Document Gen Resilient Workflow

write_file
path: /tmp/document_source.md
content: |
  # Document Title
  
  ## Section 1
  Content here...
  
  ## Section 2
  More content...

write_file
path: /tmp/sanitize_unicode.py
content: |
  #!/usr/bin/env python3
  import sys
  import re
  
  if len(sys.argv) < 2:
      print("Usage: sanitize_unicode.py <input.md> [output.md]")
      sys.exit(1)
  
  input_file = sys.argv[1]
  output_file = sys.argv[2] if len(sys.argv) > 2 else input_file.replace('.md', '_sanitized.md')
  
  replacements = {
      '—': '--',    # em dash
      '–': '-',     # en dash
      '"': '"',     # left curly quote
      '"': '"',     # right curly quote
      "'": "'",     # left curly apostrophe
      "'": "'",     # right curly apostrophe
      '…': '...',   # ellipsis
      '→': '->',    # right arrow
      '←': '<-',    # left arrow
      '↑': '^',     # up arrow
      '↓': 'v',     # down arrow
      '✓': '[x]',   # checkmark
      '✗': '[ ]',   # cross
      '★': '*',     # star
      '●': '-',     # bullet
      '©': '(c)',   # copyright
      '®': '(r)',   # registered
      '™': '(tm)',  # trademark
  }
  
  with open(input_file, 'r', encoding='utf-8') as f:
      content = f.read()
  
  for old, new in replacements.items():
      content = content.replace(old, new)
  
  with open(output_file, 'w', encoding='utf-8') as f:
      f.write(content)
  
  print(f"Sanitized: {input_file} -> {output_file}")

run_shell
command: python3 /tmp/sanitize_unicode.py /tmp/document_source.md /tmp/document_source_sanitized.md

run_shell
command: pandoc /tmp/document_source.md -o output.docx

run_shell
command: pandoc /tmp/document_source_sanitized.md -o output.pdf --pdf-engine=pdflatex

run_shell
command: pandoc /tmp/document_source.md -o output.pdf --pdf-engine=xelatex

run_shell
command: pandoc /tmp/document_source.md -o output.pdf --pdf-engine=wkhtmltopdf

write_file
path: /tmp/generate_pdf_reportlab.py
content: |
  #!/usr/bin/env python3
  from reportlab.lib.pagesizes import letter
  from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
  from reportlab.lib.styles import getSampleStyleSheet
  import markdown
  
  input_md = '/tmp/document_source.md'
  output_pdf = 'output.pdf'
  
  with open(input_md, 'r', encoding='utf-8') as f:
      md_content = f.read()
  
  html_content = markdown.markdown(md_content)
  
  doc = SimpleDocTemplate(output_pdf, pagesize=letter)
  styles = getSampleStyleSheet()
  story = []
  
  # Simple HTML to flowables (basic implementation)
  for line in html_content.split('\n'):
      if line.strip():
          story.append(Paragraph(line, styles['Normal']))
          story.append(Spacer(1, 6))
  
  doc.build(story)
  print(f"PDF created: {output_pdf}")

run_shell
command: python3 /tmp/generate_pdf_reportlab.py

write_file
path: /tmp/generate_pdf_fpdf.py
content: |
  #!/usr/bin/env python3
  from fpdf import FPDF
  
  input_md = '/tmp/document_source.md'
  output_pdf = 'output.pdf'
  
  pdf = FPDF()
  pdf.add_page()
  pdf.set_font('Helvetica', '', 12)
  
  with open(input_md, 'r', encoding='utf-8') as f:
      for line in f:
          # Simple line-by-line, escape special chars
          safe_line = line.encode('latin-1', 'replace').decode('latin-1')
          pdf.cell(0, 10, safe_line[:180], ln=True)
  
  pdf.output(output_pdf)
  print(f"PDF created: {output_pdf}")

run_shell
command: python3 /tmp/generate_pdf_fpdf.py

run_shell
command: pandoc /tmp/document_source.md -o output.html

run_shell
command: ls -lh output.docx output.pdf output.html 2>/dev/null && echo "FILES_OK" || echo "FILES_MISSING"

run_shell
command: python3 -c "import fitz; doc=fitz.open('output.pdf'); print(f'PDF_VALID: {doc.page_count} pages')" 2>/dev/null || echo "PDF_CHECK_SKIPPED"

run_shell
command: python3 -c "from docx import Document; d=Document('output.docx'); print(f'DOCX_VALID: {len(d.paragraphs)} paragraphs')" 2>/dev/null || echo "DOCX_CHECK_SKIPPED"

read_file
filetype: md
file_path: output.html

# Generate Negotiation Strategy Document (Resilient Workflow)

## Step 1: Write Markdown source
write_file
path: /tmp/negotiation_strategy.md
content: |
  # Negotiation Strategy
  
  ## Executive Summary
  Content with original unicode characters...
  
  ## Resolution Path
  More content...

## Step 2: Sanitize for PDF
write_file
path: /tmp/sanitize_unicode.py
content: |
  [Python sanitizer script from Step 2 above]

run_shell
command: python3 /tmp/sanitize_unicode.py /tmp/negotiation_strategy.md /tmp/negotiation_strategy_sanitized.md

## Step 3: Convert to DOCX (original, Unicode-safe format)
run_shell
command: pandoc /tmp/negotiation_strategy.md -o negotiation_strategy.docx

## Step 4: Convert to PDF (try pdflatex first)
run_shell
command: pandoc /tmp/negotiation_strategy_sanitized.md -o negotiation_strategy.pdf --pdf-engine=pdflatex

## Step 4b: If pdflatex failed, try xelatex
run_shell
command: pandoc /tmp/negotiation_strategy.md -o negotiation_strategy.pdf --pdf-engine=xelatex

## Step 4c: If xelatex failed, try wkhtmltopdf
run_shell
command: pandoc /tmp/negotiation_strategy.md -o negotiation_strategy.pdf --pdf-engine=wkhtmltopdf

## Step 5: Convert to HTML (original)
run_shell
command: pandoc /tmp/negotiation_strategy.md -o negotiation_strategy.html

## Step 6: Verify all outputs
run_shell
command: ls -lh negotiation_strategy.* && echo "ALL_FILES_CREATED"

run_shell
command: python3 -c "import fitz; d=fitz.open('negotiation_strategy.pdf'); print(f'PDF: {d.page_count} pages')"