repomap

package
v0.2.0 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: May 15, 2026 License: MIT Imports: 22 Imported by: 0

Documentation

Overview

Package repomap generates a lightweight code structure map of a repository by scanning files and extracting top-level symbols using regex-based parsers. The result is a token-budgeted summary suitable for injection into LLM prompts.

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func AutoFix added in v0.2.0 

func AutoFix(opp MigrationOpportunity, content string) (string, error)

AutoFix applies the regex replacement for an auto-fixable opportunity.

func CacheClear 

func CacheClear()

CacheClear removes all entries from the symbol cache.

func CacheSize 

func CacheSize() int

CacheSize returns the number of entries in the cache.

func CoChangeAnalysisMap added in v0.2.0 

func CoChangeAnalysisMap(projectDir string) map[string][]string

CoChangeAnalysisMap returns a map of files to their frequently co-changed companions.

func CompareScores added in v0.2.0 

func CompareScores(before, after *HealthScore) string

CompareScores produces a comparison between two health scores.

func ComputeFileHash 

func ComputeFileHash(path string) (string, error)

ComputeFileHash returns the SHA-256 hex digest of a file's contents.

func DetectFramework added in v0.2.0 

func DetectFramework(dir string) string

DetectFramework examines Go files in dir to determine which HTTP framework is used. Returns one of: "chi", "gin", "echo", "gorilla", "fiber", "net/http", or "unknown".

func EstimateRemovableLines added in v0.2.0 

func EstimateRemovableLines(items []DeadCode) int

EstimateRemovableLines estimates the total number of lines that could be removed if all dead code items were eliminated.

func ExpandQuery added in v0.2.0 

func ExpandQuery(query string) []string

ExpandQuery expands a query term into related terms and synonyms.

func ExtractSnippet added in v0.2.0 

func ExtractSnippet(doc *Document, queryTerms []string, maxLen int) string

ExtractSnippet finds the most relevant lines from a document containing query terms.

func FindEntryPoints added in v0.2.0 

func FindEntryPoints(projectDir string) []string

FindEntryPoints identifies program entry points in the project.

func FindKeyFiles added in v0.2.0 

func FindKeyFiles(projectDir string, limit int) []string

FindKeyFiles identifies the most important files in a project.

func FormatAPIMap added in v0.2.0 

func FormatAPIMap(apiMap *APIMap) string

FormatAPIMap produces a formatted string representation of the API map.

func FormatDeadCode added in v0.2.0 

func FormatDeadCode(items []DeadCode) string

FormatDeadCode formats the results into a human-readable report.

func FormatDefinition added in v0.2.0 

func FormatDefinition(def *Definition) string

FormatDefinition formats a definition for display.

func FormatGroups added in v0.2.0 

func FormatGroups(groups []FileGroup) string

FormatGroups produces a human-readable summary of the file groups.

func FormatOpportunities added in v0.2.0 

func FormatOpportunities(opps []MigrationOpportunity) string

FormatOpportunities produces a human-readable summary of migration opportunities.

func FormatReferences added in v0.2.0 

func FormatReferences(symbol string, refs []*Reference) string

FormatReferences formats a list of references for display.

func FormatResults added in v0.2.0 

func FormatResults(query string, hits []SearchHit) string

FormatResults produces a human-readable string of search results.

func FormatScore added in v0.2.0 

func FormatScore(score *HealthScore) string

FormatScore produces a human-readable health report.

func FormatSmells added in v0.2.0 

func FormatSmells(smells []CodeSmell) string

FormatSmells formats a list of code smells into a human-readable report.

func GenerateOpenAPI added in v0.2.0 

func GenerateOpenAPI(apiMap *APIMap) string

GenerateOpenAPI produces a basic OpenAPI 3.0 YAML skeleton from the API map.

func GenerateRemovalPlan added in v0.2.0 

func GenerateRemovalPlan(items []DeadCode) string

GenerateRemovalPlan produces an ordered list of safe removals.

func IncrementalReindex 

func IncrementalReindex(dir string, ignore []string, indexer CodeIndexer) (added, skipped, removed int, err error)

IncrementalReindex walks dir, chunks supported source files, and stores them via the indexer. Files whose hash matches the stored hash are skipped. Files that have been removed from disk are cleared from the index. File processing is parallelized across available CPUs. Uses IndexPatterns for include/exclude glob filtering and GitignoreRules for nested .gitignore support.

func InferArchitecture added in v0.2.0 

func InferArchitecture(packages []SummaryPackageInfo) string

InferArchitecture detects architectural patterns from the package layout. Returns one of: "layered", "flat", "monorepo", "microservices", "hexagonal".

func InferPurpose added in v0.2.0 

func InferPurpose(pkgPath string, symbols []string) string

InferPurpose infers a package's purpose from its path and exported symbols.

func IsInterfaceImpl added in v0.2.0 

func IsInterfaceImpl(name string, content string) bool

IsInterfaceImpl checks if a function with the given name might satisfy an interface by searching for interface declarations in the provided content.

func IsTestFunction added in v0.2.0 

func IsTestFunction(name string) bool

IsTestFunction returns true if name looks like a Go test, benchmark, or example function.

func MaintainabilityIndex added in v0.2.0 

func MaintainabilityIndex(fc FunctionComplexity) float64

MaintainabilityIndex computes a simplified maintainability index. Based on the standard formula: 171 - 5.2*ln(HV) - 0.23*CC - 16.2*ln(LOC) Simplified using CC and LOC (Halstead volume approximated from LOC).

func RenderCompact added in v0.2.0 

func RenderCompact(summary *CodebaseSummary) string

RenderCompact renders the summary as a single paragraph suitable for tight contexts.

func RenderForPrompt added in v0.2.0 

func RenderForPrompt(summary *CodebaseSummary, budget int) string

RenderForPrompt renders a CodebaseSummary as a markdown-formatted overview suitable for injection into an LLM prompt, respecting the given token budget.

func RenderTreeContext added in v0.2.0 

func RenderTreeContext(file string, symbols []Symbol, maxLines int) string

RenderTreeContext produces a tree-context rendering of symbols for a file. It groups symbols by their parent scope and renders them with proper indentation, similar to Aider's TreeContext. If maxLines <= 0, no truncation is applied.

