pdf-lite 1.0.4 → 1.0.6

package/dist/utils/algos.js

@@ -1,6 +1,6 @@
 import { deflate, Inflate } from 'pako';
 import { bytesToHex } from './bytesToHex.js';
-import { AlgorithmIdentifier } from 'pki-lite/algorithms/AlgorithmIdentifier';
+import { AlgorithmIdentifier } from 'pki-lite/algorithms/AlgorithmIdentifier.js';
 import 'pki-lite-crypto-extended';
 /**
  * Computes the SHA-1 hash of the input data.

package/dist/utils/bytesToHex.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a byte array to a hexadecimal string.
  *

package/dist/utils/bytesToHex.js

@@ -1,5 +1,5 @@
-import { bytesToHexBytes } from './bytesToHexBytes';
-import { bytesToString } from './bytesToString';
+import { bytesToHexBytes } from './bytesToHexBytes.js';
+import { bytesToString } from './bytesToString.js';
 /**
  * Converts a byte array to a hexadecimal string.
  *

package/dist/utils/bytesToHexBytes.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a byte array to a byte array containing hexadecimal character codes.
  * Each byte becomes two bytes representing its hex digits.

package/dist/utils/bytesToString.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a byte array to a string using UTF-8 decoding.
  *

package/dist/utils/concatUint8Arrays.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Concatenates multiple Uint8Array instances into a single ByteArray.
  *

package/dist/utils/escapeString.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Escapes special characters in a PDF string according to PDF specification.
  * Escapes parentheses, backslashes, line feeds, and carriage returns.

package/dist/utils/escapeString.js

@@ -1,4 +1,4 @@
-import { stringToBytes } from './stringToBytes';
+import { stringToBytes } from './stringToBytes.js';
 /**
  * Escapes special characters in a PDF string according to PDF specification.
  * Escapes parentheses, backslashes, line feeds, and carriage returns.

package/dist/utils/hexBytesToBytes.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a byte array containing hexadecimal ASCII characters to raw bytes.
  * Each pair of hex character bytes is converted to a single byte value.

package/dist/utils/hexBytesToString.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a byte array to a lowercase hexadecimal string.
  *

package/dist/utils/hexToBytes.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a hexadecimal string to a byte array.
  *

package/dist/utils/hexToBytes.js

@@ -1,5 +1,5 @@
-import { hexBytesToBytes } from './hexBytesToBytes';
-import { stringToBytes } from './stringToBytes';
+import { hexBytesToBytes } from './hexBytesToBytes.js';
+import { stringToBytes } from './stringToBytes.js';
 /**
  * Converts a hexadecimal string to a byte array.
  *

package/dist/utils/padBytes.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Pads a byte array to a specified length with trailing zeros.
  *

package/dist/utils/replaceInBuffer.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Replaces occurrences of a search buffer with a replacement buffer within a target buffer.
  *

package/dist/utils/stringToBytes.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a string or byte array to a byte array using UTF-8 encoding.
  * If the input is already a byte array, it is returned as-is.

package/dist/utils/stringToHexBytes.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Converts a hexadecimal string (optionally with angle brackets) to a byte array.
  * Strips any surrounding angle brackets before conversion.

package/dist/utils/unescapeString.d.ts

@@ -1,4 +1,4 @@
-import { ByteArray } from '../types';
+import { ByteArray } from '../types.js';
 /**
  * Unescapes a PDF literal string by processing escape sequences.
  * Handles escape sequences for special characters including newlines, tabs,

package/dist/xfa/index.d.ts

@@ -0,0 +1 @@
+export { PdfXfaManager } from './xfa-manager.js';

package/dist/xfa/index.js

@@ -0,0 +1 @@
+export { PdfXfaManager } from './xfa-manager.js';

package/dist/xfa/xfa-manager.d.ts

@@ -0,0 +1,44 @@
+import { PdfDocument } from '../pdf/pdf-document.js';
+/**
+ * Manages XFA (XML Forms Architecture) forms in PDF documents.
+ * Provides methods to read and write XFA form data as XML.
+ */
+export declare class PdfXfaManager {
+    private document;
+    private _datasetsStream?;
+    constructor(document: PdfDocument);
+    /**
+     * Checks if the document contains XFA forms.
+     * @returns True if the document has XFA forms, false otherwise
+     */
+    hasXfaForms(): Promise<boolean>;
+    /**
+     * Reads the XFA form data as XML string.
+     * @returns The XFA datasets XML content, or null if no XFA form exists
+     */
+    readXml(): Promise<string | null>;
+    /**
+     * Writes XML content to the XFA datasets stream.
+     * @param xml The XML content to write
+     * @throws Error if the document doesn't have XFA forms
+     */
+    writeXml(xml: string): Promise<void>;
+    /**
+     * Gets the AcroForm dictionary from the document catalog.
+     * @returns The AcroForm dictionary or null if not found
+     */
+    private getAcroForm;
+    /**
+     * Gets the XFA datasets stream.
+     * Caches the stream for subsequent calls to preserve modifications.
+     * @returns The datasets stream or null if not found
+     */
+    private getDatasetsStream;
+    /**
+     * Finds the XFA dataset object reference from the XFA array.
+     * XFA array structure: [(name1) ref1 (name2) ref2 ...]
+     * @param xfaArray The XFA array from the AcroForm
+     * @returns The object reference to the datasets stream, or null if not found
+     */
+    private findXfaDatasetReference;
+}

