jtcsv 2.2.8 → 3.1.0

package/dist/src/utils/bom-utils.js

@@ -0,0 +1,267 @@
+"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.BOM_SIGNATURES = void 0;
+exports.detectBom = detectBom;
+exports.stripBom = stripBom;
+exports.stripBomFromString = stripBomFromString;
+exports.createBomStripStream = createBomStripStream;
+exports.readFileWithBomHandling = readFileWithBomHandling;
+exports.fileHasBomSync = fileHasBomSync;
+exports.normalizeCsvInput = normalizeCsvInput;
+exports.normalizeCsvInputAsync = normalizeCsvInputAsync;
+exports.createBomStrippingIterator = createBomStrippingIterator;
+exports.detectBomAsync = detectBomAsync;
+const stream_1 = require("stream");
+const fs = __importStar(require("fs"));
+const fsPromises = __importStar(require("fs/promises"));
+exports.BOM_SIGNATURES = {
+    'utf-8': Buffer.from([0xEF, 0xBB, 0xBF]),
+    'utf-16le': Buffer.from([0xFF, 0xFE]),
+    'utf-16be': Buffer.from([0xFE, 0xFF]),
+    'utf-32le': Buffer.from([0xFF, 0xFE, 0x00, 0x00]),
+    'utf-32be': Buffer.from([0x00, 0x00, 0xFE, 0xFF])
+};
+function detectBom(input) {
+    if (!input) {
+        return null;
+    }
+    let buffer;
+    if (typeof input === 'string') {
+        buffer = Buffer.from(input, 'utf8');
+    }
+    else if (Buffer.isBuffer(input)) {
+        buffer = input;
+    }
+    else {
+        return null;
+    }
+    for (const [encoding, signature] of Object.entries(exports.BOM_SIGNATURES)) {
+        if (buffer.length >= signature.length) {
+            if (buffer.slice(0, signature.length).equals(signature)) {
+                return {
+                    encoding: encoding,
+                    bomLength: signature.length,
+                    hasBom: true
+                };
+            }
+        }
+    }
+    return null;
+}
+function stripBom(input) {
+    if (!input) {
+        return input;
+    }
+    const bomInfo = detectBom(input);
+    if (!bomInfo) {
+        return input;
+    }
+    if (Buffer.isBuffer(input)) {
+        return input.slice(bomInfo.bomLength);
+    }
+    if (typeof input === 'string') {
+        const buffer = Buffer.from(input, 'utf8');
+        const strippedBuffer = buffer.slice(bomInfo.bomLength);
+        let encoding = 'utf8';
+        if (bomInfo.encoding === 'utf-16le') {
+            encoding = 'utf16le';
+        }
+        else if (bomInfo.encoding === 'utf-16be') {
+            encoding = 'utf16le';
+        }
+        return strippedBuffer.toString(encoding);
+    }
+    return input;
+}
+function stripBomFromString(str) {
+    if (typeof str !== 'string') {
+        return str;
+    }
+    if (str.charCodeAt(0) === 0xFEFF) {
+        return str.slice(1);
+    }
+    if (str.length >= 3 &&
+        str.charCodeAt(0) === 0xEF &&
+        str.charCodeAt(1) === 0xBB &&
+        str.charCodeAt(2) === 0xBF) {
+        return str.slice(3);
+    }
+    return str;
+}
+function createBomStripStream() {
+    let bomStripped = false;
+    return new stream_1.Transform({
+        transform(chunk, encoding, callback) {
+            if (!bomStripped) {
+                const bomInfo = detectBom(chunk);
+                if (bomInfo) {
+                    chunk = chunk.slice(bomInfo.bomLength);
+                    bomStripped = true;
+                }
+                else {
+                    bomStripped = true;
+                }
+            }
+            this.push(chunk);
+            callback();
+        }
+    });
+}
+async function readFileWithBomHandling(filePath, options = {}) {
+    const buffer = await fsPromises.readFile(filePath);
+    const bomInfo = detectBom(buffer);
+    const hadBom = !!bomInfo;
+    let data;
+    let encoding = options.encoding || 'utf8';
+    if (bomInfo) {
+        data = buffer.slice(bomInfo.bomLength);
+        if (!options.encoding) {
+            if (bomInfo.encoding === 'utf-8') {
+                encoding = 'utf8';
+            }
+            else if (bomInfo.encoding === 'utf-16le') {
+                encoding = 'utf16le';
+            }
+            else if (bomInfo.encoding === 'utf-16be') {
+                encoding = 'utf16le';
+            }
+            else {
+                encoding = 'utf8';
+            }
+        }
+    }
+    else {
+        data = buffer;
+    }
+    if (options.encoding || bomInfo) {
+        data = data.toString(encoding);
+    }
+    return {
+        data,
+        encoding,
+        hadBom,
+        bomInfo: bomInfo || null
+    };
+}
+function fileHasBomSync(filePath) {
