self._tranlang = {}
self._tmptarget = tempfile.mkdtemp()+'/'
+ # The sitemap uses a trie structure to keep track of links
+ # A link represents the path to the document and the link
+ # representing the text on the site.
+ # A link can have several pages in different languages.
def add_link(self, link):
tokens = filter(None,re.split(r'(^/[\w-]*/|[\w-]*/)',link))
self._tree.add(tokens,Link(link))
except IOError, what_error:
print 'INFO: Could not read sitemap.txt - one will be created'
+ # Create a set of the current tree for comparison with the
+ # directory scan
def set(self):
return set(link.link() for link in self._tree)
+ # Main driver in the application processing the documents
+ # in the collected sitemap
def process(self, style):
t1 = time()
print "Prepareing the input"
print "Template [%5.2f s]" % (round(t5-t4,2))
t6 = time()
res = set()
- cwd = os.getcwd()
+ # Collect all files used by the documents
for link in self._tree:
res = res.union(link.resources())
for f in res:
mkdir_p(os.path.dirname(outfile))
shutil.copyfile(f,outfile)
print "Resources[%5.2f s]" % (round(t6-t5,2))
+ # TODO: Improve the sitemap, it is a page that is generated from
+ # the ground up and added a bit adhoc.
sitmaplink = Link('/sitemap')
for l in self._sitelang:
sitmaplink.add_page((l,'/sitemap.'+l+'.xml'))