slowniczek link

[librarian.git] / librarian / pyhtml.py

diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py
index 56b472c..b4d8557 100644 (file)
--- a/librarian/pyhtml.py
+++ b/librarian/pyhtml.py
@@ -5,20 +5,32 @@
 #
 from lxml import etree
 from librarian import IOFile, RDFNS, DCNS, Format
 #
 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 librarian import functions
 import re
 import random

+from copy import deepcopy

 
 

-
-DEFAULT_MATERIAL_FORMAT = 'odt'
-
+IMAGE_THUMB_WIDTH = 300

 
 class EduModule(Xmill):
     def __init__(self, options=None):
         super(EduModule, self).__init__(options)
         self.activity_counter = 0
 
 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", "<br/>\n")
+            return txt

         self.register_text_filter(functions.substitute_entities)
         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"""
 
     def handle_powiesc(self, element):
         return u"""


@@ -31,18 +43,37 @@ class EduModule(Xmill):
 """, u"</div>"
 
     handle_autor_utworu = tag("span", "author")
 """, u"</div>"
 
     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_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_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')
 
     handle_wyroznienie = tag('em')
     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")
+            a.attrib["href"] = "#" + self.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 ''
+        return "<h1 class='title'><a name='top'></a>%s" % add_header, "</h1>" + toc
+
+    def handle_naglowek_rozdzial(self, element):
+        return_to_top = u"<a href='#top' class='top-link'>wróć do spisu treści</a>"
+        anchor = "".join(tag_open_close("a", name=self.naglowek_to_anchor(element)))
+        return return_to_top + "<h2>", anchor + "</h2>"
+

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


@@ -75,8 +106,8 @@ class EduModule(Xmill):
 <div class="activity">
  <div class="text">
   <span class="act_counter">%(counter)d.</span>
 <div class="activity">
  <div class="text">
   <span class="act_counter">%(counter)d.</span>

-  %(opis)s
-  %(wskazowki)s
+  %(opis)s""" % locals(), \
+u"""%(wskazowki)s

  </div>
  <aside class="info">
   <section class="infobox time"><h1>Czas</h1><p>%(czas)s min</p></section>
  </div>
  <aside class="info">
   <section class="infobox time"><h1>Czas</h1><p>%(czas)s min</p></section>


@@ -112,19 +143,32 @@ class EduModule(Xmill):
             }
 
         typ = element.attrib['typ']
             }
 
         typ = element.attrib['typ']

+        self.exercise_counter += 1
+        self.options = {'exercise_counter': self.exercise_counter}

         handler = exercise_handlers[typ](self.options)
         return handler.generate(element)
 
     # Lists
     def handle_lista(self, element, attrs={}):
         ltype = element.attrib.get('typ', 'punkt')
         handler = exercise_handlers[typ](self.options)
         return handler.generate(element)
 
     # 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':
         if ltype == 'slowniczek':

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


@@ -149,16 +193,21 @@ class EduModule(Xmill):
         nxt = element.getnext()
         definiens_s = ''
 
         nxt = element.getnext()
         definiens_s = ''
 

+        if not element.text:
+            print "!! Empty <definiendum/>"
+            return None
+

         # let's pull definiens from another document
         # let's pull definiens from another document

-        if self.options['slowniczek_xml'] and (not nxt or nxt.tag != 'definiens'):
+        if self.options['slowniczek_xml'] is not None and (nxt is None or nxt.tag != 'definiens'):

             sxml = self.options['slowniczek_xml']
             sxml = self.options['slowniczek_xml']

-            assert element.text != ''

             defloc = sxml.xpath("//definiendum[text()='%s']" % element.text)
             if defloc:
                 definiens = defloc[0].getnext()
                 if definiens.tag == 'definiens':
                     subgen = EduModule(self.options)
                     definiens_s = subgen.generate(definiens)
             defloc = sxml.xpath("//definiendum[text()='%s']" % element.text)
             if defloc:
                 definiens = defloc[0].getnext()
                 if definiens.tag == 'definiens':
                     subgen = EduModule(self.options)
                     definiens_s = subgen.generate(definiens)

