sg d Z ddlZddlmZ ddlmZmZmZmZm Z ddl
m Z ddl m
Z
mZmZmZmZmZ ddlmZ dd lmZmZmZmZmZ d
d lm Z e rd d
l m Z ndZ ej> e Z!dZ" G d de Z#y)z)Tokenization classes for LayoutXLM model. N)copyfile)DictListOptionalTupleUnion )
AddedToken)
BatchEncoding EncodedInputPreTokenizedInput TextInput
TextInputPairTruncationStrategy)PreTrainedTokenizerFast)PaddingStrategy
TensorTypeadd_end_docstringsis_sentencepiece_availablelogging )VOCAB_FILES_NAMES )LayoutXLMTokenizera
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).
return_tensors (`str` or [`~file_utils.TensorType`], *optional*):
If set, will return tensors instead of list of python integers. Acceptable values are:
- `'tf'`: Return TensorFlow `tf.constant` objects.
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return Numpy `np.ndarray` objects.
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
Return:
[`BatchEncoding`]: A [`BatchEncoding`] with the following fields:
- **input_ids** -- List of token ids to be fed to a model.
[What are input IDs?](../glossary#input-ids)
- **bbox** -- List of bounding boxes to be fed to a model.
- **token_type_ids** -- List of token type ids to be fed to a model (when `return_token_type_ids=True` or
if *"token_type_ids"* is in `self.model_input_names`).
[What are token type IDs?](../glossary#token-type-ids)
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names`).
[What are attention masks?](../glossary#attention-mask)
- **labels** -- List of labels to be fed to a model. (when `word_labels` is specified).
- **overflowing_tokens** -- List of overflowing tokens sequences (when a `max_length` is specified and
`return_overflowing_tokens=True`).
- **num_truncated_tokens** -- Number of tokens truncated (when a `max_length` is specified and
`return_overflowing_tokens=True`).
- **special_tokens_mask** -- List of 0s and 1s, with 1 specifying added special tokens and 0 specifying
regular sequence tokens (when `add_special_tokens=True` and `return_special_tokens_mask=True`).
- **length** -- The length of the inputs (when `return_length=True`).
c * e Zd ZdZeZddgZeZddddddddd g d
g d g d
d d
f fd Z e
de fd Z e
e d8deeeee ee f deeeee f deeee eeee f deeee eee f de dee eef dee eef dee ded ee d ee d eeeef d ee d ee d!e d"e d#e d$e d%e def(d& Zd9ded'ee de dee fd(Zdddd
ej8 ej: dddddddddddd
fd)eee ee ee f d*e deeeee deeee de d+ed,edee ded ee d ee d ee d ee d ee d!e d"e d#e d$e d%e def(d-Z dddd
ej8 ej: dddddddddddd
fdeeef dee deeee deee de d+ed,edee ded ee d ee d ee d ee d ee d!e d"e d#e d$e d%e def(d.Z dej8 dddfd/ee!ee"f ef dee d+ed ee d ee d ee de#fd0Z$ d:d1ee d2eee dee fd3Z% d:d1ee d2eee dee fd4Z&d:d5ed6ee de'e fd7Z( xZ)S );LayoutXLMTokenizerFasta
Construct a "fast" LayoutXLM tokenizer (backed by HuggingFace's *tokenizers* library). Adapted from
[`RobertaTokenizer`] and [`XLNetTokenizer`]. Based on
[BPE](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=BPE#models).
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`):
Path to the vocabulary file.
bos_token (`str`, *optional*, defaults to `""`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
When building a sequence using special tokens, this is not the token that is used for the beginning of
sequence. The token used is the `cls_token`.
eos_token (`str`, *optional*, defaults to `""`):
The end of sequence token.
When building a sequence using special tokens, this is not the token that is used for the end of sequence.
