chm2pdf-0.9.1/0040755000000000000000000000000011035462300011540 5ustar rootrootchm2pdf-0.9.1/LICENSE0100644000000000000000000004314110651617256012564 0ustar rootroot GNU GENERAL PUBLIC LICENSE Version 2, June 1991 Copyright (C) 1989, 1991 Free Software Foundation, Inc. 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The licenses for most software are designed to take away your freedom to share and change it. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. This General Public License applies to most of the Free Software Foundation's software and to any other program whose authors commit to using it. (Some other Free Software Foundation software is covered by the GNU Library General Public License instead.) You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for this service if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs; and that you know you can do these things. To protect your rights, we need to make restrictions that forbid anyone to deny you these rights or to ask you to surrender the rights. These restrictions translate to certain responsibilities for you if you distribute copies of the software, or if you modify it. For example, if you distribute copies of such a program, whether gratis or for a fee, you must give the recipients all the rights that you have. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. We protect your rights with two steps: (1) copyright the software, and (2) offer you this license which gives you legal permission to copy, distribute and/or modify the software. Also, for each author's protection and ours, we want to make certain that everyone understands that there is no warranty for this free software. If the software is modified by someone else and passed on, we want its recipients to know that what they have is not the original, so that any problems introduced by others will not reflect on the original authors' reputations. Finally, any free program is threatened constantly by software patents. We wish to avoid the danger that redistributors of a free program will individually obtain patent licenses, in effect making the program proprietary. To prevent this, we have made it clear that any patent must be licensed for everyone's free use or not licensed at all. The precise terms and conditions for copying, distribution and modification follow. GNU GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License applies to any program or other work which contains a notice placed by the copyright holder saying it may be distributed under the terms of this General Public License. The "Program", below, refers to any such program or work, and a "work based on the Program" means either the Program or any derivative work under copyright law: that is to say, a work containing the Program or a portion of it, either verbatim or with modifications and/or translated into another language. (Hereinafter, translation is included without limitation in the term "modification".) Each licensee is addressed as "you". Activities other than copying, distribution and modification are not covered by this License; they are outside its scope. The act of running the Program is not restricted, and the output from the Program is covered only if its contents constitute a work based on the Program (independent of having been made by running the Program). Whether that is true depends on what the Program does. 1. You may copy and distribute verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this License and to the absence of any warranty; and give any other recipients of the Program a copy of this License along with the Program. You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. 2. You may modify your copy or copies of the Program or any portion of it, thus forming a work based on the Program, and copy and distribute such modifications or work under the terms of Section 1 above, provided that you also meet all of these conditions: a) You must cause the modified files to carry prominent notices stating that you changed the files and the date of any change. b) You must cause any work that you distribute or publish, that in whole or in part contains or is derived from the Program or any part thereof, to be licensed as a whole at no charge to all third parties under the terms of this License. c) If the modified program normally reads commands interactively when run, you must cause it, when started running for such interactive use in the most ordinary way, to print or display an announcement including an appropriate copyright notice and a notice that there is no warranty (or else, saying that you provide a warranty) and that users may redistribute the program under these conditions, and telling the user how to view a copy of this License. (Exception: if the Program itself is interactive but does not normally print such an announcement, your work based on the Program is not required to print an announcement.) These requirements apply to the modified work as a whole. If identifiable sections of that work are not derived from the Program, and can be reasonably considered independent and separate works in themselves, then this License, and its terms, do not apply to those sections when you distribute them as separate works. But when you distribute the same sections as part of a whole which is a work based on the Program, the distribution of the whole must be on the terms of this License, whose permissions for other licensees extend to the entire whole, and thus to each and every part regardless of who wrote it. Thus, it is not the intent of this section to claim rights or contest your rights to work written entirely by you; rather, the intent is to exercise the right to control the distribution of derivative or collective works based on the Program. In addition, mere aggregation of another work not based on the Program with the Program (or with a work based on the Program) on a volume of a storage or distribution medium does not bring the other work under the scope of this License. 3. You may copy and distribute the Program (or a work based on it, under Section 2) in object code or executable form under the terms of Sections 1 and 2 above provided that you also do one of the following: a) Accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, b) Accompany it with a written offer, valid for at least three years, to give any third party, for a charge no more than your cost of physically performing source distribution, a complete machine-readable copy of the corresponding source code, to be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange; or, c) Accompany it with the information you received as to the offer to distribute corresponding source code. (This alternative is allowed only for noncommercial distribution and only if you received the program in object code or executable form with such an offer, in accord with Subsection b above.) The source code for a work means the preferred form of the work for making modifications to it. For an executable work, complete source code means all the source code for all modules it contains, plus any associated interface definition files, plus the scripts used to control compilation and installation of the executable. However, as a special exception, the source code distributed need not include anything that is normally distributed (in either source or binary form) with the major components (compiler, kernel, and so on) of the operating system on which the executable runs, unless that component itself accompanies the executable. If distribution of executable or object code is made by offering access to copy from a designated place, then offering equivalent access to copy the source code from the same place counts as distribution of the source code, even though third parties are not compelled to copy the source along with the object code. 4. You may not copy, modify, sublicense, or distribute the Program except as expressly provided under this License. Any attempt otherwise to copy, modify, sublicense or distribute the Program is void, and will automatically terminate your rights under this License. However, parties who have received copies, or rights, from you under this License will not have their licenses terminated so long as such parties remain in full compliance. 5. You are not required to accept this License, since you have not signed it. However, nothing else grants you permission to modify or distribute the Program or its derivative works. These actions are prohibited by law if you do not accept this License. Therefore, by modifying or distributing the Program (or any work based on the Program), you indicate your acceptance of this License to do so, and all its terms and conditions for copying, distributing or modifying the Program or works based on it. 6. Each time you redistribute the Program (or any work based on the Program), the recipient automatically receives a license from the original licensor to copy, distribute or modify the Program subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. You are not responsible for enforcing compliance by third parties to this License. 7. If, as a consequence of a court judgment or allegation of patent infringement or for any other reason (not limited to patent issues), conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot distribute so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not distribute the Program at all. For example, if a patent license would not permit royalty-free redistribution of the Program by all those who receive copies directly or indirectly through you, then the only way you could satisfy both it and this License would be to refrain entirely from distribution of the Program. If any portion of this section is held invalid or unenforceable under any particular circumstance, the balance of the section is intended to apply and the section as a whole is intended to apply in other circumstances. It is not the purpose of this section to induce you to infringe any patents or other property right claims or to contest validity of any such claims; this section has the sole purpose of protecting the integrity of the free software distribution system, which is implemented by public license practices. Many people have made generous contributions to the wide range of software distributed through that system in reliance on consistent application of that system; it is up to the author/donor to decide if he or she is willing to distribute software through any other system and a licensee cannot impose that choice. This section is intended to make thoroughly clear what is believed to be a consequence of the rest of this License. 8. If the distribution and/or use of the Program is restricted in certain countries either by patents or by copyrighted interfaces, the original copyright holder who places the Program under this License may add an explicit geographical distribution limitation excluding those countries, so that distribution is permitted only in or among countries not thus excluded. In such case, this License incorporates the limitation as if written in the body of this License. 9. The Free Software Foundation may publish revised and/or new versions of the General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies a version number of this License which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of this License, you may choose any version ever published by the Free Software Foundation. 10. If you wish to incorporate parts of the Program into other free programs whose distribution conditions are different, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively convey the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA Also add information on how to contact you by electronic and paper mail. If the program is interactive, make it output a short notice like this when it starts in an interactive mode: Gnomovision version 69, Copyright (C) year name of author Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, the commands you use may be called something other than `show w' and `show c'; they could even be mouse-clicks or menu items--whatever suits your program. You should also get your employer (if you work as a programmer) or your school, if any, to sign a "copyright disclaimer" for the program, if necessary. Here is a sample; alter the names: Yoyodyne, Inc., hereby disclaims all copyright interest in the program `Gnomovision' (which makes passes at compilers) written by James Hacker. , 1 April 1989 Ty Coon, President of Vice This General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Library General Public License instead of this License.chm2pdf-0.9.1/chm2pdf0100644000000000000000000015356011035113022013007 0ustar rootroot#!/usr/bin/python ''' CHM2PDF v. 0.9.1 http://code.google.com/p/chm2pdf A script that converts a CHM compiled HTML file into a single PDF file. (c) 2007 Massimo Sandal (c) 2007 Chris Karakas This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 2 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program. If not, see . ''' import chm.chm as chm import sys import sgmllib import os, os.path import re, glob import getopt # from BeautifulSoup import BeautifulSoup global version global CHM2PDF_TEMP_WORK_DIR #where conversions etc. take place global CHM2PDF_TEMP_ORIG_DIR #where the chm file is exploded global CHM2PDF_WORK_DIR global CHM2PDF_ORIG_DIR global filename #the input filename version = '0.9.1' CHM2PDF_TEMP_WORK_DIR='/tmp/chm2pdf/work' CHM2PDF_TEMP_ORIG_DIR='/tmp/chm2pdf/orig' # YOU DON'T NEED TO CHANGE ANYTHING BELOW THIS LINE! class PageLister(sgmllib.SGMLParser): ''' parser of the chm.chm GetTopicsTree() method that retrieves the URL of the HTML page embedded in the CHM file. ''' def reset(self): sgmllib.SGMLParser.reset(self) self.pages=[] def start_param(self,attrs): urlparam_flag=False for key,value in attrs: if key=='name' and value=='Local': urlparam_flag=True if urlparam_flag and key=='value': self.pages.append('/'+value) class ImageCatcher(sgmllib.SGMLParser): ''' finds image urls in the current html page, so to take them out from the chm file. ''' def reset(self): sgmllib.SGMLParser.reset(self) self.imgurls=[] def start_img(self,attrs): for key,value in attrs: if key=='src' or key=='SRC': # Avoid duplicates in the list of image URLs. if not self.imgurls.count(value): self.imgurls.append(value) class CssCatcher(sgmllib.SGMLParser): ''' finds CSS urls in the current html page, so to take them out from the chm file. ''' def reset(self): sgmllib.SGMLParser.reset(self) self.cssurls=[] def start_link(self,attrs): for key,value in attrs: if key=='href' or key=='HREF': # Avoid duplicates in the list of CSS URLs. if not self.cssurls.count(value): self.cssurls.append(value) def get_html_list(cfile): ''' retrieves the list of HTML files contained into the CHM file, **in order** (that's the important bit). (actually performed by the PageLister class) ''' topicstree=cfile.GetTopicsTree() lister=PageLister() lister.feed(topicstree) #print 'lister pages',lister.pages return lister.pages def get_objective_urls_list(filename): ''' takes the list of files inside the chm archive, with the correct urls of each one. ''' os.system('enum_chmLib '+filename+' > '+CHM2PDF_WORK_DIR+'/urlslist.txt') flist=open(CHM2PDF_WORK_DIR+'/urlslist.txt','rU') urls_list=[] for line in flist.readlines()[3:]: #print 'line',line spline=line.split() urls_list.append(spline[5]) flist.close() # os.remove(CHM2PDF_WORK_DIR+'/urlslist.txt') return urls_list def correct_file(input_file, output_file, html_list, objective_urls, options): # Correct image links in file pf=open(input_file,'rU') page=pf.read() pf.close() # Correct the HTML markup of the page, if the --beautifulsoup was passed. if options['beautifulsoup']=='--beautifulsoup': from BeautifulSoup import BeautifulSoup, Tag soup = BeautifulSoup(page) page = str(soup) image_catcher=ImageCatcher() image_catcher.feed(page) css_catcher=CssCatcher() css_catcher.feed(page) # We substitute the image URLs of input_file with the *actual* URLs on the CHM2PDF_ORIG_DIR directory for iurl in image_catcher.imgurls: # print 'iurl = ' + iurl img_filename = '' for item in objective_urls: if iurl in item: img_filename=CHM2PDF_ORIG_DIR+item if ';' in img_filename: #hack to get rid of mysterious ; in filenames and urls... img_filename=img_filename.split(';')[0] # substitute the new image filenames - but only if an img_filename was found! if img_filename: page=re.sub(iurl,img_filename,page) # We substitute the CSS URLs of input_file with the *actual* URLs on the CHM2PDF_ORIG_DIR directory for curl in css_catcher.cssurls: # print 'curl = ' + curl css_filename = '' for item in objective_urls: if curl in item: css_filename=CHM2PDF_ORIG_DIR+item if ';' in css_filename: #hack to get rid of mysterious ; in filenames and urls... css_filename=img_filename.split(';')[0] # substitute the new image filenames - but only if a css_filename was found! if css_filename: page=re.sub(curl,css_filename,page) # Fontsize hack: # Since htmldoc ignores the --fontsize option, we have to do something about it... # If --fontsize xxx was given on the command line, # insert and tags between