Types

type APIEndpoint added in v0.2.0 

type APIEndpoint struct {
	Method      string
	Path        string
	Handler     string
	File        string
	Line        int
	Middleware  []string
	Description string
}

APIEndpoint represents a single HTTP endpoint discovered in the codebase.

func ScanChi added in v0.2.0 

func ScanChi(content, file string) []APIEndpoint

ScanChi extracts endpoints from chi router registrations. Patterns: r.Get("/path", handler), r.Post(...), r.Put(...), r.Delete(...), r.Route("/prefix", func(r chi.Router) { ... }), r.Group(func(r chi.Router) { ... })

func ScanEcho added in v0.2.0 

func ScanEcho(content, file string) []APIEndpoint

ScanEcho extracts endpoints from echo framework registrations. Patterns: e.GET("/path", handler), e.POST(...), g := e.Group("/api")

func ScanFiber added in v0.2.0 

func ScanFiber(content, file string) []APIEndpoint

ScanFiber extracts endpoints from gofiber/fiber registrations. Patterns: app.Get("/path", handler), app.Post(...), api := app.Group("/api")

func ScanGin added in v0.2.0 

func ScanGin(content, file string) []APIEndpoint

ScanGin extracts endpoints from gin router registrations. Patterns: r.GET("/path", handler), r.POST(...), group := r.Group("/api")

func ScanGorilla added in v0.2.0 

func ScanGorilla(content, file string) []APIEndpoint

ScanGorilla extracts endpoints from gorilla/mux registrations. Patterns: r.HandleFunc("/path", handler).Methods("GET")

func ScanNetHTTP added in v0.2.0 

func ScanNetHTTP(content, file string) []APIEndpoint

ScanNetHTTP extracts endpoints from net/http standard library registrations. Patterns: http.HandleFunc("/path", handler), http.Handle("/path", handler), mux.HandleFunc("/path", handler), mux.Handle("/path", handler)

type APIMap added in v0.2.0 

type APIMap struct {
	Endpoints []APIEndpoint
	BaseURL   string
	Version   string
	// contains filtered or unexported fields
}

APIMap holds all discovered endpoints and metadata about the API.

func (*APIMap) FindEndpointByPath added in v0.2.0 

func (m *APIMap) FindEndpointByPath(path string) *APIEndpoint

FindEndpointByPath returns the first endpoint matching the given path, or nil.

type APIScanner added in v0.2.0 

type APIScanner struct {
	// contains filtered or unexported fields
}

APIScanner discovers HTTP endpoints in Go projects by analyzing router registrations.

func NewAPIScanner added in v0.2.0 

func NewAPIScanner() *APIScanner

NewAPIScanner creates a new APIScanner instance.

func (*APIScanner) ScanProject added in v0.2.0 

func (s *APIScanner) ScanProject(dir string) (*APIMap, error)

ScanProject walks Go files in dir looking for router registrations and returns an APIMap with all discovered endpoints. It auto-detects the framework in use.

type CallGraph 

type CallGraph struct {
	// contains filtered or unexported fields
}

CallGraph maps functions to their callers and callees using Go AST analysis. No CGO required — uses go/parser for static analysis.

func BuildCallGraph 

func BuildCallGraph(root string) (*CallGraph, error)

BuildCallGraph parses Go files in root and extracts call relationships.

func (*CallGraph) CalleesOf 

func (cg *CallGraph) CalleesOf(funcName string, maxDepth int) []string

CalleesOf returns functions called by the given function (depth levels down).

func (*CallGraph) CallersOf 

func (cg *CallGraph) CallersOf(funcName string, maxDepth int) []string

CallersOf returns functions that call the given function (depth levels up).

func (*CallGraph) Neighborhood 

func (cg *CallGraph) Neighborhood(funcName string, depth int) []string

Neighborhood returns callers + callees within depth.

type ChangeSetContext 

type ChangeSetContext struct {
	ChangedFiles    []string
	ImpactedFiles   []string // files affected by the changes (dependents)
	DependencyFiles []string // files needed to understand the changes (imports)
	TotalFiles      int
}

ChangeSetContext loads only the code context relevant to current changes. Instead of loading the entire repo map, it: 1. Parses `git diff --name-only` to get changed files 2. For each changed file, finds its imports and dependents 3. Returns a focused context set that's 70-90% smaller than full repo

Research: Change-set-aware loading typically reduces context by 70-90% compared to loading the entire repo-map.

func FromGitDiff 

func FromGitDiff(root string, graph *ImportGraph) (*ChangeSetContext, error)

FromGitDiff builds a ChangeSetContext from the current git working tree changes. This includes both staged and unstaged modifications.

func FromGitDiffRange 

func FromGitDiffRange(root string, baseRef string, graph *ImportGraph) (*ChangeSetContext, error)

FromGitDiffRange builds a ChangeSetContext from a specific git range (e.g., "main..HEAD").

func (*ChangeSetContext) FormatContext 

func (c *ChangeSetContext) FormatContext(maxTokens int) string

FormatContext produces a token-efficient representation of the change set suitable for injection into the system prompt.

type CoChangeAnalysis 

type CoChangeAnalysis struct {
	// contains filtered or unexported fields
}

CoChangeAnalysis tracks which files frequently change together in git history.

func BuildCoChangeAnalysis 

func BuildCoChangeAnalysis(root string, commitLimit int) (*CoChangeAnalysis, error)

BuildCoChangeAnalysis parses the last N commits to find co-change patterns.

func (*CoChangeAnalysis) RelatedFiles 

func (ca *CoChangeAnalysis) RelatedFiles(filePath string, topK int) []string

RelatedFiles returns files that frequently co-change with the given file, sorted by co-change frequency.

type CodeChunk 

type CodeChunk struct {
	Path      string
	StartLine int
	EndLine   int
	Content   string
	Vector    []float32 // embedding (if computed)
}

CodeChunk represents a chunk of source code for semantic search.

type CodeIndexer 

type CodeIndexer interface {
	IndexCodeChunk(path, content, symbol, lang string, start, end, tokens int, hash string) error
	SearchCode(query string, limit int) ([]CodeSearchResult, error)
	GetFileHash(path string) (string, error)
	ClearFileChunks(path string) error
	ListIndexedPaths() ([]string, error)
}

CodeIndexer is the interface used by IncrementalReindex to store and query code chunks. The memory package's YaadBridge implements this interface.

type CodeSearchResult 

type CodeSearchResult struct {
	Path      string
	StartLine int
	EndLine   int
	Content   string
	Symbol    string
	Score     float64
}

CodeSearchResult represents a code chunk returned by a search.

type CodeSmell added in v0.2.0 

type CodeSmell struct {
	ID                    string
	Name                  string
	File                  string
	Line                  int
	Severity              string // "minor", "major", "critical"
	Description           string
	RefactoringSuggestion string
	Category              string // "design", "complexity", "coupling", "naming"
}

CodeSmell represents a detected design issue in source code.

type CodebaseSummary added in v0.2.0 

type CodebaseSummary struct {
	ProjectName  string
	Description  string
	Language     string
	Packages     []SummaryPackageInfo
	EntryPoints  []string
	KeyFiles     []string
	Architecture string
	TotalLOC     int
	TotalFiles   int
	GeneratedAt  time.Time
}

CodebaseSummary holds the high-level overview of a repository.

type ComplexityAnalyzer added in v0.2.0 

type ComplexityAnalyzer struct {
	HighCyclomatic int
	HighCognitive  int
	HighNesting    int
	HighLOC        int
}

ComplexityAnalyzer computes complexity metrics with configurable thresholds.

func NewComplexityAnalyzer added in v0.2.0 

func NewComplexityAnalyzer() *ComplexityAnalyzer

NewComplexityAnalyzer creates a ComplexityAnalyzer with default thresholds.

func (*ComplexityAnalyzer) AnalyzeFile added in v0.2.0 

func (ca *ComplexityAnalyzer) AnalyzeFile(path, content string) (*ComplexityReport, error)

AnalyzeFile analyzes the complexity of a file given its path and content.

func (*ComplexityAnalyzer) AnalyzeGeneric added in v0.2.0 

func (ca *ComplexityAnalyzer) AnalyzeGeneric(content, language string) []FunctionComplexity

