giteadmin/datatools-dev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(gui): sidebar sections + non-technical tool labels

Browse Source 
Sidebar nav now groups tools under Data Review / Data Cleaners /
Transformations / Automations via st.navigation, replacing the flat
auto-discovered list. Tool display names switch to action-first
phrasing (Find Duplicates, Fix Missing Values, Find Unusual Values,
Standardize Formats, Clean Text, Quality Check, Map Columns, Combine
Files, Automated Workflows) in EN + ES packs and on each page's H1.

The Data Cleaners section follows the requested order: Missing
Values → Outliers → Text Cleaner → Format Standardizer → Deduplicator
→ Quality Check. (Text Cleaner kept inside cleaners since the request
didn't list it but the tool still ships.) Registry now carries a
section field; helpers added: tools_in_section(), section_label().

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Michael
2026-05-16 19:36:01 +00:00
parent 624f99653e
commit 93e43fc0d9
19 changed files with 356 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files

256
src/gui/app.py
View File

@@ -2,6 +2,14 @@
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
@@ -18,102 +26,186 @@ if str(_project_root) not in sys.path:
# ---------------------------------------------------------------------------
# Page config
# Home page (rendered when the user selects the default nav entry)
# ---------------------------------------------------------------------------
from src.gui.components import (
findings_count_for_tool,
hide_streamlit_chrome,
upload_and_analyze_section,
)
from src.i18n import t
def _home_page() -> None:
"""Render the home page — upload section + tool grid + footer."""
from src.gui.components import (
findings_count_for_tool,
hide_streamlit_chrome,
upload_and_analyze_section,
)
from src.gui.tools_registry import (
TOOLS,
section_label,
tool_description,
tool_name,
)
from src.i18n import t
from src.license import get_manager
st.set_page_config(
page_title=t("home.page_title"),
page_icon="🧹",
layout="wide",
)
st.set_page_config(
page_title=t("home.page_title"),
page_icon="🧹",
layout="wide",
)
hide_streamlit_chrome()
# ``hide_streamlit_chrome`` also renders the sidebar language selector,
# so every page that hides chrome picks up the same picker.
hide_streamlit_chrome()
st.title(t("home.title"))
st.caption(t("home.caption"))
st.divider()
upload_and_analyze_section()
st.divider()
# Per-tier feature set for badging — Ready tools that the user's
# tier doesn't unlock get a red "🔒 Locked" pill instead of the green
# "Ready" so they see at a glance which tools an upgrade would
# unlock. Dev-mode skips the lock check so the home grid renders the
# full SKU during development.
_license_state = get_manager().current_state()
_unlocked_features = (
set(_license_state.features) if _license_state.valid else set()
)
_dev_mode = get_manager().dev_mode
# Group tool cards by sidebar section so the home grid mirrors the
# left-nav layout — same vocabulary, same ordering.
sections: list[tuple[str, list]] = []
for section in ("review", "cleaners", "transformations", "automations"):
tools = [tool for tool in TOOLS if tool.section == section]
if not tools:
continue
sections.append((section_label(section), tools))
for header, tools in sections:
st.subheader(header)
for row_start in range(0, len(tools), 3):
cols = st.columns(3)
for i, col in enumerate(cols):
idx = row_start + i
if idx >= len(tools):
break
tool = tools[idx]
with col:
tool_locked = (
tool.status == "Ready"
and not _dev_mode
and tool.tool_id not in _unlocked_features
)
if tool_locked:
status_key = "license.status_locked"
status_color = "red"
elif tool.status == "Ready":
status_key = "status.ready"
status_color = "green"
else:
status_key = "status.coming_soon"
status_color = "orange"
badge = ""
n = findings_count_for_tool(tool.tool_id)
