Workaround for nasty literal HTML inserting issue.

[librarian.git] / librarian / pyhtml.py

diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py
index 33d6d9e..7047cc9 100644 (file)
--- a/librarian/pyhtml.py
+++ b/librarian/pyhtml.py
@@ -9,7 +9,20 @@ 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
+
+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):
 
 class EduModule(Xmill):
     def __init__(self, options=None):


@@ -52,24 +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


@@ -82,7 +93,10 @@ class EduModule(Xmill):
             }
         submill = EduModule(dict(self.options.items() + {'sub_gen': True}.items()))
 
             }
         submill = EduModule(dict(self.options.items() + {'sub_gen': True}.items()))
 

-        opis = submill.generate(element.xpath('opis')[0])
+        if element.xpath('opis'):
+            opis = submill.generate(element.xpath('opis')[0])
+        else:
+            opis = ''

 
         n = element.xpath('wskazowki')
         if n: wskazowki = submill.generate(n[0])
 
         n = element.xpath('wskazowki')
         if n: wskazowki = submill.generate(n[0])


@@ -148,16 +162,24 @@ 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',


@@ -255,12 +277,28 @@ u"""%(wskazowki)s
 
             return u"<a href='%s'>" % def_href, u'%s</a>%s' % (def_err, more_links)
 
 
             return u"<a href='%s'>" % def_href, u'%s</a>%s' % (def_err, more_links)
 

+    def handle_obraz(self, element):
+        name = element.attrib.get('nazwa', '').strip()
+        if not name:
+            print '!! <obraz> missing "nazwa"'
+            return
+        alt = element.attrib.get('alt', '')
+        if not alt:
+            print '** <obraz> missing "alt"'
+        slug, ext = name.rsplit('.', 1)
+        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": thumb_url, "alt": alt,
+                    "width": str(IMAGE_THUMB_WIDTH)}))
+        return etree.tostring(e, encoding=unicode), u""
+

     def handle_video(self, element):
         url = element.attrib.get('url')
         if not url:
             print '!! <video> missing url'
             return
     def handle_video(self, element):
         url = element.attrib.get('url')
         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


@@ -269,11 +307,15 @@ u"""%(wskazowki)s
 
 
 class Exercise(EduModule):
 
 
 class Exercise(EduModule):

+    INSTRUCTION = ""

     def __init__(self, *args, **kw):
         self.question_counter = 0
         super(Exercise, self).__init__(*args, **kw)
     def __init__(self, *args, **kw):
         self.question_counter = 0
         super(Exercise, self).__init__(*args, **kw)

+        self.instruction_printed = False

 
 

-    handle_opis = tag('div', 'description')
+    @tagged('div', 'description')
+    def handle_opis(self, element):
+        return "", self.get_instruction()

 
     def handle_rozw_kom(self, element):
         return u"""<div style="display:none" class="comment">""", u"""</div>"""
 
     def handle_rozw_kom(self, element):
         return u"""<div style="display:none" class="comment">""", u"""</div>"""


@@ -337,6 +379,17 @@ class Exercise(EduModule):
             (add_class, self.question_counter, solution_s + minimum_s), \
             "</div>"
 
             (add_class, self.question_counter, solution_s + minimum_s), \
             "</div>"
 

+    def get_instruction(self):
+        if not self.instruction_printed:
+            self.instruction_printed = True
+            if self.INSTRUCTION:
+                return u'<span class="instruction">%s</span>' % self.INSTRUCTION
+            else:
+                return ""
+        else:
+            return ""
+
+

 
 class Wybor(Exercise):
     def handle_cwiczenie(self, element):
 
 class Wybor(Exercise):
     def handle_cwiczenie(self, element):


@@ -346,13 +399,13 @@ class Wybor(Exercise):
         if not pytania:
             pytania = [element]
         for p in pytania:
         if not pytania:
             pytania = [element]
         for p in pytania:

-            solutions = re.split(r"[, ]+", p.attrib['rozw'])
+            solutions = re.split(r"[, ]+", p.attrib.get('rozw', ''))

             if len(solutions) != 1:
                 is_single_choice = False
                 break
             choices = p.xpath(".//*[@nazwa]")
             uniq = set()
             if len(solutions) != 1:
                 is_single_choice = False
                 break
             choices = p.xpath(".//*[@nazwa]")
             uniq = set()

-            for n in choices: uniq.add(n.attrib['nazwa'])
+            for n in choices: uniq.add(n.attrib.get('nazwa', ''))

             if len(choices) != len(uniq):
                 is_single_choice = False
                 break
             if len(choices) != len(uniq):
                 is_single_choice = False
                 break


@@ -385,6 +438,8 @@ class Wybor(Exercise):
 
 
 class Uporzadkuj(Exercise):
 
 
 class Uporzadkuj(Exercise):

