@pujansrt/data-genie/dist/readers/fixed-width-reader.js

High performant ETL engine written in TypeScript

"use strict";
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    var desc = Object.getOwnPropertyDescriptor(m, k);
    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
      desc = { enumerable: true, get: function() { return m[k]; } };
    }
    Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
    if (k2 === undefined) k2 = k;
    o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
    Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
    o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
    var ownKeys = function(o) {
        ownKeys = Object.getOwnPropertyNames || function (o) {
            var ar = [];
            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
            return ar;
        };
        return ownKeys(o);
    };
    return function (mod) {
        if (mod && mod.__esModule) return mod;
        var result = {};
        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
        __setModuleDefault(result, mod);
        return result;
    };
})();
Object.defineProperty(exports, "__esModule", { value: true });
exports.FixedWidthReader = void 0;
const fs_1 = require("fs");
const readline = __importStar(require("readline"));
class FixedWidthReader {
    constructor(filePath) {
        this.filePath = filePath;
        this.fieldWidths = [];
        this.fieldNames = [];
        this.hasFieldNamesInFirstRow = false;
        this.initialized = false;
    }
    setFieldWidths(...widths) {
        this.fieldWidths = widths;
        return this;
    }
    setFieldNames(...names) {
        this.fieldNames = names;
        return this;
    }
    setFieldNamesInFirstRow(value) {
        this.hasFieldNamesInFirstRow = value;
        return this;
    }
    async *read() {
        if (this.fieldWidths.length === 0) {
            throw new Error('Field widths must be defined before reading.');
        }
        const stream = (0, fs_1.createReadStream)(this.filePath, { encoding: 'utf-8' });
        const rl = readline.createInterface({ input: stream, crlfDelay: Infinity });
        for await (const line of rl) {
            if (!line.trim())
                continue;
            // If field names come from first row
            if (!this.initialized && this.hasFieldNamesInFirstRow) {
                this.fieldNames = this.splitLine(line);
                this.initialized = true;
                continue; // skip header line
            }
            // Auto-generate field names if not set
            if (!this.initialized && this.fieldNames.length === 0) {
                this.fieldNames = this.fieldWidths.map((_, i) => `field${i}`);
                this.initialized = true;
            }
            const values = this.splitLine(line);
            const record = {};
            for (let i = 0; i < this.fieldNames.length; i++) {
                record[this.fieldNames[i]] = values[i];
            }
            yield record;
        }
    }
    splitLine(line) {
        const values = [];
        let pos = 0;
        for (const width of this.fieldWidths) {
            const field = line.substring(pos, pos + width).trim();
            values.push(field);
            pos += width;
        }
        return values;
    }
}
exports.FixedWidthReader = FixedWidthReader;