Document Gen Resilient Workflow

run_shell
command: pandoc --version 2>&1 || echo "PANDOC NOT AVAILABLE"

## Pre-Flight Checks

### Check 1: Verify working directory
run_shell
command: pwd && ls -la

### Check 2: Verify pandoc availability
run_shell
command: pandoc --version 2>&1 | head -3 || echo "PANDOC MISSING"

### Check 3: Check LaTeX engines
run_shell
command: which pdflatex xelatex wkhtmltopdf 2>&1 || echo "Some engines missing"

### Check 4: Check Python libraries (fallback option)
run_shell
command: python3 -c "import fpdf; print('fpdf OK')" 2>&1 || echo "fpdf missing"
run_shell
command: python3 -c "import docx; print('python-docx OK')" 2>&1 || echo "python-docx missing"

run_shell
command: pwd && echo "Test write" > /tmp/workspace_test_$$.txt && ls -la /tmp/workspace_test_$$.txt && rm /tmp/workspace_test_$$.txt

write_file
path: /tmp/document_source.md
content: |
  # Document Title
  
  ## Section 1
  Content here...

write_file
path: /tmp/document_source_sanitized.md
content: |
  # Document Title
  
  [Same content with: em-dash → --, curly quotes → straight, → arrows → text, etc.]

run_shell
command: pandoc /tmp/document_source.md -o output.docx 2>&1 && echo "SUCCESS" || echo "FAILED: $?"

run_shell
command: pandoc /tmp/document_source.md -f markdown+utf8 -o output.docx 2>&1

run_shell
command: pandoc /tmp/document_source_sanitized.md -o output.pdf 2>&1 | tee /tmp/pdf_error.log && echo "PDF SUCCESS"

run_shell
command: pandoc /tmp/document_source_sanitized.md --pdf-engine=xelatex -o output.pdf 2>&1 | tee /tmp/pdf_error.log && echo "PDF SUCCESS"

run_shell
command: pandoc /tmp/document_source_sanitized.md --pdf-engine=wkhtmltopdf -o output.pdf 2>&1 | tee /tmp/pdf_error.log && echo "PDF SUCCESS"

execute_code_sandbox
language: python
code: |
  from fpdf import FPDF
  
  pdf = FPDF()
  pdf.add_page()
  pdf.set_font('Arial', 'B', 16)
  pdf.cell(40, 10, 'Document Title')
  pdf.ln(20)
  pdf.set_font('Arial', '', 12)
  pdf.multi_cell(0, 10, 'Your content here...')
  pdf.output('output.pdf')
  print('PDF created successfully')

execute_code_sandbox
language: python
code: |
  from docx import Document
  
  doc = Document()
  doc.add_heading('Document Title', 0)
  doc.add_paragraph('Your content here...')
  doc.save('output.docx')
  print('DOCX created successfully')

run_shell
command: ls -lh output.* 2>&1

run_shell
command: file output.docx output.pdf 2>&1

run_shell
command: unzip -p output.docx word/document.xml 2>&1 | head -50 || echo "Cannot read DOCX"

run_shell
command: pdfinfo output.pdf 2>&1 | grep Pages || echo "pdfinfo not available"

execute_code_sandbox
code: |
  import os
  for f in ['output.docx', 'output.pdf', 'output.html']:
    if os.path.exists(f):
      size = os.path.getsize(f)
      print(f'{f}: {size} bytes')
    else:
      print(f'{f}: NOT FOUND')

# Generate Quarterly Report (DOCX + PDF)

## Step 1: Pre-flight checks
run_shell
command: pandoc --version 2>&1 | head -1

## Step 2: Write Markdown source
write_file
path: /tmp/quarterly_report.md
content: |
  # Quarterly Business Report
  
  ## Executive Summary
  Q4 performance exceeded expectations...
  
  ## Key Metrics
  - Revenue: $1.2M
  - Growth: 15%
  
  ## Recommendations
  Continue current strategy...

## Step 3: Create sanitized version for PDF
write_file
path: /tmp/quarterly_report_sanitized.md
content: |
  # Quarterly Business Report
  
  ## Executive Summary
  Q4 performance exceeded expectations...
  
  [Rest of content with special chars replaced]

## Step 4: Generate DOCX
run_shell
command: pandoc /tmp/quarterly_report.md -o quarterly_report.docx 2>&1 && echo "DOCX OK"

## Step 5: Generate PDF (try xelatex for Unicode safety)
run_shell
command: pandoc /tmp/quarterly_report_sanitized.md --pdf-engine=xelatex -o quarterly_report.pdf 2>&1 && echo "PDF OK"

## Step 6: Verify outputs
run_shell
command: ls -lh quarterly_report.* && file quarterly_report.*