digital-waqif/assemble_pdf.py

#!/usr/bin/env python3
"""Assemble 'The Digital Waqif: Waqf, Faraid, and the Architecture of Legacy' PDF
Will & Testament Playbook — Legal-document aesthetic, 6×9in."""
import os, re, sys
from reportlab.lib.pagesizes import letter
from reportlab.lib.units import inch
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib.enums import TA_CENTER, TA_LEFT, TA_JUSTIFY
from reportlab.lib.colors import HexColor
from reportlab.platypus import (
    Paragraph, Spacer, PageBreak, Frame, PageTemplate, BaseDocTemplate
)

OUTPUT_DIR = os.path.expanduser("~/odysseus_book/digital_waqif")
CHAPTERS_DIR = os.path.join(OUTPUT_DIR, "chapters")
PDF_PATH = os.path.join(OUTPUT_DIR, "pdf", "The_Digital_Waqif.pdf")

MARGIN = 0.85 * inch
FOOTER_H = 0.4 * inch
PAGE_W = 6 * inch
PAGE_H = 9 * inch

NAVY = HexColor('#1B2A4A')
GOLD = HexColor('#C8A951')
DARK = HexColor('#1a1a1a')
GREY = HexColor('#666666')
INK = HexColor('#222222')
ACCENT_RED = HexColor('#8B0000')

style_title = ParagraphStyle('Title', fontName='Helvetica-Bold', fontSize=24,
    leading=30, alignment=TA_CENTER, textColor=NAVY, spaceAfter=8)
style_subtitle = ParagraphStyle('Subtitle', fontName='Helvetica-Oblique', fontSize=13,
    leading=17, alignment=TA_CENTER, textColor=GOLD, spaceAfter=20)
style_author = ParagraphStyle('Author', fontName='Helvetica', fontSize=12,
    leading=16, alignment=TA_CENTER, textColor=GREY, spaceAfter=28)
style_copyright = ParagraphStyle('Copyright', fontName='Helvetica', fontSize=9,
    leading=12, alignment=TA_CENTER, textColor=GREY)
style_ch_num = ParagraphStyle('ChNum', fontName='Helvetica-Bold', fontSize=10,
    leading=13, alignment=TA_CENTER, textColor=GOLD, spaceAfter=4, spaceBefore=18)
style_ch_title = ParagraphStyle('ChTitle', fontName='Helvetica-Bold', fontSize=17,
    leading=23, alignment=TA_LEFT, textColor=NAVY, spaceAfter=8, spaceBefore=4)
style_subtitle_ch = ParagraphStyle('SubtitleCh', fontName='Helvetica-Oblique', fontSize=11,
    leading=15, alignment=TA_LEFT, textColor=ACCENT_RED, spaceAfter=14, spaceBefore=2)
style_framework = ParagraphStyle('Framework', fontName='Helvetica-Bold', fontSize=10.5,
    leading=14, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=14,
    backColor=HexColor('#F4F6FA'), borderColor=GOLD, borderWidth=1, borderPadding=8)
style_body = ParagraphStyle('Body', fontName='Times-Roman', fontSize=10,
    leading=14.5, alignment=TA_JUSTIFY, textColor=INK, spaceAfter=7, firstLineIndent=0)
style_clause = ParagraphStyle('Clause', fontName='Times-Bold', fontSize=11,
    leading=15, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=10,
    backColor=HexColor('#F4F6FA'), borderColor=NAVY, borderWidth=1, borderPadding=10)
style_nass = ParagraphStyle('Nass', fontName='Times-Italic', fontSize=10,
    leading=14.5, alignment=TA_JUSTIFY, textColor=DARK, spaceAfter=6, leftIndent=24,
    backColor=HexColor('#FDFBF3'), borderColor=GOLD, borderWidth=0.5, borderPadding=8)
style_faradi = ParagraphStyle('Faradi', fontName='Times-Bold', fontSize=10,
    leading=14.5, alignment=TA_LEFT, textColor=NAVY, spaceAfter=3, leftIndent=24)
style_waqif = ParagraphStyle('Waqif', fontName='Times-Bold', fontSize=10,
    leading=14.5, alignment=TA_LEFT, textColor=GOLD, spaceAfter=3, leftIndent=24)
style_principle = ParagraphStyle('Principle', fontName='Times-Bold', fontSize=11,
    leading=15, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=10,
    backColor=HexColor('#F4F6FA'), borderColor=NAVY, borderWidth=1, borderPadding=10)
style_protocol = ParagraphStyle('Protocol', fontName='Times-Roman', fontSize=10,
    leading=14.5, alignment=TA_LEFT, textColor=DARK, spaceAfter=6, leftIndent=36)
style_hisbah = ParagraphStyle('Hisbah', fontName='Times-Italic', fontSize=10.5,
    leading=15, alignment=TA_CENTER, textColor=GREY, spaceAfter=16, spaceBefore=16,
    backColor=HexColor('#F8F9FA'), borderColor=GREY, borderWidth=0.5, borderPadding=12)
style_toc_ch = ParagraphStyle('TOCCh', fontName='Helvetica-Bold', fontSize=11,
    leading=17, alignment=TA_LEFT, textColor=NAVY)
style_toc_sub = ParagraphStyle('TOCSub', fontName='Helvetica', fontSize=9.5,
    leading=13, alignment=TA_LEFT, textColor=GREY)

