X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/723bbca1bfd747722ee2ccd1ae1b262c497144de..a36b71e91ec260eae71f133f450fe4de80974461:/librarian/pyhtml.py diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index bed9798..68ae384 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -5,18 +5,30 @@ # 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 - class EduModule(Xmill): def __init__(self, options=None): super(EduModule, self).__init__(options) self.activity_counter = 0 - self.register_text_filter(lambda t: functions.substitute_entities(None, t)) + 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""" @@ -29,14 +41,38 @@ 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('h3') - handle_naglowek_osoba = handle_naglowek_podrozdzial = tag('h4') + 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"] = "#" + self.naglowek_to_anchor(naglowek) + a.text = naglowek.text + atxt = etree.tostring(a, encoding=unicode) + toc.append("
  • %s
    • " % atxt) + toc = "" % "".join(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=self.naglowek_to_anchor(element))) + + def handle_uwaga(self, _e): + return None def handle_aktywnosc(self, element): self.activity_counter += 1 @@ -46,7 +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]) @@ -65,15 +104,16 @@ class EduModule(Xmill): return u"""
    -
    %(counter)d. - %(opis)s - %(wskazowki)s +
    + %(counter)d. + %(opis)s""" % locals(), \ +u"""%(wskazowki)s
    -
    -

    Czas: %(czas)s min

    -

    Forma: %(forma)s

    +
    +
    """ % locals() @@ -82,9 +122,9 @@ class EduModule(Xmill): handle_wskazowki = ifoption(sub_gen=True)(tag('div', ('hints', 'teacher'))) @ifoption(sub_gen=True) - @tagged('div', 'materials') + @tagged('section', 'infobox materials') def handle_pomoce(self, _): - return "Pomoce: ", "" + return """

    Pomoce

    """, "" def handle_czas(self, *_): return @@ -103,6 +143,8 @@ class EduModule(Xmill): } 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) @@ -110,7 +152,10 @@ class EduModule(Xmill): 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()) @@ -140,23 +185,27 @@ class EduModule(Xmill): 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 def handle_definiens(self, element): return u"
    ", u"
    " - def handle_podpis(self, element): return u"""
    """, u"
    " @@ -177,13 +226,37 @@ class EduModule(Xmill): return def handle_link(self, element): - if 'material' in element.attrib: - formats = re.split(r"[, ]+", element.attrib['format']) + if 'url' in element.attrib: + 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(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: - fmt_links.append(u'%s' % (self.options['urlmapper'].url_for_material(element.attrib['material'], f), f.upper())) + for f in formats[1:]: + try: + fmt_links.append(u'%s' % (make_url(f[0]), f[0].upper())) + except self.options['urlmapper'].MaterialNotFound: + 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"", u' (%s)' % u' '.join(fmt_links) + return u"" % def_href, u'%s%s' % (def_err, more_links) class Exercise(EduModule): @@ -191,6 +264,8 @@ class Exercise(EduModule): self.question_counter = 0 super(Exercise, self).__init__(*args, **kw) + handle_opis = tag('div', 'description') + def handle_rozw_kom(self, element): return u"""""" @@ -202,7 +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"""
    @@ -249,11 +333,21 @@ class Wybor(Exercise): def handle_cwiczenie(self, element): pre, post = super(Wybor, self).handle_cwiczenie(element) is_single_choice = True - for p in element.xpath(".//pytanie"): + pytania = element.xpath(".//pytanie") + 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 + choices = p.xpath(".//*[@nazwa]") + uniq = set() + for n in choices: uniq.add(n.attrib['nazwa']) + if len(choices) != len(uniq): + is_single_choice = False + break + self.options = {'single': is_single_choice} return pre, post @@ -302,12 +396,15 @@ Overrides the returned content default handle_pytanie class Luki(Exercise): def find_pieces(self, question): - return question.xpath("//luka") + return question.xpath(".//luka") def solution_html(self, piece): - return piece.text + ''.join( - [etree.tostring(n, encoding=unicode) - for n in 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) @@ -325,8 +422,7 @@ class Luki(Exercise): return qpre, qpost def handle_opis(self, element): - pre, post = super(Luki, self).handle_opis(element) - return pre, self.words_html + post + return '', self.words_html def handle_luka(self, element): self.piece_counter += 1 @@ -335,7 +431,7 @@ class Luki(Exercise): class Zastap(Luki): def find_pieces(self, question): - return question.xpath("//zastap") + return question.xpath(".//zastap") def solution_html(self, piece): return piece.attrib['rozw'] @@ -376,16 +472,16 @@ class Przyporzadkuj(Exercise): if self.options['subject']: self.piece_counter += 1 if self.options['handles']: - return '
  • %s' % (element.attrib['rozw'], self.piece_counter, self.piece_counter), '
    • ' + 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) @@ -404,21 +500,42 @@ class PrawdaFalsz(Exercise): 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): - 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): - # 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):