AnalyzeGeneric performs regex-based complexity analysis for non-Go languages.

func (*ComplexityAnalyzer) AnalyzeGoAST added in v0.2.0 

func (ca *ComplexityAnalyzer) AnalyzeGoAST(content string) []FunctionComplexity

AnalyzeGoAST performs full AST-based complexity analysis on Go source code.

func (*ComplexityAnalyzer) FindHotspots added in v0.2.0 

func (ca *ComplexityAnalyzer) FindHotspots(dir string, limit int) []FunctionComplexity

FindHotspots walks all files under dir, analyzes them, and returns the top N most complex functions sorted by cyclomatic complexity descending.

func (*ComplexityAnalyzer) FormatReport added in v0.2.0 

func (ca *ComplexityAnalyzer) FormatReport(report *ComplexityReport) string

FormatReport formats a ComplexityReport into a human-readable string.

func (*ComplexityAnalyzer) SuggestRefactoring added in v0.2.0 

func (ca *ComplexityAnalyzer) SuggestRefactoring(fc FunctionComplexity) []string

SuggestRefactoring generates refactoring suggestions based on function metrics.

type ComplexityReport added in v0.2.0 

type ComplexityReport struct {
	File           string
	Functions      []FunctionComplexity
	FileComplexity float64
	LOC            int
	CLOC           int // comment lines
	BlankLines     int
}

ComplexityReport holds complexity metrics for a single file.

type Contributor added in v0.2.0 

type Contributor struct {
	Name       string
	Commits    int
	Percentage float64
	LastActive time.Time
}

Contributor represents a person who has contributed to a file.

type DeadCode added in v0.2.0 

type DeadCode struct {
	File       string
	Line       int
	Name       string
	Kind       string  // "function", "type", "var", "const", "method"
	Confidence float64 // 0.0 to 1.0
	Reason     string
}

DeadCode represents a detected dead code item.

type DeadCodeDetector added in v0.2.0 

type DeadCodeDetector struct {
	Declarations map[string]*Declaration
	References   map[string]int
	// contains filtered or unexported fields
}

DeadCodeDetector scans Go projects to find unused declarations.

func NewDeadCodeDetector added in v0.2.0 

func NewDeadCodeDetector() *DeadCodeDetector

NewDeadCodeDetector creates a new initialized DeadCodeDetector.

func (*DeadCodeDetector) FindUnused added in v0.2.0 

func (d *DeadCodeDetector) FindUnused() []DeadCode

FindUnused returns declarations with zero references, filtering out known special functions (main, init, test functions, interface implementations).

func (*DeadCodeDetector) FindUnusedExports added in v0.2.0 

func (d *DeadCodeDetector) FindUnusedExports(projectDir string) []DeadCode

FindUnusedExports finds exported symbols not referenced anywhere in the project.

func (*DeadCodeDetector) Scan added in v0.2.0 

func (d *DeadCodeDetector) Scan(projectDir string) ([]DeadCode, error)

Scan walks all Go files in projectDir, collects declarations and references, and returns detected dead code items.

func (*DeadCodeDetector) ScanFile added in v0.2.0 

func (d *DeadCodeDetector) ScanFile(path, content string)

ScanFile uses go/ast to extract declarations and references from a single file.

type Declaration added in v0.2.0 

type Declaration struct {
	Name     string
	Kind     string
	File     string
	Line     int
	Exported bool
	Package  string
}

Declaration represents a top-level declaration in a Go source file.

type Definition added in v0.2.0 

type Definition struct {
	Name       string
	Kind       string // "func", "type", "var", "const", "method", "interface"
	File       string
	Line       int
	Package    string
	Exported   bool
	Signature  string
	DocComment string
}

Definition represents a symbol definition in the codebase.

type DepEdge added in v0.2.0 

type DepEdge struct {
	From   string
	To     string
	Weight int // number of imports between these packages
}

DepEdge represents a directed edge from one package to another.

type DepGraph added in v0.2.0 

type DepGraph struct {
	Nodes map[string]*DepNode
	Edges []DepEdge
	Root  string
	// contains filtered or unexported fields
}

DepGraph represents a directed dependency graph of packages/modules.

func NewDepGraph added in v0.2.0 

func NewDepGraph() *DepGraph

NewDepGraph creates and returns a new empty DepGraph.

func (*DepGraph) AddEdge added in v0.2.0 

func (dg *DepGraph) AddEdge(edge DepEdge)

AddEdge adds a directed edge to the graph. If an edge between From and To already exists, its weight is incremented.

func (*DepGraph) AddNode added in v0.2.0 

func (dg *DepGraph) AddNode(node DepNode)

AddNode adds a node to the graph. If a node with the same ID already exists, it is overwritten.

func (*DepGraph) BuildFromGoMod added in v0.2.0 

func (dg *DepGraph) BuildFromGoMod(projectDir string) error

BuildFromGoMod reads go.mod and scans .go files to build the dependency graph.

func (*DepGraph) BuildFromPackageJSON added in v0.2.0 

func (dg *DepGraph) BuildFromPackageJSON(projectDir string) error

BuildFromPackageJSON reads package.json and scans JS/TS files to build the dependency graph.

func (*DepGraph) FindCycles added in v0.2.0 

func (dg *DepGraph) FindCycles() [][]string

FindCycles detects circular dependencies and returns all cycles found.

func (*DepGraph) HotPaths added in v0.2.0 

func (dg *DepGraph) HotPaths() [][]string

HotPaths finds the most-depended-on paths using a PageRank-like importance scoring. Returns paths sorted by importance (most critical first).

func (*DepGraph) Layers added in v0.2.0 

func (dg *DepGraph) Layers() [][]string

Layers groups packages into layers based on dependency depth. Layer 0 contains packages with no dependencies, layer 1 depends only on layer 0, etc.

func (*DepGraph) RenderASCII added in v0.2.0 

func (dg *DepGraph) RenderASCII(maxWidth int) string

RenderASCII generates an ASCII art visualization of the dependency graph.

func (*DepGraph) RenderDOT added in v0.2.0 

func (dg *DepGraph) RenderDOT() string

RenderDOT generates a Graphviz DOT format representation of the graph.

func (*DepGraph) RenderMermaid added in v0.2.0 

func (dg *DepGraph) RenderMermaid() string

RenderMermaid generates a Mermaid.js format representation for markdown rendering.

func (*DepGraph) Stats added in v0.2.0 

func (dg *DepGraph) Stats() GraphStats

Stats returns summary statistics about the dependency graph.

func (*DepGraph) TopologicalSort added in v0.2.0 

func (dg *DepGraph) TopologicalSort() []string

TopologicalSort returns packages in dependency order (leaves first). Packages with no dependencies appear first.

type DepNode added in v0.2.0 

type DepNode struct {
	ID         string // package/module path
	Name       string // short name
	Type       string // "internal", "external", "stdlib"
	FileCount  int
	LOC        int
	ImportedBy []string
	Imports    []string
}

DepNode represents a single package or module in the dependency graph.

type DocIssue added in v0.2.0 

type DocIssue struct {
	Line       int
	Symbol     string
	Type       string // "missing", "outdated", "incomplete", "unclear"
	Message    string
	Severity   string // "error", "warning", "info"
	Suggestion string
}

