qidZddlmZmZmZmZmZmZddlm Z m Z m Z m Z m Z mZmZmZddlmZddlmZmZej,eZddd Zd Zd ZGd d eZd gZeZy)z8 Tokenization class for LayoutLMv2. Based on WordPiece. ) Tokenizerdecodersmodels normalizerspre_tokenizers processors) BatchEncoding EncodedInputPaddingStrategyPreTokenizedInput TensorType TextInput TextInputPairTruncationStrategy)TokenizersBackend)add_end_docstringsloggingz vocab.txtztokenizer.json) vocab_filetokenizer_filea add_special_tokens (`bool`, *optional*, defaults to `True`): Whether or not to encode the sequences with the special tokens relative to their model. padding (`bool`, `str` or [`~file_utils.PaddingStrategy`], *optional*, defaults to `False`): Activates and controls padding. Accepts the following values: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). truncation (`bool`, `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `False`): Activates and controls truncation. Accepts the following values: - `True` or `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. This will truncate token by token, removing a token from the longest sequence in the pair if a pair of sequences (or a batch of pairs) is provided. - `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided. - `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided. - `False` or `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths greater than the model maximum admissible input size). max_length (`int`, *optional*): Controls the maximum length to use by one of the truncation/padding parameters. If left unset or set to `None`, this will use the predefined model maximum length if a maximum length is required by one of the truncation/padding parameters. If the model has no specific maximum input length (like XLNet) truncation/padding to a maximum length will be deactivated. stride (`int`, *optional*, defaults to 0): If set to a number along with `max_length`, the overflowing tokens returned when `return_overflowing_tokens=True` will contain some tokens from the end of the truncated sequence returned to provide some overlap between truncated and overflowing sequences. The value of this argument defines the number of overlapping tokens. pad_to_multiple_of (`int`, *optional*): If set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability `>= 7.5` (Volta). an return_token_type_ids (`bool`, *optional*): Whether to return token type IDs. If left to the default, will return the token type IDs according to the specific tokenizer's default, defined by the `return_outputs` attribute. [What are token type IDs?](../glossary#token-type-ids) return_attention_mask (`bool`, *optional*): Whether to return the attention mask. If left to the default, will return the attention mask according to the specific tokenizer's default, defined by the `return_outputs` attribute. [What are attention masks?](../glossary#attention-mask) return_overflowing_tokens (`bool`, *optional*, defaults to `False`): Whether or not to return overflowing token sequences. If a pair of sequences of input ids (or a batch of pairs) is provided with `truncation_strategy = longest_first` or `True`, an error is raised instead of returning overflowing