@saluzi/codegraph 0.2.0 → 0.2.1

package/dist/extraction/astro-extractor.js

@@ -0,0 +1,320 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.AstroExtractor = void 0;
+const tree_sitter_helpers_1 = require("./tree-sitter-helpers");
+const tree_sitter_1 = require("./tree-sitter");
+const grammars_1 = require("./grammars");
+/**
+ * Astro built-in components — compiler-provided (`<Fragment>`) or shipped by
+ * `astro:components` (`<Code>`, `<Debug>`), not user code.
+ */
+const ASTRO_BUILTIN_COMPONENTS = new Set(['Fragment', 'Code', 'Debug']);
+/**
+ * AstroExtractor - Extracts code relationships from Astro component files
+ *
+ * Astro files are multi-language: a TypeScript frontmatter block fenced by
+ * `---` lines, a JSX-like HTML template, and optional <script>/<style> blocks.
+ * Rather than parsing a full Astro grammar, we extract the frontmatter and
+ * <script> contents and delegate them to the TypeScript TreeSitterExtractor
+ * (Astro processes both as TypeScript by default — no `lang` attr needed).
+ *
+ * Also extracts function calls from template expressions (`{fn(...)}`) and
+ * component usages (`<PascalCase>`) so cross-file edges are captured even
+ * when the only reference lives in markup.
+ *
+ * Every .astro file produces a component node (Astro components are always
+ * importable).
+ */
+class AstroExtractor {
+    filePath;
+    source;
+    nodes = [];
+    edges = [];
+    unresolvedReferences = [];
+    errors = [];
+    constructor(filePath, source) {
+        this.filePath = filePath;
+        this.source = source;
+    }
+    /**
+     * Extract from Astro source
+     */
+    extract() {
+        const startTime = Date.now();
+        try {
+            // Create component node for the .astro file itself
+            const componentNode = this.createComponentNode();
+            // Extract and process the frontmatter block (--- fenced, TypeScript)
+            const frontmatter = this.extractFrontmatter();
+            if (frontmatter) {
+                this.processScriptContent(frontmatter, componentNode.id, 'frontmatter');
+            }
+            // Extract and process <script> blocks (client-side, TypeScript-capable)
+            for (const block of this.extractScriptBlocks()) {
+                this.processScriptContent(block, componentNode.id, 'script');
+            }
+            // Ranges the template scans must skip: frontmatter + <script>/<style>
+            const coveredRanges = this.getCoveredRanges(frontmatter);
+            // Extract function calls from template expressions ({fn(...)})
+            this.extractTemplateCalls(componentNode.id, coveredRanges);
+            // Extract component usages from template (<ComponentName>)
+            this.extractTemplateComponents(componentNode.id, coveredRanges);
+        }
+        catch (error) {
+            this.errors.push({
+                message: `Astro extraction error: ${error instanceof Error ? error.message : String(error)}`,
+                severity: 'error',
+                code: 'parse_error',
+            });
+        }
+        return {
+            nodes: this.nodes,
+            edges: this.edges,
+            unresolvedReferences: this.unresolvedReferences,
+            errors: this.errors,
+            durationMs: Date.now() - startTime,
+        };
+    }
+    /**
+     * Create a component node for the .astro file
+     */
+    createComponentNode() {
+        const lines = this.source.split('\n');
+        const fileName = this.filePath.split(/[/\\]/).pop() || this.filePath;
+        const componentName = fileName.replace(/\.astro$/, '');
+        const id = (0, tree_sitter_helpers_1.generateNodeId)(this.filePath, 'component', componentName, 1);
+        const node = {
+            id,
+            kind: 'component',
+            name: componentName,
+            qualifiedName: `${this.filePath}::${componentName}`,
+            filePath: this.filePath,
+            language: 'astro',
+            startLine: 1,
+            endLine: lines.length,
+            startColumn: 0,
+            endColumn: lines[lines.length - 1]?.length || 0,
+            isExported: true, // Astro components are always importable
+            updatedAt: Date.now(),
+        };
+        this.nodes.push(node);
+        return node;
+    }
+    /**
+     * Extract the frontmatter block: the content between the opening `---`
+     * fence (first non-blank line of the file) and the closing `---` fence.
+     * An unclosed fence is treated as "no frontmatter" rather than swallowing
+     * the whole template as TypeScript.
+     *
+     * Returns the content plus its 0-indexed start line, or null.
