2 else num
        token = token.strip()
        vocab[token] = int(index)
    return vocab


def convert_by_vocab(vocab, items):
  """Converts a sequence of [tokens|ids] using the vocab."""
  output = []
  for item in items:
    output.append(vocab[item])
  return output


def convert_tokens_to_ids(vocab, tokens):
  return convert_by_vocab(vocab, tokens)


def convert_ids_to_tokens(inv_vocab, ids):
  return convert_by_vocab(inv_vocab, ids)


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


class FullTokenizer(object):
  """Runs end-to-end tokenziation."""

  def __init__(self, vocab_file, do_lower_case=True, model_file='./30k-clean.model'):
    self.vocab = None
    self.sp_model = None
    if model_file:
      self.sp_model = spm.SentencePieceProcessor()
      self.sp_model.Load(model_file)
      self.vocab = load_vocab(vocab_file)
    else:
      raise ValueError('albert use spm by default')
    self.inv_vocab = {v: k for k, v in self.vocab.items()}

  def tokenize(self, text):
    if self.sp_model:
      split_tokens = encode_pieces(self.sp_model, text, return_unicode=False)
    else:
      raise ValueError('albert use spm by default')

    return split_tokens


  def tokenize_for_pretrain(self, tok_list):
    import tok as tok_protocol
    text = " ".join([t.token for t in tok_list])

    split_tokens = encode_pieces(self.sp_model, text, return_unicode=False)
    ids = self.convert_tokens_to_ids(split_tokens)

    if not (len(preprocess_text(''.join(split_tokens))) == len(text) + 1):
      return None

    if len(split_tokens) != len(ids):
      return None

    sent_piece_tokens = []
    i = 0
    position_to_nth = self.inverse_index_str("_" + text)
    for t, id in zip(split_tokens, ids):
      t = t.decode('utf8')
      nth = position_to_nth[i]
      token = tok_list[nth]

      tok = tok_protocol.Tok()
      tok.token = t
      tok.id = id
      tok.bio = token.bio
      tok.origin = token.origin
      tok.appear = token.appear
      i += len(t)
      sent_piece_tokens.append(tok)

    return sent_piece_tokens

  def inverse_index_str(self, s):
    nth_tok = 0
    position_to_nth = {}
    for i, c in enumerate(s):
        if c == " ":
            nth_tok += 1
        position_to_nth[i] = nth_tok
    return position_to_nth

  def convert_tokens_to_ids(self, tokens):
    tokens_out = []
    for i in tokens:
      item = i
      if item in self.vocab:
        tokens_out.append(self.vocab[item])
      else:
        tokens_out.append(self.vocab['[UNK]'])
    return tokens_out


  def convert_ids_to_tokens(self, ids):
    if self.sp_model:
      #tf.logging.info("using sentence piece tokenzier.")
      return [self.sp_model.IdToPiece(id_) for id_ in ids]
    else:
      return convert_by_vocab(self.inv_vocab, ids)


class BasicTokenizer(object):
  """Runs basic tokenization (punctuation splitting, lower casing, etc.)."""

  def __init__(self, do_lower_case=True):
    """Constructs a BasicTokenizer.

    Args:
      do_lower_case: Whether to lower case the input.
    """
    self.do_lower_case = do_lower_case

  def tokenize(self, text):
    """Tokenizes a piece of text."""
    text = convert_to_unicode(text)
    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.).
    text = self._tokenize_chinese_chars(text)

    orig_tokens = whitespace_tokenize(text)
    split_tokens = []
    for token in orig_tokens:
      if self.do_lower_case:
        token = token.lower()
        token = self._run_strip_accents(token)
      split_tokens.extend(self._run_split_on_punc(token))

    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):
    """Splits punctuation on a piece of 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)


class WordpieceTokenizer(object):
  """Runs WordPiece tokenziation."""

  def __init__(self, vocab, unk_token="<unk>", max_input_chars_per_word=200):
    self.vocab = vocab
    self.unk_token = unk_token
    self.max_input_chars_per_word = max_input_chars_per_word

  def tokenize(self, text):
    """Tokenizes a piece of text into its word pieces.

    This uses a greedy longest-match-first algorithm to perform tokenization
    using the given vocabulary.

    For example:
      input = "unaffable"
      output = ["un", "##aff", "##able"]

    Args:
      text: A single token or whitespace separated tokens. This should have
        already been passed through `BasicTokenizer.

    Returns:
      A list of wordpiece tokens.
    """

    text = convert_to_unicode(text)

    output_tokens = []
    for token in whitespace_tokenize(text):
      chars = list(token)
      if len(chars) > self.max_input_chars_per_word:
        output_tokens.append(self.unk_token)
        continue

      is_bad = False
      start = 0
      sub_tokens = []
      while start < len(chars):
        end = len(chars)
        cur_substr = None
        while start < end:
          substr = "".join(chars[start:end])
          if start > 0:
            substr = "##" + six.ensure_str(substr)
          if substr in self.vocab:
            cur_substr = substr
            break
          end -= 1
        if cur_substr is None:
          is_bad = True
          break
        sub_tokens.append(cur_substr)
        start = end

      if is_bad:
        output_tokens.append(self.unk_token)
      else:
        output_tokens.extend(sub_tokens)
    return output_tokens


def _is_whitespace(char):
  """Checks whether `chars` is a whitespace character."""
  # \t, \n, and \r are technically control characters but we treat them
  # as whitespace since they are generally considered as such.
  if char == " " or char == "\t" or char == "\n" or char == "\r":
    return True
  cat = unicodedata.category(char)
  if cat == "Zs":
    return True
  return False


def _is_control(char):
  """Checks whether `chars` is a control character."""
  # These are technically control characters but we count them as whitespace
  # characters.
  if char == "\t" or char == "\n" or char == "\r":
    return False
  cat = unicodedata.category(char)
  if cat in ("Cc", "Cf"):
    return True
  return False


def _is_punctuation(char):
  """Checks whether `chars` is a punctuation character."""
  cp = ord(char)
  # We treat all non-letter/number ASCII as punctuation.
  # Characters such as "^", "$", and "`" are not in the Unicode
  # Punctuation class but we treat them as punctuation anyways, for
  # consistency.
  if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or
    (cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)):
    return True
  cat = unicodedata.category(char)
  if cat.startswith("P"):
    return True
  return False