feat: update version to 5.3.2 and implement duplicate text removal in PdfReader and PdfReaderLegacy

Author: snowfluke

jsr.json

@@ -1,6 +1,6 @@
 {
   "name": "@snowfluke/ppu-pdf",
-  "version": "5.3.1",
+  "version": "5.3.2",
   "license": "MIT",
   "exports": "./src/index.ts",
   "publish": {

package.json

@@ -1,6 +1,6 @@
 {
   "name": "ppu-pdf",
-  "version": "5.3.1",
+  "version": "5.3.2",
   "description": "Easily extract text from digital PDF files with coordinate and font size included, and optionally group text by lines or render scanned pdf to canvas/png.",
   "keywords": [
     "pdf-reader",

src/pdf-reader-legacy.ts

@@ -187,7 +187,7 @@ export class PdfReaderLegacy extends PdfReaderCommon {
       const scale = x / token.transform[4];
 
       const pdfWord: PdfWord = {
-        text: token.str,
+        text: this.options.raw ? token.str : this.removeDuplicates(token.str),
         bbox: {
           x0: x,
           y0: y - token.height * scale,

src/pdf-reader.ts

@@ -186,7 +186,7 @@ export class PdfReader extends PdfReaderCommon {
       const font = item.font;
 
       const pdfWord: PdfWord = {
-        text: item.text,
+        text: this.options.raw ? item.text : this.removeDuplicates(item.text),
         bbox: {
           x0: x,
           y0: y,