Merge pull request #37 from theodevelop/dev

release: v1.5.1

Author: theodevelop

.gitignore

@@ -3,4 +3,7 @@ dist/
 client/out/
 server/out/
 *.vsix
-.env
+.env
+tests/_*
+docs/
+.vscode/

.vscodeignore

@@ -24,3 +24,4 @@ package-lock.json
 .gitattributes
 .env
 .env.*
+docs/

CHANGELOG.md

@@ -2,6 +2,22 @@
 
 All notable changes to the **Bison/Flex Language Support** extension will be documented in this file.
 
+## [1.5.1] - 2026-04-02
+
+### Fixed
+
+- **Flex — escaped quotes in quoted string patterns** (#30): patterns like `X"\'"` and `Y"\""` no longer trigger false `flex/invalid-pattern` errors. The validator now correctly handles `\"` and `\'` escape sequences inside Flex quoted strings.
+- **Flex — abbreviation refs on rule lines with no inline action** (#31): `{ABBR}` used after a `^` BOL anchor or on a rule line whose action block appears on the following line was not recorded as an abbreviation reference, causing false `flex/unused-abbrev` warnings.
+- **Flex — quoted strings with spaces in `rawPattern`** (audit-A): patterns like `"hello world"` were truncated at the space inside the quoted literal, causing false `flex/unreachable-rule` duplicates for distinct patterns sharing a common word prefix. `rawPattern()` now tracks quoted-string depth.
+- **Flex — standalone `{` as multi-line action opener** (audit-B): a `{` appearing alone on the line after a rule pattern (valid Flex multi-line action syntax) was pushed as a spurious rule entry with pattern `{`, producing false `flex/unreachable-rule` diagnostics for every subsequent multi-line-action rule.
+- **Flex — lowercase start condition names** (audit-C): all start-condition regex patterns used `[A-Z_][A-Z0-9_]*` (uppercase only). SC names that are valid C identifiers but lowercase (e.g. `%x comment`) were silently ignored, skipping `flex/undefined-sc` and `flex/unused-sc` diagnostics for them entirely.
+- **Flex — single-tab action separator in abbreviation ref scan** (audit-D): the heuristic that separates the pattern from the action used `\s{2,}`, which did not match a single-tab separator. `{identifier}` tokens inside the C action body (e.g. compound literals) were falsely counted as abbreviation references, suppressing `flex/unused-abbrev`.
+- **Cleanup**: removed two dead entries in the catch-all pattern set that contained a literal newline character and could never match a rule line.
+- **Bison — lowercase/mixed-case tokens in precedence declarations** (audit-E): `%left`/`%right`/`%nonassoc` used an uppercase-only regex `[A-Z_][A-Z0-9_]*`, silently dropping tokens like `kPLUS` or `tTOKEN` from the precedence table. This caused false `bison/undeclared-token` warnings and incorrect shift/reduce heuristic results for such tokens.
+- **Bison — `$N` references after nested sub-blocks in inline actions** (audit-F): the `extractDollarRefs` scanner used `/\{([^}]*)\}/` which stops at the first `}`, missing `$N` references that appear after a nested `{ … }` block inside the same action (e.g. `{ if (cond) { log(); } $$ = $5; }`). Replaced with a brace-depth scanner; the same fix was applied to `extractSymbols`, `getFirstSymbol`, and `extractRuleReferences` for consistency.
+
+---
+
 ## [1.5.0] - 2026-04-01
 
 ### Added
@@ -11,7 +27,7 @@ All notable changes to the **Bison/Flex Language Support** extension will be doc
   - **`Bison/Flex: Show in Generated File`** — from a `.y` / `.l` source, locates the generated file (using `bisonFlex.buildDirectory` setting, CMake detection, Makefile detection, same-directory fallback, then workspace-wide search) and navigates to the matching line. A QuickPick is shown when multiple candidates are found.
   - New setting `bisonFlex.buildDirectory`: optional path to the build output directory, used by **Show in Generated File** to locate generated files when they are not in the same directory as the source.
 
