codegraph-java 0.1.0

package/dist/extraction/grammars.js

@@ -0,0 +1,558 @@
+"use strict";
+/**
+ * Grammar Loading and Caching
+ *
+ * Uses web-tree-sitter (WASM) for universal cross-platform support.
+ * Grammars are loaded lazily — only languages actually present in the project
+ * are compiled, keeping V8 WASM memory pressure low on large codebases.
+ */
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.EXTENSION_MAP = void 0;
+exports.isSourceFile = isSourceFile;
+exports.isShopifyLiquidJson = isShopifyLiquidJson;
+exports.isErlangAppFile = isErlangAppFile;
+exports.isPlayRoutesFile = isPlayRoutesFile;
+exports.initGrammars = initGrammars;
+exports.readGrammarWasmBytes = readGrammarWasmBytes;
+exports.loadGrammarsForLanguages = loadGrammarsForLanguages;
+exports.loadAllGrammars = loadAllGrammars;
+exports.isGrammarsInitialized = isGrammarsInitialized;
+exports.getParser = getParser;
+exports.detectLanguage = detectLanguage;
+exports.hasTreeSitterGrammar = hasTreeSitterGrammar;
+exports.isLanguageSupported = isLanguageSupported;
+exports.isGrammarLoaded = isGrammarLoaded;
+exports.isFileLevelOnlyLanguage = isFileLevelOnlyLanguage;
+exports.getSupportedLanguages = getSupportedLanguages;
+exports.resetParser = resetParser;
+exports.clearParserCache = clearParserCache;
+exports.getUnavailableGrammarErrors = getUnavailableGrammarErrors;
+exports.getLanguageDisplayName = getLanguageDisplayName;
+const path = __importStar(require("path"));
+const fsp = __importStar(require("fs/promises"));
+const web_tree_sitter_1 = require("web-tree-sitter");
+/**
+ * WASM filename map — maps each language to its .wasm grammar file
+ * in the tree-sitter-wasms package.
+ *
+ * Java-only build: only `java` ships. Partial so the other GrammarLanguage
+ * keys (still referenced by the type system elsewhere) can be absent.
+ */
+const WASM_GRAMMAR_FILES = {
+    java: 'tree-sitter-java.wasm',
+};
+/**
+ * File extension to Language mapping
+ */
+exports.EXTENSION_MAP = {
+    // Java-only build: the only indexable source extension.
+    '.java': 'java',
+};
+/**
+ * Whether a file is one CodeGraph can parse, based purely on its extension.
+ * This is the single source of truth for "should we index this file" — derived
+ * from EXTENSION_MAP so parser support and indexing selection never drift.
+ *
+ * `overrides` is the project's validated custom extension → language map (from
+ * `codegraph.json`); when present its extensions count as indexable in addition
+ * to the built-ins. Omitting it is byte-identical to the zero-config behavior.
+ */
+function isSourceFile(filePath, overrides) {
+    if (isPlayRoutesFile(filePath))
+        return true; // Play `conf/routes` is extensionless
+    if (isShopifyLiquidJson(filePath))
+        return true; // Shopify OS 2.0 JSON templates / section groups
+    if (isErlangAppFile(filePath))
+        return true; // OTP `.app`/`.app.src` resource files
+    const dot = filePath.lastIndexOf('.');
+    if (dot < 0)
+        return false;
+    const ext = filePath.slice(dot).toLowerCase();
+    return ext in exports.EXTENSION_MAP || (!!overrides && ext in overrides);
+}
+/**
+ * Shopify OS 2.0 JSON template (`templates/*.json`) or section group
+ * (`sections/*.json`) — these reference sections by `"type"`, so the Liquid
+ * extractor links them. (config/ + locales/ JSON have no section refs.)
+ */
+function isShopifyLiquidJson(filePath) {
+    // Allow nested template dirs (`templates/customers/login.json`), not just
+    // top-level (`templates/product.json`).
+    return /(^|\/)(templates|sections)\/.+\.json$/i.test(filePath);
+}
+/**
+ * OTP application resource file: `<app>.app.src` (checked into every rebar3/
+ * erlang.mk app) or its compiled `<app>.app`. Erlang TERMS, not forms — the
+ * grammar parses them as top-level expressions, and the Erlang extractor's
+ * application-tuple handler turns `{mod, {Mod, _}}` and `{applications, […]}`
+ * into entry-module and dependency edges. Routed by full suffix because the
+ * last-dot extension (`.src`) is far too generic for EXTENSION_MAP.
+ */
+function isErlangAppFile(filePath) {
+    return /\.app(?:\.src)?$/i.test(filePath);
+}
+/**
+ * Play Framework routes file: the extensionless `conf/routes` (and included
+ * `conf/*.routes`). No grammar — route extraction is done by the Play framework
+ * resolver, so it's processed through the no-grammar (`yaml`-style) path.
+ */
+function isPlayRoutesFile(filePath) {
+    return (filePath === 'conf/routes' ||
+        filePath.endsWith('/conf/routes') ||
+        filePath.endsWith('.routes'));
+}
+/**
+ * Caches for loaded grammars and parsers
+ */
+const parserCache = new Map();
+const languageCache = new Map();
+const unavailableGrammarErrors = new Map();
+let parserInitialized = false;
+/**
+ * Initialize the tree-sitter WASM runtime. Must be called before loading grammars.
+ * Does NOT load any grammar WASM files — use loadGrammarsForLanguages() for that.
+ * Idempotent — safe to call multiple times.
