X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/f7260ec22a6bcb39fe800ac21f335c2c903a2072..3b0b98465bc1862306b05bb8305a1abbf40ca310:/librarian/pyhtml.py?ds=inline diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index b4d8557..163d11c 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -4,7 +4,7 @@ # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # from lxml import etree -from librarian import IOFile, RDFNS, DCNS, Format +from librarian import IOFile, Format from xmlutils import Xmill, tag, tagged, ifoption, tag_open_close from librarian import functions import re @@ -13,10 +13,12 @@ from copy import deepcopy IMAGE_THUMB_WIDTH = 300 + class EduModule(Xmill): def __init__(self, options=None): super(EduModule, self).__init__(options) self.activity_counter = 0 + self.activity_last = None self.exercise_counter = 0 # text filters @@ -25,7 +27,7 @@ class EduModule(Xmill): txt = txt.replace("/\n", "
\n") return txt self.register_text_filter(functions.substitute_entities) - self.register_text_filter(swap_endlines) + self.register_escaped_text_filter(swap_endlines) @tagged('div', 'stanza') def handle_strofa(self, element): @@ -47,7 +49,7 @@ class EduModule(Xmill): handle_podtytul = tag("span", "subtitle") handle_naglowek_akt = handle_naglowek_czesc = handle_srodtytul = tag("h2") handle_naglowek_scena = tag('h2') - handle_naglowek_osoba = handle_naglowek_podrozdzial = tag('h3') + handle_naglowek_osoba = tag('h3') handle_akap = handle_akap_dialog = handle_akap_cd = tag('p', 'paragraph') handle_wyroznienie = tag('em') @@ -55,7 +57,7 @@ class EduModule(Xmill): handle_slowo_obce = tag('em', 'foreign') def naglowek_to_anchor(self, naglowek): - return re.sub(r" +", " ", naglowek.text.strip()) + return self.options['urlmapper'].naglowek_to_anchor(naglowek) def handle_nazwa_utworu(self, element): toc = [] @@ -67,12 +69,19 @@ class EduModule(Xmill): 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 + return "

    %s" % add_header, "

    " + toc def handle_naglowek_rozdzial(self, element): return_to_top = u"wróć do spisu treści" - anchor = "".join(tag_open_close("a", name=self.naglowek_to_anchor(element))) - return return_to_top + "

    ", anchor + "