+    INSTRUCTION = u"Kliknij wybraną odpowiedź i przeciągnij w nowe miejsce."
+

     def handle_pytanie(self, element):
         """
 Overrides the returned content default handle_pytanie
     def handle_pytanie(self, element):
         """
 Overrides the returned content default handle_pytanie


@@ -398,22 +453,21 @@ 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>"
 
 
 class Luki(Exercise):
             % element.attrib,\
             "</li>"
 
 
 class Luki(Exercise):

+    INSTRUCTION = u"Przeciągnij odpowiedzi i upuść w wybranym polu."

     def find_pieces(self, question):
         return question.xpath(".//luka")
 
     def solution_html(self, piece):
     def find_pieces(self, question):
         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)


@@ -439,11 +493,13 @@ class Luki(Exercise):
 
 
 class Zastap(Luki):
 
 
 class Zastap(Luki):

+    INSTRUCTION = u"Przeciągnij odpowiedzi i upuść je na słowie lub wyrażeniu, które chcesz zastąpić."
+

     def find_pieces(self, question):
         return question.xpath(".//zastap")
 
     def solution_html(self, piece):
     def find_pieces(self, question):
         return question.xpath(".//zastap")
 
     def solution_html(self, piece):

-        return piece.attrib['rozw']
+        return piece.attrib.get('rozw', '')

 
     def handle_zastap(self, element):
         self.piece_counter += 1
 
     def handle_zastap(self, element):
         self.piece_counter += 1


@@ -452,6 +508,23 @@ class Zastap(Luki):
 
 
 class Przyporzadkuj(Exercise):
 
 
 class Przyporzadkuj(Exercise):

+    INSTRUCTION = [u"Przeciągnij odpowiedzi i upuść w wybranym polu.",
+                   u"Kliknij numer odpowiedzi, przeciągnij i upuść w wybranym polu."]
+
+    def get_instruction(self):
+        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]
+        else:
+            return ""
+
+    def handle_cwiczenie(self, element):
+        pre, post = super(Przyporzadkuj, self).handle_cwiczenie(element)
+        lista_with_handles = element.xpath(".//*[@uchwyty]")
+        if lista_with_handles:
+            self.options = {'handles': True}
+        return pre, post
+

     def handle_pytanie(self, element):
         pre, post = super(Przyporzadkuj, self).handle_pytanie(element)
         minimum = element.attrib.get("min", None)
     def handle_pytanie(self, element):
         pre, post = super(Przyporzadkuj, self).handle_pytanie(element)
         minimum = element.attrib.get("min", None)


@@ -471,7 +544,7 @@ class Przyporzadkuj(Exercise):
                 'data-target': lista.attrib['cel'],
                 'class': 'subject'
             }
                 'data-target': lista.attrib['cel'],
                 'class': 'subject'
             }

-            self.options = {'subject': True, 'handles': 'uchwyty' in lista.attrib}
+            self.options = {'subject': True}

         else:
             attrs = {}
         pre, post = super(Przyporzadkuj, self).handle_lista(lista, attrs)
         else:
             attrs = {}
         pre, post = super(Przyporzadkuj, self).handle_lista(lista, attrs)


@@ -481,16 +554,16 @@ class Przyporzadkuj(Exercise):
         if self.options['subject']:
             self.piece_counter += 1
             if self.options['handles']:
         if self.options['subject']:
             self.piece_counter += 1
             if self.options['handles']:

-                return '<li><span data-solution="%s" data-no="%s" class="question-piece draggable handle add-li">%s</span>' % (element.attrib['rozw'], self.piece_counter, self.piece_counter), '</li>'
+                return '<li><span data-solution="%s" data-no="%s" class="question-piece draggable handle add-li">%s</span>' % (element.attrib.get('rozw', ''), self.piece_counter, self.piece_counter), '</li>'

             else:
             else:

-                return '<li data-solution="%s" data-no="%s" class="question-piece draggable">' % (element.attrib['rozw'], self.piece_counter), '</li>'
+                return '<li data-solution="%s" data-no="%s" class="question-piece draggable">' % (element.attrib.get('rozw', ''), self.piece_counter), '</li>'

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

 
         else:
             return super(Przyporzadkuj, self).handle_punkt(element)
 
         else:
             return super(Przyporzadkuj, self).handle_punkt(element)


@@ -546,6 +619,9 @@ class EduModuleFormat(Format):
     def url_for_material(self, slug, fmt):
         return "%s.%s" % (slug, fmt)
 
     def url_for_material(self, slug, fmt):
         return "%s.%s" % (slug, fmt)
 

+    def url_for_image(self, slug, fmt, width=None):
+        return self.url_for_material(self, slug, fmt)
+

 
 def transform(wldoc, stylesheet='edumed', options=None, flags=None):
     """Transforms the WL document to XHTML.
 
 def transform(wldoc, stylesheet='edumed', options=None, flags=None):
     """Transforms the WL document to XHTML.