diff --git a/src/gui/_home.py b/src/gui/_home.py
index 64a202a..b39753b 100644
--- a/src/gui/_home.py
+++ b/src/gui/_home.py
@@ -36,6 +36,61 @@ class _StashedUpload:
return self._data
+def _render_stats_overview(findings_by_file: dict) -> None:
+ """4-card grid above the per-file findings — summarizes the run.
+
+ Card layout follows ``datatools_layout_redesign2.html`` §stats:
+ Files analyzed, Total findings, Warnings (severity ``warn`` ∪
+ ``error``), Info (severity ``info``). The warn + info cards are
+ tinted via ``.is-warn`` / ``.is-info`` modifiers that read the
+ severity colors theme.py declares.
+ """
+ import html as _html
+
+ n_files = len(findings_by_file)
+ all_findings = [f for fs in findings_by_file.values() for f in fs]
+ n_total = len(all_findings)
+ # Mockup groups errors with warnings on the "to review" card —
+ # both demand the user act. ``info`` is the lower-priority pile.
+ n_warn = sum(1 for f in all_findings if f.severity in ("warn", "error"))
+ n_info = sum(1 for f in all_findings if f.severity == "info")
+
+ def _card(label: str, value: int, unit: str = "", kind: str = "") -> str:
+ cls = "dt-stat" + (f" {kind}" if kind else "")
+ unit_html = (
+ f'{_html.escape(unit)}'
+ if unit else ""
+ )
+ return (
+ f''
+ f'
{_html.escape(label)}
'
+ f'
{value}{unit_html}
'
+ f"
{cards}
',
+ unsafe_allow_html=True,
+ )
+
+
def _sync_uploader_to_home_uploads() -> None:
"""``on_change`` callback for the home-page file_uploader.
@@ -272,6 +327,11 @@ def _home_page() -> None:
if findings_by_file:
st.divider()
+ # Overview row before drilling into per-file detail. Mockup
+ # layout (datatools_layout_redesign2.html §stats) puts a
+ # 4-card summary above the findings panels so the user can
+ # eyeball the run before expanding any one file.
+ _render_stats_overview(findings_by_file)
# Preserve the upload-stash order so the user sees results in
# the same order they appear in the file list above.
for name in home_uploads:
diff --git a/src/gui/app.py b/src/gui/app.py
index ad31b80..875c13e 100644
--- a/src/gui/app.py
+++ b/src/gui/app.py
@@ -84,7 +84,7 @@ def _build_navigation() -> dict[str, list]:
home = st.Page(
_home_page,
title=_t("nav.home_page_title") or "Home",
- icon="🧹",
+ icon=":material/home:",
default=True,
url_path="home",
)
@@ -99,13 +99,13 @@ def _build_navigation() -> dict[str, list]:
activate = st.Page(
"pages/_Activate.py",
title=_t("nav.activate_title") or "Activate",
- icon="🔑",
+ icon=":material/key:",
url_path="activate",
)
close = st.Page(
"pages/99_Close.py",
title=_t("nav.close_title") or "Close",
- icon="🛑",
+ icon=":material/close:",
url_path="close",
)
diff --git a/src/gui/components/_legacy.py b/src/gui/components/_legacy.py
index cb64e08..68dd18c 100644
--- a/src/gui/components/_legacy.py
+++ b/src/gui/components/_legacy.py
@@ -414,6 +414,60 @@ div[data-testid="stContainer"][data-border="true"] {
border: 1px solid var(--border) !important;
overflow: hidden !important;
}
+
+/* ---------- Stats overview ---------- */
+/* 4-card grid shown above the per-file findings on the home page,
+ summarizing the most recent analysis run. Numeric values use the
+ "Display number" row from geist_spec.md §4 — Geist 28px / 600 /
+ -0.03em — and the severity-tinted variants pick up ``--warn`` /
+ ``--info`` from theme.py. */
+.dt-stats {
+ display: grid;
+ grid-template-columns: repeat(4, 1fr);
+ gap: 12px;
+ margin: 8px 0 20px;
+}
+.dt-stat {
+ background: var(--surface);
+ border: 1px solid var(--border);
+ border-radius: var(--r-lg);
+ padding: 16px 18px;
+ box-shadow: 0 1px 2px rgba(28,25,23,0.03);
+}
+.dt-stat-label {
+ font-size: 11.5px;
+ text-transform: uppercase;
+ letter-spacing: 0.08em;
+ color: var(--ink-tertiary);
+ font-weight: 500;
+ margin-bottom: 6px;
+ line-height: 1.4;
+}
+.dt-stat-value {
+ font-family: var(--font-sans);
+ font-size: 28px;
+ font-weight: 600;
+ letter-spacing: -0.03em;
+ line-height: 1;
+ color: var(--ink);
+ display: flex;
+ align-items: baseline;
+ gap: 6px;
+}
+.dt-stat-unit {
+ font-family: var(--font-sans);
+ font-size: 12px;
