API tools faq
paste
johanneswilm

lyx2googletranslate

johanneswilm
Sep 6th, 2011
1,106
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 8.90 KB | None | 0 0
raw download clone embed print report
  1. #!/usr/bin/python
  2. # coding=utf-8
  3. # Copyright Johannes 2011
  4. # [email protected]
  5. # Licensed under the GPL v. 3
  6.  
  7. def lyx2tex(filename):
  8.     basefilename=filename[:-4]
  9.     print "Converting " + filename + " -> "+basefilename+".tex..."
  10.     runcommand('lyx -e luatex -f all '+filename)
  11.     #print "Removing extra headers..."
  12.     #regex_remove_shell(basefilename+'.tex',r'(?s)\\begin{document}(.*)\\end{document}')
  13.     #print "Remove extra bibliographies..." # remove natbib bibliographies
  14.     #regex_replace(basefilename+'.tex',r'\\bibliography{([^}]*)}','')  
  15.     print "Fixing latex..."
  16.     runcommand('rpl "{[}" "[" '+basefilename+'.tex')
  17.     runcommand('rpl "{]}" "]" '+basefilename+'.tex')
  18.     runcommand('rpl -q ">{\\raggedright}" "" '+basefilename+'.tex')
  19.     runcommand('rpl -q ">{\\raggedleft}" "" '+basefilename+'.tex')
  20.     #runcommand('rpl -q "\\lyxdot " "." '+basefilename+'.tex')
  21.     return filename[:-4]+'.tex'
  22.  
  23. from sys import exit
  24. from commands import getstatusoutput
  25.  
  26. def runcommand(command,exit_on_failure=True):
  27.     output = getstatusoutput(command)
  28.     if (output[0] != 0 and exit_on_failure==True):
  29.         print command
  30.         print output[1]
  31.         exit()
  32.     return output
  33.  
  34. import re
  35.  
  36. def regex_replace(filename,from_string,to_string):
  37.     orig_filecontents = file(filename).read()
  38.     replacement_file = open(filename,'w')
  39.     replacement_file.write(re.sub(from_string, to_string, orig_filecontents))
  40.     replacement_file.close()
  41.     return True
  42.  
  43. def split_html(filename,words):
  44.     splits = words/5000
  45.     regex_replace(filename,'<html><body><p>','')
  46.     regex_replace(filename,'</body></html>','')
  47.     orig_filecontents = file(filename).read()
  48.     orig_filecontents_plist = orig_filecontents.split('<p>')
  49.     orig_filecontents_plist_len = len(orig_filecontents_plist)
  50.     orig_filecontents_plist_len_part = orig_filecontents_plist_len/splits
  51.     for split in range(splits):
  52.         part_filecontents = '<html><body><p>' + "<p>".join(orig_filecontents_plist[(orig_filecontents_plist_len_part*split):(orig_filecontents_plist_len_part*(split+1))]) + '</body></html>'
  53.         part_file = open(filename[:-5]+'_'+str(split)+'.html','w')
  54.         part_file.write(part_filecontents)
  55.         part_file.close()
  56.     runcommand('rm '+filename)
  57.     return True
  58.  
  59. def spacerepl(matchobj):
  60.     return matchobj.group(0)+matchobj.group(1).replace(' ','SPACEMARK')+matchobj.group(2)
  61.  
  62. def dotrepl(matchobj):
  63.     return matchobj.group(0)+matchobj.group(1).replace('.','DOTMARK')+matchobj.group(2)
  64.  
  65. def commarepl(matchobj):
  66.     return matchobj.group(0)+matchobj.group(1).replace(',','COMMAMARK')+matchobj.group(2)
  67.  
  68.  
  69.  
