treecutter/page.py

   1 #!/usr/bin/python
   2 import os
   3 import subprocess
   4 import tempfile
   5 import re
   6 import getpass
   7 import gnupg
   8 from lxml import etree
   9 from Cheetah.Template import Template
  10 from pkg_resources import resource_filename, resource_listdir
  11 from time import time
  12 import treecutter.constants as const
  13 from treecutter.tools import mkdir_p
  14
  15 class Page():
  16     """Class representing a version of a webpage"""
  17     def __init__(self,link,page):
  18         self._link = link
  19         self._file = page[1]
  20         self._lang = page[0]
  21         self._doc = None
  22         self._resources = []
  23         self._title = None
  24         self._menu = None
  25         self._rendered_article = None
  26
  27     def language(self):
  28         return self._lang
  29
  30     def resources(self):
  31         return set(self._resources)
  32
  33     def menu(self):
  34         return self._menu
  35
  36     def set_article(self,art):
  37         self._rendered_article = art
  38
  39     def prepare(self):
  40         self._doc = etree.parse(self._file)
  41         t = self._doc.xpath(u'/db:article/db:info/db:title',namespaces=const.XPATH)
  42         if t:
  43             self._title = unicode(t[0].text)
  44         ta = self._doc.xpath(u'/db:article/db:info/db:titleabbrev',namespaces=const.XPATH)
  45         if ta:
  46             self._menu = unicode(ta[0].text)
  47
  48         dirname = os.path.dirname(self._file)
  49         cwd = os.getcwd()
  50         code  = self._doc.xpath(u"//xi:include[@parse='text']",namespaces=const.XPATH)
  51         if code:
  52             for c in code:
  53                 href = c.get('href')
  54                 alang = c.get('accept-language')
  55                 xpointer = c.get('xpointer')
  56                 (p, ext) = os.path.splitext(href)
  57                 if ext in const.valid_scripts:
  58                     exe = []
  59                     script = os.path.join(os.path.abspath(dirname)+'/'+href)
  60                     if os.path.isfile(script):
  61                         exe.append(script)
  62                     else:
  63                         if href in resource_listdir('xinclude', ''):
  64                             script = resource_filename('xinclude', href)
  65                             exe.append(script)
  66                         else:
  67                             print "Script "+href+" in "+self._file+" missing"
  68                     if alang:
  69                         exe.append("lang="+alang)
  70                     if xpointer:
  71                         exe.append("xptr="+xpointer)
  72                     print "  executing %15s" % (href),
  73                     ts = time()
  74                     os.chdir(dirname)
  75                     xml = subprocess.Popen(exe,stdout=subprocess.PIPE,
  76                                            stderr=subprocess.PIPE)
  77                     (stdout, stderr) = xml.communicate()
  78                     if stderr:
  79                         print " ".join(exe)+" ERROR : [ "+stderr+" ]"
  80                     os.chdir(cwd)
  81                     te = time()
  82                     print " [%5.2f s]  (%s)" % (round(te-ts,2),xpointer)
  83                     xstr = etree.fromstring(stdout)
  84 # inserting the generated code and remove the xinclude reference
  85                     idp = c.getparent()
  86                     idp.insert(idp.index(c)+1,xstr)
  87                     idp.remove(c)
  88
  89         for r in self._doc.xpath(u"//db:link[@xlink:href]",namespaces=const.XPATH):
  90             rf = os.path.join(dirname,r.get(const.XLINK+'href'))
  91             if os.path.isfile(rf):
  92                 if r.get('security')=='encrypt':
  93                     with open(rf, 'rb') as f:
  94                         gpg = gnupg.GPG()
  95                         status = gpg.encrypt_file(
  96                         f, None, passphrase=getpass.getpass(rf+' password:'), symmetric=True,
  97                         output=rf+'.gpg')
  98                     r.set(const.XLINK+'href', r.get(const.XLINK+'href')+'.gpg')
  99                     rf=rf+'.gpg'
 100                 self._resources.append(rf)
 101         for i in self._doc.xpath(u"//db:imagedata[@fileref]",namespaces=const.XPATH):
 102             im = os.path.join(dirname,i.get('fileref'))
 103             if os.path.isfile(im):
 104                 self._resources.append(im)
 105         for i in self._doc.xpath(u"//html:form[@action]",namespaces=const.XPATH):
 106             pyscript = re.split('\.py',i.get('action'),1)[0]+'.py'
 107             im = os.path.join(dirname,pyscript)
 108             if os.path.isfile(im):
 109                 self._resources.append(im)
 110
 111     def render(self, style):
 112
 113 #        xslt_root = etree.XML(open(style+"docbook.xsl", 'r').read())
 114 #        transform = etree.XSLT(xslt_root)
 115 #        result = etree.tostring(transform(xml_root))
 116
 117         cwd = os.getcwd()
 118         dirname = os.path.dirname(self._file)
 119         os.chdir(dirname)
 120         infile  = os.path.basename(tempfile.mktemp())
 121         outfile = tempfile.mktemp()
 122         tfi = open(infile,'w')
 123         tfi.write(etree.tostring(self._doc,encoding='UTF-8',pretty_print=False))
 124         tfi.close()
 125 #  cmd = ["saxon-xslt-xinclude","-o",outfile,infile,style_xslt]
 126         cmd = ["xsltproc","--xinclude","--output",outfile,style+"docbook.xsl",infile]
 127         retcode = subprocess.call(cmd)
 128         if retcode:
 129             print 'Error: '+' '.join(cmd)+' Returncode ['+str(retcode)+']'
 130         tfo = open(outfile,'r')
 131         self._rendered_article = tfo.read()
 132         tfo.close()
 133         os.remove(infile)
 134         os.remove(outfile)
 135         os.chdir(cwd)
 136
 137     def template(self,sitemap,style,tdir):
 138         htmlmenu =  sitemap.gen_menu(self._lang,None,"menu")
 139         levelmenu = sitemap.gen_menu(self._lang,self,"tree")
 140         langmenu = sitemap.lang_menu(self._lang,self._link)
 141         template = Template(file=style+'index.'+self._lang+'.html.tmpl',
 142                             searchList=[{'title':self._title},
 143                                         {'menu':htmlmenu},
 144                                         {'article':self._rendered_article},
 145                                         {'levelmenu':levelmenu},
 146                                         {'langmenu':langmenu}])
 147         outfile = tdir+'html'.join(self._file.rsplit('xml',1))
 148         mkdir_p(os.path.dirname(outfile))
 149         out = open(outfile, 'w')
 150         out.write(str(template))
 151         out.close()