Ng1dZddlZddlZddlZddlmZddlmZ ddl m Z ddl m Z ejZejeZGdde jZGdde jZdS) ) PdfTextPagePdfTextSearcherN) PdfiumError) PDFIUM_INFOczeZdZdZfdZedZddZdd Zdd Z d Z dd Z dZ ddZ dZddZxZS)rz Text page helper class. Attributes: raw (FPDF_TEXTPAGE): The underlying PDFium textpage handle. page (PdfPage): Reference to the page this textpage belongs to. cz||_||_ttjdSN)rawpagesuper__init__pdfium_cFPDFText_ClosePage)selfr r __class__s W/var/www/html/ai-engine/env/lib/python3.11/site-packages/pypdfium2/_helpers/textpage.pyr zPdfTextPage.__init__s2  455555c|jSr )r rs rparentzPdfTextPage.parent!s yrrc||krdStj||}|dkr||dz||dz|Stj||}|dkr|||dz ||dzS||||fS)Nr)r"FPDFText_GetTextIndexFromCharIndex_get_active_text_range)rc_startc_end l_passive r_passivet_startt_ends rrz"PdfTextPage._get_active_text_range&s U??1=dGLL b==..wqy%1iXX X;D%HH B;;..waIVWKXX Xy)33rrignoreFc||fdkr,|s*tjd||S|dkr||z }||||zdz }|dkrdS|\}}}} ||z }||| zz}|dz|z } dt jcxkrd krnn| d z} | dz } tj| d z} tj | tj tj } tj |||| } | | ksJd | d | | jd | dz d zd|S)a Warning: .. versionchanged:: 4.28 For various reasons, calling this method with default params now implicitly translates to :meth:`.get_text_bounded` (pass ``force_this=True`` to circumvent). Extract text from a given range. Parameters: index (int): Index of the first char to include. count (int): Number of chars to cover, relative to the internal char list. Defaults to -1 for all remaining chars after *index*. errors (str): Error handling when decoding the data (see :meth:`bytes.decode`). Returns: str: The text in the range in question, or an empty string if no text was found. Note: * The returned text's length does not have to match *count*, even if it will for most PDFs. This is because the underlying API may exclude/insert chars compared to the internal list, although rare in practice. This means, if the char at ``i`` is excluded, ``get_text_range(i, 2)[1]`` will raise an index error. Pdfium provides raw APIs ``FPDFText_GetTextIndexFromCharIndex()`` / ``FPDFText_GetCharIndexFromTextIndex()`` to translate between the two views and identify excluded/inserted chars. * In case of leading/trailing excluded characters, pypdfium2 modifies *index* and *count* accordingly to prevent pdfium from unexpectedly reading beyond ``range(index, index+count)``. rrz]get_text_range() call with default params will be implicitly redirected to get_text_bounded()errorsrrriizBuffer too small: z vs N utf-16-le)warningswarnget_text_bounded count_charsrrbuildctypescreate_string_buffercastPOINTERc_ushortrFPDFText_GetTextr decode)rindexcountr& force_this active_ranger r!rrin_countbuffer buffer_ptr out_counts rget_text_rangezPdfTextPage.get_text_range6s2 5>W $ $Z $ My z z z(((77 7 B;;$$&&.E225%+a-HH 1  20<, 9  Y&&7W$ +# * * * *d * * * * * MHA ,X\::[)H)HII -dE5*MM 9$$$&T8&T&T&T&T$$$z*IaK?*+22;v2NNNrNc|j}||d}||d}||d}||d}|||||f}tjg|ddR}|dkrdSt j|dz} t j| t jtj} tjg|| |R| j d|S) a Extract text from given boundaries in PDF coordinates. If a boundary value is None, it defaults to the corresponding value of :meth:`.PdfPage.get_bbox`. Parameters: errors (str): Error treatment when decoding the data (see :meth:`bytes.decode`). Returns: str: The text on the page area in question, or an empty string if no text was found. Nrrr(r'r)r%) r get_bboxrFPDFText_GetBoundedTextr/r0r1r2r3r r5) rleftbottomrighttopr&bboxargsn_charsr;r<s rr,zPdfTextPage.get_text_boundedqsy!!## <7D >!WF =GE ;q'CdC/2BDB$BBBB a<<2,Wq[99[)H)HII (D$D DGDDDDz  V <<?? ?rc\tj|||}|dkrtd|S)a Parameters: index (int): Start character index. count (int): Character count to consider (defaults to -1 for all remaining). Returns: int: The number of text rectangles in the given character range. rzFailed to count rectangles.)rFPDFText_CountRectsr)rr6r7n_rectss r count_rectszPdfTextPage.count_rectss5.tUEBB b==;<< <rcFtj|||||}|dkrdS|S)a Get the index of a character by position. Parameters: x (float): Horizontal position (in PDF canvas units). y (float): Vertical position. x_tol (float): Horizontal