@thecodingwhale/cv-processor/dist/extractors/SectionExtractor.js

CV Processor to extract structured data from PDF resumes using TypeScript

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.SectionExtractor = void 0;
const patterns_1 = require("../utils/patterns");
/**
 * Class for extracting sections from CV text
 */
class SectionExtractor {
    /**
     * Split CV text into sections based on common section headers
     */
    segmentCVIntoSections(text) {
        // Split text into lines for processing
        const lines = text.split('\n');
        let currentSection = 'header';
        const sections = { [currentSection]: [] };
        for (const line of lines) {
            const trimmedLine = line.trim();
            if (!trimmedLine) {
                continue;
            }
            // Check if this line is a section header
            let sectionFound = false;
            for (const [sectionName, pattern] of Object.entries(patterns_1.Patterns.sections)) {
                if (pattern.test(trimmedLine) && trimmedLine.length < 50) {
                    // Section headers are usually short
                    currentSection = sectionName;
                    if (!sections[currentSection]) {
                        sections[currentSection] = [];
                    }
                    sectionFound = true;
                    break;
                }
            }
            if (!sectionFound) {
                sections[currentSection].push(trimmedLine);
            }
        }
        // Combine lines in each section
        const result = {};
        for (const [section, lines] of Object.entries(sections)) {
            result[section] = lines.join('\n');
        }
        return result;
    }
}
exports.SectionExtractor = SectionExtractor;