id-scanner-lib 1.3.3 → 1.5.0

package/src/types/tesseract.d.ts

@@ -2,36 +2,279 @@
  * Type definitions for tesseract.js
  */
 
-declare module 'tesseract.js' {
+declare module "tesseract.js" {
+  // Based on https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts
+  // and https://github.com/naptha/tesseract.js/blob/master/docs/api.md
+
+  export interface Point {
+    x: number
+    y: number
+  }
+
+  export interface Bbox {
+    x0: number
+    y0: number
+    x1: number
+    y1: number
+  }
+
+  export interface Baseline {
+    x0: number
+    y0: number
+    x1: number
+    y1: number
+    has_descenders: boolean
+    has_ascenders: boolean
+  }
+
+  export interface Word {
+    symbols: Symbol[]
+    choices: Choice[]
+    text: string
+    confidence: number
+    baseline: Baseline
+    bbox: Bbox
+    is_numeric: boolean
+    in_dictionary: boolean
+    direction: string
+    language: string
+    is_from_dictionary: boolean
+    is_fuzzy: boolean
+    is_certain: boolean
+    is_bold: boolean
+    is_italic: boolean
+    is_underlined: boolean
+    is_monospace: boolean
+    is_serif: boolean
+    is_smallcaps: boolean
+    font_id: number
+    font_size: number
+    font_name: string
+  }
+
+  export interface Symbol {
+    choices: Choice[]
+    image: null | HTMLImageElement // Or string if it's a path/URL
+    text: string
+    confidence: number
+    baseline: Baseline
+    bbox: Bbox
+    is_superscript: boolean
+    is_subscript: boolean
+    is_dropcap: boolean
+  }
+
+  export interface Choice {
+    text: string
+    confidence: number
+  }
+
+  export interface Line {
+    words: Word[]
+    text: string
+    confidence: number
+    baseline: Baseline
+    bbox: Bbox
+  }
+
+  export interface Paragraph {
+    lines: Line[]
+    text: string
+    confidence: number
+    baseline: Baseline
+    bbox: Bbox
+    is_ltr: boolean
+  }
+
+  export interface Block {
+    paragraphs: Paragraph[]
+    lines: Line[]
+    words: Word[]
+    text: string
+    confidence: number
+    baseline: Baseline
+    bbox: Bbox
+    blocktype: string
+    polygon: Point[]
+  }
+
+  export interface Page {
+    blocks: Block[]
+    confidence: number
+    html: string // HTML representation of the page
+    jobId?: string
+    text: string
+    lines: Line[]
+    oem: string
+    operator: string
+    paragraphs: Paragraph[]
+    psm: string
+    symbols: Symbol[]
+    version: string
+    words: Word[]
+    hocr?: string // hOCR output
+    tsv?: string // TSV output
+  }
+
+  export interface LoggerMessage {
+    jobId?: string
+    workerId?: string
+    status: string
+    progress: number
+    userfriendlyText?: string
+  }
+
   export interface WorkerOptions {
-    langPath?: string;
-    corePath?: string;
-    workerPath?: string;
-    logger?: (message: any) => void;
-    errorHandler?: (error: Error) => void;
+    langPath?: string
+    corePath?: string
+    workerPath?: string
+    logger?: (message: LoggerMessage) => void // More specific type for logger message <mcreference index="1" link="https://github.com/naptha/tesseract.js/blob/master/docs/api.md"></mcreference>
+    errorHandler?: (error: Error) => void
+    // Add other options based on documentation if needed
+    [key: string]: any // For other less common or dynamic options
   }
 
   export interface RecognizeResult {
+    data: Page // Use the detailed Page interface
+  }
+
+  export interface DetectResult {
     data: {
-      text: string;
-      hocr: string;
-      tsv: string;
-      confidence: number;
-      blocks: any[];
-      lines: any[];
-      words: any[];
-      symbols: any[];
-    };
+      tesseract_script_id: number | null
+      script: string | null
+      script_confidence: number | null
+      orientation_degrees: number | null
+      orientation_confidence: number | null
+    }
+    jobId?: string
+  }
+
+  export interface ConfigResult {
+    data: null
+    jobId?: string
   }
 
