From 2e3cdd3eea7df42ce23400669f4fec25c10a2567 Mon Sep 17 00:00:00 2001
From: Carlos Salgado <csalgado@uwo.ca>
Date: Thu, 18 Apr 2024 17:11:12 -0400
Subject: [PATCH] rework io bug

---
 app.py     | 12 +++++++++---
 scripts.py | 13 ++++++++-----
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/app.py b/app.py
index 2d3e6f4..87dd9bb 100644
--- a/app.py
+++ b/app.py
@@ -12,11 +12,17 @@
 
 if uploaded_file is not None:
     try:
-        file_ext = uploaded_file.name.split('.')[-1].lower()
-        pdf_file = io.BytesIO(uploaded_file.read())
-        docs = ingest(pdf_file, file_ext)
+        with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(uploaded_file.name)[1]) as tmp:
+            tmp.write(uploaded_file.read())
+            file_path = tmp.name
+
+        docs = ingest(file_path)
         metadata = generate_metadata(docs)
         st.write('## Converted Text')
         st.write(metadata)
+
+        # Clean up the temporary file
+        os.remove(file_path)
+
     except Exception as e:
         st.error(f'Error: {e}')
\ No newline at end of file
diff --git a/scripts.py b/scripts.py
index 646ef04..d4060c8 100644
--- a/scripts.py
+++ b/scripts.py
@@ -15,11 +15,13 @@
 
 import io
 
-def ingest(file_obj, file_ext='pdf'):
-    if file_ext == 'pdf':
-        loader = UnstructuredPDFLoader(file_obj)
-    elif file_ext == 'txt':
-        loader = TextLoader(file_obj)
+def ingest(file_path):
+    extension = os.path.splitext(file_path)[1].lower()
+
+    if extension == '.pdf':
+        loader = UnstructuredPDFLoader(file_path)
+    elif extension == '.txt':
+        loader = TextLoader(file_path)
     else:
         raise NotImplementedError('Only .txt or .pdf files are supported')
 
@@ -43,6 +45,7 @@ def ingest(file_obj, file_ext='pdf'):
     return docs
 
 
+
 def generate_metadata(docs):
     prompt_template = """
     BimDiscipline = ['plumbing', 'network', 'heating', 'electrical', 'ventilation', 'architecture']