and

. # While doing so, use xxx as the value of the size attribute of the font tag. if options['fontsize']: # page=re.sub('(]*>)','\\1' + os.linesep + '' + os.linesep, page) # page=re.sub('(<\/p[^>]*>)', os.linesep + '' + os.linesep + '\\1' + os.linesep, page) # page=re.sub('(]*>)','\\1' + '',page) # page=re.sub('(<\/body[^>]*>)','' + '\\1',page) # page=re.sub('(]*>)','\\1' + os.linesep + '' + os.linesep, page) # page=re.sub('(<\/table[^>]*>)', os.linesep + '' + os.linesep + '\\1' + os.linesep, page) # page=re.sub('(]*>)','\\1' + ' ',page) page=re.sub('(]*>)','\\1' + '',page) page=re.sub('(<\/body[^>]*>)','' + '\\1',page) # Delete unwanted HTML elements. page=re.sub('
','', page) page=re.sub(']*><\/a>','' ,page) page=re.sub(']*><\/a>','', page) page=re.sub(']*><\/a>','', page) page=re.sub('"[^"]*previous\.gif"','""', page) page=re.sub('"[^"]*prev\.gif"','""', page) page=re.sub('"[^"]*next\.gif"','""', page) # Delete CSS markup (]*>','', page) # Change font size between 
 and
to the value given by the '--prefontsize' option. if options['prefontsize'] != '': page=re.sub('
','
', page)
        page=re.sub('<\/pre>','
', page)


