X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/a7133c06fd9738c11a2bf60b4fc09365d15da1d7..d329e7e5c88a9445e10083536ae1549e6fc1a1be:/librarian/pypdf.py?ds=inline diff --git a/librarian/pypdf.py b/librarian/pypdf.py index cb082ca..0793951 100644 --- a/librarian/pypdf.py +++ b/librarian/pypdf.py @@ -9,26 +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 -import os +from copy import deepcopy import os.path import shutil -from StringIO import StringIO -from tempfile import mkdtemp, NamedTemporaryFile import re -from copy import deepcopy -from subprocess import call, PIPE +import random +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 +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): @@ -48,15 +42,21 @@ def escape(really): return deco -def cmd(name, pass_text=False): - def wrap(self, element): - pre = u'' % name +def cmd(name, parms=None): + def wrap(self, element=None): + pre, post = tag_open_close('cmd', name=name) - if pass_text: - pre += "%s" % element.text - return pre + '' + if parms: + for parm in parms: + e = etree.Element("parm") + e.text = parm + pre += etree.tostring(e) + if element is not None: + pre += "" + post = "" + post + return pre, post else: - return pre, '' + return pre + post return wrap @@ -66,9 +66,16 @@ def mark_alien_characters(text): class EduModule(Xmill): - def __init__(self, options=None): - super(EduModule, self).__init__(options) + def __init__(self, options=None, state=None): + super(EduModule, self).__init__(options, state) self.activity_counter = 0 + self.exercise_counter = 0 + + def swap_endlines(txt): + 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) @@ -91,11 +98,15 @@ class EduModule(Xmill): u'' @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): @@ -116,32 +127,97 @@ class EduModule(Xmill): \\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''] return u"".join(filter(None, lines)), u'' - handle_naglowek_rozdzial = escape(True)(cmd("naglowekrozdzial", True)) - handle_naglowek_podrozdzial = escape(True)(cmd("naglowekpodrozdzial", True)) - @escape(1) def handle_powiesc(self, element): return u""" - """, """""" + """, """""" + + @escape(1) + def handle_texcommand(self, element): + cmd = functions.texcommand(element.tag) + return u'' % cmd, u'' + + handle_akap = \ + handle_akap = \ + handle_akap_cd = \ + handle_akap_cd = \ + handle_akap_dialog = \ + handle_akap_dialog = \ + handle_autor_utworu = \ + handle_dedykacja = \ + handle_didaskalia = \ + handle_didask_tekst = \ + handle_dlugi_cytat = \ + handle_dzielo_nadrzedne = \ + handle_lista_osoba = \ + handle_mat = \ + handle_miejsce_czas = \ + handle_motto = \ + handle_motto_podpis = \ + handle_naglowek_akt = \ + handle_naglowek_czesc = \ + handle_naglowek_listy = \ + handle_naglowek_osoba = \ + handle_naglowek_podrozdzial = \ + handle_naglowek_scena = \ + handle_nazwa_utworu = \ + handle_nota = \ + handle_osoba = \ + handle_pa = \ + handle_pe = \ + handle_podtytul = \ + handle_poezja_cyt = \ + handle_pr = \ + handle_pt = \ + handle_sekcja_asterysk = \ + handle_sekcja_swiatlo = \ + handle_separator_linia = \ + handle_slowo_obce = \ + handle_srodtytul = \ + handle_tytul_dziela = \ + handle_wyroznienie = \ + handle_dywiz = \ + handle_texcommand + + def handle_naglowek_rozdzial(self, element): + if not self.options['teacher']: + if element.text.startswith((u'Wiedza', u'Zadania', u'Słowniczek')): + self.state['mute'] = False + else: + self.state['mute'] = True + return None + return self.handle_texcommand(element) + handle_naglowek_rozdzial.unmuter = True + + + def handle_uwaga(self, _e): + return