jarvis-ai-assistant 0.1.134__py3-none-any.whl → 0.1.138__py3-none-any.whl

jarvis/jarvis_rag/file_processors.py

@@ -11,7 +11,7 @@ class FileProcessor:
     def can_handle(file_path: str) -> bool:
         """Determine if the file can be processed"""
         raise NotImplementedError
-        
+
     @staticmethod
     def extract_text(file_path: str) -> str:
         """Extract file text content"""
@@ -21,7 +21,7 @@ class TextFileProcessor(FileProcessor):
     """Text file processor"""
     ENCODINGS = ['utf-8', 'gbk', 'gb2312', 'latin1']
     SAMPLE_SIZE = 8192  # Read the first 8KB to detect encoding
-    
+
     @staticmethod
     def can_handle(file_path: str) -> bool:
         """Determine if the file is a text file by trying to decode it"""
@@ -29,16 +29,16 @@ class TextFileProcessor(FileProcessor):
             # Read the first part of the file to detect encoding
             with open(file_path, 'rb') as f:
                 sample = f.read(TextFileProcessor.SAMPLE_SIZE)
-                
+
             # Check if it contains null bytes (usually represents a binary file)
             if b'\x00' in sample:
                 return False
-                
+
             # Check if it contains too many non-printable characters (usually represents a binary file)
             non_printable = sum(1 for byte in sample if byte < 32 and byte not in (9, 10, 13))  # tab, newline, carriage return
             if non_printable / len(sample) > 0.3:  # If non-printable characters exceed 30%, it is considered a binary file
                 return False
-                
+
             # Try to decode with different encodings
             for encoding in TextFileProcessor.ENCODINGS:
                 try:
@@ -46,12 +46,12 @@ class TextFileProcessor(FileProcessor):
                     return True
                 except UnicodeDecodeError:
                     continue
-                    
+
             return False
-            
+
         except Exception:
             return False
-    
+
     @staticmethod
     def extract_text(file_path: str) -> str:
         """Extract text content, using the detected correct encoding"""
@@ -60,7 +60,7 @@ class TextFileProcessor(FileProcessor):
             # First try to detect encoding
             with open(file_path, 'rb') as f:
                 raw_data = f.read()
-                
+
             # Try different encodings
             for encoding in TextFileProcessor.ENCODINGS:
                 try:
@@ -69,19 +69,19 @@ class TextFileProcessor(FileProcessor):
                     break
                 except UnicodeDecodeError:
                     continue
-                    
+
             if not detected_encoding:
                 raise UnicodeDecodeError(f"Failed to decode file with supported encodings: {file_path}") # type: ignore
-                
+
             # Use the detected encoding to read the file
             with open(file_path, 'r', encoding=detected_encoding, errors='ignore') as f:
                 content = f.read()
-                
+
             # Normalize Unicode characters
             content = unicodedata.normalize('NFKC', content)
-            
+
             return content
-            
+
         except Exception as e:
             raise Exception(f"Failed to read file: {str(e)}")
 
@@ -90,7 +90,7 @@ class PDFProcessor(FileProcessor):
     @staticmethod
     def can_handle(file_path: str) -> bool:
         return Path(file_path).suffix.lower() == '.pdf'
-    
+
     @staticmethod
     def extract_text(file_path: str) -> str:
         text_parts = []
@@ -104,7 +104,7 @@ class DocxProcessor(FileProcessor):
     @staticmethod
     def can_handle(file_path: str) -> bool:
         return Path(file_path).suffix.lower() == '.docx'
-    
+
     @staticmethod
     def extract_text(file_path: str) -> str:
         doc = DocxDocument(file_path)
@@ -115,7 +115,7 @@ class PPTProcessor(FileProcessor):
     @staticmethod
     def can_handle(file_path: str) -> bool:
         return Path(file_path).suffix.lower() in ['.ppt', '.pptx']
-    
+
     @staticmethod
     def extract_text(file_path: str) -> str:
         prs = Presentation(file_path)
@@ -131,7 +131,7 @@ class ExcelProcessor(FileProcessor):
     @staticmethod
     def can_handle(file_path: str) -> bool:
         return Path(file_path).suffix.lower() in ['.xls', '.xlsx']
-    
+
     @staticmethod
     def extract_text(file_path: str) -> str:
         df = pd.read_excel(file_path)