"""
Post process markdown HTML file.
Ideally integrate as an add-on to:
    http://www.freewisdom.org/projects/python-markdown/

But this works on output from the original tool so is useful as prototype.

Features:

*   Added a title to the html doc based on the first H1 (title)
    Very simplistic H1 must be ona single line as output by markdown
*   Add a TOC - based on headers found, this is very simplistic, see:

    *   http://www.oac.uci.edu/indiv/ehood/htmltoc.doc.html
    *   http://www.katspace.org/tools/hypertoc/
        
    My regex TOC finder (only handles single line headers as 
    generated by markdown, freaks on multi line and bad header defs:
    
        <h(?P<heading_type>[123456])>(?P<heading_title>.*)</h[123456]>
        SET IgnoreCase  - haven't got multi line going yet
    
    Currently ignores H1 headers in the TOC - this is selective - but does
    create anchor tags for them.
        
*   ? call initial markdown conversion? / Add as a NanoDom PostProcessor to python markdown.
*   ? Integrate with tidy? Either use uTinyLib etc. or just call tidy exe directly (see cherrypy tidy filter)
*   ? look at adding an internal/external CSS style sheet depending on flags? Tidy does this

"""

import sys
import getopt


def h1_to_title(infile=None, outfile=None):
    #inlines = infile.read()
    inlines = infile.readlines()
    #infile.close()


    title=''
    # simple lame non-regex approach
    for line in inlines:
        if line.startswith('<h1>'):
            title=line[len('<h1>'):]
            title=title[:title.find('</h1>')]
           
    """           
    print '<title>%s</title>' % title
    for line in inlines:
        print line,
    """
    outfile.write('<title> %s </title>' % title)
    """
    for line in inlines:
        outfile.write(line)
    """
    html_string = "".join(inlines)
    outfile.write(html_string)

def html_add_toc(infile=None, outfile=None,TOC_INCLUDE_MARKER=None):
    if TOC_INCLUDE_MARKER is None:
        TOC_INCLUDE_MARKER='<!-- CMC_TOC_CREATE -->'
    
    inlines = infile.readlines()

    import re
    rawstr = r"""<h(?P<heading_type>[123456])>(?P<heading_title>.*)</h[123456]>"""
    compile_obj = re.compile(rawstr,  re.IGNORECASE| re.MULTILINE)

    add_toc_to_html=False
    outlines=[]
    headers_list=[]
    generated_anchor_id=0
    for line in inlines:
        # Simple line at a time, head def HAS to be on a single line or this fails
        if line.find(TOC_INCLUDE_MARKER) != -1:
            add_toc_to_html=True
            
        """
        # 2 pieces of code to find groups
        match_obj = compile_obj.search(line)
        headers_info = match_obj.groups()
        """
        # or single line:
        # list of tuples
        headers_info = compile_obj.findall(line)
        
        if headers_info != [] :
            headers_info = headers_info[0]
            if headers_info[1].strip() !="":
                html_anchor_name='MD_autoTOC_%d' % (generated_anchor_id)
                html_anchor='<a name ="%s"></a>' % (html_anchor_name)
                headers_list.append( (headers_info[0], headers_info[1], html_anchor_name) )
                outlines.append(html_anchor)
                generated_anchor_id = generated_anchor_id + 1
            
        outlines.append(line)
    inlines = outlines
        
    html_string = "".join(inlines)
    
    
    if add_toc_to_html:
        include_header_one_in_toc = True
        include_header_one_in_toc = False
        last_heading_type=0
        toc_heading_type=2
        toc_html=[]
        toc_html.append("<h%d>Table Of Contents</h%d>" %(toc_heading_type, toc_heading_type))
        
        '''
        # nested TOC that isn't quite working yet :-(
        for (heading_type, heading_title, html_anchor_name) in headers_list:
            if include_header_one_in_toc or heading_type !='1' :
                if heading_type > last_heading_type:
                    toc_html.append("<ul>")
                elif heading_type == last_heading_type:
                    toc_html.append("</li>")
                else:
                    toc_html.append("</ul>")
                #print heading_type, "<li>%d %s" % (heading_type, heading_title)
                #print "<li>%s" % (heading_title)
                toc_html.append( '<li><a href="#%s">%s</a>' % (html_anchor_name, heading_title) )
                last_heading_type=heading_type
        toc_html.append("</ul>")
        toc_html.append("<hr>")
        toc_html = ''.join(toc_html)
        '''

        toc_html.append("<ul>\n")
        for (heading_type, heading_title, html_anchor_name) in headers_list:
            if include_header_one_in_toc or heading_type !='1' :
                indent_list=range(1, int(heading_type)-1)
                for x in indent_list:
                    toc_html.append('<ul>')
                toc_html.append( '    <li><a href="#%s">%s</a></li>\n' % (html_anchor_name, heading_title) )
                for x in indent_list:
                    toc_html.append('</ul>')
                last_heading_type=heading_type
        toc_html.append("</ul>\n")
        toc_html.append("<hr>")
        toc_html = ''.join(toc_html)


        html_string = html_string.replace(TOC_INCLUDE_MARKER, toc_html)
    
    outfile.write(html_string)

def html_add_toc_old_and_busted(infile=None, outfile=None):
    inlines = infile.readlines()

    html_string = "".join(inlines)
    