DocIssue represents a single documentation problem found in a file.

type DocLintResult added in v0.2.0 

type DocLintResult struct {
	File   string
	Issues []DocIssue
	Score  float64
	Stats  DocStats
}

DocLintResult holds the documentation quality analysis for a single file.

type DocLinter added in v0.2.0 

type DocLinter struct {
	MinCommentLength int
	RequireExported  bool
	// contains filtered or unexported fields
}

DocLinter performs documentation quality analysis on Go source files.

func NewDocLinter added in v0.2.0 

func NewDocLinter() *DocLinter

NewDocLinter creates a DocLinter with sensible default configuration.

func (*DocLinter) CheckGoDoc added in v0.2.0 

func (dl *DocLinter) CheckGoDoc(name, comment string) []DocIssue

CheckGoDoc inspects a doc comment for an exported symbol and returns issues.

func (*DocLinter) CoverageReport added in v0.2.0 

func (dl *DocLinter) CoverageReport(results []*DocLintResult) string

CoverageReport produces an overall documentation coverage summary.

func (*DocLinter) FormatReport added in v0.2.0 

func (dl *DocLinter) FormatReport(results []*DocLintResult) string

FormatReport produces a human-readable documentation lint report.

func (*DocLinter) LintDirectory added in v0.2.0 

func (dl *DocLinter) LintDirectory(dir string) ([]*DocLintResult, error)

LintDirectory walks all Go files in a directory and lints each one.

func (*DocLinter) LintFile added in v0.2.0 

func (dl *DocLinter) LintFile(path, content string) (*DocLintResult, error)

LintFile analyzes the documentation quality of a single Go source file.

func (*DocLinter) SuggestDocComment added in v0.2.0 

func (dl *DocLinter) SuggestDocComment(name, kind, signature string) string

SuggestDocComment generates a suggested doc comment for a given symbol.

type DocStats added in v0.2.0 

type DocStats struct {
	TotalExported int
	Documented    int
	Coverage      float64
	AvgLength     int
	MissingCount  int
}

DocStats holds aggregate documentation statistics for a file.

type Document added in v0.2.0 

type Document struct {
	ID      string
	Path    string
	Content string
	Terms   map[string]int
	Length  int
	Type    string // "function", "type", "file", "block"
}

Document represents a single indexable unit (function, type, file, or block).

type EnhancedGoParser 

type EnhancedGoParser struct{}

EnhancedGoParser uses go/ast for accurate Go symbol extraction. Replaces regex-based parsing for Go files with zero-CGO AST parsing. This covers what tree-sitter would give us: method receivers, nested types, interface methods, embedded fields — without requiring CGO.

func (*EnhancedGoParser) ParseGoFile 

func (p *EnhancedGoParser) ParseGoFile(content, filePath string) []EnhancedSymbol

ParseGoFile extracts all symbols from a Go file using the standard library parser.

type EnhancedSymbol 

type EnhancedSymbol struct {
	Name       string
	Kind       string // function, method, type, interface, struct, field, variable, interface_method
	Line       int
	File       string
	Exported   bool
	References []string // symbols this one references
}

EnhancedSymbol represents a richly-extracted code symbol with references.

func ParsePythonFile 

func ParsePythonFile(content, filePath string) []EnhancedSymbol

ParsePythonFile extracts symbols from Python using enhanced regex patterns. Handles: classes, methods (with self), decorators, nested classes.

type FileCache 

type FileCache struct {
	Hash    string   `json:"hash"`
	Mtime   int64    `json:"mtime"`
	Symbols []string `json:"symbols"`
}

FileCache holds the cached metadata for a single file.

type FileGroup added in v0.2.0 

type FileGroup struct {
	Name       string
	Files      []string
	Reason     string
	Confidence float64
	Type       string // "package", "feature", "layer", "test_pair", "config"
}

FileGroup represents a set of files that logically belong together.

type FileGrouper added in v0.2.0 

type FileGrouper struct {
	ProjectDir string
	Groups     []FileGroup
	// contains filtered or unexported fields
}

FileGrouper identifies which files belong together and should be edited as a unit.

func NewFileGrouper added in v0.2.0 

func NewFileGrouper(projectDir string) *FileGrouper

NewFileGrouper creates a new FileGrouper for the given project directory.

func (*FileGrouper) AnalyzeGroups added in v0.2.0 

func (fg *FileGrouper) AnalyzeGroups() ([]FileGroup, error)

AnalyzeGroups runs multiple strategies to identify file groups in the project.

func (*FileGrouper) FindByFeature added in v0.2.0 

func (fg *FileGrouper) FindByFeature(featureName string) []string

FindByFeature finds all files related to a feature by name.

func (*FileGrouper) FindRelated added in v0.2.0 

func (fg *FileGrouper) FindRelated(file string) []string

FindRelated returns all files related to the given file.

func (*FileGrouper) FindTestPair added in v0.2.0 

func (fg *FileGrouper) FindTestPair(file string) string

FindTestPair finds the corresponding test file for a source file or vice versa.

func (*FileGrouper) SuggestEditGroup added in v0.2.0 

func (fg *FileGrouper) SuggestEditGroup(targetFile string) []string

SuggestEditGroup suggests related files that likely need updates when editing a target file.

type FileMap 

type FileMap struct {
	Path    string
	Symbols []Symbol
}

FileMap holds the extracted symbols for a single file.

type FileOwnership added in v0.2.0 

type FileOwnership struct {
	Path         string
	PrimaryOwner string
	Contributors []Contributor
	LastModified time.Time
	TotalCommits int
}

FileOwnership represents the ownership metadata for a single file.

type FileSummary 

type FileSummary struct {
	Path      string
	Functions []string // exported function signatures
	Types     []string // exported type names
	LineCount int
}

FileSummary is a level-3 summary of a single file.

type FileWatcher 

type FileWatcher struct {
	// contains filtered or unexported fields
}

FileWatcher monitors the project directory for changes and triggers re-indexing.

func NewFileWatcher 

func NewFileWatcher(root string, onChange func(path string)) (*FileWatcher, error)

NewFileWatcher creates a watcher for Go/Python/TS files in the given root.

func (*FileWatcher) Start 

func (fw *FileWatcher) Start()

Start begins watching for file changes in a goroutine.

func (*FileWatcher) Stop 

func (fw *FileWatcher) Stop()

Stop terminates the watcher.

type FunctionComplexity added in v0.2.0 

type FunctionComplexity struct {
	Name       string
	StartLine  int
	EndLine    int
	Cyclomatic int
	Cognitive  int
	LOC        int
	Parameters int
	Returns    int
	Nesting    int // max depth
}

FunctionComplexity holds complexity metrics for a single function.

type GitignoreRules 

type GitignoreRules struct {
	// contains filtered or unexported fields
}

GitignoreRules holds composed gitignore patterns from multiple levels.

func LoadGitignoreRules 

func LoadGitignoreRules(dir string) *GitignoreRules

LoadGitignoreRules walks from dir up to the filesystem root, loading all .gitignore files. Rules from deeper directories take precedence (are appended last). Also loads the global gitignore (~/.config/git/ignore) if it exists.