+ */
+async function initGrammars() {
+    if (parserInitialized)
+        return;
+    await web_tree_sitter_1.Parser.init();
+    parserInitialized = true;
+}
+/**
+ * Grammars that ship their own vendored WASMs under `dist/extraction/wasm/`
+ * (not in tree-sitter-wasms, or the tree-sitter-wasms build is too old).
+ * Lua: tree-sitter-wasms ships an ABI-13 build that corrupts the shared WASM
+ * heap under web-tree-sitter 0.25 (drops nested calls/imports on every file
+ * after the first); we vendor the upstream ABI-15 wasm instead. C#: the
+ * tree-sitter-wasms build (ABI 13) has no primary-constructor support and
+ * parses `class Foo(...)` as an ERROR that swallows the whole class (#237); we
+ * vendor the upstream ABI-15 tree-sitter-c-sharp 0.23.5 wasm, which parses
+ * primary constructors natively. Terraform: tree-sitter-wasms does not ship
+ * HCL/Terraform at all, so we vendor the prebuilt tree-sitter-terraform.wasm
+ * from @tree-sitter-grammars/tree-sitter-hcl 1.2.0 (Apache-2.0) —
+ * byte-identical to the npm package's artifact. ArkTS: tree-sitter-wasms
+ * doesn't ship it either; we vendor the prebuilt tree-sitter-arkts.wasm from
+ * the tree-sitter-arkts 0.2.0 npm package (harmony-contrib/tree-sitter-arkts,
+ * MIT) — byte-identical to the npm tarball's artifact. It extends the
+ * tree-sitter-javascript grammar the same way tree-sitter-typescript does,
+ * adding `struct_declaration` and the `arkui_component_expression` build()
+ * DSL. Nix: tree-sitter-wasms doesn't ship it; we vendor a wasm built from
+ * nix-community/tree-sitter-nix @ 3d0173d (MIT) with tree-sitter-cli 0.25.10
+ * (`generate` + `build --wasm`, ABI 15 — upstream's checked-in parser.c is
+ * still ABI 13; all 54 upstream corpus tests pass on the regenerated parser).
+ *
+ * TypeScript/TSX/JavaScript (+jsx, which shares the javascript grammar): the
+ * tree-sitter-wasms builds are 2023-era (^0.20.x); we vendor wasm built from
+ * the SAME grammar revisions the native extraction kernel compiles
+ * (codegraph-kernel/Cargo.toml), so the kernel path and the wasm fallback
+ * parse identically and per-language routing stays graph-neutral:
+ *   - tree-sitter/tree-sitter-typescript v0.23.2 (f975a62) → typescript + tsx
+ *   - tree-sitter/tree-sitter-javascript v0.25.0 (44c892e) → javascript + jsx
+ *   - tree-sitter/tree-sitter-java v0.23.5 (94703d5) → java
+ *   - tree-sitter/tree-sitter-python v0.23.6 (bffb65a) → python
+ *   - tree-sitter/tree-sitter-go v0.23.4 (3c3775f) → go
+ * Built from each repo's CHECKED-IN parser.c (no `generate`) with
+ * tree-sitter-cli 0.25.10 `build --wasm` — the same tables crates.io compiles
+ * (parser.c sha-matched against the crates.io tarball).
+ * The kernel-grammar-parity test asserts this alignment; bump the crate and
+ * the vendored wasm together.
+ */
+// Java-only build: the only vendored wasm shipped is tree-sitter-java.wasm.
+const VENDORED_WASM_LANGS = new Set(['java']);
+/** Absolute path of a language's grammar WASM (vendored or tree-sitter-wasms). */
+function resolveWasmPath(lang) {
+    const wasmFile = WASM_GRAMMAR_FILES[lang];
+    if (!wasmFile) {
+        throw new Error(`no wasm grammar mapped for language '${lang}' (java-only build)`);
+    }
+    return VENDORED_WASM_LANGS.has(lang)
+        ? path.join(__dirname, 'wasm', wasmFile)
+        : require.resolve(`tree-sitter-wasms/out/${wasmFile}`);
+}
+/**
+ * Expand an index set's languages to the grammars actually needed to parse it.
+ * SFC languages (svelte/vue/astro) have no grammar of their own — their
+ * extractors delegate <script>/frontmatter content to the TS/JS extractor, so
+ * those grammars must be loaded even when no plain .ts/.js file is in the index
+ * set (e.g. a pure-.astro content site). CFML (.cfc/.cfm) likewise delegates
+ * bare-script content, <cfscript> tag bodies, and <cfquery> SQL bodies to the
+ * cfscript/cfquery grammars (see injections.scm in tree-sitter-cfml).
+ */
+function expandGrammarLanguages(languages) {
+    if (languages.some((l) => l === 'svelte' || l === 'vue' || l === 'astro')) {
+        languages = [...languages, 'typescript', 'javascript'];
+    }
+    if (languages.some((l) => l === 'cfml')) {
+        languages = [...languages, 'cfscript', 'cfquery'];
+    }
+    return languages;
+}
+/**
+ * Pre-read the grammar WASM bytes for an index set, keyed by language. The
+ * orchestrator reads each grammar ONCE and hands the bytes to every parse
+ * worker via its `load-grammars` message, so worker spawns/respawns load
+ * grammars from memory instead of re-reading them from disk — on slow storage
+ * (HDD, issue #1231) each respawn's grammar re-read otherwise amplifies the
+ * I/O contention that caused the respawn. Best-effort: a language whose WASM
+ * can't be read here is simply omitted, and the worker falls back to its own
+ * disk load (which surfaces the real error/warning path).
