- Drop unused 'from src.i18n import t' from pages 1-9 (the swap to render_tool_header(tool_id) means no page calls t() directly anymore). Pages 10, 11 and the underscore-prefixed pages were already clean or legitimately use t(). - Rewrite PDF Extractor help_md (en + es). The original prose described features the tool does NOT have — template drawing, per-source saved templates, automatic reuse. The actual tool is a heuristic batch scanner (per its own docstring: "No templates, no per-bank configuration"). New copy: scan → uncheck → pick date format → enable OCR if needed → download. Spanish version tagged with '<!-- TODO: review Spanish -->' since the prose is best-effort. - Document why both stSidebarNavSectionHeader (legacy, streamlit~=1.35) and stNavSectionHeader (current, 1.57) testids appear in the chrome CSS — requirements floor is streamlit>=1.35,<2 so dropping the legacy selector would silently break the lower bound. - Pin the t()-returns-key-on-miss contract that render_tool_header's fallback path depends on, with a comment at the call site. - Pin the demo's intentional skip of hide_streamlit_chrome (so the +/- sidebar swap JS doesn't ever try to load there) with a load- bearing comment in app_demo.py. - Confirmed i18n parity: every tool id has page_title / page_caption / description / name / help_md in BOTH packs; help.button_label and help.missing_body in both. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
97 lines
3.2 KiB
Python
97 lines
3.2 KiB
Python
"""DataTools Combine Files — 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))
|
|
|
|
from src.gui.components import (
|
|
back_to_home_link,
|
|
render_sticky_footer,
|
|
render_tool_header,
|
|
hide_streamlit_chrome,
|
|
require_feature_or_render_upgrade,
|
|
)
|
|
from src.license import FeatureFlag
|
|
|
|
hide_streamlit_chrome()
|
|
render_sticky_footer()
|
|
back_to_home_link()
|
|
from src.audit import log_page_open
|
|
log_page_open("7_Multi_File_Merger")
|
|
require_feature_or_render_upgrade(FeatureFlag.MULTI_FILE_MERGER)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Header
|
|
# ---------------------------------------------------------------------------
|
|
|
|
render_tool_header("07_multi_file_merger")
|
|
|
|
st.info("This tool is under development.")
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# What this tool will do
|
|
# ---------------------------------------------------------------------------
|
|
|
|
st.markdown("""
|
|
**Features:**
|
|
- Import 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(
|
|
"Import CSV or Excel files",
|
|
type=["csv", "tsv", "xlsx", "xls"],
|
|
accept_multiple_files=True,
|
|
help="Import 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), width="stretch")
|
|
except Exception as e:
|
|
from src.core.errors import format_for_user
|
|
st.error(
|
|
f"**Could not read `{f.name}`**\n\n"
|
|
f"```\n{format_for_user(e)}\n```"
|
|
)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 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", width="stretch", disabled=True)
|
|
|