+    const fd = fs.openSync(filePath, 'r');
+    const buffer = Buffer.alloc(4);
+    const bytesRead = fs.readSync(fd, buffer, 0, 4, 0);
+    fs.closeSync(fd);
+    if (bytesRead < 2) {
+        return null;
+    }
+    return detectBom(buffer.slice(0, bytesRead));
+}
+function normalizeCsvInput(csvInput, options = {}) {
+    if (!csvInput) {
+        return '';
+    }
+    let normalized;
+    if (Buffer.isBuffer(csvInput)) {
+        const bomInfo = detectBom(csvInput);
+        if (bomInfo) {
+            normalized = csvInput.slice(bomInfo.bomLength).toString(bomInfo.encoding);
+        }
+        else {
+            normalized = csvInput.toString(options.encoding || 'utf8');
+        }
+    }
+    else if (typeof csvInput === 'string') {
+        normalized = stripBomFromString(csvInput);
+    }
+    else {
+        throw new Error('CSV input must be a string or Buffer');
+    }
+    if (options.normalizeLineEndings !== false) {
+        normalized = normalized.replace(/\r\n|\r/g, '\n');
+    }
+    return normalized;
+}
+async function normalizeCsvInputAsync(csvInput, options = {}) {
+    if (typeof csvInput === 'object' && 'filePath' in csvInput) {
+        const result = await readFileWithBomHandling(csvInput.filePath, {
+            encoding: options.encoding || 'utf8'
+        });
+        let normalized = typeof result.data === 'string' ? result.data : result.data.toString();
+        if (options.normalizeLineEndings !== false) {
+            normalized = normalized.replace(/\r\n|\r/g, '\n');
+        }
+        return normalized;
+    }
+    return normalizeCsvInput(csvInput, options);
+}
+async function* createBomStrippingIterator(stream) {
+    let bomStripped = false;
+    for await (const chunk of stream) {
+        if (!bomStripped) {
+            const bomInfo = detectBom(chunk);
+            if (bomInfo) {
+                yield chunk.slice(bomInfo.bomLength);
+                bomStripped = true;
+                continue;
+            }
+            else {
+                bomStripped = true;
+            }
+        }
+        yield chunk;
+    }
+}
+async function detectBomAsync(filePath) {
+    const fd = await fsPromises.open(filePath, 'r');
+    const buffer = Buffer.alloc(4);
+    const { bytesRead } = await fd.read(buffer, 0, 4, 0);
+    await fd.close();
+    if (bytesRead < 2) {
+        return null;
+    }
+    return detectBom(buffer.slice(0, bytesRead));
+}
+exports.default = {
+    detectBom,
+    stripBom,
+    stripBomFromString,
+    createBomStripStream,
+    readFileWithBomHandling,
+    fileHasBomSync,
+    normalizeCsvInput,
+    normalizeCsvInputAsync,
+    createBomStrippingIterator,
+    detectBomAsync,
+    BOM_SIGNATURES: exports.BOM_SIGNATURES
+};
+//# sourceMappingURL=bom-utils.js.map

package/dist/src/utils/bom-utils.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"bom-utils.js","sourceRoot":"","sources":["../../../src/utils/bom-utils.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAkDA,8BA4BC;AAQD,4BA+BC;AAQD,gDAmBC;AAOD,oDAoBC;AASD,0DA4CC;AAQD,wCAWC;AASD,8CA6BC;AASD,wDAqBC;AAQD,gEAoBC;AAQD,wCAWC;AA7VD,mCAAmC;AACnC,uCAAyB;AACzB,wDAA0C;AAK7B,QAAA,cAAc,GAAG;IAC5B,OAAO,EAAE,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IACxC,UAAU,EAAE,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACrC,UAAU,EAAE,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACrC,UAAU,EAAE,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;IACjD,UAAU,EAAE,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC;CACzC,CAAC;AA4BX,SAAgB,SAAS,CAAC,KAAyC;IACjE,IAAI,CAAC,KAAK,EAAE,CAAC;QACX,OAAO,IAAI,CAAC;IACd,CAAC;IAED,IAAI,MAAc,CAAC;IACnB,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;QAC9B,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;IACtC,CAAC;SAAM,IAAI,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;QAClC,MAAM,GAAG,KAAK,CAAC;IACjB,CAAC;SAAM,CAAC;QACN,OAAO,IAAI,CAAC;IACd,CAAC;IAGD,KAAK,MAAM,CAAC,QAAQ,EAAE,SAAS,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,sBAAc,CAAC,EAAE,CAAC;QACnE,IAAI,MAAM,CAAC,MAAM,IAAI,SAAS,CAAC,MAAM,EAAE,CAAC;YACtC,IAAI,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,SAAS,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,EAAE,CAAC;gBACxD,OAAO;oBACL,QAAQ,EAAE,QAAoB;oBAC9B,SAAS,EAAE,SAAS,CAAC,MAAM;oBAC3B,MAAM,EAAE,IAAI;iBACb,CAAC;YACJ,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAQD,SAAgB,QAAQ,CAAC,KAAyC;IAChE,IAAI,CAAC,KAAK,EAAE,CAAC;QACX,OAAO,KAAY,CAAC;IACtB,CAAC;IAED,MAAM,OAAO,GAAG,SAAS,CAAC,KAAK,CAAC,CAAC;IACjC,IAAI,CAAC,OAAO,EAAE,CAAC;QACb,OAAO,KAAK,CAAC;IACf,CAAC;IAED,IAAI,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;QAC3B,OAAO,KAAK,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;IACxC,CAAC;IAED,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;QAE9B,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;QAC1C,MAAM,cAAc,GAAG,MAAM,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;QAGvD,IAAI,QAAQ,GAAmB,MAAM,CAAC;QACtC,IAAI,OAAO,CAAC,QAAQ,KAAK,UAAU,EAAE,CAAC;YACpC,QAAQ,GAAG,SAAS,CAAC;QACvB,CAAC;aAAM,IAAI,OAAO,CAAC,QAAQ,KAAK,UAAU,EAAE,CAAC;YAC3C,QAAQ,GAAG,SAAS,CAAC;QACvB,CAAC;QAED,OAAO,cAAc,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC;IAC3C,CAAC;IAED,OAAO,KAAK,CAAC;AACf,CAAC;AAQD,SAAgB,kBAAkB,CAAC,GAAW;IAC5C,IAAI,OAAO,GAAG,KAAK,QAAQ,EAAE,CAAC;QAC5B,OAAO,GAAU,CAAC;IACpB,CAAC;IAGD,IAAI,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,KAAK,MAAM,EAAE,CAAC;QACjC,OAAO,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;IACtB,CAAC;IAGD,IAAI,GAAG,CAAC,MAAM,IAAI,CAAC;QACf,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,KAAK,IAAI;QAC1B,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,KAAK,IAAI;QAC1B,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QAC/B,OAAO,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;IACtB,CAAC;IAED,OAAO,GAAG,CAAC;AACb,CAAC;AAOD,SAAgB,oBAAoB;IAClC,IAAI,WAAW,GAAG,KAAK,CAAC;IAExB,OAAO,IAAI,kBAAS,CAAC;QACnB,SAAS,CAAC,KAAa,EAAE,QAAgB,EAAE,QAAuD;YAChG,IAAI,CAAC,WAAW,EAAE,CAAC;gBACjB,MAAM,OAAO,GAAG,SAAS,CAAC,KAAK,CAAC,CAAC;gBACjC,IAAI,OAAO,EAAE,CAAC;oBAEZ,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;oBACvC,WAAW,GAAG,IAAI,CAAC;gBACrB,CAAC;qBAAM,CAAC;oBACN,WAAW,GAAG,IAAI,CAAC;gBACrB,CAAC;YACH,CAAC;YAED,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;YACjB,QAAQ,EAAE,CAAC;QACb,CAAC;KACF,CAAC,CAAC;AACL,CAAC;AASM,KAAK,UAAU,uBAAuB,CAC3C,QAAgB,EAChB,UAAyC,EAAE;IAE3C,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC;IAEnD,MAAM,OAAO,GAAG,SAAS,CAAC,MAAM,CAAC,CAAC;IAClC,MAAM,MAAM,GAAG,CAAC,CAAC,OAAO,CAAC;IAEzB,IAAI,IAAqB,CAAC;IAC1B,IAAI,QAAQ,GAAG,OAAO,CAAC,QAAQ,IAAI,MAAM,CAAC;IAE1C,IAAI,OAAO,EAAE,CAAC;QAEZ,IAAI,GAAG,MAAM,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;QAGvC,IAAI,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;YAEtB,IAAI,OAAO,CAAC,QAAQ,KAAK,OAAO,EAAE,CAAC;gBACjC,QAAQ,GAAG,MAAM,CAAC;YACpB,CAAC;iBAAM,IAAI,OAAO,CAAC,QAAQ,KAAK,UAAU,EAAE,CAAC;gBAC3C,QAAQ,GAAG,SAAS,CAAC;YACvB,CAAC;iBAAM,IAAI,OAAO,CAAC,QAAQ,KAAK,UAAU,EAAE,CAAC;gBAC3C,QAAQ,GAAG,SAAS,CAAC;YACvB,CAAC;iBAAM,CAAC;gBACN,QAAQ,GAAG,MAAM,CAAC;YACpB,CAAC;QACH,CAAC;IACH,CAAC;SAAM,CAAC;QACN,IAAI,GAAG,MAAM,CAAC;IAChB,CAAC;IAGD,IAAI,OAAO,CAAC,QAAQ,IAAI,OAAO,EAAE,CAAC;QAChC,IAAI,GAAG,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC;IACjC,CAAC;IAED,OAAO;QACL,IAAI;QACJ,QAAQ;QACR,MAAM;QACN,OAAO,EAAE,OAAO,IAAI,IAAI;KACzB,CAAC;AACJ,CAAC;AAQD,SAAgB,cAAc,CAAC,QAAgB;IAC7C,MAAM,EAAE,GAAG,EAAE,CAAC,QAAQ,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACtC,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;IAC/B,MAAM,SAAS,GAAG,EAAE,CAAC,QAAQ,CAAC,EAAE,EAAE,MAAM,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;IACnD,EAAE,CAAC,SAAS,CAAC,EAAE,CAAC,CAAC;IAEjB,IAAI,SAAS,GAAG,CAAC,EAAE,CAAC;QAClB,OAAO,IAAI,CAAC;IACd,CAAC;IAED,OAAO,SAAS,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;AAC/C,CAAC;AASD,SAAgB,iBAAiB,CAC/B,QAAyB,EACzB,UAAoC,EAAE;IAEtC,IAAI,CAAC,QAAQ,EAAE,CAAC;QACd,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,UAAkB,CAAC;IAEvB,IAAI,MAAM,CAAC,QAAQ,CAAC,QAAQ,CAAC,EAAE,CAAC;QAC9B,MAAM,OAAO,GAAG,SAAS,CAAC,QAAQ,CAAC,CAAC;QACpC,IAAI,OAAO,EAAE,CAAC;YACZ,UAAU,GAAG,QAAQ,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,QAAQ,CAAC,OAAO,CAAC,QAA0B,CAAC,CAAC;QAC9F,CAAC;aAAM,CAAC;YACN,UAAU,GAAG,QAAQ,CAAC,QAAQ,CAAE,OAAO,CAAC,QAA2B,IAAI,MAAM,CAAC,CAAC;QACjF,CAAC;IACH,CAAC;SAAM,IAAI,OAAO,QAAQ,KAAK,QAAQ,EAAE,CAAC;QACxC,UAAU,GAAG,kBAAkB,CAAC,QAAQ,CAAC,CAAC;IAC5C,CAAC;SAAM,CAAC;QACN,MAAM,IAAI,KAAK,CAAC,sCAAsC,CAAC,CAAC;IAC1D,CAAC;IAGD,IAAI,OAAO,CAAC,oBAAoB,KAAK,KAAK,EAAE,CAAC;QAC3C,UAAU,GAAG,UAAU,CAAC,OAAO,CAAC,UAAU,EAAE,IAAI,CAAC,CAAC;IACpD,CAAC;IAED,OAAO,UAAU,CAAC;AACpB,CAAC;AASM,KAAK,UAAU,sBAAsB,CAC1C,QAAgD,EAChD,UAAoC,EAAE;IAEtC,IAAI,OAAO,QAAQ,KAAK,QAAQ,IAAI,UAAU,IAAI,QAAQ,EAAE,CAAC;QAE3D,MAAM,MAAM,GAAG,MAAM,uBAAuB,CAAC,QAAQ,CAAC,QAAQ,EAAE;YAC9D,QAAQ,EAAE,OAAO,CAAC,QAA0B,IAAI,MAAM;SACvD,CAAC,CAAC;QACH,IAAI,UAAU,GAAG,OAAO,MAAM,CAAC,IAAI,KAAK,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,QAAQ,EAAE,CAAC;QAGxF,IAAI,OAAO,CAAC,oBAAoB,KAAK,KAAK,EAAE,CAAC;YAC3C,UAAU,GAAG,UAAU,CAAC,OAAO,CAAC,