+ */
+async function readGrammarWasmBytes(languages) {
+    const out = {};
+    const toRead = [...new Set(expandGrammarLanguages(languages))].filter((lang) => lang in WASM_GRAMMAR_FILES);
+    for (const lang of toRead) {
+        try {
+            out[lang] = await fsp.readFile(resolveWasmPath(lang));
+        }
+        catch {
+            // fall through — the worker's own load reports the failure
+        }
+    }
+    return out;
+}
+/**
+ * Load grammar WASM files for specific languages only.
+ * Skips languages that are already loaded or have no WASM grammar.
+ * Must be called after initGrammars().
+ *
+ * `wasmBytes` (optional) holds pre-read grammar bytes keyed by language (from
+ * {@link readGrammarWasmBytes}, forwarded through the parse pool); when a
+ * language's bytes are present they're loaded from memory instead of disk.
+ */
+async function loadGrammarsForLanguages(languages, wasmBytes) {
+    if (!parserInitialized) {
+        await initGrammars();
+    }
+    languages = expandGrammarLanguages(languages);
+    // Deduplicate and filter to languages that have WASM grammars and aren't already loaded
+    const toLoad = [...new Set(languages)].filter((lang) => lang in WASM_GRAMMAR_FILES &&
+        !languageCache.has(lang) &&
+        !unavailableGrammarErrors.has(lang));
+    // Load grammars sequentially to avoid web-tree-sitter WASM race condition on Node 20+
+    // See: https://github.com/tree-sitter/tree-sitter/issues/2338
+    for (const lang of toLoad) {
+        try {
+            const bytes = wasmBytes?.[lang];
+            const language = await web_tree_sitter_1.Language.load(bytes ?? resolveWasmPath(lang));
+            languageCache.set(lang, language);
+        }
+        catch (error) {
+            const message = error instanceof Error ? error.message : String(error);
+            console.warn(`[CodeGraph] Failed to load ${lang} grammar — parsing will be unavailable: ${message}`);
+            unavailableGrammarErrors.set(lang, message);
+        }
+    }
+}
+/**
+ * Load ALL grammar WASM files. Convenience function for tests and
+ * backward compatibility. Prefer loadGrammarsForLanguages() in production.
+ */
+async function loadAllGrammars() {
+    const allLanguages = Object.keys(WASM_GRAMMAR_FILES);
+    await loadGrammarsForLanguages(allLanguages);
+}
+/**
+ * Check if grammars have been initialized
+ */
+function isGrammarsInitialized() {
+    return parserInitialized;
+}
+/**
+ * Get a parser for the specified language.
+ * Returns synchronously from pre-loaded cache.
+ */
+function getParser(language) {
+    if (parserCache.has(language)) {
+        return parserCache.get(language);
+    }
+    const lang = languageCache.get(language);
+    if (!lang) {
+        return null;
+    }
+    const parser = new web_tree_sitter_1.Parser();
+    parser.setLanguage(lang);
+    parserCache.set(language, parser);
+    return parser;
+}
+/**
+ * Detect language from file extension.
+ *
+ * `overrides` is the project's validated custom extension → language map (from
+ * `codegraph.json`); when present its mappings take precedence over the built-in
+ * `EXTENSION_MAP`. Omitting it is byte-identical to the zero-config behavior.
+ */
+function detectLanguage(filePath, source, overrides) {
+    // Play `conf/routes` has no grammar — route through the no-symbol path; the
+    // Play framework resolver extracts route nodes from it.
+    if (isPlayRoutesFile(filePath))
+        return 'yaml';
+    const ext = filePath.substring(filePath.lastIndexOf('.')).toLowerCase();
+    // Shopify OS 2.0 JSON templates / section groups → the Liquid extractor (it
+    // links each section `"type"` to its `sections/<type>.liquid`).
+    if (isShopifyLiquidJson(filePath))
+        return 'liquid';
+    // OTP `.app`/`.app.src` resource files — Erlang terms the grammar parses as
+    // top-level expressions (last-dot ext `.src` is too generic for the map).
+    if (isErlangAppFile(filePath))
+        return 'erlang';
+    const lang = (overrides && overrides[ext]) || exports.EXTENSION_MAP[ext] || 'unknown';
+    // .h files could be C, C++, or Objective-C — check source content
+    if (lang === 'c' && ext === '.h' && source) {
+        if (looksLikeCpp(source))
+            return 'cpp';
+        if (looksLikeObjc(source))
+            return 'objc';
+    }
+    return lang;
+}
+/**
+ * A class/struct BASE CLAUSE — `struct Derived : Base {`, `class Foo final :
+ * public Bar, private Baz {`, `struct D : ns::B<T> {` — which is never valid
+ * C. In C the only thing that can follow `struct <tag>` is `{`, `;`, `*`, an
+ * identifier (declarator), or a closing `)`: a bit-field's `:` sits after a
+ * member NAME inside the body (`unsigned a : 3;`), a ternary's `:` is
+ * separated from the tag by `)` / `*` / a declarator (`sizeof(struct foo) :
+ * 0`), and a label such as `struct_end:` has no whitespace after `struct`. An
+ * optional access specifier / `virtual` after the colon and an optional
+ * `final` before it cover the spelled-out forms; the base may be scoped
+ * (`ns::Base`) and carry template arguments, and must be followed by the
+ * body's `{` or a `,` introducing the next base — prose like
+ * `struct timeval: seconds and microseconds` inside a string never has that
+ * terminator. Comments are stripped before the scan (see `looksLikeCpp`).