func (*GitignoreRules) ShouldIgnore 

func (gr *GitignoreRules) ShouldIgnore(path string) bool

ShouldIgnore checks if a path should be ignored according to gitignore rules. The path should be relative to the repository root.

type GraphStats added in v0.2.0 

type GraphStats struct {
	TotalNodes    int
	InternalNodes int
	ExternalNodes int
	StdlibNodes   int
	TotalEdges    int
	MaxDepth      int
	Cycles        int
	MostImported  string
	MostImporting string
}

GraphStats holds summary statistics about the dependency graph.

type HealthIssue added in v0.2.0 

type HealthIssue struct {
	Dimension   string
	Description string
	Severity    string
	File        string
	Suggestion  string
}

HealthIssue represents a specific health concern in a project.

type HealthScore added in v0.2.0 

type HealthScore struct {
	Overall    float64
	Dimensions map[string]float64
	Issues     []HealthIssue
	Strengths  []string
	Grade      string
}

HealthScore represents the overall health assessment of a project.

type HealthScorer added in v0.2.0 

type HealthScorer struct {
	Weights map[string]float64
	// contains filtered or unexported fields
}

HealthScorer evaluates project health across multiple dimensions.

func NewHealthScorer added in v0.2.0 

func NewHealthScorer() *HealthScorer

NewHealthScorer creates a HealthScorer with default dimension weights.

func (*HealthScorer) Score added in v0.2.0 

func (hs *HealthScorer) Score(projectDir string) (*HealthScore, error)

Score evaluates the overall health of a project directory.

func (*HealthScorer) ScoreCodeQuality added in v0.2.0 

func (hs *HealthScorer) ScoreCodeQuality(dir string) (float64, []HealthIssue)

ScoreCodeQuality evaluates overall code quality signals.

func (*HealthScorer) ScoreComplexity added in v0.2.0 

func (hs *HealthScorer) ScoreComplexity(dir string) (float64, []HealthIssue)

ScoreComplexity evaluates code complexity across the project.

func (*HealthScorer) ScoreDependencies added in v0.2.0 

func (hs *HealthScorer) ScoreDependencies(dir string) (float64, []HealthIssue)

ScoreDependencies evaluates dependency health.

func (*HealthScorer) ScoreDocumentation added in v0.2.0 

func (hs *HealthScorer) ScoreDocumentation(dir string) (float64, []HealthIssue)

ScoreDocumentation evaluates documentation quality.

func (*HealthScorer) ScoreMaintainability added in v0.2.0 

func (hs *HealthScorer) ScoreMaintainability(dir string) (float64, []HealthIssue)

ScoreMaintainability evaluates how maintainable the codebase is.

func (*HealthScorer) ScoreSecurity added in v0.2.0 

func (hs *HealthScorer) ScoreSecurity(dir string) (float64, []HealthIssue)

ScoreSecurity evaluates basic security signals in the codebase.

func (*HealthScorer) ScoreTestCoverage added in v0.2.0 

func (hs *HealthScorer) ScoreTestCoverage(dir string) (float64, []HealthIssue)

ScoreTestCoverage evaluates testing practices and coverage.

type HierarchicalSummary 

type HierarchicalSummary struct {
	Root     string
	Packages []PackageSummary
}

HierarchicalSummary provides 3-level code summarization: Level 1: Project (all packages as one-liners) Level 2: Package (file list with exported symbols) Level 3: File (function signatures, no bodies)

func BuildHierarchy 

func BuildHierarchy(root string) (*HierarchicalSummary, error)

BuildHierarchy scans a Go project and builds a 3-level summary.

func (*HierarchicalSummary) FormatLevel1 

func (h *HierarchicalSummary) FormatLevel1(maxTokens int) string

FormatLevel1 returns the project-level summary (one line per package).

func (*HierarchicalSummary) FormatLevel2 

func (h *HierarchicalSummary) FormatLevel2(pkgPath string, maxTokens int) string

FormatLevel2 returns the package-level summary (files + exported symbols).

func (*HierarchicalSummary) FormatLevel3 

func (h *HierarchicalSummary) FormatLevel3(filePath string) string

FormatLevel3 returns a file-level summary (full function signatures).

type ImportGraph 

type ImportGraph struct {
	// contains filtered or unexported fields
}

ImportGraph builds and queries file-level import/dependency relationships. When file A is identified as relevant, this finds: - Files that A imports (its dependencies) - Files that import A (its dependents)

This is the cheapest cross-file signal. Research shows import graph traversal prevents "undefined symbol" errors by 30-40%.

func BuildImportGraph 

func BuildImportGraph(root string) (*ImportGraph, error)

BuildImportGraph scans source files in the given root directory and builds the import graph. For Go, this parses import statements and maps import paths to local files. Also supports basic Python and TypeScript/JavaScript.

func (*ImportGraph) DependenciesOf 

func (g *ImportGraph) DependenciesOf(filePath string, maxDepth int) []string

DependenciesOf returns files that the given file imports (up to maxDepth).

func (*ImportGraph) DependentsOf 

func (g *ImportGraph) DependentsOf(filePath string, maxDepth int) []string

DependentsOf returns files that import the given file (up to maxDepth).

func (*ImportGraph) Edges 

func (g *ImportGraph) Edges() map[string][]string

Edges returns the forward edge map (file -> imports). Useful for inspection.

func (*ImportGraph) ImpactSet 

func (g *ImportGraph) ImpactSet(files []string, maxDepth int) []string

ImpactSet returns the union of dependencies and dependents for a set of files. This is used for change-set-aware context: "what other files matter given these changes?"

func (*ImportGraph) Reverse 

func (g *ImportGraph) Reverse() map[string][]string

Reverse returns the reverse edge map (file -> dependents). Useful for inspection.

type IncrementalMap 

type IncrementalMap struct {
	// contains filtered or unexported fields
}

IncrementalMap maintains a cached symbol index that only reprocesses changed files. It stores file hashes (SHA-256 of content) in a cache file (.hawk/repomap-cache.json). On regeneration, only files whose hash changed are re-parsed. Symbols from changed files are merged into the existing map, and symbols from deleted files are removed.

func NewIncrementalMap 

func NewIncrementalMap(cacheDir string) (*IncrementalMap, error)

NewIncrementalMap loads or creates a repomap cache. cacheDir is the directory where the cache file will be stored (typically ".hawk").

func (*IncrementalMap) AllSymbols 

func (im *IncrementalMap) AllSymbols() map[string][]string

AllSymbols returns every symbol across all cached files.

func (*IncrementalMap) Save 

func (im *IncrementalMap) Save() error

Save persists the cache to disk.

func (*IncrementalMap) Symbols 

func (im *IncrementalMap) Symbols(path string) []string

Symbols returns all cached symbols for a file.

func (*IncrementalMap) Update 

func (im *IncrementalMap) Update(rootDir string) (changed []string, err error)

Update scans the directory and only reprocesses changed files. Returns the list of files that were re-indexed. Uses fast change detection: checks mtime first, only hashes if mtime differs.

type IndexPatterns 

type IndexPatterns struct {
	Include []string `json:"include"` // if non-empty, ONLY files matching these are indexed
	Exclude []string `json:"exclude"` // files matching these are NEVER indexed (overrides include)
}

