obscenity - npm Package Compare versions

Comparing version 0.3.1 to 0.4.0

dist/matcher/regexp/RegExpMatcher.d.ts

@@ -69,2 +69,3 @@ import type { TransformerContainer } from '../../transformer/Transformers';
     private compileTerms;
+    private validateWhitelistedTerms;
 }
@@ -71,0 +72,0 @@ /**

dist/matcher/regexp/RegExpMatcher.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.RegExpMatcher = void 0;
+const Char_1 = require("../../util/Char");
 const Util_1 = require("../../pattern/Util");
 const TransformerSet_1 = require("../../transformer/TransformerSet");
-const Char_1 = require("../../util/Char");
 const CharacterIterator_1 = require("../../util/CharacterIterator");
@@ -66,2 +66,3 @@ const IntervalCollection_1 = require("../IntervalCollection");
         this.blacklistedTerms = this.compileTerms(blacklistedTerms);
+        this.validateWhitelistedTerms(whitelistedTerms);
         this.whitelistedTerms = whitelistedTerms;
@@ -73,19 +74,22 @@ this.blacklistMatcherTransformers = new TransformerSet_1.TransformerSet(blacklistMatcherTransformers);
         const whitelistedIntervals = this.getWhitelistedIntervals(input);
-        const [indices, transformed] = this.applyTransformers(input, this.blacklistMatcherTransformers);
+        const [transformedToOrigIndex, transformed] = this.applyTransformers(input, this.blacklistMatcherTransformers);
         const matches = [];
         for (const blacklistedTerm of this.blacklistedTerms) {
             for (const match of transformed.matchAll(blacklistedTerm.regExp)) {
-                const matchLength = [...match[0]].length; // spread so we count code points, not code units
-                const startIndex = indices[match.index];
-                // eslint-disable-next-line @typescript-eslint/restrict-plus-operands
-                let endIndex = indices[match.index + matchLength - 1];
-                // Adjust the end index if needed.
-                if (endIndex < transformed.length - 1 && // not the last character
-                    (0, Char_1.isHighSurrogate)(transformed.charCodeAt(endIndex)) && // character is a high surrogate
-                    (0, Char_1.isLowSurrogate)(transformed.charCodeAt(endIndex + 1)) // next character is a low surrogate
+                const origStartIndex = transformedToOrigIndex[match.index];
+                let origEndIndex = transformedToOrigIndex[match.index + match[0].length - 1];
+                // End index is (unfortunately) inclusive, so adjust as necessary.
+                if (origEndIndex < input.length - 1 && // not the last character
+                    (0, Char_1.isHighSurrogate)(input.charCodeAt(origEndIndex)) && // character is a high surrogate
+                    (0, Char_1.isLowSurrogate)(input.charCodeAt(origEndIndex + 1)) // next character is a low surrogate
                 ) {
-                    endIndex++;
+                    origEndIndex++;
                 }
-                if (!whitelistedIntervals.query(startIndex, endIndex)) {
-                    matches.push({ termId: blacklistedTerm.id, startIndex, endIndex, matchLength });
+                if (!whitelistedIntervals.query(origStartIndex, origEndIndex)) {
+                    matches.push({
+                        termId: blacklistedTerm.id,
+                        startIndex: origStartIndex,
+                        endIndex: origEndIndex,
+                        matchLength: [...match[0]].length,
+                    });
                 }
@@ -100,17 +104,15 @@ }
         const whitelistedIntervals = this.getWhitelistedIntervals(input);
-        const [indices, transformed] = this.applyTransformers(input, this.blacklistMatcherTransformers);
+        const [transformedToOrigIndex, transformed] = this.applyTransformers(input, this.blacklistMatcherTransformers);
         for (const blacklistedTerm of this.blacklistedTerms) {
             for (const match of transformed.matchAll(blacklistedTerm.regExp)) {
-                const matchLength = [...match[0]].length; // spread so we count code points, not code units
-                const startIndex = indices[match.index];
-                // eslint-disable-next-line @typescript-eslint/restrict-plus-operands
-                let endIndex = indices[match.index + matchLength - 1];
-                // Adjust the end index if needed.
-                if (endIndex < transformed.length - 1 && // not the last character
-                    (0, Char_1.isHighSurrogate)(transformed.charCodeAt(endIndex)) && // character is a high surrogate
-                    (0, Char_1.isLowSurrogate)(transformed.charCodeAt(endIndex + 1)) // next character is a low surrogate
+                const origStartIndex = transformedToOrigIndex[match.index];
+                let origEndIndex = transformedToOrigIndex[match.index + match[0].length - 1];
+                // End index is (unfortunately) inclusive, so adjust as necessary.
+                if (origEndIndex < input.length - 1 && // not the last character
+                    (0, Char_1.isHighSurrogate)(input.charCodeAt(origEndIndex)) && // character is a high surrogate
+                    (0, Char_1.isLowSurrogate)(input.charCodeAt(origEndIndex + 1)) // next character is a low surrogate
                 ) {
-                    endIndex++;
+                    origEndIndex++;
                 }
-                if (!whitelistedIntervals.query(startIndex, endIndex))
+                if (!whitelistedIntervals.query(origStartIndex, origEndIndex))
                     return true;
@@ -123,17 +125,16 @@ }
         const matches = new IntervalCollection_1.IntervalCollection();
-        const [indices, transformed] = this.applyTransformers(input, this.whitelistMatcherTransformers);
+        const [transformedToOrigIndex, transformed] = this.applyTransformers(input, this.whitelistMatcherTransformers);
         for (const whitelistedTerm of this.whitelistedTerms) {
-            const length = [...whitelistedTerm].length;
             let lastEnd = 0;
             for (let startIndex = transformed.indexOf(whitelistedTerm, lastEnd); startIndex !== -1; startIndex = transformed.indexOf(whitelistedTerm, lastEnd)) {
-                let endIndex = indices[startIndex + length - 1];
-                // Adjust the end index if needed.
-                if (endIndex < transformed.length - 1 && // not the last character
-                    (0, Char_1.isHighSurrogate)(transformed.charCodeAt(endIndex)) && // character is a high surrogate
-                    (0, Char_1.isLowSurrogate)(transformed.charCodeAt(endIndex + 1)) // next character is a low surrogate
+                let origEndIndex = transformedToOrigIndex[startIndex + whitelistedTerm.length - 1];
+                // End index is (unfortunately) inclusive, so adjust as necessary.
+                if (origEndIndex < input.length - 1 && // not the last character
+                    (0, Char_1.isHighSurrogate)(input.charCodeAt(origEndIndex)) && // character is a high surrogate
+                    (0, Char_1.isLowSurrogate)(input.charCodeAt(origEndIndex + 1)) // next character is a low surrogate
                 ) {
-                    endIndex++;
+                    origEndIndex++;
                 }
-                matches.insert(indices[startIndex], endIndex);
-                lastEnd = endIndex + 1;
+                matches.insert(transformedToOrigIndex[startIndex], origEndIndex);
+                lastEnd = startIndex + whitelistedTerm.length;
             }
@@ -144,3 +145,3 @@ }
     applyTransformers(input, transformers) {
-        const indices = [];
+        const transformedToOrigIndex = [];
         let transformed = '';
@@ -151,8 +152,9 @@ const iter = new CharacterIterator_1.CharacterIterator(input);
             if (transformedChar !== undefined) {
-                indices.push(iter.position);
                 transformed += String.fromCodePoint(transformedChar);
+                while (transformedToOrigIndex.length < transformed.length)
+                    transformedToOrigIndex.push(iter.position);
             }
         }
         transformers.resetAll();
-        return [indices, transformed];
+        return [transformedToOrigIndex, transformed];
     }
@@ -176,3 +178,8 @@ compileTerms(terms) {
     }
+    validateWhitelistedTerms(whitelist) {
+        if (whitelist.some((term) => term.length === 0)) {
+            throw new Error('Whitelisted term set contains empty string; this is unsupported.');
+        }
+    }
 }
 exports.RegExpMatcher = RegExpMatcher;