tolerance. y_tol (float): Vertical tolerance. Returns: int | None: The index of the character at or nearby the point (x, y). May be None if there is no character or an error occurred. rN)rFPDFText_GetCharIndexAtPos)rxyx_toly_tolr6s r get_indexzPdfTextPage.get_indexs/3D!QuMM 1994 rc|rItj}tj|||}|j|j|j|jf\}}}}nsttttf\}}}}tj||||||}|j |j |j |j f\}}}}|std||||fS)a Get the bounding box of a single character. Parameters: index (int): Index of the character to work with, in the page's character array. loose (bool): Get a more comprehensive box covering the entire font bounds, as opposed to the default tight box specific to the one character. Returns: Float values for left, bottom, right and top in PDF canvas units. zFailed to get charbox.) rFS_RECTFFPDFText_GetLooseCharBoxrCrDrErFc_doubleFPDFText_GetCharBoxvaluer) rr6looserectoklbrts r get_charboxzPdfTextPage.get_charboxs  <$&&D24EEBDKTXEJAq!QQ!XZZXZZGJAq!Q-dE1aAFFB!'17AG;JAq!Q 8677 7!Qzrcttttf\}}}}tj||||||}|std|j|j|j|jfS)al Get the bounding box of a text rectangle at the given index. Note that :meth:`.count_rects` must be called once with default parameters before subsequent :meth:`.get_rect` calls for this function to work (due to PDFium's API). Returns: Float values for left, bottom, right and top in PDF canvas units. zzFailed to get rectangle. (Make sure count_rects() was called with default params once before subsequent get_rect() calls.))rZrFPDFText_GetRectrr\)rr6r`rarbrcr_s rget_rectzPdfTextPage.get_rectsZZXZZC 1a  &tUAq!Q ? ? \[\\ \!'1733rct|dkrtdd}|r|tjz}|r|tjz}|r|tjz}|dzd}tj|tj tj }tj ||||} t| |} | | | S)au Locate text on the page. Parameters: text (str): The string to search for. index (int): Character index at which to start searching. match_case (bool): If True, the search will be case-specific (upper and lower letters treated as different characters). match_whole_word (bool): If True, substring occurrences will be ignored (e. g. `cat` would not match `category`). consecutive (bool): If False (the default), :meth:`.search` will skip past the current match to look for the next match. If True, parts of the previous match may be caught again (e. g. searching for `aa` in `aaaa` would match 3 rather than 2 times). Returns: PdfTextSearcher: A helper object to search text. rz#Text length must be greater than 0.r))len ValueErrorrFPDF_MATCHCASEFPDF_MATCHWHOLEWORDFPDF_CONSECUTIVEencoder/r1r2r3FPDFText_FindStartr_add_kid) rtextr6 match_casematch_whole_word consecutiveflagsenc_text enc_text_ptr raw_searchersearchers rsearchzPdfTextPage.searchs( t99>>BCC C  - X, ,E  2 X1 1E  / X. .E6M))+66{8V^FO-L-LMM 24ueTT "<66 hr)rr)rrr"F)NNNNr"r$)F)rFFF)__name__ __module__ __qualname____doc__r propertyrrr>r,r-rOrVrdrgr{ __classcell__rs@rrrs66666 X 4 4 4 4 8O8O8O8Ov====@    &8 4 4 4 $$$$$$$$rrcJeZdZdZfdZedZdZdZdZ xZ S)rz Text searcher helper class. Attributes: raw (FPDF_SCHHANDLE): The underlying PDFium searcher handle. textpage (PdfTextPage): Reference to the textpage this searcher belongs to. cz||_||_ttjdSr )r textpager r rFPDFText_FindClose)rr rrs rr zPdfTextSearcher.__init__s2   455555rc|jSr )rrs rrzPdfTextSearcher.parents }rcx||}|sdStj|}tj|}||fSr )rFPDFText_GetSchResultIndexFPDFText_GetSchCount)r find_funcr_r6r7s r_get_occurrencezPdfTextSearcher._get_occurrence#sF Yt__ 43D99-d33e|rc@|tjS)z Returns: (int, int): Start character index and count of the next occurrence, or None if the last occurrence was passed. )rrFPDFText_FindNextrs rget_nextzPdfTextSearcher.get_next+ ##H$>???rc@|tjS)z Returns: (int, int): Start character index and count of the previous occurrence (i. e. the one before the last valid occurrence), or None if the last occurrence was passed. )rrFPDFText_FindPrevrs rget_prevzPdfTextSearcher.get_prev3rr) r|r}r~rr rrrrrrrs@rrrs66666 X@@@@@@@@@@rr)__all__r/loggingr* pypdfium2.rawr rpypdfium2.internalinternalpdfium_ipypdfium2._helpers.miscrpypdfium2.versionrrZ getLoggerr|logger AutoCloseablerrrrrs -  %%%%%%//////)))))) ?  8 $ $zzzzz8)zzzz)@)@)@)@)@x-)@)@)@)@)@r