---
+---
 
 ## [1.4.1] - 2026-03-31
 

README.md

@@ -39,6 +39,44 @@ Real-time error detection as you type:
 | Shift/reduce conflict heuristic | |
 | Unknown/invalid directive | |
 
+Every diagnostic carries a **source** field (`bison` / `flex`), a **code slug** (e.g. `bison/unused-token`), and where available a **link** to the GNU documentation — rendered as a clickable `[bison/unused-token]` link in the Problems panel. Unused symbols are rendered greyed-out via `DiagnosticTag.Unnecessary`.
+
+### Fix-it Hints (Quick Fixes)
+
+22 code actions available via the lightbulb (`Ctrl+.`) or directly from the Problems panel:
+
+**Bison** (11 fixes):
+- Insert missing `%%` separator
+- Declare undeclared `%token`
+- Insert `%empty` for empty production
+- Remove unused token declaration
+- Remove unknown directive
+- Add rule stub for missing non-terminal
+- Add `%type <todo>` declaration
+- Remove invalid `%start` / Add `%start` directive
+- Close unclosed `%{` block
+- Migrate Yacc legacy directives (`%error-verbose` → `%define parse.error verbose`, `%name-prefix`, `%pure-parser`, `%binary`)
+
+**Flex** (11 fixes):
+- Insert missing `%%` separator
+- Define abbreviation stub
+- Remove unused abbreviation
+- Remove unused start condition
+- Remove unknown directive
+- Declare `%x SC_NAME` for undefined start condition
+- Remove unused `%option`
+- Remove duplicate `<<EOF>>` rule
+- Add `%option noyywrap`
+- Close unclosed `%{` block
+- Remove inaccessible rule
+
+### Source ↔ Generated File Navigation
+
+Jump between Bison/Flex grammar sources and their generated C files using `#line` directives:
+
+- **Bison/Flex: Show in Source** — from a generated `.tab.c` / `lex.yy.c` file, reads the nearest `#line N "file.y"` directive above the cursor and opens the grammar source at the correct line. Appears in the context menu only when a generated file is detected.
+- **Bison/Flex: Show in Generated File** — from a `.y` / `.l` source, locates the generated file and navigates to the matching line. Searches `bisonFlex.buildDirectory`, then CMake/Makefile detection, then the same directory, then a workspace-wide scan. A QuickPick is shown when multiple candidates are found.
+
 ### Autocompletion
 
 Context-aware suggestions triggered as you type:
@@ -185,6 +223,10 @@ Then press `F5` in VS Code to launch the Extension Development Host.
 | `bisonFlex.showInlayHints` | `boolean` | `true` | Show inline type hints for `$$`/`$1`/`@$` semantic values |
 | `bisonFlex.enableCodeLens` | `boolean` | `true` | Show reference counts and entry-point badges above rules |
 | `bisonFlex.enableCmakeDiagnostics` | `boolean` | `true` | Warn when a `.y`/`.l` file is not referenced in `CMakeLists.txt` |
+| `bisonFlex.minVersionBison` | `string` | `""` | Suppress checks that require a newer Bison version (e.g. `"3.0"`). Fires `bison/feature-requires-version` when a `%define` feature exceeds this version. |
+| `bisonFlex.minVersionFlex` | `string` | `""` | Same as above for Flex. |
+| `bisonFlex.disabledChecks` | `array` | `[]` | Diagnostic code slugs to suppress entirely (e.g. `["bison/shift-reduce", "flex/missing-yywrap"]`). |
+| `bisonFlex.buildDirectory` | `string` | `""` | Path to the build output directory. Used by **Show in Generated File** to locate `.tab.c` / `lex.yy.c` when they are not next to the source. |
 