+ */
+const CPP_BASE_CLAUSE_RE = /\b(?:class|struct)\s+\w+\s*(?:final\s*)?:\s*(?:(?:public|protected|private|virtual)\s+)*[A-Za-z_][\w:]*(?:\s*<[^{};]*>)?\s*[{,]/;
+/** Block and line comments, for a code-only scan. Lazy block match → linear. */
+const C_COMMENT_RE = /\/\*[\s\S]*?\*\/|\/\/[^\n]*/g;
+/**
+ * Heuristic: does a .h file contain C++ constructs?
+ *
+ * Two passes. The first checks the first ~8KB for patterns that are unique to
+ * C++ and never valid C. The second scans the FULL source for a class/struct
+ * base clause (`CPP_BASE_CLAUSE_RE`): a large header with a long C-compatible
+ * preamble — include guards, `#define`s, plain C typedefs — can put its only
+ * C++ signal past the sample, and the cost of that miss is the C extractor
+ * (classTypes: []) dropping the derived type entirely and minting a phantom
+ * `function Base` from the base clause instead (#1592). The base-clause regex
+ * is anchored on a `struct`/`class` keyword followed by a tag and a colon, a
+ * shape with no C reading, so widening it to the whole file cannot drag a C
+ * header over to C++.
+ */
+function looksLikeCpp(source) {
+    const sample = source.substring(0, 8192);
+    // The `class MACRO Name : Base` / `class MACRO Name { … }` branch mirrors what
+    // `blankCppExportMacros` recovers: an ALL-CAPS export/visibility macro
+    // (`ENGINE_API`, `MYMODULE_API`, `*_EXPORT`, …) sitting between `class`/`struct`
+    // and the type name. Without it, a header whose ONLY C++ signal is such a
+    // macro-annotated class — common for lean Unreal-Engine types that carry just
+    // `GENERATED_BODY()` and no explicit `public:`/`virtual` — is misdetected as C,
+    // routed through the C extractor (which extracts no classes), and its class
+    // definition silently vanishes. The two-token shape (`<KW> <MACRO> <Name>`
+    // before a `[:{]`) never occurs in valid C, so this can't misclassify C headers.
+    if (/\bnamespace\b|\bclass\s+\w+\s*[:{]|\b(?:class|struct)\s+[A-Z][A-Z0-9_]+\s+\w+\s*(?:final\s*)?[:{]|\btemplate\s*<|\b(?:public|private|protected)\s*:|\bvirtual\b|\busing\s+(?:namespace\b|\w+\s*=)/.test(sample)) {
+        return true;
+    }
+    // Plain `struct Derived : Base` (no export macro, no `class` keyword, no
+    // explicit access section) — the #1159 branch above only recognizes the
+    // macro-annotated form. Scanned over the whole file, not the sample, with
+    // comments removed so a doc comment's prose (`struct foo: x, y`) can't
+    // flip a C header.
+    return CPP_BASE_CLAUSE_RE.test(source.replace(C_COMMENT_RE, ' '));
+}
+/**
+ * Heuristic: does a .h file contain Objective-C constructs?
+ */
+function looksLikeObjc(source) {
+    const sample = source.substring(0, 8192);
+    return /@(?:interface|implementation|protocol|synthesize)\b/.test(sample);
+}
+/**
+ * Whether a language has a tree-sitter grammar of its own.
+ *
+ * Narrower than {@link isLanguageSupported}, which also answers true for the
+ * formats handled by custom extractors (SFCs, Liquid, Razor, YAML, XML,
+ * properties) — those have extraction but no grammar, so anything that needs to
+ * PARSE the file (the viewer's syntax classification, for one) has to ask this
+ * instead.
+ */
+function hasTreeSitterGrammar(language) {
+    return !!language && language in WASM_GRAMMAR_FILES;
+}
+/**
+ * Check if a language is supported (has a grammar defined).
+ * Returns true if the grammar exists, even if not yet loaded.
+ */
+function isLanguageSupported(language) {
+    if (language === 'svelte')
+        return true; // custom extractor (script block delegation)
+    if (language === 'vue')
+        return true; // custom extractor (script block delegation)
+    if (language === 'astro')
+        return true; // custom extractor (frontmatter/script block delegation)
+    if (language === 'liquid')
+        return true; // custom regex extractor
+    if (language === 'razor')
+        return true; // custom RazorExtractor (.cshtml/.razor markup)
+    if (language === 'yaml')
+        return true; // file-level tracking only; Drupal routing extraction via framework resolver
+    if (language === 'twig')
+        return true; // file-level tracking only
+    if (language === 'xml')
+        return true; // MyBatis mapper extractor
+    if (language === 'properties')
+        return true; // Spring config keys
+    if (language === 'unknown')
+        return false;
+    return language in WASM_GRAMMAR_FILES;
+}
+/**
+ * Check if a grammar has been loaded and is ready for parsing.
+ */
+function isGrammarLoaded(language) {
+    if (language === 'svelte' || language === 'vue' || language === 'astro' || language === 'liquid' || language === 'razor')
+        return true;
+    if (language === 'yaml' || language === 'twig')
+        return true; // no WASM grammar needed
+    if (language === 'xml' || language === 'properties')
+        return true; // no WASM grammar needed
+    return languageCache.has(language);
+}
+/**
+ * Languages tracked at the file-record level only: parsing emits zero symbol
+ * nodes, but the file is still stored (and framework resolvers may add per-file
+ * references later, e.g. Drupal routing yml, Spring `@Value` against
+ * application.properties). This is the canonical set behind the no-symbol
+ * branch in `tree-sitter.ts`; `xml` is intentionally excluded because its
+ * MyBatis extractor emits a file node. Callers use this to count such files as
+ * indexed rather than skipped, so it must stay in sync with that branch.
+ */
+function isFileLevelOnlyLanguage(language) {
+    return language === 'yaml' || language === 'twig' || language === 'properties';
+}
+/**
+ * Get all supported languages (those with grammar definitions).