CHAPTERS = [
    ("Clause 1: The Wasiyyah — The Will That God Commanded", "The Will as Sunnah", "Wasiyyah Quadrant: Mandatory / Recommended / Permitted / Nullified — the 1/3 cap"),
    ("Clause 2: The Faraid Matrix — The Fixed Shares Decoded", "God's Distribution Algorithm", "Faraid Matrix: Ashab al-Furud / 1/2, 1/4, 1/8, 2/3, 1/3, 1/6"),
    ("Clause 3: The Waqf — The Three Exits of Wealth", "Wasiyyah vs Waqf vs Gift", "Exit Quadrant: Wasiyyah / Waqf / Hibah / Inheritance"),
    ("Clause 4: The Digital Kingdom — Inventorying the Invisible Estate", "The Estate Nobody Can See", "Digital Inventory: Crypto / Domains / IP / SaaS / DAO / Social"),
    ("Clause 5: The Keys — Custody and the Executor Who Cannot Be Bribed", "Access Is the Whole Game", "Custody Quadrant: Hot / Cold / Multi-sig / Inherited"),
    ("Clause 6: The Amil — Choosing the Executor of the Digital Estate", "The Executor as Deputy of the Waqif", "Executor Quadrant: Family / Professional / Institutional / Hybrid"),
    ("Clause 7: The Purification — Debt, Zakat, and Cleaning the Estate", "The Estate Must Be Clean Before It Is Shared", "Purification Order: Burial → Debts → Wasiyyah (1/3) → Faraid"),
    ("Clause 8: The Token — Smart-Contract Faraid and On-Chain Waqf", "The Code That Distributes What We Cannot", "Tokenization Quadrant: Smart wills / Multi-sig / Time-locked / On-chain"),
    ("Clause 9: The Successor — Business Continuity for the Digital Kingdom", "The Business That Survives Its Founder", "Continuity Quadrant: Sole / Partnership / Company / Waqf-owned"),
    ("Clause 10: The Perpetuity — The Eternal Contract of the Digital Waqif", "From Legacy to Ongoing Charity", "Perpetuity Quadrant: Exit / Inheritance / Waqf / Sadaqah Jariyah"),
]