 ---
 

package-lock.json

@@ -2,7 +2,7 @@
   "name": "bison-flex-lang",
   "displayName": "Bison/Flex Language Support",
   "description": "Full-featured language support for GNU Bison (.y, .yy) and Flex/RE-flex (.l, .ll) — syntax highlighting with embedded C/C++, real-time diagnostics, intelligent autocompletion, and hover documentation for all directives.",
-  "version": "1.5.0",
+  "version": "1.5.1",
   "publisher": "theodevelop",
   "license": "MIT",
   "repository": {

package.json

@@ -166,7 +166,7 @@ export function parseBisonDocument(text: string): BisonDocument {
     const precMatch = trimmed.match(/^%(left|right|nonassoc|precedence)\s+(.*)/);
     if (precMatch) {
       const kind = precMatch[1] as PrecedenceDeclaration['kind'];
-      const rawSymbols = precMatch[2].match(/[A-Z_][A-Z0-9_]*|"[^"]*"/g) || [];
+      const rawSymbols = precMatch[2].match(/[A-Za-z_][A-Za-z0-9_]*|"[^"]*"/g) || [];
       const symbols: string[] = [];
       const symbolRanges: Range[] = [];
       for (const raw of rawSymbols) {
@@ -389,6 +389,33 @@ function replaceStringLiterals(text: string): string {
     .replace(/'((?:[^'\\]|\\.)*)'/g, (_, content) => ` ${strLiteralPlaceholder(`'${content}'`)} `);
 }
 
+/**
+ * Remove all brace-balanced { ... } blocks from `text`, replacing each with `replacement`.
+ * Handles arbitrarily nested braces, unlike /\{[^}]*\}/ which stops at the first `}`.
+ * Unmatched `{` without a closing `}` (e.g. a multi-line action opener on its own line)
+ * are left out of the result — the Phase 3 brace tracker handles them separately.
+ */
+function removeBalancedBraces(text: string, replacement: string = ' '): string {
+  let result = '';
+  let depth = 0;
+  let pendingOpen = false;  // true while inside a block that hasn't been closed yet
+  for (let i = 0; i < text.length; i++) {
+    if (text[i] === '{') {
+      if (depth === 0) pendingOpen = true;
+      depth++;
+    } else if (text[i] === '}') {
+      depth = Math.max(0, depth - 1);
+      if (depth === 0 && pendingOpen) {
+        result += replacement;  // only emit placeholder when the block is fully closed
+        pendingOpen = false;
+      }
+    } else if (depth === 0) {
+      result += text[i];
+    }
+  }
+  return result;
+}
+
 /**
  * Extract all grammar symbols (identifiers) from a production RHS in order.
  *
@@ -399,8 +426,7 @@ function replaceStringLiterals(text: string): string {
  * `"("` apart from `"{"` (both have different placeholders).
  */
 function extractSymbols(text: string): string[] {
-  const cleaned = replaceStringLiterals(text)
-    .replace(/\{[^}]*\}/g, ' __midaction__ ')     // inline actions count as a symbol ($N position)
+  const cleaned = removeBalancedBraces(replaceStringLiterals(text), ' __midaction__ ')  // inline actions count as a symbol ($N position)
     .replace(/%prec\s+\S+/g, ' ')                 // remove %prec TOKEN
     .replace(/%empty/g, ' ')                      // remove %empty
     .replace(/\/\/.*$/g, ' ')                     // remove line comments
@@ -423,8 +449,7 @@ function extractSymbols(text: string): string[] {
  * `__s` (not all-caps) and is therefore not confused with a real terminal.
  */
 function getFirstSymbol(text: string): string | undefined {
-  const cleaned = replaceStringLiterals(text)
-    .replace(/\{[^}]*\}/g, ' ')                   // remove inline actions
+  const cleaned = removeBalancedBraces(replaceStringLiterals(text))   // remove inline actions
     .replace(/%prec\s+\S+/g, ' ')                 // remove %prec TOKEN
     .replace(/%empty/g, ' ')                      // remove %empty
     .replace(/\/\/.*$/g, ' ')                     // remove line comments
@@ -518,15 +543,27 @@ function parseTokenNames(text: string, type: string | undefined, lineNum: number
 
