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         dirname = os.path.dirname(self._file)
  50         cwd = os.getcwd()
  51         code  = self._doc.xpath(u"//xi:include[@parse='text']",namespaces=const.XPATH)
  52         if code:
  53             for c in code:
  54                 href = c.get('href')
  55                 alang = c.get('accept-language')
  56                 xpointer = c.get('xpointer')
  57                 (p, ext) = os.path.splitext(href)
  58                 if ext in const.valid_scripts:
  59                     exe = []
  60                     script = os.path.join(os.path.abspath(dirname)+'/'+href)
  61                     if os.path.isfile(script):
  62                         exe.append(script)
  63                     else:
  64                         if href in resource_listdir('xinclude', ''):
  65                             script = resource_filename('xinclude', href)
  66                             exe.append(script)
  67                         else:
  68                             print "Script "+href+" in "+self._file+" missing"
  69                     if alang:
  70                         exe.append("lang="+alang)
  71                     if xpointer:
  72                         exe.append("xptr="+xpointer)
  73                     print "  executing %15s" % (href),
  74                     ts = time()
  75                     os.chdir(dirname)
  76                     xml = subprocess.Popen(exe,stdout=subprocess.PIPE,
  77                                            stderr=subprocess.PIPE)
  78                     (stdout, stderr) = xml.communicate()
  79                     if stderr:
  80                         print " ".join(exe)+" ERROR : [ "+stderr+" ]"
  81                     os.chdir(cwd)
  82                     te = time()
  83                     print " [%5.2f s]  (%s)" % (round(te-ts,2),xpointer)
  84                     xstr = etree.fromstring(stdout)
  85 # inserting the generated code and remove the xinclude reference
  86                     idp = c.getparent()
  87                     idp.insert(idp.index(c)+1,xstr)
  88                     idp.remove(c)
  89
  90         for r in self._doc.xpath(u"//db:link[@xlink:href]",namespaces=const.XPATH):
  91             rf = os.path.join(dirname,r.get(const.XLINK+'href'))
  92             if os.path.isfile(rf):
  93                 if r.get('security')=='encrypt':
  94                     with open(rf, 'rb') as f:
  95                         gpg = gnupg.GPG()
  96                         status = gpg.encrypt_file(
  97                         f, None, passphrase=getpass.getpass(rf+' password:'), symmetric=True,
  98                         output=rf+'.gpg')
  99                     r.set(const.XLINK+'href', r.get(const.XLINK+'href')+'.gpg')
 100                     rf=rf+'.gpg'
 101                 self._resources.append(rf)
 102         for i in self._doc.xpath(u"//db:imagedata[@fileref]",namespaces=const.XPATH):
 103             im = os.path.join(dirname,i.get('fileref'))
 104             if os.path.isfile(im):
 105                 self._resources.append(im)
 106             else:
 107                 print "WARNING: File "+im+" is missing!"
 108         for i in self._doc.xpath(u"//html:form[@action]",namespaces=const.XPATH):
 109             pyscript = re.split('\.py',i.get('action'),1)[0]+'.py'
 110             im = os.path.join(dirname,pyscript)
 111             if os.path.isfile(im):
 112                 self._resources.append(im)
 113
 114     def render(self, style):
 115
 116 #        xslt_root = etree.XML(open(style+"docbook.xsl", 'r').read())
 117 #        transform = etree.XSLT(xslt_root)
 118 #        result = etree.tostring(transform(xml_root))
 119
 120         cwd = os.getcwd()
 121         dirname = os.path.dirname(self._file)
 122         os.chdir(dirname)
 123         infile  = os.path.basename(tempfile.mktemp())
 124         outfile = tempfile.mktemp()
 125         tfi = open(infile,'w')
 126         tfi.write(etree.tostring(self._doc,encoding='UTF-8',pretty_print=False))
 127         tfi.close()
 128 #  cmd = ["saxon-xslt-xinclude","-o",outfile,infile,style_xslt]
 129         cmd = ["xsltproc","--xinclude","--output",outfile,style+"docbook.xhtml5.xsl",infile]
 130         retcode = subprocess.call(cmd)
 131         if retcode:
 132             print 'Error: '+' '.join(cmd)+' Returncode ['+str(retcode)+']'
 133         tfo = codecs.open(outfile, "r", "utf-8")
 134         self._rendered_article = tfo.read()
 135         tfo.close()
 136         os.remove(infile)
 137         os.remove(outfile)
 138         os.chdir(cwd)
 139
 140     def template(self,sitemap,style,tdir,subdir):
 141         htmlmenu =  sitemap.gen_menu(self._lang,None,"menu")
 142         levelmenu = sitemap.gen_menu(self._lang,self,"tree")
 143         langmenu = sitemap.lang_menu(self._lang,self._link)
 144         article = self._rendered_article
 145         templateLoader = jinja2.FileSystemLoader( searchpath="/" )
 146         templateEnv = jinja2.Environment( loader=templateLoader )
 147
 148         templateVars = {'title':self._title,
 149                         'menu':htmlmenu,
 150                         'article':article,
 151                         'levelmenu':levelmenu,
 152                         'langmen':langmenu,
 153                         'subdir':subdir}
 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()