X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/b10cdf123648beb76120194d7f9bb69fc8433ede..565aa32ff31bdbe6e2aaf9f47b124ac1f883a990:/librarian/pyhtml.py?ds=sidebyside diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index a6f6686..163d11c 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -4,18 +4,35 @@ # 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 import random +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 + 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""" @@ -32,27 +49,39 @@ 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_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"] = "#" + naglowek.text + 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) - return "

    Lekcja: ", "

    " + 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=element.text)) + 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 @@ -65,38 +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'))) @@ -123,30 +180,47 @@ u"""%(wskazowki)s } 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) # 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': + return '

    W przygotowaniu.

    ' + else: + return None if ltype == 'slowniczek': - surl = element.attrib.get('href', None) - sxml = None - if surl: - sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string()) - self.options = {'slowniczek': True, 'slowniczek_xml': sxml } - return '
    ', '
    ' - - listtag = {'num': 'ol', - 'punkt': 'ul', - 'alfa': 'ul', - 'czytelnia': 'ul'}[ltype] + 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', + '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 @@ -160,18 +234,26 @@ u"""%(wskazowki)s 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 "'" 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).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"
    " @@ -181,8 +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): @@ -200,38 +281,72 @@ u"""%(wskazowki)s return tag('a', href=element.attrib['url'])(self, element) elif 'material' in element.attrib: material_err = u' [BRAKUJĄCY MATERIAŁ]' - make_url = lambda f: self.options['urlmapper'] \ - .url_for_material(element.attrib['material'], f) + slug = element.attrib['material'] - 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) try: - def_href = make_url(formats[0]) + def_href = make_url(formats[0][0]) def_err = u"" - except self.options['urlmapper'].MaterialNotFound: + 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), f.upper())) + fmt_links.append(u'%s' % (make_url(f[0]), f[0].upper())) except self.options['urlmapper'].MaterialNotFound: - fmt_links.append(u'%s%s' % (f.upper(), material_err)) + 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 '!!