mindee/src/parsing/common/ocrPage.js

Mindee Client Library for Node.js

"use strict";
var __classPrivateFieldGet = (this && this.__classPrivateFieldGet) || function (receiver, state, kind, f) {
    if (kind === "a" && !f) throw new TypeError("Private accessor was defined without a getter");
    if (typeof state === "function" ? receiver !== state || !f : !state.has(receiver)) throw new TypeError("Cannot read private member from an object whose class did not declare it");
    return kind === "m" ? f : kind === "a" ? f.call(receiver) : f ? f.value : state.get(receiver);
};
var _OcrPage_instances, _OcrPage_areWordsOnSameLine, _OcrPage_toLines;
Object.defineProperty(exports, "__esModule", { value: true });
exports.OcrPage = void 0;
const geometry_1 = require("../../geometry");
class OcrPage {
    constructor(rawPrediction) {
        _OcrPage_instances.add(this);
        /** Flat list of all words read */
        this.allWords = [];
        /** List of words by which line they are on */
        this.allLines = [];
        const allWords = [];
        rawPrediction["all_words"] &&
            rawPrediction["all_words"].forEach((word) => {
                allWords.push(word);
            });
        this.allWords = allWords.sort((word1, word2) => (0, geometry_1.compareOnY)(word1.polygon, word2.polygon));
    }
    /**
     * Get all words on the page as ordered lines
     * @returns Sorted lines on the pages
     */
    getAllLines() {
        if (!this.allLines || this.allLines.length === 0) {
            this.allLines = __classPrivateFieldGet(this, _OcrPage_instances, "m", _OcrPage_toLines).call(this);
        }
        return this.allLines;
    }
    /**
     * Default string representation.
     */
    toString() {
        return this.getAllLines()
            .map((line) => line.map((word) => word.text).join(" "))
            .join("\n");
    }
}
exports.OcrPage = OcrPage;
_OcrPage_instances = new WeakSet(), _OcrPage_areWordsOnSameLine = function _OcrPage_areWordsOnSameLine(currentWord, nextWord) {
    const currentInNext = (0, geometry_1.isPointInPolygonY)((0, geometry_1.getCentroid)(currentWord.polygon), nextWord.polygon);
    const nextInCurrent = (0, geometry_1.isPointInPolygonY)((0, geometry_1.getCentroid)(nextWord.polygon), currentWord.polygon);
    return nextInCurrent || currentInNext;
}, _OcrPage_toLines = function _OcrPage_toLines() {
    const lines = [];
    const lineIdx = [];
    this.allWords.forEach((current, idxCurrent) => {
        if (!lineIdx.includes(idxCurrent)) {
            lines.push([current]);
            lineIdx.push(idxCurrent);
        }
        this.allWords.forEach((next, idxNext) => {
            if (idxCurrent === idxNext || lineIdx.includes(idxNext)) {
                return;
            }
            if (__classPrivateFieldGet(this, _OcrPage_instances, "m", _OcrPage_areWordsOnSameLine).call(this, current, next)) {
                lineIdx.push(idxNext);
                lines[lines.length - 1].push(next);
            }
        });
    });
    lines.forEach((line) => line.sort((word1, word2) => (0, geometry_1.compareOnX)(word1.polygon, word2.polygon)));
    return lines;
};