datatools-dev/src/gui/app.py

"""DataTools — Data Cleaning Mastery Suite.

Launch:
    streamlit run src/gui/app.py

This module is the navigation manager for the full GUI: it registers
every tool page with ``st.navigation`` so the sidebar can render
section headers ("Data Review", "Data Cleaners", "Transformations",
"Automations") instead of the flat numbered list Streamlit's
auto-page-discovery would produce. The Home page itself is registered
as a callable defined below so the entry script remains the single
file users invoke.
"""

from __future__ import annotations

import sys
from pathlib import Path

import streamlit as st

# Ensure project root is on sys.path so `src.core` imports work
_project_root = Path(__file__).resolve().parent.parent.parent
if str(_project_root) not in sys.path:
    sys.path.insert(0, str(_project_root))


# ---------------------------------------------------------------------------
# Home page (rendered when the user selects the default nav entry)
# ---------------------------------------------------------------------------

def _home_page() -> None:
    """Render the home page — multi-file upload + per-file analysis."""
    from src.gui.components import hide_streamlit_chrome, render_findings_panel
    from src.gui.components._legacy import _run_analysis_on_upload
    from src.i18n import t

    st.set_page_config(
        page_title=t("home.page_title"),
        page_icon="🧹",
        layout="wide",
    )
    hide_streamlit_chrome()

    st.title(t("home.title"))
    st.caption(t("home.caption"))
    st.divider()

    st.markdown(f"### {t('upload.heading')}")
    st.caption(t("upload.intro_multi"))

    uploaded_files = st.file_uploader(
        t("upload.uploader_label_multi"),
        type=["csv", "tsv", "xlsx", "xls"],
        accept_multiple_files=True,
        key="home_upload",
        help=t("upload.uploader_help"),
    )

    if not uploaded_files:
        st.info(t("upload.empty_state"))
        return

    # Keep tool pages working: they consume a single ``home_uploaded_*``
    # set via ``pickup_or_upload``. Expose the first uploaded file as
    # the "active" upload for that contract; the rest live alongside
    # for per-file analysis on this page.
    first = uploaded_files[0]
    if (
        st.session_state.get("home_uploaded_name") != first.name
        or st.session_state.get("home_uploaded_size") != first.size
    ):
        st.session_state["home_uploaded_name"] = first.name
        st.session_state["home_uploaded_size"] = first.size
        st.session_state["home_uploaded_bytes"] = first.getvalue()

    # Per-file findings live in a dict so removing a file from the
    # uploader (Streamlit's "x" button) drops its results too. We only
    # re-analyze files we haven't already analyzed in this session.
    findings_by_file: dict = st.session_state.setdefault(
        "home_findings_by_file", {}
    )
    current_names = {f.name for f in uploaded_files}
    findings_by_file = {
        name: result for name, result in findings_by_file.items()
        if name in current_names
    }
    st.session_state["home_findings_by_file"] = findings_by_file

    pending = [f for f in uploaded_files if f.name not in findings_by_file]

    col_run, col_clear, _ = st.columns([1, 1, 4])
    with col_run:
        run_clicked = st.button(
            t("upload.run_button"),
            type="primary",
            key="home_run_analysis",
            disabled=not pending,
            use_container_width=True,
        )
    with col_clear:
        clear_clicked = st.button(
            t("upload.clear_results"),
            key="home_clear_results",
            disabled=not findings_by_file,
            use_container_width=True,
        )

    if clear_clicked:
        st.session_state["home_findings_by_file"] = {}
        st.rerun()

    if run_clicked:
        progress = st.progress(0.0, text=t("upload.scanning"))
        for i, f in enumerate(pending, start=1):
            findings_by_file[f.name] = _run_analysis_on_upload(f)
            progress.progress(i / len(pending), text=f"{f.name}")
        st.session_state["home_findings_by_file"] = findings_by_file
        progress.empty()
        st.rerun()

    if findings_by_file:
        st.divider()
        # Preserve uploader order so the user sees results in the same
        # order they appear in the file list above.
        for f in uploaded_files:
            if f.name not in findings_by_file:
                continue
            findings = findings_by_file[f.name]
            with st.container(border=True):
                if not findings:
                    st.markdown(f"### 📄 {f.name}")
                    st.success(t("findings.none"))
                else:
                    render_findings_panel(findings, header=f"📄 {f.name}")

    st.divider()
    st.caption(t("chrome.footer"))


# ---------------------------------------------------------------------------
# Navigation registration
# ---------------------------------------------------------------------------
#
# ``st.navigation`` overrides Streamlit's auto-discovery of the
# ``pages/`` directory, so every page we want in the sidebar must be
# listed here. The dict key becomes the section header rendered above
# the entries; an empty-string key suppresses the header so the Home
# entry sits at the top without a label above it.

from src.gui.tools_registry import TOOLS, section_label  # noqa: E402
from src.i18n import t as _t  # noqa: E402


def _page_for(tool_id: str, *, page_slug: str, icon: str, title: str) -> "st.Page":
    return st.Page(
        f"pages/{page_slug}.py",
        title=title,
        icon=icon,
        url_path=tool_id,
    )


def _build_navigation() -> dict[str, list]:
    by_section: dict[str, list] = {
        "cleaners": [],
        "transformations": [],
        "automations": [],
    }
    for tool in TOOLS:
        by_section[tool.section].append(
            _page_for(
                tool.tool_id,
                page_slug=tool.page_slug,
                icon=tool.icon,
                title=tool.name,
            )
        )

    home = st.Page(
        _home_page,
        title=_t("nav.home_page_title") or "Home",
        icon="🧹",
        default=True,
        url_path="home",
    )
    activate = st.Page(
        "pages/_Activate.py",
        title=_t("nav.activate_title") or "Activate",
        icon="🔑",
        url_path="activate",
    )
    close = st.Page(
        "pages/99_Close.py",
        title=_t("nav.close_title") or "Close",
        icon="🛑",
        url_path="close",
    )

    account_header = _t("nav.section_account") or "Account"
    return {
        "": [home],
        section_label("cleaners"): by_section["cleaners"],
        section_label("transformations"): by_section["transformations"],
        section_label("automations"): by_section["automations"],
        account_header: [activate, close],
    }


pg = st.navigation(_build_navigation())
pg.run()