Add option asciiWordBoundaries

README.md

@@ -78,7 +78,9 @@ type OnigurumaToEsOptions = {
   hasIndices?: boolean;
   maxRecursionDepth?: number | null;
   overrides?: {
+    allowAllSearchStartAnchors?: boolean;
     allowOrphanBackrefs?: boolean;
+    asciiWordBoundaries?: boolean;
   };
   target?: 'auto' | 'ES2025' | 'ES2024' | 'ES2018';
   verbose?: boolean;
@@ -209,11 +211,12 @@ Using a high limit has a small impact on performance. Generally, this is only a
 
 ### `overrides`
 
-Advanced options that take precedence over standard error checking and flags.
+Advanced options that take precedence over standard error checking and flags when enabled.
 
-- `allowOrphanBackrefs`: Useful with TextMate grammars that merge backreferences across `begin` and `end` patterns.
 - `allowAllSearchStartAnchors`: Silences errors for unsupported uses of the search-start anchor `\G`.
   - Oniguruma-To-ES uses a variety of strategies to accurately emulate many common uses of `\G`. When using this option, if a `\G` is found that doesn't have a known emulation strategy, the `\G` is simply removed and JavaScript's `y` (`sticky`) flag is added. This might lead to some false positives and negatives, but is useful for non-critical matching like syntax highlighting when having some mismatches is better than not working.
+- `allowOrphanBackrefs`: Useful with TextMate grammars that merge backreferences across `begin` and `end` patterns.
+- `asciiWordBoundaries`: ASCII-only `\b` and `\B`.
 
 ### `target`
 

demo/demo.js

@@ -21,8 +21,9 @@ const state = {
     hasIndices: getValue('option-hasIndices'),
     maxRecursionDepth: getValue('option-maxRecursionDepth'),
     overrides: {
-      allowOrphanBackrefs: getValue('option-allowOrphanBackrefs'),
       allowAllSearchStartAnchors: getValue('option-allowAllSearchStartAnchors'),
+      allowOrphanBackrefs: getValue('option-allowOrphanBackrefs'),
+      asciiWordBoundaries: getValue('option-asciiWordBoundaries'),
     },
     target: getValue('option-target'),
     verbose: getValue('option-verbose'),

demo/index.html

@@ -108,22 +108,29 @@ <h2>Try it</h2>
           </p>
         </div>
         <div>
+          <p>
+            <label>
+              <input type="checkbox" id="option-allowAllSearchStartAnchors" onchange="setOverride('allowAllSearchStartAnchors', this.checked)">
+              <code>allowAllSearchStartAnchors</code>
+              <span class="tip tip-lg">Silences errors for unsupported uses of <code>\G</code></span>
+            </label>
+          </p>
           <p>
             <label>
               <input type="checkbox" id="option-allowOrphanBackrefs" onchange="setOverride('allowOrphanBackrefs', this.checked)">
               <code>allowOrphanBackrefs</code>
               <span class="tip tip-xl">Useful with TextMate grammars that merge backrefs across <code>begin</code> and <code>end</code> patterns</span>
             </label>
           </p>
+        </div>
+        <div>
           <p>
             <label>
-              <input type="checkbox" id="option-allowAllSearchStartAnchors" onchange="setOverride('allowAllSearchStartAnchors', this.checked)">
-              <code>allowAllSearchStartAnchors</code>
-              <span class="tip tip-lg">Silences errors for unsupported uses of <code>\G</code></span>
+              <input type="checkbox" id="option-asciiWordBoundaries" onchange="setOverride('asciiWordBoundaries', this.checked)">
+              <code>asciiWordBoundaries</code>
+              <span class="tip tip-lg">ASCII-only <code>\b</code> and <code>\B</code></span>
             </label>
           </p>
-        </div>
-        <div>
           <p>
             <label>
               <input type="checkbox" id="option-verbose" onchange="setOption('verbose', this.checked)">