    # Correct the HTML markup of the page, if the --beautifulsoup was passed.
    if options['beautifulsoup']=='--beautifulsoup':
        # from BeautifulSoup import BeautifulSoup
        soup = BeautifulSoup(page)
        # page = soup.prettify()

        # top_vevel_table = soup.table
        # top_vevel_table.extract()
        # top_vevel_table['width'] = options['browserwidth']

#         tables=soup.findAll('table')
#         for table in tables:
#             # table['cellpadding'] = '0.15in'
#             table['border'] = '1'
#             table['width'] = '95%'
#             # table['width'] = options['browserwidth']

#             trs=table.findAll('tr')
#             for tr in trs:
#                 tds=tr.findAll('td')
#                 for td in tds:
#                     # print td.find(text=True)
#                     # td['cellpadding'] = '0.15in'
#                     # td['nowrap'] = 'false'
#                     # if td.content != None:
#                     for tag in td.contents:
#                         if tag.__class__.__name__ == 'NavigableString' and (tag == "\n" or tag == ''):
#                             print 'The following is of class ' + tag.__class__.__name__ + ' and is empty: '
#                             print '-->' + tag + '<--'
#                             tag.extract
#                             # print td.content
#                             # td.string = re.sub('^[\n\t\r ]*$', '', td.string)
#                             # if td.string == '':
#                             #     td.extract()

#         pixelimgs=soup.findAll('img', {"width" : "1", "height" : "1"})
#         for pixelimg in pixelimgs:
#             pixelimg.extract()

#         divs=soup.findAll('div')
#         for div in divs:
#             if div.string == None or div.string == os.linesep:
#                 div.extract()
#             # else:
#             #     print '-->"' + div.string + '"'


        pres = soup.findAll('pre')
        line_regex = re.compile(r'^.*$', re.MULTILINE)
        for pre in pres:

            pre['width'] = '50'

#             font_tag = Tag(BeautifulSoup(), 'font')
#             font_tag['size'] = '-1'
#             pre.insert(0, font_tag)

            texts_with_linesep = pre.findAll(text=line_regex, recursive=True)
            for text in texts_with_linesep:
                newtext=re.sub(os.linesep,'
',text.string)
#                 print "#########################################################################"
#                 print text
#                 print "#########################################################################"
#                 print
#                 print
                text.replaceWith(newtext)


        # page = soup.prettify()
        page = str(soup)


    f=open(output_file,'w')
    f.write(page)
    f.close()


def convert_to_pdf(cfile, filename, outputfilename, options):
    '''
    Performs actual converting.
    '''

    # Extract the files from the CHM archive and correct them ONLY IF '--dontextract' was NOT given!
    # ########################### File extraction and correction: START ############################
    #
    if options['dontextract'] == '':
    
        try:
            os.mkdir(CHM2PDF_TEMP_WORK_DIR)
        except OSError: # The directory already exists.
            pass
        
        try:
            os.mkdir(CHM2PDF_TEMP_ORIG_DIR)
        except OSError: # The directory already exists.
            pass
        
        try:
            os.mkdir(CHM2PDF_ORIG_DIR)
        except OSError: # The directory already exists.
            pass
        
        try:
            os.mkdir(CHM2PDF_WORK_DIR)
        except OSError: # The directory already exists.
            pass
   
    # Compute filenames and lists. This is needed no matter if '--dontextract' was given or not!
     
    html_list=get_html_list(cfile)
    objective_urls=get_objective_urls_list(filename)

    # print 'objective_urls'
    # print '=============='
    # print objective_urls
    # print
    # print 'html_list'
    # print '========='
    # print html_list

    true_html_list=[] #Should mostly coincide with html_list, but...
   
    input_titlefile = '' 
    output_titlefile = '' 
    for html_file in html_list:
        for item in objective_urls:
            if html_file in item:
                true_html_list.append(CHM2PDF_ORIG_DIR+item)
            if not options['titlefile']=='' and options['titlefile'] in item:
                input_titlefile = CHM2PDF_ORIG_DIR+item
                output_titlefile = CHM2PDF_WORK_DIR + os.sep + options['titlefile']

    if not options['titlefile']=='' and not output_titlefile:
        print '### WARNING: ' + options['titlefile'] + ' not found inside ' + filename + ' - possible spelling error.'
        print '### You can check it if you do  \'' + sys.argv[0] + ' --extract-only\','
        print '### then have a look at the files in  ' + CHM2PDF_ORIG_DIR + '.'
        print '### Option \'--titlefile ' + options['titlefile'] + '\' ignored'
        options['titlefile'] = ''


    # Process toc file. This depends on the '--dontextract' option.
    
    if options['dontextract'] == '':
        # Correct image links in toc file.
        if not options['titlefile']=='' and os.path.exists(input_titlefile):
            correct_file(input_titlefile, output_titlefile, html_list, objective_urls, options)

    
    # Now process the rest of HTML files.

    # Compute some lists. Again, this is independent of the '--dontextract' option.

    c=0
    htmlout_filename_list=''
    htmlout_filenames = []
    if output_titlefile:
        htmlout_filenames.append(output_titlefile)
    match_strings = []
    replace_strings = []
    replace_garbled_strings = []
    for url in html_list:
        c+=1
        page_filename=CHM2PDF_ORIG_DIR + url
        # Some names contain a '%20' (an HTML code for a space). We substitute with a "real space"
        # otherwise a 'File not found' error will occur.
        page_filename = re.sub('%20',' ',page_filename)
        
        if options['verbose']=='--verbose' and options['verbositylevel']=='high' and options['dontextract'] == '':
            print "Correcting " + page_filename

 
        if os.path.exists(page_filename) and (options['titlefile'] == '' or not options['titlefile'] in url):
            htmlout_filename=CHM2PDF_WORK_DIR+'/temp'+'%(#)04d' %{"#":c}+'.html'
            htmlout_filename_list+=' '+ htmlout_filename
            htmlout_filenames.append(htmlout_filename)
    
            if options['dontextract'] == '':
                # Correct image links in file page_filename.
                correct_file(page_filename, htmlout_filename, html_list, objective_urls, options)

