# -*- coding: UTF-8 -*-
'''
rtx - RetroText
rtxPwage: Klasse zur Benutzung einer CEPT-Seite
by Anna Christina Naß <acn@acn.wtf>
released under GPL
'''

import os
import re
import config
import logging

class rtxPage:
	""" Klasse zur Benutzung einer CEPT-Seite
	"""

	die_seite = ""
	seiten_nummer = -1
	link_liste = {}

	def __init__(self, page = None):
		""" create a new page object for the page 'page' 
		returns False if the page cannot be found
		returns True if the page has been loaded
		"""
		if page == None:
			return
		else:
			self.die_seite = ""
			self.seiten_nummer = -1
			self.link_liste = {}
			self._load_page(page)

	@staticmethod
	def exists(page):
		""" checks if the page (i.e. the file) exists """
		return os.path.isfile(config.PAGES + page)

	def get_page(self):
		""" returns the page if loaded 
		returns False if no page has been loaded
		"""
		if self.die_seite != "":
			return self.die_seite
		else:
			return False

	def set_page(self,pagedata):
		""" write the pagedata as the new page and (probably) the link list """
		self.die_seite = pagedata
		self.link_liste = self._get_link_list()

	def get_links(self):
		""" returns the list of links found in this page """
		return self.link_liste

	def get_link(self, link):
		""" returns the target for a given link
		returns False if this link does not exist 
		"""
		if link in self.link_liste:
			return self.link_liste[link]
		else:
			return False

	def get_page_id(self):
		""" returns the id of the current page """
		return self.seiten_nummer

	def _load_page(self, page):
		""" Load a CEPT page from the file system 
		returns False if the page cannot be found
		returns True if the page has been loaded
		"""
		filename = config.PAGES + page

		if os.path.isfile(filename):
			with open(filename, "rb") as f:
				self.die_seite = f.read()
			self.seiten_nummer = page
			link_liste = self._get_link_list()
			return True
		else:
			return False

	def _get_link_list(self):
		""" private function which parses the CEPT page and extracts the link list
		returns True if links have been found
		returns False if no links have been found
		"""
		links = []
		links = re.findall("\x1f\x3d([^\x1f\x9b\x1b]+)", str(self.die_seite, "latin-1"))

		for item in links:
			if item[0] != "0":
				link = item[1:3].strip()
				target = item[3:].strip()
				self.link_liste[link] = target

		logging.info(self.link_liste)

		if self.link_liste == {}:
			return False
		else:
			return True