~/

medical exam question classification MK DK NK LAQ SAQ meaning

~/attachments/17fe309c-8645-423e-a664-c786c1b3e9d0

mkdir -p "/tmp/workspace/git-question-extraction/output" && python -c "import pdfplumber; p='/tmp/workspace/attachments/17fe309c-8645-423e-a664-c786c1b3e9d0/Practice of Medicine (2).pdf'; out='/tmp/workspace/git-question-extraction/output/extracted.txt'; pdf=pdfplumber.open(p); f=open(out,'w',encoding='utf-8'); [f.write('\\n\\n===== PAGE %d =====\\n%s' % (i+1, page.extract_text() or '')) for i,page in enumerate(pdf.pages)]; f.close(); print('pages',len(pdf.pages),'out',out)"

"GIT" in ~/git-question-extraction/output

"LAQ" in ~/git-question-extraction/output

"SAQ" in ~/git-question-extraction/output

"MK" in ~/git-question-extraction/output

"DK" in ~/git-question-extraction/output

"NK" in ~/git-question-extraction/output

"5.5." in ~/git-question-extraction/output

python -c "import re; t=open('/tmp/workspace/git-question-extraction/output/extracted.txt',encoding='utf8').read(); s=t.index('HomUG-PM II.42.'); e=t.index('5.5. Disorders of Liver'); x=t[s:e]; parts=re.split(r'(?=HomUG-)',x); out='\\n\\n'.join(p.replace('\\n',' ') for p in parts if p.strip()); open('/tmp/workspace/git-question-extraction/output/git_rows_raw.txt','w',encoding='utf8').write(out); print('parts',len(parts)); print('chars',len(x))" && python -c "import re; x=open('/tmp/workspace/git-question-extraction/output/git_rows_raw.txt',encoding='utf8').read(); print('\\n'.join(x.split('\\n')[:35]))"

python - <<'PY' import re p='/tmp/workspace/git-question-extraction/output/git_rows_raw.txt' x=open(p,encoding='utf8').read() # Split on section heading secs=re.split(r'(?=HomUG-PM II\.\d+\.)',x) for sec in secs: h=re.match(r'(HomUG-PM II\.\d+\.\s*[^\n]+)',sec) if not h: continue title=h.group(1).replace('HomUG-PM ','') rows=re.split(r'(?=HomUG-)',sec)[1:] print('\n###',title,'ROWS',len(rows)) for r in rows: r=' '.join(r.split()) code=re.search(r'II\.\d+\.\d+',r) pri=re.search(r'\b(?:MK|DK|NK)\b',r) assess=[] # rough: everything after priority tail=r[pri.end():] if pri else '' if 'SAQ' in tail: assess.append('SAQ') if 'LAQ' in tail: assess.append('LAQ') if assess: print(code.group() if code else '?','|',pri.group() if pri else '?','|','/'.join(assess),'|',r[:240]) PY

python - <<'PY' import pdfplumber p='/tmp/workspace/attachments/17fe309c-8645-423e-a664-c786c1b3e9d0/Practice of Medicine (2).pdf' with pdfplumber.open(p) as pdf: for ix in [97,98,99,100]: page=pdf.pages[ix] print('\nPAGE',ix+1) tabs=page.extract_tables() print('tables',len(tabs)) for t in tabs: for r in t[:3]: print(r) PY

python - <<'PY' import re x=open('/tmp/workspace/git-question-extraction/output/git_rows_raw.txt',encoding='utf8').read() for sec in re.split(r'(?=HomUG-PM II\.\d+\.)',x): h=re.match(r'HomUG-PM (II\.\d+(?:\.[AB])?\.\s*[^\n]+)',sec) if not h: continue title=h.group(1) rows=re.split(r'(?=HomUG-)',sec)[1:] print('\n##',title) for r in rows: r=' '.join(r.split()) # identify code permits 52.A code=re.search(r'II\.\d+(?:\.[AB])?\.\d+',r) pri=re.search(r'\b(MK|DK|NK)\b',r) # take from priority to integration, summative appears after T-L method words # identify all sequence occurrences SAQ LAQ. Print compact if pri and ('SAQ' in r[pri.end():] or 'LAQ' in r[pri.end():]): # content around before SLO at priority: crude capture after competency code but order corrupted print(code.group() if code else '?', pri.group(), 'SAQ' if 'SAQ' in r[pri.end():] else '', 'LAQ' if 'LAQ' in r[pri.end():] else '', ' :: ', r[:150]) PY > "/tmp/workspace/git-question-extraction/output/summary.txt"

