X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/45aed036278c98bda04414dfd6f216bc5d2f7586..f7260ec22a6bcb39fe800ac21f335c2c903a2072:/librarian/pyhtml.py diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index e5ca40e..b4d8557 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -5,18 +5,32 @@ # from lxml import etree from librarian import IOFile, RDFNS, DCNS, Format -from xmlutils import Xmill, tag, tagged, ifoption +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.register_text_filter(lambda t: functions.substitute_entities(None, t)) + 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_powiesc(self, element): return u""" @@ -29,14 +43,39 @@ class EduModule(Xmill): """, 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 @@ -65,15 +104,16 @@ 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() @@ -82,9 +122,9 @@ class EduModule(Xmill): handle_wskazowki = ifoption(sub_gen=True)(tag('div', ('hints', 'teacher'))) @ifoption(sub_gen=True) - @tagged('div', 'materials') + @tagged('section', 'infobox materials') def handle_pomoce(self, _): - return "Pomoce: ", "" + return """

    Pomoce

    """, "" def handle_czas(self, *_): return @@ -103,19 +143,32 @@ class EduModule(Xmill): } 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={}): 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) + 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 } - return '
    ', '
    ' + 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', @@ -140,23 +193,27 @@ class EduModule(Xmill): 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 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"
    " @@ -177,19 +234,77 @@ class EduModule(Xmill): return def handle_link(self, element): - if 'material' in element.attrib: - formats = re.split(r"[, ]+", element.attrib['format']) - fmt_links = [] - for f in formats: - fmt_links.append(u'%s' % (self.options['urlmapper'].url_for_material(element.attrib['material'], f), f.upper())) + 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] - return u"", u' (%s)' % u' '.join(fmt_links) + 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 '!!