X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/a17ace8296df1d91d9f940c80d96a269eba626e5..63cfa40372a9d33c84c0e4b61ed505173c780eae:/librarian/pyhtml.py diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index 106e30b..1043f4f 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -4,45 +4,99 @@ # 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 +from copy import deepcopy + +IMAGE_THUMB_WIDTH = 300 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.activity_last = None + 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_escaped_text_filter(swap_endlines) + + @tagged('div', 'stanza') + def handle_strofa(self, element): + self.options = {'strofa': True} + return "", "" 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 = 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 self.options['urlmapper'].naglowek_to_anchor(naglowek) + + 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 + + def handle_naglowek_rozdzial(self, element): + return_to_top = u"wróć do spisu treści" + pre, post = tag_open_close("h2", id=self.naglowek_to_anchor(element)) + url = self.options['urlmapper'].get_help_url(element) + if url: + post = " ?" % (url,) + post + return return_to_top + pre, post + + def handle_naglowek_podrozdzial(self, element): + self.activity_counter = 0 + return tag('h3')(self, 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_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]) @@ -54,33 +108,55 @@ class EduModule(Xmill): else: pomoce = '' forma = ''.join(element.xpath('forma/text()')) + get_forma_url = self.options['urlmapper'].get_forma_url + forms = [] + for form_name in forma.split(','): + name = form_name.strip() + url = get_forma_url(name) + if url: + forms.append("%s" % (url, name)) + else: + forms.append(name) + forma = ', '.join(forms) + if forma: + forma = '

    Metoda

    %s

    ' % forma czas = ''.join(element.xpath('czas/text()')) + if czas: + czas = '

    Czas

    %s min

    ' % czas counter = self.activity_counter + if element.getnext().tag == 'aktywnosc' or self.activity_last.getnext() == element: + counter_html = """%(counter)d.""" % locals() + else: + counter_html = '' + + self.activity_last = element + return u"""
    -
    %(counter)d. - %(opis)s - %(wskazowki)s +
    + %(counter_html)s + %(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'))) + handle_opis = ifoption(sub_gen=True)(tag('div', 'description')) + handle_wskazowki = ifoption(sub_gen=True)(tag('div', ('hints', 'teacher'))) - @ifoption(activity=False) - @tagged('div', 'materials') + @ifoption(sub_gen=True) + @tagged('section', 'infobox materials') def handle_pomoce(self, _): - return "Pomoce: ", "" + return """

    Pomoce

    """, "" def handle_czas(self, *_): return @@ -89,7 +165,7 @@ class EduModule(Xmill): return def handle_cwiczenie(self, element): - excercise_handlers = { + exercise_handlers = { 'wybor': Wybor, 'uporzadkuj': Uporzadkuj, 'luki': Luki, @@ -99,16 +175,32 @@ class EduModule(Xmill): } 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, attrs={}): ltype = element.attrib.get('typ', 'punkt') + if not element.findall("punkt"): + if ltype == 'czytelnia': + return '

    W przygotowaniu.

    ' + else: + return None if ltype == 'slowniczek': - self.options = {'slowniczek': True} - return '
    ', '
    ' -### robie teraz punkty wyboru + surl = element.attrib.get('src', None) + if surl is None: + # print '** missing src on , setting default' + surl = 'http://edukacjamedialna.edu.pl/lekcje/slowniczek/' + sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string()) + + self.options = {'slowniczek': True, 'slowniczek_xml': sxml } + pre, post = '
    ', '
    ' + if not self.options['wldoc'].book_info.url.slug.startswith('slowniczek'): + post += u'

    Zobacz cały słowniczek.

    ' % surl + return pre, post + listtag = {'num': 'ol', 'punkt': 'ul', 'alfa': 'ul', @@ -128,33 +220,154 @@ 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'] + if "'" in (element.text or ''): + defloc = sxml.xpath("//definiendum[text()=\"%s\"]" % (element.text or '').strip()) + else: + defloc = sxml.xpath("//definiendum[text()='%s']" % (element.text or '').strip()) + 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: '%s'" % element.text + + return u"
    " % self.naglowek_to_anchor(element), 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 - -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) + + def handle_obraz(self, element): + name = element.attrib.get('nazwa', '').strip() + if not name: + print '!! missing "nazwa"' + return + alt = element.attrib.get('alt', '') + if not alt: + print '** 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 '!!
    """ def handle_punkt(self, element): - return """
  • """ \ + return """
  • """ \ % element.attrib,\ "
    • " -class Luki(Excercise): +class Luki(Exercise): + INSTRUCTION = u"Przeciągnij odpowiedzi i upuść w wybranym polu." 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]) + 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) @@ -249,8 +508,7 @@ class Luki(Excercise): 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 @@ -258,11 +516,13 @@ class Luki(Excercise): 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") + 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 @@ -270,19 +530,45 @@ class Zastap(Luki): % self.piece_counter, '' -class Przyporzadkuj(Excercise): +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'%s' % 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) + 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' - } + } + if lista.attrib.get('krotkie'): + self.options = {'short': True} self.options = {'subject': True} else: attrs = {} @@ -293,19 +579,25 @@ class Przyporzadkuj(Excercise): 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.get('rozw', ''), self.piece_counter, self.piece_counter), '
    • ' else: - return '
  • ' % (element.attrib['rozw'], self.piece_counter), '
    • ' + extra_class = "" + if self.options['short']: + extra_class += ' short' + return '
  • ' % (element.attrib.get('rozw', ''), self.piece_counter, extra_class), '
    • ' elif self.options['predicate']: - placeholders = u'
  • ' - return '
  • ' % element.attrib, '
    • ' + if self.options['min']: + placeholders = u'
  • ' * self.options['min'] + else: + placeholders = u'
  • ' + return '
  • ' % element.attrib.get('nazwa', ''), '
    • ' else: return super(Przyporzadkuj, self).handle_punkt(element) -class PrawdaFalsz(Excercise): +class PrawdaFalsz(Exercise): def handle_punkt(self, element): if 'rozw' in element.attrib: return u'''
  • @@ -317,15 +609,66 @@ class PrawdaFalsz(Excercise): return super(PrawdaFalsz, self).handle_punkt(element) -def transform(wldoc, stylesheet='edumed', options=None, flags=None): +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 url_for_image(self, slug, fmt, width=None): + return self.url_for_material(self, slug, fmt) + + def text_to_anchor(self, text): + return re.sub(r" +", " ", text) + + def naglowek_to_anchor(self, naglowek): + return self.text_to_anchor(naglowek.text.strip()) + + def get_forma_url(self, forma): + return None + + def get_help_url(self, naglowek): + return None + + +def transform(wldoc, stylesheet='edumed', options=None, flags=None, verbose=None): """Transforms the WL document to XHTML. If output_filename is None, returns an XML, 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()