#!/usr/bin/env python
import os
import os.path
import glob
import sys
import re
import pprint
import StringIO

BODY_COLOR = "#B1B18B"
SIDEBAR_COLOR = "#998066"
MAINAREA_COLOR = "#CCCC99"

HTACCESS='''
RewriteEngine On
RewriteCond %{HTTP_REFERER} !^$
RewriteCond %{HTTP_REFERER} !^http://(www\.)?ncertbooks.prashanthellina.com/.*$ [NC]
RewriteRule \.(PDF|pdf)$ http://ncertbooks.prashanthellina.com/ [R,L]
'''

GOOGLE_ANALYTICS_CODE = '''
<script type="text/javascript">
var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www.");
document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E"));
</script>
<script type="text/javascript">
var pageTracker = _gat._getTracker("UA-2476413-4");
pageTracker._initData();
pageTracker._trackPageview();
</script>
'''

STATCOUNTER_CODE = '''
<!-- Start of StatCounter Code -->
<script type="text/javascript">
var sc_project=3898838; 
var sc_invisible=1; 
var sc_partition=47; 
var sc_click_stat=1; 
var sc_security="254977f1"; 
</script>

<script type="text/javascript" src="http://www.statcounter.com/counter/counter.js"></script><noscript><div class="statcounter"><a href="http://www.statcounter.com/" target="_blank"><img class="statcounter" src="http://c.statcounter.com/3898838/0/254977f1/1/" alt="counter statistics" ></a></div></noscript>
<!-- End of StatCounter Code -->
'''

GOOGLE_ADS_IMAGES_BOX_CODE = '''
<div style="width:400px">
<script type="text/javascript"><!--
google_ad_client = "pub-5102327673490351";
/* 336x280, created 4/1/08 */
google_ad_slot = "0454407677";
google_ad_width = 336;
google_ad_height = 280;
//-->
</script>
<script type="text/javascript"
src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script>
</div>
'''

GOOGLE_HEADER_AD_CODE = '''
<script type="text/javascript"><!--
google_ad_client = "pub-5102327673490351";
/* 728x90, created 4/1/08 */
google_ad_slot = "0712734226";
google_ad_width = 728;
google_ad_height = 90;
//-->
</script>
<script type="text/javascript"
src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script>
'''

WORDZA_AD_CODE = '''
<br/><br/>
<center>
<font size="+1">
Preparing for GRE, SAT or CAT?<br/>Use <strong><a href="http://www.wordza.com">Wordza</a></strong> to quickly boost your vocabulary.<br/>
<a href="http://www.wordza.com"><img src="http://www.prashanthellina.com/images/wordza_logo.gif" alt="wordza"/></a>
</font>
</center>
'''

def sort_by_first_number(items):
    BIG_NUMBER = 1000
    numbered_items = []

    for item in items:
        number = re.findall('^.*?([0-9]+)', item)
        if not number: numbered_items.append((BIG_NUMBER, item))
        else: numbered_items.append((int(number[0]), item))

    numbered_items.sort()
    items = [item for number, item in numbered_items]
    return items

def sort_book_parts(parts):
    parts = parts[:]

    contents_part = [(i, p) for i, p in enumerate(parts) if p.lower().startswith('co')]
    if len(contents_part) == 1:
        index, contents_part = contents_part[0]
        del parts[index]
    else: contents_part = None

    ch_parts = [(i, p) for i, p in enumerate(parts) if p.lower().startswith('ch')]
    sorted_ch_parts = sort_by_first_number([p for i,p in ch_parts])

    for index, part in ch_parts: parts[index] = None
    parts = [p for p in parts if p is not None]
    parts.sort()

    sorted_book_parts = []
    if contents_part: sorted_book_parts.append(contents_part)
    sorted_book_parts.extend(sorted_ch_parts)
    sorted_book_parts.extend(parts)

    return sorted_book_parts

def load_structure(books_dir):
    book_dirs = glob.glob(os.path.join(books_dir, '*'))
    books_dirs = [b for b in book_dirs if not b.endswith('.html')]

    classes = {}
    for book_dir in book_dirs:
        book_base_name = os.path.basename(book_dir)
        book_info = re.findall('^class_([0-9]+)\.(.*)\.(.*?)$', book_base_name)
        if not book_info: continue
        class_no, subject, book_name = book_info[0]
        class_no = int(class_no)

        class_data = classes.get(class_no, {})
        subject_data = class_data.get(subject, {})
        book_data = subject_data.get(book_name, {})

        pdfs = glob.glob(os.path.join(book_dir, '*.[pP][dD][fF]'))
        pdfs = [os.path.basename(p) for p in pdfs]
        pdfs = sort_book_parts(pdfs)
        book_data['pdfs'] = pdfs

        subject_data[book_name] = book_data
        class_data[subject] = subject_data
        classes[class_no] = class_data

    return classes

def write_tracking_scripts():
    return '<head>%s\n%s</head>' % (GOOGLE_ANALYTICS_CODE, STATCOUNTER_CODE)

def write_sidebar():
    return '<table border="0" bgcolor="%s"><tr><td>%s</td></tr>\
<tr><td>  <br/> <br/> <br/> <br/> <br/> </td></tr>\
<tr><td>  <br/> <br/> <br/> <br/> <br/> </td></tr>\
<tr><td>%s</td></tr>\
<tr><td>  <br/> <br/> <br/> <br/> <br/> </td></tr>\
<tr><td>  <br/> <br/> <br/> <br/> <br/> </td></tr>\
<tr><td>%s</td></tr></table>' % (SIDEBAR_COLOR, GOOGLE_ADS_IMAGES_BOX_CODE, WORDZA_AD_CODE, GOOGLE_ADS_IMAGES_BOX_CODE)

