treecutter/page.py

   1 #!/usr/bin/python
   2 import os
   3 import subprocess
   4 import tempfile
   5 from amara import bindery
   6 from amara.xslt import transform
   7 from Cheetah.Template import Template
   8 from pkg_resources import resource_filename, resource_listdir
   9 import treecutter.const as const
  10 from treecutter.tools import mkdir_p
  11
  12 class Page():
  13     """Class representing a version of a webpage"""
  14     def __init__(self,link,page):
  15         self._link = link
  16         self._file = page[1]
  17         self._lang = page[0]
  18         self._doc = None
  19         self._resources = []
  20         self._title = None
  21         self._menu = None
  22         self._rendered_article = None
  23
  24     def language(self):
  25         return self._lang
  26
  27     def resources(self):
  28         return set(self._resources)
  29
  30     def menu(self):
  31         return self._menu
  32
  33     def set_article(self,art):
  34         self._rendered_article = art
  35
  36     def prepare(self):
  37         self._doc = bindery.parse(self._file, prefixes=const.PREFIXES)
  38         if self._doc.xml_select(u'/db:article/db:info/db:title'):
  39             self._title = unicode(self._doc.article.info.title)
  40         if self._doc.xml_select(u'/db:article/db:info/db:titleabbrev'):
  41             self._menu = unicode(self._doc.article.info.titleabbrev)
  42
  43         dirname = os.path.dirname(self._file)
  44         code  = self._doc.xml_select(u"//xi:include[@parse='text']")
  45         if code:
  46             for c in code:
  47                 (p, ext) = os.path.splitext(c.href)
  48                 if ext in const.valid_scripts:
  49                     exe = []
  50                     script = os.path.join(os.path.abspath(dirname)+'/'+c.href)
  51                     if os.path.isfile(script):
  52                         exe.append(script)
  53                     else:
  54                         if c.href in resource_listdir('xinclude', ''):
  55                             script = resource_filename('xinclude', c.href)
  56                             exe.append(script)
  57                         else:
  58                             print "Script "+c.href+" in "+self._file+" missing"
  59                     if c.xml_select(u"//xi:include[@accept-language]"):
  60                         alang = c.xml_attributes[None, "accept-language"]
  61                         exe.append("lang="+alang)
  62                     if c.xml_select(u"//xi:include[@xpointer]"):
  63                         exe.append("xptr="+c.xpointer)
  64                     xml = subprocess.Popen(exe,stdout=subprocess.PIPE)
  65                     xmlblock = str(xml.stdout.read())
  66                     xstr = bindery.parse(xmlblock)
  67                     idp = c.xml_index_on_parent
  68                     for x in xstr.xml_children:
  69                         c.xml_parent.xml_insert(idp,x)
  70                         c.xml_parent.xml_remove(c)
  71
  72         for r in self._doc.xml_select(u"//db:link[@xl:href]"):
  73             rf = os.path.join(dirname,r.href)
  74             if os.path.isfile(rf):
  75                 self._resources.append(rf)
  76         for i in self._doc.xml_select(u"//db:imagedata[@fileref]"):
  77             im = os.path.join(dirname,i.fileref)
  78             if os.path.isfile(im):
  79                 self._resources.append(im)
  80         for i in self._doc.xml_select(u"//html:form[@action]"):
  81             pyscript = re.split('\.py',i.action,1)[0]+'.py'
  82             im = os.path.join(dirname,pyscript)
  83             if os.path.isfile(im):
  84                 self._resources.append(im)
  85
  86     def render(self, style):
  87         #  amara can not handle the docbook stylesheets
  88         #  xmlarticle = transform(doc,style_xslt)
  89         cwd = os.getcwd()
  90         dirname = os.path.dirname(self._file)
  91         os.chdir(dirname)
  92         infile  = os.path.basename(tempfile.mktemp())
  93         outfile = tempfile.mktemp()
  94         tfi = open(infile,'w')
  95         tfi.write(self._doc.xml_encode(omit_xml_declaration=True))
  96         tfi.close()
  97 #  cmd = ["saxon-xslt-xinclude","-o",outfile,infile,style_xslt]
  98         cmd = ["xsltproc","--xinclude","--output",outfile,style+"docbook.xsl",infile]
  99         retcode = subprocess.call(cmd)
 100         if retcode:
 101             print 'Error: '+' '.join(cmd)+' Returncode ['+str(retcode)+']'
 102         tfo = open(outfile,'r')
 103         self._rendered_article = tfo.read()
 104         tfo.close()
 105         os.remove(infile)
 106         os.remove(outfile)
 107         os.chdir(cwd)
 108
 109     def template(self,sitemap,style,tdir):
 110         htmlmenu =  sitemap.gen_menu(self._lang,None,"menu")
 111         levelmenu = sitemap.gen_menu(self._lang,self,"tree")
 112         langmenu = sitemap.lang_menu(self._lang,self._link)
 113         template = Template(file=style+'index.'+self._lang+'.html.tmpl',
 114                             searchList=[{'title':self._title},
 115                                         {'menu':htmlmenu},
 116                                         {'article':self._rendered_article},
 117                                         {'levelmenu':levelmenu},
 118                                         {'langmenu':langmenu}])
 119         outfile = tdir+'html'.join(self._file.rsplit('xml',1))
 120         mkdir_p(os.path.dirname(outfile))
 121         out = open(outfile, 'w')
 122         out.write(str(template))
 123         out.close()