Upload 4 files

BG.py

@@ -0,0 +1,80 @@
+import streamlit as st
+import pandas as pd
+from io import BytesIO
+
+def split_excel(file, columns, original_file_name, sheet_name="Linjer", header_row=3):
+    try:
+        # Load only the "Linjer" sheet
+        df = pd.read_excel(file, sheet_name=sheet_name, header=header_row-1)  # Adjust for zero-based index
+        log_messages = [f"Loaded worksheet '{sheet_name}'. Other worksheets were ignored."]
+    except ValueError:
+        return {}, [f"Worksheet '{sheet_name}' not found. Please upload a file with the correct structure."]
+    except Exception as e:
+        return {}, [f"An error occurred while reading the file: {e}"]
+
+    split_files = {}
+    all_unique_values = set()
+
+    # Validate that both columns exist in the dataframe
+    for col in columns:
+        if col not in df.columns:
+            log_messages.append(f"Column '{col}' not found in the worksheet. Please check the file.")
+            return {}, log_messages
+
+    # Collect all unique values across both columns
+    for col in columns:
+        unique_values = df[col].dropna().unique()
+        log_messages.append(f"Found unique values in column '{col}': {list(unique_values)}")
+        all_unique_values.update(unique_values)
+
+    log_messages.append(f"Total unique values across columns: {list(all_unique_values)}")
+
+    # Create files for each unique value
+    for value in all_unique_values:
+        split_df = df[(df[columns[0]] == value) | (df[columns[1]] == value)]
+        if split_df.empty:
+            log_messages.append(f"No rows found for value '{value}'. Skipping file creation.")
+            continue
+
+        sanitized_value = str(value).replace("/", "-").replace("\\", "-")
+        file_name = f"{original_file_name} - {sanitized_value}.xlsx"
+
+        output = BytesIO()
+        with pd.ExcelWriter(output, engine='xlsxwriter') as writer:
+            split_df.to_excel(writer, index=False, sheet_name='Sheet1')
+        output.seek(0)
+        split_files[file_name] = output
+        log_messages.append(f"File '{file_name}' created with {len(split_df)} rows.")
+    
+    return split_files, log_messages
+
+st.title("BG File Splitter")
+st.write("Upload an Excel file to split it based on unique values in specified columns.")
+
+uploaded_file = st.file_uploader("Upload Excel File", type=["xlsx"])
+
+if uploaded_file:
+    st.write("Processing the uploaded file...")
+    original_file_name = uploaded_file.name.rsplit(".", 1)[0]  # Extract the file name without extension
+    columns_to_split = ['Afsenderkunde', 'Modtagerkunde']  # Column names to check for unique values
+
+    split_files, logs = split_excel(uploaded_file, columns_to_split, original_file_name)
+
+    st.write("### Logs")
+    if logs:
+        for log in logs:
+            st.write(log)
+    else:
+        st.write("No logs available. Something might have gone wrong.")
+
+    if split_files:
+        st.write("### Download Split Files")
+        for file_name, file_content in split_files.items():
+            st.download_button(
+                label=f"Download {file_name}",
+                data=file_content,
+                file_name=file_name,
+                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+            )
+    else:
+        st.write("No files were created. Check the logs for details.")

GB-GB.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import pandas as pd
+from io import BytesIO
+
+# Streamlit App
+st.title("GB-GB Split Multiple CSVs by Account Numbers")
+
+# Allow multiple files to be uploaded
+uploaded_files = st.file_uploader("Upload your CSV files", type=["csv"], accept_multiple_files=True)
+
+if uploaded_files:
+    for uploaded_file in uploaded_files:
+        # Read each CSV file and get the original file name
+        original_file_name = uploaded_file.name.split(".")[0]
+        st.write(f"Processing file: {uploaded_file.name}")
+        data = pd.read_csv(uploaded_file)
+        st.write(f"File '{uploaded_file.name}' loaded successfully.")
+
+        # Check required columns
+        required_columns = ["SHIPPER ACCOUNT NUMBER", "RECEIVER ACCOUNT NUMBER"]
+        if not all(column in data.columns for column in required_columns):
+            st.error(f"File '{uploaded_file.name}' is missing required columns: {required_columns}")
+            continue
+
+        st.write(f"Columns verified for '{uploaded_file.name}'. Processing the data...")
+
+        # Extract unique values from the columns
+        unique_values = set(data["SHIPPER ACCOUNT NUMBER"].dropna().unique()) | set(
+            data["RECEIVER ACCOUNT NUMBER"].dropna().unique()
+        )
+        st.write(f"Found {len(unique_values)} unique values in '{uploaded_file.name}'.")
+
+        # Process each unique value
+        for unique_value in unique_values:
+            # Filter data for the unique value
+            filtered_data = data[
+                (data["SHIPPER ACCOUNT NUMBER"] == unique_value)
+                | (data["RECEIVER ACCOUNT NUMBER"] == unique_value)
+            ]
+
+            # Determine where the unique value was found
+            found_in_columns = []
+            if (data["SHIPPER ACCOUNT NUMBER"] == unique_value).any():
+                found_in_columns.append("SHIPPER ACCOUNT NUMBER")
+            if (data["RECEIVER ACCOUNT NUMBER"] == unique_value).any():
+                found_in_columns.append("RECEIVER ACCOUNT NUMBER")
+
+            # Log details
+            st.write(
+                f"Processed {unique_value}: {len(filtered_data)} rows found in columns {', '.join(found_in_columns)}."
+            )
+
+            # Save the filtered data to an Excel file in memory
+            output = BytesIO()
+            with pd.ExcelWriter(output, engine="xlsxwriter") as writer:
+                filtered_data.to_excel(writer, index=False, sheet_name="Sheet1")
+            output.seek(0)
+
+            # Provide a download link for each Excel file
+            st.download_button(
+                label=f"Download Excel for {uploaded_file.name} - {unique_value}",
+                data=output,
+                file_name=f"{original_file_name} - {unique_value}.xlsx",
+                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+            )

