ericgandrade/claude-superskills/pptx-translator

python3 -c "import pptx" 2>/dev/null || pip install --user python-pptx -q && echo "Installed python-pptx"

╔══════════════════════════════════════════════════════════════╗
║  PPTX TRANSLATOR — Configuration                            ║
╠══════════════════════════════════════════════════════════════╣
║  File:            ~/docs/proposta.pptx                      ║
║  Direction:       Portuguese → English                      ║
║  Speaker notes:   Yes (included)                            ║
║  Original:        preserved (output saved as new file)      ║
║  Output file:     ~/docs/proposta_en.pptx                   ║
║  ⚠️  YOLO: original will be overwritten + backup created    ║
╚══════════════════════════════════════════════════════════════╝
Proceed? [Y/n]

How should the output file be named?
 
  [1] {stem}_{lang_code}.pptx              ← original name + target language suffix (default)
  [2] {translated_stem}_{lang_code}.pptx   ← filename translated to {target_language} (AI suggestion)
  [3] Custom name                           ← I'll type it myself
 
Choice [1]:

[████░░░░░░░░░░░░░░░░] 20% — Step 2/5: Extracting slide content

from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE
import json, sys
def iter_shapes(shapes, parent_id=None):
    """Recursively yield all leaf shapes, descending into GROUP shapes."""
    for shape in shapes:
        if shape.shape_type == MSO_SHAPE_TYPE.GROUP:
            yield from iter_shapes(shape.shapes, parent_id=shape.shape_id)
        else:
            yield shape, parent_id
def extract_text(pptx_path):
    prs = Presentation(pptx_path)
    manifest = []
    for slide_num, slide in enumerate(prs.slides, start=1):
        text_blocks = []
        for shape, parent_id in iter_shapes(slide.shapes):
            # Text frames in regular shapes (including children of groups)
            if shape.has_text_frame:
                for para_idx, para in enumerate(shape.text_frame.paragraphs):
                    for run_idx, run in enumerate(para.runs):
                        if run.text.strip():
                            text_blocks.append({
                                "shape_id": shape.shape_id,
                                "parent_id": parent_id,   # None if top-level
                                "shape_name": shape.name,
                                "para_idx": para_idx,
                                "run_idx": run_idx,
                                "original_text": run.text
                            })
            # Tables
            if shape.has_table:
                for row_idx, row in enumerate(shape.table.rows):
                    for col_idx, cell in enumerate(row.cells):
                        if cell.text.strip():
                            text_blocks.append({
                                "shape_id": shape.shape_id,
                                "parent_id": parent_id,
                                "shape_name": f"table_{shape.name}",
                                "row_idx": row_idx,
                                "col_idx": col_idx,
                                "original_text": cell.text
                            })
        # Speaker notes
        notes_text = ""
        if slide.has_notes_slide:
            notes_tf = slide.notes_slide.notes_text_frame
            notes_text = notes_tf.text.strip() if notes_tf else ""
        # SmartArt detection — flag slides with embedded diagrams
        smartart_found = []
        for shape in slide.shapes:
            if shape.shape_type is None:  # graphicFrame (SmartArt/Chart)
                smartart_found.append(shape.name)
        manifest.append({
            "slide_num": slide_num,
            "text_blocks": text_blocks,
            "notes": notes_text,
            "smartart_shapes": smartart_found  # non-empty = has SmartArt
        })
    return manifest
manifest = extract_text(sys.argv[1])
print(json.dumps(manifest, ensure_ascii=False, indent=2))

import zipfile, os, json
from lxml import etree
smartart_slides = [s for s in manifest if s.get("smartart_shapes")]
if smartart_slides:
    print(f"\n⚠️  {len(smartart_slides)} slide(s) contain SmartArt — text stored in separate XML files:")
    for s in smartart_slides:
        print(f"   Slide {s['slide_num']}: {s['smartart_shapes']}")
    print("   SmartArt text will be translated via direct XML editing after write-back.")
    DRAWING_NS = 'http://schemas.openxmlformats.org/drawingml/2006/main'
    with zipfile.ZipFile(output_path, 'r') as zin:
        diagram_files = [f for f in zin.namelist()
                         if f.startswith('ppt/diagrams/data') and f.endswith('.xml')]
        file_roots = {}
        smartart_items = []
        for df in diagram_files:
            root = etree.fromstring(zin.read(df))
            file_roots[df] = root
            for i, t in enumerate(root.findall(f'.//{{{DRAWING_NS}}}t')):
                if t.text and t.text.strip():
                    smartart_items.append({"file": df, "node_idx": i, "text": t.text})
    if smartart_items:
        smartart_input = json.dumps(
            [{"i": idx, "t": item["text"]} for idx, item in enumerate(smartart_items)],
            ensure_ascii=False
        )
        with open("/tmp/smartart_input.json", "w") as f:
            f.write(smartart_input)
        print(f"   {len(smartart_items)} SmartArt text nodes — launching SmartArtTranslator agent…")
        # Launch SmartArtTranslator sub-agent (same prompt pattern as SlideTranslator):
        # Input: /tmp/smartart_input.json — list of {"i": idx, "t": "source text"}
        # Output: /tmp/smartart_output.json — list of {"i": idx, "t": "translated text"}
        # Apply same STRICT RULES (preserve proper nouns, whitespace, completeness)
        with open("/tmp/smartart_output.json") as f:
            smartart_translations = {item["i"]: item["t"] for item in json.load(f)}
        for df, root in file_roots.items():
            nodes = root.findall(f'.//{{{DRAWING_NS}}}t')
            for idx, item in enumerate(smartart_items):
                if item["file"] == df and idx in smartart_translations:
                    nodes[item["node_idx"]].text = smartart_translations[idx]
        tmp_smartart = output_path + ".sa.tmp"
        with zipfile.ZipFile(output_path, 'r') as zin:
            with zipfile.ZipFile(tmp_smartart, 'w', zipfile.ZIP_DEFLATED) as zout:
                for zi in zin.infolist():
                    if zi.filename in file_roots:
                        data = etree.tostring(file_roots[zi.filename],
                                              xml_declaration=True, encoding='UTF-8', standalone=True)
                    else:
                        data = zin.read(zi.filename)
                    zout.writestr(zi, data)
        os.replace(tmp_smartart, output_path)
        print(f"   ✅ SmartArt translations applied to {len(diagram_files)} diagram file(s)")