with TeXML, then runs it by XeLaTeX.
"""
-from __future__ import with_statement
from copy import deepcopy
-import os
import os.path
import shutil
-from StringIO import StringIO
-from tempfile import mkdtemp, NamedTemporaryFile
import re
import random
-from copy import deepcopy
-from subprocess import call, PIPE
+from urllib2 import urlopen
-from Texml.processor import process
from lxml import etree
-from lxml.etree import XMLSyntaxError, XSLTApplyError
from xmlutils import Xmill, tag, tagged, ifoption, tag_open_close
from librarian.dcparser import Person
-from librarian.parser import WLDocument
-from librarian import ParseError, DCNS, get_resource, IOFile, Format
+from librarian import DCNS, get_resource, IOFile
from librarian import functions
-from pdf import PDFFormat
-
+from pdf import PDFFormat, substitute_hyphens, fix_hanging
def escape(really):
def cmd(name, parms=None):
- def wrap(self, element):
+ def wrap(self, element=None):
pre, post = tag_open_close('cmd', name=name)
if parms:
e = etree.Element("parm")
e.text = parm
pre += etree.tostring(e)
- pre += "<parm>"
- post = "</parm>" + post
- return pre, post
+ if element is not None:
+ pre += "<parm>"
+ post = "</parm>" + post
+ return pre, post
+ else:
+ return pre + post
return wrap
if self.options['strofa']:
txt = txt.replace("/\n", '<ctrl ch="\\"/>')
return txt
+ self.register_text_filter(swap_endlines)
self.register_text_filter(functions.substitute_entities)
self.register_text_filter(mark_alien_characters)
- self.register_text_filter(swap_endlines)
def get_dc(self, element, dc_field, single=False):
values = map(lambda t: t.text, element.xpath("//dc:%s" % dc_field, namespaces={'dc': DCNS.uri}))
u'</cmd>'
@escape(True)
- def get_authors(self, element):
- authors = self.get_dc(element, 'creator.expert') + \
- self.get_dc(element, 'creator.scenario') + \
- self.get_dc(element, 'creator.textbook')
- return u', '.join(authors)
+ def get_authors(self, element, which=None):
+ dc = self.options['wldoc'].book_info
+ if which is None:
+ authors = dc.authors_textbook + \
+ dc.authors_scenario + \
+ dc.authors_expert
+ else:
+ authors = getattr(dc, "authors_%s" % which)
+ return u', '.join(author.readable() for author in authors)
@escape(1)
def get_title(self, element):
\\usepackage{morefloats}
}{}'''),
u'''\\def\\authors{%s}''' % self.get_authors(element),
+ u'''\\def\\authorsexpert{%s}''' % self.get_authors(element, 'expert'),
+ u'''\\def\\authorsscenario{%s}''' % self.get_authors(element, 'scenario'),
+ u'''\\def\\authorstextbook{%s}''' % self.get_authors(element, 'textbook'),
+
u'''\\author{\\authors}''',
u'''\\title{%s}''' % self.get_title(element),
- u'''\\def\\bookurl{%s}''' % self.get_dc(element, 'identifier.url', True),
+ u'''\\def\\bookurl{%s}''' % self.options['wldoc'].book_info.url.canonical(),
u'''\\def\\rightsinfo{%s}''' % self.get_rightsinfo(element),
u'</TeXML>']
return u"""
<env name="document">
<cmd name="maketitle"/>
- """, """</env>"""
+ """, """<cmd name="editorialsection" /></env>"""
@escape(1)
def handle_texcommand(self, element):
handle_srodtytul = \
handle_tytul_dziela = \
handle_wyroznienie = \
+ handle_dywiz = \
handle_texcommand
+ def handle_uwaga(self, _e):
+ return None
+ def handle_extra(self, _e):
+ return None
+
+ def handle_nbsp(self, _e):
+ return '<spec cat="tilde" />'
+
_handle_strofa = cmd("strofa")
def handle_strofa(self, element):
}
submill = EduModule(self.options)
- 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])
counter = self.activity_counter
return u"""
-
+<cmd name="noindent" />
