Update src/app.py

src/app.py

@@ -1,4 +1,7 @@
 import os
+os.environ["STREAMLIT_CONFIG_DIR"] = "/tmp/.streamlit"
+os.makedirs("/tmp/.streamlit", exist_ok=True)
+
 import tempfile
 from gtts import gTTS
 from docx import Document
@@ -12,23 +15,14 @@ def text_to_speech(text, output_file):
 
 def convert_docx_to_text(docx_file):
     doc = Document(docx_file)
-    text = ""
-    for paragraph in doc.paragraphs:
-        text += paragraph.text + "\n"
-    return text
+    return "\n".join([p.text for p in doc.paragraphs])
 
 def convert_pdf_to_text(pdf_file):
-    text = ""
     pdf_reader = PdfReader(pdf_file)
-    for page in pdf_reader.pages:
-        page_text = page.extract_text()
-        if page_text:
-            text += page_text
-    return text
+    return "\n".join([page.extract_text() or '' for page in pdf_reader.pages])
 
 def get_binary_file_downloader_html(bin_file, file_label='File'):
-    data = bin_file
-    b64 = base64.b64encode(data).decode()
+    b64 = base64.b64encode(bin_file).decode()
     href = f'<a href="data:application/octet-stream;base64,{b64}" download="{file_label}" target="_blank">Download {file_label}</a>'
     return href
 
@@ -38,40 +32,34 @@ def main():
     uploaded_file = st.file_uploader("Upload a text, docx, or pdf file", type=["txt", "docx", "pdf"])
 
     if uploaded_file:
-        try:
-            with tempfile.NamedTemporaryFile(delete=False, suffix='.' + uploaded_file.name.split('.')[-1]) as temp_file:
-                temp_file.write(uploaded_file.read())
-                temp_file_path = temp_file.name
-
-            file_extension = uploaded_file.name.split('.')[-1].lower()
-
-            if file_extension == 'txt':
-                with open(temp_file_path, 'r', encoding='utf-8') as f:
-                    text = f.read()
-            elif file_extension == 'docx':
-                text = convert_docx_to_text(temp_file_path)
-            elif file_extension == 'pdf':
-                text = convert_pdf_to_text(temp_file_path)
-            else:
-                st.error("Unsupported file format")
-                return
-
-            if not text.strip():
-                st.warning("No text found in the file.")
-                return
-
-            with st.spinner("Converting text to speech..."):
-                output_audio_file = os.path.join(tempfile.gettempdir(), "output.mp3")
-                text_to_speech(text, output_audio_file)
-
-            st.audio(output_audio_file, format="audio/mp3")
-
-            with open(output_audio_file, 'rb') as f:
-                audio_bytes = f.read()
-            st.markdown(get_binary_file_downloader_html(audio_bytes, "output.mp3"), unsafe_allow_html=True)
-
-        except Exception as e:
-            st.error(f"An error occurred: {e}")
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.' + uploaded_file.name.split('.')[-1]) as tmp:
+            tmp.write(uploaded_file.read())
+            tmp_path = tmp.name
+
+        ext = uploaded_file.name.split('.')[-1].lower()
+        text = ""
+
+        if ext == 'txt':
+            with open(tmp_path, 'r', encoding='utf-8') as f:
+                text = f.read()
+        elif ext == 'docx':
+            text = convert_docx_to_text(tmp_path)
+        elif ext == 'pdf':
+            text = convert_pdf_to_text(tmp_path)
+
+        if not text.strip():
+            st.warning("No readable text found.")
+            return
+
+        output_audio_path = os.path.join(tempfile.gettempdir(), "output.mp3")
+        text_to_speech(text, output_audio_path)
+
+        st.audio(output_audio_path, format="audio/mp3")
+
+        with open(output_audio_path, 'rb') as audio_file:
+            audio_bytes = audio_file.read()
+
+        st.markdown(get_binary_file_downloader_html(audio_bytes, "output.mp3"), unsafe_allow_html=True)
 
 if __name__ == "__main__":
     main()