treecutter/page.py

   1 #!/usr/bin/python
   2 import os
   3 import subprocess
   4 import tempfile
   5 import re
   6 from lxml import etree
   7 from Cheetah.Template import Template
   8 from pkg_resources import resource_filename, resource_listdir
   9 from time import time
  10 import treecutter.constants 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 = etree.parse(self._file)
  39         t = self._doc.xpath(u'/db:article/db:info/db:title',namespaces=const.XPATH)
  40         if t:
  41             self._title = unicode(t[0].text)
  42         ta = self._doc.xpath(u'/db:article/db:info/db:titleabbrev',namespaces=const.XPATH)
  43         if ta:
  44             self._menu = unicode(ta[0].text)
  45
  46         dirname = os.path.dirname(self._file)
  47         cwd = os.getcwd()
  48         code  = self._doc.xpath(u"//xi:include[@parse='text']",namespaces=const.XPATH)
  49         if code:
  50             for c in code:
  51                 href = c.get('href')
  52                 alang = c.get('accept-language')
  53                 xpointer = c.get('xpointer')
  54                 (p, ext) = os.path.splitext(href)
  55                 if ext in const.valid_scripts:
  56                     exe = []
  57                     script = os.path.join(os.path.abspath(dirname)+'/'+href)
  58                     if os.path.isfile(script):
  59                         exe.append(script)
  60                     else:
  61                         if href in resource_listdir('xinclude', ''):
  62                             script = resource_filename('xinclude', href)
  63                             exe.append(script)
  64                         else:
  65                             print "Script "+href+" in "+self._file+" missing"
  66                     if alang:
  67                         exe.append("lang="+alang)
  68                     if xpointer:
  69                         exe.append("xptr="+xpointer)
  70                     print "  executing %15s" % (href),
  71                     ts = time()
  72                     os.chdir(dirname)
  73                     xml = subprocess.Popen(exe,stdout=subprocess.PIPE,
  74                                            stderr=subprocess.PIPE)
  75                     (stdout, stderr) = xml.communicate()
  76                     if stderr:
  77                         print " ".join(exe)+" ERROR : [ "+stderr+" ]"
  78                     os.chdir(cwd)
  79                     te = time()
  80                     print " [%5.2f s]  (%s)" % (round(te-ts,2),xpointer)
  81                     xstr = etree.fromstring(stdout)
  82 # inserting the generated code and remove the xinclude reference
  83                     idp = c.getparent()
  84                     idp.insert(idp.index(c)+1,xstr)
  85                     idp.remove(c)
  86
  87         for r in self._doc.xpath(u"//db:link[@xlink:href]",namespaces=const.XPATH):
  88             rf = os.path.join(dirname,r.get(const.XLINK+'href'))
  89             if os.path.isfile(rf):
  90                 self._resources.append(rf)
  91         for i in self._doc.xpath(u"//db:imagedata[@fileref]",namespaces=const.XPATH):
  92             im = os.path.join(dirname,i.get('fileref'))
  93             if os.path.isfile(im):
  94                 self._resources.append(im)
  95         for i in self._doc.xpath(u"//html:form[@action]",namespaces=const.XPATH):
  96             pyscript = re.split('\.py',i.get('action'),1)[0]+'.py'
  97             im = os.path.join(dirname,pyscript)
  98             if os.path.isfile(im):
  99                 self._resources.append(im)
 100
 101     def render(self, style):
 102
 103 #        xslt_root = etree.XML(open(style+"docbook.xsl", 'r').read())
 104 #        transform = etree.XSLT(xslt_root)
 105 #        result = etree.tostring(transform(xml_root))
 106
 107         cwd = os.getcwd()
 108         dirname = os.path.dirname(self._file)
 109         os.chdir(dirname)
 110         infile  = os.path.basename(tempfile.mktemp())
 111         outfile = tempfile.mktemp()
 112         tfi = open(infile,'w')
 113         tfi.write(etree.tostring(self._doc,encoding='UTF-8',pretty_print=False))
 114         tfi.close()
 115 #  cmd = ["saxon-xslt-xinclude","-o",outfile,infile,style_xslt]
 116         cmd = ["xsltproc","--xinclude","--output",outfile,style+"docbook.xsl",infile]
 117         retcode = subprocess.call(cmd)
 118         if retcode:
 119             print 'Error: '+' '.join(cmd)+' Returncode ['+str(retcode)+']'
 120         tfo = open(outfile,'r')
 121         self._rendered_article = tfo.read()
 122         tfo.close()
 123         os.remove(infile)
 124         os.remove(outfile)
 125         os.chdir(cwd)
 126
 127     def template(self,sitemap,style,tdir):
 128         htmlmenu =  sitemap.gen_menu(self._lang,None,"menu")
 129         levelmenu = sitemap.gen_menu(self._lang,self,"tree")
 130         langmenu = sitemap.lang_menu(self._lang,self._link)
 131         template = Template(file=style+'index.'+self._lang+'.html.tmpl',
 132                             searchList=[{'title':self._title},
 133                                         {'menu':htmlmenu},
 134                                         {'article':self._rendered_article},
 135                                         {'levelmenu':levelmenu},
 136                                         {'langmenu':langmenu}])
 137         outfile = tdir+'html'.join(self._file.rsplit('xml',1))
 138         mkdir_p(os.path.dirname(outfile))
 139         out = open(outfile, 'w')
 140         out.write(str(template))
 141         out.close()