<cmd name="activitycounter"><parm>%(counter)d.</parm></cmd>
<cmd name="activityinfo"><parm>
<cmd name="activitytime"><parm>%(czas)s</parm></cmd>
return
def handle_lista(self, element, attrs={}):
- if not element.findall("punkt"):
- return None
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 <slowniczek>, setting default'
+ surl = 'http://edukacjamedialna.edu.pl/lekcje/slowniczek/'
sxml = None
if surl:
- sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string())
+ sxml = etree.fromstring(self.options['wldoc'].provider.by_uri(surl).get_string())
self.options = {'slowniczek': True, 'slowniczek_xml': sxml }
listcmd = {'num': 'enumerate',
definiens_s = ''
# 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)
def handle_link(self, element):
if element.attrib.get('url'):
- return cmd('href', parms=[element.attrib['url']])(self, element)
+ url = element.attrib.get('url')
+ if url == element.text:
+ return cmd('url')(self, element)
+ else:
+ return cmd('href', parms=[element.attrib['url']])(self, element)
else:
- return cmd('em')(self, element)
+ return cmd('emph')(self, element)
+
+ def handle_obraz(self, element):
+ frmt = self.options['format']
+ name = element.attrib.get('nazwa', '').strip()
+ image = frmt.get_image(name.strip())
+ img_path = "obraz/%s" % name.replace("_", "")
+ frmt.attachments[img_path] = image
+ return cmd("obraz", parms=[img_path])(self)
+
+ def handle_video(self, element):
+ url = element.attrib.get('url')
+ if not url:
+ print '!! <video> missing url'
+ return
+ m = re.match(r'(?:https?://)?(?:www.)?youtube.com/watch\?(?:.*&)?v=([^&]+)(?:$|&)', url)
+ if not m:
+ print '!! unknown <video> url scheme:', url
+ return
+ name = m.group(1)
+ thumb = IOFile.from_string(urlopen
+ ("http://img.youtube.com/vi/%s/0.jpg" % name).read())
+ img_path = "video/%s.jpg" % name.replace("_", "")
+ self.options['format'].attachments[img_path] = thumb
+ canon_url = "https://www.youtube.com/watch?v=%s" % name
+ return cmd("video", parms=[img_path, canon_url])(self)
class Exercise(EduModule):
if not pytania:
pytania = [element]
for p in pytania:
- solutions = re.split(r"[, ]+", p.attrib['rozw'])
+ solutions = re.split(r"[, ]+", p.attrib.get('rozw', ''))
if len(solutions) != 1:
is_single_choice = False
break
choices = p.xpath(".//*[@nazwa]")
uniq = set()
- for n in choices: uniq.add(n.attrib['nazwa'])
+ for n in choices: uniq.add(n.attrib.get('nazwa', ''))
if len(choices) != len(uniq):
is_single_choice = False
break
return question.xpath(".//zastap")
def solution(self, piece):
- return piece.attrib['rozw']
+ return piece.attrib.get('rozw', '')
def list_header(self):
return u"Elementy do wstawienia"
class EduModulePDFFormat(PDFFormat):
+ style = get_resource('res/styles/edumed/pdf/edumed.sty')
+
def get_texml(self):
- edumod = EduModule({"teacher": self.customization.get('teacher')})
+ substitute_hyphens(self.wldoc.edoc)
+ fix_hanging(self.wldoc.edoc)
+
+ self.attachments = {}
+ edumod = EduModule({
+ "wldoc": self.wldoc,
+ "format": self,
+ "teacher": self.customization.get('teacher'),
+ })
texml = edumod.generate(fix_lists(self.wldoc.edoc.getroot())).encode('utf-8')
open("/tmp/texml.xml", "w").write(texml)
return texml
+
+ def get_tex_dir(self):
+ temp = super(EduModulePDFFormat, self).get_tex_dir()
+ shutil.copy(get_resource('res/styles/edumed/logo.png'), temp)
+ for name, iofile in self.attachments.items():
+ iofile.save_as(os.path.join(temp, name))
+ return temp
+
+ def get_image(self, name):
+ return self.wldoc.source.attachments[name]
+
fnp / librarian.git / blobdiff