            # Escape slashes in url.
            url_filename_escaped = re.sub('/', '\/', os.path.basename(url))
            # Escape dots in url.
            url_filename_escaped = re.sub('\.', '\.', url_filename_escaped)
            # Escape slashes in htmlout_filename.
            htmlout_filename_escaped = re.sub('/', '\/', os.path.basename(htmlout_filename))
            # Compute a "garbled" htmlout_filename, where dots are simply replaced with underscores.
            htmlout_filename_escaped_garbled = re.sub('\.', '_', htmlout_filename_escaped)

            # Build a list for each of the three strings (the original URL, the output filename and the garbled one).
            # The idea is that we want to replace the match_strings with the corresponding replace_garbled_strings first.
            # Then, in a second pass, we will replace the garbled strings with the "real" replace_strings.
            # This trick is necessary to avoid problems in cases where the original URLs look like
            #
            # 0001.html, 0002.html, 0003.html...
            #
            # and we want to replace as follows:
            #
            # toc.html	-> temp0001.html
            # 0001.html	-> temp0002.html
            # 0002.html -> temp0003.html
            # 0003.html -> temp0004.html
            #
            # If we try it "directly", i.e. without the "garbled" names first, we will end up changing:
            #
            # tol.html	-> temp0001.html -> temptemp0002.html -> temptemptemp0003.html ...
            # 0001.html	-> temp0002.html -> temptemp0003.html -> temptemptemp0004.html ...
            # ...
            # 
            # which is not what we want.
            match_strings.append(url_filename_escaped)
            replace_strings.append(htmlout_filename_escaped)
            replace_garbled_strings.append(htmlout_filename_escaped_garbled)
        
    # Now we've got the lists computed. We proceed with the actual correction,
    # which IS dependent on the '--dontextract' option:

    if options['dontextract'] == '':
        # Correct links to files in the local collection.
        if options['verbose']=='--verbose' and options['verbositylevel']=='low':
            print 'Correcting links in the HTML files...'
    
        if options['verbose']=='--verbose' and options['verbositylevel']=='high':
            print '############### 1st pass ###############'
        for match_string in  match_strings:
            replace_string = replace_garbled_strings[match_strings.index(match_string)]
            if options['verbose']=='--verbose' and options['verbositylevel']=='high':
                print "match " + match_string + ' ' + "and replace it with " + replace_string
        if options['verbose']=='--verbose' and options['verbositylevel']=='high':
            print
            
        if options['verbose']=='--verbose' and options['verbositylevel']=='high':
            print '############### 2nd pass ###############'
        for match_string in  replace_garbled_strings:
            replace_string = replace_strings[replace_garbled_strings.index(match_string)]
            if options['verbose']=='--verbose' and options['verbositylevel']=='high':
                print "match " + match_string + ' ' + "and replace it with " + replace_string
        if options['verbose']=='--verbose' and options['verbositylevel']=='high':
            print
            
        for filename in htmlout_filenames:
            
            pf=open(filename,'rU')
            page=pf.read()
            pf.close()
    
            # Substitutions in 1st pass: we replace the original filenames with their corresponding "garbled" equivalents.
            for match_string in  match_strings:
                replace_string = replace_garbled_strings[match_strings.index(match_string)]
                page = re.sub(match_string, replace_string, page)
            
    
            # Substitutuions in the 2nd pass: we replace the garbled filenames with the correct ones.
            for match_string in  replace_garbled_strings:
                replace_string = replace_strings[replace_garbled_strings.index(match_string)]
                page = re.sub(match_string, replace_string, page)
    
            # Replace links of the form "somefile.html#894" with "somefile0206.html"        
            # The following will match anchors like ' /dev/null"
    exit_value=os.system ('htmldoc' + htmldoc_opts + ' ' + htmlout_filename_list + " -f "+ outputfilename + " > /dev/null")

    if exit_value != 0:
        print 'Something wrong happened when launching htmldoc.'
        print 'exit value: ',exit_value
        print 'Check if output exists or if it is good.'
    else: 
        print 'Written file ' + outputfilename
    print 'Done.'    