package.json

 {
   "name": "obscenity",
-  "version": "0.3.1",
+  "version": "0.4.0",
   "description": "Robust, extensible profanity filter.",
@@ -54,9 +54,8 @@ "files": [
     "@types/jest": "^29.5.2",
-    "@typescript-eslint/eslint-plugin": "^6.0.0",
-    "@typescript-eslint/parser": "^6.0.0",
+    "@typescript-eslint/eslint-plugin": "^6.21.0",
+    "@typescript-eslint/parser": "^6.21.0",
     "conventional-github-releaser": "^3.1.5",
-    "eslint": "^8.42.0",
-    "eslint-config-neon": "^0.1.47",
-    "eslint-config-prettier": "^9.0.0",
-    "eslint-plugin-jest": "^27.2.1",
+    "eslint": "^8.57.0",
+    "eslint-config-prettier": "^9.1.0",
+    "eslint-plugin-jest": "^27.9.0",
     "eslint-plugin-prettier": "^4.2.1",
@@ -69,3 +68,3 @@ "fast-check": "^2.25.0",
     "prettier": "^2.8.8",
-    "rimraf": "^5.0.0",
+    "rimraf": "^6.0.0",
     "standard-version": "^9.5.0",
@@ -72,0 +71,0 @@ "ts-jest": "^29.1.1",

No alert changes

Improved metrics

Total package byte prevSize

153856

increased by0.28%

Dev dependency count

24

decreased by-4%

Lines of code

3450

increased by0.23%

No dependency changes