api change

flyingeek · Mar 31, 2020 · 710b527 · 710b527
1 parent 4b293f1
commit 710b527
Show file tree

Hide file tree

Showing 6 changed files with 78 additions and 73 deletions.
diff --git a/README.md b/README.md
@@ -24,33 +24,9 @@ npm run build
 
 ## Running from Scriptable
 
-Copy `dist/scriptable-pdfjs.html` into Scriptable Document Folder.
+Copy the file `dist/scriptable-pdfjs.html` into Scriptable Document Folder.
 
-```javascript
-const fm = FileManager.iCloud();
-const wv = new WebView();
-const htmlFileUrl = fm.joinPath(fm.documentsDirectory(), "scriptable-pdfjs.html");
-await wv.loadFile(htmlFileUrl);
-
-/*
- In the WebView your javascript will have access to the pdfjs global var.
- pdfjs.pdfjsLib is the pdfjs module
- pdfjs.getPDFText is a convenience wrapper
- You have to pass the pdf file as a base64 string
-*/
-
-let javascript = 'pdfjs.getPDFText(';
-javascript += '"' + fm.read(pdfFilePath).toBase64String() + '"';
-javascript += ');'
-
-let result = "";
-try {
-  result = await wv.evaluateJavaScript(javascript, true);
-} catch (e) {
-  //...
-}
-//...
-```
+and use [scriptable-pdfjs-demo](https://gist.github.com/flyingeek/70f5e09887f17dbfcd11a4b620a68b28) to play.
 
 ## Running from Shortcuts app
 
@@ -71,27 +47,30 @@ try {
 }
 // use the same bookmark name as in the action above
 const filePath = fm.bookmarkedPath("ShortcutPDF");
-await fm. downloadFileFromiCloud(filePath); // works also for local file
 
 // We execute pdfjs in a WebView
 const wv = new WebView();
 const htmlFileUrl = fm.joinPath(fm.documentsDirectory(), "scriptable-pdfjs.html");
+await fm.downloadFileFromiCloud(htmlFileUrl);
 await wv.loadFile(htmlFileUrl);
 
-let javascript = 'pdfjs.getPDFText(';
+let javascript = 'pdfjs.getText(';
 javascript += '"' + fm.read(filePath).toBase64String() + '"';
-javascript += ', (pageText) => pageText.includes("(Long copy #1)")';
-javascript += ', true';
+//javascript += ', (pageText) => pageText.includes("(Long copy #1)")';
+//javascript += ', true';
 javascript += ');'
 
-
+let result = "";
 try {
   result = await wv.evaluateJavaScript(javascript, true);
 } catch (e) {
   result = "";
 }
-Script.setShortcutOutput(result);
+return result;
 ```
 For some reasons... (bug in shortcuts or scriptable ?) You cannot convert
 the PDF to Base64 and pass it as an argument to the script. You have to use
 the bookmark trick and make the base64 conversion in Scriptable.
+
+For file larger than 2.5 Mo, you can not run this script inline and you 
+have to modify the script to get results by using the clipboard.
diff --git a/package-lock.json b/package-lock.json
diff --git a/package.json b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "scriptable-pdfjs",
-  "version": "1.0.0",
+  "version": "1.0.0-beta.1",
   "description": "converts a pdf to text in ios app scriptable app.",
   "main": "index.js",
   "scripts": {

diff --git a/src/index.html b/src/index.html
@@ -1,10 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
-  <meta charset="UTF-8">
-  <title>scriptable-pdfjs</title>
-</head>
-<body>
-
-</body>
-</html>

diff --git a/src/index.js b/src/index.js
@@ -13,13 +13,14 @@ if (typeof window !== 'undefined' && 'Worker' in window) {
  * returns the text of a page
  * @param pdf:pdfjs.Document
  * @param pageNo:number
+ * @param separator:string=""
  * @returns {Promise<string>}
  */
-async function getPageText(pdf, pageNo) {
+async function getPageText(pdf, pageNo, separator="") {
   // noinspection JSUnresolvedFunction
   const page = await pdf.getPage(pageNo);
   const tokenizedText = await page.getTextContent();
-  return tokenizedText.items.map(token => token.str).join("");
+  return tokenizedText.items.map(token => token.str).join(separator);
 }
 
 /**
@@ -42,15 +43,17 @@ async function getPageText(pdf, pageNo) {
  * @param source: pdfjs.Document - the pdf document
  * @param matchFn:[function] - the match function
  * @param breakAfter:[boolean=false] - if true, stop the search after failure
+ * @param pageSeparator:string="" - the page separator
+ * @param tokenSeparator:string="" - the token separator
  * @returns {Promise<string>}
  */
-async function extractPDFText(source, matchFn, breakAfter=false){
+export async function extractText(source, matchFn, breakAfter=false, pageSeparator="", tokenSeparator=""){
   const pdfPages = [];
   let matchingPagesCount = 0;
   const pdf = await pdfjs.getDocument(source).promise;
   const maxPages = pdf.numPages;
   for (let pageNo = 1; pageNo <= maxPages; pageNo += 1) {
-    const pageText = await getPageText(pdf, pageNo);
+    const pageText = await getPageText(pdf, pageNo, tokenSeparator);
     if (matchFn) {
       if (matchFn(pageText, pageNo, pdf)) {
         pdfPages.push(pageText);
@@ -62,23 +65,34 @@ async function extractPDFText(source, matchFn, breakAfter=false){
       pdfPages.push(pageText);
     }
   }
-  return pdfPages.join("");
+  return pdfPages.join(pageSeparator);
 }
 
 /**
- * a wrapper to the extractPDFText with completion and error handling
- * @param base64string:string - the pdf in base64 string format
+ * a convenience wrapper to extractText using Scriptable completion fn
+ * @param source:[string|object] - pdf source accepted by pdfjs.getDocument
  * @param matchFn:[function] - optional text matching function
  * @param breakAfter:[boolean=false]
+ * @param pageSeparator:string="" - the page separator
+ * @param tokenSeparator:string="" - the token separator
  */
-export function getPDFText(base64string, matchFn, breakAfter=false ) {
-  extractPDFText(
-    {data: atob(base64string)},
-    matchFn,
-    breakAfter).then((text) => {
+export function getText(source, matchFn, breakAfter=false, pageSeparator="", tokenSeparator = "" ) {
+  extractText(source, matchFn, breakAfter, pageSeparator, tokenSeparator)
+    .then((text) => {
       completion(text)
   }, (error) => {
       throw Error(error);
   });
 }
+/**
+ * a wrapper for getText when you need to use base64 string as source
+ * @param base64string:string - the pdf in base64 string format
+ * @param matchFn:[function] - optional text matching function
+ * @param breakAfter:[boolean=false]
+ * @param pageSeparator:string="" - the page separator
+ * @param tokenSeparator:string="" - the token separator
+ */
+export function getTextFromBase64String(base64string, matchFn, breakAfter=false,  pageSeparator="", tokenSeparator = "") {
+  getText({data: atob(base64string)}, matchFn, breakAfter, pageSeparator, tokenSeparator);
+}
 
diff --git a/webpack.config.js b/webpack.config.js
@@ -30,7 +30,7 @@ const config = {
       inlineSource: '.(js|css)$',
       filename: `${infos.name}.html`,
     }),
-    new HtmlWebpackInlineSourcePlugin(HtmlWebpackPlugin),
+    new HtmlWebpackInlineSourcePlugin(HtmlWebpackPlugin)
   ]
 };