Issue/94 and more

README.md

@@ -10,6 +10,17 @@ I have no plans to shut down or increase/decrease my level of support for the si
 
 Thank you all for the support over the past few years! 
 
+## How to run this code
+
+Install NPM per your OS-specific guidance found here: https://nodejs.org/en/download/package-manager
+
+run 'npm run build'  
+cd into the build directory, then serve the files via an HTTP server
+
+If testing on Windows, these commands will do for testing (use a better server for production):
+
+'npm run build; cd build; python -m http.server'; then browse to http://localhost:8000
+
 ## pdf analysis of air force forms
 
 One of the most pointless and time-consuming things that Air Force officer and enlisted personnel do every year is bullet-writing. 

src/BulletApp.js

@@ -8,7 +8,7 @@ import { tokenize } from "./components/Bullets/utils";
 import AbbreviationViewer from "./components/Abbreviation/AbbreviationViewer";
 import SynonymViewer from "./components/Toolbars/Thesaurus.js";
 import { EditorState, ContentState, Modifier, SelectionState, CompositeDecorator } from "draft-js";
-import { defaultAbbrData, defaultText, defaultWidth } from "./const/defaults";
+import { defaultAbbrData, defaultText, defaultWidth, stopWords } from "./const/defaults";
 
 const defaultEditorState = EditorState.createWithContent(
   ContentState.createFromText(defaultText)
@@ -186,9 +186,12 @@ function BulletApp({enableHighlight, onHighlightChange}) {
 
       function findWithRegex(duplicates, contentBlock, callback) {
         const text = contentBlock.getText();
+        const duplicatesMinusStopWords = new Set(duplicates).difference(stopWords);
 
-        duplicates.forEach(word => {
-          const matches = [...text.matchAll(word)];
+        duplicatesMinusStopWords.forEach(word => {
+          // use global (g) and case insensitive (i) match
+          let re = new RegExp(String.raw`\s${word}\s`, "gi");
+          const matches = [...text.matchAll(re)];
           matches.forEach(match =>
             callback(match.index, match.index + match[0].length)
           );
@@ -327,10 +330,13 @@ function BulletApp({enableHighlight, onHighlightChange}) {
 
         function findWithRegex(duplicates, contentBlock, callback) {
           const text = contentBlock.getText();
-
-          duplicates.forEach(word => {
-            const matches = [...text.matchAll(word)];
-            matches.forEach(match =>
+          const duplicatesMinusStopWords = new Set(duplicates).difference(stopWords);
+
+          duplicatesMinusStopWords.forEach(word => {
+            // use global (g) and case insensitive (i) match
+            let re = new RegExp(String.raw`\s${word}\s`, "gi"); 
+            const matches = [...text.matchAll(re)];
+            matches.forEach(match => 
               callback(match.index, match.index + match[0].length)
             );
           });

src/components/Bullets/BulletComparator.js

@@ -2,6 +2,7 @@ import { useState, useEffect } from "react";
 import { Editor, RichUtils, CompositeDecorator, EditorState } from "draft-js";
 import "draft-js/dist/Draft.css";
 import Bullet from "./Bullet";
+import { stopWords } from "../../const/defaults";
 
 
 const DPI = 96;
@@ -66,9 +67,12 @@ export default function BulletComparator({
 
         function findWithRegex(duplicates, contentBlock, callback) {
           const text = contentBlock.getText();
+          const duplicatesMinusStopWords = new Set(duplicates).difference(stopWords);
 
-          duplicates.forEach(word => {
-            const matches = [...text.matchAll(word)];
+          duplicatesMinusStopWords.forEach(word => {
+            // use global (g) and case insensitive (i) match
+            let re = new RegExp(String.raw`\s${word}\s`, "gi");
+            const matches = [...text.matchAll(re)];
             matches.forEach(match =>
               callback(match.index, match.index + match[0].length)
             );