if n:
badge_key = (
"home.findings_badge_one"
if n == 1
else "home.findings_badge_other"
)
badge = f" :red-background[**{t(badge_key, n=n)}**]"
lock_glyph = "🔒 " if tool_locked else ""
st.markdown(
f"### {tool.icon} {tool_name(tool.tool_id)}{badge}\n\n"
f"{tool_description(tool.tool_id)}\n\n"
f":{status_color}[**{lock_glyph}{t(status_key)}**]"
)
st.divider()
st.caption(t("chrome.footer"))
# ---------------------------------------------------------------------------
# Home page
# 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.
st.title(t("home.title"))
st.caption(t("home.caption"))
from src.gui.tools_registry import TOOLS, section_label # noqa: E402
from src.i18n import t as _t # noqa: E402
st.divider()
# ---------------------------------------------------------------------------
# Upload & analyze (optional onboarding step)
# ---------------------------------------------------------------------------
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,
)
upload_and_analyze_section()
st.divider()
# ---------------------------------------------------------------------------
# Tool cards
# ---------------------------------------------------------------------------
from src.gui.tools_registry import TOOLS, tool_description, tool_name
from src.license import get_manager
# Per-tier feature set for badging — Ready tools that the user's
# tier doesn't unlock get a red "🔒 Locked" pill instead of the green
# "Ready" so they see at a glance which tools an upgrade would
# unlock. Dev-mode skips the lock check so the home grid renders the
# full SKU during development.
_license_state = get_manager().current_state()
_unlocked_features = set(_license_state.features) if _license_state.valid else set()
_dev_mode = get_manager().dev_mode
# Render tool cards in a 3-column grid. Cards picked up by the analyzer get a
# coloured "N findings" badge so the user can see at a glance which tools
# would help with the just-uploaded file.
for row_start in range(0, len(TOOLS), 3):
cols = st.columns(3)
for i, col in enumerate(cols):
idx = row_start + i
if idx >= len(TOOLS):
break
tool = TOOLS[idx]
with col:
tool_locked = (
tool.status == "Ready"
and not _dev_mode
and tool.tool_id not in _unlocked_features
def _build_navigation() -> dict[str, list]:
by_section: dict[str, list] = {
"review": [],
"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,
)
if tool_locked:
status_key = "license.status_locked"
status_color = "red"
elif tool.status == "Ready":
status_key = "status.ready"
status_color = "green"
else:
status_key = "status.coming_soon"
status_color = "orange"
)
badge = ""
n = findings_count_for_tool(tool.tool_id)
if n:
badge_key = "home.findings_badge_one" if n == 1 else "home.findings_badge_other"
badge = f" :red-background[**{t(badge_key, n=n)}**]"
lock_glyph = "🔒 " if tool_locked else ""
st.markdown(
f"### {tool.icon} {tool_name(tool.tool_id)}{badge}\n\n"
f"{tool_description(tool.tool_id)}\n\n"
f":{status_color}[**{lock_glyph}{t(status_key)}**]"
)
# The Review gate has no entry in the registry (it isn't a "tool")
# so register it by hand at the top of its section.
review_page = st.Page(
"pages/0_Review.py",
title=_t("nav.review_page_title") or "Review",
icon="🛡️",
url_path="review",
)
by_section["review"].insert(0, review_page)
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("review"): by_section["review"],
section_label("cleaners"): by_section["cleaners"],
section_label("transformations"): by_section["transformations"],
section_label("automations"): by_section["automations"],
account_header: [activate, close],
}
# ---------------------------------------------------------------------------
# Footer
# ---------------------------------------------------------------------------
st.divider()
st.caption(t("chrome.footer"))
pg = st.navigation(_build_navigation())
pg.run()

