Add support for Zig

README.md

@@ -386,7 +386,7 @@ Code Context is a monorepo containing three main packages:
 - **Embedding Providers**: [OpenAI](https://openai.com), [VoyageAI](https://voyageai.com), [Ollama](https://ollama.ai), [Gemini](https://gemini.google.com)
 - **Vector Databases**: [Milvus](https://milvus.io) or [Zilliz Cloud](https://zilliz.com/cloud)(fully managed vector database as a service)
 - **Code Splitters**: AST-based splitter (with automatic fallback), LangChain character-based splitter
-- **Languages**: TypeScript, JavaScript, Python, Java, C++, C#, Go, Rust, PHP, Ruby, Swift, Kotlin, Scala, Markdown
+- **Languages**: TypeScript, JavaScript, Python, Java, C++, C#, Go, Rust, Zig, PHP, Ruby, Swift, Kotlin, Scala, Markdown
 - **Development Tools**: VSCode, Model Context Protocol
 
 ---

package.json

@@ -52,5 +52,8 @@
         "url": "https://github.com/zilliztech/code-context.git"
     },
     "license": "MIT",
-    "author": "Cheney Zhang <[email protected]>"
+    "author": "Cheney Zhang <[email protected]>",
+    "dependencies": {
+        "@tree-sitter-grammars/tree-sitter-zig": "^1.1.2"
+    }
 }

packages/core/README.md

@@ -94,7 +94,7 @@ results.forEach(result => {
 
 ## Features
 
-- **Multi-language Support**: Index TypeScript, JavaScript, Python, Java, C++, and many other programming languages
+- **Multi-language Support**: Index TypeScript, JavaScript, Python, Java, C++, Zig, and many other programming languages
 - **Semantic Search**: Find code using natural language queries powered by AI embeddings
 - **Flexible Architecture**: Pluggable embedding providers and vector databases
 - **Smart Chunking**: Intelligent code splitting that preserves context and structure
@@ -136,7 +136,7 @@ interface CodeContextConfig {
 [
   // Programming languages
   '.ts', '.tsx', '.js', '.jsx', '.py', '.java', '.cpp', '.c', '.h', '.hpp',
-  '.cs', '.go', '.rs', '.php', '.rb', '.swift', '.kt', '.scala', '.m', '.mm',
+  '.cs', '.go', '.rs', '.zig', '.php', '.rb', '.swift', '.kt', '.scala', '.m', '.mm',
   // Text and markup files  
   '.md', '.markdown'
 ]

packages/core/package.json

@@ -14,6 +14,7 @@
     },
     "dependencies": {
         "@google/genai": "^1.9.0",
+        "@tree-sitter-grammars/tree-sitter-zig": "^1.1.2",
         "@zilliz/milvus2-sdk-node": "^2.5.10",
         "faiss-node": "^0.5.1",
         "fs-extra": "^11.0.0",

packages/core/src/context.ts

@@ -23,7 +23,7 @@ import { FileSynchronizer } from './sync/synchronizer';
 const DEFAULT_SUPPORTED_EXTENSIONS = [
     // Programming languages
     '.ts', '.tsx', '.js', '.jsx', '.py', '.java', '.cpp', '.c', '.h', '.hpp',
-    '.cs', '.go', '.rs', '.php', '.rb', '.swift', '.kt', '.scala', '.m', '.mm',
+    '.cs', '.go', '.rs', '.php', '.rb', '.swift', '.kt', '.scala', '.m', '.mm', '.zig',
     // Text and markup files
     '.md', '.markdown', '.ipynb',
     // '.txt',  '.json', '.yaml', '.yml', '.xml', '.html', '.htm',
@@ -626,7 +626,8 @@ export class CodeContext {
             '.scala': 'scala',
             '.m': 'objective-c',
             '.mm': 'objective-c',
-            '.ipynb': 'jupyter'
+            '.ipynb': 'jupyter',
+            '.zig': 'zig'
         };
         return languageMap[ext] || 'text';
     }

packages/core/src/splitter/ast-splitter.ts

@@ -9,6 +9,7 @@ const Java = require('tree-sitter-java');
 const Cpp = require('tree-sitter-cpp');
 const Go = require('tree-sitter-go');
 const Rust = require('tree-sitter-rust');
+const Zig = require('@tree-sitter-grammars/tree-sitter-zig');
 
