ds apis implemneted

2025-02-06 20:12:43 +00:00
parent 58e0cbfa3c
commit 4cd9aeac51
17 changed files with 5612 additions and 0 deletions
@@ -0,0 +1,53 @@
+import os
+from spire.doc import Document, FileFormat
+from langchain_community.document_loaders import PyPDFLoader
+
+def convert_word_to_pdf(doc_path: str) -> str:
+    """
+    Convert a .doc or .docx file to PDF using Spire.Doc.
+    
+    Args:
+        doc_path (str): The path to the .doc or .docx file.
+
+    Returns:
+        str: The path to the converted PDF file.
+    """
+    pdf_path = os.path.splitext(doc_path)[0] + '.pdf'
+    
+    # Create a Document object
+    document = Document()
+    # Load the Word document
+    document.LoadFromFile(doc_path)
+    # Save as PDF
+    document.SaveToFile(pdf_path, FileFormat.PDF)
+    document.Close()
+    
+    return pdf_path
+
+def load_document(file_path: str):
+    """
+    Utility function to load a PDF, DOCX, or DOC file by first converting it to PDF.
+
+    Args:
+        file_path (str): The path to the file to load.
+
+    Returns:
+        List[Document]: A list of Document objects representing the contents of the file.
+    """
+    
+    try:
+        extension = os.path.splitext(file_path)[1].lower()
+        
+        if extension in ['.doc', '.docx']:
+            # Convert .doc or .docx to PDF first
+            pdf_path = convert_word_to_pdf(file_path)
+            loader = PyPDFLoader(pdf_path)
+        elif extension == '.pdf':
+            loader = PyPDFLoader(file_path)
+        else:
+            raise ValueError(f"Unsupported file type: {extension}. Only .pdf, .docx, and .doc are supported.")
+        
+        return loader.load()
+    except Exception as e:
+        print(f"Error loading document: {str(e)}")
+        return None