The token used is the `sep_token`.
sep_token (`str`, *optional*, defaults to `""`):
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.
cls_token (`str`, *optional*, defaults to `""`):
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.
unk_token (`str`, *optional*, defaults to `""`):
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.
pad_token (`str`, *optional*, defaults to `""`):
The token used for padding, for example when batching sequences of different lengths.
mask_token (`str`, *optional*, defaults to `""`):
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.
additional_special_tokens (`List[str]`, *optional*, defaults to `["NOTUSED", "NOTUSED"]`):
Additional special tokens used by the tokenizer.
input_idsattention_maskNzzzzz)r r r r ) r r r iTc t | t rt | dd n| } t | |f|||||||| |
| | |
|d
| || _ |
| _ | | _ | | _ |
| _ || _
y )NTF)lstriprstrip)
tokenizer_file bos_token eos_token sep_token cls_token unk_token pad_token
mask_token
cls_token_box
sep_token_box
pad_token_boxpad_token_labelonly_label_first_subword)
isinstancestrr
super__init__
vocab_filer+ r, r- r. r/ )selfr4 r# r$ r% r& r' r( r) r* r+ r, r- r. r/ kwargs __class__s l/var/www/html/venv/lib/python3.12/site-packages/transformers/models/layoutxlm/tokenization_layoutxlm_fast.pyr3 z LayoutXLMTokenizerFast.__init__ s & KUU_adJeZ
4Fku
) !''' +%=
$ % + * * . (@% returnc p | j r)t j j | j S dS NF)r4 ospathisfile)r5 s r8 can_save_slow_tokenizerz.LayoutXLMTokenizerFast.can_save_slow_tokenizer s$ 26//rww~~doo.LuLr9 Fr text 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_lengthverbosec h d }|4 || s t d t |t t f s,t d t |t t f s t d |t |t t f }n5t |t t f xr |xr t |d t t f }||n|}| t d |rYt | t | k7 r t d t || D ]' \ }}t | t | k7 s t d n"t | t | k7 r t d |r|;t | t | k7 r$t d
t | d t | d |t t || n|}t
|du } | j d"i d
|d|d|d|d|d|d|d|d| d|
d| d| d|
d|d|d |d |d |d ||S | j d"i d |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).
c t | t ryt | t t f rft | dk( ryt | d t ryt | d t t f r)t | d dk( xs t | d d t S yy)NTr F)r0 r1 listtuplelen)ts r8 _is_valid_text_inputz=LayoutXLMTokenizerFast.__call__.._is_valid_text_input6 sz !S!Ae}-q6Q; !c* !tUm4 qt9>EZ!Q-EE r9 NzStext input must of type `str` (single example) or `List[str]` (batch of examples). ztwords must of type `List[str]` (single pretokenized example), or `List[List[str]]` (batch of pretokenized examples).ztWords must of type `List[str]` (single pretokenized example), or `List[List[str]]` (batch of pretokenized examples).r z-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_pairrC rD rE rF rG rH rI rJ rK rL rM rN rO rP rQ rR rS rA rB )
ValueErrorr0 rV rW rX zipboolbatch_encode_plus encode_plus) r5 rA rB rC rD rE rF rG rH rI rJ rK rL rM rN rO rP rQ rR rS r6 rZ
is_batchedwords
words_example
boxes_exampler\ r] s r8 __call__z LayoutXLMTokenizerFast.__call__ sa V ( '- !vww i$ 7 M dT5M2 M
#D4-8J#D4-8hThjQUVWQX[_afZgFhJ!)y = LM M 5zSZ' !cdd03E50A