def clean_text(text):
    # Minimal markdown→HTML conversion for reportlab
    import re
    text = re.sub(r'\*\*(.+?)\*\*', r'<b>\1</b>', text)
    text = re.sub(r'(?<!\*)\*([^*]+)\*(?!\*)', r'<i>\1</i>', text)
    text = re.sub(r'`([^`]+)`', r'<font face="Courier">\1</font>', text)
    text = text.replace('\\n', '\n')
    # Strip remaining markdown headers etc
    text = re.sub(r'^#{1,6}\s*', '', text, flags=re.MULTILINE)
    # Escape any stray angle brackets that would break reportlab
    text = text.replace('&', '&amp;').replace('<b>', '&lt;b&gt;').replace('</b>', '&lt;/b&gt;')
    text = text.replace('<i>', '&lt;i&gt;').replace('</i>', '&lt;/i&gt;')
    text = text.replace('<font face="Courier">', '&lt;font&gt;').replace('</font>', '&lt;/font&gt;')
    # Now re-apply our tags (since we escaped the originals)
    text = re.sub(r'&lt;b&gt;', '<b>', text)
    text = re.sub(r'&lt;/b&gt;', '</b>', text)
    text = re.sub(r'&lt;i&gt;', '<i>', text)
    text = re.sub(r'&lt;/i&gt;', '</i>', text)
    text = re.sub(r'&lt;font&gt;(.+?)&lt;/font&gt;', r'<font face="Courier">\1</font>', text)
    text = re.sub(r'&amp;', '&', text)
    return text

def parse_chapter(md_text):
    sections = {'clause': [], 'nass': [], 'faradi': [], 'waqif': [], 'declaration': [], 'execution': [], 'hisbah': []}
    current = None
    for line in md_text.split('\n'):
        stripped = line.strip()
        if not stripped:
            continue
        low = stripped.lower()
        if low.startswith('# the clause') or low.startswith('## the clause') or low == 'the clause' or low.startswith('clause 1:'):
            current = 'clause'
            continue
        elif low.startswith('# the nass') or low.startswith('## the nass') or low.startswith('the nass') or low == 'nass':
            current = 'nass'
            continue
        elif low.startswith('# faradi') or low.startswith('## faradi') or low.startswith('faradi') or low.startswith('**faradi'):
            current = 'faradi'
            continue
        elif low.startswith('# waqif') or low.startswith('## waqif') or low.startswith('waqif') or low.startswith('**waqif'):
            current = 'waqif'
            continue
        elif low.startswith('# the declaration') or low.startswith('## the declaration') or low.startswith('the declaration') or low.startswith('declaration'):
            current = 'declaration'
            continue
        elif low.startswith('# the execution') or low.startswith('## the execution') or low.startswith('the execution') or low.startswith('execution'):
            current = 'execution'
            continue
        elif low.startswith('# the hisbah') or low.startswith('## the hisbah') or low.startswith('the hisbah') or low.startswith('hisbah') or low.startswith('muhasaba'):
            current = 'hisbah'
            continue
        if stripped.startswith('#'):
            continue
        if stripped == '---' or stripped == '***':
            continue
        if current:
            sections[current].append(stripped)
    for k in sections:
        sections[k] = '\n\n'.join(sections[k])
    return sections

class BookDoc(BaseDocTemplate):
    def __init__(self, *args, **kw):
        BaseDocTemplate.__init__(self, *args, **kw)

def footer_fn(canvas, doc):
    canvas.saveState()
    canvas.setFont('Helvetica', 8)
    canvas.setFillColor(HexColor('#999999'))
    canvas.drawCentredString(PAGE_W / 2, 0.35 * inch, f'— {doc.page} —')
    canvas.restoreState()

def build_pdf():
    os.makedirs(os.path.join(OUTPUT_DIR, 'pdf'), exist_ok=True)

    frame = Frame(MARGIN, MARGIN + FOOTER_H,
                  PAGE_W - 2 * MARGIN,
                  PAGE_H - 2 * MARGIN - FOOTER_H, id='normal')
    doc = BookDoc(PDF_PATH, pagesize=(PAGE_W, PAGE_H),
        leftMargin=MARGIN, rightMargin=MARGIN,
        topMargin=MARGIN, bottomMargin=MARGIN,
        title="The Digital Waqif: Waqf, Faraid, and the Architecture of Legacy",
        author='Jauhari Che Wan')
    doc.addPageTemplates([PageTemplate(id='main', frames=frame, onPage=footer_fn)])

    story = []