tokens. return_special_tokens_mask (`bool`, *optional*, defaults to `False`): Whether or not to return special tokens mask information. return_offsets_mapping (`bool`, *optional*, defaults to `False`): Whether or not to return `(char_start, char_end)` for each token. This is only available on fast tokenizers inheriting from [`PreTrainedTokenizerFast`], if using Python's tokenizer, this method will raise `NotImplementedError`. return_length (`bool`, *optional*, defaults to `False`): Whether or not to return the lengths of the encoded inputs. verbose (`bool`, *optional*, defaults to `True`): Whether or not to print more information and warnings. **kwargs: passed to the `self.tokenize()` method c*eZdZdZeZejZgdZ ddddddd gd gd gd d dddd fde e e e fzdzffd Z eee d4deezeezeezdeeezdzdeee eeee zdzdee eee zdzdedee zezdee zezde dzde de dzde dzde ezdzdedzdedzd ed!ed"ed#ed$ed%ef(d&Zeee d4d'eeeezeezd(edzdeeee dzdee eee zdzdedee zezdee zezde dzde de dzde dzde ezdzdedzdedzd ed!ed"ed#ed$ed%ef(d)Zd5de d*e dzded%ee fd+Zeee d4deezdedzdeee dzdee dzdedee zezdee zezde dzde de dzde dzde ezdzdedzdedzd ed!ed"ed#ed$ed%ef(d,Zddddej<ej>ddddddddddddfd'eeeezeezd(edzdeeee dzdeee dzded-ed.ede dzde de dzde dzde dzdedzdedzd ed!ed"ed#ed$ed%ef(d/Z ddddej<ej>ddddddddddddfdeezdedzdeee dzdee dzded-ed.ede dzde de dzde dzdedzdedzdedzd ed!ed"ed#ed$ed%ef(d0Z!dej<dddfd1e e e"fezde dzd-ede dzde dzdedzd%e fd2Z#d6d3Z$xZ%S)7LayoutLMv2Tokenizera& Construct a "fast" LayoutLMv2 tokenizer (backed by HuggingFace's *tokenizers* library). Based on WordPiece. This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. Args: vocab_file (`str`): File containing the vocabulary. do_lower_case (`bool`, *optional*, defaults to `True`): Whether or not to lowercase the input when tokenizing. 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. sep_token (`str`, *optional*, defaults to `"[SEP]"`): The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for sequence classification or for a text and a question for question answering. It is also used as the last token of a sequence built with special tokens. pad_token (`str`, *optional*, defaults to `"[PAD]"`): The token used for padding, for example when batching sequences of different lengths. cls_token (`str`, *optional*, defaults to `"[CLS]"`): The classifier token which is used when doing sequence classification (classification of the whole sequence instead of per-token classification). It is the first token of the sequence when built with special tokens. mask_token (`str`, *optional*, defaults to `"[MASK]"`): The token used for masking values. This is the token used when training this model with masked language modeling. This is the token which the model will try to predict. cls_token_box (`List[int]`, *optional*, defaults to `[0, 0, 0, 0]`): The bounding box to use for the special [CLS] token. sep_token_box (`List[int]`, *optional*, defaults to `[1000, 1000, 1000, 1000]`): The bounding box to use for the special [SEP] token. pad_token_box (`List[int]`, *optional*, defaults to `[0, 0, 0, 0]`): The bounding box to use for the special [PAD] token. pad_token_label (`int`, *optional*, defaults to -100): The label to use for padding tokens. Defaults to -100, which is the `ignore_index` of PyTorch's CrossEntropyLoss. only_label_first_subword (`bool`, *optional*, defaults to `True`): Whether or not to only label the first subword, in case word labels are provided. 