c,
}}%]);;$%abb
c 5zSZ' !]^^ $Tc)n)D .s4yk :I'q* FOEZtCi,@'A`d $9D01G)4)) )A (
$6
& & $6 * . '< '< +D ,F!" (>#$ ,%& )
. $4## # (
$6
& & $6 * . '< '< +D ,F!" (>#$ ,%& )
r9 pairc |r||fgn|g}|j d| j j | j _ | j j |f|dd|}|d j S )Nsplit_special_tokensFrE is_pretokenizedr )pop
_tokenizerencode_special_tokens encode_batchtokens)r5 rA ri rE r6
batched_input encodingss r8 tokenizez LayoutXLMTokenizerFast.tokenize sw *.$ TF
06
"DOO$I$I1
- 1DOO00
.@RW
[a
|"""r9 r\ r] padding_strategytruncation_strategyc
| t |t st dt | d | j |||| |
| |r$|D cg c] \ }}|j |f }}}| j j ||d }|D cg c] }| j ||
||||dn||| ! }}i }|d d j D ]' }|D cg c] \ } } | | D ] } | } } } } | ||< ) |D cg c] \ } } | D ] } | } } } } |r2g }!t | D ] \ }"\ }#} |!|"gt |#d z z
}! |!|d < |d D ] }$| j |$|| g }%t t |d D ]! }&|r |d |& }'n|&}'g }(t |d |& | |& j | |& j D ] \ })}*}+|+;|r!|*dk( r |(j# | j$ ,|(j# ||' |+ D|)| j& k( r |(j# | j( o|)| j* k( r |(j# | j, |)| j. k( r |(j# | j$ t1 d
|%j# |( $ |%|d < |g },t t |d D ] }&|r |d |& }'n|&}'g }-t |d |& |d |& | |& j D ] \ })}.}+|+`| j2 r<|.d dk( r|-j# ||' |+ 5|-j# | j4 Q|-j# ||' |+ i|-j# | j4 |,j# |- |,|d
< |s|d = t7 || | S c c}}w c c}w c c} } } w c c} } } w )Nz/batch_text_or_text_pairs has to be a list (got ))rv rw rH rI rJ rK Trl )encodingrM rN rO rP rQ rR rS r r overflow_to_sample_mappingzId not recognizedbboxoffset_mappinglabels) tensor_type) r0 rV TypeErrortypeset_truncation_and_paddingsplitro rq _convert_encodingkeys enumeraterX &_eventual_warn_about_too_long_sequenceranger` sequence_idsword_idsappendr- cls_token_idr+ sep_token_idr, pad_token_idr_ r/ r. r )/r5 r\ r] rC rD rE rv rw rH rI rJ rK rL rM rN rO rP rQ rR rS r6 rA rB rt rz tokens_and_encodingssanitized_tokenskeyitem_estacksanitized_encodingsr{ itoksr token_boxes batch_indexoriginal_indextoken_boxes_exampleid sequence_idword_idr~ labels_exampleoffsets/ r8 _batch_encode_plusz)LayoutXLMTokenizerFast._batch_encode_plus s 6 2D9 MdSkNlMmmn op p
'' - 3! 1%
(
Yq'rodI y(A'r $'rOO00 $ 1 1
2 &
" "!&;&;*C+E * (,+ +
#
, '*1-224 *C&:NN74DINqQNQNEN$) S ! * 1E S SWQd Sq Sq S S %)+ & )*> ?
K 9D!*qcC[8I4J.JJ*
K=W 9 :)+6 XI 7 7 :w W X %5k%B!CD 4K(!12N!OP[!\!,"$ ,/ -k:#K0==#K099-
>(K
& ;!#3+2243E3EF+225 3H3QRT . ..+2243E3EFt 0 00+2243E3EFt 0 00+2243E3EF ()< ==%
>&
2 33 46 $/ "F $S)9+)F%G H
. ,%56R%ST_%`N%0N!#+.$[1+>$%56{C' 4==, D'B
* 88 %ayA~ . 5 5k.6QRY6Z [ . 5 5d6J6J K * 1 1+n2Mg2V W&--d.B.BC D
n--
.0 *0 X &)$%56 -/BP^__i (s
0 O Ss N%$N+N0
6N7c |r||fgn|g}|g}||gnd } | j |fi dt |d u d|d|d|d|d|d|d| d |
d
| d | d |
d
|d|d|d|d|d||}| `|s^t |j D ci c]. \ }}|t | dkD rt |d t r|d n|0 c}}|j }| j |d || |S c c}}w )Nr] rC rD rE rv rw rH rI rJ rK rL rM rN rO rP rQ rR rS r r ) r ra r itemsrX r0 rV rt r )r5 rA rB rC rD rE rv rw rH rI rJ rK rL rM rN rO rP rQ rR rS r6 rs
batched_boxesbatched_word_labelsbatched_outputr values r8 _encode_plusz#LayoutXLMTokenizerFast._encode_plusO s 6 09$ *+tf
/:/F{mD000
$./
,
2
.
!4
"
2
&
*
#8
#8
'@
(B!