  70. def fit_for_html(html_file):
  71.     regex_replace(html_file,'{}`','`')# cleaning up
  72.     regex_replace(html_file,r'\\%','PERCENTAGE')
  73.     regex_replace(html_file,r'%([^\n]*)\n',r'\n')# cleaning up
  74.     regex_replace(html_file,'PERCENTAGE',r'<span class="notranslate">\\%</span>')  
  75.     regex_replace(html_file,r'^^','<html><body><div class="notranslate"><p>')
  76.     regex_replace(html_file,r'$$','</p></body><html>')
  77.     regex_replace(html_file,r'\n\n',r'\n</p><p>\n')
  78.     regex_replace(html_file,r'<body>\n</p>',r'<body>\n')
  79.     regex_replace(html_file,r'\\begin{document}',r'\\begin{document}</p></div>\n<p>')
  80.     regex_replace(html_file,r'\\\\','SLASH')
  81.     regex_replace(html_file,r'\\\[','BEGINPARENTESIS')
  82.     regex_replace(html_file,r'\\\]','ENDPARENTESIS')
  83.     regex_replace(html_file,r'\\\{','BEGINBRACKET')
  84.     regex_replace(html_file,r'\\\}','ENDBRACKET')
  85.     regex_replace(html_file,r'\{\}','EMPTYBRACKET')
  86.     regex_replace(html_file,r'\\protect','')   
  87.     regex_replace(html_file,r'\\(hline|tabularnewline|ldots| \& |item)',r'<span class="notranslate">\\\1</span>') # without contents
  88.     regex_replace(html_file,r'\\(index){([^}]*)}',r'<span class="notranslate">\\\1{</span>\2<span class="notranslate">endparentesis</span>') # translate contents
  89.     regex_replace(html_file,r'\\(citep|citet|citetitle|citeauthor|begin|includegraphics|label|bibliography|input|include|ref|vref|pageref)({|\[)([^}]*)}',r'<span class="notranslate">\\\1\2\3endparentesis</span>') # don't translate contents
  90.     regex_replace(html_file,r'\\(end)({|\[)([^}]*)}',r'</p><p class="notranslate">\\\1\2\3endparentesis</p><p>') # don't translate contents and add paragraph end  
  91.     regex_replace(html_file,r'\\(emph){([^}]*)}',r'<span class="notranslate">\\\1{</span>\2<span class="notranslate">endparentesis</span>') # translate contents
  92.     regex_replace(html_file,r'\\(chapter|section|subsection|subsubsection|chapter\*|section\*|subsection\*|subsubsection\*|caption|footnote){([^}]*)}',r'<span class="notranslate">\\\1{</span>\2<span class="notranslate">}</span>') # translate contents
  93.     regex_replace(html_file,r'\\(chapter|section|subsection|subsubsection|chapter\*|section\*|subsection\*|subsubsection\*|caption|footnote)\[([^\]]*)\]{([^}]*)}',r'<span class="notranslate">\\\1[</span>\2<span class="notranslate">]{</span>\3<span class="notranslate">}</span>') # translate contents
  94.     regex_replace(html_file,r'\\(addcontentsline)({[^}]*})({[^}]*}){([^}]*)}',r'<span class="notranslate">\\\1\2\3{</span>\4<span class="notranslate">}</span>') # translate some contents
  95.     regex_replace(html_file,r'\\(item</span>) \[{([^}]*)}\]',r'\\\1 <span class="notranslate">[</span>\2<span class="notranslate">]</span>') # don't translate and remove extra bracket
  96.     regex_replace(html_file,r'([|{)([^]}]*)(]|})',spacerepl) # temporarily remove spaces inside arguments
  97.     regex_replace(html_file,r'([|{)([^]}]*)(]|})',dotrepl) # temporarily remove dots inside arguments
  98.     regex_replace(html_file,r'([|{)([^]}]*)(]|})',commarepl) # temporarily remove commas inside arguments
  99.     regex_replace(html_file,r'\\(parencites)([^\s\\\<\.\,]*)(\r|\s|\\|\<|\.|\,|\r)',r'<span class="notranslate">\\\1\2</span>\3') # don't translate contents, goes on forever
  100.     regex_replace(html_file,'endparentesis','}')
  101.     regex_replace(html_file,r'</span>({|\[)([^\s\r]*)(\r|\s)',r'\1\2</span>\3') # some arguments fell outside of span
  102.     regex_replace(html_file,'&','<span class=\"notranslate\">&amp;</span>')
  103.     regex_replace(html_file,r' \\\$',r'<span class="notranslate">-\\$</span>') # with space in front
  104.     regex_replace(html_file,r'\\\$',r'<span class="notranslate">\\$</span>')
  105.     regex_replace(html_file,'~','<span class="notranslate">~</span>')
  106.     regex_replace(html_file,'\`',r'<span class="notranslate">`</span>')
  107.     regex_replace(html_file,'\'s',"APOSMARKs") # genetive s singular
  108.     regex_replace(html_file,'s\'',"sAPOSMARK") # genetive s plural
  109.     regex_replace(html_file,r'([A-z])\'([A-z])',r"\1APOSMARK\2") # inside word, not likely quotation marks
  110.     regex_replace(html_file,'\''," <span class=\"notranslate\">'</span>")
  111.     regex_replace(html_file,'APOSMARK','\'')
  112.     regex_replace(html_file,'SPACEMARK',' ')
  113.     regex_replace(html_file,'DOTMARK','.')
