feat(design-media): /clone-style — extracção de design tokens (web + pptx)

Resolve dor real: clonar estilos visuais de sites e slides para propostas. Tentativas anteriores (Penpot, scrapers HTML, Figma import) falharam porque tentavam reproduzir layouts. Esta skill extrai tokens (cores, fontes, espaçamento, raios, sombras) e alimenta gerador (Stitch / design-engine). Modos: - /clone-style web <url>: extract-web-tokens.js via chrome real (CSS computado) - /clone-style slides <pptx>: extract-pptx-theme.py (theme1.xml + slideMasters) - /clone-style apply <tokens.json>: mapeia para Stitch / design-engine / pptx Validado: PPTX (Calibri/Calibri Light + 6 accent colors do Office default theme). Web: aguarda primeiro teste end-to-end com browser real. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 05:13:16 +01:00
parent 37f62eb733
commit a33c5e1b05
4 changed files with 533 additions and 0 deletions
@@ -0,0 +1,133 @@
+#!/usr/bin/env python3
+"""
+extract-pptx-theme.py — extrai design tokens de um ficheiro PPTX
+
+Uso:
+    python3 extract-pptx-theme.py <caminho.pptx> [--output tokens.json]
+
+Devolve JSON no mesmo formato do extract-web-tokens.js para que /clone-style apply
+seja unificado entre os 2 modos.
+"""
+import sys
+import json
+import zipfile
+import xml.etree.ElementTree as ET
+from pathlib import Path
+from datetime import datetime, timezone
+
+NS = {'a': 'http://schemas.openxmlformats.org/drawingml/2006/main'}
+
+
+def extract_theme(pptx_path: Path) -> dict:
+    if not pptx_path.exists():
+        raise FileNotFoundError(f"Não encontrado: {pptx_path}")
+
+    with zipfile.ZipFile(pptx_path) as z:
+        # Listar themes (pode haver múltiplos; usar o primeiro)
+        theme_files = sorted([n for n in z.namelist() if n.startswith('ppt/theme/theme') and n.endswith('.xml')])
+        if not theme_files:
+            raise ValueError("PPTX sem theme — formato inválido ou corrompido")
+
+        theme_xml = z.read(theme_files[0])
+        root = ET.fromstring(theme_xml)
+
+    # Extrair cores do clrScheme
+    colors = {}
+    for clr_scheme in root.iter('{http://schemas.openxmlformats.org/drawingml/2006/main}clrScheme'):
+        for color_node in clr_scheme:
+            name = color_node.tag.split('}')[1]  # ex: 'accent1', 'dk1', 'lt1'
+            srgb = color_node.find('a:srgbClr', NS)
+            sysclr = color_node.find('a:sysClr', NS)
+            if srgb is not None:
+                colors[name] = '#' + srgb.get('val')
+            elif sysclr is not None:
+                # sysClr usa o lastClr como fallback (cor resolvida)
+                colors[name] = '#' + sysclr.get('lastClr', '000000')
+
+    # Extrair fontes do fontScheme
+    fonts = {'headline': None, 'body': None}
+    for fs in root.iter('{http://schemas.openxmlformats.org/drawingml/2006/main}fontScheme'):
+        major = fs.find('a:majorFont/a:latin', NS)
+        minor = fs.find('a:minorFont/a:latin', NS)
+        if major is not None:
+            fonts['headline'] = major.get('typeface')
+        if minor is not None:
+            fonts['body'] = minor.get('typeface')
+
+    # Mapear cores PPTX → estrutura unificada
+    accent_keys = ['accent1', 'accent2', 'accent3', 'accent4', 'accent5', 'accent6']
+    accents = [colors[k] for k in accent_keys if k in colors]
+
+    primary = colors.get('accent1') or accents[0] if accents else '#000000'
+    secondary = colors.get('accent2')
+    tertiary = colors.get('accent3')
+    neutral = colors.get('lt1') or colors.get('dk1') or '#ffffff'
+    background = colors.get('lt1') or colors.get('bg1') or '#ffffff'
+
+    is_dark = colors.get('lt1', '#ffffff').lstrip('#').upper() != 'FFFFFF'
+
+    return {
+        'url': str(pptx_path),
+        'title': pptx_path.stem,
+        'source': 'pptx',
+        'timestamp': datetime.now(timezone.utc).isoformat(),
+        'colors': {
+            'top': [{'value': v, 'count': 1} for v in accents],
+            'backgrounds': [{'value': background, 'count': 1}],
+            'dominant': primary,
+            'raw_scheme': colors,
+        },
+        'fonts': {
+            'families': [
+                {'value': fonts['headline'], 'count': 1, 'role': 'headline'},
+                {'value': fonts['body'], 'count': 1, 'role': 'body'},
+            ],
+            'sizes': [],
+            'weights': [],
+            'lineHeights': [],
+        },
+        'borderRadius': [],
+        'shadows': [],
+        'spacing': {'gridBaseGuess': 8, 'top': []},
+        'components': {},
+        'meta': {
+            'colorMode': 'DARK' if is_dark else 'LIGHT',
+            'theme_file': theme_files[0],
+            'accent_count': len(accents),
+        },
+        'mapping_hint': {
+            'stitch_customColor': primary,
+            'stitch_overrideSecondary': secondary,
+            'stitch_overrideTertiary': tertiary,
+            'stitch_overrideNeutral': neutral,
+            'note': 'PPTX só fornece cores e fontes — borderRadius/shadows/spacing têm de ser definidos manualmente em designMd',
+        },
+    }
+
+
+def main():
+    if len(sys.argv) < 2:
+        print(__doc__, file=sys.stderr)
+        sys.exit(1)
+
+    pptx = Path(sys.argv[1]).expanduser().resolve()
+
+    output_path = None
+    if '--output' in sys.argv:
+        idx = sys.argv.index('--output')
+        if idx + 1 < len(sys.argv):
+            output_path = Path(sys.argv[idx + 1]).expanduser().resolve()
+
+    tokens = extract_theme(pptx)
+    js = json.dumps(tokens, indent=2, ensure_ascii=False)
+
+    if output_path:
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+        output_path.write_text(js, encoding='utf-8')
+        print(f"✅ Tokens guardados em {output_path}", file=sys.stderr)
+    else:
+        print(js)
+
+
+if __name__ == '__main__':
+    main()