package/dist/xfa/xfa-manager.js

@@ -0,0 +1,138 @@
+import { PdfStream } from '../core/objects/pdf-stream.js';
+import { PdfDictionary } from '../core/objects/pdf-dictionary.js';
+import { PdfArray } from '../core/objects/pdf-array.js';
+import { PdfString } from '../core/objects/pdf-string.js';
+import { PdfObjectReference } from '../core/objects/pdf-object-reference.js';
+import { PdfIndirectObject } from '../core/index.js';
+/**
+ * Manages XFA (XML Forms Architecture) forms in PDF documents.
+ * Provides methods to read and write XFA form data as XML.
+ */
+export class PdfXfaManager {
+    document;
+    _datasetsStream;
+    constructor(document) {
+        this.document = document;
+    }
+    /**
+     * Checks if the document contains XFA forms.
+     * @returns True if the document has XFA forms, false otherwise
+     */
+    async hasXfaForms() {
+        try {
+            const stream = await this.getDatasetsStream();
+            return stream !== null;
+        }
+        catch {
+            return false;
+        }
+    }
+    /**
+     * Reads the XFA form data as XML string.
+     * @returns The XFA datasets XML content, or null if no XFA form exists
+     */
+    async readXml() {
+        const stream = await this.getDatasetsStream();
+        if (!stream)
+            return null;
+        // Get decompressed data without modifying the original stream
+        const decompressed = stream.content.decode();
+        // Return the raw XML content as string
+        const decoder = new TextDecoder();
+        return decoder.decode(decompressed);
+    }
+    /**
+     * Writes XML content to the XFA datasets stream.
+     * @param xml The XML content to write
+     * @throws Error if the document doesn't have XFA forms
+     */
+    async writeXml(xml) {
+        const stream = await this.getDatasetsStream();
+        if (!stream) {
+            throw new Error('Document does not contain XFA forms');
+        }
+        // Update the cached stream directly with the new XML content
+        const datasetsIndirect = new PdfIndirectObject({
+            ...stream,
+            content: PdfStream.fromString(xml),
+        });
+        const isIncremental = this.document.isIncremental();
+        this.document.setIncremental(true);
+        await this.document.commit(datasetsIndirect);
+        this.document.setIncremental(isIncremental);
+        // Reset cached stream to force re-fetch if needed
+        this._datasetsStream = undefined;
+    }
+    /**
+     * Gets the AcroForm dictionary from the document catalog.
+     * @returns The AcroForm dictionary or null if not found
+     */
+    async getAcroForm() {
+        const catalog = this.document.rootDictionary;
+        if (!catalog)
+            return null;
+        const acroFormRef = catalog.get('AcroForm');
+        if (!acroFormRef)
+            return null;
+        if (acroFormRef instanceof PdfObjectReference) {
+            const acroFormObject = await this.document.readObject({
+                objectNumber: acroFormRef.objectNumber,
+                generationNumber: acroFormRef.generationNumber,
+            });
+            if (!acroFormObject)
+                return null;
+            return acroFormObject.content.as(PdfDictionary);
+        }
+        else if (acroFormRef instanceof PdfDictionary) {
+            return acroFormRef;
+        }
+        return null;
+    }
+    /**
+     * Gets the XFA datasets stream.
+     * Caches the stream for subsequent calls to preserve modifications.
+     * @returns The datasets stream or null if not found
+     */
+    async getDatasetsStream() {
+        if (this._datasetsStream) {
+            return this._datasetsStream;
+        }
+        const acroForm = await this.getAcroForm();
+        if (!acroForm)
+            return null;
+        const xfaArray = acroForm.get('XFA');
+        if (!(xfaArray instanceof PdfArray))
+            return null;
+        const datasetsRef = this.findXfaDatasetReference(xfaArray);
+        if (!datasetsRef)
+            return null;
+        const datasetObject = await this.document.readObject({
+            objectNumber: datasetsRef.objectNumber,
+            generationNumber: datasetsRef.generationNumber,
+            allowUnindexed: true,
+        });
+        if (!datasetObject)
+            return null;
+        return datasetObject;
+    }
+    /**
+     * Finds the XFA dataset object reference from the XFA array.
+     * XFA array structure: [(name1) ref1 (name2) ref2 ...]
+     * @param xfaArray The XFA array from the AcroForm
+     * @returns The object reference to the datasets stream, or null if not found
+     */
+    findXfaDatasetReference(xfaArray) {
+        const items = xfaArray.items;
+        // XFA array alternates between name strings and object references
+        for (let i = 0; i < items.length - 1; i += 2) {
+            const name = items[i];
+            const ref = items[i + 1];
+            if (name instanceof PdfString && name.value === 'datasets') {
+                if (ref instanceof PdfObjectReference) {
+                    return ref;
+                }
+            }
+        }
+        return null;
+    }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pdf-lite",
-  "version": "1.0.4",
+  "version": "1.0.6",
   "main": "dist/index.js",
   "type": "module",
   "exports": {
@@ -54,8 +54,8 @@
   ],
   "dependencies": {
     "pako": "2.1.0",
-    "pki-lite": "^1.0.12",
-    "pki-lite-crypto-extended": "^1.0.12"
+    "pki-lite": "^1.0.13",
+    "pki-lite-crypto-extended": "^1.0.13"
   },
   "scripts": {
     "test:acceptance": "vitest run test/acceptance",