+ font-weight: 400;
+ color: var(--ink-tertiary);
+ letter-spacing: 0;
+}
+.dt-stat.is-warn .dt-stat-value { color: var(--warn); }
+.dt-stat.is-info .dt-stat-value { color: var(--info); }
+.dt-stat.is-success .dt-stat-value { color: var(--success); }
+
+@media (max-width: 900px) {
+ .dt-stats { grid-template-columns: repeat(2, 1fr); }
+}
"""
diff --git a/src/gui/theme.py b/src/gui/theme.py
index 7bf8725..fbf0bd6 100644
--- a/src/gui/theme.py
+++ b/src/gui/theme.py
@@ -173,6 +173,30 @@ _CSS = f"""
font-size: 0.92em;
font-feature-settings: "ss02";
}}
+
+ /* Material icons in the sidebar nav. Streamlit's ``:material/:``
+ syntax injects a first-child ```` whose text is the icon's
+ Material Symbols ligature (e.g. ``home``), expected to be rendered
+ by the Material Symbols font. Our base rule above forces
+ ``var(--font-sans)`` on every span inside ``stSidebarNav``, which
+ turns those spans into literal text labels. Override the icon
+ span back to the Material font here. Targeting by ``:first-child``
+ of the nav-link anchor is stable across Streamlit versions —
+ emotion-class hashes are not. */
+ [data-testid="stSidebarNavLink"] > span:first-child,
+ [data-testid="stSidebarNavLink"] > span:first-child * {{
+ font-family: "Material Symbols Outlined", "Material Symbols Rounded",
+ "Material Icons" !important;
+ font-feature-settings: normal !important;
+ font-weight: 400 !important;
+ font-size: 18px !important;
+ line-height: 1 !important;
+ color: var(--ink-secondary);
+ }}
+ [data-testid="stSidebarNavLink"][aria-current="page"] > span:first-child,
+ [data-testid="stSidebarNavLink"][aria-current="page"] > span:first-child * {{
+ color: var(--ink) !important;
+ }}
"""
diff --git a/src/gui/tools_registry.py b/src/gui/tools_registry.py
index 50a9db9..dbfa93c 100644
--- a/src/gui/tools_registry.py
+++ b/src/gui/tools_registry.py
@@ -49,7 +49,7 @@ class Tool:
TOOLS: list[Tool] = [
Tool(
tool_id="04_missing_handler",
- icon="🕳️",
+ icon=":material/help_outline:",
name="Fix Missing Values",
description=(
"Detect disguised nulls, missingness analysis, and imputation strategies."
@@ -60,7 +60,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="06_outlier_detector",
- icon="📊",
+ icon=":material/insights:",
name="Find Unusual Values",
description=(
"Z-score, IQR, and MAD detection with domain-rule violations and "
@@ -72,7 +72,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="02_text_cleaner",
- icon="✂️",
+ icon=":material/text_format:",
name="Clean Text",
description=(
"Whitespace trim, multi-space collapse, Unicode normalization, "
@@ -84,7 +84,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="03_format_standardizer",
- icon="📐",
+ icon=":material/format_list_bulleted:",
name="Standardize Formats",
description=(
"Standardize dates, currencies, names, phone numbers, and addresses."
@@ -95,7 +95,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="01_deduplicator",
- icon="🔍",
+ icon=":material/search:",
name="Find Duplicates",
description=(
"Fuzzy matching, normalization, survivor selection, and "
@@ -107,7 +107,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="08_validator_reporter",
- icon="✅",
+ icon=":material/check_circle:",
name="Quality Check",
description=(
"Validate against rules and generate PDF/Excel quality reports."
@@ -118,7 +118,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="05_column_mapper",
- icon="🗂️",
+ icon=":material/view_column:",
name="Map Columns",
description="Rename columns, enforce a target schema, and coerce types.",
page_slug="5_Column_Mapper",
@@ -127,7 +127,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="07_multi_file_merger",
- icon="📎",
+ icon=":material/account_tree:",
name="Combine Files",
description="Combine multiple CSV/Excel files with schema alignment.",
page_slug="7_Multi_File_Merger",
@@ -136,7 +136,7 @@ TOOLS: list[Tool] = [
),
Tool(
tool_id="09_pipeline_runner",
- icon="⚙️",
+ icon=":material/auto_awesome:",
name="Automated Workflows",
description=(
"Chain tools in recommended order and pass output between steps."