+ */
+function getSupportedLanguages() {
+    // Java-only build: keys of WASM_GRAMMAR_FILES (= ['java']).
+    return Object.keys(WASM_GRAMMAR_FILES);
+}
+/**
+ * Reset the cached parser for a language to reclaim WASM heap memory.
+ * The tree-sitter WASM runtime accumulates fragmented memory over thousands
+ * of parses. Deleting and recreating the Parser instance forces the WASM
+ * heap to reset, preventing "memory access out of bounds" crashes in
+ * large repos.
+ */
+function resetParser(language) {
+    const old = parserCache.get(language);
+    if (old) {
+        old.delete();
+        parserCache.delete(language);
+    }
+}
+/**
+ * Clear parser/grammar caches (useful for testing)
+ */
+function clearParserCache() {
+    for (const parser of parserCache.values()) {
+        parser.delete();
+    }
+    parserCache.clear();
+    // Note: languageCache is NOT cleared — WASM languages persist.
+    // To fully re-init, set parserInitialized = false and call initGrammars() again.
+    unavailableGrammarErrors.clear();
+}
+/**
+ * Report grammars that failed to load.
+ */
+function getUnavailableGrammarErrors() {
+    const out = {};
+    for (const [language, message] of unavailableGrammarErrors.entries()) {
+        out[language] = message;
+    }
+    return out;
+}
+/**
+ * Get language display name
+ */
+function getLanguageDisplayName(language) {
+    const names = {
+        typescript: 'TypeScript',
+        javascript: 'JavaScript',
+        tsx: 'TypeScript (TSX)',
+        jsx: 'JavaScript (JSX)',
+        python: 'Python',
+        go: 'Go',
+        rust: 'Rust',
+        r: 'R',
+        java: 'Java',
+        c: 'C',
+        cpp: 'C++',
+        csharp: 'C#',
+        razor: 'Razor/Blazor',
+        php: 'PHP',
+        ruby: 'Ruby',
+        swift: 'Swift',
+        kotlin: 'Kotlin',
+        dart: 'Dart',
+        svelte: 'Svelte',
+        vue: 'Vue',
+        astro: 'Astro',
+        liquid: 'Liquid',
+        pascal: 'Pascal / Delphi',
+        scala: 'Scala',
+        lua: 'Lua',
+        luau: 'Luau',
+        objc: 'Objective-C',
+        solidity: 'Solidity',
+        nix: 'Nix',
+        yaml: 'YAML',
+        twig: 'Twig',
+        xml: 'XML',
+        properties: 'Java properties',
+        cfml: 'CFML',
+        cfscript: 'CFScript',
+        cfquery: 'CFQuery (SQL)',
+        cobol: 'COBOL',
+        vbnet: 'Visual Basic .NET',
+        erlang: 'Erlang',
+        terraform: 'Terraform',
+        arkts: 'ArkTS',
+        unknown: 'Unknown',
+    };
+    return names[language] || language;
+}
+//# sourceMappingURL=grammars.js.map

package/dist/extraction/grammars.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"grammars.js","sourceRoot":"","sources":["../../src/extraction/grammars.ts"],"names":[],"mappings":";AAAA;;;;;;GAMG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAqCH,oCAQC;AAOD,kDAIC;AAUD,0CAEC;AAOD,4CAMC;AAgBD,oCAMC;AAoFD,oDAaC;AAWD,4DA4BC;AAMD,0CAGC;AAKD,sDAEC;AAMD,8BAcC;AASD,wCAoBC;AA4ED,oDAEC;AAMD,kDAYC;AAKD,0CAKC;AAWD,0DAEC;AAKD,sDAGC;AASD,kCAMC;AAKD,4CAQC;AAKD,kEAMC;AAKD,wDA8CC;AAvgBD,2CAA6B;AAC7B,iDAAmC;AACnC,qDAAmE;AAKnE;;;;;;GAMG;AACH,