def usage (name):
    print 'Usage:'
    print "\t%s [options] input_filename [output_filename]" % name
    print
    print 'Options:'
    print
    print '\t--beautifulsoup\n\t\tCorrect the HTML code of the pages before converting them to PDF. The BeautifulSoup package (see http://www.crummy.com/software/BeautifulSoup/) needs to be installed.'
    print '\t--bodycolor color\n\t\tSpecifies the background color for all pages.'
    print '\t--bodyfont {courier,helvetica,monospace,sans,serif,times}. Default is times.'
    print '\t--bodyimage filename.{bmp,gif,jpg,png}'
    print '\t--book\n\t\tSpecifies that the HTML sources are structured (headings, chapters, etc.).'
    print '\t--bottom margin{in,cm,mm}\n\t\tSpecifies the bottom margin in points (no suffix or ##pt), inches  (##in),  centimeters  (##cm),  or millimeters (##mm).'
    print '\t--browserwidth pixels\n\t\tSee http://www.htmldoc.org/newsgroups.php?ghtmldoc.general+v:3465'
    print '\t--charset {cp-874...1258,iso-8859-1...8859-15,koi8-r}\n\t\tSpecifies the ISO character set to use for the output.'
    print '\t--color\n\t\tSpecifies that PDF output should be in color.'
    print '\t--compression[=level]\n\t\t'
    print '\t--continuous\n\t\tSpecifies  that  the  HTML  sources are unstructured (plain web pages).\n\t\tNo page breaks are inserted between each file or URL in the output.'
    print '\t--cookies \'name="value with space"; name=value\'\n\t\t'
    print '\t--datadir directory\n\t\tSpecifies the  location  of  the  HTMLDOC  data  files,  usually  /usr/share/htmldoc  or  C:\Program Files\HTMLDOC '
    print "\t--dontextract \n\t\tIf given, %s will not extract the HTML files from the given CHM file, but will use previously extracted copies from the temporary directory " %name + '(i.e. ' + CHM2PDF_TEMP_ORIG_DIR + ' and ' + CHM2PDF_TEMP_WORK_DIR + '). Usually you will use this option after you have used the \'--extract-only\' option to extract the files in order to correct them manually (in ' + CHM2PDF_TEMP_WORK_DIR + '). After the correction, a call with \'--dontextract\' will not overwrite your changes, but will use the corrected files instead.'
    print '\t--duplex\n\t\tSpecifies that the output should be formatted for double-sided printing.'
    print '\t--effectduration {0.1..10.0}\n\t\tSpecifies the duration in seconds of PDF page transition effects.'
    print '\t--embedfonts\n\t\tSpecifies that fonts should be embedded in PDF output.'
    print '\t--encryption\n\t\tEnables encryption of PDF files.'
    print '\t--extract-only\n\t\tExtract the HTML files from the CHM file and stop.\n\t\tThe extracted files will be found in CHM2PDF_WORK_DIR/input_filename_without_extension.'
    print '\t--firstpage {p1,toc,c1}\n\t\t'
    print '\t--fontsize {4.0..24.0}\n\t\tSpecifies the default font size for body text.'
    print '\t--fontspacing {1.0..3.0}\n\t\tSpecifies  the  default  line  spacing  for body text.\n\t\tThe line spacing is a multiplier for the font size, so a value of 1.2 \n\t\twill provide an additional 20% of space between the lines.'
    print '\t--footer fff\n\t\t'
    print '\t{--format, -t} {pdf11,pdf12,pdf13,pdf14}\n\t\tSpecifies the output format: pdf11\n\t\tpdf11 (PDF 1.1/Acrobat 2.0), pdf12 (PDF 1.2/Acrobat 3.0), \n\t\tpdf or pdf13 (PDF  1.3/Acrobat  4.0),  or  pdf14 (PDF 1.4/Acrobat 5.0)'
    print '\t--gray\n\t\t'
    print '\t--header fff\n\t\t'
    print '\t--header1 fff\n\t\t'
    print '\t--headfootfont {courier{-bold,-oblique,-boldoblique}, \n\t\thelvetica{-bold,-oblique,-boldoblique}, \n\t\tmonospace{-bold,-oblique,-boldoblique}, \n\t\tsans{-bold,-oblique,-boldoblique}, \n\t\tserif{-bold,-italic,-bolditalic}, \n\t\ttimes{-roman,-bold,-italic,-bolditalic}} \n\t\t\tSets the font to use on headers and footers.'
    print '\t--headfootsize {6.0..24.0}\n\t\tSets the size of the font to use on headers and footers.'
    print '\t--headingfont {courier,helvetica,monospace,sans,serif,times}\n\t\tSets the typeface to use for headings.'
    print '\t--help\n\t\tDisplays a summary of command-line options.'
    print '\t--hfimage0 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage1 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage2 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage3 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage4 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage5 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage6 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage7 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage8 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--hfimage9 filename.{bmp,gif,jpg,png}\n\t\t '
    print '\t--jpeg quality\n\t\tSets the JPEG compression level to use for large images. A value of 0 disables JPEG compression.'
    print '\t--landscape\n\t\t'
    print '\t--left margin{in,cm,mm}\n\t\tSpecifies the left margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or  millimeters (##mm).'
    print '\t--linkcolor color\n\t\tSets the color of links. You can use well-known color names like blue, or the usual #RRGGBB notation.'
    print '\t--links\n\t\tEnables generation of links in PDF files (default).'
    print '\t--linkstyle {plain,underline}\n\t\tSets the style of links.'
    print '\t--logoimage filename.{bmp,gif,jpg,png}\n\t\tSpecifies an image to be used as a logo in the header or footer in a PDF document.'
    print '\t--logoimage filename.{bmp,gif,jpg,png}\n\t\tNote that you need to use the --header and/or --footer options with the l parameter.'
    print '\t--no-compression\n\t\tDisables compression of PDF file.'
    print '\t--no-duplex\n\t\tDisables double-sided printing.'
    print '\t--no-embedfonts\n\t\tSpecifies that fonts should not be embedded in PDF and PostScript output.'
    print '\t--no-encryption\n\t\tDisables document encryption.'
    print '\t--no-links\n\t\tDisables generation of links in a PDF document. '
    print '\t--no-localfiles\n\t\t'
    print '\t--no-numbered\n\t\tDisables automatic heading numbering.'
    print '\t--no-overflow\n\t\t'
    print '\t--no-strict\n\t\tDisables strict HTML input checking.'
    print '\t--no-title\n\t\tDisables generation of a title page.'
    print '\t--no-toc\n\t\tDisables generation of a table of contents.'
    print '\t--numbered\n\t\tNumbers all headings in a document.'
    print '\t--nup {1,2,4,6,9,16}\n\t\tSets  the  number of pages that are placed on each output page.  Valid values are 1, 2, 4, 6, 9, and 16.'
    print '\t{--outfile, -f} filename{.pdf}\n\t\tSpecifies the name of the output file. If no ending is given, ".pdf" is used.'
    print '\t--overflow\n\t\t'
    print '\t--owner-password password\n\t\tSets the owner password for encrypted PDF files.'
    print '\t--pageduration {1.0..60.0}\n\t\tSets the view duration of a page in a PDF document.'
    print '\t--pageeffect {none,bi,bo,d,gd,gdr,gr,hb,hsi,hso,vb,vsi,vso,wd,wl,wr,wu}\n\t\tSpecifies the page transition effect for all pages; this attribute is ignored by all Adobe PDF viewers.. '
    print '\t--pagelayout {single,one,twoleft,tworight}\n\t\tSpecifies the initial layout of pages for a PDF file.'
    print '\t--pagemode {document,outline,fullscreen}\n\t\tSpecifies the initial viewing mode for a PDF file.'
    print '\t--path "dir1;dir2;dir3;...;dirN"\n\t\tSpecifies a search path for files in a document.'
    print '\t--permissions {all,annotate,copy,modify,print,no-annotate,no-copy,no-modify,no-print,none}\n\t\tSpecifies document permissions for encrypted PDF files. Separate multiple permissions with commas. '
    print '\t--portrait\n\t\t'
    print '\t--prefontsize {4.0..24.0, small, normal, big, huge, +1, +2, -1, -2,...whatever}\n\t\tSpecifies the font size for text inside 
 tags. Whatever you pass here will be used as font size inside preformatted pieces of text (usually code snippets, console output, program messages...). Effective only together with the \'--beautifulsoup\' option.'
    print '\t--quiet\n\t\tSuppresses all messages, even error messages.'
    print '\t--right margin{in,cm,mm}\n\t\tSpecifies the right margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).'
    print '\t--size {letter,a4,WxH{in,cm,mm},etc}\n\t\tSpecifies the page size using a standard name or in points (no suffix or ##x##pt), inches (##x##in),\n\t\tcentimeters (##x##cm), or millimeters (##x##mm). The standard sizes that  are  currently  recognized\n\t\tare "letter" (8.5x11in), "legal" (8.5x14in), "a4" (210x297mm), and "universal" (8.27x11in).'
    print '\t--strict\n\t\tEnables strict HTML input checking.'
    print '\t--textcolor color\n\t\tSpecifies the default color of all text.'
    print '\t--textfont {courier,helvetica,monospace,sans,serif,times}\n\t\t'
    print '\t--title\n\t\tEnables the generation of a title page.'
    print '\t--titlefile filename.{htm,html,shtml}\n\t\tSpecifies  the  file to use for the title page. If the file is an image then the title page\n\t\tis automatically generated using the document meta data and image title.'
    print '\t--titleimage filename.{bmp,gif,jpg,png}\n\t\tSpecifies  the  image to use for the title page. The title page is automatically \n\t\tgenerated using the document meta data and title image.'
    print '\t--tocfooter fff\n\t\tSets the page footer to use on table-of-contents pages. See below for the format of fff.'
    print '\t--tocheader fff\n\t\tSets the page header to use on table-of-contents pages. See below for the format of fff.'
    print '\t--toclevels levels\n\t\tSets the number of levels in the table-of-contents.'
    print '\t--toctitle string\n\t\tSets the title for the table-of-contents.'
    print '\t--top margin{in,cm,mm}\n\t\tSpecifies the top margin in points (no suffix or ##pt), inches (##in), centimeters (##cm),  or  millimeters (##mm).'
    print '\t--user-password password\n\t\tSpecifies the user password for encryption of PDF files.'
    print '\t--verbose\n\t\tDisplays various messages indicating the progress of the conversion process. The verbosity depends on --verbositylevel. If --verbose is not set, almost no messages will be printed. The default is \'not set\', so if you want the minimum amount of messages, just don\' use this option.'
    print '\t--verbositylevel\n\t\tSpecifies the verbosity level of the messages. Can be either \'low\' or \'high\'. Default is low. The --verbose option must be set, otherwise this option will have no effect.'
    print '\t--version\n\t\tDisplays the current version number.'
    print '\t--webpage\n\t\tSpecifies  that  the  HTML  sources  are  unstructured  (plain web pages).\n\t\tA page break is inserted between each file or URL in the output.'
    print
    print '\tfff\n\t\tHeading format string; each \'f\' can be one of:'
    print
    print '\t\t\t. = blank'
    print '\t\t\t/ = n/N arabic page numbers (1/3, 2/3, 3/3)'
    print '\t\t\t: = c/C arabic chapter page numbers (1/2, 2/2, 1/4, 2/4, ...)'
    print '\t\t\t1 = arabic numbers (1, 2, 3, ...)'
    print '\t\t\ta = lowercase letters'
    print '\t\t\tA = uppercase letters'
    print '\t\t\tc = current chapter heading'
    print '\t\t\tC = current chapter page number (arabic)'
    print '\t\t\td = current date'
    print '\t\t\tD = current date and time'
    print '\t\t\th = current heading'
    print '\t\t\ti = lowercase roman numerals'
    print '\t\t\tI = uppercase roman numerals'
    print '\t\t\tl = logo image'
    print '\t\t\tt = title text'
    print '\t\t\tT = current time'
    print
    print '### See also: http://www.karakas-online.de/forum/viewtopic.php?t=10275'