UAAU,EAAE,IAAI,CAAC,CAAC;QACpD,CAAC;QAED,OAAO,UAAU,CAAC;IACpB,CAAC;IAGD,OAAO,iBAAiB,CAAC,QAA2B,EAAE,OAAO,CAAC,CAAC;AACjE,CAAC;AAQM,KAAK,SAAS,CAAC,CAAC,0BAA0B,CAC/C,MAA6B;IAE7B,IAAI,WAAW,GAAG,KAAK,CAAC;IAExB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QACjC,IAAI,CAAC,WAAW,EAAE,CAAC;YACjB,MAAM,OAAO,GAAG,SAAS,CAAC,KAAe,CAAC,CAAC;YAC3C,IAAI,OAAO,EAAE,CAAC;gBAEZ,MAAO,KAAgB,CAAC,KAAK,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;gBACjD,WAAW,GAAG,IAAI,CAAC;gBACnB,SAAS;YACX,CAAC;iBAAM,CAAC;gBACN,WAAW,GAAG,IAAI,CAAC;YACrB,CAAC;QACH,CAAC;QAED,MAAM,KAAe,CAAC;IACxB,CAAC;AACH,CAAC;AAQM,KAAK,UAAU,cAAc,CAAC,QAAgB;IACnD,MAAM,EAAE,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IAChD,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;IAC/B,MAAM,EAAE,SAAS,EAAE,GAAG,MAAM,EAAE,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;IACrD,MAAM,EAAE,CAAC,KAAK,EAAE,CAAC;IAEjB,IAAI,SAAS,GAAG,CAAC,EAAE,CAAC;QAClB,OAAO,IAAI,CAAC;IACd,CAAC;IAED,OAAO,SAAS,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,SAAS,CAAC,CAAC,CAAC;AAC/C,CAAC;AAED,kBAAe;IACb,SAAS;IACT,QAAQ;IACR,kBAAkB;IAClB,oBAAoB;IACpB,uBAAuB;IACvB,cAAc;IACd,iBAAiB;IACjB,sBAAsB;IACtB,0BAA0B;IAC1B,cAAc;IACd,cAAc,EAAd,sBAAc;CACf,CAAC","sourcesContent":["/**\r\n * BOM (Byte Order Mark) Utilities for jtcsv\r\n * \r\n * Provides functions to detect and strip BOM characters from UTF-8, UTF-16 LE/BE,\r\n * and UTF-32 encoded strings/buffers.\r\n * \r\n * @module bom-utils\r\n */\r\n\r\nimport { Transform } from 'stream';\r\nimport * as fs from 'fs';\r\nimport * as fsPromises from 'fs/promises';\r\n\r\n/**\r\n * BOM signatures for different encodings\r\n */\r\nexport const BOM_SIGNATURES = {\r\n  'utf-8': Buffer.from([0xEF, 0xBB, 0xBF]),\r\n  'utf-16le': Buffer.from([0xFF, 0xFE]),\r\n  'utf-16be': Buffer.from([0xFE, 0xFF]),\r\n  'utf-32le': Buffer.from([0xFF, 0xFE, 0x00, 0x00]),\r\n  'utf-32be': Buffer.from([0x00, 0x00, 0xFE, 0xFF])\r\n} as const;\r\n\r\nexport type Encoding = keyof typeof BOM_SIGNATURES;\r\n\r\nexport interface BomDetectionResult {\r\n  encoding: Encoding;\r\n  bomLength: number;\r\n  hasBom: boolean;\r\n}\r\n\r\nexport interface ReadFileWithBomResult {\r\n  data: Buffer | string;\r\n  encoding: string;\r\n  hadBom: boolean;\r\n  bomInfo: BomDetectionResult | null;\r\n}\r\n\r\nexport interface NormalizeCsvInputOptions {\r\n  encoding?: string;\r\n  normalizeLineEndings?: boolean;\r\n}\r\n\r\n/**\r\n * Detects if a buffer or string starts with a BOM\r\n * \r\n * @param input - Input to check for BOM\r\n * @returns Detection result or null if no BOM found\r\n */\r\nexport function detectBom(input: Buffer | string | null | undefined): BomDetectionResult | null {\r\n  if (!input) {\r\n    return null;\r\n  }\r\n  \r\n  let buffer: Buffer;\r\n  if (typeof input === 'string') {\r\n    buffer = Buffer.from(input, 'utf8');\r\n  } else if (Buffer.isBuffer(input)) {\r\n    buffer = input;\r\n  } else {\r\n    return null;\r\n  }\r\n  \r\n  // Check each BOM signature\r\n  for (const [encoding, signature] of Object.entries(BOM_SIGNATURES)) {\r\n    if (buffer.length >= signature.length) {\r\n      if (buffer.slice(0, signature.length).equals(signature)) {\r\n        return {\r\n          encoding: encoding as Encoding,\r\n          bomLength: signature.length,\r\n          hasBom: true\r\n        };\r\n      }\r\n    }\r\n  }\r\n  \r\n  return null;\r\n}\r\n\r\n/**\r\n * Strips BOM from a buffer or string\r\n * \r\n * @param input - Input to strip BOM from\r\n * @returns Input without BOM\r\n */\r\nexport function stripBom(input: Buffer | string | null | undefined): Buffer | string {\r\n  if (!input) {\r\n    return input as any;\r\n  }\r\n  \r\n  const bomInfo = detectBom(input);\r\n  if (!bomInfo) {\r\n    return input;\r\n  }\r\n  \r\n  if (Buffer.isBuffer(input)) {\r\n    return input.slice(bomInfo.bomLength);\r\n  }\r\n  \r\n  if (typeof input === 'string') {\r\n    // Convert to buffer, strip BOM, then convert back to string\r\n    const buffer = Buffer.from(input, 'utf8');\r\n    const strippedBuffer = buffer.slice(bomInfo.bomLength);\r\n    \r\n    // Determine correct encoding for conversion\r\n    let encoding: BufferEncoding = 'utf8';\r\n    if (bomInfo.encoding === 'utf-16le') {\r\n      encoding = 'utf16le';\r\n    } else if (bomInfo.encoding === 'utf-16be') {\r\n      encoding = 'utf16le'; // Node.js uses utf16le for both LE and BE, conversion handled by Buffer\r\n    }\r\n    \r\n    return strippedBuffer.toString(encoding);\r\n  }\r\n  \r\n  return input;\r\n}\r\n\r\n/**\r\n * Strips BOM from a string (optimized for strings)\r\n * \r\n * @param str - String to strip BOM from\r\n * @returns String without BOM\r\n */\r\nexport function stripBomFromString(str: string): string {\r\n  if (typeof str !