slugify anchors, fix some minor html issues

[librarian.git] / librarian / pyhtml.py

diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py
index d36e0fe..1f1f3df 100644 (file)
--- a/librarian/pyhtml.py
+++ b/librarian/pyhtml.py
@@ -9,9 +9,21 @@ from xmlutils import Xmill, tag, tagged, ifoption, tag_open_close
 from librarian import functions
 import re
 import random
 from librarian import functions
 import re
 import random

+from copy import deepcopy

 
 IMAGE_THUMB_WIDTH = 300
 
 
 IMAGE_THUMB_WIDTH = 300
 

+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)
 class EduModule(Xmill):
     def __init__(self, options=None):
         super(EduModule, self).__init__(options)


@@ -53,24 +65,22 @@ class EduModule(Xmill):
     handle_tytul_dziela = tag('em', 'title')
     handle_slowo_obce = tag('em', 'foreign')
 
     handle_tytul_dziela = tag('em', 'title')
     handle_slowo_obce = tag('em', 'foreign')
 

-    def naglowek_to_anchor(self, naglowek):
-        return re.sub(r" +", " ", naglowek.text.strip())
-

     def handle_nazwa_utworu(self, element):
         toc = []
         for naglowek in element.getparent().findall('.//naglowek_rozdzial'):
             a = etree.Element("a")
     def handle_nazwa_utworu(self, element):
         toc = []
         for naglowek in element.getparent().findall('.//naglowek_rozdzial'):
             a = etree.Element("a")

-            a.attrib["href"] = "#" + self.naglowek_to_anchor(naglowek)
+            a.attrib["href"] = "#" + naglowek_to_anchor(naglowek)

             a.text = naglowek.text
             atxt = etree.tostring(a, encoding=unicode)
             toc.append("<li>%s</li>" % atxt)
         toc = "<ul class='toc'>%s</ul>" % "".join(toc)
         add_header = "Lekcja: " if self.options['wldoc'].book_info.type in ('course', 'synthetic') else ''
             a.text = naglowek.text
             atxt = etree.tostring(a, encoding=unicode)
             toc.append("<li>%s</li>" % atxt)
         toc = "<ul class='toc'>%s</ul>" % "".join(toc)
         add_header = "Lekcja: " if self.options['wldoc'].book_info.type in ('course', 'synthetic') else ''

-        return "<h1 class='title'>%s" % add_header, "</h1>" + toc
+        return "<h1 class='title' id='top'>%s" % add_header, "</h1>" + toc

 
 

-    @tagged("h2")

     def handle_naglowek_rozdzial(self, element):
     def handle_naglowek_rozdzial(self, element):

-        return "", "".join(tag_open_close("a", name=self.naglowek_to_anchor(element)))
+        return_to_top = u"<a href='#top' class='top-link'>wróć do spisu treści</a>"
+        pre, post = tag_open_close("h2", id=naglowek_to_anchor(element))
+        return return_to_top + pre, post

 
     def handle_uwaga(self, _e):
         return None
 
     def handle_uwaga(self, _e):
         return None


@@ -149,16 +159,24 @@ u"""%(wskazowki)s
     # Lists
     def handle_lista(self, element, attrs={}):
         ltype = element.attrib.get('typ', 'punkt')
     # Lists
     def handle_lista(self, element, attrs={}):
         ltype = element.attrib.get('typ', 'punkt')

+        if not element.findall("punkt"):
+            if ltype == 'czytelnia':
+                return '<p>W przygotowaniu.</p>'
+            else:
+                return None

         if ltype == 'slowniczek':
             surl = element.attrib.get('src', None)
             if surl is None:
                 # print '** missing src on <slowniczek>, setting default'
         if ltype == 'slowniczek':
             surl = element.attrib.get('src', None)
             if surl is None:
                 # print '** missing src on <slowniczek>, setting default'

-                surl = 'http://edukacjamedialna.edu.pl/slowniczek'
+                surl = 'http://edukacjamedialna.edu.pl/lekcje/slowniczek/'

             sxml = None
             if surl:
                 sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string())
             self.options = {'slowniczek': True, 'slowniczek_xml': sxml }
             sxml = None
             if surl:
                 sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string())
             self.options = {'slowniczek': True, 'slowniczek_xml': sxml }

-            return '<div class="slowniczek">', '</div>'
+            pre, post = '<div class="slowniczek">', '</div>'
+            if self.options['wldoc'].book_info.url.slug != 'slowniczek':
+                post += u'<p class="see-more"><a href="%s">Zobacz cały słowniczek.</a></p>' % surl
+            return pre, post

 
         listtag = {'num': 'ol',
                'punkt': 'ul',
 
         listtag = {'num': 'ol',
                'punkt': 'ul',


@@ -268,7 +286,7 @@ u"""%(wskazowki)s
         url = self.options['urlmapper'].url_for_image(slug, ext)
         thumb_url = self.options['urlmapper'].url_for_image(slug, ext, IMAGE_THUMB_WIDTH)
         e = etree.Element("a", attrib={"href": url, "class": "image"})
         url = self.options['urlmapper'].url_for_image(slug, ext)
         thumb_url = self.options['urlmapper'].url_for_image(slug, ext, IMAGE_THUMB_WIDTH)
         e = etree.Element("a", attrib={"href": url, "class": "image"})

