flatten scrape config to 'sites:'

* flatten scrape config to 'sites:'. Update unit tests and readme.
* remove check for file_extensions configuration. 
* show progress indication after 5 seconds.
* add documentation to functions
* fix: remove MaxDepth and link extraction functionality
* fix: Remove MaxDepth references from cmd/web.go

internal/config/config_test.go

@@ -9,34 +9,33 @@ import (
 func TestLoad(t *testing.T) {
 	// Create a temporary config file
 	content := []byte(`
-file_types:
-  - go
-  - md
-ignore:
+file_extensions:
+  - .go
+  - .md
+ignore_paths:
   - "*.tmp"
   - "**/*.log"
-code_generated:
+code_generated_paths:
   - "generated_*.go"
-scrape:
-  sites:
-    - base_url: "https://example.com"
-      css_locator: "main"
-      exclude_selectors:
-        - ".ads"
-      max_depth: 2
-      allowed_paths:
-        - "/blog"
-      exclude_paths:
-        - "/admin"
-      output_alias: "example"
-      path_overrides:
-        - path: "/special"
-          css_locator: ".special-content"
-          exclude_selectors:
-            - ".sidebar"
-  output_type: "single"
-  requests_per_second: 1.0
-  burst_limit: 5
+sites:
+  - base_url: "https://example.com"
+    css_locator: "main"
+    exclude_selectors:
+      - ".ads"
+    max_depth: 2
+    allowed_paths:
+      - "/blog"
+    exclude_paths:
+      - "/admin"
+    output_alias: "example"
+    path_overrides:
+      - path: "/special"
+        css_locator: ".special-content"
+        exclude_selectors:
+          - ".sidebar"
+output_type: "single"
+requests_per_second: 1.0
+burst_limit: 5
 `)
 
 	tmpfile, err := os.CreateTemp("", "config*.yml")
@@ -59,33 +58,33 @@ scrape:
 	}
 
 	// Check if the loaded config matches the expected values
+	rps := 1.0
+	bl := 5
 	expectedConfig := &Config{
-		FileTypes:     []string{"go", "md"},
-		Ignore:        []string{"*.tmp", "**/*.log"},
-		CodeGenerated: []string{"generated_*.go"},
-		Scrape: ScrapeConfig{
-			Sites: []SiteConfig{
-				{
-					BaseURL:          "https://example.com",
-					CSSLocator:       "main",
-					ExcludeSelectors: []string{".ads"},
-					MaxDepth:         2,
-					AllowedPaths:     []string{"/blog"},
-					ExcludePaths:     []string{"/admin"},
-					OutputAlias:      "example",
-					PathOverrides: []PathOverride{
-						{
-							Path:             "/special",
-							CSSLocator:       ".special-content",
-							ExcludeSelectors: []string{".sidebar"},
-						},
+		FileExtensions:     []string{".go", ".md"},
+		IgnorePaths:        []string{"*.tmp", "**/*.log"},
+		CodeGeneratedPaths: []string{"generated_*.go"},
+		Sites: []SiteConfig{
+			{
+				BaseURL:          "https://example.com",
+				CSSLocator:       "main",
+				ExcludeSelectors: []string{".ads"},
+				MaxDepth:         2,
+				AllowedPaths:     []string{"/blog"},
+				ExcludePaths:     []string{"/admin"},
+				OutputAlias:      "example",
+				PathOverrides: []PathOverride{
+					{
+						Path:             "/special",
+						CSSLocator:       ".special-content",
+						ExcludeSelectors: []string{".sidebar"},
 					},
 				},
 			},
-			OutputType:        "single",
-			RequestsPerSecond: 1.0,
-			BurstLimit:        5,
 		},
+		OutputType:        "single",
+		RequestsPerSecond: &rps,
+		BurstLimit:        &bl,
 	}
 
 	if !reflect.DeepEqual(config, expectedConfig) {
@@ -93,28 +92,67 @@ scrape:
 	}
 }
 
-func TestDefaultConfigPath(t *testing.T) {
-	expected := "rollup.yml"
-	result := DefaultConfigPath()
-	if result != expected {
-		t.Errorf("DefaultConfigPath() = %q, want %q", result, expected)
-	}
-}
-
-func TestFileExists(t *testing.T) {
-	// Test with an existing file
-	tmpfile, err := os.CreateTemp("", "testfile")
-	if err != nil {
-		t.Fatalf("Failed to create temp file: %v", err)
-	}
-	defer os.Remove(tmpfile.Name())
-
-	if !FileExists(tmpfile.Name()) {
-		t.Errorf("FileExists(%q) = false, want true", tmpfile.Name())
-	}
-
-	// Test with a non-existing file
-	if FileExists("non_existing_file.txt") {
-		t.Errorf("FileExists(\"non_existing_file.txt\") = true, want false")
+func TestValidate(t *testing.T) {
+	tests := []struct {
+		name    string
+		config  Config
+		wantErr bool
+	}{
+		{
+			name: "Valid config",
+			config: Config{
+				FileExtensions: []string{".go"},
+				Sites: []SiteConfig{
+					{BaseURL: "https://example.com", MaxDepth: 2},
+				},
+			},
+			wantErr: false,
+		},
+		{
+			name:    "No file extensions",
+			config:  Config{},
+			wantErr: true,
+		},
+		{
+			name: "Invalid requests per second",
+			config: Config{
+				FileExtensions:    []string{".go"},
+				RequestsPerSecond: func() *float64 { f := -1.0; return &f }(),
+			},
+			wantErr: true,
+		},
+		{
+			name: "Invalid burst limit",
+			config: Config{
+				FileExtensions: []string{".go"},
+				BurstLimit:     func() *int { i := -1; return &i }(),
+			},
+			wantErr: true,
+		},
+		{
+			name: "Site without base URL",
+			config: Config{
+				FileExtensions: []string{".go"},
+				Sites:          []SiteConfig{{}},
+			},
+			wantErr: true,
+		},
+		{
+			name: "Negative max depth",
+			config: Config{
+				FileExtensions: []string{".go"},
+				Sites:          []SiteConfig{{BaseURL: "https://example.com", MaxDepth: -1}},
+			},
+			wantErr: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := tt.config.Validate()
+			if (err != nil) != tt.wantErr {
+				t.Errorf("Validate() error = %v, wantErr %v", err, tt.wantErr)
+			}
+		})
 	}
 }