None + def handle_extra(self, _e): + return None - handle_autor_utworu = cmd('autorutworu', True) - handle_nazwa_utworu = cmd('nazwautworu', True) - handle_dzielo_nadrzedne = cmd('dzielonadrzedne', True) - handle_podtytul = cmd('podtytul', True) + def handle_nbsp(self, _e): + return '' - handle_akap = handle_akap_dialog = handle_akap_cd = lambda s, e: ("\n", "\n") - handle_strofa = lambda s, e: ("\n","\n") + _handle_strofa = cmd("strofa") + + def handle_strofa(self, element): + self.options = {'strofa': True} + return self._handle_strofa(element) def handle_aktywnosc(self, element): self.activity_counter += 1 @@ -150,9 +226,12 @@ class EduModule(Xmill): 'activity_counter': self.activity_counter, 'sub_gen': True, } - submill = EduModule(self.options) + submill = EduModule(self.options, self.state) - 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]) @@ -170,11 +249,16 @@ class EduModule(Xmill): counter = self.activity_counter return u""" -Czas: %(czas)s min -Forma: %(forma)s -%(pomoce)s + +%(counter)d. + + %(czas)s + %(forma)s + %(pomoce)s + + -%(counter)d. %(opis)s +%(opis)s %(wskazowki)s """ % locals() @@ -192,162 +276,358 @@ Forma: %(forma)s def handle_forma(self, *_): return -# def handle_cwiczenie(self, element): -# exercise_handlers = { -# 'wybor': Wybor, -# 'uporzadkuj': Uporzadkuj, -# 'luki': Luki, -# 'zastap': Zastap, -# 'przyporzadkuj': Przyporzadkuj, -# 'prawdafalsz': PrawdaFalsz -# } - -# typ = element.attrib['typ'] -# handler = exercise_handlers[typ](self.options) -# return handler.generate(element) - -# # Lists -# def handle_lista(self, element, attrs={}): -# ltype = element.attrib.get('typ', 'punkt') -# if ltype == 'slowniczek': -# surl = element.attrib.get('href', None) -# sxml = None -# if surl: -# sxml = etree.fromstring(self.options['provider'].by_uri(surl).get_string()) -# self.options = {'slowniczek': True, 'slowniczek_xml': sxml } -# return '
', '
' - -# listtag = {'num': 'ol', -# 'punkt': 'ul', -# 'alfa': 'ul', -# 'czytelnia': 'ul'}[ltype] - -# classes = attrs.get('class', '') -# if classes: del attrs['class'] - -# 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 - -# def handle_punkt(self, element): -# if self.options['slowniczek']: -# return '
', '
' -# else: -# return '
  • ', '
  • ' - -# def handle_definiendum(self, element): -# nxt = element.getnext() -# definiens_s = '' - -# # let's pull definiens from another document -# if self.options['slowniczek_xml'] and (not nxt 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) - -# return u"
    ", u"
    " + definiens_s - -# def handle_definiens(self, element): -# return u"
    ", u"
    " - - -# def handle_podpis(self, element): -# return u"""
    """, u"
    " - -# def handle_tabela(self, element): -# has_frames = int(element.attrib.get("ramki", "0")) -# if has_frames: frames_c = "framed" -# else: frames_c = "" -# return u"""""" % frames_c, u"
    " - -# def handle_wiersz(self, element): -# return u"", u"" - -# def handle_kol(self, element): -# return u"", u"" - -# def handle_rdf__RDF(self, _): -# # ustal w opcjach rzeczy :D -# return - -# def handle_link(self, element): -# if 'material' in element.attrib: -# formats = re.split(r"[, ]+", element.attrib['format']) -# fmt_links = [] -# for f in formats: -# fmt_links.append(u'%s' % (self.options['urlmapper'].url_for_material(element.attrib['material'], f), f.upper())) - -# return u"", u' (%s)' % u' '.join(fmt_links) - - -# class Exercise(EduModule): -# def __init__(self, *args, **kw): -# self.question_counter = 0 -# super(Exercise, self).__init__(*args, **kw) - -# def handle_rozw_kom(self, element): -# return u"""""" - -# def handle_cwiczenie(self, element): -# self.options = {'exercise': element.attrib['typ']} -# self.question_counter = 0 -# self.piece_counter = 0 - -# pre = u""" -#