== 'string') {\r\n    return str as any;\r\n  }\r\n  \r\n  // Check for UTF-8 BOM (most common)\r\n  if (str.charCodeAt(0) === 0xFEFF) {\r\n    return str.slice(1);\r\n  }\r\n  \r\n  // Check for UTF-8 BOM bytes as characters\r\n  if (str.length >= 3 && \r\n      str.charCodeAt(0) === 0xEF && \r\n      str.charCodeAt(1) === 0xBB && \r\n      str.charCodeAt(2) === 0xBF) {\r\n    return str.slice(3);\r\n  }\r\n  \r\n  return str;\r\n}\r\n\r\n/**\r\n * Creates a transform stream that strips BOM from incoming data\r\n * \r\n * @returns Transform stream\r\n */\r\nexport function createBomStripStream(): Transform {\r\n  let bomStripped = false;\r\n  \r\n  return new Transform({\r\n    transform(chunk: Buffer, encoding: string, callback: (error?: Error | null, data?: Buffer) => void) {\r\n      if (!bomStripped) {\r\n        const bomInfo = detectBom(chunk);\r\n        if (bomInfo) {\r\n          // Strip BOM from first chunk\r\n          chunk = chunk.slice(bomInfo.bomLength);\r\n          bomStripped = true;\r\n        } else {\r\n          bomStripped = true; // No BOM found, but we've checked\r\n        }\r\n      }\r\n      \r\n      this.push(chunk);\r\n      callback();\r\n    }\r\n  });\r\n}\r\n\r\n/**\r\n * Reads a file and automatically handles BOM\r\n * \r\n * @param filePath - Path to file\r\n * @param options - Read options\r\n * @returns Promise with file data and BOM info\r\n */\r\nexport async function readFileWithBomHandling(\r\n  filePath: string, \r\n  options: { encoding?: BufferEncoding } = {}\r\n): Promise<ReadFileWithBomResult> {\r\n  const buffer = await fsPromises.readFile(filePath);\r\n  \r\n  const bomInfo = detectBom(buffer);\r\n  const hadBom = !!bomInfo;\r\n  \r\n  let data: Buffer | string;\r\n  let encoding = options.encoding || 'utf8';\r\n  \r\n  if (bomInfo) {\r\n    // Strip BOM\r\n    data = buffer.slice(bomInfo.bomLength);\r\n    \r\n    // Use detected encoding if not specified\r\n    if (!options.encoding) {\r\n      // Convert our encoding names to Node.js BufferEncoding\r\n      if (bomInfo.encoding === 'utf-8') {\r\n        encoding = 'utf8';\r\n      } else if (bomInfo.encoding === 'utf-16le') {\r\n        encoding = 'utf16le';\r\n      } else if (bomInfo.encoding === 'utf-16be') {\r\n        encoding = 'utf16le'; // Node.js uses utf16le for both\r\n      } else {\r\n        encoding = 'utf8'; // fallback\r\n      }\r\n    }\r\n  } else {\r\n    data = buffer;\r\n  }\r\n  \r\n  // Convert to string if encoding is specified\r\n  if (options.encoding || bomInfo) {\r\n    data = data.toString(encoding);\r\n  }\r\n  \r\n  return {\r\n    data,\r\n    encoding,\r\n    hadBom,\r\n    bomInfo: bomInfo || null\r\n  };\r\n}\r\n\r\n/**\r\n * Checks if a file has BOM (synchronous)\r\n * \r\n * @param filePath - Path to file\r\n * @returns BOM info or null\r\n */\r\nexport function fileHasBomSync(filePath: string): BomDetectionResult | null {\r\n  const fd = fs.openSync(filePath, 'r');\r\n  const buffer = Buffer.alloc(4);\r\n  const bytesRead = fs.readSync(fd, buffer, 0, 4, 0);\r\n  fs.closeSync(fd);\r\n  \r\n  if (bytesRead < 2) {\r\n    return null;\r\n  }\r\n  \r\n  return detectBom(buffer.slice(0, bytesRead));\r\n}\r\n\r\n/**\r\n * Normalizes CSV input by stripping BOM and ensuring proper encoding\r\n * \r\n * @param csvInput - CSV input\r\n * @param options - Processing options\r\n * @returns Normalized CSV string\r\n */\r\nexport function normalizeCsvInput(\r\n  csvInput: string | Buffer, \r\n  options: NormalizeCsvInputOptions = {}\r\n): string {\r\n  if (!csvInput) {\r\n    return '';\r\n  }\r\n  \r\n  let normalized: string;\r\n  \r\n  if (Buffer.isBuffer(csvInput)) {\r\n    const bomInfo = detectBom(csvInput);\r\n    if (bomInfo) {\r\n      normalized = csvInput.slice(bomInfo.bomLength).toString(bomInfo.encoding as BufferEncoding);\r\n    } else {\r\n      normalized = csvInput.toString((options.encoding as BufferEncoding) || 'utf8');\r\n    }\r\n  } else if (typeof csvInput === 'string') {\r\n    normalized = stripBomFromString(csvInput);\r\n  } else {\r\n    throw new Error('CSV input must be a string or Buffer');\r\n  }\r\n  \r\n  // Ensure proper line endings\r\n  if (options.normalizeLineEndings !== false) {\r\n    normalized = normalized.replace(/\\r\\n|\\r/g, '\\n');\r\n  }\r\n  \r\n  return normalized;\r\n}\r\n\r\n/**\r\n * Async version of normalizeCsvInput that can handle large files\r\n * \r\n * @param csvInput - CSV input as string, Buffer, or file path\r\n * @param options - Processing options\r\n * @returns Promise with normalized CSV string\r\n */\r\nexport async function normalizeCsvInputAsync(\r\n  csvInput: string | Buffer | { filePath: string },\r\n  options: NormalizeCsvInputOptions = {}\r\n): Promise<string> {\r\n  if (typeof csvInput === 'object' && 'filePath' in csvInput) {\r\n    // Read file asynchronously\r\n    const result = await readFileWithBomHandling(csvInput.filePath, {\r\n      encoding: options.encoding as BufferEncoding || 'utf8'\r\n    });\r\n    let normalized = typeof result.data === 'string' ? result.data : result.data.toString();\r\n    \r\n    // Ensure proper line endings\r\n    if (options.normalizeLineEndings !== false) {\r\n      normalized = normalized.replace(/\\r\\n|\\r/g, '\\n');\r\n    }\r\n    \r\n    return normalized;\r\n  }\r\n  \r\n  // Handle string or Buffer input\r\n  return normalizeCsvInput(csvInput as string | Buffer, options);\r\n}\r\n\r\n/**\r\n * Creates an async iterator that strips BOM from a stream\r\n * \r\n * @param stream - Readable stream\r\n * @returns Async iterator yielding chunks without BOM\r\n */\r\nexport async function* createBomStrippingIterator(\r\n  stream: NodeJS.ReadableStream\r\n): AsyncIterableIterator<Buffer> {\r\n  let bomStripped = false;\r\n  \r\n  for await (const chunk of stream) {\r\n    if (!bomStripped) {\r\n      const bomInfo = detectBom(chunk as Buffer);\r\n      if (bomInfo) {\r\n        // Strip BOM from first chunk\r\n        yield (chunk as Buffer).slice(bomInfo.bomLength);\r\n        bomStripped = true;\r\n        continue;\r\n      } else {\r\n        bomStripped = true;\r\n      }\r\n    }\r\n    \r\n    yield chunk as Buffer;\r\n  }\r\n}\r\n\r\n/**\r\n * Detects BOM asynchronously for large files\r\n * \r\n * @param filePath - Path to file\r\n * @returns Promise with BOM info or null\r\n */\r\nexport async function detectBomAsync(filePath: string): Promise<BomDetectionResult | null> {\r\n  const fd = await fsPromises.open(filePath, 'r');\r\n  const buffer = Buffer.alloc(4);\r\n  const { bytesRead } = await fd.read(buffer, 0, 4, 0);\r\n  await fd.close();\r\n  \r\n  if (bytesRead < 2) {\r\n    return null;\r\n  }\r\n  \r\n  return detectBom(buffer.slice(0, bytesRead));\r\n}\r\n\r\nexport default {\r\n  detectBom,\r\n  stripBom,\r\n  stripBomFromString,\r\n  createBomStripStream,\r\n  readFileWithBomHandling,\r\n  fileHasBomSync,\r\n  normalizeCsvInput,\r\n  normalizeCsvInputAsync,\r\n  createBomStrippingIterator,\r\n  detectBomAsync,\r\n  BOM_SIGNATURES\r\n};"]}

package/dist/src/utils/encoding-support.js

@@ -0,0 +1,77 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.detectEncoding = detectEncoding;
+exports.convertToUtf8 = convertToUtf8;
+exports.autoDetectAndConvert = autoDetectAndConvert;
+exports.csvToJsonWithEncoding = csvToJsonWithEncoding;
+exports.csvToJsonWithEncodingAsync = csvToJsonWithEncodingAsync;
+const errors_1 = require("../errors");
+function detectEncoding(buffer, options = {}) {
+    const { fallback = 'utf8' } = options;
+    if (!Buffer.isBuffer(buffer)) {
+        throw new errors_1.ValidationError('Input must be a Buffer');
+    }
+    if (buffer.length >= 3 && buffer[0] === 0xEF && buffer[1] === 0xBB && buffer[2] === 0xBF) {
+        return 'utf8';
+    }
+    if (buffer.length >= 2 && buffer[0] === 0xFE && buffer[1] === 0xFF) {
+        return 'utf16be';
+    }
+    if (buffer.length >= 2 && buffer[0] === 0xFF && buffer[1] === 0xFE) {
+        return 'utf16le';
+    }
+    return fallback;
+}
+function convertToUtf8(buffer, encoding = 'utf8') {
+    if (!Buffer.isBuffer(buffer)) {
+        throw new errors_1.ValidationError('Input must be a Buffer');
+    }
+    let offset = 0;
+    if (encoding === 'utf8' && buffer.length >= 3 && buffer[0] === 0xEF && buffer[1] === 0xBB && buffer[2] === 0xBF) {
+        offset = 3;
+    }
+    else if (encoding === 'utf16be' && buffer.length >= 2 && buffer[0] === 0xFE && buffer[1] === 0xFF) {
+        offset = 2;
+    }
+    else if (encoding === 'utf16le' && buffer.length >= 2 && buffer[0] === 0xFF && buffer[1] === 0xFE) {
+        offset = 2;
+    }
+    const slice = buffer.slice(offset);
+    return slice.toString(encoding);
+}
+function autoDetectAndConvert(buffer, options = {}) {
