Update parser and project changes

internal/parser/archive.go

@@ -14,11 +14,14 @@ import (
 
 const maxSingleFileSize = 10 * 1024 * 1024
 const maxZipArchiveSize = 50 * 1024 * 1024
+const maxGzipDecompressedSize = 50 * 1024 * 1024
 
 // ExtractedFile represents a file extracted from archive
 type ExtractedFile struct {
-	Path    string
-	Content []byte
+	Path             string
+	Content          []byte
+	Truncated        bool
+	TruncatedMessage string
 }
 
 // ExtractArchive extracts tar.gz or zip archive and returns file contents
@@ -121,12 +124,16 @@ func extractTarGzFromReader(r io.Reader, filename string) ([]ExtractedFile, erro
 	}
 	defer gzr.Close()
 
-	// Read all decompressed content into buffer
-	// Limit to 50MB for plain gzip files, 10MB per file for tar.gz
-	decompressed, err := io.ReadAll(io.LimitReader(gzr, 50*1024*1024))
+	// Read decompressed content with a hard cap.
+	// When the payload exceeds the cap, keep the first chunk and mark it as truncated.
+	decompressed, err := io.ReadAll(io.LimitReader(gzr, maxGzipDecompressedSize+1))
 	if err != nil {
 		return nil, fmt.Errorf("read gzip content: %w", err)
 	}
+	gzipTruncated := len(decompressed) > maxGzipDecompressedSize
+	if gzipTruncated {
+		decompressed = decompressed[:maxGzipDecompressedSize]
+	}
 
 	// Try to read as tar archive
 	tr := tar.NewReader(bytes.NewReader(decompressed))
@@ -142,12 +149,19 @@ func extractTarGzFromReader(r io.Reader, filename string) ([]ExtractedFile, erro
 				baseName = gzr.Name
 			}
 
-			return []ExtractedFile{
-				{
-					Path:    baseName,
-					Content: decompressed,
-				},
-			}, nil
+			file := ExtractedFile{
+				Path:    baseName,
+				Content: decompressed,
+			}
+			if gzipTruncated {
+				file.Truncated = true
+				file.TruncatedMessage = fmt.Sprintf(
+					"decompressed gzip content exceeded %d bytes and was truncated",
+					maxGzipDecompressedSize,
+				)
+			}
+
+			return []ExtractedFile{file}, nil
 		}
 		return nil, fmt.Errorf("tar read: %w", err)
 	}
@@ -288,16 +302,24 @@ func extractSingleFileFromReader(r io.Reader, filename string) ([]ExtractedFile,
 	if err != nil {
 		return nil, fmt.Errorf("read file content: %w", err)
 	}
-	if len(content) > maxSingleFileSize {
-		return nil, fmt.Errorf("file too large: max %d bytes", maxSingleFileSize)
+	truncated := len(content) > maxSingleFileSize
+	if truncated {
+		content = content[:maxSingleFileSize]
 	}
 
-	return []ExtractedFile{
-		{
-			Path:    filepath.Base(filename),
-			Content: content,
-		},
-	}, nil
+	file := ExtractedFile{
+		Path:    filepath.Base(filename),
+		Content: content,
+	}
+	if truncated {
+		file.Truncated = true
+		file.TruncatedMessage = fmt.Sprintf(
+			"file exceeded %d bytes and was truncated",
+			maxSingleFileSize,
+		)
+	}
+
+	return []ExtractedFile{file}, nil
 }
 
 // FindFileByPattern finds files matching pattern in extracted files