MAAM,kBAAkB,GAA6C;IACnE,IAAI,EAAE,uBAAuB;CAC9B,CAAC;AAEF;;GAEG;AACU,QAAA,aAAa,GAA6B;IACrD,wDAAwD;IACxD,OAAO,EAAE,MAAM;CAChB,CAAC;AAEF;;;;;;;;GAQG;AACH,SAAgB,YAAY,CAAC,QAAgB,EAAE,SAAoC;IACjF,IAAI,gBAAgB,CAAC,QAAQ,CAAC;QAAE,OAAO,IAAI,CAAC,CAAC,sCAAsC;IACnF,IAAI,mBAAmB,CAAC,QAAQ,CAAC;QAAE,OAAO,IAAI,CAAC,CAAC,iDAAiD;IACjG,IAAI,eAAe,CAAC,QAAQ,CAAC;QAAE,OAAO,IAAI,CAAC,CAAC,uCAAuC;IACnF,MAAM,GAAG,GAAG,QAAQ,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;IACtC,IAAI,GAAG,GAAG,CAAC;QAAE,OAAO,KAAK,CAAC;IAC1B,MAAM,GAAG,GAAG,QAAQ,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,WAAW,EAAE,CAAC;IAC9C,OAAO,GAAG,IAAI,qBAAa,IAAI,CAAC,CAAC,CAAC,SAAS,IAAI,GAAG,IAAI,SAAS,CAAC,CAAC;AACnE,CAAC;AAED;;;;GAIG;AACH,SAAgB,mBAAmB,CAAC,QAAgB;IAClD,0EAA0E;IAC1E,wCAAwC;IACxC,OAAO,wCAAwC,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;AACjE,CAAC;AAED;;;;;;;GAOG;AACH,SAAgB,eAAe,CAAC,QAAgB;IAC9C,OAAO,mBAAmB,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;AAC5C,CAAC;AAED;;;;GAIG;AACH,SAAgB,gBAAgB,CAAC,QAAgB;IAC/C,OAAO,CACL,QAAQ,KAAK,aAAa;QAC1B,QAAQ,CAAC,QAAQ,CAAC,cAAc,CAAC;QACjC,QAAQ,CAAC,QAAQ,CAAC,SAAS,CAAC,CAC7B,CAAC;AACJ,CAAC;AAED;;GAEG;AACH,MAAM,WAAW,GAAG,IAAI,GAAG,EAAoB,CAAC;AAChD,MAAM,aAAa,GAAG,IAAI,GAAG,EAA0B,CAAC;AACxD,MAAM,wBAAwB,GAAG,IAAI,GAAG,EAAoB,CAAC;AAE7D,IAAI,iBAAiB,GAAG,KAAK,CAAC;AAE9B;;;;GAIG;AACI,KAAK,UAAU,YAAY;IAChC,IAAI,iBAAiB;QAAE,OAAO;IAE9B,MAAM,wBAAM,CAAC,IAAI,EAAE,CAAC;IAEpB,iBAAiB,GAAG,IAAI,CAAC;AAC3B,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAsCG;AACH,4EAA4E;AAC5E,MAAM,mBAAmB,GAAiC,IAAI,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC;AAE5E,kFAAkF;AAClF,SAAS,eAAe,CAAC,IAAqB;IAC5C,MAAM,QAAQ,GAAG,kBAAkB,CAAC,IAAI,CAAC,CAAC;IAC1C,IAAI,CAAC,QAAQ,EAAE,CAAC;QACd,MAAM,IAAI,KAAK,CAAC,wCAAwC,IAAI,qBAAqB,CAAC,CAAC;IACrF,CAAC;IACD,OAAO,mBAAmB,CAAC,GAAG,CAAC,IAAI,CAAC;QAClC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,MAAM,EAAE,QAAQ,CAAC;QACxC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,yBAAyB,QAAQ,EAAE,CAAC,CAAC;AAC3D,CAAC;AAED;;;;;;;;GAQG;AACH,SAAS,sBAAsB,CAAC,SAAqB;IACnD,IAAI,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,QAAQ,IAAI,CAAC,KAAK,KAAK,IAAI,CAAC,KAAK,OAAO,CAAC,EAAE,CAAC;QAC1E,SAAS,GAAG,CAAC,GAAG,SAAS,EAAE,YAAY,EAAE,YAAY,CAAC,CAAC;IACzD,CAAC;IACD,IAAI,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,MAAM,CAAC,EAAE,CAAC;QACxC,SAAS,GAAG,CAAC,GAAG,SAAS,EAAE,UAAU,EAAE,SAAS,CAAC,CAAC;IACpD,CAAC;IACD,OAAO,SAAS,CAAC;AACnB,CAAC;AAED;;;;;;;;;GASG;AACI,KAAK,UAAU,oBAAoB,CAAC,SAAqB;IAC9D,MAAM,GAAG,GAA+B,EAAE,CAAC;IAC3C,MAAM,MAAM,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,sBAAsB,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,MAAM,CACnE,CAAC,IAAI,EAA2B,EAAE,CAAC,IAAI,IAAI,kBAAkB,CAC9D,CAAC;IACF,KAAK,MAAM,IAAI,IAAI,MAAM,EAAE,CAAC;QAC1B,IAAI,CAAC;YACH,GAAG,CAAC,IAAI,CAAC,GAAG,MAAM,GAAG,CAAC,QAAQ,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC;QACxD,CAAC;QAAC,MAAM,CAAC;YACP,2DAA2D;QAC7D,CAAC;IACH,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED;;;;;;;;GAQG;AACI,KAAK,UAAU,wBAAwB,CAAC,SAAqB,EAAE,SAAsC;IAC1G,IAAI,CAAC,iBAAiB,EAAE,CAAC;QACvB,MAAM,YAAY,EAAE,CAAC;IACvB,CAAC;IAED,SAAS,GAAG,sBAAsB,CAAC,SAAS,CAAC,CAAC;IAE9C,wFAAwF