j5j9dZddlmZddlZddlZddlZddlZddlmZddl m Z m Z ddl m ZddlmZmZmZmZmZe dZej,eZej2ZGd d eZGd d Zy) zParser for hOCR format files. This module provides functionality to parse hOCR files (HTML-based OCR format) and convert them to the engine-agnostic OcrElement tree structure. For details of the hOCR format, see: http://kba.github.io/hocr-spec/1.2/ ) annotationsN)Path)Literalcast) ElementTree)Baseline BoundingBoxFontInfoOcrClass OcrElementltrrtlceZdZdZy)HocrParseErrorzError while parsing hOCR file.N)__name__ __module__ __qualname____doc__X/var/www/html/qr/venv/lib/python3.12/site-packages/ocrmypdf/hocrtransform/hocr_parser.pyrr(s(rrceZdZdZej dej Zej dej Zej dej Z ej dej Z ej dej Z ej dej Z ej dej Z ej d ej Zdd Zdd Zddd ZddZd dZ d!dZd"dZd#dZed$dZd%dZd&dZd'dZd'dZd(dZd'dZd)dZy )* HocrParseraParser for hOCR format files. Converts hOCR XML/HTML files into OcrElement trees. The hOCR format uses HTML with special class attributes (ocr_page, ocr_line, ocrx_word, etc.) and a title attribute containing properties like bbox, baseline, and confidence scores. z bbox \s+ (\d+) \s+ # left: uint (\d+) \s+ # top: uint (\d+) \s+ # right: uint (\d+) # bottom: uint z baseline \s+ ([\-\+]?\d*\.?\d*) \s+ # slope: +/- decimal float ([\-\+]?\d+) # intercept: +/- int zV textangle \s+ ([\-\+]?\d*\.?\d*) # angle: +/- decimal float zG x_wconf \s+ (\d+) # confidence: uint (0-100) zE x_fsize \s+ (\d*\.?\d+) # font size: float za x_font \s+ ([^\s;]+) # font name: non-whitespace, non-semicolon string z@ ppageno \s+ (\d+) # page number: uint zb scan_res \s+ (\d+) \s+ # x resolution (\d+) # y resolution ct||_ tjt j ||_|j jj}tjd|}|r|jd|_yd|_y#tj$r}td||d}~wwxYw)zInitialize the parser with an hOCR file. Args: hocr_file: Path to the hOCR file to parse Raises: HocrParseError: If the file cannot be parsed zFailed to parse hOCR file: Nz ({.*})html)r _hocr_pathETparseosfspath_tree ParseErrorrgetroottagrematchgroup_xmlns)self hocr_fileeroot_tagmatchess r__init__zHocrParser.__init__|sy/ K"))I"67DJ ::%%'++((=(3*1gmmA& r }} K #>qc!BC J Ks-BC-B<<Cc|jj|jdd}| td|j |S)zParse the hOCR file and return an OcrElement tree. Returns: The root OcrElement (ocr_page) containing the document structure Raises: HocrParseError: If no ocr_page element is found divocr_pagez&No ocr_page element found in hOCR file)r#find_xpathr _parse_page)r+page_divs rr zHocrParser.parsesD::??4;;uj#AB   !IJ J))rNc>d|j|}|r |d|dz }|S)zBuild an XPath expression for finding elements. Args: html_tag: HTML tag name (e.g., 'div', 'span', 'p') html_class: Optional class attribute to match Returns: XPath expression string z.//z [@class='z'])r*)r+html_tag html_classxpaths rr5zHocrParser._xpaths3dkk]8*-  y B/ /E rcd|jjdd}|j|}| td|j |}|j |}t tj|||}|j|jddD]1}|j|}||jj|3|jsU|j|jddD]1} |j| } | |jj| 3|S) zParse an ocr_page element. Args: page_elem: The XML element with class="ocr_page" Returns: OcrElement representing the page titlerzocr_page missing bbox) ocr_classbbox page_numberdpipocr_parspan ocrx_word)attribget _parse_bboxr_parse_ppageno_parse_scan_resr r PAGEiterfindr5_parse_paragraphchildrenappend _parse_word) r+ page_elemr=r?r@rApagepar_elem paragraph word_elemwords rr6zHocrParser._parse_pages%  $$Wb1& < !89 9))%0 ""5)mm#  "**4;;sI+FG 0H--h7I$ $$Y/ 0}}&// FK0PQ / '' 2#MM((. /  rcD|jjdd}|j|}|jjd}|dvrtt|nd}|jjd}t t j|||}hd}|j|jd D]U} | jjd d} | |vs$|j| | ||} | ;|jj| W|jsy|S) zParse an ocr_par element. Args: par_elem: The XML element with class="ocr_par" Returns: OcrElement representing the paragraph, or None if empty r=rdirr Nlang)r>r? directionlanguage>ocr_line ocr_footer ocr_header ocr_caption ocr_textfloatrDclass) rFrGrHr TextDirectionr r PARAGRAPHrLr5 _parse_linerNrO) r+rSr=r?dir_attrrZr[rT line_classes span_elem elem_classlines rrMzHocrParser._parse_paragraphs##GR0&??&&u--5-GD )T ??&&v.((   "**4;;v+>? 