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

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:
2026-05-16 19:36:01 +00:00
parent 624f99653e
commit 93e43fc0d9
19 changed files with 356 additions and 199 deletions

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