+            else:
+                print '!! Missing definiendum in source:', element.text

 
         return u"<dt>", u"</dt>" + definiens_s
 
 
         return u"<dt>", u"</dt>" + definiens_s
 


@@ -188,25 +237,74 @@ class EduModule(Xmill):
         if 'url' in element.attrib:
             return tag('a', href=element.attrib['url'])(self, element)
         elif 'material' in element.attrib:
         if 'url' in element.attrib:
             return tag('a', href=element.attrib['url'])(self, element)
         elif 'material' in element.attrib:

-            formats = re.split(r"[, ]+",
-                               element.attrib.get('format', DEFAULT_MATERIAL_FORMAT))
+            material_err = u' [BRAKUJĄCY MATERIAŁ]'
+            slug = element.attrib['material']

             make_url = lambda f: self.options['urlmapper'] \
             make_url = lambda f: self.options['urlmapper'] \

-              .url_for_material(element.attrib['material'], f)
-            def_href = make_url(formats[0])
+              .url_for_material(slug, f)
+
+            if 'format' in element.attrib:
+                formats = re.split(r"[, ]+",
+                               element.attrib['format'])
+            else:
+                formats = [None]
+
+            formats = self.options['urlmapper'].materials(slug)
+
+            try:
+                def_href = make_url(formats[0][0])
+                def_err = u""
+            except (IndexError, self.options['urlmapper'].MaterialNotFound):
+                def_err = material_err
+                def_href = u""

             fmt_links = []
             for f in formats[1:]:
             fmt_links = []
             for f in formats[1:]:

-                fmt_links.append(u'<a href="%s">%s</a>' % (make_url(f), f.upper()))
+                try:
+                    fmt_links.append(u'<a href="%s">%s</a>' % (make_url(f[0]), f[0].upper()))
+                except self.options['urlmapper'].MaterialNotFound:
+                    fmt_links.append(u'<a>%s%s</a>' % (f[0].upper(), material_err))

             more_links = u' (%s)' % u', '.join(fmt_links) if fmt_links else u''
 
             more_links = u' (%s)' % u', '.join(fmt_links) if fmt_links else u''
 

-            return u"<a href='%s'>" % def_href, u'</a>%s' % 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
+        m = re.match(r'(?:https?://)?(?:www.)?youtube.com/watch\?(?:.*&)?v=([^&]+)(?:$|&)', url)
+        if not m:
+            print '!! unknown <video> url scheme:', url
+            return
+        return """<iframe width="630" height="384" src="http://www.youtube.com/embed/%s"
+            frameborder="0" allowfullscreen></iframe>""" % m.group(1), ""

 
 
 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>"""


@@ -219,7 +317,16 @@ class Exercise(EduModule):
         pre = u"""
 <div class="exercise %(typ)s" data-type="%(typ)s">
 <form action="#" method="POST">
         pre = u"""
 <div class="exercise %(typ)s" data-type="%(typ)s">
 <form action="#" method="POST">

-""" % element.attrib
+<h3>Zadanie %(exercies_counter)d</h3>
+<div class="buttons">
+<span class="message"></span>
+<input type="button" class="check" value="sprawdź"/>
+<input type="button" class="retry" style="display:none" value="spróbuj ponownie"/>
+<input type="button" class="solutions" value="pokaż rozwiązanie"/>
+<input type="button" class="reset" value="reset"/>
+</div>
+
+""" % {'exercies_counter': self.options['exercise_counter'], 'typ': element.attrib['typ']}

         post = u"""
 <div class="buttons">
 <span class="message"></span>
         post = u"""
 <div class="buttons">
 <span class="message"></span>