    -#
    -# """ % element.attrib -# post = u""" -#
    -# -# -# -# -# -#
    -#
    -#
    -# """ -# # Add a single tag if it's not there -# if not element.xpath(".//pytanie"): -# qpre, qpost = self.handle_pytanie(element) -# pre = pre + qpre -# post = qpost + post -# return pre, post - -# def handle_pytanie(self, element): -# """This will handle element, when there is no -# """ -# add_class = "" -# self.question_counter += 1 -# self.piece_counter = 0 -# solution = element.attrib.get('rozw', None) -# if solution: solution_s = ' data-solution="%s"' % solution -# else: solution_s = '' - -# handles = element.attrib.get('uchwyty', None) -# if handles: -# add_class += ' handles handles-%s' % handles -# self.options = {'handles': handles} - -# minimum = element.attrib.get('min', None) -# if minimum: minimum_s = ' data-minimum="%d"' % int(minimum) -# else: minimum_s = '' - -# return '
    ' %\ -# (add_class, self.question_counter, solution_s + minimum_s), \ -# "
    " + 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: + # print '** missing src on , setting default' + surl = 'http://edukacjamedialna.edu.pl/lekcje/slowniczek/' + sxml = None + if surl: + sxml = etree.fromstring(self.options['wldoc'].provider.by_uri(surl).get_string()) + self.options = {'slowniczek': True, 'slowniczek_xml': sxml } + + listcmd = {'num': 'enumerate', + 'punkt': 'itemize', + 'alfa': 'itemize', + 'slowniczek': 'itemize', + 'czytelnia': 'itemize'}[ltype] + + return u'' % listcmd, u'' + + def handle_punkt(self, element): + return '', '' + + def handle_cwiczenie(self, element): + exercise_handlers = { + 'wybor': Wybor, + 'uporzadkuj': Uporzadkuj, + 'luki': Luki, + 'zastap': Zastap, + 'przyporzadkuj': Przyporzadkuj, + 'prawdafalsz': PrawdaFalsz + } + + typ = element.attrib['typ'] + self.exercise_counter += 1 + if not typ in exercise_handlers: + return '(no handler)' + self.options = {'exercise_counter': self.exercise_counter} + handler = exercise_handlers[typ](self.options, self.state) + return handler.generate(element) + + # XXX this is copied from pyhtml.py, except for return and + # should be refactored for no code duplication + def handle_definiendum(self, element): + nxt = element.getnext() + definiens_s = '' + + # let's pull definiens from another document + 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, self.state) + definiens_s = subgen.generate(definiens) + + return u'', u": " + definiens_s + + def handle_definiens(self, element): + return u"", u"" + + def handle_podpis(self, element): + return u"""""", u"" + + def handle_tabela(self, element): + max_col = 0 + for w in element.xpath("wiersz"): + ks = w.xpath("kol") + if max_col < len(ks): + max_col = len(ks) + self.options = {'columnts': max_col} + # styling: + # has_frames = int(element.attrib.get("ramki", "0")) + # if has_frames: frames_c = "framed" + # else: frames_c = "" + # return u"""""" % frames_c, u"
    " + return u''' +tabular%s + ''' % ('l' * max_col), \ + u'''tabular''' + + @escape(1) + def handle_wiersz(self, element): + return u"", u'' + + @escape(1) + def handle_kol(self, element): + if element.getnext() is not None: + return u"", u'' + return u"", u"" + + def handle_link(self, element): + if element.attrib.get('url'): + 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('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 '!!