Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
View Source
var ExtToLanguage = map[string]string{
".go": "go",
".py": "python",
".js": "javascript",
".jsx": "javascript",
".ts": "typescript",
".tsx": "typescript",
".java": "java",
".c": "c",
".h": "c",
".cpp": "cpp",
".hpp": "cpp",
".cc": "cpp",
".cs": "csharp",
".rs": "rust",
".rb": "ruby",
".php": "php",
".swift": "swift",
".kt": "kotlin",
".scala": "scala",
".m": "objc",
".mm": "objc",
".lua": "lua",
".sh": "bash",
".bash": "bash",
".md": "markdown",
}
语言与文件扩展名的映射
Functions ¶
Types ¶
type Splitter ¶
type Splitter interface {
// Split 将文件内容按语义边界分块
Split(content string, filePath string) ([]model.CodeChunk, error)
// SupportedLanguages 返回该分块器支持的语言列表
SupportedLanguages() []string
}
Splitter 代码分块器接口
type TreeSitterSplitter ¶
type TreeSitterSplitter struct {
// contains filtered or unexported fields
}
TreeSitterSplitter 基于 tree-sitter AST 的多语言代码分块器
func NewTreeSitterSplitter ¶
func NewTreeSitterSplitter(maxChunkSize, overlap int) *TreeSitterSplitter
NewTreeSitterSplitter 创建 tree-sitter 分块器
func (*TreeSitterSplitter) SupportedLanguages ¶
func (s *TreeSitterSplitter) SupportedLanguages() []string
SupportedLanguages 返回支持的语言列表
Source Files
Click to show internal directories.
Click to hide internal directories.