def split(path):
    if path[-1] == os.sep :
        path, fname = path[:-1], ''
    else:
        path, fname = os.path.split( path )
        fname, ext = os.path.splitext( fname )
    return ( path, fname, ext[1:] )



def main(argv):

    global CHM2PDF_WORK_DIR
    global CHM2PDF_ORIG_DIR

    # Defaults
    options={}
    options['beautifulsoup'] = ''
    options['bodycolor'] = ''
    options['bodyfont'] = 'times'
    options['bodyimage'] = ''
    options['book'] = ''
    options['bottom'] = ''
    options['browserwidth'] = ''
    options['charset'] = ''
    options['color'] = ''
    options['compression'] = ''
    options['continuous'] = ''
    options['cookies'] = ''
    options['datadir'] = ''
    options['dontextract'] = ''
    options['duplex'] = '--duplex'
    options['effectduration'] = ''
    options['embedfonts'] = '--embedfonts'
    options['encryption'] = ''
    options['extract-only'] = ''
    options['firstpage'] = ''
    options['fontsize'] = ''
    options['fontspacing'] = ''
    options['footer'] = '\'c C\''
    options['format'] = '\'pdf14\''
    options['gray'] = ''
    options['header'] = '\'c C\''
    options['header1'] = ''
    options['headfootfont'] = ''
    options['headfootsize'] = ''
    options['headingfont'] = ''
    options['help'] = ''
    options['hfimage0'] = ''
    options['hfimage1'] = ''
    options['hfimage2'] = ''
    options['hfimage3'] = ''
    options['hfimage4'] = ''
    options['hfimage5'] = ''
    options['hfimage6'] = ''
    options['hfimage7'] = ''
    options['hfimage8'] = ''
    options['hfimage9'] = ''
    options['jpeg'] = '\'100\''
    options['landscape'] = ''
    options['left'] = ''
    options['linkcolor'] = '\'blue\''
    options['links'] = ''
    options['linkstyle'] = '\'plain\''
    options['logoimage'] = ''
    options['logoimage'] = ''
    options['no-compression'] = ''
    options['no-duplex'] = ''
    options['no-embedfonts'] = ''
    options['no-encryption'] = ''
    options['no-links'] = ''
    options['no-localfiles'] = ''
    options['no-numbered'] = ''
    options['no-overflow'] = ''
    options['no-strict'] = ''
    options['no-title'] = ''
    options['no-toc'] = ''
    options['numbered'] = ''
    options['nup'] = ''
    options['outfile'] = ''
    options['overflow'] = ''
    options['owner-password'] = ''
    options['pageduration'] = ''
    options['pageeffect'] = ''
    options['pagelayout'] = ''
    options['pagemode'] = ''
    options['path'] = ''
    options['permissions'] = ''
    options['portrait'] = ''
    options['prefontsize'] = ''
    options['quiet'] = ''
    options['right'] = ''
    options['size'] = '\'a4\''
    options['strict'] = ''
    options['textcolor'] = ''
    options['textfont'] = ''
    options['title'] = ''
    options['titlefile'] = ''
    options['titleimage'] = ''
    options['tocfooter'] = ''
    options['tocheader'] = ''
    options['toclevels'] = ''
    options['toctitle'] = ''
    options['top'] = ''
    options['user-password'] = ''
    options['verbose'] = ''
    options['verbositylevel'] = 'low'
    options['version'] = ''
    options['webpage'] = ''