python - <<'PY' import re, os from openpyxl import Workbook from openpyxl.styles import Font, PatternFill, Alignment src='/tmp/workspace/git-question-extraction/output/git_rows_raw.txt' x=open(src,encoding='utf8').read() sections=re.split(r'(?=HomUG-PM II\.\d+)',x) rows=[] for sec in sections: hm=re.match(r'HomUG-PM (II\.\d+(?:\.[AB])?\.\s*[^\n]+)',sec) if not hm: continue topic=re.sub(r'\s+\d+\s*=+.*','',hm.group(1)).strip() # derive clean title after code title=re.sub(r'^II\.\d+(?:\.[AB])?\.\s*','',topic).strip() for r in re.split(r'(?=HomUG-)',sec)[1:]: clean=' '.join(r.split()) cm=re.search(r'II\.\d+(?:\.[AB])?\.\d+',clean) pm=re.search(r'\b(MK|DK|NK)\b',clean) if not (cm and pm): continue tail=clean[pm.end():] # Include only if published assessment fields include SAQ/LAQ anywhere after priority if not ('SAQ' in tail or 'LAQ' in tail): continue # SLO begins around a) and ends before Bloom level before priority pre=clean[:pm.start()] slo='' m=re.search(r'(\([abc]\)\s*.*)$',pre) if m: slo=m.group(1) else: # use competency title before likely code, ignore attributes slo=pre slo=re.sub(r'\s+\d+\s+=+ PAGE \d+ =+\s*',' ',slo) # infer assessment appearance exactly as recorded. This document does not assign marks. fmt=[] if 'SAQ' in tail: fmt.append('SAQ') if 'LAQ' in tail: fmt.append('LAQ') rows.append([cm.group(), title, slo[:1200], pm.group(), ' / '.join(fmt), 'Not specified in PDF']) # duplicates eliminate by code (rows unique) seen=set(); data=[] for r in rows: if r[0] not in seen: data.append(r);seen.add(r[0]) out='/tmp/workspace/git-question-extraction/output/GIT_question_classification.xlsx' wb=Workbook(); ws=wb.active; ws.title='GIT questions' ws.append(['Competency code','Topic','Question / learning outcome','Priority','Written assessment shown','Marks / value']) for r in data: ws.append(r) for c in ws[1]: c.font=Font(bold=True,color='FFFFFF');c.fill=PatternFill('solid',fgColor='1F4E78');c.alignment=Alignment(wrap_text=True) for row in ws.iter_rows(min_row=2): for c in row: c.alignment=Alignment(wrap_text=True,vertical='top') ws.freeze_panes='A2'; ws.auto_filter.ref=ws.dimensions for col,width in {'A':18,'B':38,'C':80,'D':11,'E':25,'F':22}.items(): ws.column_dimensions[col].width=width for i in range(2,ws.max_row+1): ws.row_dimensions[i].height=55 # summary s=wb.create_sheet('Summary') s.append(['Item','Count']) s.append(['Competencies with SAQ and/or LAQ listed',len(data)]) s.append(['SAQ listed',sum('SAQ' in r[4] for r in data)]) s.append(['LAQ listed',sum('LAQ' in r[4] for r in data)]) for tag in ['MK','DK','NK']: s.append([tag,sum(r[3]==tag for r in data)]) s.append(['Note','The PDF provides priority labels and assessment formats, but no numeric marks or values.']) for c in s[1]:c.font=Font(bold=True,color='FFFFFF');c.fill=PatternFill('solid',fgColor='1F4E78') s.column_dimensions['A'].width=48;s.column_dimensions['B'].width=85 for row in s.iter_rows(): for c in row:c.alignment=Alignment(wrap_text=True,vertical='top') wb.save(out) print(len(data),out) PY