feat: refactor GUI to multi-page Streamlit app with 9 tool pages

Convert single-page deduplicator into a multi-page suite. Home page shows
tool card grid. Deduplicator extracted to its own page (fully working).
8 stub pages added for Text Cleaner, Format Standardizer, Missing Values,
Column Mapper, Outlier Detector, Multi-File Merger, Validator & Reporter,
and Pipeline Runner — each with functional file upload and coming-soon UI.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-29 01:16:12 +00:00
parent 9ec371a85f
commit f2fdc10af7
10 changed files with 1175 additions and 330 deletions

View File

@@ -0,0 +1,86 @@
"""DataTools Multi-File Merger — stub page."""
from __future__ import annotations
import sys
from pathlib import Path
import streamlit as st
_project_root = Path(__file__).resolve().parent.parent.parent.parent
if str(_project_root) not in sys.path:
sys.path.insert(0, str(_project_root))
# ---------------------------------------------------------------------------
# Header
# ---------------------------------------------------------------------------
st.title("📎 Multi-File Merger")
st.caption("Combine multiple CSV and Excel files into one dataset.")
st.info("This tool is under development.")
# ---------------------------------------------------------------------------
# What this tool will do
# ---------------------------------------------------------------------------
st.markdown("""
**Features:**
- Upload multiple CSV/Excel files at once
- Automatic schema alignment (matching columns by name)
- Append mode: stack files vertically (union)
- Join mode: merge files on shared key columns
- Handle mismatched columns (fill missing with nulls or drop)
- Source file tracking column
""")
st.divider()
# ---------------------------------------------------------------------------
# Multi-file upload (functional)
# ---------------------------------------------------------------------------
uploaded_files = st.file_uploader(
"Upload CSV or Excel files",
type=["csv", "tsv", "xlsx", "xls"],
accept_multiple_files=True,
help="Upload multiple files to preview. Processing is not yet available.",
key="merger_file_upload",
)
if uploaded_files:
import pandas as pd
for f in uploaded_files:
try:
if f.name.endswith((".xlsx", ".xls")):
df = pd.read_excel(f)
else:
df = pd.read_csv(f)
st.subheader(f"Preview: {f.name}")
st.caption(f"{len(df)} rows, {len(df.columns)} columns — Columns: {', '.join(df.columns[:10])}{'...' if len(df.columns) > 10 else ''}")
st.dataframe(df.head(5), use_container_width=True)
except Exception as e:
st.error(f"Failed to read {f.name}: {e}")
# ---------------------------------------------------------------------------
# Placeholder options
# ---------------------------------------------------------------------------
st.subheader("Merge Strategy")
st.selectbox("Mode", ["Append (stack vertically)", "Join on key columns", "Schema alignment (smart merge)"], disabled=True)
st.selectbox("Mismatched columns", ["Fill with null", "Drop non-shared columns", "Error"], disabled=True)
st.checkbox("Add source filename column", value=True, disabled=True)
st.divider()
st.button("Merge Files", type="primary", use_container_width=True, disabled=True)
# ---------------------------------------------------------------------------
# Footer
# ---------------------------------------------------------------------------
st.divider()
st.caption(
"Runs locally. Your data never leaves this computer. "
"| DataTools v3.0"
)