    # Title page
    story.append(Spacer(1, PAGE_H * 0.16))
    story.append(Paragraph("The Digital Waqif", style_title))
    story.append(Paragraph("Waqf, Faraid, and the Architecture of Legacy", style_subtitle))
    story.append(Paragraph("10 Clauses of the Digital Will &amp; Endowment", ParagraphStyle('Tagline',
        fontName='Helvetica-Oblique', fontSize=12, leading=15, alignment=TA_CENTER, textColor=HexColor('#666666'), spaceAfter=24)))
    story.append(Spacer(1, 14))
    story.append(Paragraph('A FARADI &amp; WAQIF Playbook', ParagraphStyle('StyleLine',
        fontName='Helvetica', fontSize=10, leading=13, alignment=TA_CENTER, textColor=HexColor('#888888'), spaceAfter=20)))
    story.append(Spacer(1, 14))
    story.append(Paragraph('Jauhari Che Wan', style_author))
    story.append(Spacer(1, PAGE_H * 0.1))
    story.append(Paragraph('FARADI × WAQIF × MAQASID',
        ParagraphStyle('Tag', parent=style_copyright, fontName='Helvetica-Bold', fontSize=9, textColor=GOLD)))
    story.append(PageBreak())

    # Copyright
    story.append(Spacer(1, PAGE_H * 0.28))
    for line in ['FARADI × WAQIF PLAYBOOK', '', 'The Digital Waqif', 'Jauhari Che Wan',
                 '', 'Based on Ilm al-Faraid and Waqf Jurisprudence', 'Surah An-Nisa 4:11-12, 4:176', 'Maqasid al-Shariah',
                 '', 'Copyright \u00a9 2025', 'All rights reserved',
                 '', 'Typeset in Times / Helvetica', 'Printed in Malaysia']:
        if line == '':
            story.append(Spacer(1, 4))
        else:
            story.append(Paragraph(line, style_copyright))
    story.append(PageBreak())

    # Dedication
    story.append(Spacer(1, PAGE_H * 0.28))
    story.append(Paragraph('For every founder with a seed phrase, a domain, and no will.', ParagraphStyle('Ded',
        fontName='Times-Italic', fontSize=11, leading=16, alignment=TA_CENTER, textColor=DARK, spaceAfter=24)))
    story.append(PageBreak())

    # TOC
    story.append(Paragraph('Contents', ParagraphStyle('TOCHeader',
        fontName='Helvetica-Bold', fontSize=18, leading=24, alignment=TA_LEFT, textColor=NAVY, spaceAfter=20)))
    for i, (title, subtitle, _) in enumerate(CHAPTERS, 1):
        story.append(Paragraph(f'<b>Clause {i}</b>: {title}', style_toc_ch))
        story.append(Paragraph(f'    <i>{subtitle}</i>', style_toc_sub))
        story.append(Spacer(1, 4))
    story.append(PageBreak())

    # Chapters
    for ch_num, (title, subtitle, framework) in enumerate(CHAPTERS, 1):
        fname = os.path.join(CHAPTERS_DIR, f"Clause_0{ch_num}.md") if ch_num < 10 else os.path.join(CHAPTERS_DIR, f"Clause_{ch_num}.md")
        if not os.path.exists(fname):
            print(f"  WARNING: {fname} not found")
            continue

        with open(fname, 'r', encoding='utf-8') as f:
            md = f.read()

        print(f"  Adding Clause #{ch_num}: {title}...")
        sections = parse_chapter(md)

        # Chapter header
        story.append(Paragraph(f'Clause {ch_num}', style_ch_num))
        story.append(Paragraph(title, style_ch_title))
        story.append(Paragraph(subtitle, style_subtitle_ch))
        story.append(Paragraph(framework, style_framework))
        story.append(Spacer(1, 8))

        # THE CLAUSE
        if sections['clause']:
            clause_text = clean_text(' '.join(sections['clause'].split('\n')))
            story.append(Paragraph(clause_text, style_clause))
            story.append(Spacer(1, 6))

        # THE NASS
        if sections['nass']:
            story.append(Paragraph('THE NASS — THE EVIDENCE', ParagraphStyle('NassHeader',
                fontName='Helvetica-Bold', fontSize=12, leading=16, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=10)))
            for para in sections['nass'].split('\n\n'):
                clean = clean_text(para.strip())
                if clean:
                    story.append(Paragraph(clean, style_nass))
            story.append(Spacer(1, 6))