IndexPatterns controls which files are indexed.

func DefaultIndexPatterns 

func DefaultIndexPatterns() IndexPatterns

DefaultIndexPatterns returns sensible defaults.

func LoadIndexPatterns 

func LoadIndexPatterns() IndexPatterns

LoadIndexPatterns reads from .hawk/index.json or uses defaults.

func (IndexPatterns) ShouldIndex 

func (p IndexPatterns) ShouldIndex(path string) bool

ShouldIndex checks if a path should be indexed based on include/exclude patterns.

type InterfaceExtraction 

type InterfaceExtraction struct {
	Functions []string // "func Name(args) returns"
	Types     []string // "type Name struct/interface"
	Constants []string // "const Name = ..."
	Package   string
}

InterfaceExtraction shows only exported signatures (no bodies). Uses ~100 tokens per file vs ~500+ for full content.

func ExtractInterface 

func ExtractInterface(filePath string) (*InterfaceExtraction, error)

ExtractInterface parses a Go file and returns only its exported API surface.

func (*InterfaceExtraction) Format 

func (ie *InterfaceExtraction) Format() string

Format returns the interface as a compact string.

func (*InterfaceExtraction) TokenEstimate 

func (ie *InterfaceExtraction) TokenEstimate() int

TokenEstimate returns approximate token count for this interface.

type MigrationDetector added in v0.2.0 

type MigrationDetector struct {
	Rules []MigrationRule
	// contains filtered or unexported fields
}

MigrationDetector scans source files to identify migration opportunities.

func NewMigrationDetector added in v0.2.0 

func NewMigrationDetector() *MigrationDetector

NewMigrationDetector creates a MigrationDetector with built-in rules.

func (*MigrationDetector) AddRule added in v0.2.0 

func (md *MigrationDetector) AddRule(rule MigrationRule)

AddRule adds a custom migration rule to the detector.

func (*MigrationDetector) Scan added in v0.2.0 

func (md *MigrationDetector) Scan(projectDir string) ([]MigrationOpportunity, error)

Scan walks projectDir and applies matching rules to each source file.

func (*MigrationDetector) ScanFile added in v0.2.0 

func (md *MigrationDetector) ScanFile(path, content string) []MigrationOpportunity

ScanFile applies all matching rules to the given file content.

type MigrationOpportunity added in v0.2.0 

type MigrationOpportunity struct {
	File        string
	Line        int
	OldPattern  string
	NewPattern  string
	Reason      string
	Priority    string // "high", "medium", "low"
	AutoFixable bool
	Category    string // "deprecated", "idiom", "security", "performance"
}

MigrationOpportunity represents a detected code pattern that could be updated.

type MigrationRule added in v0.2.0 

type MigrationRule struct {
	ID          string
	Language    string
	OldPattern  *regexp.Regexp
	NewPattern  string
	Reason      string
	Priority    string
	AutoFixable bool
	Category    string
	Since       string // version when old pattern became deprecated
}

MigrationRule defines a pattern to detect and suggest replacement. 

type NavIndex struct {
	Definitions     map[string]*Definition
	References      map[string][]*Reference
	Implementations map[string][]string
	// contains filtered or unexported fields
}

NavIndex provides code navigation capabilities (go-to-definition, find-references, find-implementations) without requiring an LSP server. It parses Go source files using go/ast and builds an in-memory index of definitions, references, and interface implementations.

func NewNavIndex added in v0.2.0 

func NewNavIndex() *NavIndex

NewNavIndex creates a new empty navigation index. 

func (idx *NavIndex) BuildIndex(projectDir string) error

BuildIndex parses all Go files under projectDir and populates the index with definitions, references, and implementation mappings. 

func (idx *NavIndex) FindCallees(funcName string) []string

FindCallees returns all functions called by the given function. 

func (idx *NavIndex) FindCallers(funcName string) []*Reference

FindCallers returns all call sites of the given function. 

func (idx *NavIndex) FindImplementations(interfaceName string) []string

FindImplementations returns all types that implement the given interface. 

func (idx *NavIndex) FindReferences(symbol string) []*Reference

FindReferences returns all references to the given symbol. 

func (idx *NavIndex) GoToDefinition(symbol string) *Definition

GoToDefinition returns the definition for the given symbol name. 

func (idx *NavIndex) SearchSymbols(query string, kind string) []*Definition

SearchSymbols performs a fuzzy search across all definitions, optionally filtered by kind. 

func (idx *NavIndex) TypeHierarchy(typeName string) string

TypeHierarchy shows the interface -> implementations tree for a type.

type Options 

type Options struct {
	MaxFiles       int
	MaxTokens      int
	IgnorePatterns []string
}

Options configures repo map generation.

type OwnerRule added in v0.2.0 

type OwnerRule struct {
	Pattern string
	Owners  []string
	Source  string // "codeowners", "git_history", "config"
}

OwnerRule represents a code ownership rule from a CODEOWNERS file or config.

type OwnershipMap added in v0.2.0 

type OwnershipMap struct {
	Owners map[string]*FileOwnership
	Rules  []OwnerRule
	// contains filtered or unexported fields
}

OwnershipMap tracks code ownership across a repository by combining git history analysis with CODEOWNERS-style rules. It identifies primary owners, contributors, and bus-factor risks for each file.

func NewOwnershipMap added in v0.2.0 

func NewOwnershipMap() *OwnershipMap

NewOwnershipMap creates an empty OwnershipMap ready for population.

func (*OwnershipMap) BuildFromGitHistory added in v0.2.0 

func (om *OwnershipMap) BuildFromGitHistory(projectDir string) error

BuildFromGitHistory populates the ownership map by analyzing git log output. It runs `git log --format=%an --name-only` to map files to contributors, calculates ownership percentages per file, and determines the primary owner.

func (*OwnershipMap) DetectBusFactorRisk added in v0.2.0 

func (om *OwnershipMap) DetectBusFactorRisk() []string

DetectBusFactorRisk identifies files where only one person has ever committed. These files represent a "bus factor" risk: if that person becomes unavailable, no one else has context on the code.

func (*OwnershipMap) FindExpertFor added in v0.2.0 

func (om *OwnershipMap) FindExpertFor(path string) string

FindExpertFor returns the best person to review changes to a given file path. It considers both git history and CODEOWNERS rules, preferring CODEOWNERS when available since those represent explicit ownership assignments.

func (*OwnershipMap) FormatOwnership added in v0.2.0 

func (om *OwnershipMap) FormatOwnership(limit int) string

FormatOwnership produces a human-readable summary of code ownership. The limit parameter controls how many top owners to display.

func (*OwnershipMap) GetOwner added in v0.2.0 

func (om *OwnershipMap) GetOwner(path string) *FileOwnership

GetOwner returns the FileOwnership for a given path, or nil if not tracked.

func (*OwnershipMap) GetOwnersByDirectory added in v0.2.0 

func (om *OwnershipMap) GetOwnersByDirectory(dir string) map[string]string

GetOwnersByDirectory returns a mapping of directory path to the primary owner of that directory (the person with most commits in that directory).