  114.     regex_replace(html_file,'COMMAMARK','.')
  115.     regex_replace(html_file,'BEGINPARENTESIS',r'<span class="notranslate">\\\[</span>')
  116.     regex_replace(html_file,'ENDPARENTESIS',r'<span class="notranslate">\\\]</span>')
  117.     regex_replace(html_file,'BEGINBRACKET',r'<span class="notranslate">\\\{</span>')
  118.     regex_replace(html_file,'ENDBRACKET',r'<span class="notranslate">\\\}</span>')
  119.     regex_replace(html_file,'SLASH',r'<span class="notranslate">\\\\</span>')
  120.     regex_replace(html_file,'EMPTYBRACKET',r'<span class="notranslate">{}</span>')
  121.     regex_replace(html_file,r'</span>\.',r'.</span>')
  122.     regex_replace(html_file,'</span>,',',</span>')
  123. #   regex_replace(html_file,r'{','BEGINBRACKET')
  124. #   regex_replace(html_file,r'}','ENDBRACKET') 
  125.     return True
  126.    
  127.  
  128.        
  129. def import_lyx():
  130.     lyx_files = runcommand('ls *lyx')[1].split()
  131.     for lyx_file in lyx_files:
  132.         tex_file = lyx2tex(lyx_file)
  133.         html_file = tex_file.replace('.','_') + '.html'
  134.         runcommand('cp ' + tex_file + ' ' + html_file)
  135.         fit_for_html(html_file)
  136.         words = int(runcommand('wc -w ' + html_file)[1].split()[0])
  137.         if words / 5000 > 1:
  138.             split_html(html_file,words)
  139.  
  140. def exclamrepl(matchobj):
  141.     return matchobj.group(0).replace('! ','!')
  142.  
  143. def fix_latex():
  144.     tex_files = runcommand('ls *tex')[1].split()
  145.     for tex_file in tex_files:
  146.         regex_replace(tex_file,r'Translated version of ([^\.]*)\.html','') # remove header
  147.         regex_replace(tex_file,r'\\index{([^}]*)}',exclamrepl) # replace exclamation marks
  148.         regex_replace(tex_file,r'({|\[) ',r'\1') # remove extra spaces
  149.         regex_replace(tex_file,r' (}|\])',r'\1') # remove extra spaces
  150.         regex_replace(tex_file,r' \\index',r'\\index') # remove extra spaces
  151.         regex_replace(tex_file,r'` ',r'`') # remove extra spaces
  152.         regex_replace(tex_file,' \'','\'') # remove extra spaces
  153.         regex_replace(tex_file,' ~ ','~') # remove extra spaces
  154.         regex_replace(tex_file,r' \\\\$',r'\\$') # remove extra spaces
  155.         regex_replace(tex_file,r'\-\\\\$',r'\\$') # remove extra spaces
  156.  
  157. import sys
  158.  
  159. if __name__ == "__main__":
  160.     sys_argv=sys.argv
  161.     command_options="i"
  162.     if len(sys_argv) > 1 and sys_argv[1][0]== '-':
  163.         command_options=sys_argv.pop(1)[1:]
  164.     if 'h' in command_options:
  165.         print
  166.         print "Usage:"
  167.         print sys_argv[0]+" -[hif]"
  168.         print
  169.         print "h)elp"
  170.         print "i)import"
  171.         print "f)ix output"
  172.         print
  173.     if 'i' in command_options:
  174.         import_lyx()
  175.     if 'f' in command_options:
  176.         fix_latex()
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!