        # FARADI'S READING
        if sections['faradi']:
            story.append(Paragraph('FARADI\u2019S READING — THE JUSTICE', ParagraphStyle('FaradiHeader',
                fontName='Helvetica-Bold', fontSize=12, leading=16, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=10)))
            for para in sections['faradi'].split('\n\n'):
                clean = clean_text(para.strip())
                if not clean:
                    continue
                low = clean.lower()
                if low.startswith('faradi:'):
                    story.append(Paragraph(f'<b>FARADI:</b> {clean[7:].strip()}', style_faradi))
                else:
                    story.append(Paragraph(clean, style_body))
            story.append(Spacer(1, 6))

        # WAQIF'S READING
        if sections['waqif']:
            story.append(Paragraph('WAQIF\u2019S READING — THE PERPETUITY', ParagraphStyle('WaqifHeader',
                fontName='Helvetica-Bold', fontSize=12, leading=16, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=10)))
            for para in sections['waqif'].split('\n\n'):
                clean = clean_text(para.strip())
                if not clean:
                    continue
                low = clean.lower()
                if low.startswith('waqif:'):
                    story.append(Paragraph(f'<b>WAQIF:</b> {clean[6:].strip()}', style_waqif))
                else:
                    story.append(Paragraph(clean, style_body))
            story.append(Spacer(1, 6))

        # THE DECLARATION
        if sections['declaration']:
            story.append(Paragraph('THE DECLARATION — THE LEGACY PRINCIPLE', ParagraphStyle('DeclHeader',
                fontName='Helvetica-Bold', fontSize=12, leading=16, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=10)))
            for para in sections['declaration'].split('\n\n'):
                clean = clean_text(para.strip())
                if not clean:
                    continue
                low = clean.lower()
                if low.startswith('hukm:'):
                    story.append(Paragraph(f'<b>HUKM:</b> {clean[5:].strip()}', style_body))
                elif low.startswith('daleel:'):
                    story.append(Paragraph(f'<b>DALEEL:</b> {clean[7:].strip()}', style_body))
                elif low.startswith('maqsad:'):
                    story.append(Paragraph(f'<b>MAQSAD:</b> {clean[7:].strip()}', style_body))
                elif low.startswith('shurut:'):
                    story.append(Paragraph(f'<b>SHURUT:</b> {clean[7:].strip()}', style_body))
                elif low.startswith('munkathirat:'):
                    story.append(Paragraph(f'<b>MUNKATHIRAT:</b> {clean[12:].strip()}', style_body))
                else:
                    story.append(Paragraph(clean, style_body))
            story.append(Spacer(1, 8))

        # THE EXECUTION
        if sections['execution']:
            story.append(Paragraph('THE EXECUTION — DO THIS THIS WEEK', ParagraphStyle('ExecHeader',
                fontName='Helvetica-Bold', fontSize=12, leading=16, alignment=TA_LEFT, textColor=NAVY, spaceAfter=6, spaceBefore=10)))
            for i, para in enumerate(sections['execution'].split('\n\n'), 1):
                clean = clean_text(para.strip())
                if clean:
                    if clean.lower().startswith(f'step {i}') or clean.lower().startswith(f'step {i}:'):
                        clean = clean.split(':', 1)[-1].strip()
                    story.append(Paragraph(f'<b>STEP {i}:</b> {clean}', style_protocol))
            story.append(Spacer(1, 8))

        # THE HISBAH
        if sections['hisbah']:
            clean = clean_text(' '.join(sections['hisbah'].split('\n')))
            story.append(Paragraph(clean, style_hisbah))

        story.append(PageBreak())

    print('Building PDF...')
    doc.build(story)
    print(f'Done: {PDF_PATH}')

    import subprocess
    result = subprocess.run(['wc', '-c', PDF_PATH], capture_output=True, text=True)
    size_kb = int(result.stdout.split()[0]) / 1024
    with open(PDF_PATH, 'rb') as f:
        data = f.read()
    pages = len(re.findall(rb'/Type\s*/Page[^s]', data))
    print(f'Pages: {pages}, Size: {size_kb:.0f} KB')

if __name__ == '__main__':
    build_pdf()