X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/51396a4419bb3d4b89ad65a434dfeb9e81e6f6e2..e9cdd3f1f653de79f94ddfcdf319fcc31e7f0cef:/librarian/pyhtml.py
diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py
index ded327b..7047cc9 100644
--- a/librarian/pyhtml.py
+++ b/librarian/pyhtml.py
@@ -5,20 +5,43 @@
#
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
-DEFAULT_MATERIAL_FORMAT = 'odt'
-
+try:
+ from fnpdjango.utils.text.slughifi import slughifi
+ def naglowek_to_anchor(naglowek):
+ return slughifi(naglowek.text)
+except ImportError:
+ from urllib import quote
+ def naglowek_to_anchor(naglowek):
+ return quote(re.sub(r" +", " ", naglowek.text.strip()))
+
+
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):
+ 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"""
@@ -31,18 +54,34 @@ 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('h2')
+ 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 handle_nazwa_utworu(self, element):
+ toc = []
+ for naglowek in element.getparent().findall('.//naglowek_rozdzial'):
+ a = etree.Element("a")
+ a.attrib["href"] = "#" + 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"wrÃ³Ä do spisu treÅci"
+ pre, post = tag_open_close("h2", id=naglowek_to_anchor(element))
+ return return_to_top + pre, post
+
def handle_uwaga(self, _e):
return None
@@ -54,7 +93,10 @@ 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])
@@ -75,12 +117,12 @@ class EduModule(Xmill):
%(counter)d.
- %(opis)s
- %(wskazowki)s
+ %(opis)s""" % locals(), \
+u"""%(wskazowki)s
@@ -112,19 +154,32 @@ 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 caÅy sÅowniczek.
' % surl
+ return pre, post
listtag = {'num': 'ol',
'punkt': 'ul',
@@ -149,16 +204,21 @@ 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
@@ -188,24 +248,74 @@ class EduModule(Xmill):
if 'url' in element.attrib:
return tag('a', href=element.attrib['url'])(self, element)
elif 'material' in element.attrib:
- formats = re.split(r"[, ]+",
- element.attrib.get('format', DEFAULT_MATERIAL_FORMAT))
+ material_err = u' [BRAKUJÄCY MATERIAÅ]'
+ slug = element.attrib['material']
make_url = lambda f: self.options['urlmapper'] \
- .url_for_material(element.attrib['material'], f)
- def_href = make_url(formats[0])
+ .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:]:
- fmt_links.append(u'%s' % (make_url(f), f.upper()))
-
- return u"", u' (%s)' % (def_href, u' '.join(fmt_links))
+ 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 '!!