unpdf 1.2.2 → 1.3.1

package/README.md

@@ -18,7 +18,7 @@ This library is also intended as a modern alternative to the unmaintained but st
 ## PDF.js Compatibility
 
 > [!Tip]
-> The serverless PDF.js bundle provided by `unpdf` is built from PDF.js v5.4.54.
+> The serverless PDF.js bundle provided by `unpdf` is built from PDF.js v5.4.149.
 
 You can use an [official PDF.js build](#official-or-legacy-pdfjs-build) by using the [`definePDFJSModule`](#definepdfjsmodule) method. This is useful if you want to use a specific version or a custom build of PDF.js.
 
@@ -131,11 +131,16 @@ function getResolvedPDFJS(): Promise<PDFJS>
 
 ### `getMeta`
 
+Extracts metadata from a PDF. If `parseDates` is set to `true`, the date properties will be parsed into `Date` objects.
+
 **Type Declaration**
 
 ```ts
 function getMeta(
   data: DocumentInitParameters['data'] | PDFDocumentProxy,
+  options?: {
+    parseDates?: boolean
+  },
 ): Promise<{
   info: Record<string, any>
   metadata: Record<string, any>

package/dist/index.cjs

@@ -229,14 +229,56 @@ async function getPageLinks(document, pageNumber) {
   return links;
 }
 
-async function getMeta$1(data) {
+const XMP_DATE_PROPERTIES = [
+  "xmp:createdate",
+  "xmp:modifydate",
+  "xmp:metadatadate",
+  "xap:createdate",
+  "xap:modifydate",
+  "xap:metadatadate"
+];
+async function getMeta$1(data, options = {}) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
   const meta = await pdf.getMetadata();
+  const info = meta?.info || {};
+  if (options.parseDates) {
+    const { PDFDateString } = await getResolvedPDFJS();
+    if (info?.CreationDate) {
+      info.CreationDate = PDFDateString.toDateObject(info?.CreationDate);
+    }
+    if (info?.ModDate) {
+      info.ModDate = PDFDateString.toDateObject(info?.ModDate);
+    }
+    if (meta.metadata) {
+      meta.metadata = new Proxy(meta.metadata, {
+        get(target, prop) {
+          if (prop === "get") {
+            return (name) => {
+              const value = target.get(name);
+              if (XMP_DATE_PROPERTIES.includes(name) && value) {
+                return parseISODateString(value);
+              }
+              return value;
+            };
+          }
+          return target[prop];
+        }
+      });
+    }
+  }
   return {
-    info: meta?.info ?? {},
-    metadata: { ...meta?.metadata }
+    info,
+    metadata: meta?.metadata || {}
   };
 }
+function parseISODateString(isoDateString) {
+  if (!isoDateString)
+    return;
+  const parsedDate = Date.parse(isoDateString);
+  if (!Number.isNaN(parsedDate)) {
+    return new Date(parsedDate);
+  }
+}
 
 async function extractText$1(data, options = {}) {
   const { mergePages = false } = options;

package/dist/index.d.cts

@@ -1,5 +1,6 @@
 import * as _napi_rs_canvas from '@napi-rs/canvas';
 import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
+import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata';
 import * as PDFJS from './types/src/pdf';
 
 interface ExtractedImageObject {
@@ -48,9 +49,11 @@ declare function extractLinks$1(data: DocumentInitParameters['data'] | PDFDocume
     links: string[];
 }>;
 
-declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    parseDates?: boolean;
+}): Promise<{
     info: Record<string, any>;
-    metadata: Record<string, any>;
+    metadata: pdfjs_dist_types_src_display_metadata.Metadata;
 }>;
 
 declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {

package/dist/index.d.mts

@@ -1,5 +1,6 @@
 import * as _napi_rs_canvas from '@napi-rs/canvas';
 import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
+import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata';
 import * as PDFJS from './types/src/pdf';
 
 interface ExtractedImageObject {
@@ -48,9 +49,11 @@ declare function extractLinks$1(data: DocumentInitParameters['data'] | PDFDocume
     links: string[];
 }>;
 
-declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    parseDates?: boolean;
+}): Promise<{
     info: Record<string, any>;
-    metadata: Record<string, any>;
+    metadata: pdfjs_dist_types_src_display_metadata.Metadata;
 }>;
 
 declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {

package/dist/index.d.ts

@@ -1,5 +1,6 @@
 import * as _napi_rs_canvas from '@napi-rs/canvas';
 import { DocumentInitParameters, PDFDocumentProxy } from './types/src/display/api';
+import * as pdfjs_dist_types_src_display_metadata from './types/src/display/metadata';
 import * as PDFJS from './types/src/pdf';
 
 interface ExtractedImageObject {
@@ -48,9 +49,11 @@ declare function extractLinks$1(data: DocumentInitParameters['data'] | PDFDocume
     links: string[];
 }>;
 
-declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
+    parseDates?: boolean;
+}): Promise<{
     info: Record<string, any>;
-    metadata: Record<string, any>;
+    metadata: pdfjs_dist_types_src_display_metadata.Metadata;
 }>;
 
 declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {

package/dist/index.mjs

@@ -227,14 +227,56 @@ async function getPageLinks(document, pageNumber) {
   return links;
 }
 
-async function getMeta$1(data) {
+const XMP_DATE_PROPERTIES = [
+  "xmp:createdate",
+  "xmp:modifydate",
+  "xmp:metadatadate",
+  "xap:createdate",
+  "xap:modifydate",
+  "xap:metadatadate"
+];
+async function getMeta$1(data, options = {}) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
   const meta = await pdf.getMetadata();
+  const info = meta?.info || {};
+  if (options.parseDates) {
+    const { PDFDateString } = await getResolvedPDFJS();
+    if (info?.CreationDate) {
+      info.CreationDate = PDFDateString.toDateObject(info?.CreationDate);
+    }
+    if (info?.ModDate) {
+      info.ModDate = PDFDateString.toDateObject(info?.ModDate);
+    }
+    if (meta.metadata) {
+      meta.metadata = new Proxy(meta.metadata, {
+        get(target, prop) {
+          if (prop === "get") {
+            return (name) => {
+              const value = target.get(name);
+              if (XMP_DATE_PROPERTIES.includes(name) && value) {
+                return parseISODateString(value);
+              }
+              return value;
+            };
+          }
+          return target[prop];
+        }
+      });
+    }
+  }
   return {
-    info: meta?.info ?? {},
-    metadata: { ...meta?.metadata }
+    info,
+    metadata: meta?.metadata || {}
   };
 }
+function parseISODateString(isoDateString) {
+  if (!isoDateString)
+    return;
+  const parsedDate = Date.parse(isoDateString);
+  if (!Number.isNaN(parsedDate)) {
+    return new Date(parsedDate);
+  }
+}
 
 async function extractText$1(data, options = {}) {
   const { mergePages = false } = options;