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 LayoutLMv2). ) input_idsattention_masktoken_type_idsNTz[UNK]z[SEP]z[PAD]z[CLS]z[MASK])rrrr)rrriivocabc r||_|||_n>t|dt|dt|dt|dt|di|_tt j |jt||_tjd| |||j _ tj|j _ tj d |j _t|@d|||||||| | | | | ||d |||_| |_| |_| |_| |_t|j,}t|j.}|j0}|j2}t5j6|d |d |d |d|d||f||fg|j _y)Nrr )r unk_tokenT) clean_texthandle_chinese_chars strip_accents lowercasez##)prefix) do_lower_caser" sep_token pad_token cls_token mask_token cls_token_box sep_token_box pad_token_boxpad_token_labelonly_label_first_subwordtokenize_chinese_charsr%model_max_lengthz:0 $A:0 z:0z:0 $B:1 z:1)singlepairspecial_tokens)r(_vocabstrrr WordPiece _tokenizerrBertNormalizer normalizerrBertPreTokenizer pre_tokenizerrdecodersuper__init__r-r.r/r0r1r+r) cls_token_id sep_token_idrTemplateProcessingpost_processor)selfrr(r"r)r*r+r,r-r.r/r0r1r2r%r3kwargsclsseprCrD __class__s h/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/layoutlmv2/tokenization_layoutlmv2.pyrBzLayoutLMv2Tokenizer.__init__s&+  DKIIIIJ DK$F$4$44;;RUV_R`$ab%0%?%?!7'# & ")7(G(G(I%"*"4"4D"A  '!'''+%=#9'-  $+**.(@%$..!$..!(( (( )3)F)FU(3%r*5XcU"5l#l#* &Frtext text_pairboxes word_labelsadd_special_tokenspadding truncation max_lengthstridepad_to_multiple_of padding_sidereturn_tensorsreturn_token_type_idsreturn_attention_maskreturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mapping return_lengthverbosereturnc hd}|4||s tdt|ttfs,tdt|ttfs td|t|ttf}n5t|ttfxr|xrt|dttf}||n|}| td|rYt |t |k7r tdt ||D]'\}}t |t |k7stdn"t |t |k7r td|r|;t |t |k7r$td t |d t |d |tt ||n|}t |du}|jd!id |d |d|d|d|d|d|d|d| d| d| d| d| d|d|d|d|d|d||S|jd!id|d |d|d|d|d|d|d|d| d| d| d| d| d|d|d|d|d|d||S)"a3 Main method to tokenize and prepare for the model one or several sequence(s) or one or several pair(s) of sequences with word-level normalized bounding boxes and optional labels. Args: text (`str`, `List[str]`, `List[List[str]]`): The sequence or batch of sequences to be encoded. Each sequence can be a string, a list of strings (words of a single example or questions of a batch of examples) or a list of list of strings (batch of words). text_pair (`List[str]`, `List[List[str]]`): The sequence or batch of sequences to be encoded. Each sequence should be a list of strings (pretokenized string). boxes (`List[List[int]]`, `List[List[List[int]]]`): Word-level bounding boxes. Each bounding box should be normalized to be on a 0-1000 scale. word_labels (`List[int]`, `List[List[int]]`, *optional*): Word-level integer labels (for token classification tasks such as FUNSD, CORD). ct|tryt|ttfrft |dk(ryt|dtryt|dttfr)t |ddk(xst|ddtSyy)NTrF) isinstancer9listtuplelen)ts rL_is_valid_text_inputz:LayoutLMv2Tokenizer.