#!/usr/bin/env python

import os

#
# convert links from external to internal format
#
def internalize_hrefs(line):
    newline = ''
    i = line.find('href="')
    while (i >= 0):
        newline += line[0:i+6]      # everything through href="
        line = line[i+6:]           # everything after href="
        i = line.find('\"')         
        href = line[:i]             # href value
        line = line[i:]             # everything after href
        if (href[0:4] != 'http') and (href[0:6] != 'mailto'):    # don't modify external links
            j = href.find('#')
            if j >= 0:                    # replace href="xxx.yyy#zzz" with href="#zzz"
                href = href[j:]
            else:                         # replace href="xxx.htm" or href="xxx.html" with href="#xxx"
                j = href.find('.htm')
                if j >= 0:
                    href = href[0:j]
                    href = "#" + href
        newline += href
        i = line.find('href="')
    newline += line
    return newline

#
# open output file
#
outfile_basename = '#merged_' + os.path.basename(os.getcwd())
outfile = open(outfile_basename + '.htm','w', encoding='utf-8')

#
# copy index.htm without scripts, get chapter filenames
#
infile = open('index.htm','r', encoding='utf-8')
lines = infile.readlines()
infile.close()
chapter_filenames = []
found_start = False;
inside_script = False
for line in lines:
    if line.find('<script') >= 0:
        inside_script = True
        continue
    if line.find('</script') >= 0:
        inside_script = False
        continue
    if inside_script:
        continue
    if line.find('contents_end') >= 0: 
        break
    if line.find('contents_start') >= 0: 
        found_start = True
        continue
    if found_start:
        outfile.write(internalize_hrefs(line))
        i = line.find('href=')
        if i >= 0:
            filename = line[i+6:]
            i = filename.find('\"')
            filename = filename[:i]
            chapter_filenames.append(filename)
    else:
        outfile.write(line)

#
# copy chapter files
#
for filename in chapter_filenames:
    print ('infile: %s' % filename)
    infile = open(filename, 'r', encoding='utf-8')
    lines = infile.readlines()
    infile.close()
    found_start = False;
    for line in lines:
        if line.find('contents_end') >= 0:
            break
        if line.find('contents_start') >= 0:
            found_start = True
            continue
        if found_start:
            outfile.write(internalize_hrefs(line))

#
# finish output file
#
outfile.write("""
</div>
</body>
</html>
""")
outfile.close()