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 from time import time
  10 import treecutter.const as const
  11 from treecutter.tools import mkdir_p
  12
  13 class Page():
  14     """Class representing a version of a webpage"""
  15     def __init__(self,link,page):
  16         self._link = link
  17         self._file = page[1]
  18         self._lang = page[0]
  19         self._doc = None
  20         self._resources = []
  21         self._title = None
  22         self._menu = None
  23         self._rendered_article = None
  24
  25     def language(self):
  26         return self._lang
  27
  28     def resources(self):
  29         return set(self._resources)
  30
  31     def menu(self):
  32         return self._menu
  33
  34     def set_article(self,art):
  35         self._rendered_article = art
  36
  37     def prepare(self):
  38         self._doc = bindery.parse(self._file, prefixes=const.PREFIXES)
  39         if self._doc.xml_select(u'/db:article/db:info/db:title'):
  40             self._title = unicode(self._doc.article.info.title)
  41         if self._doc.xml_select(u'/db:article/db:info/db:titleabbrev'):
  42             self._menu = unicode(self._doc.article.info.titleabbrev)
  43
  44         dirname = os.path.dirname(self._file)
  45         cwd = os.getcwd()
  46         code  = self._doc.xml_select(u"//xi:include[@parse='text']")
  47         if code:
  48             for c in code:
  49                 (p, ext) = os.path.splitext(c.href)
  50                 if ext in const.valid_scripts:
  51                     exe = []
  52                     script = os.path.join(os.path.abspath(dirname)+'/'+c.href)
  53                     if os.path.isfile(script):
  54                         exe.append(script)
  55                     else:
  56                         if c.href in resource_listdir('xinclude', ''):
  57                             script = resource_filename('xinclude', c.href)
  58                             exe.append(script)
  59                         else:
  60                             print "Script "+c.href+" in "+self._file+" missing"
  61                     if c.xml_select(u"//xi:include[@accept-language]"):
  62                         alang = c.xml_attributes[None, "accept-language"]
  63                         exe.append("lang="+alang)
  64                     if c.xml_select(u"//xi:include[@xpointer]"):
  65                         exe.append("xptr="+c.xpointer)
  66                     print "  executing %15s" % (c.href),
  67                     ts = time()
  68                     os.chdir(dirname)
  69                     xml = subprocess.Popen(exe,stdout=subprocess.PIPE)
  70                     os.chdir(cwd)
  71                     xmlblock = str(xml.stdout.read())
  72                     te = time()
  73                     print " [%5.2f s]  (%s)" % (round(te-ts,2),c.xpointer)
  74                     xstr = bindery.parse(xmlblock)
  75                     idp = c.xml_index_on_parent
  76                     for x in xstr.xml_children:
  77                         c.xml_parent.xml_insert(idp,x)
  78                         c.xml_parent.xml_remove(c)
  79
  80         for r in self._doc.xml_select(u"//db:link[@xl:href]"):
  81             rf = os.path.join(dirname,r.href)
  82             if os.path.isfile(rf):
  83                 self._resources.append(rf)
  84         for i in self._doc.xml_select(u"//db:imagedata[@fileref]"):
  85             im = os.path.join(dirname,i.fileref)
  86             if os.path.isfile(im):
  87                 self._resources.append(im)
  88         for i in self._doc.xml_select(u"//html:form[@action]"):
  89             pyscript = re.split('\.py',i.action,1)[0]+'.py'
  90             im = os.path.join(dirname,pyscript)
  91             if os.path.isfile(im):
  92                 self._resources.append(im)
  93
  94     def render(self, style):
  95         #  amara can not handle the docbook stylesheets
  96         #  xmlarticle = transform(doc,style_xslt)
  97         cwd = os.getcwd()
  98         dirname = os.path.dirname(self._file)
  99         os.chdir(dirname)
 100         infile  = os.path.basename(tempfile.mktemp())
 101         outfile = tempfile.mktemp()
 102         tfi = open(infile,'w')
 103         tfi.write(self._doc.xml_encode(omit_xml_declaration=True))
 104         tfi.close()
 105 #  cmd = ["saxon-xslt-xinclude","-o",outfile,infile,style_xslt]
 106         cmd = ["xsltproc","--xinclude","--output",outfile,style+"docbook.xsl",infile]
 107         retcode = subprocess.call(cmd)
 108         if retcode:
 109             print 'Error: '+' '.join(cmd)+' Returncode ['+str(retcode)+']'
 110         tfo = open(outfile,'r')
 111         self._rendered_article = tfo.read()
 112         tfo.close()
 113         os.remove(infile)
 114         os.remove(outfile)
 115         os.chdir(cwd)
 116
 117     def template(self,sitemap,style,tdir):
 118         htmlmenu =  sitemap.gen_menu(self._lang,None,"menu")
 119         levelmenu = sitemap.gen_menu(self._lang,self,"tree")
 120         langmenu = sitemap.lang_menu(self._lang,self._link)
 121         template = Template(file=style+'index.'+self._lang+'.html.tmpl',
 122                             searchList=[{'title':self._title},
 123                                         {'menu':htmlmenu},
 124                                         {'article':self._rendered_article},
 125                                         {'levelmenu':levelmenu},
 126                                         {'langmenu':langmenu}])
 127         outfile = tdir+'html'.join(self._file.rsplit('xml',1))
 128         mkdir_p(os.path.dirname(outfile))
 129         out = open(outfile, 'w')
 130         out.write(str(template))
 131         out.close()