    try:
        opts, args = getopt.getopt(sys.argv[1:], "f:t:v:", 
                     [
                      "beautifulsoup",
                      "bodycolor=",
                      "bodyfont=",
                      "bodyimage=",
                      "book",
                      "bottom=",
                      "browserwidth=",
                      "charset=",
                      "color",
                      "compression=",
                      "continuous",
                      "cookies=",
                      "datadir=",
                      "dontextract",
                      "duplex",
                      "effectduration=",
                      "embedfonts",
                      "encryption",
                      "extract-only",
                      "firstpage=",
                      "fontsize=",
                      "fontspacing=",
                      "footer=",
                      "format=",
                      "gray",
                      "header=",
                      "header1=",
                      "headfootfont=",
                      "headfootsize=",
                      "headingfont=",
                      "help",
                      "hfimage0=",
                      "hfimage1=",
                      "hfimage2=",
                      "hfimage3=",
                      "hfimage4=",
                      "hfimage5=",
                      "hfimage6=",
                      "hfimage7=",
                      "hfimage8=",
                      "hfimage9=",
                      "jpeg=",
                      "landscape",
                      "left=",
                      "linkcolor=",
                      "links",
                      "linkstyle=",
                      "logoimage=",
                      "logoimage=",
                      "no-compression",
                      "no-duplex",
                      "no-embedfonts",
                      "no-encryption",
                      "no-links",
                      "no-localfiles",
                      "no-numbered",
                      "no-overflow",
                      "no-strict",
                      "no-title",
                      "no-toc",
                      "numbered",
                      "nup=",
                      "outfile=",
                      "overflow",
                      "owner-password=",
                      "pageduration=",
                      "pageeffect=",
                      "pagelayout=",
                      "pagemode=",
                      "path=",
                      "permissions=",
                      "portrait",
                      "prefontsize=",
                      "quiet",
                      "right=",
                      "size=",
                      "strict",
                      "textcolor=",
                      "textfont=",
                      "title",
                      "titlefile=",
                      "titleimage=",
                      "tocfooter=",
                      "tocheader=",
                      "toclevels=",
                      "toctitle=",
                      "top=",
                      "user-password=",
                      "verbose",
                      "verbositylevel=",
                      "version",
                      "webpage"
                     ])
    except getopt.GetoptError:
        usage(sys.argv[0])
        sys.exit(1)
    
    for o, a in opts:
        if   o == '--beautifulsoup': options['beautifulsoup'] = '--beautifulsoup'
        elif o == '--bodycolor': options['bodycolor'] = a
        elif o == '--bodyfont': options['bodyfont'] = a
        elif o == '--bodyimage': options['bodyimage'] = a
        elif o == '--book': options['book'] = '--book'
        elif o == '--bottom': options['bottom'] = a
        elif o == '--browserwidth': options['browserwidth'] = a
        elif o == '--charset': options['charset'] = a
        elif o == '--color': options['color'] = '--color'
        elif o == '--compression': options['compression'] = a
        elif o == '--continuous': options['continuous'] = '--continuous'
        elif o == '--cookies': options['cookies'] = a
        elif o == '--datadir': options['datadir'] = a
        elif o == '--dontextract': options['dontextract'] = '--dontextract'
        elif o == '--duplex': options['duplex'] = '--duplex'
        elif o == '--effectduration': options['effectduration'] = a
        elif o == '--embedfonts': options['embedfonts'] = '--embedfonts'
        elif o == '--encryption': options['encryption'] = '--encryption'
        elif o == '--extract-only': options['extract-only'] = '--extract-only'
        elif o == '--firstpage': options['firstpage'] = a
        elif o == '--fontsize': options['fontsize'] = a
        elif o == '--fontspacing': options['fontspacing'] = a
        elif o == '--footer': options['footer'] = a
        elif o in ('-t', '--format'): options['format'] = a
        elif o == '--gray': options['gray'] = '--gray'
        elif o == '--header': options['header'] = a
        elif o == '--header1': options['header1'] = a
        elif o == '--headfootfont': options['headfootfont'] = a
        elif o == '--headfootsize': options['headfootsize'] = a
        elif o == '--headingfont': options['headingfont'] = a
        elif o == '--help': options['help'] = '--help'
        elif o == '--hfimage0': options['hfimage0'] = a
        elif o == '--hfimage1': options['hfimage1'] = a
        elif o == '--hfimage2': options['hfimage2'] = a
        elif o == '--hfimage3': options['hfimage3'] = a
        elif o == '--hfimage4': options['hfimage4'] = a
        elif o == '--hfimage5': options['hfimage5'] = a
        elif o == '--hfimage6': options['hfimage6'] = a
        elif o == '--hfimage7': options['hfimage7'] = a
        elif o == '--hfimage8': options['hfimage8'] = a
        elif o == '--hfimage9': options['hfimage9'] = a
        elif o == '--jpeg': options['jpeg'] = a
        elif o == '--landscape': options['landscape'] = '--landscape'
        elif o == '--left': options['left'] = a
        elif o == '--linkcolor': options['linkcolor'] = a
        elif o == '--links': options['links'] = '--links'
        elif o == '--linkstyle': options['linkstyle'] = a
        elif o == '--logoimage': options['logoimage'] = a
        elif o == '--logoimage': options['logoimage'] = a
        elif o == '--no-compression': options['no-compression'] = '--no-compression'
        elif o == '--no-duplex': options['no-duplex'] = '--no-duplex'
        elif o == '--no-embedfonts': options['no-embedfonts'] = '--no-embedfonts'
        elif o == '--no-encryption': options['no-encryption'] = '--no-encryption'
        elif o == '--no-links': options['no-links'] = '--no-links'
        elif o == '--no-localfiles': options['no-localfiles'] = '--no-localfiles'
        elif o == '--no-numbered': options['no-numbered'] = '--no-numbered'
        elif o == '--no-overflow': options['no-overflow'] = '--no-overflow'
        elif o == '--no-strict': options['no-strict'] = '--no-strict'
        elif o == '--no-title': options['no-title'] = '--no-title'
        elif o == '--no-toc': options['no-toc'] = '--no-toc'
        elif o == '--numbered': options['numbered'] = '--numbered'
        elif o == '--nup': options['nup'] = a
        elif o in ('-f', '--outfile'): options['outfile'] = a
        elif o == '--overflow': options['overflow'] = '--overflow'
        elif o == '--owner-password': options['owner-password'] = a
        elif o == '--pageduration': options['pageduration'] = a
        elif o == '--pageeffect': options['pageeffect'] = a
        elif o == '--pagelayout': options['pagelayout'] = a
        elif o == '--pagemode': options['pagemode'] = a
        elif o == '--path': options['path'] = a
        elif o == '--permissions': options['permissions'] = a
        elif o == '--portrait': options['portrait'] = '--portrait'
        elif o == '--prefontsize': options['prefontsize'] = a
        elif o == '--quiet': options['quiet'] = '--quiet'
        elif o == '--right': options['right'] = a
        elif o == '--size': options['size'] = a
        elif o == '--strict': options['strict'] = '--strict'
        elif o == '--textcolor': options['textcolor'] = a
        elif o == '--textfont': options['textfont'] = a
        elif o == '--title': options['title'] = '--title'
        elif o == '--titlefile': options['titlefile'] = a
        elif o == '--titleimage': options['titleimage'] = a
        elif o == '--tocfooter': options['tocfooter'] = a
        elif o == '--tocheader': options['tocheader'] = a
        elif o == '--toclevels': options['toclevels'] = a
        elif o == '--toctitle': options['toctitle'] = a
        elif o == '--top': options['top'] = a
        elif o == '--user-password': options['user-password'] = a
        elif o in ('-v', '--verbose'): options['verbose'] = '--verbose'
        elif o == '--verbositylevel': options['verbositylevel'] = a
        elif o == '--version': 
            print sys.argv[0] + ' version ' + version
            print 'This is free software; see the source for copying conditions.  There is NO'
            print 'warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.'
            return
        elif o == '--webpage': options['webpage'] = '--webpage'

