From d47232246a9ac49afa8414d4a55519fb85874be6 Mon Sep 17 00:00:00 2001
From: Alex <a@tushynski.me>
Date: Thu, 6 Feb 2025 19:59:42 +0000
Subject: [PATCH] fix: remove old pypdf

---
 application/parser/file/docs_parser.py | 17 +++++++++--------
 application/requirements.txt           |  2 +-
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/application/parser/file/docs_parser.py b/application/parser/file/docs_parser.py
index 55d45a64..a1295290 100644
--- a/application/parser/file/docs_parser.py
+++ b/application/parser/file/docs_parser.py
@@ -24,26 +24,27 @@ class PDFParser(BaseParser):
             # alternatively you can use local vision capable LLM
             with open(file, "rb") as file_loaded:
                 files = {'file': file_loaded}
-                response = requests.post(doc2md_service, files=files)   
-                data = response.json()["markdown"] 
+                response = requests.post(doc2md_service, files=files)
+                data = response.json()["markdown"]
             return data
 
         try:
-            import PyPDF2
+            from pypdf import PdfReader
         except ImportError:
-            raise ValueError("PyPDF2 is required to read PDF files.")
+            raise ValueError("pypdf is required to read PDF files.")
         text_list = []
         with open(file, "rb") as fp:
             # Create a PDF object
-            pdf = PyPDF2.PdfReader(fp)
+            pdf = PdfReader(fp)
 
             # Get the number of pages in the PDF document
             num_pages = len(pdf.pages)
 
             # Iterate over every page
-            for page in range(num_pages):
+            for page_index in range(num_pages):
                 # Extract the text from the page
-                page_text = pdf.pages[page].extract_text()
+                page = pdf.pages[page_index]
+                page_text = page.extract_text()
                 text_list.append(page_text)
         text = "\n".join(text_list)
 
@@ -66,4 +67,4 @@ class DocxParser(BaseParser):
 
         text = docx2txt.process(file)
 
-        return text
+        return text
\ No newline at end of file
diff --git a/application/requirements.txt b/application/requirements.txt
index 12ea4ee5..5732809b 100644
--- a/application/requirements.txt
+++ b/application/requirements.txt
@@ -66,7 +66,7 @@ pydantic==2.10.4
 pydantic-core==2.27.2
 pydantic-settings==2.7.1
 pymongo==4.10.1
-pypdf2==3.0.1
+pypdf==5.2.0
 python-dateutil==2.9.0.post0
 python-dotenv==1.0.1
 python-pptx==1.0.2