;IACxF,MAAM,MAAM,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAC3C,CAAC,IAAI,EAA2B,EAAE,CAChC,IAAI,IAAI,kBAAkB;QAC1B,CAAC,aAAa,CAAC,GAAG,CAAC,IAAI,CAAC;QACxB,CAAC,wBAAwB,CAAC,GAAG,CAAC,IAAI,CAAC,CACtC,CAAC;IAEF,sFAAsF;IACtF,8DAA8D;IAC9D,KAAK,MAAM,IAAI,IAAI,MAAM,EAAE,CAAC;QAC1B,IAAI,CAAC;YACH,MAAM,KAAK,GAAG,SAAS,EAAE,CAAC,IAAI,CAAC,CAAC;YAChC,MAAM,QAAQ,GAAG,MAAM,0BAAY,CAAC,IAAI,CAAC,KAAK,IAAI,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC;YACzE,aAAa,CAAC,GAAG,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;QACpC,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,MAAM,OAAO,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;YACvE,OAAO,CAAC,IAAI,CAAC,8BAA8B,IAAI,2CAA2C,OAAO,EAAE,CAAC,CAAC;YACrG,wBAAwB,CAAC,GAAG,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC;QAC9C,CAAC;IACH,CAAC;AACH,CAAC;AAED;;;GAGG;AACI,KAAK,UAAU,eAAe;IACnC,MAAM,YAAY,GAAG,MAAM,CAAC,IAAI,CAAC,kBAAkB,CAAsB,CAAC;IAC1E,MAAM,wBAAwB,CAAC,YAAY,CAAC,CAAC;AAC/C,CAAC;AAED;;GAEG;AACH,SAAgB,qBAAqB;IACnC,OAAO,iBAAiB,CAAC;AAC3B,CAAC;AAED;;;GAGG;AACH,SAAgB,SAAS,CAAC,QAAkB;IAC1C,IAAI,WAAW,CAAC,GAAG,CAAC,QAAQ,CAAC,EAAE,CAAC;QAC9B,OAAO,WAAW,CAAC,GAAG,CAAC,QAAQ,CAAE,CAAC;IACpC,CAAC;IAED,MAAM,IAAI,GAAG,aAAa,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;IACzC,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,OAAO,IAAI,CAAC;IACd,CAAC;IAED,MAAM,MAAM,GAAG,IAAI,wBAAM,EAAE,CAAC;IAC5B,MAAM,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC;IACzB,WAAW,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC;IAClC,OAAO,MAAM,CAAC;AAChB,CAAC;AAED;;;;;;GAMG;AACH,SAAgB,cAAc,CAAC,QAAgB,EAAE,MAAe,EAAE,SAAoC;IACpG,4EAA4E;IAC5E,wDAAwD;IACxD,IAAI,gBAAgB,CAAC,QAAQ,CAAC;QAAE,OAAO,MAAM,CAAC;IAC9C,MAAM,GAAG,GAAG,QAAQ,CAAC,SAAS,CAAC,QAAQ,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC;IACxE,4EAA4E;IAC5E,gEAAgE;IAChE,IAAI,mBAAmB,CAAC,QAAQ,CAAC;QAAE,OAAO,QAAQ,CAAC;IACnD,4EAA4E;IAC5E,0EAA0E;IAC1E,IAAI,eAAe,CAAC,QAAQ,CAAC;QAAE,OAAO,QAAQ,CAAC;IAC/C,MAAM,IAAI,GAAG,CAAC,SAAS,IAAI,SAAS,CAAC,GAAG,CAAC,CAAC,IAAI,qBAAa,CAAC,GAAG,CAAC,IAAI,SAAS,CAAC;IAE9E,kEAAkE;IAClE,IAAI,IAAI,KAAK,GAAG,IAAI,GAAG,KAAK,IAAI,IAAI,MAAM,EAAE,CAAC;QAC3C,IAAI,YAAY,CAAC,MAAM,CAAC;YAAE,OAAO,KAAK,CAAC;QACvC,IAAI,aAAa,CAAC,MAAM,CAAC;YAAE,OAAO,MAAM,CAAC;IAC3C,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;;;;;;;;;;;;;GAcG;AACH,MAAM,kBAAkB,GACtB,iIAAiI,CAAC;AAEpI,gFAAgF;AAChF,MAAM,YAAY,GAAG,8BAA8B,CAAC;AAEpD;;;;;;;;;;;;;GAaG;AACH,SAAS,YAAY,CAAC,MAAc;IAClC,MAAM,MAAM,GAAG,MAAM,CAAC,SAAS,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC;IACzC,+EAA+E;IAC/E,uEAAuE;IACvE,iFAAiF;IACjF,0EAA0E;IAC1E,8EAA8E;IAC9E,gFAAgF;IAChF,4EAA4E;IAC5E,2EAA2E;IAC3E,iFAAiF;IACjF,IAAI,mMAAmM,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;QACrN,OAAO,IAAI,CAAC;IACd,CAAC;IACD,yEAAyE;IACzE,wEAAwE;IACxE,0EAA0E;IAC1E,uEAAuE;IACvE,mBAAmB;IACnB,OAAO,kBAAkB,CAAC,IAAI,CAAC,MAAM,CAAC,OAAO,CAAC,YAAY,EAAE,GAAG,CAAC,CAAC,CAAC;AACpE,CAAC;AAED;;GAEG;AACH,SAAS,aAAa,CAAC,MAAc;IACnC,MAAM,MAAM,GAAG,MAAM,CAAC,SAAS,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC;IACzC,OAAO,qDAAqD,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;AAC5E,CAAC;AAED;;;;;;;;GAQG;AACH,SAAgB,oBAAoB,CAAC,QAAmC;IACtE,OAAO,CAAC,CAAC,QAAQ,IAAI,QAAQ,IAAI,kBAAkB,CAAC;AACtD,CAAC;AAED;;;GAGG;AACH,SAAgB,mBAAmB,CAAC,QAAkB;IACpD,IAAI,QAAQ,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAC,CAAC,6CAA6C;IACrF,IAAI,QAAQ,KAAK,KAAK;QAAE,OAAO,IAAI,CAAC,CAAC,6CAA6C;IAClF,IAAI,QAAQ,KAAK,OAAO;QAAE,OAAO,IAAI,CAAC,CAAC,yDAAyD;IAChG,IAAI,QAAQ,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAC,CAAC,yBAAyB;IACjE,IAAI,QAAQ,KAAK,OAAO;QAAE,OAAO,IAAI,CAAC,CAAC,gDAAgD;IACvF,IAAI,QAAQ,KAAK,MAAM;QAAE,OAAO,IAAI,CAAC,CAAC,6EAA6E;IACnH,IAAI,QAAQ,KAAK,MAAM;QAAE,OAAO,IAAI,CAAC,CAAC,2BAA2B;IACjE,IAAI,QAAQ,KAAK,KAAK;QAAE,OAAO,IAAI,CAAC,CAAC,2BAA2B;IAChE,IAAI,QAAQ,KAAK,YAAY;QAAE,OAAO,IAAI,CAAC,CAAC,qBAAqB;IACjE,IAAI,QAAQ,KAAK,SAAS;QAAE,OAAO,KAAK,CAAC;IACzC,OAAO,QAAQ,IAAI,kBAAkB,CAAC;AACxC,CAAC;AAED;;GAEG;AACH,SAAgB,eAAe,CAAC,QAAkB;IAChD,IAAI,QAAQ,KAAK,QAAQ,IAAI,QAAQ,KAAK,KAAK,IAAI,QAAQ,KAAK,OAAO,IAAI,QAAQ,KAAK,QAAQ,IAAI,QAAQ,KAAK,OAAO;QAAE,OAAO,IAAI,CAAC;IACtI,IAAI,QAAQ,KAAK,MAAM,IAAI,QAAQ,KAAK,MAAM;QAAE,OAAO,IAAI,CAAC,CAAC,yBAAyB;IACtF,IAAI,QAAQ,KAAK,KAAK,IAAI,QAAQ,KAAK,YAAY;QAAE,OAAO,IAAI,CAAC,CAAC,yBAAyB;IAC3F,OAAO,aAAa,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;AACrC,CAAC;AAED;;;;;;;;GAQG;AACH,SAAgB,uBAAuB,CAAC,QAAkB;IACxD,OAAO,QAAQ,KAAK,MAAM,IAAI,QAAQ,KAAK,MAAM,IAAI,QAAQ,KAAK,YAAY,CAAC;AACjF,CAAC;AAED;;GAEG;AACH,SAAgB,qBAAqB;IACnC,4DAA4D;IAC5D,OAAO,MAAM,CAAC,IAAI,CAAC,kBAAkB,CAAe,CAAC;AACvD,CAAC;AAED;;;;;;GAMG;AACH,SAAgB,WAAW,CAAC,QAAkB;IAC5C,MAAM,GAAG,GAAG,WAAW,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;IACtC,IAAI,GAAG,EAAE,CAAC;QACR,GAAG,CAAC,MAAM,EAAE,CAAC;QACb,WAAW,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;IAC/B,CAAC;AACH,CAAC;AAED;;GAEG;AACH,SAAgB,gBAAgB;IAC9B,KAAK,MAAM,MAAM,IAAI,WAAW,CAAC,MAAM,EAAE,EAAE,CAAC;QAC1C,MAAM,CAAC,MAAM,EAAE,CAAC;IAClB,CAAC;IACD,WAAW,CAAC,KAAK,EAAE,CAAC;IACpB,+DAA+D;IAC/D,iFAAiF;IACjF,wBAAwB,CAAC,KAAK,EAAE,CAAC;AACnC,CAAC;AAED;;GAEG;AACH,SAAgB,2BAA2B;IACzC,MAAM,GAAG,GAAsC,EAAE,CAAC;IAClD,KAAK,MAAM,CAAC,QAAQ,EAAE,OAAO,CAAC,IAAI,wBAAwB,CAAC,OAAO,EAAE,EAAE,CAAC;QACrE,GAAG,CAAC,QAAQ,CAAC,GAAG,OAAO,CAAC;IAC1B,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED;;GAEG;AACH,SAAgB,sBAAsB,CAAC,QAAkB;IACvD,MAAM,KAAK,GAA6B;QACtC,UAAU,EAAE,YAAY;QACxB,UAAU,EAAE,YAAY;QACxB,GAAG,EAAE,kBAAkB;QACvB,GAAG,EAAE,kBAAkB;QACvB,MAAM,EAAE,QAAQ;QAChB,EAAE,EAAE,IAAI;QACR,IAAI,EAAE,MAAM;QACZ,CAAC,EAAE,GAAG;QACN,IAAI,EAAE,MAAM;QACZ,CAAC,EAAE,GAAG;QACN,GAAG,EAAE,KAAK;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,cAAc;QACrB,GAAG,EAAE,KAAK;QACV,IAAI,EAAE,MAAM;QACZ,KAAK,EAAE,OAAO;QACd,MAAM,EAAE,QAAQ;QAChB,IAAI,EAAE,MAAM;QACZ,MAAM,EAAE,QAAQ;QAChB,GAAG,EAAE,KAAK;QACV,KAAK,EAAE,OAAO;QACd,MAAM,EAAE,QAAQ;QAChB,MAAM,EAAE,iBAAiB;QACzB,KAAK,EAAE,OAAO;QACd,GAAG,EAAE,KAAK;QACV,IAAI,EAAE,MAAM;QACZ,IAAI,EAAE,aAAa;QACnB,QAAQ,EAAE,UAAU;QACpB,GAAG,EAAE,KAAK;QACV,IAAI,EAAE,MAAM;QACZ,IAAI,EAAE,MAAM;QACZ,GAAG,EAAE,KAAK;QACV,UAAU,EAAE,iBAAiB;QAC7B,IAAI,EAAE,MAAM;QACZ,QAAQ,EAAE,UAAU;QACpB,OAAO,EAAE,eAAe;QACxB,KAAK,EAAE,OAAO;QACd,KAAK,EAAE,mBAAmB;QAC1B,MAAM,EAAE,QAAQ;QAChB,SAAS,EAAE,WAAW;QACtB,KAAK,EAAE,OAAO;QACd,OAAO,EAAE,SAAS;KACnB,CAAC;IACF,OAAO,KAAK,CAAC,QAAQ,CAAC,IAAI,QAAQ,CAAC;AACrC,CAAC"}