    # Option validation checks
    #
    # Only one of '--extract-only' and '--dontextract' may be given!
    if options['dontextract'] == '--dontextract' and options['extract-only'] == '--extract-only':
        usage(sys.argv[0])
        print
        print '### Either \'--dontextract\' or \'extract-only\' may be given!'
        print '### Only one of the two options can be present, not both!'
        print '### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.'
        return
    #
    # One of '--book' or '--webpage' MUST be given!
    if options['extract-only'] == '' and ((options['book'] == '' and options['webpage'] == '' and options['continuous'] == '') or 
                                          (options['book'] == '--book' and options['webpage'] == '--webpage') or
                                          (options['book'] == '--book' and options['continuous'] == '--continuous') or
                                          (options['webpage'] == '--webpage' and options['continuous'] == '--continuous')):
        usage(sys.argv[0])
        print
        print '### Either \'--book\' or \'--webpage\' or \'--continuous\' MUST be given!'
        print '### Only one of the three options can be present, not two, or even all three of them!'
        print '### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.'
        return

    if len(args)==0:
        usage(sys.argv[0])
        return
    elif len(args)==1:
        filename = args[0]
        dirname, basename, suffix = split(filename)
        if dirname:
            outputfilename = dirname + os.sep + basename +'.pdf'
        else:
            outputfilename = dirname + basename +'.pdf'
        # print 'outputfilename = ' + outputfilename

    elif len(args)==2:
        filename = args[0]
        dirname, basename, suffix = split(filename)
        outputfilename = args[1]
        # print 'outputfilename = ' + outputfilename
    else:
        usage(sys.argv[0])
        return
 
    CHM2PDF_WORK_DIR = CHM2PDF_TEMP_WORK_DIR + os.sep + basename
    CHM2PDF_ORIG_DIR = CHM2PDF_TEMP_ORIG_DIR + os.sep + basename

    if options['verbose']=='--verbose' and options['verbositylevel']=='low':
        print 'CHM2PDF_WORK_DIR = ' + CHM2PDF_WORK_DIR
        print 'CHM2PDF_ORIG_DIR = ' + CHM2PDF_ORIG_DIR

    if not os.path.exists(filename):
        print 'CHM file "' + filename + '" not found!'
        return
    
    #remove temporary files
    if options['dontextract'] == '':
        if options['verbose']=='--verbose' and options['verbositylevel']=='high':
            print 'Removing any previous temporary files...'
        os.system('rm -r '+CHM2PDF_ORIG_DIR+'/*')
        os.system('rm -r '+CHM2PDF_WORK_DIR+'/*')
    
    cfile = chm.CHMFile()
    cfile.LoadCHM(filename)

    if options['dontextract'] == '--dontextract':
        if options['verbose'] == '--verbose':
            print '\'--dontextract\' option was given. No files will be extracted from CHM.'
            print 'Will use the files in ' + CHM2PDF_ORIG_DIR + ' and ' + CHM2PDF_WORK_DIR + '.'
    else:
        if options['verbose'] == '--verbose' and options['verbositylevel'] == 'high':
            os.system('extract_chmLib ' + filename + ' ' + CHM2PDF_ORIG_DIR)
        else:
            os.system('extract_chmLib ' + filename + ' ' + CHM2PDF_ORIG_DIR + '&> /dev/null')
    
    convert_to_pdf(cfile, filename, outputfilename, options)


if __name__ == '__main__':
    main(sys.argv)
    
chm2pdf-0.9.1/setup.py0100644000000000000000000000072310720042741013254 0ustar  rootroot#!/usr/bin/env python

from distutils.core import setup

setup(name = "chm2pdf",
    version = "0.9",
    description = "A script to convert CHM files into PDF",
    author = "Massimo Sandal, Chris Karakas",
    author_email = "devicerandom@gmail.com, chris@karakas-online.de",
    url = "http://code.google.com/p/chm2pdf/",
    scripts = ["chm2pdf"],
    long_description = "A script to convert CHM files into PDF. Requires chmlib, pychm, htmldoc."
    )
    

    
chm2pdf-0.9.1/PKG-INFO0100644000000000000000000000055611035462137012650 0ustar  rootrootMetadata-Version: 1.0
Name: chm2pdf
Version: 0.9.1
Summary: A script to convert CHM files into PDF
Home-page: http://code.google.com/p/chm2pdf/
Author: Massimo Sandal, Chris Karakas
Author-email: devicerandom@gmail.com, chris@karakas-online.de
License: GPL v.2.
Description: A script to convert CHM files into PDF. Requires chmlib, pychm, htmldoc.
Platform: UNKNOWN
chm2pdf-0.9.1/README0100644000000000000000000000162211035113022012410 0ustar  rootrootCHM2PDF

(c) 2007 Massimo Sandal
(c) 2007-2008 Chris Karakas 

A Python script that converts a CHM file into a single PDF file.

Usage: 
chm2pdf [options] input_filename [output_filename]

See

chm2pdf --help

for all options.

RECOMMENDED READING:
    - http://www.karakas-online.de/forum/viewtopic.php?t=10275
    - http://www.karakas-online.de/forum/viewtopic.php?t=10969


Installation:
- download the .tar.gz
- unzip it: "tar -xzvf chm2pdf-a.b.c.tar.gz"
- enter the newly created directory
- acquire root privileges
- type "python setup.py install"

Requires:
    - python
    - chmlib 
      NOTE: chmlib *must* be configured with ./configure --enable-examples
    - pychm
    - htmldoc

Optional:
    - BeautifulSoup
    
All of these should be in your Linux/Unix distribution repository :)

To contact Massimo: devicerandom@gmail.com
To contact Chris: chris@karakas-online.de