+     */
+    extractFrontmatter() {
+        const lines = this.source.split('\n');
+        // Opening fence must be the first non-blank line
+        let openIdx = -1;
+        for (let i = 0; i < lines.length; i++) {
+            const trimmed = lines[i].trim();
+            if (trimmed === '')
+                continue;
+            if (trimmed === '---')
+                openIdx = i;
+            break;
+        }
+        if (openIdx === -1)
+            return null;
+        // Closing fence
+        let closeIdx = -1;
+        for (let i = openIdx + 1; i < lines.length; i++) {
+            if (lines[i].trim() === '---') {
+                closeIdx = i;
+                break;
+            }
+        }
+        if (closeIdx === -1)
+            return null;
+        return {
+            content: lines.slice(openIdx + 1, closeIdx).join('\n'),
+            startLine: openIdx + 1, // 0-indexed line where content starts
+            endLine: closeIdx, // 0-indexed line of the closing fence
+        };
+    }
+    /**
+     * Extract <script> blocks from the template portion
+     */
+    extractScriptBlocks() {
+        const blocks = [];
+        const scriptRegex = /<script(\s[^>]*)?>(?<content>[\s\S]*?)<\/script>/g;
+        let match;
+        while ((match = scriptRegex.exec(this.source)) !== null) {
+            const content = match.groups?.content || match[2] || '';
+            // Calculate the 0-indexed line where the content begins. The content
+            // starts right after the opening tag's `>` — its leading `\n` is part
+            // of the content, so relative line 1 sits ON the tag's closing line
+            // (do not add 1 here; that double-counts the embedded newline).
+            const beforeScript = this.source.substring(0, match.index);
+            const scriptTagLine = (beforeScript.match(/\n/g) || []).length;
+            const openingTag = match[0].substring(0, match[0].indexOf('>') + 1);
+            const openingTagLines = (openingTag.match(/\n/g) || []).length;
+            const contentStartLine = scriptTagLine + openingTagLines; // 0-indexed
+            blocks.push({ content, startLine: contentStartLine });
+        }
+        return blocks;
+    }
+    /**
+     * Process frontmatter / script content by delegating to TreeSitterExtractor.
+     * Astro treats both as TypeScript by default.
+     */
+    processScriptContent(block, componentNodeId, label) {
+        if (!(0, grammars_1.isLanguageSupported)('typescript')) {
+            this.errors.push({
+                message: `Parser for typescript not available, cannot parse Astro ${label} block`,
+                severity: 'warning',
+            });
+            return;
+        }
+        // Delegate to TreeSitterExtractor
+        const extractor = new tree_sitter_1.TreeSitterExtractor(this.filePath, block.content, 'typescript');
+        const result = extractor.extract();
+        // Offset line numbers from the block back to .astro file positions
+        for (const node of result.nodes) {
+            node.startLine += block.startLine;
+            node.endLine += block.startLine;
+            node.language = 'astro'; // Mark as astro, not TS
+            this.nodes.push(node);
+            // Add containment edge from component to this node
+            this.edges.push({
+                source: componentNodeId,
+                target: node.id,
+                kind: 'contains',
+            });
+        }
+        // Offset edges (they reference line numbers)
+        for (const edge of result.edges) {
+            if (edge.line) {
+                edge.line += block.startLine;
+            }
+            this.edges.push(edge);
+        }
+        // Offset unresolved references
+        for (const ref of result.unresolvedReferences) {
+            ref.line += block.startLine;
+            ref.filePath = this.filePath;
+            ref.language = 'astro';
+            this.unresolvedReferences.push(ref);
+        }
+        // Carry over errors
+        for (const error of result.errors) {
+            if (error.line) {
+                error.line += block.startLine;
+            }
+            this.errors.push(error);
+        }
+    }
+    /**
+     * Line ranges (0-indexed, inclusive) the template scans must skip:
+     * the frontmatter block and <script>/<style> blocks.
+     */
+    getCoveredRanges(frontmatter) {
+        const coveredRanges = [];
+        if (frontmatter) {
+            // Cover from the opening fence line through the closing fence line
+            coveredRanges.push([frontmatter.startLine - 1, frontmatter.endLine]);
+        }
+        const tagRegex = /<(script|style)(\s[^>]*)?>[\s\S]*?<\/\1>/g;
+        let tagMatch;
+        while ((tagMatch = tagRegex.exec(this.source)) !== null) {
+            const startLine = (this.source.substring(0, tagMatch.index).match(/\n/g) || []).length;
+            const endLine = startLine + (tagMatch[0].match(/\n/g) || []).length;
+            coveredRanges.push([startLine, endLine]);
+        }
+        return coveredRanges;
+    }
+    /**
+     * Extract function calls from Astro template expressions.
+     *
+     * Astro templates embed JSX-like expressions (`{formatDate(post.date)}`,
+     * `class:list={cn(...)}`), so calls frequently live in markup rather than
+     * the frontmatter. We scan template lines for `{expression}` groups and
+     * extract call patterns from them. A `{` group left open at end-of-line
+     * (the pervasive `{posts.map((post) => (` pattern) contributes the calls
+     * on its opening line.
