w;3h1dZddlZddlZddlZddlmZddlmZ ddl m Z ddl m Z ejZejeZGdde j$ZGdde j$Zy) ) PdfTextPagePdfTextSearcherN) PdfiumError) PDFIUM_INFOcteZdZdZfdZedZd dZddZddZ dZ ddZ d Z dd Z d Zdd ZxZS)rz Text page helper class. Attributes: raw (FPDF_TEXTPAGE): The underlying PDFium textpage handle. page (PdfPage): Reference to the page this textpage belongs to. c\||_||_t| tj yN)rawpagesuper__init__pdfium_cFPDFText_ClosePage)selfr r __class__s [/var/www/html/audio-gradio/venv/lib/python3.12/site-packages/pypdfium2/_helpers/textpage.pyr zPdfTextPage.__init__s$  445c|jSr )r rs rparentzPdfTextPage.parent!s yyrc||kDrytj||}|dk(r|j|dz||dz|Stj||}|dk(r|j||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?==dGL b=..wqy%1iX X;;D%H B;..waIVWKX Xy)33rc||fdk(r)|s'tjd|j|S|dk(r|j|z }|j |||zdz }|dk(ry|\}}}} ||z }||| zz}|dz|z } dt j cxkrd krnn| d z} | dz } tj| d z} tj| tjtj} tj|||| } | | k\s Jd | d | | jd | dz d zjd|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_range6sd2 5>W $Z MMy z(((7 7 B;$$&.E225%+a-H 1 0<, 9  Y&&7W$ +## *d * MHA ,,X\:[[)HI --dE5*M 9$T(:8*D &TT$zz*IaK?+22;v2NNrc|jj}||d}||d}||d}||d}|||||f}tjg|dd}|dkryt j |dz} t j | t jtj} tjg|| || jjd|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.r/r0r1r2r r4) rleftbottomrighttopr%bboxargsn_charsr:r;s rr+zPdfTextPage.get_text_boundedqsyy!!# <7D >!WF =GE ;q'CdC/22BDB$BB a<,,Wq[9[[)HI ((D$D DGDzz  V <? ?rcTtj|||}|dk(r td|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)rr5r6n_rectss r count_rectszPdfTextPage.count_rectss0..tUEB b=;< <rcDtj|||||}|dkry|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_tolr5s r get_indexzPdfTextPage.get_indexs+33D!QuM 19 rc|r_tj}tj|||}|j|j|j |j f\}}}}nxttttf\}}}}tj||||||}|j|j|j|jf\}}}}|s td||||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_GetLooseCharBoxrBrCrDrEc_doubleFPDFText_GetCharBoxvaluer) rr5looserectoklbrts r get_charboxzPdfTextPage.get_charboxs $$&D224EBDKKTXXEJAq!Q!XZXZGJAq!Q--dE1aAFB!''177AGG;JAq!Q67 7!Qzrcttttf\}}}}tj||||||}|s td|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.))rYrFPDFText_GetRectrr[)rr5r_r`rarbr^s rget_rectzPdfTextPage.get_rectssZXZC 1a  & &tUAq!Q ?[\ \!''17733rct|dk(r tdd}|r|tjz}|r|tjz}|r|tj z}|dzj d}tj|tjtj}tj||||} t| |} |j| | 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.r0r1r2FPDFText_FindStartr_add_kid) rtextr5 match_casematch_whole_word consecutiveflagsenc_text enc_text_ptr raw_searchersearchers rsearchzPdfTextPage.searchs( t9>BC C  X,, ,E  X11 1E  X.. .E6M))+6{{8V^^FOO-LM 224ueT "<6 hr)rr)rrignoreF)NNNNr{r#)F)rFFF)__name__ __module__ __qualname____doc__r propertyrrr=r+r,rNrUrcrfrz __classcell__rs@rrrsQ6  4 8Ov=@ &8 4 $rrcDeZdZdZfdZedZdZdZdZ xZ S)rz Text searcher helper class. Attributes: raw (FPDF_SCHHANDLE): The underlying PDFium searcher handle. textpage (PdfTextPage): Reference to the textpage this searcher belongs to. c\||_||_t| tj yr )r textpager r rFPDFText_FindClose)rr rrs rr zPdfTextSearcher.__init__s$   445rc|jSr )rrs rrzPdfTextSearcher.parents }}rct||}|sytj|}tj|}||fSr )rFPDFText_GetSchResultIndexFPDFText_GetSchCount)r find_funcr^r5r6s r_get_occurrencezPdfTextSearcher._get_occurrence#s; t_33D9--d3e|rc@|jtjS)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@|jtjS)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@rrrs26 @@rr)__all__r.loggingr) pypdfium2.rawr rpypdfium2.internalinternalpdfium_ipypdfium2._helpers.miscrpypdfium2.versionrrY getLoggerr|logger AutoCloseablerrrrrse -  %/) ??   8 $z8))zz)@x--)@r