import os
import re
from ebooklib import epub

# --- FILE PATHS ---
INPUT_FILE = r"C:\Users\User\zellig\example.txt"
OUTPUT_EPUB = r"C:\Users\User\zellig\Vera_Persijn.epub"

def to_roman(num):
    val = [1000, 900, 500, 400, 100, 90, 50, 40, 10, 9, 5, 4, 1]
    syb = ["M", "CM", "D", "CD", "C", "XC", "L", "XL", "X", "IX", "V", "IV", "I"]
    roman_num = ''
    i = 0
    while num > 0:
        for _ in range(num // val[i]):
            roman_num += syb[i]
            num -= val[i]
        i += 1
    return roman_num

def inject_footnote_links(text):
    def replacer(match):
        super_chars = match.group(1)
        trans = str.maketrans("⁰¹²³⁴⁵⁶⁷⁸⁹", "0123456789")
        fn_id = int(super_chars.translate(trans))
        return f'<a epub:type="noteref" href="#fn{fn_id}" class="dt-ref">{super_chars}</a>'
    return re.sub(r'([⁰¹²³⁴⁵⁶⁷⁸⁹]+)', replacer, text)

def format_first_paragraph(text):
    # Safely extract leading punctuation so it doesn't become a giant block
    match = re.match(r'^([^A-Za-z]*)([A-Za-z])(.*)$', text)
    if match:
        punct = match.group(1)
        first_letter = match.group(2)
        rest = match.group(3)
        
        punct_html = f'<span class="hanging-punct">{punct}</span>' if punct else ''
        return f'{punct_html}<span class="dropcap">{first_letter}</span>{rest}'
    return text

def build_epub():
    if not os.path.exists(INPUT_FILE):
        print(f"ERROR: Cannot find {INPUT_FILE}")
        return

    # --- 1. EXTRACT DATA ---
    with open(INPUT_FILE, "r", encoding="utf-8") as f:
        lines = f.readlines()

    chapters = []
    ch = None
    state = "SEARCHING"
    current_section = None

    for raw_line in lines:
        line = raw_line.strip()
        if not line: continue

        if state == "SEARCHING":
            match = re.match(r"^Chapter (\d+):\s*(.*)$", line)
            if match:
                ch = {
                    "number": int(match.group(1)),
                    "roman": to_roman(int(match.group(1))),
                    "title": match.group(2),
                    "summary": [],
                    "intro_notes": [],
                    "body": [],
                    "footnotes": []
                }
                state = "PRE_BODY"
                current_section = None
                
        elif state == "PRE_BODY":
            if line == "Chapter Text":
                state = "BODY"
            elif line.startswith("Summary:"):
                current_section = "summary"
                ch["summary"].append(line.replace("Summary:", "").strip())
            elif line.startswith("Notes:"):
                current_section = "intro_notes"
            elif line.startswith("(See the end"):
                pass 
            else:
                if current_section == "summary":
                    ch["summary"].append(line)
                elif current_section == "intro_notes":
                    ch["intro_notes"].append(line)
                    
        elif state == "BODY":
            if line == "Notes:":
                state = "FOOTNOTES"
            elif line in ["Actions", "↑ Top", "Kudos"]:
                chapters.append(ch)
                state = "SEARCHING"
            else:
                ch["body"].append(line)
                
        elif state == "FOOTNOTES":
            if line in ["Actions", "↑ Top", "Kudos"]:
                chapters.append(ch)
                state = "SEARCHING"
            elif "There are no annotations" not in line and "See the end of the chapter" not in line:
                ch["footnotes"].append(line)

    # --- 2. SETUP EPUB BOOK ---
    book = epub.EpubBook()
    book.set_identifier('zellig_1337_clone')
    book.set_title('Vera Persijn Will Have Her Revenge On Amsterdam-East')
    book.set_language('en')
    book.add_author('rlissious_deliberation')

    # EXACT CLONE CSS
    css_content = '''
    @namespace epub "http://www.idpf.org/2007/ops";
    
    body { 
        font-family: "Palatino Linotype", Palatino, Georgia, serif; 
        line-height: 1.6; 
        color: #111; 
        background-color: #fcfcfc; 
        text-align: justify;
    }
    
    /* Header Area (Cloned from Sigil Screenshot) */
    .ch-header {
        text-align: center;
        margin-top: 10%;
        margin-bottom: 4em;
    }
    .ch-num {
        display: block;
        font-family: "Palatino Linotype", Palatino, Georgia, serif;
        font-size: 1.8em;
        font-weight: bold;
        color: #c09b5a;
        margin-bottom: 0.5em;
    }
    .ch-title {
        font-family: Impact, "Arial Black", sans-serif;
        font-size: 2.2em;
        text-transform: uppercase;
        letter-spacing: 3px;
        margin: 0;
        font-weight: normal;
    }
    .ch-subtitle {
        font-family: "Palatino Linotype", Palatino, Georgia, serif;
        font-style: italic;
        color: #777;
        margin-top: 2.5em;
        line-height: 1.5;
        font-size: 1.1em;
    }
    .summary-text {
        font-family: sans-serif;
        font-size: 0.85em;
        text-transform: uppercase;
        letter-spacing: 1px;
        color: #888;
        margin-bottom: 3em;
        text-align: center;
    }
    
