~/

wound healing phases medical education overview

wound healing

~/attachments/937959e3-1cb3-4f47-9429-c43f71eb1499

mkdir -p "/tmp/workspace/wound-healing-word/assets" "/tmp/workspace/wound-healing-word/output" "/tmp/workspace/wound-healing-word/src" && python3 - <<'PY' import fitz, os, json pdf='/tmp/workspace/attachments/937959e3-1cb3-4f47-9429-c43f71eb1499/Wound Healing Part 1.pdf' out='/tmp/workspace/wound-healing-word/assets' doc=fitz.open(pdf) print('pages',len(doc)) for i,p in enumerate(doc): txt=p.get_text('text') open(f'{out}/page_{i+1:02d}.txt','w',encoding='utf-8').write(txt) imgs=p.get_images(full=True) print('page',i+1,'textchars',len(txt),'images',len(imgs)) for j,img in enumerate(imgs): xref=img[0] data=doc.extract_image(xref) ext=data['ext'] path=f'{out}/p{i+1:02d}_img{j+1:02d}_xref{xref}.{ext}' open(path,'wb').write(data['image']) print(' ',path, len(data['image']), data['width'],data['height']) PY

python3 - <<'PY' from pypdf import PdfReader import os pdf='/tmp/workspace/attachments/937959e3-1cb3-4f47-9429-c43f71eb1499/Wound Healing Part 1.pdf' out='/tmp/workspace/wound-healing-word/assets' r=PdfReader(pdf) print('pages',len(r.pages)) for n,page in enumerate(r.pages,1): text=page.extract_text() or '' with open(f'{out}/page_{n:02d}.txt','w',encoding='utf-8') as f:f.write(text) print(n, len(text),repr(text[:160]), 'images',len(list(page.images))) for k,img in enumerate(page.images): fn=f'{out}/p{n:02d}_img{k+1:02d}_{img.name}' with open(fn,'wb') as f:f.write(img.data) print(' ',os.path.basename(fn),len(img.data)) PY