func (*OwnershipMap) LoadCodeowners added in v0.2.0 

func (om *OwnershipMap) LoadCodeowners(path string) error

LoadCodeowners parses a CODEOWNERS file and adds the rules to the ownership map. The file format follows GitHub's CODEOWNERS convention: 

pattern @owner1 @owner2

Lines starting with # are comments. Blank lines are ignored.

func (*OwnershipMap) SuggestReviewers added in v0.2.0 

func (om *OwnershipMap) SuggestReviewers(changedFiles []string) []string

SuggestReviewers returns a deduplicated list of suggested reviewers for a set of changed files, based on ownership data. Reviewers are ordered by relevance (number of files they own among the changed set).

type PackageSummary 

type PackageSummary struct {
	Path    string
	Name    string
	Files   []FileSummary
	Symbols int
}

PackageSummary is a level-2 summary of a Go package.

type PredictedFile 

type PredictedFile struct {
	Path   string
	Score  float64
	Reason string // why it was predicted relevant
}

PredictedFile is a file predicted to be relevant to the current task.

type RecentEdit 

type RecentEdit struct {
	Path string
	At   time.Time
}

RecentEdit tracks a file that was recently modified.

type RecentEditTracker 

type RecentEditTracker struct {
	// contains filtered or unexported fields
}

RecentEditTracker maintains a list of recently edited files.

func NewRecentEditTracker 

func NewRecentEditTracker(max int) *RecentEditTracker

NewRecentEditTracker creates a tracker with a max capacity.

func (*RecentEditTracker) Recent 

func (t *RecentEditTracker) Recent(within time.Duration) []RecentEdit

Recent returns edits within the given duration.

func (*RecentEditTracker) Record 

func (t *RecentEditTracker) Record(path string)

Record adds a file edit event.

type Reference added in v0.2.0 

type Reference struct {
	File    string
	Line    int
	Context string // surrounding line text
	Kind    string // "call", "type_use", "import", "assignment"
}

Reference represents a usage of a symbol in the codebase.

type RelevancePrediction 

type RelevancePrediction struct {
	Files []PredictedFile
}

RelevancePrediction holds predicted files with their relevance scores.

func PredictRelevantFiles 

func PredictRelevantFiles(prompt string, recentEdits []RecentEdit, graph *ImportGraph, symbols map[string]string) *RelevancePrediction

PredictRelevantFiles predicts which files are likely relevant given: - The user's prompt (keyword matching against repo map symbols) - Recently edited files (locality heuristic) - Import graph relationships - Co-change history

type RepoMap 

type RepoMap struct {
	Files    []FileMap
	TokenEst int
}

RepoMap is the full repository map result.

func Generate 

func Generate(dir string, opts Options) (*RepoMap, error)

Generate scans dir and produces a RepoMap with symbols from supported files.

func (*RepoMap) Format 

func (rm *RepoMap) Format(maxTokens int) string

Format renders the repo map as a text block, truncated to fit maxTokens.

type RerankResult 

type RerankResult struct {
	Chunk CodeSearchResult
	Score float64
}

RerankResult pairs a search result with a re-ranking score.

func Rerank 

func Rerank(query string, candidates []CodeSearchResult, topK int) []RerankResult

Rerank re-scores candidates using BM25 (k1=1.2, b=0.75) against the query and returns the top-K results sorted by descending score.

type SearchHit added in v0.2.0 

type SearchHit struct {
	Document     *Document
	Score        float64
	MatchedTerms []string
	Snippet      string
}

SearchHit represents a single search result with scoring information.

type SemanticIndex 

type SemanticIndex struct {
	// contains filtered or unexported fields
}

SemanticIndex holds chunked source files and supports TF-IDF search.

func BuildSemanticIndex 

func BuildSemanticIndex(dir string, ignore []string, maxFiles int) (*SemanticIndex, error)

BuildSemanticIndex scans dir, chunks files into ~40-line blocks, and builds an index.

func LoadSemanticIndex 

func LoadSemanticIndex(path string) (*SemanticIndex, error)

LoadSemanticIndex decodes a previously saved index from a gob file.

func (*SemanticIndex) Save 

func (idx *SemanticIndex) Save(path string) error

Save encodes the index to a file using gob.

func (*SemanticIndex) Search 

func (idx *SemanticIndex) Search(query string, topK int) []CodeChunk

Search performs TF-IDF based search over the index, returning the top-K chunks.

func (*SemanticIndex) Size 

func (idx *SemanticIndex) Size() int

Size returns the number of chunks in the index.

type SemanticSearchIndex added in v0.2.0 

type SemanticSearchIndex struct {
	Documents map[string]*Document
	IDF       map[string]float64
	AvgDocLen float64
	TotalDocs int
	// contains filtered or unexported fields
}

SemanticSearchIndex holds documents indexed for BM25 semantic search.

func NewSemanticSearchIndex added in v0.2.0 

func NewSemanticSearchIndex() *SemanticSearchIndex

NewSemanticIndex creates a new empty SemanticSearchIndex ready for use.

func (*SemanticSearchIndex) BM25Score added in v0.2.0 

func (si *SemanticSearchIndex) BM25Score(queryTerms []string, doc *Document) float64

BM25Score computes the BM25 score for a document given query terms. Uses standard BM25 with k1=1.5, b=0.75.

func (*SemanticSearchIndex) IndexDirectory added in v0.2.0 

func (si *SemanticSearchIndex) IndexDirectory(dir string) error

IndexDirectory walks a directory and indexes all supported source files.

func (*SemanticSearchIndex) IndexFile added in v0.2.0 

func (si *SemanticSearchIndex) IndexFile(path, content string)

IndexFile splits a file into documents (functions, types, blocks) and indexes them.

func (*SemanticSearchIndex) RebuildIndex added in v0.2.0 

func (si *SemanticSearchIndex) RebuildIndex() error

RebuildIndex recalculates IDF values and average document length.

func (*SemanticSearchIndex) Search added in v0.2.0 

func (si *SemanticSearchIndex) Search(query string, limit int) []SearchHit

Search tokenizes the query and returns the top-scoring documents using BM25.

func (*SemanticSearchIndex) SearchByIntent added in v0.2.0 

func (si *SemanticSearchIndex) SearchByIntent(intent string) []SearchHit

SearchByIntent searches using expanded query terms to find code by meaning/intent. For example, "authentication" will find auth-related code even if the exact word isn't present.

type ShapleyRanker 

type ShapleyRanker struct {
	// contains filtered or unexported fields
}

ShapleyRanker scores code chunks by their marginal contribution to generation quality using an approximate Shapley value approach.

func NewShapleyRanker 

func NewShapleyRanker(chunks []CodeChunk) *ShapleyRanker

NewShapleyRanker creates a ranker from the given code chunks.

func (*ShapleyRanker) ComputeScores 

func (sr *ShapleyRanker) ComputeScores(relevantPaths []string, query string) []ShapleyScore

ComputeScores calculates approximate Shapley values for each chunk.

