j5j dZddlmZddlmZmZddlmZeGddZeGddZ eGd d Z eGd d Z ed Z GddZ y)a)OCR element dataclasses for representing OCR output structure. This module provides a generic, engine-agnostic representation of OCR output. The OcrElement dataclass can represent structural units from any OCR source (hOCR, ALTO, custom engines, etc.) in a unified format suitable for rendering. ) annotations) dataclassfield)LiteralcdeZdZUdZded<ded<ded<ded<ed dZed dZd Zy ) BoundingBoxa%An axis-aligned bounding box in pixel coordinates. Coordinates use top-left origin (standard for images and hOCR). Attributes: left: Left edge x-coordinate top: Top edge y-coordinate right: Right edge x-coordinate bottom: Bottom edge y-coordinate floatlefttoprightbottomc4|j|jz S)zWidth of the bounding box.)r r selfs Q/var/www/html/qr/venv/lib/python3.12/site-packages/ocrmypdf/models/ocr_element.pywidthzBoundingBox.width#szzDII%%c4|j|jz S)zHeight of the bounding box.)r r rs rheightzBoundingBox.height(s{{TXX%%rc|j|jkr&td|jd|jd|j|jkr&td|jd|jdy)z"Validate bounding box coordinates.zInvalid bounding box: right (z ) < left ()zInvalid bounding box: bottom (z ) < top (N)r r ValueErrorr r rs r __post_init__zBoundingBox.__post_init__-sy :: !/ |:dii[PQR  ;; !0 YtxxjPQR  "rN)returnr ) __name__ __module__ __qualname____doc____annotations__propertyrrrrrrrsH  K J L M &&&& rrc.eZdZUdZdZded<dZded<y)BaselineakText baseline information. The baseline is represented as a linear equation: y = slope * x + intercept. This describes the line along which text characters sit, relative to the bottom-left corner of the line's bounding box. In hOCR, the baseline is specified relative to the bottom of the line's bbox, with the intercept being the vertical offset from the bottom and the slope representing rotation (positive = ascending left-to-right). Attributes: slope: Slope of the baseline (rise over run) intercept: Y-intercept of the baseline (vertical offset from bbox bottom) gr slope interceptN)rrrrr$rr%r!rrr#r#9s E5Iurr#ceZdZUdZdZded<dZded<dZded <dZded <dZ ded <dZ ded <dZ ded <dZ ded<y)FontInfoaFont information for text rendering. Attributes: name: Font family name (e.g., "Times New Roman") size: Font size in points bold: Whether the font is bold italic: Whether the font is italic monospace: Whether the font is monospace serif: Whether the font is serif (vs sans-serif) smallcaps: Whether the font uses small caps underline: Whether the text is underlined N str | Nonename float | NonesizeFboolbolditalic monospaceserif smallcaps underline) rrrrr)rr+r-r.r/r0r1r2r!rrr'r'NsY D*D,D$FDItE4ItItrr'c.eZdZUdZded<dZded<dZded<d Zded <dZd ed <e e Z ded<dZ ded<dZ ded<dZded<dZd ed<dZded<dZd ed<dZded<dZded<d#dZd$dZd%dZed&d Zed&d!Zed&d"Zy)' OcrElementaA generic OCR element representing any structural unit of OCR output. OcrElements form a tree structure where pages contain paragraphs, paragraphs contain lines, lines contain words, etc. The specific hierarchy depends on the OCR engine, but this dataclass can represent any of these levels. The ocr_class field uses hOCR naming conventions (ocr_page, ocr_par, ocr_line, ocrx_word, etc.) as a common vocabulary, but elements from other sources can map to these classes. Common hOCR classes: - ocr_page: The root element for a page - ocr_carea: A content/column area - ocr_par: A paragraph - ocr_line: A line of text - ocr_header: A header line - ocr_footer: A footer line - ocr_caption: A caption line - ocr_textfloat: A floating text element - ocrx_word: A single word Attributes: ocr_class: The element type (e.g., "ocr_page", "ocr_line", "ocrx_word") bbox: Axis-aligned bounding box in source pixel coordinates (top-left origin) poly: Polygon vertices for oriented/non-rectangular bounds text: Text content (primarily for leaf nodes like words) confidence: OCR confidence score (0.0-1.0) children: Child elements (hierarchical structure) direction: Text direction ("ltr" or "rtl") language: Language code (e.g., "eng", "deu", "chi_sim") baseline: Text baseline information (slope and intercept) textangle: Text rotation angle in degrees (counter-clockwise from horizontal) font: Font information (name, size, style) dpi: Image resolution in dots per inch (typically for page-level) page_number: Physical page number (0-indexed) logical_page_number: Logical page number (as printed on the page) str ocr_classNzBoundingBox | Nonebboxz list[tuple[float, float]] | Nonepolytextr* confidence)default_factorylist[OcrElement]childrenzLiteral['ltr', 'rtl'] | None directionr(languagezBaseline | Nonebaseline textanglezFontInfo | Nonefontdpiz int | None page_numberlogical_page_numbercg}|j|vr|j||jD] }|j|j|"|S)zIterate over all descendants matching the given class(es). Args: *ocr_classes: One or more ocr_class values to match Returns: List of all matching descendant elements (depth-first order) )r6appendr>extend iter_by_class)r ocr_classesresultchilds rrJzOcrElement.iter_by_classsS >>[ ( MM$ ]] =E MM-%--{; < = rcp|j|vr|S|jD]}|j|}||cSy)zFind the first descendant matching the given class(es). Args: *ocr_classes: One or more ocr_class values to match Returns: The first matching element, or None if not found N)r6r> find_by_class)rrKrMrLs rrOzOcrElement.find_by_classsJ >>[ (K]] E(U((+6F!  rc|jr |jS|jDcgc]}|j}}djd|DScc}w)zGet the combined text of this element and all descendants. Returns: Combined text content, with words separated by spaces  c3&K|] }|s| yw)Nr!).0ts r z0OcrElement.get_text_recursive..s.aA.s)r:r>get_text_recursivejoin)rrMtextss rrVzOcrElement.get_text_recursivesP 9999 9=G))+GGxx.5...HsAc$|jdS)zr?r@rArBrCrDrErFrJrOrVr r\rcrfr!rrr4r4gs$LN $D #-1D *1D#N $J #"'t!rs#( $$ $N  (  0 C-C- C-N % GGr