Create file_utils.py

file_utils.py

@@ -0,0 +1,47 @@
+import fitz  # PyMuPDF
+from pptx import Presentation
+
+
+def extract_text_from_pdf(pdf_path):
+    text = ""
+    with fitz.open(pdf_path) as doc:
+        for page in doc:
+            text += page.get_text()
+    return text
+
+
+def extract_text_from_txt(file_path):
+    with open(file_path, 'r', encoding='utf-8') as f:
+        return f.read()
+
+
+def extract_text_from_md(file_path):
+    with open(file_path, 'r', encoding='utf-8') as f:
+        return f.read()
+
+
+def extract_text_from_pptx(file_path):
+    text = ""
+    prs = Presentation(file_path)
+    for slide in prs.slides:
+        for shape in slide.shapes:
+            if hasattr(shape, "text"):
+                text += shape.text + "\n"
+    return text
+
+
+def extract_text_from_file(file):
+    if file is None:
+        return ""
+
+    name = file.name.lower()
+    if name.endswith(".pdf"):
+        return extract_text_from_pdf(file.name)
+    elif name.endswith(".txt"):
+        return extract_text_from_txt(file.name)
+    elif name.endswith(".md"):
+        return extract_text_from_md(file.name)
+    elif name.endswith(".pptx"):
+        return extract_text_from_pptx(file.name)
+    else:
+        return "Unsupported file type."