    /* Classic Fiction Paragraphs */
    p {
        text-indent: 1.5em;
        margin-top: 0;
        margin-bottom: 0;
    }
    p.first-p {
        text-indent: 0;
        margin-top: 1.5em;
    }
    
    /* Drop Cap */
    .dropcap {
        font-family: "Palatino Linotype", Palatino, Garamond, serif;
        font-size: 3.5em;
        font-weight: bold;
        float: left;
        line-height: 0.8;
        margin-right: 0.05em;
        margin-top: -0.05em;
        color: #c09b5a;
    }
    .hanging-punct {
        font-family: "Palatino Linotype", Palatino, Garamond, serif;
        font-size: 1.8em;
        float: left;
        line-height: 1.5;
        margin-right: 0.05em;
        color: #c09b5a;
    }
    
    /* Footnotes */
    .dt-ref { text-decoration: none; vertical-align: super; font-size: 0.75em; color: #4da3ff; }
    .footnote-divider { width: 25%; margin: 4em auto 2em auto; border: 0; border-top: 1px solid #bbb; }
    .footnote-box { font-size: 0.9em; margin-bottom: 1.5em; padding: 0 1em; text-indent: 0;}

    /* Dark Mode */
    @media (prefers-color-scheme: dark) {
        body { background-color: #121212; color: #e6e6e6; }
        .ch-subtitle { color: #aaa; }
        .summary-text { color: #888; }
        .footnote-divider { border-top: 1px solid #444; }
    }
    '''
    nav_css = epub.EpubItem(uid="style_nav", file_name="style.css", media_type="text/css", content=css_content)
    book.add_item(nav_css)

    # --- 3. PROCESS CHAPTERS ---
    epub_chapters = []
    
    for ch in chapters:
        # Footnote Parsing (Includes the V2 fix for Chapter 11!)
        parsed_fns = {}
        current_fn_id = None
        for note_line in ch["footnotes"]:
            match = re.match(r'^\s*\(*(\d+)[\.\)]*\.?\s+(.*)$', note_line)
            if match:
                current_fn_id = int(match.group(1))
                parsed_fns[current_fn_id] = [match.group(2)]
            elif current_fn_id is not None:
                parsed_fns[current_fn_id].append(note_line)

        # Build HTML matching the Sigil Screenshot exactly
        html = [
            '<div class="ch-header">',
            f'  <span class="ch-num"><span class="sc">{ch["roman"]}</span></span>',
            f'  <h2 class="ch-title">{ch["title"]}</h2>'
        ]
        
        if ch["summary"]:
            html.append('  <p class="summary-text"><strong>Summary:</strong> ' + " ".join(ch["summary"]) + '</p>')
            
        if ch["intro_notes"]:
            # Lyrics joined by <br/> exactly like the screenshot
            html.append('  <p class="ch-subtitle">')
            html.append('<br/>'.join(ch["intro_notes"]))
            html.append('  </p>')

        html.append('</div>')
        
        is_first_paragraph = True
        for para in ch["body"]:
            processed_text = inject_footnote_links(para)
            if is_first_paragraph:
                processed_text = format_first_paragraph(processed_text)
                html.append(f'<p class="first-p">{processed_text}</p>')
                is_first_paragraph = False
            else:
                html.append(f'<p>{processed_text}</p>')

        if parsed_fns:
            html.append('<hr class="footnote-divider" />')
            html.append('<section class="footnotes" epub:type="footnotes">')
            for fn_id, paragraphs in parsed_fns.items():
                html.append(f'<aside epub:type="footnote" id="fn{fn_id}" class="footnote-box">')
                for fp in paragraphs: html.append(f'<p>{fp}</p>')
                html.append('</aside>')
            html.append('</section>')

        epub_ch = epub.EpubHtml(title=ch["title"], file_name=f'chapter_{ch["number"]:02d}.html', lang='en')
        epub_ch.content = "\n".join(html)
        epub_ch.add_item(nav_css)
        book.add_item(epub_ch)
        epub_chapters.append(epub_ch)

    # --- 4. FINALIZE ---
    book.toc = tuple(epub_chapters)
    book.add_item(epub.EpubNcx())
    book.add_item(epub.EpubNav())
    book.spine = ['nav'] + epub_chapters

    print("Packaging Cloned EPUB...")
    epub.write_epub(OUTPUT_EPUB, book, {})
    print(f"SUCCESS! Open {OUTPUT_EPUB} to see the replicated design.")

if __name__ == '__main__':
    build_epub()