    " + 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 @@ -85,38 +94,66 @@ 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]) - - else: wskazowki = '' + if n: + wskazowki = submill.generate(n[0]) + else: + wskazowki = '' n = element.xpath('pomoce') - if n: pomoce = submill.generate(n[0]) - else: pomoce = '' + if n: + pomoce = submill.generate(n[0]) + 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 - return u""" + if element.getnext().tag == 'aktywnosc' or (self.activity_last and self.activity_last.getnext() == element): + counter_html = """%(counter)d.""" % {'counter': counter} + else: + counter_html = '' + + self.activity_last = element + + return ( + u"""
    -
    - %(counter)d. - %(opis)s""" % locals(), \ -u"""%(wskazowki)s -
    - -
    +
    + %(counter_html)s + %(opis)s""" % {'counter_html': counter_html, 'opis': opis}, + u"""%(wskazowki)s +
    + +
    -""" % locals() +""" % {'wskazowki': wskazowki, 'czas': czas, 'forma': forma, 'pomoce': pomoce}) handle_opis = ifoption(sub_gen=True)(tag('div', 'description')) handle_wskazowki = ifoption(sub_gen=True)(tag('div', ('hints', 'teacher'))) @@ -149,7 +186,9 @@ u"""%(wskazowki)s return handler.generate(element) # Lists - def handle_lista(self, element, attrs={}): + def handle_lista(self, element, attrs=None): + if attrs is None: + attrs = {} ltype = element.attrib.get('typ', 'punkt') if not element.findall("punkt"): if ltype == 'czytelnia': @@ -161,25 +200,27 @@ u"""%(wskazowki)s if surl is None: # print '** missing src on , 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 = etree.fromstring(self.options['provider'].by_uri(surl).get_string()) + + self.options = {'slowniczek': True, 'slowniczek_xml': sxml} pre, post = '
    ', '
    ' - if self.options['wldoc'].book_info.url.slug != 'slowniczek': + 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', - 'czytelnia': 'ul'}[ltype] + listtag = { + 'num': 'ol', + 'punkt': 'ul', + 'alfa': 'ul', + 'czytelnia': 'ul'}[ltype] classes = attrs.get('class', '') - if classes: del attrs['class'] + if classes: + del attrs['class'] attrs_s = ' '.join(['%s="%s"' % kv for kv in attrs.items()]) - if attrs_s: attrs_s = ' ' + attrs_s + if attrs_s: + attrs_s = ' ' + attrs_s return '<%s class="lista %s %s"%s>' % (listtag, ltype, classes, attrs_s), '' % listtag @@ -200,16 +241,19 @@ u"""%(wskazowki)s # 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 "'" 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:', element.text + print ("!! Missing definiendum in source: '%s'" % element.text).encode('utf-8') - return u"
    ", u"
    " + definiens_s + return u"
    " % self.naglowek_to_anchor(element), u"
    " + definiens_s def handle_definiens(self, element): return u"
    ", u"
    " @@ -219,8 +263,7 @@ u"""%(wskazowki)s def handle_tabela(self, element): has_frames = int(element.attrib.get("ramki", "0")) - if has_frames: frames_c = "framed" - else: frames_c = "" + frames_c = "framed" if has_frames else "" return u"""""" % frames_c, u"
    " def handle_wiersz(self, element): @@ -239,14 +282,9 @@ u"""%(wskazowki)s 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] + def make_url(f): + return self.options['urlmapper'].url_for_material(slug, f) formats = self.options['urlmapper'].materials(slug) @@ -278,8 +316,10 @@ u"""%(wskazowki)s 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)})) + 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): @@ -297,10 +337,12 @@ u"""%(wskazowki)s class Exercise(EduModule): INSTRUCTION = "" + def __init__(self, *args, **kw): self.question_counter = 0 super(Exercise, self).__init__(*args, **kw) self.instruction_printed = False + self.piece_counter = None @tagged('div', 'description') def handle_opis(self, element): @@ -341,7 +383,7 @@ class Exercise(EduModule): # Add a single tag if it's not there if not element.xpath(".//pytanie"): qpre, qpost = self.handle_pytanie(element) - pre = pre + qpre + pre += qpre post = qpost + post return pre, post @@ -352,8 +394,7 @@ class Exercise(EduModule): 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 = '' + solution_s = ' data-solution="%s"' % solution if solution else '' handles = element.attrib.get('uchwyty', None) if handles: @@ -361,8 +402,7 @@ class Exercise(EduModule): self.options = {'handles': handles} minimum = element.attrib.get('min', None) - if minimum: minimum_s = ' data-minimum="%d"' % int(minimum) - else: minimum_s = '' + minimum_s = ' data-minimum="%d"' % int(minimum) if minimum else '' return '
    ' %\ (add_class, self.question_counter, solution_s + minimum_s), \ @@ -379,7 +419,6 @@ class Exercise(EduModule): return "" - class Wybor(Exercise): def handle_cwiczenie(self, element): pre, post = super(Wybor, self).handle_cwiczenie(element) @@ -388,13 +427,14 @@ class Wybor(Exercise): if not pytania: pytania = [element] for p in pytania: - solutions = re.split(r"[, ]+", p.attrib['rozw']) + solutions = re.split(r"[, ]+", p.attrib.get('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']) + for n in choices: + uniq.add(n.attrib.get('nazwa', '')) if len(choices) != len(uniq): is_single_choice = False break @@ -442,13 +482,14 @@ Overrides the returned content default handle_pytanie u"""
    """ def handle_punkt(self, element): - return """
  • """ \ + return """
  • """ \ % element.attrib,\ "
    • " class Luki(Exercise): INSTRUCTION = u"Przeciągnij odpowiedzi i upuść w wybranym polu." + def find_pieces(self, question): return question.xpath(".//luka") @@ -488,7 +529,7 @@ class Zastap(Luki): 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 @@ -533,6 +574,8 @@ class Przyporzadkuj(Exercise): 'data-target': lista.attrib['cel'], 'class': 'subject' } + if lista.attrib.get('krotkie'): + self.options = {'short': True} self.options = {'subject': True} else: attrs = {} @@ -543,16 +586,29 @@ 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.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']: if self.options['min']: - placeholders = u'
  • ' * self.options['min'] + placeholders = u'
  • ' * self.options['min'] else: - placeholders = u'
  • ' - return '
  • ' % element.attrib, '
      ' + placeholders + '
    • ' + placeholders = u'
  • ' + return ( + '
  • ' % element.attrib.get('nazwa', ''), + '
      ' + placeholders + '
    • ') else: return super(Przyporzadkuj, self).handle_punkt(element) @@ -578,6 +634,7 @@ class EduModuleFormat(Format): def __init__(self, wldoc, **kwargs): super(EduModuleFormat, self).__init__(wldoc, **kwargs) + self.materials_by_slug = None def build(self): # Sort materials by slug. @@ -599,20 +656,33 @@ class EduModuleFormat(Format): def materials(self, slug): """Returns a list of pairs: (ext, iofile).""" - order = dict(reversed(k) for k in enumerate(self.PRIMARY_MATERIAL_FORMATS)) + order = {pmf: i for (i, pmf) in enumerate(self.PRIMARY_MATERIAL_FORMATS)} mats = self.materials_by_slug.get(slug, {}).items() if not mats: - print "!! Material missing: '%s'" % slug + print ("!! Material missing: '%s'" % slug).encode('utf-8') return sorted(mats, key=lambda (x, y): order.get(x, x)) def url_for_material(self, slug, fmt): return "%s.%s" % (slug, fmt) + # WTF: tutaj był błąd, ale nikomu to nie przeszkadzało? def url_for_image(self, slug, fmt, width=None): - return self.url_for_material(self, slug, fmt) + return self.url_for_material(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): +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,