feat: classify comment and code line stats

Author: aksOps

CHANGELOG.md

@@ -5,7 +5,7 @@
 - Parse `.gitignore`, `.ignore`, and `.git/info/exclude` during working-tree scans.
 - Add `--exclude-tests` to skip well-known test-case paths from aggregate scan analysis.
 - Replace the linear score deduction with a bounded issue-density curve so noisy large repositories do not collapse to zero.
-- Add aggregate commented-line statistics to scan and diff reports.
+- Add aggregate code/blank/comment-only/inline-comment line statistics to scan and diff reports, and use code lines for issue-density scoring when available.
 
 ## 0.0.1 - 2026-06-30
 

README.md

@@ -97,9 +97,11 @@ Detection uses extensions, shebangs, and common manifests such as `go.mod`, `pac
 
 ## Aggregate line statistics
 
-Scan JSON includes `comment_lines` and `comment_density_percent` beside existing line totals. The same aggregate fields are reported for `totals`, `by_language`, and `by_module`; diff JSON includes before/after/delta values under `totals_delta`.
+Scan JSON includes `lines_scanned`, `blank_lines`, `code_lines`, `comment_lines`, `comment_only_lines`, `inline_comment_lines`, and `comment_density_percent`. The same aggregate fields are reported for `totals`, `by_language`, and `by_module`; diff JSON includes before/after/delta values under `totals_delta`.
 
-Comment detection is lexical and language-aware: it recognizes `//`, `#`, and `/* ... */` style comments where those markers are valid, ignores markers inside quoted strings/raw strings, and never emits per-file locations or source snippets.
+`lines_scanned` is physical scanned lines. `code_lines` excludes blank lines and comment-only lines, but keeps lines that contain code plus an inline comment. The score model uses `code_lines` when available and falls back to physical lines for older reports.
+
+Comment detection is lexical and language-aware for supported languages: it recognizes `//`, `#`, `/* ... */`, Rust nested block comments, Ruby `=begin`/`=end`, and standalone Python triple-quoted doc/comment blocks where those forms are valid. It ignores common markers inside quoted strings/raw strings/template literals and JavaScript/TypeScript regex literals, and never emits per-file locations or source snippets.
 
 ## Ignore files, test exclusion, and skip policy
 
@@ -143,7 +145,7 @@ Unknown config fields and trailing JSON values are rejected.
 The score is a bounded weighted issue-density signal, not a SonarQube debt rating:
 
 ```text
-weighted_density_per_kloc = round((errors*10 + warnings*4 + info*1) * 1000 / max(lines_scanned, 1000))
+weighted_density_per_kloc = round((errors*10 + warnings*4 + info*1) * 1000 / max(code_lines, 1000))
 score = round(100 * 100 / (100 + weighted_density_per_kloc))
 ```
 

internal/cli/cli.go

@@ -556,10 +556,11 @@ func printScan(stdout io.Writer, scanReport model.ScanReport) error {
 	fmt.Fprintf(&builder, "Score: %d (%s)\n", scanReport.Score, scanReport.Band)
 	fmt.Fprintf(&builder, "Issues: %d (errors: %d, warnings: %d, info: %d)\n",
 		scanReport.Totals.Issues, scanReport.Totals.Errors, scanReport.Totals.Warnings, scanReport.Totals.Info)
-	fmt.Fprintf(&builder, "Files scanned: %d | Lines scanned: %d | Files skipped: %d\n",
-		scanReport.Totals.FilesScanned, scanReport.Totals.LinesScanned, scanReport.Totals.FilesSkipped)
-	fmt.Fprintf(&builder, "Comment lines: %d (%.1f%%)\n",
-		scanReport.Totals.CommentLines, scanReport.Totals.CommentDensityPercent)
+	fmt.Fprintf(&builder, "Files scanned: %d | Lines scanned: %d | Code lines: %d | Files skipped: %d\n",
+		scanReport.Totals.FilesScanned, scanReport.Totals.LinesScanned, scanReport.Totals.CodeLines, scanReport.Totals.FilesSkipped)
+	fmt.Fprintf(&builder, "Comments: %d lines (%.1f%%) | Comment-only: %d | Inline: %d | Blank: %d\n",
+		scanReport.Totals.CommentLines, scanReport.Totals.CommentDensityPercent,
+		scanReport.Totals.CommentOnlyLines, scanReport.Totals.InlineCommentLines, scanReport.Totals.BlankLines)
 	fmt.Fprintf(&builder, "Languages: %s | Modules: %d (%s)\n",
 		joinOrNone(scanLanguages(scanReport)), scanModuleCount(scanReport), moduleProfileText(scanReport))
 	printDuplicationSummary(&builder, scanReport.Duplication)

internal/delta/delta.go

@@ -28,7 +28,11 @@ func compareTotals(base, head model.ScanTotals) model.TotalsDelta {
 		FilesScanned:          countDelta(base.FilesScanned, head.FilesScanned),
 		FilesSkipped:          countDelta(base.FilesSkipped, head.FilesSkipped),
 		LinesScanned:          countDelta(base.LinesScanned, head.LinesScanned),
+		BlankLines:            countDelta(base.BlankLines, head.BlankLines),
+		CodeLines:             countDelta(base.CodeLines, head.CodeLines),
 		CommentLines:          countDelta(base.CommentLines, head.CommentLines),
+		CommentOnlyLines:      countDelta(base.CommentOnlyLines, head.CommentOnlyLines),
+		InlineCommentLines:    countDelta(base.InlineCommentLines, head.InlineCommentLines),
 		CommentDensityPercent: percentDelta(base.CommentDensityPercent, head.CommentDensityPercent),
 		Issues:                countDelta(base.Issues, head.Issues),
 		Errors:                countDelta(base.Errors, head.Errors),