+     */
+    extractTemplateCalls(componentNodeId, coveredRanges) {
+        const lines = this.source.split('\n');
+        // Complete groups: {...} — excluding JSX comments ({/* ... */})
+        const exprRegex = /\{([^}/][^}]*)\}/g;
+        // A group opened but not closed on this line
+        const openExprRegex = /\{([^}/][^}]*)$/;
+        for (let lineIdx = 0; lineIdx < lines.length; lineIdx++) {
+            if (coveredRanges.some(([start, end]) => lineIdx >= start && lineIdx <= end))
+                continue;
+            const line = lines[lineIdx];
+            const exprs = [];
+            let exprMatch;
+            while ((exprMatch = exprRegex.exec(line)) !== null) {
+                exprs.push({ text: exprMatch[1], offset: exprMatch.index });
+            }
+            const openMatch = openExprRegex.exec(line.replace(exprRegex, ''));
+            if (openMatch) {
+                exprs.push({ text: openMatch[1], offset: line.lastIndexOf('{') });
+            }
+            for (const expr of exprs) {
+                // Extract function calls: identifiers followed by (
+                // Matches: cn(...), formatDate(...), obj.method(...)
+                const callRegex = /\b([a-zA-Z_$][\w$.]*)\s*\(/g;
+                let callMatch;
+                while ((callMatch = callRegex.exec(expr.text)) !== null) {
+                    const calleeName = callMatch[1];
+                    // Skip control-flow keywords valid inside expressions
+                    if (calleeName === 'if' || calleeName === 'await' || calleeName === 'function')
+                        continue;
+                    this.unresolvedReferences.push({
+                        fromNodeId: componentNodeId,
+                        referenceName: calleeName,
+                        referenceKind: 'calls',
+                        line: lineIdx + 1, // 1-indexed
+                        column: expr.offset + callMatch.index,
+                        filePath: this.filePath,
+                        language: 'astro',
+                    });
+                }
+            }
+        }
+    }
+    /**
+     * Extract component usages from the Astro template.
+     *
+     * PascalCase tags like <Layout>, <PostCard /> represent component
+     * instantiations — analogous to function calls in imperative code.
+     * Lowercase tags are native HTML (Astro does not register kebab-case
+     * components the way Vue does, so those are real custom elements and
+     * are skipped).
+     */
+    extractTemplateComponents(componentNodeId, coveredRanges) {
+        const lines = this.source.split('\n');
+        // Opening/self-closing tags (closing tags </Foo> start with </ so won't match)
+        const componentTagRegex = /<([A-Z][a-zA-Z0-9_$]*)\b/g;
+        for (let lineIdx = 0; lineIdx < lines.length; lineIdx++) {
+            if (coveredRanges.some(([start, end]) => lineIdx >= start && lineIdx <= end))
+                continue;
+            const line = lines[lineIdx];
+            let match;
+            while ((match = componentTagRegex.exec(line)) !== null) {
+                const componentName = match[1];
+                if (ASTRO_BUILTIN_COMPONENTS.has(componentName))
+                    continue;
+                this.unresolvedReferences.push({
+                    fromNodeId: componentNodeId,
