pdf-lite 1.0.7 → 1.0.8

package/dist/core/objects/pdf-string.js

@@ -1,5 +1,8 @@
 import { bytesToString } from '../../utils/bytesToString.js';
 import { stringToBytes } from '../../utils/stringToBytes.js';
+import { needsUnicodeEncoding } from '../../utils/needsUnicodeEncoding.js';
+import { encodeAsUTF16BE } from '../../utils/encodeAsUTF16BE.js';
+import { decodeFromUTF16BE } from '../../utils/decodeFromUTF16BE.js';
 import { PdfStringToken } from '../tokens/string-token.js';
 import { PdfObject } from './pdf-object.js';
 export class PdfString extends PdfObject {
@@ -9,7 +12,20 @@ export class PdfString extends PdfObject {
     _raw;
     constructor(raw) {
         super();
-        this._raw = typeof raw === 'string' ? stringToBytes(raw) : raw;
+        if (typeof raw === 'string') {
+            // Check if the string contains non-ASCII characters
+            if (needsUnicodeEncoding(raw)) {
+                // Use UTF-16BE encoding with BOM for Unicode strings
+                this._raw = encodeAsUTF16BE(raw);
+            }
+            else {
+                // Use PDFDocEncoding (ASCII-compatible) for simple strings
+                this._raw = stringToBytes(raw);
+            }
+        }
+        else {
+            this._raw = raw;
+        }
     }
     get raw() {
         return this._raw;
@@ -19,6 +35,13 @@ export class PdfString extends PdfObject {
         this._raw = raw;
     }
     get value() {
+        // Check for UTF-16BE BOM (0xFE 0xFF)
+        if (this.raw.length >= 2 &&
+            this.raw[0] === 0xfe &&
+            this.raw[1] === 0xff) {
+            return decodeFromUTF16BE(this.raw);
+        }
+        // Default: use UTF-8 decoding
         return bytesToString(this.raw);
     }
     tokenize() {

package/dist/utils/decodeFromUTF16BE.d.ts

@@ -0,0 +1,18 @@
+import { ByteArray } from '../types.js';
+/**
+ * Decodes a UTF-16BE byte array to a string
+ *
+ * Assumes the byte array starts with UTF-16BE BOM (0xFE 0xFF) which is skipped.
+ * Each character is represented by 2 bytes (high byte, low byte).
+ *
+ * @param bytes - The byte array to decode (should start with BOM)
+ * @returns The decoded string
+ *
+ * @example
+ * ```typescript
+ * // Byte array with BOM: 0xFE, 0xFF, 0x00, 0x50, 0x00, 0x52 -> "PR"
+ * decodeFromUTF16BE(new Uint8Array([0xFE, 0xFF, 0x00, 0x50, 0x00, 0x52]))
+ * // Returns "PR"
+ * ```
+ */
+export declare function decodeFromUTF16BE(bytes: ByteArray): string;

package/dist/utils/decodeFromUTF16BE.js

@@ -0,0 +1,27 @@
+/**
+ * Decodes a UTF-16BE byte array to a string
+ *
+ * Assumes the byte array starts with UTF-16BE BOM (0xFE 0xFF) which is skipped.
+ * Each character is represented by 2 bytes (high byte, low byte).
+ *
+ * @param bytes - The byte array to decode (should start with BOM)
+ * @returns The decoded string
+ *
+ * @example
+ * ```typescript
+ * // Byte array with BOM: 0xFE, 0xFF, 0x00, 0x50, 0x00, 0x52 -> "PR"
+ * decodeFromUTF16BE(new Uint8Array([0xFE, 0xFF, 0x00, 0x50, 0x00, 0x52]))
+ * // Returns "PR"
+ * ```
+ */
+export function decodeFromUTF16BE(bytes) {
+    // Skip the BOM (first 2 bytes) and decode the rest
+    const chars = [];
+    for (let i = 2; i < bytes.length; i += 2) {
+        const high = bytes[i];
+        const low = bytes[i + 1] || 0;
+        const charCode = (high << 8) | low;
+        chars.push(String.fromCharCode(charCode));
+    }
+    return chars.join('');
+}