def generate_main_page(data, books_dir):
    o = StringIO.StringIO()

    o.write('<html><head><title>Download NCERT Text Books</title> %s </head>\n' % write_tracking_scripts())
    o.write('<body bgcolor="%s">\n' % BODY_COLOR)
    o.write('<div align="center"><h1>NCERT BOOKS</h1></div>\n')
    
    o.write('<table bgcolor="%s" width="100%%"><tr>' % MAINAREA_COLOR)
    o.write('<td width="300px" valign="top">%s</td>' % (write_sidebar()))

    o.write('<td>')
    o.write('%s' % (GOOGLE_HEADER_AD_CODE))

    for i in range(12, 0, -1):
        o.write('<div>\n')
        o.write('<font size="7">%s</font><br/>\n' % (i))

        subjects = data[i].keys()
        subjects.sort()

        subject_links = []
        for s in subjects:
            subject_links.append('<a href="%s_%s.html">%s</a>\n' % (i, s, s))

        o.write(' | '.join(subject_links))

        o.write('</div><br/>\n')
        
    o.write('</td>')

    o.write('</tr></table>')
    o.write('%s</body></html>\n' % (WORDZA_AD_CODE))

    html = o.getvalue()
    fname = os.path.join(books_dir, 'index.html')
    open(fname, 'wb').write(html)

def generate_subject_pages(data, books_dir):
    for i in range(1, 13):
        subjects = data[i]

        for s in subjects:
            o = StringIO.StringIO()

            books = subjects[s].keys()

            o.write('<html><head><title>Download NCERT Book: Class %s: %s</title> %s </head>\n' % (i, s, write_tracking_scripts()))
            o.write('<body bgcolor="%s">\n' % BODY_COLOR)
            o.write('<div align="left"><h1>Class %s: %s</h1></div>\n' % (i, s))
            
            o.write('<table bgcolor="%s" width="100%%"><tr>' % MAINAREA_COLOR)
            o.write('<td width="300px" valign="top">%s</td>' % (write_sidebar()))

            o.write('<td>')
            o.write('%s' % (GOOGLE_HEADER_AD_CODE))

            books.sort()
            for b in books:
                book_dir = 'class_%s.%s.%s'  % (i, s, b)
                o.write('<div>\n')

                o.write('<a href="%s/index.html">\n' % (book_dir))
                o.write('<h3>%s</h3><img src="%s/image.jpg" alt="NCERT class %s %s book %s"/>\n' % (b, book_dir, i, s, b))
                o.write('</a>\n')
                
                o.write('</div>\n')
        
            o.write('</td>')

            o.write('</tr></table>')
            o.write('%s</body></html>\n' % (WORDZA_AD_CODE))

            html = o.getvalue()
            fname = os.path.join(books_dir, '%s_%s.html' % (i, s))
            open(fname, 'wb').write(html)

def generate_book_pages(data, books_dir):
    for i in range(1, 13):
        subjects = data[i]

        for s in subjects:
            books = subjects[s]

            for b in books:
                o = StringIO.StringIO()
                book_dir = 'class_%s.%s.%s'  % (i, s, b)

                o.write('<html><head><title>Download NCERT Book: Class %s: %s: %s</title> %s </head>\n' % (i, s, b, write_tracking_scripts()))
                o.write('<body bgcolor="%s">\n' % BODY_COLOR)
                o.write('<div align="left"><h1>Class %s: %s: %s</h1></div>\n' % (i, s, b))
                
                o.write('<h3>%s</h3><img src="image.jpg" alt="NCERT class %s %s book %s"/>' % (b, i, s, b))
                o.write('<br/><br/><br/>')
    
                o.write('<table bgcolor="%s" width="100%%"><tr>' % MAINAREA_COLOR)
                o.write('<td valign="top">%s</td>' % (write_sidebar()))

                o.write('<td>')
                o.write('%s' % (GOOGLE_HEADER_AD_CODE))

                pdfs = books[b]['pdfs']
                for p in pdfs:
                    p_name = '.'.join(p.split('.')[:-1])
                    o.write('<div>\n')

                    o.write('<a href="%s">\n' % (p))
                    o.write('<h4>%s</h4><img src="%s.gif" alt="NCERT class %s %s book %s"/>\n' % (p_name, p, i, s, b))
                    o.write('</a>\n')
                    
                    o.write('</div>\n')

                o.write('</td>')

                o.write('</tr></table>')
                o.write('%s</body></html>\n' % (WORDZA_AD_CODE))

                html = o.getvalue()
                fname = os.path.join(books_dir, book_dir, 'index.html')
                open(fname, 'wb').write(html)

def generate_htaccess(books_dir):
    open(os.path.join(books_dir, '.htaccess'), 'w').write(HTACCESS)

def generate_navigation_pages(books_dir):
    data = load_structure(books_dir)

    generate_main_page(data, books_dir)
    generate_subject_pages(data, books_dir)
    generate_book_pages(data, books_dir)
    generate_htaccess(books_dir)

if __name__ == '__main__':
    if len(sys.argv) < 2:
        print 'usage: %s <books_dir>' % (sys.argv[0])
        sys.exit(2)

    books_dir = sys.argv[1]
    generate_navigation_pages(books_dir)