X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/a14ba61c2bdad8d7dd6262e3afec8ba8f6a47416..076474d2a928649c934b4bb12031d39cdea2c77d:/librarian/pyhtml.py diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index f362715..6db1701 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -4,67 +4,88 @@ # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # from lxml import etree -from librarian import OutputFile, RDFNS, DCNS -from xmlutils import Xmill, tag, tagged, ifoption - +from librarian import IOFile, RDFNS, DCNS, Format +from xmlutils import Xmill, tag, tagged, ifoption, tag_open_close +from librarian import functions +import re +import random + class EduModule(Xmill): - def __init__(self, *args): - super(EduModule, self).__init__(*args) + 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_utwor(self, element): -# v = {} -# # from pdb import *; set_trace() -# v['title'] = element.xpath('//dc:title/text()', namespaces={'dc':DCNS.uri})[0] -# return u""" -# -# -# -# -# %(title)s -# -# -# -# -# -# """ % v, u""" -# -# -# """ - - def handle_powiesc(self, element): return u"""
- + """, 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 self.options = { - 'activity': True, - 'activity_counter': self.activity_counter + 'activity': True, + 'activity_counter': self.activity_counter, } - submill = EduModule() + 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]) @@ -83,56 +104,76 @@ 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() - handle_opis = ifoption(activity=False)(tag('div', 'description')) - handle_wskazowki = ifoption(activity=False)(tag('div', ('hints', 'teacher'))) - - @ifoption(activity=False) - @tagged('div', 'materials') + handle_opis = ifoption(sub_gen=True)(tag('div', 'description')) + handle_wskazowki = ifoption(sub_gen=True)(tag('div', ('hints', 'teacher'))) + + @ifoption(sub_gen=True) + @tagged('section', 'infobox materials') def handle_pomoce(self, _): - return "Pomoce: ", "" - + return """

    Pomoce

    """, "" + def handle_czas(self, *_): return def handle_forma(self, *_): return - + def handle_cwiczenie(self, element): - excercise_handlers = { + exercise_handlers = { 'wybor': Wybor, - 'uporzadkuj': Uporzadkuj + 'uporzadkuj': Uporzadkuj, + 'luki': Luki, + 'zastap': Zastap, + 'przyporzadkuj': Przyporzadkuj, + 'prawdafalsz': PrawdaFalsz } - + typ = element.attrib['typ'] - handler = excercise_handlers[typ](self.options) + 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): + def handle_lista(self, element, attrs={}): ltype = element.attrib.get('typ', 'punkt') if ltype == 'slowniczek': - self.options = {'slowniczek': True} + 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()) + self.options = {'slowniczek': True, 'slowniczek_xml': sxml } return '
    ', '
    ' -### robie teraz punkty wyboru - listtag = {'num': 'ol', - 'punkt': 'ul', - 'alfa': 'ul', + + listtag = {'num': 'ol', + 'punkt': 'ul', + 'alfa': 'ul', 'czytelnia': 'ul'}[ltype] - return '<%s class="lista %s">' % (listtag, ltype), '' % listtag + classes = attrs.get('class', '') + if classes: del attrs['class'] + + attrs_s = ' '.join(['%s="%s"' % kv for kv in attrs.items()]) + if attrs_s: attrs_s = ' ' + attrs_s + + return '<%s class="lista %s %s"%s>' % (listtag, ltype, classes, attrs_s), '' % listtag def handle_punkt(self, element): if self.options['slowniczek']: @@ -140,78 +181,363 @@ class EduModule(Xmill): else: return '
  • ', '
  • ' + def handle_definiendum(self, element): + 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'] is not None and (nxt is None or nxt.tag != 'definiens'): + sxml = self.options['slowniczek_xml'] + 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"
    " + + def handle_tabela(self, element): + has_frames = int(element.attrib.get("ramki", "0")) + if has_frames: frames_c = "framed" + else: frames_c = "" + return u"""""" % frames_c, u"
    " + + def handle_wiersz(self, element): + return u"", u"" + + def handle_kol(self, element): + return u"", u"" + def handle_rdf__RDF(self, _): # ustal w opcjach rzeczy :D - return - + return -class Excercise(EduModule): + def handle_link(self, element): + 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[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"" % def_href, u'%s%s' % (def_err, more_links) + + +class Exercise(EduModule): def __init__(self, *args, **kw): self.question_counter = 0 - super(Excercise, self).__init__(*args, **kw) + super(Exercise, self).__init__(*args, **kw) + + handle_opis = tag('div', 'description') + + def handle_rozw_kom(self, element): + return u"""""" def handle_cwiczenie(self, element): - self.options = {'excercise': element.attrib['typ']} + self.options = {'exercise': element.attrib['typ']} self.question_counter = 0 self.piece_counter = 0 - return u""" -
    + pre = u""" +
    -""" % element.attrib, \ -u""" +