+  export type ImageLike =
+    | HTMLImageElement
+    | HTMLCanvasElement
+    | File
+    | string
+    | Buffer
+    | ImageData // Common image types
+
   export interface Worker {
-    load(): Promise<any>;
-    loadLanguage(lang: string): Promise<any>;
-    initialize(lang: string): Promise<any>;
-    setParameters(params: Record<string, any>): Promise<any>;
-    recognize(image: HTMLCanvasElement | ImageData | Buffer | string): Promise<RecognizeResult>;
-    terminate(): Promise<any>;
+    load(jobId?: string): Promise<ConfigResult> // <mcreference index="4" link="https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts"></mcreference>
+    loadLanguage(
+      langs?: string | string[],
+      jobId?: string
+    ): Promise<ConfigResult> // <mcreference index="4" link="https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts"></mcreference>
+    initialize(
+      langs?: string | string[],
+      oem?: OEM,
+      config?: string | Partial<InitOptions>,
+      jobId?: string
+    ): Promise<ConfigResult> // <mcreference index="4" link="https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts"></mcreference>
+    setParameters(
+      params: Partial<Parameters>,
+      jobId?: string
+    ): Promise<ConfigResult> // <mcreference index="4" link="https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts"></mcreference>
+    recognize(
+      image: ImageLike,
+      options?: Partial<RecognizeOptions>,
+      output?: Partial<OutputFormats>,
+      jobId?: string
+    ): Promise<RecognizeResult> // <mcreference index="4" link="https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts"></mcreference>
+    detect(
+      image: ImageLike,
+      options?: Partial<WorkerOptions>,
+      jobId?: string
+    ): Promise<DetectResult> // <mcreference index="4" link="https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts"></mcreference>
+    terminate(jobId?: string): Promise<ConfigResult> // <mcreference index="4" link="https://github.com/naptha/tesseract.js/blob/master/src/index.d.ts"></mcreference>
+    // Add other worker methods if present in the version you are targeting
+    // Example from docs for other methods like FS operations:
+    writeText?(
+      path: string,
+      text: string,
+      jobId?: string
+    ): Promise<ConfigResult>
+    readText?(path: string, jobId?: string): Promise<ConfigResult>
+    removeFile?(path: string, jobId?: string): Promise<ConfigResult> // Assuming removeFile also returns ConfigResult or similar
+    FS?(method: string, args: any[], jobId?: string): Promise<any> // FS is more generic
+  }
+
+  // Based on Tesseract's OEM and PSM enums
+  export enum OEM {
+    TESSERACT_ONLY = 0,
+    LSTM_ONLY = 1,
+    TESSERACT_LSTM_COMBINED = 2,
+    DEFAULT = 3,
+  }
+
+  export enum PSM {
+    OSD_ONLY = 0,
+    AUTO_OSD = 1,
+    AUTO_ONLY = 2,
+    AUTO = 3,
+    SINGLE_COLUMN = 4,
+    SINGLE_BLOCK_VERT_TEXT = 5,
+    SINGLE_BLOCK = 6,
+    SINGLE_LINE = 7,
+    SINGLE_WORD = 8,
+    CIRCLE_WORD = 9,
+    SINGLE_CHAR = 10,
+    SPARSE_TEXT = 11,
+    SPARSE_TEXT_OSD = 12,
+    RAW_LINE = 13,
+  }
+
+  export interface Parameters {
+    tessedit_char_whitelist?: string
+    tessedit_pageseg_mode?: PSM
+    // Add other Tesseract parameters as needed
+    [key: string]: any // For flexibility with other parameters
+  }
+
+  export interface RecognizeOptions {
+    rectangle?: Bbox // For recognizing a specific region
+    rectangles?: Bbox[] // For recognizing multiple regions
+    // Add other recognize specific options
+    [key: string]: any
   }
 
-  export function createWorker(options?: WorkerOptions): Worker;
+  export interface OutputFormats {
+    text?: boolean
+    blocks?: boolean
+    hocr?: boolean
+    tsv?: boolean
+    pdf?: boolean // If PDF output is supported
+    // Add other output formats
+    [key: string]: any
+  }
+
+  export interface InitOptions {
+    load_system_dawg?: boolean
+    load_freq_dawg?: boolean
+    load_punc_dawg?: boolean
+    load_number_dawg?: boolean
+    load_unambig_dawg?: boolean
+    load_bigram_dawg?: boolean
+    load_fixed_length_dawgs?: boolean
+    // Add other init-only parameters
+    [key: string]: any
+  }
+
+  export function createWorker(options?: Partial<WorkerOptions>): Worker // 修正返回类型为 Worker 而非 Promise<Worker>
+  export function setLogging(logging: boolean): void
+  export function recognize(
+    image: ImageLike,
+    langs?: string | string[],
+    options?: Partial<RecognizeOptions & WorkerOptions>
+  ): Promise<RecognizeResult>
+  export function detect(
+    image: ImageLike,
+    options?: Partial<WorkerOptions>
+  ): Promise<DetectResult>
+
+  // 正确导出 OEM 和 PSM 枚举
+  export { OEM, PSM }
 }

package/src/utils/image-processing.ts

@@ -6,6 +6,7 @@
  */
 
 import imageCompression from "browser-image-compression"
+import { Point, Rect, ImageProcessingOptions } from './types';
 