diff --git a/src/i18n/packs/en.json b/src/i18n/packs/en.json
index 2e5f6c5..521e35e 100644
--- a/src/i18n/packs/en.json
+++ b/src/i18n/packs/en.json
@@ -5,7 +5,7 @@
},
"home": {
"page_title": "DataTools — Data Cleaning Mastery",
- "title": "🧹 DataTools — Data Cleaning Mastery",
+ "title": "DataTools — Data Cleaning Mastery",
"caption": "A 9-tool suite for cleaning, standardizing, and validating tabular data. Runs 100% locally.",
"findings_badge_one": "{n} finding",
"findings_badge_other": "{n} findings"
@@ -57,14 +57,14 @@
},
"close_page": {
"page_title": "DataTools — Close",
- "title": "🛑 Close DataTools",
+ "title": "Close DataTools",
"caption": "Shut down the local app and free the terminal.",
"body": "Clicking the button below will terminate the DataTools server. Any unsaved work in other tools will be lost. Once the app shuts down you can close this window.",
"button": "Close the app"
},
"activation": {
"page_title": "DataTools — Activate",
- "title": "🔑 Activate DataTools",
+ "title": "Activate DataTools",
"intro": "DataTools needs to be activated before any tools unlock. Enter the name and email tied to your purchase, then paste the license blob from your delivery email.",
"name_label": "Full name",
"name_help": "Must match the name on your purchase receipt.",
@@ -107,55 +107,55 @@
"01_deduplicator": {
"name": "Find Duplicates",
"description": "Fuzzy matching, normalization, survivor selection, and interactive review.",
- "page_title": "🔍 Find Duplicates",
+ "page_title": "Find Duplicates",
"page_caption": "Find and remove duplicate rows in CSV, delimited text, and Excel files."
},
"02_text_cleaner": {
"name": "Clean Text",
"description": "Whitespace trim, multi-space collapse, Unicode normalization, BOM and line-ending handling.",
- "page_title": "✂️ Clean Text",
+ "page_title": "Clean Text",
"page_caption": "Trim whitespace, fold smart quotes, strip invisible characters, and normalize line endings. Runs locally — your data never leaves this computer."
},
"03_format_standardizer": {
"name": "Standardize Formats",
"description": "Standardize dates, currencies, names, phone numbers, and addresses.",
- "page_title": "📐 Standardize Formats",
+ "page_title": "Standardize Formats",
"page_caption": "Canonicalize dates, phone numbers, currency, names, addresses, and booleans on a per-column basis. Runs locally — your data never leaves this computer."
},
"04_missing_handler": {
"name": "Fix Missing Values",
"description": "Detect disguised nulls, missingness analysis, and imputation strategies.",
- "page_title": "🕳️ Fix Missing Values",
+ "page_title": "Fix Missing Values",
"page_caption": "Detect disguised nulls, profile missingness, and apply imputation or drop strategies. Runs locally — your data never leaves this computer."
},
"05_column_mapper": {
"name": "Map Columns",
"description": "Rename columns, enforce a target schema, and coerce types.",
- "page_title": "🗂️ Map Columns",
+ "page_title": "Map Columns",
"page_caption": "Rename columns, enforce a target schema, and coerce types. Runs locally — your data never leaves this computer."
},
"06_outlier_detector": {
"name": "Find Unusual Values",
"description": "Z-score, IQR, and MAD detection with domain-rule violations and winsorization.",
- "page_title": "📊 Find Unusual Values",
+ "page_title": "Find Unusual Values",
"page_caption": "Detect and handle outliers in numeric columns."
},
"07_multi_file_merger": {
"name": "Combine Files",
"description": "Combine multiple CSV/Excel files with schema alignment.",
- "page_title": "📎 Combine Files",
+ "page_title": "Combine Files",
"page_caption": "Combine multiple CSV and Excel files into one dataset."
},
"08_validator_reporter": {
"name": "Quality Check",
"description": "Validate against rules and generate PDF/Excel quality reports.",
- "page_title": "✅ Quality Check",
+ "page_title": "Quality Check",
"page_caption": "Validate data against rules and generate quality reports."
},
"09_pipeline_runner": {
"name": "Automated Workflows",
"description": "Chain tools in recommended order and pass output between steps.",
- "page_title": "⚙️ Automated Workflows",
+ "page_title": "Automated Workflows",
"page_caption": "Chain DataTools cleaning steps into one repeatable workflow. The pipeline recommends an order; you stay in control."
