refactor code (#583)

### What problem does this PR solve?

### Type of change

- [x] Refactoring

deepdoc/parser/__init__.py

@@ -1,6 +1,6 @@
 
 
-from .pdf_parser import HuParser as PdfParser, PlainParser
-from .docx_parser import HuDocxParser as DocxParser
-from .excel_parser import HuExcelParser as ExcelParser
-from .ppt_parser import HuPptParser as PptParser
+from .pdf_parser import RAGFlowPdfParser as PdfParser, PlainParser
+from .docx_parser import RAGFlowDocxParser as DocxParser
+from .excel_parser import RAGFlowExcelParser as ExcelParser
+from .ppt_parser import RAGFlowPptParser as PptParser

deepdoc/parser/docx_parser.py

@@ -7,7 +7,7 @@ from rag.nlp import huqie
 from io import BytesIO
 
 
-class HuDocxParser:
+class RAGFlowDocxParser:
 
     def __extract_table_content(self, tb):
         df = []

deepdoc/parser/excel_parser.py

@@ -6,7 +6,7 @@ from io import BytesIO
 from rag.nlp import find_codec
 
 
-class HuExcelParser:
+class RAGFlowExcelParser:
     def html(self, fnm):
         if isinstance(fnm, str):
             wb = load_workbook(fnm)
@@ -74,5 +74,5 @@ class HuExcelParser:
 
 
 if __name__ == "__main__":
-    psr = HuExcelParser()
+    psr = RAGFlowExcelParser()
     psr(sys.argv[1])

deepdoc/parser/pdf_parser.py

@@ -23,7 +23,7 @@ from huggingface_hub import snapshot_download
 logging.getLogger("pdfminer").setLevel(logging.WARNING)
 
 
-class HuParser:
+class RAGFlowPdfParser:
     def __init__(self):
         self.ocr = OCR()
         if hasattr(self, "model_speciess"):

deepdoc/parser/ppt_parser.py

@@ -14,7 +14,7 @@ from io import BytesIO
 from pptx import Presentation
 
 
-class HuPptParser(object):
+class RAGFlowPptParser(object):
     def __init__(self):
         super().__init__()