4I"))--gr:J\)'' :y(S#&&--d3  4!!rc2|jjdd}|j|}|y|j|}|j |}|jjd} | dvrt t | } n|} |jjdxs|} t||||| | } |j|jdd D]1} |j| }|| jj|3| jsy| S) aParse a line element (ocr_line, ocr_header, etc.). Args: line_elem: The XML element representing the line ocr_class: The hOCR class of the line parent_direction: Text direction inherited from parent parent_language: Language inherited from parent Returns: OcrElement representing the line, or None if empty r=rNrXr rY)r>r?baseline textanglerZr[rDrE) rFrGrH_parse_baseline_parse_textanglerrbr rLr5rPrNrO)r+ line_elemr>parent_directionparent_languager=r?rkrlrerZr[rirUrVs rrdzHocrParser._parse_line s$  $$Wb1& <''.))%0 ##''. ~ %.2=(.KI(I##''/B?  #++DKK ,LM +I##I.D $$T* + }} rc4|jjdd}|j|}|j|}|j |}|sy|j |}||dz }|j |}ttj||||S)zParse an ocrx_word element. Args: word_elem: The XML element with class="ocrx_word" Returns: OcrElement representing the word, or None if empty r=rNgY@)r>r?text confidencefont) rFrGrH_get_element_text_normalize_text_parse_x_wconf_parse_font_infor r WORD)r+rUr=r?rsrtrus rrPzHocrParser._parse_wordBs  $$Wb1&%%i0##D)((/  !#e+J$$U+mm!   rc|j |jnd}|D]}||j|z }||j|jz }|Sdz }|S)zGet the full text content of an element including children. Args: element: XML element Returns: Combined text content r)rsrvtail)r+elementrschilds rrvzHocrParser._get_element_textesh '||7w||R 2E D**51 1D 2  8 @ ?A@ rcJtjd|jS)zNormalize text using NFKC normalization. This splits ligatures and combines diacritics. Args: text: Raw text Returns: Normalized text, stripped of leading/trailing whitespace NFKC) unicodedata normalizestrip)rss rrwzHocrParser._normalize_textts $$VT288::rc <|jj|}|sy tt|j dt|j dt|j dt|j dS#t $rYywxYw)zParse a bbox from an hOCR title attribute. Args: title: The title attribute value Returns: BoundingBox or None if not found Nr)lefttoprightbottom) _bbox_patternsearchr floatr) ValueErrorr+r=r(s rrHzHocrParser._parse_bboxs""))%0 5;;q>*%++a.)EKKN+U[[^,     sA.B BBc|jj|}|sy t|jdrt |jdndt |jdS#t $rYywxYw)zParse baseline from an hOCR title attribute. Args: title: The title attribute value Returns: Baseline or None if not found Nrgr)slope intercept)_baseline_patternrrr)rrrs rrmzHocrParser._parse_baselinesr&&--e4 /4{{1~eEKKN+3 A/   sAA00 A<;A<c|jj|}|sy t|jdS#t$rYywxYw)zParse textangle from an hOCR title attribute. Args: title: The title attribute value Returns: Angle in degrees or None if not found Nr)_textangle_patternrrr)rrs rrnzHocrParser._parse_textanglesJ''..u5 Q( (  : AAc|jj|}|sy t|jdS#t$rYywxYw)zParse word confidence from an hOCR title attribute. Args: title: The title attribute value Returns: Confidence (0-100) or None if not found Nr)_x_wconf_patternrrr)rrs rrxzHocrParser._parse_x_wconfsJ%%,,U3 Q( (  rc|jj|}|sy t|jdS#t$rYywxYw)zParse physical page number from an hOCR title attribute. Args: title: The title attribute value Returns: Page number or None if not found Nr)_ppageno_patternrintr)rrs rrIzHocrParser._parse_ppagenosJ%%,,U3 u{{1~& &  rc|jj|}|sy t|jdS#t$rYywxYw)zParse scan resolution (DPI) from an hOCR title attribute. Args: title: The title attribute value Returns: DPI (using first value if x and y differ) or None if not found Nr)_scan_res_patternrrr)rrs rrJzHocrParser._parse_scan_ressJ&&--e4 Q( (  rc|jj|}|jj|}|s|syt|r|j dnd|rt |j dSdS)zParse font information from an hOCR title attribute. Args: title: The title attribute value Returns: FontInfo or None if no font info found Nr)namesize)_x_font_patternr_x_fsize_patternr r)r)r+r= font_match size_matchs rryzHocrParser._parse_font_infosy))007 **11%8 *(2!!!$/9z''*+  ?C  r)r,z str | Path)returnr )N)r9strr: str | Nonerr)rQElementrr )rSrrOcrElement | None) rorr>rrpzTextDirection | Nonerqrrr)rUrrr)r}rrr)rsrrr)r=rrzBoundingBox | None)r=rrzBaseline | None)r=rrz float | None)r=rrz int | None)r=rrzFontInfo | None) rrrrr'compileVERBOSErrrrrrrrr0r r5r6rMrdrPrv staticmethodrwrHrmrnrxrIrJryrrrrr,sBJJ   M#  $  "rzz  "rzz  !bjj  O"rzz  #  :(* (T.`777/ 7 $ 7  7r! F  ; ;.*$$$& rr)r __future__rloggingr!r'rpathlibrtypingrr xml.etreerrocrmypdf.models.ocr_elementrr r r r rb getLoggerrlogr Exceptionrrrrrrsm #  ' % g! **)Y)] ] r