X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/b10cdf123648beb76120194d7f9bb69fc8433ede..a36b71e91ec260eae71f133f450fe4de80974461:/librarian/pyhtml.py diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index a6f6686..68ae384 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -15,7 +15,20 @@ 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""" @@ -34,25 +47,29 @@ class EduModule(Xmill): 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 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"] = "#" + naglowek.text + a.attrib["href"] = "#" + self.naglowek_to_anchor(naglowek) a.text = naglowek.text atxt = etree.tostring(a, encoding=unicode) toc.append("
  • %s
    • " % atxt) toc = "" % "".join(toc) - return "

    Lekcja: ", "

    " + toc + add_header = "Lekcja: " if self.options['wldoc'].book_info.type in ('course', 'synthetic') else '' + return "

    %s" % add_header, "

    " + toc @tagged("h2") def handle_naglowek_rozdzial(self, element): - return "", "".join(tag_open_close("a", name=element.text)) + return "", "".join(tag_open_close("a", name=self.naglowek_to_anchor(element))) def handle_uwaga(self, _e): return None @@ -65,7 +82,10 @@ class EduModule(Xmill): } 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]) @@ -123,6 +143,8 @@ u"""%(wskazowki)s } 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) @@ -130,7 +152,10 @@ u"""%(wskazowki)s def handle_lista(self, element, attrs={}): ltype = element.attrib.get('typ', 'punkt') if ltype == 'slowniczek': - surl = element.attrib.get('href', None) + surl = element.attrib.get('src', None) + if surl is None: + # print '** missing src on , setting default' + surl = 'http://edukacjamedialna.edu.pl/slowniczek' sxml = None if surl: sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string()) @@ -160,16 +185,21 @@ u"""%(wskazowki)s nxt = element.getnext() definiens_s = '' + if not element.text: + print "!! Empty " + return None + # 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'] - 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) + else: + print '!! Missing definiendum in source:', element.text return u"
    ", u"
    " + definiens_s @@ -200,8 +230,9 @@ u"""%(wskazowki)s return tag('a', href=element.attrib['url'])(self, element) elif 'material' in element.attrib: material_err = u' [BRAKUJĄCY MATERIAŁ]' + slug = element.attrib['material'] make_url = lambda f: self.options['urlmapper'] \ - .url_for_material(element.attrib['material'], f) + .url_for_material(slug, f) if 'format' in element.attrib: formats = re.split(r"[, ]+", @@ -209,18 +240,20 @@ u"""%(wskazowki)s else: formats = [None] + formats = self.options['urlmapper'].materials(slug) + try: - def_href = make_url(formats[0]) + def_href = make_url(formats[0][0]) def_err = u"" - except self.options['urlmapper'].MaterialNotFound: + except (IndexError, self.options['urlmapper'].MaterialNotFound): def_err = material_err def_href = u"" fmt_links = [] for f in formats[1:]: try: - fmt_links.append(u'%s' % (make_url(f), f.upper())) + fmt_links.append(u'%s' % (make_url(f[0]), f[0].upper())) except self.options['urlmapper'].MaterialNotFound: - fmt_links.append(u'%s%s' % (f.upper(), material_err)) + fmt_links.append(u'%s%s' % (f[0].upper(), material_err)) more_links = u' (%s)' % u', '.join(fmt_links) if fmt_links else u'' return u"" % def_href, u'%s%s' % (def_err, more_links) @@ -244,7 +277,16 @@ class Exercise(EduModule): pre = u"""
    -""" % element.attrib +

    Zadanie %(exercies_counter)d

    +
    + + + + + +
    + +""" % {'exercies_counter': self.options['exercise_counter'], 'typ': element.attrib['typ']} post = u"""
    @@ -432,14 +474,14 @@ class Przyporzadkuj(Exercise): if self.options['handles']: return '
  • %s' % (element.attrib['rozw'], self.piece_counter, self.piece_counter), '
    • ' else: - return '
  • ' % (element.attrib['rozw'], self.piece_counter), '
    • ' + return '
  • ' % (element.attrib.get('rozw', ''), self.piece_counter), '
    • ' elif self.options['predicate']: if self.options['min']: placeholders = u'
  • ' * self.options['min'] else: placeholders = u'
  • ' - return '
  • ' % element.attrib, '
      ' + placeholders + '
    • ' + return '
  • ' % element.attrib.get('nazwa', ''), '
      ' + placeholders + '
    • ' else: return super(Przyporzadkuj, self).handle_punkt(element) @@ -458,7 +500,7 @@ class PrawdaFalsz(Exercise): class EduModuleFormat(Format): - DEFAULT_MATERIAL_FORMAT = 'odt' + PRIMARY_MATERIAL_FORMATS = ('pdf', 'odt') class MaterialNotFound(BaseException): pass @@ -467,19 +509,33 @@ class EduModuleFormat(Format): 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')) - def url_for_material(self, slug, fmt=None): - if fmt is None: - fmt = self.DEFAULT_MATERIAL_FORMAT - # 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: + pass # 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 transform(wldoc, stylesheet='edumed', options=None, flags=None):