    '''
    import re
    rawstr = r"""<h(?P<heading_type>[123456])>(?P<heading_title>.*)</h[123456]>"""
    embedded_rawstr = r"""(?i)<h(?P<heading_type>[123456])>(?P<heading_title>.*)</h[123456]>"""
    
    # method 1: using a compile object
    compile_obj = re.compile(rawstr,  re.IGNORECASE| re.MULTILINE)
    match_obj = compile_obj.search(html_string)
    
    # method 2: using search function (w/ external flags)
    #match_obj = re.search(rawstr, html_string,  re.IGNORECASE| re.MULTILINE)
    
    # method 3: using search function (w/ embedded flags)
    #match_obj = re.search(embedded_rawstr, html_string)
    
    # Retrieve group(s) from match_obj
    #all_groups = match_obj.groups()
    all_groups = None
    
    # Retrieve group(s) by index
    group_1 = match_obj.group(1)
    group_2 = match_obj.group(2)


    print "group_1", group_1
    print "group_2", group_2
    print "all_groups ", all_groups 
    print "findall", compile_obj.findall(html_string)
    '''


    TOC_INCLUDE_MARKER='<CMC_TOC_CREATE>'
    TOC_INCLUDE_MARKER='<!-- CMC_TOC_CREATE -->'
    if html_string.find(TOC_INCLUDE_MARKER) != -1:
        # code to dump out TOC
        # at this time, missing href links!
        import re
        rawstr = r"""<h(?P<heading_type>[123456])>(?P<heading_title>.*)</h[123456]>"""
        embedded_rawstr = r"""(?i)<h(?P<heading_type>[123456])>(?P<heading_title>.*)</h[123456]>"""
        
        compile_obj = re.compile(rawstr,  re.IGNORECASE| re.MULTILINE)
        headers_found = compile_obj.findall(html_string)
        include_header_one_in_toc = True
        include_header_one_in_toc = False
        last_heading_type=0
        toc_heading_type=2
        toc_html=[]
        toc_html.append("<h%d>Table Of Contents</h%d>" %(toc_heading_type, toc_heading_type))
        toc_html.append("<ul>")
        for (heading_type, heading_title) in headers_found:
            if include_header_one_in_toc or heading_type !='1' :
                if heading_type > last_heading_type:
                    toc_html.append("<ul>")
                elif heading_type == last_heading_type:
                    toc_html.append("</li>")
                else:
                    toc_html.append("</ul>")
                #print heading_type, "<li>%d %s" % (heading_type, heading_title)
                #print "<li>%s" % (heading_title)
                toc_html.append("<li>%s" % (heading_title))
                last_heading_type=heading_type
        toc_html.append("</ul>")
        toc_html.append("<hr>")
        toc_html = ''.join(toc_html)
        
        html_string = html_string.replace(TOC_INCLUDE_MARKER, toc_html)
    
    outfile.write(html_string)

class Usage(Exception):
    def __init__(self, msg):
        self.msg = msg

def main(argv=None):
    try:
        try:
            opts, args = getopt.getopt(argv[1:], "t:o", ["help"])
        except getopt.error, msg:
             raise Usage(msg)
        # more code, unchanged
    except Usage, err:
        print >>sys.stderr, err.msg
        print >>sys.stderr, "for help use --help"
        return 2

    """
    print "opts = " + str(opts)
    print "args = " + str(args)
    return 1
    """
    
    infile = sys.stdin
    outfile = sys.stdout
    if args != []:
        infile_name = args[0]
        infile = open(infile_name , "r")
    else:
        infile = sys.stdin

    function_to_perform = h1_to_title
    if opts != []:
        for (flag, flag_param) in opts:
            if flag == '-t':
                if flag_param == 'toc':
                    function_to_perform = html_add_toc
                if flag_param == 'title':
                    function_to_perform = h1_to_title
            if flag == '-o':
                outfile = open(flag_param, "w")


    """
    outfile = sys.stdout
    infile_name = '-'
    if args != []:
        infile_name = args[0]
    inlines = []
    import fileinput
    for line in fileinput.input(infile_name):
        inlines.append(line)
    """

    #h1_to_title(infile=infile, outfile=outfile)
    #html_add_toc(infile=infile, outfile=outfile)
    function_to_perform(infile=infile, outfile=outfile)
    



if __name__ == "__main__":
    sys.exit(main(argv=sys.argv))