__call__.._is_valid_text_inputsz!S!Ae}-q6Q;!c*!tUm4qt9>EZ!Q-EE rMNzStext input must of type `str` (single example) or `List[str]` (batch of examples). zwWords must be of type `List[str]` (single pretokenized example), or `List[List[str]]` (batch of pretokenized examples).rz-You must provide corresponding bounding boxesz@You must provide words and boxes for an equal amount of examplesz:You must provide as many words as there are bounding boxeszbatch length of `text`: z- does not match batch length of `text_pair`: .batch_text_or_text_pairsis_pairrPrQrRrSrTrUrVrWrXrYrZr[r\r]r^r_r`rNrOr7) ValueErrorrdrerfrgzipboolbatch_encode_plus encode_plus)rGrNrOrPrQrRrSrTrUrVrWrXrYrZr[r\r]r^r_r`rHri is_batchedwords words_example boxes_examplerkrls rL__call__zLayoutLMv2Tokenizer.__call__saV (  '- !vwwi$7 M dT5M2 M  #D4-8J#D4-8hThjQUVWQX[_afZgFhJ!)y =LM M 5zSZ' !cdd03E50A c, }}%]);;$%abb c5zSZ' !]^^ $Tc)n)D .s4yk:I'q*FOEZtCi,@'A`d $9D01G)4)))A(  $6   &&$6* .'<'<+D ,F!"(>#$,%& ) .$4###(  $6   &&$6* .'<'<+D ,F!"(>#$,%& ) rMrkrlc |jd|||| |d|\}}}}|jdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|d||S)NrSrTrUrWr`rkrlrPrQrRpadding_strategytruncation_strategyrUrVrWrXrYrZr[r\r]r^r_r`r7)"_get_padding_truncation_strategies_batch_encode_plus)rGrkrlrPrQrRrSrTrUrVrWrXrYrZr[r\r]r^r_r`rHryrzs rLrpz%LayoutLMv2Tokenizer.batch_encode_pluss2ElDDkDkE !!1 E  E A-z6't&& %=   $  2  .  !4 "   2 & * #8 #8 '@ (B! "$:# $(% &)  rMr5c ||r||fgn|g}|jj|f|dd|}|r|djSgS)NFrRis_pretokenizedr)r; encode_batchtokens)rGrNr5rRrH batched_input encodingss rLtokenizezLayoutLMv2Tokenizer.tokenizesX*.$TF 0DOO00  .@RW [a '0y|""7R7rMc |jd|||| |d|\}}}}|jdid|d|d|d|d|d|d|d |d | d | d | d | d| d|d|d|d|d|d||S)aj Tokenize and prepare for the model a sequence or a pair of sequences. .. warning:: This method is deprecated, `__call__` should be used instead. Args: text (`str`, `List[str]`, `List[List[str]]`): The first sequence to be encoded. This can be a string, a list of strings or a list of list of strings. text_pair (`List[str]` or `List[int]`, *optional*): Optional second sequence to be encoded. This can be a list of strings (words of a single example) or a list of list of strings (words of a batch of examples). rxrNrPrOrQrRryrzrUrVrWrXrYrZr[r\r]r^r_r`r7)r{ _encode_plus)rGrNrOrPrQrRrSrTrUrVrWrXrYrZr[r\r]r^r_r`rHryrzs rLrqzLayoutLMv2Tokenizer.encode_plussJElDDkDkE !!1 E  E A-z6!t       $  2  .  !4 "   2 & * #8 #8 '@ (B! "$:# $(% &)  rMryrzc `t|tstdt|d|j |||| | | |r$|Dcgc]\}}|j |f}}}|j j||d}|Dcgc]}|j|| ||||dn|||!}}i}|ddD]'}|Dcgc]\}}||D]}|}}}}|||<)|Dcgc]\}}|D]}|}}}}|r2g} t|D]\}!\}"}| |!gt|"dzz } | |d <|dD]}#|j|#||g}$tt|dD]!}%|r |d |%}&n|%}&g}'t|d|%||%j||%jD]\}(})}*|*;|r!|)dk(r|'j!|j",|'j!||&|*D|(|j$k(r|'j!|j&o|(|j(k(r|'j!|j*|(|j,k(r|'j!|j"t/d |$j!|'$|$|d <|g}+tt|dD]}%|r |d |%}&n|%}&g},t|d|%|d |%||%jD]\}(}-}*|*`|j0r<|-ddk(r|,j!||&|*5|,j!|j2Q|,j!||&|*i|,j!|j2|+j!|,|+|d <|s|d =t5||| Scc}}wcc}wcc}}}wcc}}}w)Nz/batch_text_or_text_pairs has to be a list (got ))ryrzrUrVrWrXTr~)encodingrZr[r\r]r^r_r`rroverflow_to_sample_mappingzId not recognizedbboxoffset_mappinglabels) tensor_type)rdre TypeErrortypeset_truncation_and_paddingsplitr;r_convert_encoding enumeraterg&_eventual_warn_about_too_long_sequencerangern sequence_idsword_idsappendr/rCr-rDr. pad_token_idrmr1r0r ).rGrkrlrPrQrRryrzrUrVrWrXrYrZr[r\r]r^r_r`rNrOrrtokens_and_encodingssanitized_tokenskeyitem_estacksanitized_encodingsritoksr token_boxes batch_indexoriginal_indextoken_boxes_exampleid sequence_idword_idrlabels_exampleoffsets. rLr|z&LayoutLMv2Tokenizer._batch_encode_pluss,2D9MdSkNlMmmnop p ''- 3!1% (  Yq'rodIy(A'r $'rOO00 $1 1 2&   " "!