python3 - <<'PY' from pathlib import Path src=Path('/tmp/workspace/wound-healing-word/src/create_wound_healing_doc.py') script=r'''from pathlib import Path import os, re from docx import Document from docx.shared import Pt, Inches, Cm from docx.enum.section import WD_SECTION from docx.enum.text import WD_ALIGN_PARAGRAPH from docx.enum.style import WD_STYLE_TYPE from docx.oxml import OxmlElement from docx.oxml.ns import qn from PIL import Image assets=Path('/tmp/workspace/wound-healing-word/assets') out=Path('/tmp/workspace/wound-healing-word/output/Wound_Healing_Part_1_Editable.docx') def set_run_font(run, size, bold=False, italic=False): run.font.name='Times New Roman' run._element.rPr.rFonts.set(qn('w:eastAsia'), 'Times New Roman') run.font.size=Pt(size); run.font.bold=bold; run.font.italic=italic def shade(paragraph, fill): pPr=paragraph._p.get_or_add_pPr(); shd=OxmlElement('w:shd'); shd.set(qn('w:fill'),fill); pPr.append(shd) def border_bottom(paragraph): pPr=paragraph._p.get_or_add_pPr(); borders=OxmlElement('w:pBdr'); b=OxmlElement('w:bottom') b.set(qn('w:val'),'single');b.set(qn('w:sz'),'6');b.set(qn('w:space'),'4');b.set(qn('w:color'),'1F4E79');borders.append(b);pPr.append(borders) def normalize(raw): # retain original wording while making PDF line extraction readable lines=[] for line in raw.splitlines(): line=re.sub(r'\s+',' ',line).strip() if not line: continue # discard isolated source-page numbers only if re.fullmatch(r'\d+',line): continue lines.append(line) # Join split heading word pairs like HEALIN / G joined=[] for line in lines: if joined and len(joined[-1])<=8 and joined[-1].isupper() and len(line)<=3 and line.isupper(): joined[-1]+=line else: joined.append(line) return joined def is_heading(line, index): letters=re.sub(r'[^A-Za-z]','',line) if not letters: return False upper=letters.isupper() if index==0 and len(line)<=85: return True if upper and 3<=len(line)<=90 and not line.startswith(('•','-','–','1.','2.','3.','4.','5.','6.','7.','8.','9.')): return True # common named section headings even if mixed case headings=('INTRODUCTION','CLASSIFICATION','CROSS- SECTION','CROSS-SECTION','REGENERATION','REPAIR','HEALING BY','STEPS OF','INFLAMMATORY PHASE','PROLIFERATIVE PHASE','MATURATION PHASE','GRANULATION','BONE HEALING','WOUND ASSESSMENT','REFERENCES') return any(line.upper().startswith(h) for h in headings) and len(line)<95 def usable_images(page): # Large images are content photographs/diagrams. Tiny repeated PNGs are template logos/icons. allimgs=sorted(assets.glob(f'p{page:02d}_img*'), key=lambda x:x.name) keep=[] for fp in allimgs: if fp.stat().st_size < 10000: continue try: with Image.open(fp) as im: w,h=im.size if w<100 or h<70: continue except Exception: continue keep.append(fp) return keep def add_page_number(section): footer=section.footer.paragraphs[0] footer.alignment=WD_ALIGN_PARAGRAPH.CENTER r=footer.add_run('Page ');set_run_font(r,8) fld=OxmlElement('w:fldSimple');fld.set(qn('w:instr'),'PAGE'); footer._p.append(fld) doc=Document() sec=doc.sections[0] sec.page_width=Cm(21);sec.page_height=Cm(29.7) sec.top_margin=Cm(1.7);sec.bottom_margin=Cm(1.5);sec.left_margin=Cm(1.8);sec.right_margin=Cm(1.8) add_page_number(sec) styles=doc.styles normal=styles['Normal'];normal.font.name='Times New Roman';normal._element.rPr.rFonts.set(qn('w:eastAsia'),'Times New Roman');normal.font.size=Pt(12) normal.paragraph_format.space_after=Pt(4);normal.paragraph_format.line_spacing=1.08 for name in ('Heading 1','Heading 2','Title'): st=styles[name];st.font.name='Times New Roman';st._element.rPr.rFonts.set(qn('w:eastAsia'),'Times New Roman');st.font.size=Pt(14);st.font.bold=True st.paragraph_format.space_before=Pt(10);st.paragraph_format.space_after=Pt(6) caption=styles['Caption'];caption.font.name='Times New Roman';caption._element.rPr.rFonts.set(qn('w:eastAsia'),'Times New Roman');caption.font.size=Pt(8);caption.font.italic=True caption.paragraph_format.space_after=Pt(8) # Title page p=doc.add_paragraph();p.alignment=WD_ALIGN_PARAGRAPH.CENTER;p.paragraph_format.space_before=Pt(120) r=p.add_run('WOUND HEALING & TISSUE REPAIR');set_run_font(r,14,True);border_bottom(p) p=doc.add_paragraph();p.alignment=WD_ALIGN_PARAGRAPH.CENTER r=p.add_run('Editable conversion of “Wound Healing Part 1”');set_run_font(r,12) p=doc.add_paragraph();p.alignment=WD_ALIGN_PARAGRAPH.CENTER r=p.add_run('All readable source text is editable. Original content photographs and diagrams are included with captions.');set_run_font(r,8,italic=True) txtfiles=sorted(assets.glob('page_*.txt')) for ix, txtfile in enumerate(txtfiles,1): if ix>1: doc.add_page_break() lines=normalize(txtfile.read_text(encoding='utf-8')) source=doc.add_paragraph(); source.alignment=WD_ALIGN_PARAGRAPH.RIGHT rr=source.add_run(f'Source page {ix}');set_run_font(rr,8,italic=True) if lines: for j,line in enumerate(lines): p=doc.add_paragraph() p.paragraph_format.keep_together=True if is_heading(line,j): p.style='Heading 1';p.alignment=WD_ALIGN_PARAGRAPH.LEFT r=p.add_run(line);set_run_font(r,14,True);shade(p,'D9EAF7') else: # formatting visibly retains bullets but permits simple editing bullet=False if line.startswith(('•','–','-')): bullet=True;line=line.lstrip('•–- ').strip() elif re.match(r'^\d+\.',line): bullet=True if bullet: p.style='List Bullet' r=p.add_run(line);set_run_font(r,12) else: p=doc.add_paragraph();r=p.add_run('[This source page contains visual material only.]');set_run_font(r,12,italic=True) for n,img in enumerate(usable_images(ix),1): p=doc.add_paragraph();p.alignment=WD_ALIGN_PARAGRAPH.CENTER;p.paragraph_format.keep_together=True try: with Image.open(img) as im: w,h=im.size # fit within portrait text width / height width=5.9 if w/h>=1 else 4.4 p.add_run().add_picture(str(img), width=Inches(width)) cap=doc.add_paragraph(style='Caption');cap.alignment=WD_ALIGN_PARAGRAPH.CENTER r=cap.add_run(f'Figure {ix}.{n}. Original visual from source page {ix}.');set_run_font(r,8,italic=True) except Exception as e: cap=doc.add_paragraph(style='Caption');r=cap.add_run(f'[Unable to insert image: {img.name}]');set_run_font(r,8,italic=True) # core document metadata doc.core_properties.title='Wound Healing Part 1 - Editable' doc.core_properties.subject='Editable Word conversion with source images' doc.core_properties.author='Converted from supplied presentation PDF' doc.save(out) print(out) print('images added',sum(len(usable_images(i)) for i in range(1,len(txtfiles)+1))) ''' src.write_text(script,encoding='utf-8') PY python3 "/tmp/workspace/wound-healing-word/src/create_wound_healing_doc.py"

python3 - <<'PY' from docx import Document from pathlib import Path p=Path('/tmp/workspace/wound-healing-word/output/Wound_Healing_Part_1_Editable.docx') d=Document(p) print('exists',p.exists(),'bytes',p.stat().st_size) print('sections',len(d.sections),'portrait',d.sections[0].page_height>d.sections[0].page_width) print('paragraphs',len(d.paragraphs),'inline_shapes',len(d.inline_shapes)) from collections import Counter fonts=Counter(); sizes=Counter() for para in d.paragraphs: for run in para.runs: if run.text.strip(): fonts[run.font.name]+=1 sizes[round(run.font.size.pt if run.font.size else 0,1)]+=1 print('fonts',fonts) print('sizes',sizes) print('headings',sum(1 for q in d.paragraphs if q.style.name.startswith('Heading'))) print('captions',sum(1 for q in d.paragraphs if q.style.name=='Caption')) PY