X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/9b253dcb10940e8c8d25a02059153d4c80469b79..f7260ec22a6bcb39fe800ac21f335c2c903a2072:/librarian/pyhtml.py diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index da7e643..b4d8557 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -4,65 +4,86 @@ # 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.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 + + 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 + "

    " + + 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]) @@ -83,56 +104,84 @@ 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 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 - listtag = {'num': 'ol', - 'punkt': 'ul', - 'alfa': 'ul', + surl = element.attrib.get('src', None) + 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 } + pre, post = '
    ', '
    ' + if self.options['wldoc'].book_info.url.slug != 'slowniczek': + post += u'

    Zobacz cały słowniczek.

    ' % surl + return pre, post + + 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 +189,429 @@ 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) + + 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 '!!