src/index.js

@@ -29,8 +29,9 @@ import {recursion} from 'regex-recursion';
   hasIndices?: boolean;
   maxRecursionDepth?: number | null;
   overrides?: {
+    allowAllSearchStartAnchors?: boolean;
     allowOrphanBackrefs?: boolean;
-    allowAllSearchStartAnchors: boolean;
+    asciiWordBoundaries?: boolean;
   };
   target?: keyof Target;
   verbose?: boolean;
@@ -57,6 +58,7 @@ function toDetails(pattern, options) {
   const regexAst = transform(onigurumaAst, {
     accuracy: opts.accuracy,
     allowAllSearchStartAnchors: opts.overrides.allowAllSearchStartAnchors,
+    asciiWordBoundaries: opts.overrides.asciiWordBoundaries,
     avoidSubclass: opts.avoidSubclass,
     bestEffortTarget: opts.target,
   });

src/options.js

@@ -51,12 +51,14 @@ function getOptions(options) {
     // Disables optimizations that simplify the pattern when it doesn't change the meaning.
     verbose: false,
     ...options,
-    // Advanced options that take precedence over standard error checking and flags.
+    // Advanced options that take precedence over standard error checking and flags when enabled.
     overrides: {
-      // Useful with TextMate grammars that merge backreferences across `begin` and `end` patterns.
-      allowOrphanBackrefs: false,
       // Silences errors for unsupported uses of the search-start anchor `\G`.
       allowAllSearchStartAnchors: false,
+      // Useful with TextMate grammars that merge backreferences across `begin` and `end` patterns.
+      allowOrphanBackrefs: false,
+      // ASCII-only `\b` and `\B`.
+      asciiWordBoundaries: false,
       ...(options?.overrides),
     },
   };

src/transform.js

@@ -31,6 +31,7 @@ AST represents what's needed to precisely reproduce Oniguruma behavior using Reg
 @param {{
   accuracy?: keyof Accuracy;
   allowAllSearchStartAnchors?: boolean;
+  asciiWordBoundaries?: boolean;
   avoidSubclass?: boolean;
   bestEffortTarget?: keyof Target;
 }} [options]
@@ -46,6 +47,7 @@ function transform(ast, options) {
     //   based on `target`/`accuracy`, so produce the appropriate structure here.
     accuracy: 'default',
     allowAllSearchStartAnchors: false,
+    asciiWordBoundaries: false,
     avoidSubclass: false,
     bestEffortTarget: 'ES2025',
     ...options,
@@ -55,6 +57,7 @@ function transform(ast, options) {
   const firstPassState = {
     accuracy: opts.accuracy,
     allowAllSearchStartAnchors: opts.allowAllSearchStartAnchors,
+    asciiWordBoundaries: opts.asciiWordBoundaries,
     flagDirectivesByAlt: new Map(),
     minTargetEs2024: isMinTarget(opts.bestEffortTarget, 'ES2024'),
     // Subroutines can appear before the groups they ref, so collect reffed nodes for a second pass 
@@ -127,7 +130,7 @@ const FirstPassVisitor = {
     },
   },
 
-  Assertion({node, ast, remove, replaceWith}, {allowAllSearchStartAnchors, supportedGNodes, wordIsAscii}) {
+  Assertion({node, ast, remove, replaceWith}, {allowAllSearchStartAnchors, asciiWordBoundaries, supportedGNodes, wordIsAscii}) {
     const {kind, negate} = node;
     if (kind === AstAssertionKinds.line_end) {
       // Onig's only line break char is line feed, unlike JS
@@ -143,7 +146,7 @@ const FirstPassVisitor = {
       remove();
     } else if (kind === AstAssertionKinds.string_end_newline) {
       replaceWith(parseFragment(r`(?=\n?\z)`));
-    } else if (kind === AstAssertionKinds.word_boundary && !wordIsAscii) {
+    } else if (kind === AstAssertionKinds.word_boundary && !wordIsAscii && !asciiWordBoundaries) {
       const b = `(?:(?<=${defaultWordChar})(?!${defaultWordChar})|(?<!${defaultWordChar})(?=${defaultWordChar}))`;
       const B = `(?:(?<=${defaultWordChar})(?=${defaultWordChar})|(?<!${defaultWordChar})(?!${defaultWordChar}))`;
       replaceWith(parseFragment(negate ? B : b));