 /**
  * Scan the inline action block(s) on a single line for $n references.
- * Only handles single-line { ... } blocks; multi-line actions are not detected here.
+ * Uses a brace-depth scanner so that $n references appearing after a nested
+ * sub-block (e.g. `{ if (x) { foo(); } $$ = $1; }`) are not missed.
+ * Only handles single-line { ... } blocks; multi-line actions are tracked by
+ * the caller (Phase 3 loop in parseBisonDocument).
  * $$ and $<type>n are deliberately skipped.
  */
 function extractDollarRefs(text: string, lineNum: number, fullLine: string): DollarRef[] {
   const refs: DollarRef[] = [];
-  const actionRegex = /\{([^}]*)\}/g;
-  let actionMatch: RegExpExecArray | null;
-  while ((actionMatch = actionRegex.exec(text)) !== null) {
-    const actionContent = actionMatch[1];
+  let i = 0;
+  while (i < text.length) {
+    if (text[i] !== '{') { i++; continue; }
+    // Found the opening brace of an action block — scan to the matching '}'
+    let depth = 1;
+    let j = i + 1;
+    while (j < text.length && depth > 0) {
+      if (text[j] === '{') depth++;
+      else if (text[j] === '}') depth--;
+      j++;
+    }
+    // text[i+1 .. j-2] is the full content of this balanced action block
+    const actionContent = text.substring(i + 1, j - 1);
     const dollarRegex = /\$(\d+)/g;
     let m: RegExpExecArray | null;
     while ((m = dollarRegex.exec(actionContent)) !== null) {
@@ -540,6 +577,7 @@ function extractDollarRefs(text: string, lineNum: number, fullLine: string): Dol
         range: Range.create(lineNum, col >= 0 ? col : 0, lineNum, (col >= 0 ? col : 0) + fullMatch.length),
       });
     }
+    i = j; // advance past the entire balanced block
   }
   return refs;
 }
@@ -579,9 +617,7 @@ function extractRuleReferences(text: string, lineNum: number, fullLine: string,
 
   // Find identifiers in rule bodies (potential token/nonterminal references)
   // Skip: strings, actions (braces), %prec keyword (but keep its token), %empty, comments
-  const cleaned = text
-    .replace(/"(?:[^"\\]|\\.)*"/g, '')     // remove strings
-    .replace(/\{[^}]*\}/g, '')             // remove inline actions
+  const cleaned = removeBalancedBraces(text.replace(/"(?:[^"\\]|\\.)*"/g, ''))  // remove strings, then inline actions
     .replace(/%prec/g, '')                 // remove %prec keyword (keep the token name)
     .replace(/%empty/g, '')                // remove %empty
     .replace(/\/\/.*$/g, '');              // remove line comments

server/src/parser/bisonParser.ts

@@ -234,7 +234,7 @@ export function parseFlexDocument(text: string): FlexDocument {
       if (closeIdx >= 0) {
         // Collect any additional SC names before the >
         const before = trimmed.substring(0, closeIdx);
-        const moreConds = before.match(/[A-Z_][A-Z0-9_]*/g);
+        const moreConds = before.match(/[A-Za-z_][A-Za-z0-9_]*/g);
         if (moreConds) pendingScHeader += ',' + moreConds.join(',');
         const conds = pendingScHeader.replace(/^,+/, '').split(',').filter(s => s.length > 0);
         pendingScHeader = null;
@@ -246,7 +246,7 @@ export function parseFlexDocument(text: string): FlexDocument {
         }
       } else {
         // Still accumulating conditions from this line
-        const moreConds = trimmed.match(/[A-Z_][A-Z0-9_]*/g);
+        const moreConds = trimmed.match(/[A-Za-z_][A-Za-z0-9_]*/g);
         if (moreConds) pendingScHeader += ',' + moreConds.join(',');
       }
       continue;
@@ -267,10 +267,19 @@ export function parseFlexDocument(text: string): FlexDocument {
       continue;
     }
 
