Read this and let me know if there is any mistake
python -m markitdown /home/daytona/workspace/attachments/61a361dd-3ff4-41c0-ad2a-db3c1b85dea8/Persetation.pptx
python3 -c " from pptx import Presentation prs = Presentation('/home/daytona/workspace/attachments/61a361dd-3ff4-41c0-ad2a-db3c1b85dea8/Persetation.pptx') for i, slide in enumerate(prs.slides): print(f'--- Slide {i+1} ---') for shape in slide.shapes: if shape.has_text_frame: for para in shape.text_frame.paragraphs: text = para.text.strip() if text: print(text) print() "
ls /home/daytona/skills/pptx/scripts/ 2>/dev/null; which node; node --version; ls /home/daytona/skills/pptx/
ls /home/daytona/skills/pptx/scripts/office/; ls /home/daytona/skills/shared/scripts/ 2>/dev/null
python3 /home/daytona/skills/pptx/scripts/office/unpack.py /home/daytona/workspace/attachments/61a361dd-3ff4-41c0-ad2a-db3c1b85dea8/Persetation.pptx /home/daytona/workspace/pptx_unpacked/
mkdir -p /home/daytona/workspace/pptx_unpacked && unzip -o /home/daytona/workspace/attachments/61a361dd-3ff4-41c0-ad2a-db3c1b85dea8/Persetation.pptx -d /home/daytona/workspace/pptx_unpacked/ 2>&1 | head -30
ls /home/daytona/workspace/pptx_unpacked/ppt/slides/ | head -20
python3 -c " import xml.etree.ElementTree as ET import os, re ns = { 'a': 'http://schemas.openxmlformats.org/drawingml/2006/main', 'p': 'http://schemas.openxmlformats.org/presentationml/2006/main', 'r': 'http://schemas.openxmlformats.org/officeDocument/2006/relationships', } slides_dir = '/home/daytona/workspace/pptx_unpacked/ppt/slides' slide_files = sorted([f for f in os.listdir(slides_dir) if f.startswith('slide') and f.endswith('.xml')], key=lambda x: int(re.search(r'\d+', x).group())) for slide_file in slide_files: path = os.path.join(slides_dir, slide_file) tree = ET.parse(path) root = tree.getroot() texts = [] for t in root.iter('{http://schemas.openxmlformats.org/drawingml/2006/main}t'): if t.text and t.text.strip(): texts.append(t.text.strip()) slide_num = re.search(r'\d+', slide_file).group() if texts: print(f'=== Slide {slide_num} ===') print('\n'.join(texts)) print() "
| Slide | Issue | Type |
|---|---|---|
| 12 | "#36" split as "#3 6"; TTP for #36 unclear | Formatting + Content |
| 15 | Diagnosis only covers #46, not #35/#36 | Content gap |
| 16 | "periapical" vs. "apical" periodontitis (items 2 & 4) | Terminology |
| 16 | Item 4 starts with lowercase "i" | Formatting |
| 17 | "#36" split as "#3 6"; "#46" split as "#4 6" | Formatting |
| 7 | "Not specific" should be "Not significant" | Minor wording |
| Filename | "Persetation" misspelled | Typo |
Be quick