From a4a0d6ab3c0a97fbb7ffeae0454e448c92cb67ce Mon Sep 17 00:00:00 2001 From: Radek Czajka Date: Tue, 19 Feb 2013 11:14:45 +0100 Subject: [PATCH] various pdf fixes --- librarian/pdf/wl.cls | 2 +- librarian/pyhtml.py | 10 ++++++- librarian/pypdf.py | 32 +++++++++++----------- librarian/res/styles/edumed/pdf/edumed.sty | 5 +--- 4 files changed, 27 insertions(+), 22 deletions(-) diff --git a/librarian/pdf/wl.cls b/librarian/pdf/wl.cls index f0280eb..c04a8c8 100755 --- a/librarian/pdf/wl.cls +++ b/librarian/pdf/wl.cls @@ -295,7 +295,7 @@ Letters={Uppercase} \subsubsection*{\typosubsubsection{#1}}% } \newcommand{\naglowekrozdzial}[1]{% -\subsubsection*{\typosubsubsection{#1}}% +{\raggedright\subsubsection*{\typosubsubsection{#1}}}% } \newcommand{\naglowekosoba}[1]{% diff --git a/librarian/pyhtml.py b/librarian/pyhtml.py index 6d1e914..6bfbf8a 100644 --- a/librarian/pyhtml.py +++ b/librarian/pyhtml.py @@ -151,6 +151,11 @@ u"""%(wskazowki)s # 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('src', None) if surl is None: @@ -173,7 +178,10 @@ u"""%(wskazowki)s attrs_s = ' '.join(['%s="%s"' % kv for kv in attrs.items()]) if attrs_s: attrs_s = ' ' + attrs_s - return '<%s class="lista %s %s"%s>' % (listtag, ltype, classes, attrs_s), '' % listtag + pre, post = '<%s class="lista %s %s"%s>' % (listtag, ltype, classes, attrs_s), '' % listtag + if ltype == 'slowniczek': + post += '

Zobacz cały słowniczek.

' % surl + return pre, post def handle_punkt(self, element): if self.options['slowniczek']: diff --git a/librarian/pypdf.py b/librarian/pypdf.py index 2bcd8d0..d89d4af 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})) @@ -204,6 +194,7 @@ class EduModule(Xmill): handle_srodtytul = \ handle_tytul_dziela = \ handle_wyroznienie = \ + handle_dywiz = \ handle_texcommand def handle_uwaga(self, _e): @@ -211,6 +202,9 @@ class EduModule(Xmill): def handle_extra(self, _e): return None + def handle_nbsp(self, _e): + return '' + _handle_strofa = cmd("strofa") def handle_strofa(self, element): @@ -272,14 +266,17 @@ 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()) @@ -599,6 +596,9 @@ 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, diff --git a/librarian/res/styles/edumed/pdf/edumed.sty b/librarian/res/styles/edumed/pdf/edumed.sty index a936ef7..b25a99d 100755 --- a/librarian/res/styles/edumed/pdf/edumed.sty +++ b/librarian/res/styles/edumed/pdf/edumed.sty @@ -1,3 +1,4 @@ +\usepackage[MeX]{polski} \newcommand{\activitycounter}[1]{\vspace{1em}\par{\huge{#1}}} @@ -57,10 +58,6 @@ \color{theme} \noindent \rule{\linewidth}{0.4pt} - \rightsinfo - \vspace{.6em} - - Tekst: \authorstextbook, scenariusz: \authorsscenario, konsultacja merytoryczna: \authorsexpert. Materiał pochodzi z serwisu \href{http://edukacjamedialna.edu.pl}{edukacjamedialna.edu.pl} prowadzonego przez \href{http://nowoczesnapolska.org.pl}{Fundację Nowoczesna Polska}. -- 2.20.1