+    // ── Multi-line action opener: bare `{` on its own line ────────────────────
+    // In Flex, the action brace may appear on the line after the pattern.
+    // Treat a standalone `{` as the opening of a C action block, not a rule.
+    if (trimmed === '{') {
+      actionDepth = 1;
+      continue;
+    }
+
     // ── SC block opener: <SC1,SC2>{ ───────────────────────────────────────────
     // Single-line header: <SC1,SC2>{ or <SC1,SC2> {
+    // SC names may be upper or lower case (any valid C identifier).
     {
-      const scBlockMatch = trimmed.match(/^<([A-Z_][A-Z0-9_]*(?:,[A-Z_][A-Z0-9_]*)*)>\s*\{/);
+      const scBlockMatch = trimmed.match(/^<([A-Za-z_][A-Za-z0-9_]*(?:,[A-Za-z_][A-Za-z0-9_]*)*)>\s*\{/);
       if (scBlockMatch) {
         const conds = scBlockMatch[1].split(',');
         scBlockStack.push(conds);
@@ -284,7 +293,7 @@ export function parseFlexDocument(text: string): FlexDocument {
         continue;
       }
       // Multi-line header start: <SC1,   (no closing > on this line)
-      const scMultiStart = trimmed.match(/^<([A-Z_][A-Z0-9_]*(?:,[A-Z_][A-Z0-9_]*)*,\s*)$/);
+      const scMultiStart = trimmed.match(/^<([A-Za-z_][A-Za-z0-9_]*(?:,[A-Za-z_][A-Za-z0-9_]*)*,\s*)$/);
       if (scMultiStart) {
         pendingScHeader = scMultiStart[1].replace(/,\s*$/, '');
         continue;
@@ -293,7 +302,8 @@ export function parseFlexDocument(text: string): FlexDocument {
 
     // ── Extract start condition references: <SC_NAME> or <SC1,SC2> ────────────
     // Exclude <<EOF>> which is a special pattern, not a start condition
-    const scRefs = line.matchAll(/(?<!<)<([A-Z_][A-Z0-9_]*(?:,[A-Z_][A-Z0-9_]*)*)>(?!>)/g);
+    // SC names may be upper or lower case (any valid C identifier).
+    const scRefs = line.matchAll(/(?<!<)<([A-Za-z_][A-Za-z0-9_]*(?:,[A-Za-z_][A-Za-z0-9_]*)*)>(?!>)/g);
     for (const m of scRefs) {
       const conditions = m[1].split(',');
       for (const cond of conditions) {
@@ -311,8 +321,11 @@ export function parseFlexDocument(text: string): FlexDocument {
     const abbrRefs = line.matchAll(/\{([a-zA-Z_][a-zA-Z0-9_]*)\}/g);
     for (const m of abbrRefs) {
       const name = m[1];
-      // Only count as abbreviation ref if it appears before any action block on this line
-      const actionStart = line.indexOf('{', (line.match(/\s{2,}\{/) || { index: line.length }).index || line.length);
+      // Only count as abbreviation ref if it appears before any action block on this line.
+      // If there is no action { on this line (multi-line action), treat actionStart as line.length
+      // so all {name} refs on this line are counted.
+      const actionMatch = line.match(/\s+\{/);
+      const actionStart = actionMatch !== null ? line.indexOf('{', actionMatch.index!) : line.length;
       if (m.index !== undefined && m.index < actionStart) {
         const col = m.index;
         const range = Range.create(i, col, i, col + m[0].length);
@@ -327,7 +340,7 @@ export function parseFlexDocument(text: string): FlexDocument {
     // Start conditions: explicit <SC> prefix on this line PLUS any inherited from <SC>{ block
     const inherited = scBlockStack.length > 0 ? scBlockStack[scBlockStack.length - 1] : [];
     const startConditions: string[] = [...inherited];
-    const scMatch = trimmed.match(/^<([A-Z_][A-Z0-9_]*(?:,[A-Z_][A-Z0-9_]*)*)>/);
+    const scMatch = trimmed.match(/^<([A-Za-z_][A-Za-z0-9_]*(?:,[A-Za-z_][A-Za-z0-9_]*)*)>/);
     if (scMatch) {
       for (const c of scMatch[1].split(',')) {
         if (!startConditions.includes(c)) startConditions.push(c);
@@ -375,7 +388,7 @@ function parseOptions(text: string, lineNum: number, fullLine: string, doc: Flex
 }
 
 function parseStartConditions(text: string, exclusive: boolean, lineNum: number, fullLine: string, doc: FlexDocument): void {
-  const names = text.match(/[A-Z_][A-Z0-9_]*/g);
+  const names = text.match(/[A-Za-z_][A-Za-z0-9_]*/g);
   if (!names) return;
   for (const name of names) {
     const col = fullLine.indexOf(name);