unpdf 1.5.1 → 1.6.0

package/dist/index.cjs

@@ -340,6 +340,32 @@ function parseISODateString(isoDateString) {
   }
 }
 
+async function extractTextItems$1(data) {
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const items = await Promise.all(
+    Array.from({ length: pdf.numPages }, (_, i) => getPageTextItems(pdf, i + 1))
+  );
+  return { totalPages: pdf.numPages, items };
+}
+async function getPageTextItems(document, pageNumber) {
+  const page = await document.getPage(pageNumber);
+  const content = await page.getTextContent();
+  const styles = content.styles;
+  return content.items.filter((item) => item.str != null).map((item) => {
+    const [_a, _b, c, d, e, f] = item.transform;
+    return {
+      str: item.str,
+      x: e,
+      y: f,
+      width: item.width,
+      height: item.height,
+      fontSize: Math.hypot(c, d),
+      fontFamily: styles[item.fontName]?.fontFamily ?? "",
+      dir: item.dir,
+      hasEOL: item.hasEOL
+    };
+  });
+}
 async function extractText$1(data, options = {}) {
   const { mergePages = false } = options;
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
@@ -372,6 +398,10 @@ const extractText = async (...args) => {
   await resolvePDFJSImport();
   return await extractText$1(...args);
 };
+const extractTextItems = async (...args) => {
+  await resolvePDFJSImport();
+  return await extractTextItems$1(...args);
+};
 const extractImages = async (...args) => {
   await resolvePDFJSImport();
   return await extractImages$1(...args);
@@ -391,6 +421,7 @@ exports.definePDFJSModule = definePDFJSModule;
 exports.extractImages = extractImages;
 exports.extractLinks = extractLinks;
 exports.extractText = extractText;
+exports.extractTextItems = extractTextItems;
 exports.getDocumentProxy = getDocumentProxy;
 exports.getMeta = getMeta;
 exports.getResolvedPDFJS = getResolvedPDFJS;

package/dist/index.d.cts

@@ -100,6 +100,30 @@ declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentPro
     metadata: pdfjs_dist_types_src_display_metadata.Metadata;
 }>;
 
+interface StructuredTextItem {
+    /** Text content. */
+    str: string;
+    /** X position in PDF coordinate space (origin: bottom-left). */
+    x: number;
+    /** Y position in PDF coordinate space (origin: bottom-left). */
+    y: number;
+    /** Width in device space. */
+    width: number;
+    /** Height in device space. */
+    height: number;
+    /** Font size derived from the transformation matrix. */
+    fontSize: number;
+    /** Font family name. */
+    fontFamily: string;
+    /** Text direction: `"ltr"`, `"rtl"`, or `"ttb"`. */
+    dir: string;
+    /** Whether the text item is followed by a line break. */
+    hasEOL: boolean;
+}
+declare function extractTextItems$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    totalPages: number;
+    items: StructuredTextItem[][];
+}>;
 declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
     mergePages?: false;
 }): Promise<{
@@ -149,8 +173,10 @@ declare function resolvePDFJSImport(pdfjsResolver?: () => Promise<any>, { reload
 
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
+declare const extractTextItems: typeof extractTextItems$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
 declare const extractLinks: typeof extractLinks$1;
 
-export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, extractTextItems, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export type { StructuredTextItem };

package/dist/index.d.mts

@@ -100,6 +100,30 @@ declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentPro
     metadata: pdfjs_dist_types_src_display_metadata.Metadata;
 }>;
 
+interface StructuredTextItem {
+    /** Text content. */
+    str: string;
+    /** X position in PDF coordinate space (origin: bottom-left). */
+    x: number;
+    /** Y position in PDF coordinate space (origin: bottom-left). */
+    y: number;
+    /** Width in device space. */
+    width: number;
+    /** Height in device space. */
+    height: number;
+    /** Font size derived from the transformation matrix. */
+    fontSize: number;
+    /** Font family name. */
+    fontFamily: string;
+    /** Text direction: `"ltr"`, `"rtl"`, or `"ttb"`. */
+    dir: string;
+    /** Whether the text item is followed by a line break. */
+    hasEOL: boolean;
+}
+declare function extractTextItems$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    totalPages: number;
+    items: StructuredTextItem[][];
+}>;
 declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
     mergePages?: false;
 }): Promise<{
@@ -149,8 +173,10 @@ declare function resolvePDFJSImport(pdfjsResolver?: () => Promise<any>, { reload
 