+                    referenceName: componentName,
+                    referenceKind: 'references',
+                    line: lineIdx + 1, // 1-indexed
+                    column: match.index + 1,
+                    filePath: this.filePath,
+                    language: 'astro',
+                });
+            }
+        }
+    }
+}
+exports.AstroExtractor = AstroExtractor;
+//# sourceMappingURL=astro-extractor.js.map

package/dist/extraction/astro-extractor.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"astro-extractor.js","sourceRoot":"","sources":["../../src/extraction/astro-extractor.ts"],"names":[],"mappings":";;;AACA,+DAAuD;AACvD,+CAAoD;AACpD,yCAAiD;AAEjD;;;GAGG;AACH,MAAM,wBAAwB,GAAG,IAAI,GAAG,CAAC,CAAC,UAAU,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC;AAExE;;;;;;;;;;;;;;;GAeG;AACH,MAAa,cAAc;IACjB,QAAQ,CAAS;IACjB,MAAM,CAAS;IACf,KAAK,GAAW,EAAE,CAAC;IACnB,KAAK,GAAW,EAAE,CAAC;IACnB,oBAAoB,GAA0B,EAAE,CAAC;IACjD,MAAM,GAAsB,EAAE,CAAC;IAEvC,YAAY,QAAgB,EAAE,MAAc;QAC1C,IAAI,CAAC,QAAQ,GAAG,QAAQ,CAAC;QACzB,IAAI,CAAC,MAAM,GAAG,MAAM,CAAC;IACvB,CAAC;IAED;;OAEG;IACH,OAAO;QACL,MAAM,SAAS,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;QAE7B,IAAI,CAAC;YACH,mDAAmD;YACnD,MAAM,aAAa,GAAG,IAAI,CAAC,mBAAmB,EAAE,CAAC;YAEjD,qEAAqE;YACrE,MAAM,WAAW,GAAG,IAAI,CAAC,kBAAkB,EAAE,CAAC;YAC9C,IAAI,WAAW,EAAE,CAAC;gBAChB,IAAI,CAAC,oBAAoB,CAAC,WAAW,EAAE,aAAa,CAAC,EAAE,EAAE,aAAa,CAAC,CAAC;YAC1E,CAAC;YAED,wEAAwE;YACxE,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,mBAAmB,EAAE,EAAE,CAAC;gBAC/C,IAAI,CAAC,oBAAoB,CAAC,KAAK,EAAE,aAAa,CAAC,EAAE,EAAE,QAAQ,CAAC,CAAC;YAC/D,CAAC;YAED,sEAAsE;YACtE,MAAM,aAAa,GAAG,IAAI,CAAC,gBAAgB,CAAC,WAAW,CAAC,CAAC;YAEzD,+DAA+D;YAC/D,IAAI,CAAC,oBAAoB,CAAC,aAAa,CAAC,EAAE,EAAE,aAAa,CAAC,CAAC;YAE3D,2DAA2D;YAC3D,IAAI,CAAC,yBAAyB,CAAC,aAAa,CAAC,EAAE,EAAE,aAAa,CAAC,CAAC;QAClE,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC;gBACf,OAAO,EAAE,2BAA2B,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE;gBAC5F,QAAQ,EAAE,OAAO;gBACjB,IAAI,EAAE,aAAa;aACpB,CAAC,CAAC;QACL,CAAC;QAED,OAAO;YACL,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,oBAAoB,EAAE,IAAI,CAAC,oBAAoB;YAC/C,MAAM,EAAE,IAAI,CAAC,MAAM;YACnB,UAAU,EAAE,IAAI,CAAC,GAAG,EAAE,GAAG,SAAS;SACnC,CAAC;IACJ,CAAC;IAED;;OAEG;IACK,mBAAmB;QACzB,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACtC,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,GAAG,EAAE,IAAI,IAAI,CAAC,QAAQ,CAAC;QACrE,MAAM,aAAa,GAAG,QAAQ,CAAC,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;QACvD,MAAM,EAAE,GAAG,IAAA,oCAAc,EAAC,IAAI,CAAC,QAAQ,EAAE,WAAW,EAAE,aAAa,EAAE,CAAC,CAAC,CAAC;QAExE,MAAM,IAAI,GAAS;YACjB,EAAE;YACF,IAAI,EAAE,WAAW;YACjB,IAAI,EAAE,aAAa;YACnB,aAAa,EAAE,GAAG,IAAI,CAAC,QAAQ,KAAK,aAAa,EAAE;YACnD,QAAQ,EAAE,IAAI,CAAC,QAAQ;YACvB,QAAQ,EAAE,OAAO;YACjB,SAAS,EAAE,CAAC;YACZ,OAAO,EAAE,KAAK,CAAC,MAAM;YACrB,WAAW,EAAE,CAAC;YACd,SAAS,EAAE,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,EAAE,MAAM,IAAI,CAAC;YAC/C,UAAU,EAAE,IAAI,EAAE,yCAAyC;YAC3D,SAAS,EAAE,IAAI,CAAC,GAAG,EAAE;SACtB,CAAC;QAEF,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACtB,OAAO,IAAI,CAAC;IACd,CAAC;IAED;;;;;;;OAOG;IACK,kBAAkB;QACxB,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAEtC,iDAAiD;QACjD,IAAI,OAAO,GAAG,CAAC,CAAC,CAAC;QACjB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YACtC,MAAM,OAAO,GAAG,KAAK,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,CAAC;YACjC,IAAI,OAAO,KAAK,EAAE;gBAAE,SAAS;YAC7B,IAAI,OAAO,KAAK,KAAK;gBAAE,OAAO,GAAG,CAAC,CAAC;YACnC,MAAM;QACR,CAAC;QACD,IAAI,OAAO,KAAK,CAAC,CAAC;YAAE,OAAO,IAAI,CAAC;QAEhC,gBAAgB;QAChB,IAAI,QAAQ,GAAG,CAAC,CAAC,CAAC;QAClB,KAAK,IAAI,CAAC,GAAG,OAAO,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YAChD,IAAI,KAAK,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,KAAK,KAAK,EAAE,CAAC;gBAC/B,QAAQ,GAAG,CAAC,CAAC;gBACb,MAAM;YACR,CAAC;QACH,CAAC;QACD,IAAI,QAAQ,KAAK,CAAC,CAAC;YAAE,OAAO,IAAI,CAAC;QAEjC,OAAO;YACL,OAAO,EAAE,KAAK,CAAC,KAAK,CAAC,OAAO,GAAG,CAAC,EAAE,QAAQ,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;YACtD,SAAS,EAAE,OAAO,GAAG,CAAC,EAAE,sCAAsC;YAC9D,OAAO,EAAE,QAAQ,EAAE,sCAAsC;SAC1D,CAAC;IACJ,CAAC;IAED;;OAEG;IACK,mBAAmB;QACzB,MAAM,MAAM,GAAkD,EAAE,CAAC;QAEjE,MAAM,WAAW,GAAG,mDAAmD,CAAC;QACxE,IAAI,KAAK,CAAC;QAEV,OAAO,CAAC,KAAK,GAAG,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;YACxD,MAAM,OAAO,GAAG,KAAK,CAAC,MAAM,EAAE,OAAO,IAAI,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;YAExD,qEAAqE;YACrE,sEAAsE;YACtE,oEAAoE;YACpE,gEAAgE;YAChE,MAAM,YAAY,GAAG,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC;YAC3D,MAAM,aAAa,GAAG,CAAC,YAAY,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC;YAC/D,MAAM,UAAU,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC;YACpE,MAAM,eAAe,GAAG,CAAC,UAAU,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC;YAC/D,MAAM,gBAAgB,GAAG,aAAa,GAAG,eAAe,CAAC,CAAC,YAAY;YAEtE,MAAM,CAAC,IAAI,CAAC,EAAE,OAAO,EAAE,SAAS,EAAE,gBAAgB,EAAE,CAAC,CAAC;QACxD,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAED;;;OAGG;IACK,oBAAoB,CAC1B,KAA6C,EAC7C,eAAuB,EACvB,KAA+B;QAE/B,IAAI,CAAC,IAAA,8BAAmB,EAAC,YAAY,CAAC,EAAE,CAAC;YACvC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC;gBACf,OAAO,EAAE,2DAA2D,KAAK,QAAQ;gBACjF,QAAQ,EAAE,SAAS;aACpB,CAAC,CAAC;YACH,OAAO;QACT,CAAC;QAED,kCAAkC;QAClC,MAAM,SAAS,GAAG,IAAI,iCAAmB,CAAC,IAAI,CAAC,QAAQ,EAAE,KAAK,CAAC,OAAO,EAAE,YAAY,CAAC,CAAC;QACtF,MAAM,MAAM,GAAG,SAAS,CAAC,OAAO,EAAE,CAAC;QAEnC,mEAAmE;QACnE,KAAK,MAAM,IAAI,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;YAChC,IAAI,CAAC,SAAS,IAAI,KAAK,CAAC,SAAS,CAAC;YAClC,IAAI,CAAC,OAAO,IAAI,KAAK,CAAC,SAAS,CAAC;YAChC,IAAI,CAAC,QAAQ,GAAG,OAAO,CAAC,CAAC,wBAAwB;YAEjD,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YAEtB,mDAAmD;YACnD,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC;gBACd,MAAM,EAAE,eAAe;gBACvB,MAAM,EAAE,IAAI,CAAC,EAAE;gBACf,IAAI,EAAE,UAAU;aACjB,CAAC,CAAC;QACL,CAAC;QAED,6CAA6C;QAC7C,KAAK,MAAM,IAAI,IAAI,MAAM,CAAC,KAAK,EAAE,CAAC;YAChC,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC;gBACd,IAAI,CAAC,IAAI,IAAI,KAAK,CAAC,SAAS,CAAC;YAC/B,CAAC;YACD,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACxB,CAAC;QAED,+BAA+B;QAC/B,KAAK,MAAM,GAAG,IAAI,MAAM,CAAC,oBAAoB,EAAE,CAAC;YAC9C,GAAG,CAAC,IAAI,IAAI,KAAK,CAAC,SAAS,CAAC;YAC5B,GAAG,CAAC,QAAQ,GAAG,IAAI,CAAC,QAAQ,CAAC;YAC7B,GAAG,CAAC,QAAQ,GAAG,OAAO,CAAC;YACvB,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;QACtC,CAAC;QAED,oBAAoB;QACpB,KAAK,MAAM,KAAK,IAAI,MAAM,CAAC,MAAM,EAAE,CAAC;YAClC,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC;gBACf,KAAK,CAAC,IAAI,IAAI,KAAK,CAAC,SAAS,CAAC;YAChC,CAAC;YACD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAC1B,CAAC;IACH,CAAC;IAED;;;OAGG;IACK,gBAAgB,CACtB,WAA0D;QAE1D,MAAM,aAAa,GAA4B,EAAE,CAAC;QAElD,IAAI,WAAW,EAAE,CAAC;YAChB,mEAAmE;YACnE,aAAa,CAAC,IAAI,CAAC,CAAC,WAAW,CAAC,SAAS,GAAG,CAAC,EAAE,WAAW,CAAC,OAAO,CAAC,CAAC,CAAC;QACvE,CAAC;QAED