+    const encoding = detectEncoding(buffer, options);
+    const text = convertToUtf8(buffer, encoding);
+    return { encoding, text };
+}
+async function csvToJsonWithEncoding(input, parseOptions = {}) {
+    const { encoding = 'auto', fallbackEncoding = 'utf8', ...restOptions } = parseOptions;
+    let text;
+    if (Buffer.isBuffer(input)) {
+        if (encoding === 'auto') {
+            const detected = autoDetectAndConvert(input, { fallback: fallbackEncoding });
+            text = detected.text;
+        }
+        else {
+            text = convertToUtf8(input, encoding);
+        }
+    }
+    else if (typeof input === 'string') {
+        text = input;
+    }
+    else {
+        throw new errors_1.ValidationError('Input must be a Buffer or string');
+    }
+    throw new Error('csvToJson function not available. This function requires csvToJson to be provided.');
+}
+async function csvToJsonWithEncodingAsync(input, parseOptions = {}) {
+    return csvToJsonWithEncoding(input, parseOptions);
+}
+exports.default = {
+    detectEncoding,
+    convertToUtf8,
+    autoDetectAndConvert,
+    csvToJsonWithEncoding,
+    csvToJsonWithEncodingAsync
+};
+//# sourceMappingURL=encoding-support.js.map

package/dist/src/utils/encoding-support.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"encoding-support.js","sourceRoot":"","sources":["../../../src/utils/encoding-support.ts"],"names":[],"mappings":";;AAsCA,wCAoBC;AAUD,sCAkBC;AAUD,oDAOC;AAWD,sDAsBC;AAKD,gEAKC;AApID,sCAA4C;AAwB5C,SAAgB,cAAc,CAAC,MAAc,EAAE,UAAiC,EAAE;IAChF,MAAM,EAAE,QAAQ,GAAG,MAAM,EAAE,GAAG,OAAO,CAAC;IAEtC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;QAC7B,MAAM,IAAI,wBAAe,CAAC,wBAAwB,CAAC,CAAC;IACtD,CAAC;IAGD,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACzF,OAAO,MAAM,CAAC;IAChB,CAAC;IACD,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACnE,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACnE,OAAO,SAAS,CAAC;IACnB,CAAC;IAGD,OAAO,QAAQ,CAAC;AAClB,CAAC;AAUD,SAAgB,aAAa,CAAC,MAAc,EAAE,WAAmB,MAAM;IACrE,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;QAC7B,MAAM,IAAI,wBAAe,CAAC,wBAAwB,CAAC,CAAC;IACtD,CAAC;IAED,IAAI,MAAM,GAAG,CAAC,CAAC;IAGf,IAAI,QAAQ,KAAK,MAAM,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QAChH,MAAM,GAAG,CAAC,CAAC;IACb,CAAC;SAAM,IAAI,QAAQ,KAAK,SAAS,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACpG,MAAM,GAAG,CAAC,CAAC;IACb,CAAC;SAAM,IAAI,QAAQ,KAAK,SAAS,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACpG,MAAM,GAAG,CAAC,CAAC;IACb,CAAC;IAED,MAAM,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;IACnC,OAAO,KAAK,CAAC,QAAQ,CAAC,QAA0B,CAAC,CAAC;AACpD,CAAC;AAUD,SAAgB,oBAAoB,CAClC,MAAc,EACd,UAAuC,EAAE;IAEzC,MAAM,QAAQ,GAAG,cAAc,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IACjD,MAAM,IAAI,GAAG,aAAa,CAAC,MAAM,EAAE,QAAQ,CAAC,CAAC;IAC7C,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC;AAC5B,CAAC;AAWM,KAAK,UAAU,qBAAqB,CACzC,KAAsB,EACtB,eAA6C,EAAE;IAE/C,MAAM,EAAE,QAAQ,GAAG,MAAM,EAAE,gBAAgB,GAAG,MAAM,EAAE,GAAG,WAAW,EAAE,GAAG,YAAY,CAAC;IAEtF,IAAI,IAAY,CAAC;IACjB,IAAI,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;QAC3B,IAAI,QAAQ,KAAK,MAAM,EAAE,CAAC;YACxB,MAAM,QAAQ,GAAG,oBAAoB,CAAC,KAAK,EAAE,EAAE,QAAQ,EAAE,gBAAgB,EAAE,CAAC,CAAC;YAC7E,IAAI,GAAG,QAAQ,CAAC,IAAI,CAAC;QACvB,CAAC;aAAM,CAAC;YACN,IAAI,GAAG,aAAa,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC;QACxC,CAAC;IACH,CAAC;SAAM,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;QACrC,IAAI,GAAG,KAAK,CAAC;IACf,CAAC;SAAM,CAAC;QACN,MAAM,IAAI,wBAAe,CAAC,kCAAkC,CAAC,CAAC;IAChE,CAAC;IAGD,MAAM,IAAI,KAAK,CAAC,oFAAoF,CAAC,CAAC;AACxG,CAAC;AAKM,KAAK,UAAU,0BAA0B,CAC9C,KAAsB,EACtB,eAA6C,EAAE;IAE/C,OAAO,qBAAqB,CAAC,KAAK,EAAE,YAAY,CAAC,CAAC;AACpD,CAAC;AAED,kBAAe;IACb,cAAc;IACd,aAAa;IACb,oBAAoB;IACpB,qBAAqB;IACrB,0BAA0B;CAC3B,CAAC","sourcesContent":["/**\r\n * Encoding detection and conversion utilities.\r\n * \r\n * Provides basic auto‑detection of UTF‑8, UTF‑16LE, UTF‑16BE with BOM,\r\n * and fallback to a default encoding.\r\n * \r\n * @example\r\n * import { detectEncoding, convertToUtf8 } from './encoding-support';\r\n * \r\n * const buffer = fs.readFileSync('data.csv');\r\n * const encoding = detectEncoding(buffer, { fallback: 'utf8' });\r\n * const utf8Text = convertToUtf8(buffer, encoding);\r\n */\r\n\r\nimport { ValidationError } from '../errors';\r\n\r\nexport interface DetectEncodingOptions {\r\n  fallback?: 'utf8' | 'utf16le' | 'utf16be' | string;\r\n}\r\n\r\nexport interface AutoDetectAndConvertOptions {\r\n  fallback?: string;\r\n}\r\n\r\nexport interface CsvToJsonWithEncodingOptions {\r\n  encoding?: 'auto' | 'utf8' | 'utf16le' | 'utf16be' | string;\r\n  fallbackEncoding?: string;\r\n  [key: string]: any;\r\n}\r\n\r\n/**\r\n * Detects encoding from buffer based on BOM.