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
+declare const extractTextItems: typeof extractTextItems$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
 declare const extractLinks: typeof extractLinks$1;
 
-export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, extractTextItems, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export type { StructuredTextItem };

package/dist/index.d.ts

@@ -100,6 +100,30 @@ declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentPro
     metadata: pdfjs_dist_types_src_display_metadata.Metadata;
 }>;
 
+interface StructuredTextItem {
+    /** Text content. */
+    str: string;
+    /** X position in PDF coordinate space (origin: bottom-left). */
+    x: number;
+    /** Y position in PDF coordinate space (origin: bottom-left). */
+    y: number;
+    /** Width in device space. */
+    width: number;
+    /** Height in device space. */
+    height: number;
+    /** Font size derived from the transformation matrix. */
+    fontSize: number;
+    /** Font family name. */
+    fontFamily: string;
+    /** Text direction: `"ltr"`, `"rtl"`, or `"ttb"`. */
+    dir: string;
+    /** Whether the text item is followed by a line break. */
+    hasEOL: boolean;
+}
+declare function extractTextItems$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    totalPages: number;
+    items: StructuredTextItem[][];
+}>;
 declare function extractText$1(data: DocumentInitParameters['data'] | PDFDocumentProxy, options?: {
     mergePages?: false;
 }): Promise<{
@@ -149,8 +173,10 @@ declare function resolvePDFJSImport(pdfjsResolver?: () => Promise<any>, { reload
 
 declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
+declare const extractTextItems: typeof extractTextItems$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
 declare const extractLinks: typeof extractLinks$1;
 
-export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, extractTextItems, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export type { StructuredTextItem };

package/dist/index.mjs

@@ -338,6 +338,32 @@ function parseISODateString(isoDateString) {
   }
 }
 
+async function extractTextItems$1(data) {
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const items = await Promise.all(
+    Array.from({ length: pdf.numPages }, (_, i) => getPageTextItems(pdf, i + 1))
+  );
+  return { totalPages: pdf.numPages, items };
+}
+async function getPageTextItems(document, pageNumber) {
+  const page = await document.getPage(pageNumber);
+  const content = await page.getTextContent();
+  const styles = content.styles;
+  return content.items.filter((item) => item.str != null).map((item) => {
+    const [_a, _b, c, d, e, f] = item.transform;
+    return {
+      str: item.str,
+      x: e,
+      y: f,
+      width: item.width,
+      height: item.height,
+      fontSize: Math.hypot(c, d),
+      fontFamily: styles[item.fontName]?.fontFamily ?? "",
+      dir: item.dir,
+      hasEOL: item.hasEOL
+    };
+  });
+}
 async function extractText$1(data, options = {}) {
   const { mergePages = false } = options;
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
@@ -370,6 +396,10 @@ const extractText = async (...args) => {
   await resolvePDFJSImport();
   return await extractText$1(...args);
 };
+const extractTextItems = async (...args) => {
+  await resolvePDFJSImport();
+  return await extractTextItems$1(...args);
+};
 const extractImages = async (...args) => {
   await resolvePDFJSImport();
   return await extractImages$1(...args);
@@ -383,4 +413,4 @@ const extractLinks = async (...args) => {
   return await extractLinks$1(...args);
 };
 
-export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, createIsomorphicCanvasFactory, definePDFJSModule, extractImages, extractLinks, extractText, extractTextItems, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "unpdf",
   "type": "module",
-  "version": "1.5.1",
+  "version": "1.6.0",
   "packageManager": "pnpm@10.33.0",
   "description": "PDF extraction and rendering across all JavaScript runtimes",
   "author": "Johann Schopplich <hello@johannschopplich.com>",