,MAAM,QAAQ,GAAG,2CAA2C,CAAC;QAC7D,IAAI,QAAQ,CAAC;QACb,OAAO,CAAC,QAAQ,GAAG,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;YACxD,MAAM,SAAS,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,EAAE,QAAQ,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC;YACvF,MAAM,OAAO,GAAG,SAAS,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC;YACpE,aAAa,CAAC,IAAI,CAAC,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC,CAAC;QAC3C,CAAC;QAED,OAAO,aAAa,CAAC;IACvB,CAAC;IAED;;;;;;;;;OASG;IACK,oBAAoB,CAC1B,eAAuB,EACvB,aAAsC;QAEtC,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACtC,gEAAgE;QAChE,MAAM,SAAS,GAAG,mBAAmB,CAAC;QACtC,6CAA6C;QAC7C,MAAM,aAAa,GAAG,iBAAiB,CAAC;QAExC,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,GAAG,KAAK,CAAC,MAAM,EAAE,OAAO,EAAE,EAAE,CAAC;YACxD,IAAI,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,OAAO,IAAI,KAAK,IAAI,OAAO,IAAI,GAAG,CAAC;gBAAE,SAAS;YAEvF,MAAM,IAAI,GAAG,KAAK,CAAC,OAAO,CAAE,CAAC;YAC7B,MAAM,KAAK,GAA4C,EAAE,CAAC;YAE1D,IAAI,SAAS,CAAC;YACd,OAAO,CAAC,SAAS,GAAG,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;gBACnD,KAAK,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,SAAS,CAAC,CAAC,CAAE,EAAE,MAAM,EAAE,SAAS,CAAC,KAAK,EAAE,CAAC,CAAC;YAC/D,CAAC;YACD,MAAM,SAAS,GAAG,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC,CAAC;YAClE,IAAI,SAAS,EAAE,CAAC;gBACd,KAAK,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,SAAS,CAAC,CAAC,CAAE,EAAE,MAAM,EAAE,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;YACrE,CAAC;YAED,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;gBACzB,oDAAoD;gBACpD,qDAAqD;gBACrD,MAAM,SAAS,GAAG,6BAA6B,CAAC;gBAChD,IAAI,SAAS,CAAC;gBACd,OAAO,CAAC,SAAS,GAAG,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;oBACxD,MAAM,UAAU,GAAG,SAAS,CAAC,CAAC,CAAE,CAAC;oBACjC,sDAAsD;oBACtD,IAAI,UAAU,KAAK,IAAI,IAAI,UAAU,KAAK,OAAO,IAAI,UAAU,KAAK,UAAU;wBAAE,SAAS;oBAEzF,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC;wBAC7B,UAAU,EAAE,eAAe;wBAC3B,aAAa,EAAE,UAAU;wBACzB,aAAa,EAAE,OAAO;wBACtB,IAAI,EAAE,OAAO,GAAG,CAAC,EAAE,YAAY;wBAC/B,MAAM,EAAE,IAAI,CAAC,MAAM,GAAG,SAAS,CAAC,KAAK;wBACrC,QAAQ,EAAE,IAAI,CAAC,QAAQ;wBACvB,QAAQ,EAAE,OAAO;qBAClB,CAAC,CAAC;gBACL,CAAC;YACH,CAAC;QACH,CAAC;IACH,CAAC;IAED;;;;;;;;OAQG;IACK,yBAAyB,CAC/B,eAAuB,EACvB,aAAsC;QAEtC,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACtC,+EAA+E;QAC/E,MAAM,iBAAiB,GAAG,2BAA2B,CAAC;QAEtD,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,GAAG,KAAK,CAAC,MAAM,EAAE,OAAO,EAAE,EAAE,CAAC;YACxD,IAAI,aAAa,CAAC,IAAI,CAAC,CAAC,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,OAAO,IAAI,KAAK,IAAI,OAAO,IAAI,GAAG,CAAC;gBAAE,SAAS;YAEvF,MAAM,IAAI,GAAG,KAAK,CAAC,OAAO,CAAE,CAAC;YAC7B,IAAI,KAAK,CAAC;YACV,OAAO,CAAC,KAAK,GAAG,iBAAiB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;gBACvD,MAAM,aAAa,GAAG,KAAK,CAAC,CAAC,CAAE,CAAC;gBAChC,IAAI,wBAAwB,CAAC,GAAG,CAAC,aAAa,CAAC;oBAAE,SAAS;gBAE1D,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC;oBAC7B,UAAU,EAAE,eAAe;oBAC3B,aAAa,EAAE,aAAa;oBAC5B,aAAa,EAAE,YAAY;oBAC3B,IAAI,EAAE,OAAO,GAAG,CAAC,EAAE,YAAY;oBAC/B,MAAM,EAAE,KAAK,CAAC,KAAK,GAAG,CAAC;oBACvB,QAAQ,EAAE,IAAI,CAAC,QAAQ;oBACvB,QAAQ,EAAE,OAAO;iBAClB,CAAC,CAAC;YACL,CAAC;QACH,CAAC;IACH,CAAC;CACF;AAjVD,wCAiVC"}

package/dist/extraction/cfml-extractor.d.ts

@@ -0,0 +1,107 @@
+import { ExtractionResult, Language } from '../types';
+/**
+ * CfmlExtractor - Extracts code relationships from CFML source (.cfc/.cfm).
+ *
+ * tree-sitter-cfml splits CFML into two related grammars: `cfml` (tag-based —
+ * `<cfcomponent>`/`<cffunction>`/HTML) and `cfscript` (modern bare-script
+ * `component { ... }` syntax). The `cfml` grammar's own injections.scm treats
+ * bare-script content as an opaque blob meant to be re-parsed by `cfscript` —
+ * that re-parsing only happens at the editor/highlighting layer, not in the
+ * raw AST, so this extractor replicates it: a file whose first real token
+ * isn't `<` is delegated wholesale to the cfscript grammar (the dominant
+ * modern style); otherwise the file is walked tag-by-tag with the cfml
+ * grammar, delegating any `<cfscript>` tag bodies the same way.
+ */
+export declare class CfmlExtractor {
+    private filePath;
+    private source;
+    private language;
+    private nodes;
+    private edges;
+    private unresolvedReferences;
+    private errors;
+    /** `language` is the file's detected language — `'cfml'` for `.cfc`/`.cfm`, `'cfscript'` for `.cfs`. Both dialect-switch internally; this only controls the language tag stamped onto emitted nodes/refs. */
+    constructor(filePath: string, source: string, language?: Language);
+    extract(): ExtractionResult;
+    /** Modern bare-script `.cfc`/`.cfm`: delegate the whole file to the cfscript grammar. */
+    private extractBareScript;
+    /** Legacy tag-based CFML: walk `<cfcomponent>`/`<cffunction>`, delegating `<cfscript>` bodies. */
+    private extractTagBased;
+    /** Build the file's own `kind:'file'` node, spanning the whole source. Tag-based files need this explicitly — unlike `extractBareScript` (which delegates the whole file to `TreeSitterExtractor` and inherits its file node), `extractTagBased` walks the tree itself and has no other source of one. */
+    private createFileNode;
+    /**
+     * Walks `program`'s named children with a single forward cursor (not an
+     * index loop) — `extractComponent` consumes a variable run of FOLLOWING
+     * siblings as the component body (see its doc comment), so this must
+     * resume from whatever it last consumed rather than revisiting those same
+     * cffunction/cfscript siblings a second time as bogus top-level symbols.
+     */
+    private walkProgram;
+    /**
+     * `<cfcomponent extends="Base" implements="IFoo,IBar">...</cfcomponent>`.
+     * The grammar's implicit-end-tag scanner means component body content
+     * (cffunction tags, cfscript tags, etc.) appears as the open tag's FOLLOWING
+     * siblings in `program`, not nested children — walk forward to the matching
+     * cf_component_close_tag.
+     */
+    private extractComponent;
+    /**
+     * `<cffunction name="..." access="..." returntype="...">...</cffunction>`.
+     * `parentClassId` decides `method` vs top-level `function`; `containerId` is
+     * the `contains`-edge target (the class when inside one, otherwise the file
+     * node for a bare top-level cffunction) — kept separate so a top-level
+     * function still gets a containment edge without being misclassified as a
+     * method of the file. A method's qualifiedName is scoped under
+     * `parentClassName` (`TagService::save`, the same `Class::member` shape the
+     * generic extractor produces) so type-validated method resolution can match.
+     */
+    private extractFunctionTag;
+    /**
+     * Recursively delegates any `cf_script_tag`/`cf_query_tag` found within
+     * `node`'s subtree — e.g. a `<cfscript>`/`<cfquery>` nested inside
+     * `<cfif>`/`<cfloop>`/`<cftry>` control-flow tags, which (unlike
+     * `<cfcomponent>`'s body — see the implicit-end-tag note on `extractComponent`)
+     * ARE normal children, just possibly several levels deep, so a direct-children
+     * check misses them. Does not descend into a nested `cf_function_tag` — that
+     * has its own scope and is walked separately. `parentClassName` rides along
+     * so a `<cfscript>` at component scope classifies its functions as methods
+     * scoped under the component.