    Zadanie %(exercies_counter)d

    + + +
    + +""" % {'exercies_counter': self.options['exercise_counter'], 'typ': element.attrib['typ']} + post = u""" +
    + + + + +
    """ - + # Add a single tag if it's not there + if not element.xpath(".//pytanie"): + qpre, qpost = self.handle_pytanie(element) + pre = pre + qpre + post = qpost + post + return pre, post + def handle_pytanie(self, element): + """This will handle element, when there is no + """ + add_class = "" self.question_counter += 1 self.piece_counter = 0 solution = element.attrib.get('rozw', None) if solution: solution_s = ' data-solution="%s"' % solution else: solution_s = '' - return '
    ' %\ - (self.question_counter, solution_s), \ - "
    " + handles = element.attrib.get('uchwyty', None) + if handles: + add_class += ' handles handles-%s' % handles + self.options = {'handles': handles} + minimum = element.attrib.get('min', None) + if minimum: minimum_s = ' data-minimum="%d"' % int(minimum) + else: minimum_s = '' + + return '
    ' %\ + (add_class, self.question_counter, solution_s + minimum_s), \ + "
    " + + +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: + 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 -class Wybor(Excercise): def handle_punkt(self, element): - if self.options['excercise'] and element.attrib.get('nazwa', None): + if self.options['exercise'] and element.attrib.get('nazwa', None): qc = self.question_counter self.piece_counter += 1 no = self.piece_counter - - return u""" -
  • -""" % locals(), u"
  • " + eid = "q%(qc)d_%(no)d" % locals() + aname = element.attrib.get('nazwa', None) + if self.options['single']: + return u""" +
  • + +
  • " + else: + return u""" +
  • + +
  • " else: return super(Wybor, self).handle_punkt(element) -class Uporzadkuj(Excercise): - def handle_cwiczenie(self, element): - pre, post = super(Uporzadkuj, self).handle_cwiczenie(element) +class Uporzadkuj(Exercise): + def handle_pytanie(self, element): + """ +Overrides the returned content default handle_pytanie + """ + # we ignore the result, returning our own + super(Uporzadkuj, self).handle_pytanie(element) order_items = element.xpath(".//punkt/@rozw") - import pdb - if order_items == []: pdb.set_trace() - return pre + u"""
    """ % \ - ','.join(order_items), \ - u"""
    """ + post - + return u"""
    """ % \ + (','.join(order_items), self.question_counter), \ + u"""
    """ + def handle_punkt(self, element): - return """
  • """ % element.attrib,\ + return """
  • """ \ + % element.attrib,\ "
  • " +class Luki(Exercise): + def find_pieces(self, question): + return question.xpath(".//luka") + + def solution_html(self, 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) + + luki = list(enumerate(self.find_pieces(element))) + luki_html = "" + i = 0 + random.shuffle(luki) + for (i, luka) in luki: + i += 1 + luka_html = self.solution_html(luka) + luki_html += u'%s' % (i, luka_html) + self.words_html = '
    %s
    ' % luki_html + + return qpre, qpost + + def handle_opis(self, element): + return '', self.words_html + + def handle_luka(self, element): + self.piece_counter += 1 + return '' % self.piece_counter + + +class Zastap(Luki): + def find_pieces(self, question): + return question.xpath(".//zastap") + + def solution_html(self, piece): + return piece.attrib['rozw'] + + def handle_zastap(self, element): + self.piece_counter += 1 + return '' \ + % self.piece_counter, '' + + +class Przyporzadkuj(Exercise): + def handle_pytanie(self, element): + pre, post = super(Przyporzadkuj, self).handle_pytanie(element) + minimum = element.attrib.get("min", None) + if minimum: + self.options = {"min": int(minimum)} + return pre, post + + def handle_lista(self, lista): + if 'nazwa' in lista.attrib: + attrs = { + 'data-name': lista.attrib['nazwa'], + 'class': 'predicate' + } + self.options = {'predicate': True} + elif 'cel' in lista.attrib: + attrs = { + 'data-target': lista.attrib['cel'], + 'class': 'subject' + } + self.options = {'subject': True, 'handles': 'uchwyty' in lista.attrib} + else: + attrs = {} + pre, post = super(Przyporzadkuj, self).handle_lista(lista, attrs) + return pre, post + '
    ' + + def handle_punkt(self, element): + if self.options['subject']: + self.piece_counter += 1 + if self.options['handles']: + return '
  • %s' % (element.attrib['rozw'], self.piece_counter, self.piece_counter), '
  • ' + else: + return '
  • ' % (element.attrib['rozw'], self.piece_counter), '
  • ' + + elif self.options['predicate']: + if self.options['min']: + placeholders = u'
  • ' * self.options['min'] + else: + placeholders = u'
  • ' + return '
  • ' % element.attrib, '
      ' + placeholders + '
  • ' + + else: + return super(Przyporzadkuj, self).handle_punkt(element) + + +class PrawdaFalsz(Exercise): + def handle_punkt(self, element): + if 'rozw' in element.attrib: + return u'''
  • + + Prawda + Fałsz + ''' % {'prawda': 'true', 'falsz': 'false'}[element.attrib['rozw']], '
  • ' + else: + return super(PrawdaFalsz, self).handle_punkt(element) + + +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): + # 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 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 transform(wldoc, stylesheet='edumed', options=None, flags=None): """Transforms the WL document to XHTML. @@ -219,9 +545,5 @@ def transform(wldoc, stylesheet='edumed', options=None, flags=None): otherwise returns True if file has been written,False if it hasn't. File won't be written if it has no content. """ - - edumod = EduModule(options) -# from pdb import set_trace; set_trace() - html = edumod.generate(wldoc.edoc.getroot()) - - return OutputFile.from_string(html.encode('utf-8')) + edumodfor = EduModuleFormat(wldoc) + return edumodfor.build()