Score = relevance_to_query * centrality_in_graph * recency_bonus - redundancy_penalty

  • relevance: keyword overlap with query
  • centrality: how many other chunks reference symbols in this chunk
  • recency: files in relevantPaths get a boost
  • redundancy: chunks similar to already-scored chunks get penalized

func (*ShapleyRanker) Format 

func (sr *ShapleyRanker) Format(chunks []CodeChunk) string

Format renders selected chunks as a text block for prompt injection.

func (*ShapleyRanker) SelectOptimalContext 

func (sr *ShapleyRanker) SelectOptimalContext(query string, tokenBudget int) []CodeChunk

SelectOptimalContext greedily selects chunks that maximize information within the token budget, recomputing redundancy penalties after each addition.

type ShapleyScore 

type ShapleyScore struct {
	Path      string
	StartLine int
	EndLine   int
	Score     float64 // higher = more helpful in context
	Content   string
}

ShapleyScore represents the computed marginal contribution of a code chunk.

type SmellDetector added in v0.2.0 

type SmellDetector struct {
	Thresholds SmellThresholds
	// contains filtered or unexported fields
}

SmellDetector identifies code smells using structural analysis.

func NewSmellDetector added in v0.2.0 

func NewSmellDetector() *SmellDetector

NewSmellDetector creates a SmellDetector with default thresholds.

func (*SmellDetector) DetectDataClump added in v0.2.0 

func (sd *SmellDetector) DetectDataClump(content string) []CodeSmell

DetectDataClump finds groups of parameters that appear together in multiple functions.

func (*SmellDetector) DetectFeatureEnvy added in v0.2.0 

func (sd *SmellDetector) DetectFeatureEnvy(content string) []CodeSmell

DetectFeatureEnvy finds methods that use another type's fields more than their own.

func (*SmellDetector) DetectGodObject added in v0.2.0 

func (sd *SmellDetector) DetectGodObject(content string) []CodeSmell

DetectGodObject finds types with too many methods or fields.

func (*SmellDetector) DetectInFile added in v0.2.0 

func (sd *SmellDetector) DetectInFile(path, content string) []CodeSmell

DetectInFile runs all smell detectors on a file given its path and content.

func (*SmellDetector) DetectLongParamList added in v0.2.0 

func (sd *SmellDetector) DetectLongParamList(content string) []CodeSmell

DetectLongParamList finds functions with too many parameters.

func (*SmellDetector) DetectPrimitiveObsession added in v0.2.0 

func (sd *SmellDetector) DetectPrimitiveObsession(content string) []CodeSmell

DetectPrimitiveObsession finds functions taking too many string/int params.

func (*SmellDetector) ScanDirectory added in v0.2.0 

func (sd *SmellDetector) ScanDirectory(dir string) []CodeSmell

ScanDirectory walks a directory and detects code smells in all Go files.

type SmellThresholds added in v0.2.0 

type SmellThresholds struct {
	MaxParams          int
	MaxMethodsPerType  int
	MaxFieldsPerStruct int
	MaxImports         int
	MaxFileLines       int
	MaxFuncLines       int
	MinMethodCohesion  float64
}

SmellThresholds defines configurable limits for code smell detection.

type SummaryGenerator added in v0.2.0 

type SummaryGenerator struct {
	ProjectDir string
	MaxTokens  int
	// contains filtered or unexported fields
}

SummaryGenerator produces concise codebase overviews for context injection.

func NewSummaryGenerator added in v0.2.0 

func NewSummaryGenerator(projectDir string, maxTokens int) *SummaryGenerator

NewSummaryGenerator creates a new SummaryGenerator for the given project directory.

func (*SummaryGenerator) Generate added in v0.2.0 

func (sg *SummaryGenerator) Generate() (*CodebaseSummary, error)

Generate walks the project directory, analyzes packages, identifies entry points and key files, infers architecture, and produces a CodebaseSummary.

type SummaryPackageInfo added in v0.2.0 

type SummaryPackageInfo struct {
	Name          string
	Path          string
	Purpose       string
	PublicSymbols int
	Files         int
	LOC           int
	Dependencies  []string
	Dependents    []string
}

SummaryPackageInfo holds the overview of a single package/module for summaries.

type Symbol 

type Symbol struct {
	Name string
	Kind string
	Line int
}

Symbol represents a top-level code symbol (function, type, class, etc.).

func ParseFileEnhanced added in v0.2.0 

func ParseFileEnhanced(path string) ([]Symbol, error)

ParseFileEnhanced is the new default parser entry point. It dispatches to parseGoAST for .go files and enhanced regex parsers for Python, TypeScript, JavaScript, and Rust. For other languages, it falls back to the existing regex parsers.

func ParseSourceEnhanced added in v0.2.0 

func ParseSourceEnhanced(src, ext string) ([]Symbol, error)

ParseSourceEnhanced parses source code directly without reading from disk. Useful for testing.

type SymbolGraph 

type SymbolGraph struct {
	// contains filtered or unexported fields
}

SymbolGraph is a directed graph of symbol references used for PageRank computation over a codebase.

func BuildSymbolGraph 

func BuildSymbolGraph(dir string, opts Options) (*SymbolGraph, error)

BuildSymbolGraph scans the directory, extracts symbols using the existing repomap parsers, then builds a directed graph by grepping for references.

func (*SymbolGraph) ComputePageRank 

func (sg *SymbolGraph) ComputePageRank(iterations int, damping float64)

ComputePageRank runs the standard PageRank algorithm on the symbol graph. 

rank[i] = (1-d) + d * sum(rank[j]/outlinks[j]) for all j->i

Default: iterations=20, damping=0.85.

func (*SymbolGraph) FormatMap 

func (sg *SymbolGraph) FormatMap(maxTokens int) string

FormatMap renders the ranked symbols as a repo map string, highest-rank first, stopping when the estimated token budget is reached.

func (*SymbolGraph) TopSymbols 

func (sg *SymbolGraph) TopSymbols(n int) []SymbolNode

TopSymbols returns the top-N symbols ordered by rank (descending).

type SymbolNode 

type SymbolNode struct {
	File   string
	Symbol string
	Kind   string
	Rank   float64
}

SymbolNode is a single node in the symbol graph.

type TreeContextRenderer added in v0.2.0 

type TreeContextRenderer struct{}

TreeContextRenderer renders symbols with parent scope context, showing definition signatures indented under their parent scope like a tree outline.

type TreeSitterParser added in v0.2.0 

type TreeSitterParser struct {
	// IncludeUnexported controls whether unexported symbols are included.
	// By default only exported/public symbols are returned for Go.
	IncludeUnexported bool
}

TreeSitterParser provides language-aware structural parsing that replaces simple regex-based symbol extraction. For Go files, it uses the stdlib go/parser + go/ast for true AST-level parsing. For other languages, it uses enhanced regex patterns with scope-tracking to produce AST-like results.

This is a "tree-sitter-inspired" approach: it produces the same kinds of structured, scope-aware symbol extraction that tree-sitter would, without requiring any CGO dependencies.

func NewTreeSitterParser added in v0.2.0 

func NewTreeSitterParser() *TreeSitterParser

NewTreeSitterParser creates a new parser with default settings.

func (*TreeSitterParser) ParseFile added in v0.2.0 

func (p *TreeSitterParser) ParseFile(path string) ([]Symbol, error)

ParseFile dispatches to the appropriate language parser based on file extension.

func (*TreeSitterParser) ParseSource added in v0.2.0 

func (p *TreeSitterParser) ParseSource(src, ext, path string) ([]Symbol, error)

ParseSource parses source code given its extension and optional path.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.