.ih4dZddlZddlZddlmZddlmZddl m Z ddl m Z ej Z ejeZGddejZGddejZdS) ) PdfTextPagePdfTextSearcherN) PdfiumError) PdfTextObjceZdZdZfdZedZddZddZdd Z d Z dd Z d Z ddZ dZdZddZxZS)ra Text page helper class. Hint: (py)pdfium itself does not implement layout analysis, such as detecting words/lines/paragraphs. However, there may be third-party extensions for this job, e.g.: https://github.com/VikParuchuri/pdftext 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/analyses/venv/lib/python3.11/site-packages/pypdfium2/_helpers/textpage.pyr zPdfTextPage.__init__ s2  455555c|jSr )r rs rparentzPdfTextPage.parent%s yrNignorec|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 canvas units. 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. Note: PDFium outputs CRLF (``\r\n``) style line breaks. This may be undesirable or confusing in some situations, e.g. when processing the output with an (unaware) parser on the command line. If this is an issue, replace ``\r\n`` with just ``\n``. Nr utf-16-leerrors) r get_bboxrFPDFText_GetBoundedTextctypescreate_string_buffercastPOINTERc_ushortr decode) rleftbottomrighttoprbboxargsn_charsbuffer buffer_ptrs rget_text_boundedzPdfTextPage.get_text_bounded*s y!!## <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. r3zFailed to count rectangles.)rFPDFText_CountRectsr)rr?r@n_rectss r count_rectszPdfTextPage.count_rectss5.tUEBB b==;<< <rctj|||||}|dkrdS|dkrtd|dks Jd|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. If an internal error occurred, an exception will be raised. r3Nz6An error occurred on attempt to get char index by pos.rz8Negative return is not permitted (unhandled error code?))rFPDFText_GetCharIndexAtPosr)rxyx_toly_tolr?s r get_indexzPdfTextPage.get_indexs[3D!QuMM B;;4 b[[VWW WzzzUzzz rFc|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_GetLooseCharBoxr(r)r*r+c_doubleFPDFText_GetCharBoxvaluer) rr?looserectoklbrts r get_charboxzPdfTextPage.get_charboxs  <$&&D24EEBDKTXEJAq!QQ!XZZXZZGJAq!Q-dE1aAFFB!'17AG;JAq!Q 8677 7!Qzrcttttf\}}}}tj||||||}|std|j|j|j|jfS)aX Get the bounding box of a text rectangle at the given index. Attention: :meth:`.count_rects` must be called once with default params before subsequent :meth:`.get_rect` calls for this function to work. 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.))rVrFPDFText_GetRectrrX)rr?r\r]r^r_r[s rget_rectzPdfTextPage.get_rectsZZXZZC 1a  &tUAq!Q ? ? \[\\ \!'1733rcVtj||}|sdSt||S)a Returns: PdfTextObj | None: A handle to the textobject that includes the char at *index*, or None if it could not be resolved (e.g. escape character). Tip: Textobjects can also be obtained through :meth:`.PdfPage.get_objects`. Ntextpage)rFPDFText_GetTextObjectr)rr?raw_objs r get_textobjzPdfTextPage.get_textobjs61$>> 4'D1111rct|dkrtd|r|tjz}|r|tjz}|r|tjz}|dzd}tj|tj tj }tj ||||} t| |} | | | S)a Locate text on the page. Parameters: text (str): The string to search for. index (int): Character index at which to start searching. match_case (bool): If True, the search will be case-specific (upper and lower letters treated as different characters). match_whole_word (bool): If True, substring occurrences will be ignored (e. g. `cat` would not match `category`). consecutive (bool): If False (the default), :meth:`.search` will skip past the current match to look for the next match. If True, parts of the previous match may be caught again (e. g. searching for `aa` in `aaaa` would match 3 rather than 2 times). flags (int): Passthrough of raw pdfium searching flags. Note that you may want to use the boolean options instead. Returns: PdfTextSearcher: A helper object to search text. rz#Text length must be greater than 0.r)len ValueErrorrFPDF_MATCHCASEFPDF_MATCHWHOLEWORDFPDF_CONSECUTIVEencoder"r$r%r&FPDFText_FindStartr_add_kid) rtextr? 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)NNNNr)rr)rr3r)rr3)F)rFFFr)__name__ __module__ __qualname____doc__r propertyrr1r5rDr=rJrRr`rcrir} __classcell__rs@rrrs  66666 X#=#=#=#=L 4 4 4 4 +O+O+O+O\    ,8444" 2 2 2%%%%%%%%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 rfr r rFPDFText_FindClose)rr rfrs rr zPdfTextSearcher.__init__)s2   455555rc|jSr rers rrzPdfTextSearcher.parent.s }rcx||}|sdStj|}tj|}||fSr )rFPDFText_GetSchResultIndexFPDFText_GetSchCount)r find_funcr[r?r@s r_get_occurrencezPdfTextSearcher._get_occurrence3sF Yt__ 43D99-d33e|rc@|tjS)z Returns: (int, int) | None: 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) | None: 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_prevBrr) r~rrrr rrrrrrrs@rrr s66666 X@@@@@@@@@@rr)__all__r"logging pypdfium2.rawr rpypdfium2.internalinternalpdfium_ipypdfium2._helpers.miscrpypdfium2._helpers.pageobjectsrrV getLoggerr~logger AutoCloseablerrrrrs -  %%%%%%//////555555 ?  8 $ $LLLLL8)LLL^'@'@'@'@'@x-'@'@'@'@'@r