fix: resolve 5 bugs identified in code review

- Fix malformed YAML in config_test.go (incorrect indentation)
- Add validation for empty file_extensions in Config.Validate()
- Remove obsolete max_depth test case (field no longer exists)
- Remove unused global cfg variable in main.go
- Fix race condition in ScrapeSites by counting URLs before goroutines
- Remove unreachable JavaScript code in scroll script, add proper delay
- Standardize file extensions to not include leading dot

cmd/files.go

@@ -33,7 +33,7 @@ whose name is <project-directory-name>-rollup-<timestamp>.md.`,
 
 func init() {
 	filesCmd.Flags().StringVarP(&path, "path", "p", ".", "Path to the project directory")
-	filesCmd.Flags().StringVarP(&fileTypes, "types", "t", ".go,.md,.txt", "Comma-separated list of file extensions to include")
+	filesCmd.Flags().StringVarP(&fileTypes, "types", "t", "go,md,txt", "Comma-separated list of file extensions to include (without leading dot)")
 	filesCmd.Flags().StringVarP(&codeGenPatterns, "codegen", "g", "", "Comma-separated list of glob patterns for code-generated files")
 	filesCmd.Flags().StringVarP(&ignorePatterns, "ignore", "i", "", "Comma-separated list of glob patterns for files to ignore")
 }

internal/config/config.go

@@ -88,6 +88,10 @@ func Load(configPath string) (*Config, error) {
 
 // Validate checks the configuration for any invalid values
 func (c *Config) Validate() error {
+	if len(c.FileExtensions) == 0 && len(c.Sites) == 0 {
+		return fmt.Errorf("file_extensions or sites must be specified")
+	}
+
 	if c.RequestsPerSecond != nil && *c.RequestsPerSecond <= 0 {
 		return fmt.Errorf("requests_per_second must be positive")
 	}

internal/config/config_test.go

@@ -10,8 +10,8 @@ func TestLoad(t *testing.T) {
 	// Create a temporary config file
 	content := []byte(`
 file_extensions:
-  - .go
+  - go
-  - .md
+  - md
 ignore_paths:
   - "*.tmp"
   - "**/*.log"
@@ -27,7 +27,7 @@ sites:
       - "/blog"
     exclude_paths:
       - "/admin"
-      file_name_prefix: "example"
+    file_name_prefix: "example"
     path_overrides:
       - path: "/special"
         css_locator: ".special-content"
@@ -61,7 +61,7 @@ burst_limit: 5
 	rps := 1.0
 	bl := 5
 	expectedConfig := &Config{
-		FileExtensions:     []string{".go", ".md"},
+		FileExtensions:     []string{"go", "md"},
 		IgnorePaths:        []string{"*.tmp", "**/*.log"},
 		CodeGeneratedPaths: []string{"generated_*.go"},
 		Sites: []SiteConfig{
@@ -100,7 +100,7 @@ func TestValidate(t *testing.T) {
 		{
 			name: "Valid config",
 			config: Config{
-				FileExtensions: []string{".go"},
+				FileExtensions: []string{"go"},
 				Sites: []SiteConfig{
 					{BaseURL: "https://example.com"},
 				},
@@ -115,7 +115,7 @@ func TestValidate(t *testing.T) {
 		{
 			name: "Invalid requests per second",
 			config: Config{
-				FileExtensions:    []string{".go"},
+				FileExtensions:    []string{"go"},
 				RequestsPerSecond: func() *float64 { f := -1.0; return &f }(),
 			},
 			wantErr: true,
@@ -123,7 +123,7 @@ func TestValidate(t *testing.T) {
 		{
 			name: "Invalid burst limit",
 			config: Config{
-				FileExtensions: []string{".go"},
+				FileExtensions: []string{"go"},
 				BurstLimit:     func() *int { i := -1; return &i }(),
 			},
 			wantErr: true,
@@ -131,19 +131,11 @@ func TestValidate(t *testing.T) {
 		{
 			name: "Site without base URL",
 			config: Config{
-				FileExtensions: []string{".go"},
+				FileExtensions: []string{"go"},
 				Sites:          []SiteConfig{{}},
 			},
 			wantErr: true,
 		},
-		{
-			name: "Negative max depth",
-			config: Config{
-				FileExtensions: []string{".go"},
-				Sites:          []SiteConfig{{BaseURL: "https://example.com"}},
-			},
-			wantErr: true,
-		},
 	}
 
 	for _, tt := range tests {

internal/scraper/scraper.go

@@ -74,6 +74,9 @@ func ScrapeSites(config Config) error {
 
 	var wg sync.WaitGroup
 	totalURLs := 0
+	for _, site := range config.Sites {
+		totalURLs += len(site.AllowedPaths)
+	}
 	for _, site := range config.Sites {
 		logger.Printf("Processing site: %s\n", site.BaseURL)
 		wg.Add(1)
@@ -81,7 +84,6 @@ func ScrapeSites(config Config) error {
 			defer wg.Done()
 			for _, path := range site.AllowedPaths {
 				fullURL := site.BaseURL + path
-				totalURLs++
 				logger.Printf("Queueing URL for scraping: %s\n", fullURL)
 				scrapeSingleURL(fullURL, site, results, limiter)
 			}
@@ -532,8 +534,6 @@ func scrollPage(page playwright.Page) error {
 		() => {
 			window.scrollTo(0, document.body.scrollHeight);
 			return document.body.scrollHeight;
-			// wait for 500 ms
-			new Promise(resolve => setTimeout(resolve, 500));
 		}
 	`
 
@@ -565,8 +565,8 @@ func scrollPage(page playwright.Page) error {
 
 		previousHeight = currentHeight
 
-		// Wait for a while before scrolling again
+		// Wait for content to load before scrolling again
-
+		time.Sleep(100 * time.Millisecond)
 	}
 
 	logger.Println("Scrolling back to top")

main.go

@@ -10,8 +10,6 @@ import (
 	"github.com/tnypxl/rollup/internal/scraper"
 )
 
-var cfg *config.Config
-
 func main() {
 	// Check if the command is "help"
 	isHelpCommand := len(os.Args) > 1 && (os.Args[1] == "help" || os.Args[1] == "--help" || os.Args[1] == "-h")