Add filters for excessive spaces and tabs

Copilot · SamMorrowDrums · Copilot · commit 2e27e2aca369 · 2025-05-23T21:40:21.000Z
Co-authored-by: SamMorrowDrums &lt;4811358+SamMorrowDrums@users.noreply.github.com&gt;
diff --git a/pkg/filtering/content_filter.go b/pkg/filtering/content_filter.go
@@ -37,6 +37,12 @@ var (
 
 	// Excessive whitespace (more than 3 consecutive newlines)
 	excessiveWhitespaceRegex = regexp.MustCompile(`\n{4,}`)
+	
+	// Excessive spaces (15 or more consecutive spaces)
+	excessiveSpacesRegex = regexp.MustCompile(` {15,}`)
+	
+	// Excessive tabs (6 or more consecutive tabs)
+	excessiveTabsRegex = regexp.MustCompile(`\t{6,}`)
 )
 
 // Config holds configuration for content filtering
@@ -93,6 +99,12 @@ func FilterContent(input string, cfg *Config) string {
 
 	// Normalize excessive whitespace
 	result = excessiveWhitespaceRegex.ReplaceAllString(result, "\n\n\n")
+	
+	// Normalize excessive spaces
+	result = excessiveSpacesRegex.ReplaceAllString(result, "              ")
+	
+	// Normalize excessive tabs
+	result = excessiveTabsRegex.ReplaceAllString(result, "     ")
 
 	return result
 }
diff --git a/pkg/filtering/content_filter_test.go b/pkg/filtering/content_filter_test.go
@@ -59,6 +59,18 @@ func TestFilterContent(t *testing.T) {
 			expected: "Line 1\n\n\nLine 2",
 			cfg:      DefaultConfig(),
 		},
+		{
+			name:     "Text with excessive spaces",
+			input:    "Normal                               Excessive",
+			expected: "Normal              Excessive",
+			cfg:      DefaultConfig(),
+		},
+		{
+			name:     "Text with excessive tabs",
+			input:    "Normal\t\t\t\t\t\t\t\tExcessive",
+			expected: "Normal     Excessive",
+			cfg:      DefaultConfig(),
+		},
 		{
 			name:     "Text with HTML attributes",
 			input:    "<p data-hidden=\"true\" style=\"display:none\">Hidden paragraph</p>",