MultiL.py

@@ -0,0 +1,45 @@
+import streamlit as st
+import pandas as pd
+
+st.title("MultiL Split Excel File by Column Value (4-digit formatting)")
+
+# File uploader
+uploaded_file = st.file_uploader("Upload an Excel file", type=["xlsx"])
+
+if uploaded_file:
+    # Load Excel file with the header starting at row 3 (Python's 0-index is row 2)
+    df = pd.read_excel(uploaded_file, header=2)
+    
+    # Ensure the column exists
+    if "Afsenderkunde løbenumme" in df.columns:
+        st.write(f"File uploaded: {uploaded_file.name}")
+        unique_values = df["Afsenderkunde løbenumme"].unique()
+        st.write(f"Found {len(unique_values)} unique values in 'Afsenderkunde løbenumme'.")
+        
+        # Iterate through unique values to split the file
+        for value in unique_values:
+            formatted_value = f"{int(value):04}"  # Format as 4-digit integer
+            split_df = df[df["Afsenderkunde løbenumme"] == value]
+            output_filename = f"{uploaded_file.name.split('.')[0]} - {formatted_value}.xlsx"
+            
+            # Convert DataFrame to Excel file for download
+            @st.cache_data
+            def convert_df_to_excel(dataframe):
+                from io import BytesIO
+                output = BytesIO()
+                with pd.ExcelWriter(output, engine="xlsxwriter") as writer:
+                    dataframe.to_excel(writer, index=False, sheet_name="Sheet1")
+                output.seek(0)
+                return output
+            
+            excel_data = convert_df_to_excel(split_df)
+            
+            # Download button for each file
+            st.download_button(
+                label=f"Download {output_filename}",
+                data=excel_data,
+                file_name=output_filename,
+                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+            )
+    else:
+        st.error("The column 'Afsenderkunde løbenumme' was not found in the uploaded file.")

app.py

@@ -1,65 +1,24 @@
-import streamlit as st
-import pandas as pd
-from io import BytesIO
-
-# Streamlit App
-st.title("Split Multiple CSVs by Account Numbers")
-
-# Allow multiple files to be uploaded
-uploaded_files = st.file_uploader("Upload your CSV files", type=["csv"], accept_multiple_files=True)
-
-if uploaded_files:
-    for uploaded_file in uploaded_files:
-        # Read each CSV file and get the original file name
-        original_file_name = uploaded_file.name.split(".")[0]
-        st.write(f"Processing file: {uploaded_file.name}")
-        data = pd.read_csv(uploaded_file)
-        st.write(f"File '{uploaded_file.name}' loaded successfully.")
-
-        # Check required columns
-        required_columns = ["SHIPPER ACCOUNT NUMBER", "RECEIVER ACCOUNT NUMBER"]
-        if not all(column in data.columns for column in required_columns):
-            st.error(f"File '{uploaded_file.name}' is missing required columns: {required_columns}")
-            continue
-
-        st.write(f"Columns verified for '{uploaded_file.name}'. Processing the data...")
-
-        # Extract unique values from the columns
-        unique_values = set(data["SHIPPER ACCOUNT NUMBER"].dropna().unique()) | set(
-            data["RECEIVER ACCOUNT NUMBER"].dropna().unique()
-        )
-        st.write(f"Found {len(unique_values)} unique values in '{uploaded_file.name}'.")
-
-        # Process each unique value
-        for unique_value in unique_values:
-            # Filter data for the unique value
-            filtered_data = data[
-                (data["SHIPPER ACCOUNT NUMBER"] == unique_value)
-                | (data["RECEIVER ACCOUNT NUMBER"] == unique_value)
-            ]
-
-            # Determine where the unique value was found
-            found_in_columns = []
-            if (data["SHIPPER ACCOUNT NUMBER"] == unique_value).any():
-                found_in_columns.append("SHIPPER ACCOUNT NUMBER")
-            if (data["RECEIVER ACCOUNT NUMBER"] == unique_value).any():
-                found_in_columns.append("RECEIVER ACCOUNT NUMBER")
-
-            # Log details
-            st.write(
-                f"Processed {unique_value}: {len(filtered_data)} rows found in columns {', '.join(found_in_columns)}."
-            )
-
-            # Save the filtered data to an Excel file in memory
-            output = BytesIO()
-            with pd.ExcelWriter(output, engine="xlsxwriter") as writer:
-                filtered_data.to_excel(writer, index=False, sheet_name="Sheet1")
-            output.seek(0)
-
-            # Provide a download link for each Excel file
-            st.download_button(
-                label=f"Download Excel for {uploaded_file.name} - {unique_value}",
-                data=output,
-                file_name=f"{original_file_name} - {unique_value}.xlsx",
-                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-            )
+import streamlit as st
+
+# Define the menu structure with labels and their associated script names
+menu = {
+    "GB-GB": "GB-GB.py",
+    "BG": "BG.py",
+    "MultiL": "MultiL.py",
+}
+
+# Sidebar title
+st.sidebar.title("Navigation")
+
+# Sidebar menu implementation
+selected_script = None
+for label, script in menu.items():
+    if st.sidebar.button(label):
+        selected_script = script
+
+# Default script on app load
+if selected_script is None:
+    selected_script = "GB-GB.py"
+
+# Execute the selected script
+exec(open(selected_script).read())