@@ -261,20 +368,31 @@ 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):
         pre, post = super(Wybor, self).handle_cwiczenie(element)
         is_single_choice = True
         pytania = element.xpath(".//pytanie")
 
 class Wybor(Exercise):
     def handle_cwiczenie(self, element):
         pre, post = super(Wybor, self).handle_cwiczenie(element)
         is_single_choice = True
         pytania = element.xpath(".//pytanie")

-        if not pytania: 
+        if not pytania:

             pytania = [element]
         for p in pytania:
             solutions = re.split(r"[, ]+", p.attrib['rozw'])
             if len(solutions) != 1:
                 is_single_choice = False
                 break
             pytania = [element]
         for p in pytania:
             solutions = re.split(r"[, ]+", p.attrib['rozw'])
             if len(solutions) != 1:
                 is_single_choice = False
                 break

-            choices = element.xpath(".//*[@nazwa]")
+            choices = p.xpath(".//*[@nazwa]")

             uniq = set()
             for n in choices: uniq.add(n.attrib['nazwa'])
             if len(choices) != len(uniq):
             uniq = set()
             for n in choices: uniq.add(n.attrib['nazwa'])
             if len(choices) != len(uniq):


@@ -309,6 +427,8 @@ 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


@@ -328,13 +448,15 @@ Overrides the returned content default handle_pytanie
 
 
 class Luki(Exercise):
 
 
 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):

-        return piece.text + ''.join(
-            [etree.tostring(n, encoding=unicode)
-             for n in piece])
+        piece = deepcopy(piece)
+        piece.tail = None
+        sub = EduModule()
+        return sub.generate(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)


@@ -360,6 +482,8 @@ 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 find_pieces(self, question):
         return question.xpath(".//zastap")
 


@@ -373,6 +497,23 @@ 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)


@@ -392,7 +533,7 @@ 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)


@@ -430,21 +571,45 @@ class PrawdaFalsz(Exercise):
 
 
 class EduModuleFormat(Format):
 
 
 class EduModuleFormat(Format):

+    PRIMARY_MATERIAL_FORMATS = ('pdf', 'odt')
+
+    class MaterialNotFound(BaseException):
+        pass
+

     def __init__(self, wldoc, **kwargs):
         super(EduModuleFormat, self).__init__(wldoc, **kwargs)
 
     def build(self):
     def __init__(self, wldoc, **kwargs):
         super(EduModuleFormat, self).__init__(wldoc, **kwargs)
 
     def build(self):

-        edumod = EduModule({'provider': self.wldoc.provider, 'urlmapper': self})
+        # Sort materials by slug.
+        self.materials_by_slug = {}
+        for name, att in self.wldoc.source.attachments.items():
+            parts = name.rsplit('.', 1)
+            if len(parts) == 1:
+                continue
+            slug, ext = parts
+            if slug not in self.materials_by_slug:
+                self.materials_by_slug[slug] = {}
+            self.materials_by_slug[slug][ext] = att
+
+        edumod = EduModule({'provider': self.wldoc.provider, 'urlmapper': self, 'wldoc': self.wldoc})

 
         html = edumod.generate(self.wldoc.edoc.getroot())
 
         return IOFile.from_string(html.encode('utf-8'))
 
 
         html = edumod.generate(self.wldoc.edoc.getroot())
 
         return IOFile.from_string(html.encode('utf-8'))
 

-    def url_for_material(self, slug, fmt=None):
-        # No briliant idea for an API here.
-        if fmt:
-            return "%s.%s" % (slug, fmt)
-        return slug
+    def materials(self, slug):
+        """Returns a list of pairs: (ext, iofile)."""
+        order = dict(reversed(k) for k in enumerate(self.PRIMARY_MATERIAL_FORMATS))
+        mats = self.materials_by_slug.get(slug, {}).items()
+        if not mats:
+            print "!! Material missing: '%s'" % slug
+        return sorted(mats, key=lambda (x, y): order.get(x, x))
+
+    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):
 
 
 def transform(wldoc, stylesheet='edumed', options=None, flags=None):