+     */
+    private delegateNestedTags;
+    /**
+     * Delegate a `<cfscript>...</cfscript>` tag body to the cfscript grammar.
+     * With `parentClassName` set (the block sits at component scope), functions
+     * declared at the script's top level are the component's methods
+     * (`<cfcomponent><cfscript>function configure(){}` — the standard ColdBox
+     * ModuleConfig shape): they're re-kinded `function` → `method`, and every
+     * merged symbol's qualifiedName is prefixed with the component scope
+     * (`configure` → `ModuleConfig::configure`) so type-validated method
+     * resolution can match them. Functions nested inside another function
+     * (closures) keep kind `function`.
+     */
+    private delegateScriptTag;
+    /**
+     * Delegate a `<cfquery>...</cfquery>` tag's SQL body to the `cfquery` grammar.
+     * `#hash#` expressions inside the SQL (e.g. `#getCurrentUser().getId()#` in a
+     * WHERE clause) are real CFML calls/references — tree-sitter-cfml's `cfquery`
+     * grammar parses them structurally (same `call_expression`/`member_expression`
+     * shape as cfscript), so without this delegation they're silently dropped as
+     * opaque SQL text. The grammar models no other symbols, so only call/reference
+     * extraction is relevant here — unlike `delegateScriptTag`, there are no nodes
+     * or contains-edges to merge.
+     */
+    private delegateQueryTag;
+    /** Read a `cf_attribute`'s value by name from a tag node's direct `cf_attribute`/`cf_tag_attributes` children. */
+    private tagAttr;
+    private componentNameFromPath;
+}
+/**
+ * Sniff whether CFML source is bare-script (`component { ... }`, modern style)
+ * vs tag-based (`<cfcomponent>`, `<cfif>`, HTML). Skips a leading UTF-8 BOM
+ * (endemic in CFML's Windows-editor history — 17% of ColdBox's files carry
+ * one; both grammars parse fine with it once routed correctly), whitespace,
+ * and `//`/`/* *\/` comments to find the first real token; tag-based files
+ * start with `<`, script-based files don't.
+ */
+export declare function isBareScriptCfml(source: string): boolean;
+//# sourceMappingURL=cfml-extractor.d.ts.map

package/dist/extraction/cfml-extractor.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"cfml-extractor.d.ts","sourceRoot":"","sources":["../../src/extraction/cfml-extractor.ts"],"names":[],"mappings":"AACA,OAAO,EAAc,gBAAgB,EAAwC,QAAQ,EAAE,MAAM,UAAU,CAAC;AAKxG;;;;;;;;;;;;GAYG;AACH,qBAAa,aAAa;IACxB,OAAO,CAAC,QAAQ,CAAS;IACzB,OAAO,CAAC,MAAM,CAAS;IACvB,OAAO,CAAC,QAAQ,CAAW;IAC3B,OAAO,CAAC,KAAK,CAAc;IAC3B,OAAO,CAAC,KAAK,CAAc;IAC3B,OAAO,CAAC,oBAAoB,CAA6B;IACzD,OAAO,CAAC,MAAM,CAAyB;IAEvC,6MAA6M;gBACjM,QAAQ,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,QAAQ,GAAE,QAAiB;IAMzE,OAAO,IAAI,gBAAgB;IA0B3B,yFAAyF;IACzF,OAAO,CAAC,iBAAiB;IA8BzB,kGAAkG;IAClG,OAAO,CAAC,eAAe;IAyBvB,0SAA0S;IAC1S,OAAO,CAAC,cAAc;IAoBtB;;;;;;OAMG;IACH,OAAO,CAAC,WAAW;IAqBnB;;;;;;OAMG;IACH,OAAO,CAAC,gBAAgB;IA0ExB;;;;;;;;;OASG;IACH,OAAO,CAAC,kBAAkB;IAsC1B;;;;;;;;;;OAUG;IACH,OAAO,CAAC,kBAAkB;IAgB1B;;;;;;;;;;OAUG;IACH,OAAO,CAAC,iBAAiB;IA8DzB;;;;;;;;;OASG;IACH,OAAO,CAAC,gBAAgB;IAwBxB,kHAAkH;IAClH,OAAO,CAAC,OAAO;IA8Bf,OAAO,CAAC,qBAAqB;CAI9B;AAED;;;;;;;GAOG;AACH,wBAAgB,gBAAgB,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAkBxD"}