X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/2919eb4f57c7e1c9dead734c685a9b36f34e30ce..d887dee631335a8c44ef75250524e69e67fbc9b4:/librarian/pyhtml.py diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index e9852a7..d138701 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -10,11 +10,13 @@ from librarian import functions import re import random +IMAGE_THUMB_WIDTH = 300 class EduModule(Xmill): def __init__(self, options=None): super(EduModule, self).__init__(options) self.activity_counter = 0 + self.exercise_counter = 0 # text filters def swap_endlines(txt): @@ -28,7 +30,7 @@ class EduModule(Xmill): def handle_strofa(self, element): self.options = {'strofa': True} return "", "" - + def handle_powiesc(self, element): return u"""
@@ -51,20 +53,25 @@ class EduModule(Xmill): 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"] = "#" + 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" + anchor = "".join(tag_open_close("a", name=self.naglowek_to_anchor(element))) + return return_to_top + "

    ", anchor + "

    " def handle_uwaga(self, _e): return None @@ -135,6 +142,8 @@ 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) @@ -142,7 +151,10 @@ u"""%(wskazowki)s def handle_lista(self, element, attrs={}): ltype = element.attrib.get('typ', 'punkt') 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/slowniczek' sxml = None if surl: sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string()) @@ -172,16 +184,21 @@ 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 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 @@ -212,8 +229,9 @@ u"""%(wskazowki)s 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(element.attrib['material'], f) + .url_for_material(slug, f) if 'format' in element.attrib: formats = re.split(r"[, ]+", @@ -221,29 +239,63 @@ u"""%(wskazowki)s else: formats = [None] + 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 '!!