cryptonas-website/templatewriter.py

#!/usr/bin/env python

import os, re, sys
try:
	import feedparser
except ImportError:
	sys.stderr.write("Could not load python module 'feedparser'!\n")
	sys.stderr.write("Maybe you should run 'apt-get install python-feedparser.\n")
	sys.exit(1)



class TemplateWriter:
	templatefile = "template.tmpl"
	tmpldir = "placeholder"
	contentdir = "content"
	tmplfileext = ".tmpl"
	outfileext = ".html"
	output_directory = "html"
	max_rss_items = 5
	## regular expressions of not-wanted file/directory names
	## for now: no svn, no vi-swap files, no backup files
	ignore_items = [ r'\.svn', r'\.swp$', r'~$' ]

	def __init__(self):
		self.placeholder = self.__get_placeholder_dict()
		self.template = open(self.templatefile).read()
	

	def get_sorted(self, flist):
		result = flist[:]
		result.sort()
		return result


	def get_filtered(self, flist):
		result = []
		for item in flist:
			found = False
			for expression in self.ignore_items:
				if re.search(expression, item):
					found = True
					continue
			if not found:
				result.append(item)
		return result


	def __get_placeholder_dict(self):
		"""returns the common dictionary for all files - except for the 'entries'
		"""
		placeholder = {}
		for tmpl in self.get_sorted(self.get_filtered(os.listdir(self.tmpldir))):
			tmplfile = os.path.join(self.tmpldir, tmpl)
			if not os.path.isfile(tmplfile):
				print "    str.repl: cancelling %s - not a file" % tmplfile
			else:
				placeholder[tmpl] = file(tmplfile).read().strip()
		placeholder["rss_content"] = self.get_rss_info()
		return placeholder


	def get_entries(self, html_name):
		"""reads all files in the given directory sorted into a string
		"""
		entries = ""
		for entry in self.get_sorted(self.get_filtered(os.listdir(
				os.path.join(self.contentdir, html_name)))):
			entries += file(os.path.join(self.contentdir, html_name, entry)).read()
		return entries


	def build_sites_from_template(self):
		print "Building:"
		for html in self.get_sorted(self.get_filtered(os.listdir(self.contentdir))):
			print "  %s%s" % (html, self.outfileext)
			self.placeholder["entries"] = self.get_entries(html)
			## start with the content of the template
			text = self.template
			## repeat substitution for five times - for recursive stuff
			text = text % self.placeholder
			text = text % self.placeholder
			text = text % self.placeholder
			text = text % self.placeholder
			text = text % self.placeholder
			## write the result
			outfile = open(os.path.join(self.output_directory, html + self.outfileext), "w")
			outfile.write(text)
			outfile.close()
		return
	

	def get_rss_info(self):
		"""retrieve rss feed from http://devel.cryptobox.org/timeline"""
		timeline_url = r'http://devel.cryptobox.org/timeline?max=%d&wiki=off&ticket=on&changeset=on&milestone=off&format=rss' % self.max_rss_items
		entry_html = r'<li><p class="date">%(updated)s</p><a href="%(link)s">%(title)s</a>%(summary)s</li>'
		feed = feedparser.parse(timeline_url)
		if feed["entries"]:
			html_items = [ entry_html % e for e in feed["entries"] ]
			return '<ul class="recent_changes">\n' + '\n'.join(html_items) + '</ul>\n'
		else:
			return '<p>The latest development changes are temporarily unavailable. Sorry!</p>'


if __name__ == "__main__":
	TemplateWriter().build_sites_from_template()