4
src/gui/pages/1_Deduplicator.py
View File

@@ -54,7 +54,7 @@ for key, default in _DEFAULTS.items():
# Header
# ---------------------------------------------------------------------------
st.title("🔍 Deduplicator")
st.title("🔍 Find Duplicates")
st.caption("Find and remove duplicate rows in CSV, delimited text, and Excel files.")
@@ -363,5 +363,5 @@ else:
st.divider()
st.caption(
"Runs locally. Your data never leaves this computer. "
"| DataTools Deduplicator v3.0"
"| DataTools v3.0"
)

2
src/gui/pages/2_Text_Cleaner.py
View File

@@ -39,7 +39,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("✂️ Text Cleaner")
st.title("✂️ Clean Text")
st.caption(
"Trim whitespace, fold smart quotes, strip invisible characters, and "
"normalize line endings. Runs locally — your data never leaves this computer."

2
src/gui/pages/3_Format_Standardizer.py
View File

@@ -37,7 +37,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("📐 Format Standardizer")
st.title("📐 Standardize Formats")
st.caption(
"Canonicalize dates, phone numbers, currency, names, addresses, and "
"booleans on a per-column basis. Runs locally — your data never leaves "

2
src/gui/pages/4_Missing_Values.py
View File

@@ -38,7 +38,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("🕳️ Missing Value Handler")
st.title("🕳️ Fix Missing Values")
st.caption(
"Detect disguised nulls, profile missingness, and apply imputation or "
"drop strategies. Runs locally — your data never leaves this computer."

2
src/gui/pages/5_Column_Mapper.py
View File

@@ -39,7 +39,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("🗂️ Column Mapper")
st.title("🗂️ Map Columns")
st.caption(
"Rename columns, enforce a target schema, and coerce types. Runs locally — "
"your data never leaves this computer."

2
src/gui/pages/6_Outlier_Detector.py
View File

@@ -26,7 +26,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("📊 Outlier Detector")
st.title("📊 Find Unusual Values")
st.caption("Detect and handle outliers in numeric columns.")
st.info("This tool is under development.")

2
src/gui/pages/7_Multi_File_Merger.py
View File

@@ -26,7 +26,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("📎 Multi-File Merger")
st.title("📎 Combine Files")
st.caption("Combine multiple CSV and Excel files into one dataset.")
st.info("This tool is under development.")

2
src/gui/pages/8_Validator_Reporter.py
View File

@@ -26,7 +26,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("✅ Validator & Reporter")
st.title("✅ Quality Check")
st.caption("Validate data against rules and generate quality reports.")
st.info("This tool is under development.")

2
src/gui/pages/9_Pipeline_Runner.py
View File

@@ -40,7 +40,7 @@ require_normalization_gate()
# Header
# ---------------------------------------------------------------------------
st.title("⚙️ Pipeline Runner")
st.title("⚙️ Automated Workflows")
st.caption(
"Chain DataTools cleaning steps into one repeatable workflow. The "
"pipeline recommends an order; you stay in control."

