o Zh1@sdZddlZddlZddlZddlmZddlmZ ddl m Z ddl m Z ejZeeZGddde jZGddde jZdS) ) PdfTextPagePdfTextSearcherN) PdfiumError) PDFIUM_INFOcseZdZdZfddZeddZdddZdd d ZdddZ ddZ d ddZ ddZ d!ddZ ddZd"ddZZS)#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||_||_ttjdSN)rawpagesuper__init__pdfium_cZFPDFText_ClosePage)selfrr  __class__R/var/www/html/lang_env/lib/python3.10/site-packages/pypdfium2/_helpers/textpage.pyr zPdfTextPage.__init__cC|jSr)r r rrrparent!zPdfTextPage.parentrcCsp||krdSt||}|dkr||d||d|St||}|dkr2|||d||dS||||fS)Nr)r Z"FPDFText_GetTextIndexFromCharIndex_get_active_text_range)r Zc_startZc_end l_passive r_passivet_startt_endrrrr&s   z"PdfTextPage._get_active_text_rangerignoreFcCs||fdkr|std|j|dS|dkr||}||||d}|dkr-dS|\}}}} ||7}||| 8}|d|} dtjkrNd krTnn| d 9} | d7} t| d } t | t tj } t |||| } | | ksJd | d | | jd | dd jd|dS)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_ushortr ZFPDFText_GetTextrdecode)r indexcountr!Z force_thisZ active_rangerrrrZin_countbuffer buffer_ptrZ out_countrrrget_text_range6s(       zPdfTextPage.get_text_rangeNc Cs|j}|dur |d}|dur|d}|dur|d}|dur%|d}|||||f}tjg|ddR}|dkr>dSt|d} t| ttj} tjg|| |R| j j d|dS) 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 Zget_bboxr ZFPDFText_GetBoundedTextr*r+r,r-r.rr/) r leftbottomrighttopr!Zbboxargsn_charsr2r3rrrr'qs" zPdfTextPage.get_text_boundedcCst|}|dkr td|S)zV Returns: int: The number of characters on the text page. rzFailed to get character count.)r ZFPDFText_CountCharsr)r r;rrrr(s zPdfTextPage.count_charscCs"t|||}|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.)r ZFPDFText_CountRectsr)r r0r1Zn_rectsrrr count_rectsszPdfTextPage.count_rectscCs"t|||||}|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)r ZFPDFText_GetCharIndexAtPos)r xyZx_tolZy_tolr0rrr get_indexs zPdfTextPage.get_indexc Cs|rt}t|||}|j|j|j|jf\}}}}n&ttttf\}}}}t||||||}|j |j |j |j f\}}}}|sHt d||||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.) r ZFS_RECTFZFPDFText_GetLooseCharBoxr6r7r8r9c_doubleZFPDFText_GetCharBoxvaluer) r r0looserectoklbrtrrr get_charboxs  zPdfTextPage.get_charboxcCsPttttf\}}}}t||||||}|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.))r@r ZFPDFText_GetRectrrA)r r0rErFrGrHrDrrrget_rects  zPdfTextPage.get_rectc Cst|dkr tdd}|r|tjO}|r|tjO}|r!|tjO}|dd}t|t tj }t ||||} 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 ValueErrorr ZFPDF_MATCHCASEZFPDF_MATCHWHOLEWORDZFPDF_CONSECUTIVEencoder*r,r-r.ZFPDFText_FindStartrZ_add_kid) r textr0 match_caseZmatch_whole_wordZ consecutiveflagsZenc_textZ enc_text_ptrZ raw_searcherZsearcherrrrsearchs      zPdfTextPage.search)rr)rrrF)NNNNrr)F)rFFF)__name__ __module__ __qualname____doc__r propertyrrr4r'r(r<r?rIrJrR __classcell__rrrrrs     ;  rcsDeZdZdZfddZeddZddZdd Zd d Z Z 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. crr)rtextpager r r ZFPDFText_FindClose)r rrYrrrr rzPdfTextSearcher.__init__cCrr)rYrrrrrrzPdfTextSearcher.parentcCs,||}|sdSt|}t|}||fSr)r ZFPDFText_GetSchResultIndexZFPDFText_GetSchCount)r Z find_funcrDr0r1rrr_get_occurrence#s   zPdfTextSearcher._get_occurrencecC |tjS)z Returns: (int, int): Start character index and count of the next occurrence, or None if the last occurrence was passed. )rZr ZFPDFText_FindNextrrrrget_next+ zPdfTextSearcher.get_nextcCr[)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. )rZr ZFPDFText_FindPrevrrrrget_prev3r]zPdfTextSearcher.get_prev) rSrTrUrVr rWrrZr\r^rXrrrrrs  r)__all__r*loggingr%Z pypdfium2.rawrr Zpypdfium2.internalZinternalZpdfium_iZpypdfium2._helpers.miscrZpypdfium2.versionrr@ getLoggerrSloggerZ AutoCloseablerrrrrrs     ~