" $:#
$ (%
& )
2 !*C * '5&:&:&<"U SZ!^
58T8RqX]] (( N
33N;4OQ[]de s 3C#
encoded_inputsc . |d| j v }|| j d }|t j k( r t | }||||z dk7 r ||z dz |z }|t j k7 xr t | |k7 }|rd|vrdgt | z |d< |r|t | z
} ||n | j
}|dk( r|r|d dg| z z |d< d|v r|d | j g| z z |d< d|v r|d | j g| z z |d< d|v r|d | j g| z z |d< d|v r|d dg| z z |d< || j g| z z || j d < |S |d k( r|rdg| z |d z |d< d|v r| j g| z |d z |d< d|v r| j g| z |d z |d< d|v r| j g| z |d z |d< d|v rdg| z |d z |d< | j g| z |z || j d < |S t d
t | z |S ) a7
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 (`str`, *optional*):
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)
r r r righttoken_type_idsr| r~ special_tokens_maskleftzInvalid padding strategy:) model_input_namesr LONGESTrX
DO_NOT_PADrK pad_token_type_idr- r. r r_ r1 )
r5 r rH rv rJ rK rN required_inputneeds_to_be_padded
differences
r8 _padzLayoutXLMTokenizerFast._pad s H ! ($48N8N$N !'(>(>q(AB 6 6 6 ^,J !&8&D*WiJimnJn%);;q@DVVJ - 1K1K K qPSTbPcgqPq !%5^%K01sS 5H/HN+ , #c.&99J+7+C<IZIZLw&(7EFV7W[\Z]`jZj7jN#34#~5&'78DC* X `
- pair of sequences: ` A B `
Args:
token_ids_0 (`List[int]`):
List of IDs to which the special tokens will be added.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
)r r )r5 r r clsseps r8 build_inputs_with_special_tokensz7LayoutXLMTokenizerFast.build_inputs_with_special_tokens sg ( %%&48I8I7JJ J ! ![ 3&,{:S@@r9 c | j g}| j g}|t ||z |z dgz S t ||z |z |z |z |z dgz S )a
Create a mask from the two sequences passed to be used in a sequence-pair classification task. XLM-RoBERTa does
not make use of token type ids, therefore a list of zeros is returned.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of zeros.
r )r r rX )r5 r r r r s r8 $create_token_type_ids_from_sequencesz;LayoutXLMTokenizerFast.create_token_type_ids_from_sequences sm $ ! ! s[(3./1#5 53$s*S0;>DEKKr9 save_directoryfilename_prefixc | j s t d t j j | st
j
d| d y t j j ||r|dz ndt d z }t j j | j t j j | k7 rt | j | |fS )NzhYour fast tokenizer does not have the necessary information to save the vocabulary for a slow tokenizer.zVocabulary path (z) should be a directory.- r4 ) r@ r_ r= r> isdirloggererrorjoinr abspathr4 r )r5 r r out_vocab_files r8 save_vocabularyz&LayoutXLMTokenizerFast.save_vocabulary s ++
ww}}^, LL,^,< ?@ U !
U tS/12U $%778U SMU U %SMU tnU !sJ!78U (~ U (~ U $(!U" %)#U$ !%%U& 'U( )U,
-U ;Un #S #
#RV #mqrumv #( 1515#',;,F,F2D2T2T$(,0'+(,0404*/+0', # 1]`"' O " #
%#
]` ]` T$s)_-.]` d49o.]` !]` *]` 0]` SM]` ]` %SM ]` tn!]`" !
#]`$ (~%]`& (~']`( $()]`* %)+]`, !%-]`. /]`0 1]`4
5]`D 26+/+/#',;,F,F2D2T2T$(,0'+)-0404*/+0', # )B I 001B -.B T#Y( B
d3i( B !
B *B 0B SMB B %SMB tnB !B (~ B (~ B $(!B " %)#B $ !%%B & 'B ( )B ,
-B N %),;,F,F,0'+04W d3 #4 5} DEW SMW * W
%SM W tn
W (~W
W t JNA 9A3;DI3FA
cA6 JNL 9L3;DI3FL
cL2!c !HSM !]bcf]g !r9 r )$r r= shutilr typingr r r r r tokenization_utilsr
tokenization_utils_baser r r
r r r tokenization_utils_fastr utilsr r r r r )xlm_roberta.tokenization_xlm_roberta_fastr tokenization_layoutxlmr
get_loggerr r r r r^ r9 r8 r sq 0 5 5 , ? i i
:
H %e% !P[
! 4 [
!r9