&;&;*C+E*(,++ #   ,'*1- *C&:NN74DINqQNQNEN$) S ! *1ESSWQdSqSqSS %)+ & )*> ? K 9D!*qcC[8I4J.JJ* K=W 9 :)+6 XI  7 7 :w W X  %5k%B!CD 4K(!12N!OP[!\!,"$ ,/ -k:#K0==#K099- >(K &;!#3+2243E3EF+2253H3QRT...+2243E3EFt000+2243E3EFt000+2243E3EF()<==% >&   2 33 46$/   "F$S)9+)F%GH . ,%56R%ST_%`N%0N!#+.$[1+>$%56{C' 4==,D'B *88%ayA~ . 5 5k.6QRY6Z [ . 5 5d6J6J K*11+n2Mg2VW&--d.B.BCD  n-- .0*0 X &)$%56-/BP^__i(s 0OSsN$NN" (N)c |r||fgn|g}|g}||gnd}|j|fidt|dud|d|d|d|d|d|d| d | d | d | d | d |d|d|d|d|d||}| `|s^t|jDcic].\}}|t |dkDrt |dt r|dn|0c}}|j}|j|d|||Scc}}w)NrlrPrQrRryrzrUrVrWrXrYrZr[r\r]r^r_r`rr) r|ror itemsrgrdrerr)rGrNrOrPrQrRryrzrUrVrWrXrYrZr[r\r]r^r_r`rHr batched_boxesbatched_word_labelsbatched_outputrvalues rLrz LayoutLMv2Tokenizer._encode_pluss609$ *+tf  /:/F{mD000  $./   ,  2  .  !4 "   2 & * #8 #8 '@ (B! "$:# $(% &) 2  !*C*'5&:&:&<"USZ!^ 58T8RqX]](( N 33N;4OQ[]des3C# encoded_inputsc.|d|jv}||jd}|tjk(r t|}||||zdk7r ||zdz|z}|tjk7xrt||k7}|rd|vrdgt|z|d<|r|t|z } ||n |j }|dk(r|r|ddg| zz|d<d|vr|d|j g| zz|d<d|vr|d|jg| zz|d<d|vr|d|jg| zz|d<d|vr|ddg| zz|d<||jg| zz||jd<|S|d k(r|rdg| z|dz|d<d|vr|j g| z|dz|d<d|vr|jg| z|dz|d<d|vr|jg| z|dz|d<d|vrdg| z|dz|d<|jg| z|z||jd<|Std t|z|S) a# Pad encoded inputs (on left/right and up to predefined length or max length in the batch) Args: encoded_inputs: Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`). max_length: maximum length of the returned list and optionally padding length (see below). Will truncate by taking into account the special tokens. padding_strategy: PaddingStrategy to use for padding. - PaddingStrategy.LONGEST Pad to the longest sequence in the batch - PaddingStrategy.MAX_LENGTH: Pad to the max length (default) - PaddingStrategy.DO_NOT_PAD: Do not pad The tokenizer padding sides are defined in self.padding_side: - 'left': pads on the left of the sequences - 'right': pads on the right of the sequences pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability `>= 7.5` (Volta). padding_side: The side on which the model should have padding applied. Should be selected between ['right', 'left']. Default value is picked from the class attribute of the same name. return_attention_mask: (optional) Set to False to avoid returning attention mask (default: set to model specifics) rrrrightrrrspecial_tokens_maskleftzInvalid padding strategy:) model_input_namesr LONGESTrg DO_NOT_PADrXpad_token_type_idr/r0rrmr9) rGrrUryrWrXr[required_inputneeds_to_be_padded differences rL_padzLayoutLMv2Tokenizer._padsH ! ($48N8N$N !'(>(>q(AB 66 6^,J  !&8&D*WiJimnJn%);;q@DVVJ-1K1KKqPSTbPcgqPq !%5^%K01sS5H/HN+ , #c.&99J+7+C<IZIZLw&(7EFV7W[\Z]`jZj7jN#34#~5&'78DC*#'056:!%)-#'26-1-1*/+0',#)U++d9o=EV@WWU%t,='>>EUDId49o!66= U #Yd3i047 U ! Uo-U3J!33U$JUU $JUDjUj(4/U $d{U $d{U $(!U"%)#U$!%%U&'U()U, -UpUn:#'056:!%)-#'26-1-1*/+0',#)6 "&y/D4G"G$O`Ja"a6 6 DcO$t+ 6 #Yd3i047 6 ! 6 o-6 3J!336 $J6 6  $J6 Dj6 j(4/6  $d{6  $d{6 $(!6 "%)#6 $!%%6 &'6 ()6 , -6 p6 p8S8d 8t8jnorjs8:rs}\[   ?0   H %#.BRS)&"V62