-        e.append(etree.Element("img", attrib={"src": url, "alt": alt,
+        e.append(etree.Element("img", attrib={"src": thumb_url, "alt": alt,

                     "width": str(IMAGE_THUMB_WIDTH)}))
         return etree.tostring(e, encoding=unicode), u""
 
                     "width": str(IMAGE_THUMB_WIDTH)}))
         return etree.tostring(e, encoding=unicode), u""
 


@@ -277,7 +295,7 @@ u"""%(wskazowki)s
         if not url:
             print '!! <video> missing url'
             return
         if not url:
             print '!! <video> missing url'
             return

-        m = re.match(r'https?://(?:www.)?youtube.com/watch\?(?:.*&)?v=([^&]+)(?:$|&)', url)
+        m = re.match(r'(?:https?://)?(?:www.)?youtube.com/watch\?(?:.*&)?v=([^&]+)(?:$|&)', url)

         if not m:
             print '!! unknown <video> url scheme:', url
             return
         if not m:
             print '!! unknown <video> url scheme:', url
             return


@@ -361,14 +379,16 @@ class Exercise(EduModule):
     def get_instruction(self):
         if not self.instruction_printed:
             self.instruction_printed = True
     def get_instruction(self):
         if not self.instruction_printed:
             self.instruction_printed = True

-            return u'<span class="instruction">%s</span>' % self.INSTRUCTION
+            if self.INSTRUCTION:
+                return u'<span class="instruction">%s</span>' % self.INSTRUCTION
+            else:
+                return ""

         else:
             return ""
 
 
 
 class Wybor(Exercise):
         else:
             return ""
 
 
 
 class Wybor(Exercise):

-    INSTRUCTION = None

     def handle_cwiczenie(self, element):
         pre, post = super(Wybor, self).handle_cwiczenie(element)
         is_single_choice = True
     def handle_cwiczenie(self, element):
         pre, post = super(Wybor, self).handle_cwiczenie(element)
         is_single_choice = True


@@ -430,7 +450,7 @@ Overrides the returned content default handle_pytanie
             u"""</div>"""
 
     def handle_punkt(self, element):
             u"""</div>"""
 
     def handle_punkt(self, element):

-        return """<li class="question-piece" data-pos="%(rozw)s"/>""" \
+        return """<li class="question-piece" data-pos="%(rozw)s">""" \

             % element.attrib,\
             "</li>"
 
             % element.attrib,\
             "</li>"
 


@@ -441,12 +461,10 @@ class Luki(Exercise):
         return question.xpath(".//luka")
 
     def solution_html(self, piece):
         return question.xpath(".//luka")
 
     def solution_html(self, piece):

+        piece = deepcopy(piece)
+        piece.tail = None

         sub = EduModule()
         return sub.generate(piece)
         sub = EduModule()
         return sub.generate(piece)

-        # print piece.text
-        # return piece.text + ''.join(
-        #     [etree.tostring(n, encoding=unicode)
-        #      for n in piece])

 
     def handle_pytanie(self, element):
         qpre, qpost = super(Luki, self).handle_pytanie(element)
 
     def handle_pytanie(self, element):
         qpre, qpost = super(Luki, self).handle_pytanie(element)


@@ -491,7 +509,6 @@ class Przyporzadkuj(Exercise):
                    u"Kliknij numer odpowiedzi, przeciągnij i upuść w wybranym polu."]
 
     def get_instruction(self):
                    u"Kliknij numer odpowiedzi, przeciągnij i upuść w wybranym polu."]
 
     def get_instruction(self):

-        print self.options['handles']

         if not self.instruction_printed:
             self.instruction_printed = True
             return u'<span class="instruction">%s</span>' % self.INSTRUCTION[self.options['handles'] and 1 or 0]
         if not self.instruction_printed:
             self.instruction_printed = True
             return u'<span class="instruction">%s</span>' % self.INSTRUCTION[self.options['handles'] and 1 or 0]


@@ -540,9 +557,9 @@ class Przyporzadkuj(Exercise):
 
         elif self.options['predicate']:
             if self.options['min']:
 
         elif self.options['predicate']:
             if self.options['min']:

-                placeholders = u'<li class="placeholder"/>' * self.options['min']
+                placeholders = u'<li class="placeholder"></li>' * self.options['min']

             else:
             else:

-                placeholders = u'<li class="placeholder multiple"/>'
+                placeholders = u'<li class="placeholder multiple"></li>'

             return '<li data-predicate="%(nazwa)s">' % element.attrib, '<ul class="subjects">' + placeholders + '</ul></li>'
 
         else:
             return '<li data-predicate="%(nazwa)s">' % element.attrib, '<ul class="subjects">' + placeholders + '</ul></li>'
 
         else: