data/process_text.py

import os

import torch
import gzip
import html
import io
from functools import lru_cache
from typing import List, Tuple

import ftfy
import regex as re
from iopath.common.file_io import g_pathmgr
BPE_PATH = os.path.join(os.path.dirname(os.path.abspath(__file__)), "bpe_simple_vocab_16e6.txt.gz")

# Modified from github.com/openai/CLIP
@lru_cache()
def bytes_to_unicode():
    """
    Returns list of utf-8 byte and a corresponding list of unicode strings.
    The reversible bpe codes work on unicode strings.
    This means you need a large # of unicode characters in your vocab if you want to avoid UNKs.
    When you're at something like a 10B token dataset you end up needing around 5K for decent coverage.
    This is a signficant percentage of your normal, say, 32K bpe vocab.
    To avoid that, we want lookup tables between utf-8 bytes and unicode strings.
    And avoids mapping to whitespace/control characters the bpe code barfs on.
    """
    bs = (
        list(range(ord("!"), ord("~") + 1))
        + list(range(ord("¡"), ord("¬") + 1))
        + list(range(ord("®"), ord("ÿ") + 1))
    )
    cs = bs[:]
    n = 0
    for b in range(2**8):
        if b not in bs:
            bs.append(b)
            cs.append(2**8 + n)
            n += 1
    cs = [chr(n) for n in cs]
    return dict(zip(bs, cs))


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 basic_clean(text):
    text = ftfy.fix_text(text)
    text = html.unescape(html.unescape(text))
    return text.strip()


def whitespace_clean(text):
    text = re.sub(r"\s+", " ", text)
    text = text.strip()
    return text

class SimpleTokenizer(object):
    def __init__(self, bpe_path: str, context_length=77):
        self.byte_encoder = bytes_to_unicode()
        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}

        with g_pathmgr.open(bpe_path, "rb") as fh:
            bpe_bytes = io.BytesIO(fh.read())
            merges: List[str] = gzip.open(bpe_bytes).read().decode("utf-8").split("\n")
        merges = merges[1 : 49152 - 256 - 2 + 1]
        merges: List[Tuple[str, ...]] = [tuple(merge.split()) for merge in merges]
        vocab = list(bytes_to_unicode().values())
        vocab = vocab + [v + "</w>" for v in vocab]
        for merge in merges:
            vocab.append("".join(merge))
        vocab.extend(["<|startoftext|>", "<|endoftext|>"])
        self.encoder = dict(zip(vocab, range(len(vocab))))
        self.decoder = {v: k for k, v in self.encoder.items()}
        self.bpe_ranks = dict(zip(merges, range(len(merges))))
        self.cache = {
            "<|startoftext|>": "<|startoftext|>",
            "<|endoftext|>": "<|endoftext|>",
        }
        self.pat = re.compile(
            r"""<\|startoftext\|>|<\|endoftext\|>|'s|'t|'re|'ve|'m|'ll|'d|[\p{L}]+|[\p{N}]|[^\s\p{L}\p{N}]+""",
            re.IGNORECASE,
        )
        self.context_length = context_length

    def bpe(self, token):
        if token in self.cache:
            return self.cache[token]
        word = tuple(token[:-1]) + (token[-1] + "</w>",)
        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)
                    new_word.extend(word[i:j])
                    i = j
                except:
                    new_word.extend(word[i:])
                    break

                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)
        self.cache[token] = word
        return word

    def encode(self, text):
        bpe_tokens = []
        text = whitespace_clean(basic_clean(text)).lower()
        for token in re.findall(self.pat, text):
            token = "".join(self.byte_encoder[b] for b in token.encode("utf-8"))
            bpe_tokens.extend(
                self.encoder[bpe_token] for bpe_token in self.bpe(token).split(" ")
            )
        return bpe_tokens

    def decode(self, tokens):
        text = "".join([self.decoder[token] for token in tokens])
        text = (
            bytearray([self.byte_decoder[c] for c in text])
            .decode("utf-8", errors="replace")
            .replace("</w>", " ")
        )
        return text

    def __call__(self, texts, context_length=None):
        if not context_length:
            context_length = self.context_length

        if isinstance(texts, str):
            texts = [texts]

        sot_token = self.encoder["<|startoftext|>"]
        eot_token = self.encoder["<|endoftext|>"]
        all_tokens = [[sot_token] + self.encode(text) + [eot_token] for text in texts]
        result = torch.zeros(len(all_tokens), context_length, dtype=torch.long)

        for i, tokens in enumerate(all_tokens):
            tokens = tokens[:context_length]
            result[i, : len(tokens)] = torch.tensor(tokens)

        if len(result) == 1:
            return result[0]
        return result

def clean_youtube(text, is_tags=False):
    text = text.lower() + ' '
    text = re.sub(
        r'#video|video|#shorts|shorts| shorts|#short| short|#youtubeshorts|youtubeshorts|#youtube| youtube|#shortsyoutube|#ytshorts|ytshorts|#ytshort|#shortvideo|shortvideo|#shortsfeed|#tiktok|tiktok|#tiktokchallenge|#myfirstshorts|#myfirstshort|#viral|viralvideo|viral|#viralshorts|#virlshort|#ytviralshorts',
        ' ', text)
    text = re.sub(r' s |short|youtube|virlshort|#', ' ', text)
    pattern = r'[^a-zA-Z0-9\s\.,;:?!\'\"|]'
    if is_tags:
        pattern = r'[^a-zA-Z0-9\s]'
    text = re.sub(pattern, '', text)
    text = whitespace_clean(basic_clean(text))
    return text

def load_and_transform_text(text, tokenizer, title=True):
    if title:
        title_hashtags = text.split('#')
        title, hashtags = title_hashtags[0], '#' + '#'.join(title_hashtags[1:])
        title = clean_youtube(title)
        hashtags = clean_youtube(hashtags, is_tags=True)
        text = title + ', ' + hashtags
    if text == '' or text.isspace():
        raise ValueError('text is empty')
    input_ids, attention_mask = tokenizer(text)
    return {'input_ids': input_ids.squeeze(), 'attention_mask': attention_mask.squeeze()}



if __name__ == '__main__':
    load_and_transform_text("bpe/bpe_simple_vocab_16e6.txt.gz")