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 import codecs
   9 from lxml import etree
  10 #from jinja2 import Template
  11 import jinja2
  12 from pkg_resources import resource_filename, resource_listdir
  13 from time import time
  14 import treecutter.constants as const
  15 from treecutter.tools import mkdir_p
  16
  17 class Page():
  18     """Class representing a version of a webpage"""
  19     def __init__(self,link,page):
  20         self._link = link
  21         self._file = page[1]
  22         self._lang = page[0]
  23         self._doc = None
  24         self._resources = []
  25         self._title = None
  26         self._menu = None
  27         self._rendered_article = None
  28
  29     def language(self):
  30         return self._lang
  31
  32     def resources(self):
  33         return set(self._resources)
  34
  35     def menu(self):
  36         return self._menu
  37
  38     def set_article(self,art):
  39         self._rendered_article = art
  40
  41     def prepare(self):
  42         self._doc = etree.parse(self._file)
  43         t = self._doc.xpath(u'/db:article/db:info/db:title',namespaces=const.XPATH)
  44         if t:
  45             self._title = unicode(t[0].text)
  46         ta = self._doc.xpath(u'/db:article/db:info/db:titleabbrev',namespaces=const.XPATH)
  47         if ta:
  48             self._menu = unicode(ta[0].text)
  49
  50         dirname = os.path.dirname(self._file)
  51         cwd = os.getcwd()
  52         code  = self._doc.xpath(u"//xi:include[@parse='text']",namespaces=const.XPATH)
  53         if code:
  54             for c in code:
  55                 href = c.get('href')
  56                 alang = c.get('accept-language')
  57                 xpointer = c.get('xpointer')
  58                 (p, ext) = os.path.splitext(href)
  59                 if ext in const.valid_scripts:
  60                     exe = []
  61                     script = os.path.join(os.path.abspath(dirname)+'/'+href)
  62                     if os.path.isfile(script):
  63                         exe.append(script)
  64                     else:
  65                         if href in resource_listdir('xinclude', ''):
  66                             script = resource_filename('xinclude', href)
  67                             exe.append(script)
  68                         else:
  69                             print "Script "+href+" in "+self._file+" missing"
  70                     if alang:
  71                         exe.append("lang="+alang)
  72                     if xpointer:
  73                         exe.append("xptr="+xpointer)
  74                     print "  executing %15s" % (href),
  75                     ts = time()
  76                     os.chdir(dirname)
  77                     xml = subprocess.Popen(exe,stdout=subprocess.PIPE,
  78                                            stderr=subprocess.PIPE)
  79                     (stdout, stderr) = xml.communicate()
  80                     if stderr:
  81                         print " ".join(exe)+" ERROR : [ "+stderr+" ]"
  82                     os.chdir(cwd)
  83                     te = time()
  84                     print " [%5.2f s]  (%s)" % (round(te-ts,2),xpointer)
  85                     xstr = etree.fromstring(stdout)
  86 # inserting the generated code and remove the xinclude reference
  87                     idp = c.getparent()
  88                     idp.insert(idp.index(c)+1,xstr)
  89                     idp.remove(c)
  90
  91         for r in self._doc.xpath(u"//db:link[@xlink:href]",namespaces=const.XPATH):
  92             rf = os.path.join(dirname,r.get(const.XLINK+'href'))
  93             if os.path.isfile(rf):
  94                 if r.get('security')=='encrypt':
  95                     with open(rf, 'rb') as f:
  96                         gpg = gnupg.GPG()
  97                         status = gpg.encrypt_file(
  98                         f, None, passphrase=getpass.getpass(rf+' password:'), symmetric=True,
  99                         output=rf+'.gpg')
 100                     r.set(const.XLINK+'href', r.get(const.XLINK+'href')+'.gpg')
 101                     rf=rf+'.gpg'
 102                 self._resources.append(rf)
 103         for i in self._doc.xpath(u"//db:imagedata[@fileref]",namespaces=const.XPATH):
 104             im = os.path.join(dirname,i.get('fileref'))
 105             if os.path.isfile(im):
 106                 self._resources.append(im)
 107             else:
 108                 print "WARNING: File "+im+" is missing!"
 109         for i in self._doc.xpath(u"//html:form[@action]",namespaces=const.XPATH):
 110             pyscript = re.split('\.py',i.get('action'),1)[0]+'.py'
 111             im = os.path.join(dirname,pyscript)
 112             if os.path.isfile(im):
 113                 self._resources.append(im)
 114
 115     def render(self, style):
 116
 117 #        xslt_root = etree.XML(open(style+"docbook.xsl", 'r').read())
 118 #        transform = etree.XSLT(xslt_root)
 119 #        result = etree.tostring(transform(xml_root))
 120
 121         cwd = os.getcwd()
 122         dirname = os.path.dirname(self._file)
 123         os.chdir(dirname)
 124         infile  = os.path.basename(tempfile.mktemp())
 125         outfile = tempfile.mktemp()
 126         tfi = open(infile,'w')
 127         tfi.write(etree.tostring(self._doc,encoding='UTF-8',pretty_print=False))
 128         tfi.close()
 129 #  cmd = ["saxon-xslt-xinclude","-o",outfile,infile,style_xslt]
 130         cmd = ["xsltproc","--xinclude","--output",outfile,style+"docbook.xhtml5.xsl",infile]
 131         retcode = subprocess.call(cmd)
 132         if retcode:
 133             print 'Error: '+' '.join(cmd)+' Returncode ['+str(retcode)+']'
 134         tfo = codecs.open(outfile, "r", "utf-8")
 135         self._rendered_article = tfo.read()
 136         tfo.close()
 137         os.remove(infile)
 138         os.remove(outfile)
 139         os.chdir(cwd)
 140
 141     def template(self,sitemap,style,tdir):
 142         htmlmenu =  sitemap.gen_menu(self._lang,None,"menu")
 143         levelmenu = sitemap.gen_menu(self._lang,self,"tree")
 144         langmenu = sitemap.lang_menu(self._lang,self._link)
 145         article = self._rendered_article
 146         templateLoader = jinja2.FileSystemLoader( searchpath="/" )
 147         templateEnv = jinja2.Environment( loader=templateLoader )
 148
 149         templateVars = {'title':self._title,
 150                         'menu':htmlmenu,
 151                         'article':article,
 152                         'levelmenu':levelmenu,
 153                         'langmen':langmenu}
 154
 155         s = unicode(style, "utf-8")
 156         t = s+'index.'+self._lang+'.xhtml.tmpl'
 157         template = templateEnv.get_template( t )
 158         templateout = template.render( templateVars )
 159
 160         outfile = tdir+'xhtml'.join(self._file.rsplit('xml',1))
 161         mkdir_p(os.path.dirname(outfile))
 162         out = codecs.open(outfile, 'w', 'utf-8')
 163         out.write(templateout)
 164         out.close()