}
},
diff --git a/src/i18n/packs/es.json b/src/i18n/packs/es.json
index 7e0a5bb..9a7eea7 100644
--- a/src/i18n/packs/es.json
+++ b/src/i18n/packs/es.json
@@ -5,7 +5,7 @@
},
"home": {
"page_title": "DataTools — Maestría en limpieza de datos",
- "title": "🧹 DataTools — Maestría en limpieza de datos",
+ "title": "DataTools — Maestría en limpieza de datos",
"caption": "Conjunto de 9 herramientas para limpiar, estandarizar y validar datos tabulares. Se ejecuta 100% en local.",
"findings_badge_one": "{n} hallazgo",
"findings_badge_other": "{n} hallazgos"
@@ -57,14 +57,14 @@
},
"close_page": {
"page_title": "DataTools — Cerrar",
- "title": "🛑 Cerrar DataTools",
+ "title": "Cerrar DataTools",
"caption": "Detén la aplicación local y libera la terminal.",
"body": "Al pulsar el botón de abajo se cerrará el servidor de DataTools. Cualquier trabajo sin guardar en otras herramientas se perderá. Una vez cerrada la app, puedes cerrar esta ventana.",
"button": "Cerrar la app"
},
"activation": {
"page_title": "DataTools — Activar",
- "title": "🔑 Activar DataTools",
+ "title": "Activar DataTools",
"intro": "DataTools debe activarse antes de desbloquear cualquier herramienta. Introduce el nombre y correo asociados a tu compra, y luego pega el código de licencia del correo de entrega.",
"name_label": "Nombre completo",
"name_help": "Debe coincidir con el nombre en el recibo de compra.",
@@ -107,55 +107,55 @@
"01_deduplicator": {
"name": "Buscar duplicados",
"description": "Coincidencia difusa, normalización, selección de superviviente y revisión interactiva.",
- "page_title": "🔍 Buscar duplicados",
+ "page_title": "Buscar duplicados",
"page_caption": "Encuentra y elimina filas duplicadas en archivos CSV, texto delimitado y Excel."
},
"02_text_cleaner": {
"name": "Limpiar texto",
"description": "Recorte de espacios, colapso de espacios múltiples, normalización Unicode, manejo de BOM y de finales de línea.",
- "page_title": "✂️ Limpiar texto",
+ "page_title": "Limpiar texto",
"page_caption": "Recorta espacios, normaliza comillas tipográficas, elimina caracteres invisibles y unifica saltos de línea. Se ejecuta localmente — tus datos nunca salen de este equipo."
},
"03_format_standardizer": {
"name": "Estandarizar formatos",
"description": "Estandariza fechas, monedas, nombres, números de teléfono y direcciones.",
- "page_title": "📐 Estandarizar formatos",
+ "page_title": "Estandarizar formatos",
"page_caption": "Canoniza fechas, números de teléfono, monedas, nombres, direcciones y booleanos columna por columna. Se ejecuta localmente — tus datos nunca salen de este equipo."
},
"04_missing_handler": {
"name": "Corregir valores faltantes",
"description": "Detecta nulos disfrazados, analiza la ausencia de datos y aplica estrategias de imputación.",
- "page_title": "🕳️ Corregir valores faltantes",
+ "page_title": "Corregir valores faltantes",
"page_caption": "Detecta nulos disfrazados, perfila la ausencia de datos y aplica imputación o estrategias de descarte. Se ejecuta localmente — tus datos nunca salen de este equipo."
},
"05_column_mapper": {
"name": "Mapear columnas",
"description": "Renombra columnas, aplica un esquema objetivo y fuerza tipos de datos.",
- "page_title": "🗂️ Mapear columnas",
+ "page_title": "Mapear columnas",
"page_caption": "Renombra columnas, aplica un esquema objetivo y fuerza tipos. Se ejecuta localmente — tus datos nunca salen de este equipo."
},
"06_outlier_detector": {
"name": "Detectar valores atípicos",
"description": "Detección por Z-score, IQR y MAD con reglas de dominio y winsorización.",
- "page_title": "📊 Detectar valores atípicos",
+ "page_title": "Detectar valores atípicos",
"page_caption": "Detecta y trata valores atípicos en columnas numéricas."
},
"07_multi_file_merger": {
"name": "Combinar archivos",
"description": "Combina varios archivos CSV/Excel alineando sus esquemas.",
- "page_title": "📎 Combinar archivos",
+ "page_title": "Combinar archivos",
"page_caption": "Combina varios archivos CSV y Excel en un único conjunto de datos."
},
"08_validator_reporter": {
"name": "Verificación de calidad",
"description": "Valida contra reglas y genera informes de calidad en PDF/Excel.",
- "page_title": "✅ Verificación de calidad",
+ "page_title": "Verificación de calidad",
"page_caption": "Valida datos contra reglas y genera informes de calidad."
},
"09_pipeline_runner": {
"name": "Flujos automatizados",
"description": "Encadena herramientas en el orden recomendado y pasa la salida entre pasos.",
- "page_title": "⚙️ Flujos automatizados",
+ "page_title": "Flujos automatizados",
"page_caption": "Encadena pasos de limpieza de DataTools en un flujo repetible. La canalización recomienda un orden; tú mantienes el control."
}
},