kh#ddlmZmZmZmZmZddlZddlZddl m Z ddl m Z dZ dd ejjd e fd Zd ddd d d d de f dededededededededeeeded eee eee edfffdZy))ListUnionOptionalDictTupleN)Layout)load_dataframeH?FTpagereturnc |ddg}|j|||||||}tj|} t| dk(r t S| ddgj dt |jjd| ddg<| d d gj dt |jjd| d d g<t| jjd d d ddddd} | S)zThe helper function used for extracting words from a pdfplumber page object. Returns: Layout: a layout object representing all extracted pdf tokens on this page. fontnamesize x_tolerance y_tolerancekeep_blank_chars use_text_flowhorizontal_ltr vertical_ttb extra_attrsrx0x1)lowerupperfloattopbottomx_1x_2y_1y_2idtype)rrr r!indexr)columns rectangle) block_type) extract_wordspd DataFramelenr clipintwidthastypeheightr reset_indexrename) rrrrrrrrtokensdf page_tokenss O/var/www/teggl/fontify/venv/lib/python3.12/site-packages/layoutparser/io/pdf.pyextract_words_for_pager;s+ !6*   )#%! F f B 2w!|x D$<AS_=DDWMd| E8 ""#dkk2B"CJJ7Sx! "   K filename load_imagesrrrrrrrdpiz Image.Imagec tj|} g} tt| jD]} | j| } t | |||||||}t | j|jd<t | j|jd<| |jd<| j||s| Sddl }|j|| }t|D]\} }|j\}}| | }|jd}|jd}||k7s||k7sC||z }||z }|j||f}||jd<||jd<|| | <| |fS)aLoad all tokens for each page from a PDF file, and save them in a list of Layout objects with the original page order. Args: filename (str): The path to the PDF file. load_images (bool, optional): Whether load screenshot for each page of the PDF file. When set to true, the function will return both the layout and screenshot image for each page. Defaults to False. x_tolerance (int, optional): The threshold used for extracting "word tokens" from the pdf file. It will merge the pdf characters into a word token if the difference between the x_2 of one character and the x_1 of the next is less than or equal to x_tolerance. See details in `pdf2plumber's documentation `_. Defaults to 1.5. y_tolerance (int, optional): The threshold used for extracting "word tokens" from the pdf file. It will merge the pdf characters into a word token if the difference between the y_2 of one character and the y_1 of the next is less than or equal to y_tolerance. See details in `pdf2plumber's documentation `_. Defaults to 2. keep_blank_chars (bool, optional): When keep_blank_chars is set to True, it will treat blank characters are treated as part of a word, not as a space between words. See details in `pdf2plumber's documentation `_. Defaults to False. use_text_flow (bool, optional): When use_text_flow is set to True, it will use the PDF's underlying flow of characters as a guide for ordering and segmenting the words, rather than presorting the characters by x/y position. (This mimics how dragging a cursor highlights text in a PDF; as with that, the order does not always appear to be logical.) See details in `pdf2plumber's documentation `_. Defaults to True. horizontal_ltr (bool, optional): When horizontal_ltr is set to True, it means the doc should read text from left to right, vice versa. Defaults to True. vertical_ttb (bool, optional): When vertical_ttb is set to True, it means the doc should read text from top to bottom, vice versa. Defaults to True. extra_attrs (Optional[List[str]], optional): Passing a list of extra_attrs (e.g., ["fontname", "size"]) will restrict each words to characters that share exactly the same value for each of those `attributes extracted by pdfplumber `_, and the resulting word dicts will indicate those attributes. See details in `pdf2plumber's documentation `_. Defaults to `["fontname", "size"]`. dpi (int, optional): When loading images of the pdf, you can also specify the resolution (or `DPI, dots per inch `_) for rendering the images. Higher DPI values mean clearer images (also larger file sizes). Setting dpi will also automatically resizes the extracted pdf_layout to match the sizes of the images. Therefore, when visualizing the pdf_layouts, it can be rendered appropriately. Defaults to `DEFAULT_PDF_DPI=72`, which is also the default rendering dpi from the pdfplumber PDF parser. Returns: List[Layout]: When `load_images=False`, it will only load the pdf_tokens from the PDF file. Each element of the list denotes all the tokens appeared on a single page, and the list is ordered the same as the original PDF page order. Tuple[List[Layout], List["Image.Image"]]: When `load_images=True`, besides the `all_page_layout`, it will also return a list of page images. Examples:: >>> import layoutparser as lp >>> pdf_layout = lp.load_pdf("path/to/pdf") >>> pdf_layout[0] # the layout for page 0 >>> pdf_layout, pdf_images = lp.load_pdf("path/to/pdf", load_images=True) >>> lp.draw_box(pdf_images[0], pdf_layout[0]) rr2r4r(rN)r?) pdfplumberopenranger/pagesr;rr2 page_datar4append pdf2imageconvert_from_path enumeraterscale)r=r>rrrrrrrr?plumber_pdf_objectall_page_layoutpage_idcur_pager9rG pdf_images page_image image_width image_height page_layout layout_width layout_heightscale_xscale_ys r:load_pdfrXTsB$2O/5567,%++G4, ##-')%#  */x~~)> g&*/*@ h')0 g&{+',* 00s0C #,Z#8 7 GZ(2 %K)'2K&009L'11(;Ml*lm.K% 4&6)//'0BC 1< %%g.2> %%h/+6( 7 **r<)r rFTTTN)typingrrrrrrApandasr-elementsr basicr DEFAULT_PDF_DPIrPager;strboolr1rXr<r:rbs65! 7 //  7 7x"'+M+M+M+M+ M+  M+  M+M+M+$s)$M+ M+ 4<tF|T--@@A ABM+r<