X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/6df7f4fb5a5f4f7d1fcf059837219a912a14dcd8..893924685f2bc659cb71d7c68501fc3cf1daa0f0:/librarian/pypdf.py
diff --git a/librarian/pypdf.py b/librarian/pypdf.py
index 6d6e0aa..b261eb6 100644
--- a/librarian/pypdf.py
+++ b/librarian/pypdf.py
@@ -9,30 +9,20 @@ Creates one big XML from the book and its children, converts it to LaTeX
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):
@@ -85,9 +75,9 @@ class EduModule(Xmill):
if self.options['strofa']:
txt = txt.replace("/\n", '')
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}))
@@ -204,8 +194,17 @@ class EduModule(Xmill):
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 ''
+
_handle_strofa = cmd("strofa")
def handle_strofa(self, element):
@@ -221,7 +220,10 @@ class EduModule(Xmill):
}
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])
@@ -267,14 +269,17 @@ class EduModule(Xmill):
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('src', None)
if surl is None:
# print '** missing src on , setting default'
- surl = 'http://edukacjamedialna.edu.pl/slowniczek'
+ surl = 'http://edukacjamedialna.edu.pl/lekcje/slowniczek/'
sxml = None
if surl:
sxml = etree.fromstring(self.options['wldoc'].provider.by_uri(surl).get_string())
@@ -373,7 +378,7 @@ class EduModule(Xmill):
def handle_obraz(self, element):
frmt = self.options['format']
- name = element.attrib['nazwa'].strip()
+ name = element.attrib.get('nazwa', '').strip()
image = frmt.get_image(name.strip())
img_path = "obraz/%s" % name.replace("_", "")
frmt.attachments[img_path] = image
@@ -467,13 +472,13 @@ class Wybor(Exercise):
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
@@ -550,7 +555,7 @@ class Zastap(Luki):
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"
@@ -594,6 +599,9 @@ class EduModulePDFFormat(PDFFormat):
style = get_resource('res/styles/edumed/pdf/edumed.sty')
def get_texml(self):
+ substitute_hyphens(self.wldoc.edoc)
+ fix_hanging(self.wldoc.edoc)
+
self.attachments = {}
edumod = EduModule({
"wldoc": self.wldoc,