package/dist/utils/encodeAsUTF16BE.d.ts

@@ -0,0 +1,17 @@
+import { ByteArray } from '../types.js';
+/**
+ * Encodes a string as UTF-16BE with BOM for PDF
+ *
+ * PDF strings can use UTF-16BE encoding to represent Unicode characters.
+ * The encoding must start with the UTF-16BE BOM (0xFE 0xFF) to be recognized.
+ *
+ * @param str - The string to encode
+ * @returns Byte array with UTF-16BE BOM followed by the encoded string
+ *
+ * @example
+ * ```typescript
+ * encodeAsUTF16BE('PROSZĘ')
+ * // Returns Uint8Array([0xFE, 0xFF, 0x00, 0x50, 0x00, 0x52, ...])
+ * ```
+ */
+export declare function encodeAsUTF16BE(str: string): ByteArray;

package/dist/utils/encodeAsUTF16BE.js

@@ -0,0 +1,26 @@
+/**
+ * Encodes a string as UTF-16BE with BOM for PDF
+ *
+ * PDF strings can use UTF-16BE encoding to represent Unicode characters.
+ * The encoding must start with the UTF-16BE BOM (0xFE 0xFF) to be recognized.
+ *
+ * @param str - The string to encode
+ * @returns Byte array with UTF-16BE BOM followed by the encoded string
+ *
+ * @example
+ * ```typescript
+ * encodeAsUTF16BE('PROSZĘ')
+ * // Returns Uint8Array([0xFE, 0xFF, 0x00, 0x50, 0x00, 0x52, ...])
+ * ```
+ */
+export function encodeAsUTF16BE(str) {
+    // UTF-16BE BOM (0xFE 0xFF)
+    const result = [0xfe, 0xff];
+    for (let i = 0; i < str.length; i++) {
+        const code = str.charCodeAt(i);
+        // UTF-16BE: high byte first, then low byte
+        result.push((code >> 8) & 0xff);
+        result.push(code & 0xff);
+    }
+    return new Uint8Array(result);
+}

package/dist/utils/index.d.ts

@@ -5,10 +5,13 @@ export * from './bytesToHex.js';
 export * from './bytesToHexBytes.js';
 export * from './bytesToString.js';
 export * from './concatUint8Arrays.js';
+export * from './decodeFromUTF16BE.js';
+export * from './encodeAsUTF16BE.js';
 export * from './escapeString.js';
 export * from './hexBytesToBytes.js';
 export * from './hexBytesToString.js';
 export * from './hexToBytes.js';
+export * from './needsUnicodeEncoding.js';
 export * from './padBytes.js';
 export * from './predictors.js';
 export * from './replaceInBuffer.js';

package/dist/utils/index.js

@@ -5,10 +5,13 @@ export * from './bytesToHex.js';
 export * from './bytesToHexBytes.js';
 export * from './bytesToString.js';
 export * from './concatUint8Arrays.js';
+export * from './decodeFromUTF16BE.js';
+export * from './encodeAsUTF16BE.js';
 export * from './escapeString.js';
 export * from './hexBytesToBytes.js';
 export * from './hexBytesToString.js';
 export * from './hexToBytes.js';
+export * from './needsUnicodeEncoding.js';
 export * from './padBytes.js';
 export * from './predictors.js';
 export * from './replaceInBuffer.js';

package/dist/utils/needsUnicodeEncoding.d.ts

@@ -0,0 +1,13 @@
+/**
+ * Checks if a string contains non-ASCII characters that require UTF-16BE encoding
+ *
+ * @param str - The string to check
+ * @returns True if the string contains characters above ASCII range (code > 127)
+ *
+ * @example
+ * ```typescript
+ * needsUnicodeEncoding('Hello') // Returns false
+ * needsUnicodeEncoding('PROSZĘ') // Returns true
+ * ```
+ */
+export declare function needsUnicodeEncoding(str: string): boolean;

package/dist/utils/needsUnicodeEncoding.js

@@ -0,0 +1,20 @@
+/**
+ * Checks if a string contains non-ASCII characters that require UTF-16BE encoding
+ *
+ * @param str - The string to check
+ * @returns True if the string contains characters above ASCII range (code > 127)
+ *
+ * @example
+ * ```typescript
+ * needsUnicodeEncoding('Hello') // Returns false
+ * needsUnicodeEncoding('PROSZĘ') // Returns true
+ * ```
+ */
+export function needsUnicodeEncoding(str) {
+    for (let i = 0; i < str.length; i++) {
+        if (str.charCodeAt(i) > 127) {
+            return true;
+        }
+    }
+    return false;
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pdf-lite",
-  "version": "1.0.7",
+  "version": "1.0.8",
   "main": "dist/index.js",
   "type": "module",
   "exports": {