initial commit

indexer/walker.go

@@ -0,0 +1,38 @@
+package indexer
+
+import (
+	"bytes"
+	"os/exec"
+	"strings"
+
+	"github.com/odvcencio/gotreesitter/grammars"
+)
+
+// WalkFiles returns all git-tracked files that tree-sitter can parse.
+// It uses `git ls-files` to respect .gitignore rules correctly.
+func WalkFiles(root string) ([]string, error) {
+	cmd := exec.Command("git", "ls-files", "--cached", "--others", "--exclude-standard")
+	cmd.Dir = root
+	out, err := cmd.Output()
+	if err != nil {
+		return nil, err
+	}
+
+	var files []string
+	for _, line := range bytes.Split(out, []byte("\n")) {
+		relPath := strings.TrimSpace(string(line))
+		if relPath == "" {
+			continue
+		}
+
+		// Check if tree-sitter can handle this file
+		// DetectLanguage works on filename, not full path
+		parts := strings.Split(relPath, "/")
+		filename := parts[len(parts)-1]
+		if entry := grammars.DetectLanguage(filename); entry != nil {
+			files = append(files, relPath)
+		}
+	}
+
+	return files, nil
+}