151
src/gui/tools_registry.py
View File

@@ -1,9 +1,9 @@
"""Per-tool manifest registry.
Single source of truth for what tools exist, their display strings, and
the tier (which controls whether a tool ships in a given build SKU). The
home-page sidebar consumes this list; future per-tool packaging will
filter it via the ``tier`` field.
Single source of truth for what tools exist, their display strings, the
left-nav section they belong to, and the tier (which controls whether a
tool ships in a given build SKU). The home-page sidebar consumes this
list; future per-tool packaging will filter it via the ``tier`` field.
Adding a tool: append one ``Tool`` entry. Page filenames must match the
``page_slug`` so Streamlit's automatic page discovery picks them up.
@@ -22,6 +22,10 @@ from typing import Literal
Tier = Literal["core", "pro", "enterprise"]
Status = Literal["Ready", "Coming Soon"]
# Sidebar grouping. The Review gate is its own section; cleaners,
# transformations, and automations group the tools by what the user is
# trying to accomplish rather than by implementation detail.
Section = Literal["review", "cleaners", "transformations", "automations"]
@dataclass(frozen=True)
@@ -34,102 +38,127 @@ class Tool:
description: str # One-sentence card body.
page_slug: str # Streamlit page filename without ".py" (e.g. "1_Deduplicator").
status: Status # "Ready" or "Coming Soon" — drives the card badge color.
section: Section # Sidebar group this tool belongs to.
tier: Tier = "core" # Build-time gating hook; every tool is "core" today.
# Order in this list IS the order shown in each sidebar section, so
# arranging it carefully matters: within "cleaners" we lead with the
# operations a non-technical user is most likely to need (filling
# blanks, flagging outliers) before progressing to format cleanup,
# dedup, and the final quality report.
TOOLS: list[Tool] = [
Tool(
tool_id="01_deduplicator",
icon="🔍",
name="Deduplicator",
description=(
"Fuzzy matching, normalization, survivor selection, and "
"interactive review."
),
page_slug="1_Deduplicator",
status="Ready",
),
Tool(
tool_id="02_text_cleaner",
icon="✂️",
name="Text Cleaner",
description=(
"Whitespace trim, multi-space collapse, Unicode normalization, "
"BOM and line-ending handling."
),
page_slug="2_Text_Cleaner",
status="Ready",
),
Tool(
tool_id="03_format_standardizer",
icon="📐",
name="Format Standardizer",
description=(
"Standardize dates, currencies, names, phone numbers, and addresses."
),
page_slug="3_Format_Standardizer",
status="Ready",
),
Tool(
tool_id="04_missing_handler",
icon="🕳️",
name="Missing Value Handler",
name="Fix Missing Values",
description=(
"Detect disguised nulls, missingness analysis, and imputation strategies."
),
page_slug="4_Missing_Values",
status="Ready",
),
Tool(
tool_id="05_column_mapper",
icon="🗂️",
name="Column Mapper",
description="Rename columns, enforce a target schema, and coerce types.",
page_slug="5_Column_Mapper",
status="Ready",
section="cleaners",
),
Tool(
tool_id="06_outlier_detector",
icon="📊",
name="Outlier Detector",
name="Find Unusual Values",
description=(
"Z-score, IQR, and MAD detection with domain-rule violations and "
"winsorization."
),
page_slug="6_Outlier_Detector",
status="Coming Soon",
section="cleaners",
),
Tool(
tool_id="07_multi_file_merger",
icon="📎",
name="Multi-File Merger",
description="Combine multiple CSV/Excel files with schema alignment.",
page_slug="7_Multi_File_Merger",
status="Coming Soon",
tool_id="02_text_cleaner",
icon="✂️",
name="Clean Text",
description=(
"Whitespace trim, multi-space collapse, Unicode normalization, "
"BOM and line-ending handling."
),
page_slug="2_Text_Cleaner",
status="Ready",
section="cleaners",
),
Tool(
tool_id="03_format_standardizer",
icon="📐",
name="Standardize Formats",
description=(
"Standardize dates, currencies, names, phone numbers, and addresses."
),
page_slug="3_Format_Standardizer",
status="Ready",
section="cleaners",
),
Tool(
tool_id="01_deduplicator",
icon="🔍",
name="Find Duplicates",
description=(
"Fuzzy matching, normalization, survivor selection, and "
"interactive review."
),
page_slug="1_Deduplicator",
status="Ready",
section="cleaners",
),
Tool(
tool_id="08_validator_reporter",
icon="✅",
name="Validator & Reporter",
name="Quality Check",
description=(
"Validate against rules and generate PDF/Excel quality reports."
),
page_slug="8_Validator_Reporter",
status="Coming Soon",
section="cleaners",
),
Tool(
tool_id="05_column_mapper",
icon="🗂️",
name="Map Columns",
description="Rename columns, enforce a target schema, and coerce types.",
page_slug="5_Column_Mapper",
status="Ready",
section="transformations",
),
Tool(
tool_id="07_multi_file_merger",
icon="📎",
name="Combine Files",
description="Combine multiple CSV/Excel files with schema alignment.",
page_slug="7_Multi_File_Merger",
status="Coming Soon",
section="transformations",
),
Tool(
tool_id="09_pipeline_runner",
icon="⚙️",
name="Pipeline Runner",
name="Automated Workflows",
description=(
"Chain tools in recommended order and pass output between steps."
),
page_slug="9_Pipeline_Runner",
status="Ready",
section="automations",
),
]
# Display labels for each sidebar section. Kept here so i18n falls back
# to a sensible English string if a translation pack is missing the key.
SECTION_LABELS: dict[Section, str] = {
"review": "Data Review",
"cleaners": "Data Cleaners",
"transformations": "Transformations",
"automations": "Automations",
}
def tools_for_tier(*tiers: Tier) -> list[Tool]:
"""Subset filter for build-time slicing.
@@ -142,6 +171,11 @@ def tools_for_tier(*tiers: Tier) -> list[Tool]:
return [t for t in TOOLS if t.tier in keep]
def tools_in_section(section: Section) -> list[Tool]:
"""Return the tools in *section*, preserving registry order."""
return [t for t in TOOLS if t.section == section]
def tool_by_id(tool_id: str) -> Tool | None:
return next((t for t in TOOLS if t.tool_id == tool_id), None)
@@ -167,3 +201,12 @@ def tool_description(tool_id: str) -> str:
fallback = tool.description if tool else ""
translated = _t(f"tools.{tool_id}.description")
return translated if translated != f"tools.{tool_id}.description" else fallback
def section_label(section: Section) -> str:
"""Return the localized sidebar section header."""
from src.i18n import t as _t
fallback = SECTION_LABELS[section]
key = f"nav.section_{section}"
translated = _t(key)
return translated if translated != key else fallback