 /**
  * 图像处理器配置选项
@@ -481,68 +482,86 @@ export class ImageProcessor {
   }
 
   /**
-   * 调整图像大小
-   *
-   * @param imageData 原始图像数据
+   * 将图像调整到指定大小
+   * @param image 输入图像
    * @param maxWidth 最大宽度
    * @param maxHeight 最大高度
-   * @param maintainAspectRatio 是否保持宽高比
-   * @returns ImageData 调整大小后的图像数据
+   * @param keepAspectRatio 是否保持宽高比
+   * @returns 调整后的图像
    */
-  static resizeImage(
-    imageData: ImageData,
+  public static resizeImage(
+    image: ImageData | HTMLImageElement | HTMLCanvasElement,
     maxWidth: number,
     maxHeight: number,
-    maintainAspectRatio: boolean = true
+    keepAspectRatio: boolean = true
   ): ImageData {
-    const { width, height } = imageData
-
-    // 如果图像已经小于指定大小，则不需要调整
-    if (width <= maxWidth && height <= maxHeight) {
-      return imageData
+    // 创建canvas元素
+    const canvas = document.createElement('canvas');
+    const ctx = canvas.getContext('2d');
+    
+    if (!ctx) {
+      throw new Error('无法创建Canvas上下文');
     }
-
-    let newWidth = maxWidth
-    let newHeight = maxHeight
-
-    // 计算新的尺寸，保持宽高比
-    if (maintainAspectRatio) {
-      const ratio = Math.min(maxWidth / width, maxHeight / height)
-      newWidth = Math.floor(width * ratio)
-      newHeight = Math.floor(height * ratio)
+    
+    // 获取图像尺寸
+    let width: number;
+    let height: number;
+    
+    if (image instanceof ImageData) {
+      width = image.width;
+      height = image.height;
+    } else {
+      width = image.width;
+      height = image.height;
     }
-
-    // 创建用于调整大小的Canvas
-    const canvas = document.createElement("canvas")
-    canvas.width = newWidth
-    canvas.height = newHeight
-
-    const ctx = canvas.getContext("2d")
-    if (!ctx) {
-      throw new Error("无法创建2D上下文")
+    
+    // 计算调整后的尺寸
+    let newWidth = width;
+    let newHeight = height;
+    
+    if (keepAspectRatio) {
+      if (width > height) {
+        if (width > maxWidth) {
+          newHeight = Math.round(height * (maxWidth / width));
+          newWidth = maxWidth;
+        }
+      } else {
+        if (height > maxHeight) {
+          newWidth = Math.round(width * (maxHeight / height));
+          newHeight = maxHeight;
+        }
+      }
+    } else {
+      newWidth = Math.min(width, maxWidth);
+      newHeight = Math.min(height, maxHeight);
     }
-
-    // 创建临时Canvas绘制原始ImageData
-    const tempCanvas = document.createElement("canvas")
-    tempCanvas.width = width
-    tempCanvas.height = height
-
-    const tempCtx = tempCanvas.getContext("2d")
+    
+    // 设置canvas尺寸
+    canvas.width = newWidth;
+    canvas.height = newHeight;
+    
+    // 绘制调整后的图像
+    if (image instanceof ImageData) {
+      // 创建临时canvas存储ImageData
+      const tempCanvas = document.createElement('canvas');
+      const tempCtx = tempCanvas.getContext('2d');
+      
     if (!tempCtx) {
-      throw new Error("无法创建临时2D上下文")
+        throw new Error('无法创建临时Canvas上下文');
     }
 
-    tempCtx.putImageData(imageData, 0, 0)
-
-    // 使用缩放平滑算法
-    ctx.imageSmoothingEnabled = true
-    ctx.imageSmoothingQuality = "high"
-
-    // 绘制调整大小的图像
-    ctx.drawImage(tempCanvas, 0, 0, width, height, 0, 0, newWidth, newHeight)
+      tempCanvas.width = image.width;
+      tempCanvas.height = image.height;
+      tempCtx.putImageData(image, 0, 0);
+      
+      // 绘制调整后的图像
+      ctx.drawImage(tempCanvas, 0, 0, width, height, 0, 0, newWidth, newHeight);
+    } else {
+      ctx.drawImage(image, 0, 0, width, height, 0, 0, newWidth, newHeight);
+    }
 
-    // 获取新的ImageData
-    return ctx.getImageData(0, 0, newWidth, newHeight)
+    // 返回调整后的ImageData
+    return ctx.getImageData(0, 0, newWidth, newHeight);
   }
   
   /**