X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/c7d738ac87aa4933b276103870abb5145fd326f2..e9cdd3f1f653de79f94ddfcdf319fcc31e7f0cef:/librarian/pyhtml.py?ds=inline
diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py
index 6a3d40d..7047cc9 100644
--- a/librarian/pyhtml.py
+++ b/librarian/pyhtml.py
@@ -5,20 +5,43 @@
#
from lxml import etree
from librarian import IOFile, RDFNS, DCNS, Format
-from xmlutils import Xmill, tag, tagged, ifoption
+from xmlutils import Xmill, tag, tagged, ifoption, tag_open_close
from librarian import functions
import re
import random
+from copy import deepcopy
+IMAGE_THUMB_WIDTH = 300
-DEFAULT_MATERIAL_FORMAT = 'odt'
-
+try:
+ from fnpdjango.utils.text.slughifi import slughifi
+ def naglowek_to_anchor(naglowek):
+ return slughifi(naglowek.text)
+except ImportError:
+ from urllib import quote
+ def naglowek_to_anchor(naglowek):
+ return quote(re.sub(r" +", " ", naglowek.text.strip()))
+
+
class EduModule(Xmill):
def __init__(self, options=None):
super(EduModule, self).__init__(options)
self.activity_counter = 0
+ self.exercise_counter = 0
+
+ # text filters
+ def swap_endlines(txt):
+ if self.options['strofa']:
+ txt = txt.replace("/\n", "
\n")
+ return txt
self.register_text_filter(functions.substitute_entities)
+ self.register_text_filter(swap_endlines)
+
+ @tagged('div', 'stanza')
+ def handle_strofa(self, element):
+ self.options = {'strofa': True}
+ return "", ""
def handle_powiesc(self, element):
return u"""
@@ -31,18 +54,34 @@ class EduModule(Xmill):
""", u""
handle_autor_utworu = tag("span", "author")
- handle_nazwa_utworu = tag("h1", "title")
handle_dzielo_nadrzedne = tag("span", "collection")
handle_podtytul = tag("span", "subtitle")
handle_naglowek_akt = handle_naglowek_czesc = handle_srodtytul = tag("h2")
- handle_naglowek_scena = handle_naglowek_rozdzial = tag('h2')
+ handle_naglowek_scena = tag('h2')
handle_naglowek_osoba = handle_naglowek_podrozdzial = tag('h3')
handle_akap = handle_akap_dialog = handle_akap_cd = tag('p', 'paragraph')
- handle_strofa = tag('div', 'stanza')
+
handle_wyroznienie = tag('em')
handle_tytul_dziela = tag('em', 'title')
handle_slowo_obce = tag('em', 'foreign')
+ def handle_nazwa_utworu(self, element):
+ toc = []
+ for naglowek in element.getparent().findall('.//naglowek_rozdzial'):
+ a = etree.Element("a")
+ a.attrib["href"] = "#" + naglowek_to_anchor(naglowek)
+ a.text = naglowek.text
+ atxt = etree.tostring(a, encoding=unicode)
+ toc.append("