 // Node types that represent logical code units
 const SPLITTABLE_NODE_TYPES = {
@@ -18,7 +19,8 @@ const SPLITTABLE_NODE_TYPES = {
     java: ['method_declaration', 'class_declaration', 'interface_declaration', 'constructor_declaration'],
     cpp: ['function_definition', 'class_specifier', 'namespace_definition', 'declaration'],
     go: ['function_declaration', 'method_declaration', 'type_declaration', 'var_declaration', 'const_declaration'],
-    rust: ['function_item', 'impl_item', 'struct_item', 'enum_item', 'trait_item', 'mod_item']
+    rust: ['function_item', 'impl_item', 'struct_item', 'enum_item', 'trait_item', 'mod_item'],
+    zig: ['function_declaration', 'variable_declaration', 'test_declaration', 'comptime_declaration', 'using_namespace_declaration']
 };
 
 export class AstCodeSplitter implements Splitter {
@@ -93,7 +95,8 @@ export class AstCodeSplitter implements Splitter {
             'c': { parser: Cpp, nodeTypes: SPLITTABLE_NODE_TYPES.cpp },
             'go': { parser: Go, nodeTypes: SPLITTABLE_NODE_TYPES.go },
             'rust': { parser: Rust, nodeTypes: SPLITTABLE_NODE_TYPES.rust },
-            'rs': { parser: Rust, nodeTypes: SPLITTABLE_NODE_TYPES.rust }
+            'rs': { parser: Rust, nodeTypes: SPLITTABLE_NODE_TYPES.rust },
+            'zig': { parser: Zig, nodeTypes: SPLITTABLE_NODE_TYPES.zig }
         };
 
         return langMap[language.toLowerCase()] || null;
@@ -109,9 +112,18 @@ export class AstCodeSplitter implements Splitter {
         const chunks: CodeChunk[] = [];
         const codeLines = code.split('\n');
 
-        const traverse = (currentNode: Parser.SyntaxNode) => {
+        // For Zig and similar languages, only extract top-level declarations
+        // to avoid duplicating nested functions/types
+        const shouldOnlyExtractTopLevel = ['zig', 'rust', 'go'].includes(language);
+
+        const traverse = (currentNode: Parser.SyntaxNode, depth: number = 0) => {
             // Check if this node type should be split into a chunk
             if (splittableTypes.includes(currentNode.type)) {
+                // For certain languages, skip nested declarations
+                if (shouldOnlyExtractTopLevel && depth > 1) {
+                    return;
+                }
+
                 const startLine = currentNode.startPosition.row + 1;
                 const endLine = currentNode.endPosition.row + 1;
                 const nodeText = code.slice(currentNode.startIndex, currentNode.endIndex);
@@ -132,7 +144,7 @@ export class AstCodeSplitter implements Splitter {
 
             // Continue traversing child nodes
             for (const child of currentNode.children) {
-                traverse(child);
+                traverse(child, depth + 1);
             }
         };
 
@@ -256,7 +268,7 @@ export class AstCodeSplitter implements Splitter {
     static isLanguageSupported(language: string): boolean {
         const supportedLanguages = [
             'javascript', 'js', 'typescript', 'ts', 'python', 'py',
-            'java', 'cpp', 'c++', 'c', 'go', 'rust', 'rs'
+            'java', 'cpp', 'c++', 'c', 'go', 'rust', 'rs', 'zig'
         ];
         return supportedLanguages.includes(language.toLowerCase());
     }

packages/core/src/splitter/langchain-splitter.ts

@@ -63,7 +63,7 @@ export class LangChainCodeSplitter implements Splitter {
 
     private mapLanguage(language: string): SupportedLanguage | null {
         // Map common language names to LangChain supported formats
-        const languageMap: Record<string, SupportedLanguage> = {
+        const languageMap: Record<string, SupportedLanguage | null> = {
             'javascript': 'js',
             'typescript': 'js',
             'python': 'python',
@@ -84,9 +84,11 @@ export class LangChainCodeSplitter implements Splitter {
             'tex': 'latex',
             'solidity': 'sol',
             'sol': 'sol',
+            'zig': null, // LangChain doesn't have native Zig support, will use fallback
         };
 
-        return languageMap[language.toLowerCase()] || null;
+        const mapped = languageMap[language.toLowerCase()];
+        return mapped !== undefined ? mapped : null;
     }
 
     private async fallbackSplit(code: string, language: string, filePath?: string): Promise<CodeChunk[]> {