\r\n * \r\n * @param buffer - Input buffer\r\n * @param options - Detection options\r\n * @param options.fallback - Fallback encoding if detection fails (default: 'utf8')\r\n * @returns Detected encoding: 'utf8', 'utf16le', 'utf16be', or fallback\r\n */\r\nexport function detectEncoding(buffer: Buffer, options: DetectEncodingOptions = {}): string {\r\n  const { fallback = 'utf8' } = options;\r\n  \r\n  if (!Buffer.isBuffer(buffer)) {\r\n    throw new ValidationError('Input must be a Buffer');\r\n  }\r\n  \r\n  // Check BOM\r\n  if (buffer.length >= 3 && buffer[0] === 0xEF && buffer[1] === 0xBB && buffer[2] === 0xBF) {\r\n    return 'utf8';\r\n  }\r\n  if (buffer.length >= 2 && buffer[0] === 0xFE && buffer[1] === 0xFF) {\r\n    return 'utf16be';\r\n  }\r\n  if (buffer.length >= 2 && buffer[0] === 0xFF && buffer[1] === 0xFE) {\r\n    return 'utf16le';\r\n  }\r\n  \r\n  // No BOM detected, use fallback\r\n  return fallback;\r\n}\r\n\r\n/**\r\n * Converts buffer to UTF‑8 string using detected encoding.\r\n * Strips BOM if present.\r\n * \r\n * @param buffer - Input buffer\r\n * @param encoding - Source encoding ('utf8', 'utf16le', 'utf16be')\r\n * @returns UTF‑8 string without BOM\r\n */\r\nexport function convertToUtf8(buffer: Buffer, encoding: string = 'utf8'): string {\r\n  if (!Buffer.isBuffer(buffer)) {\r\n    throw new ValidationError('Input must be a Buffer');\r\n  }\r\n  \r\n  let offset = 0;\r\n  \r\n  // Skip BOM\r\n  if (encoding === 'utf8' && buffer.length >= 3 && buffer[0] === 0xEF && buffer[1] === 0xBB && buffer[2] === 0xBF) {\r\n    offset = 3;\r\n  } else if (encoding === 'utf16be' && buffer.length >= 2 && buffer[0] === 0xFE && buffer[1] === 0xFF) {\r\n    offset = 2;\r\n  } else if (encoding === 'utf16le' && buffer.length >= 2 && buffer[0] === 0xFF && buffer[1] === 0xFE) {\r\n    offset = 2;\r\n  }\r\n  \r\n  const slice = buffer.slice(offset);\r\n  return slice.toString(encoding as BufferEncoding);\r\n}\r\n\r\n/**\r\n * Auto‑detects encoding and converts buffer to UTF‑8 string.\r\n * \r\n * @param buffer - Input buffer\r\n * @param options - Options\r\n * @param options.fallback - Fallback encoding (default: 'utf8')\r\n * @returns Detected encoding and converted text\r\n */\r\nexport function autoDetectAndConvert(\r\n  buffer: Buffer, \r\n  options: AutoDetectAndConvertOptions = {}\r\n): { encoding: string; text: string } {\r\n  const encoding = detectEncoding(buffer, options);\r\n  const text = convertToUtf8(buffer, encoding);\r\n  return { encoding, text };\r\n}\r\n\r\n/**\r\n * Creates a wrapper around csvToJson that accepts Buffer or string with encoding detection.\r\n * \r\n * @param input - CSV as Buffer or string\r\n * @param parseOptions - Options for csvToJson\r\n * @param parseOptions.encoding - Explicit encoding (default: 'auto')\r\n * @param parseOptions.fallbackEncoding - Fallback if auto detection fails (default: 'utf8')\r\n * @returns Promise with parsed JSON data\r\n */\r\nexport async function csvToJsonWithEncoding(\r\n  input: Buffer | string,\r\n  parseOptions: CsvToJsonWithEncodingOptions = {}\r\n): Promise<any[]> {\r\n  const { encoding = 'auto', fallbackEncoding = 'utf8', ...restOptions } = parseOptions;\r\n  \r\n  let text: string;\r\n  if (Buffer.isBuffer(input)) {\r\n    if (encoding === 'auto') {\r\n      const detected = autoDetectAndConvert(input, { fallback: fallbackEncoding });\r\n      text = detected.text;\r\n    } else {\r\n      text = convertToUtf8(input, encoding);\r\n    }\r\n  } else if (typeof input === 'string') {\r\n    text = input;\r\n  } else {\r\n    throw new ValidationError('Input must be a Buffer or string');\r\n  }\r\n  \r\n  // csvToJson will be provided by the caller or imported elsewhere\r\n  throw new Error('csvToJson function not available. This function requires csvToJson to be provided.');\r\n}\r\n\r\n/**\r\n * Async version of csvToJsonWithEncoding\r\n */\r\nexport async function csvToJsonWithEncodingAsync(\r\n  input: Buffer | string,\r\n  parseOptions: CsvToJsonWithEncodingOptions = {}\r\n): Promise<any[]> {\r\n  return csvToJsonWithEncoding(input, parseOptions);\r\n}\r\n\r\nexport default {\r\n  detectEncoding,\r\n  convertToUtf8,\r\n  autoDetectAndConvert,\r\n  csvToJsonWithEncoding,\r\n  csvToJsonWithEncodingAsync\r\n};"]}