X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/d9766370d8eee5c067756af3c06a4b6ab6583d0e..6a2a1ba8ab5cad50af8dc0b1ec0387e4e4f41f4b:/librarian/pypdf.py

diff --git a/librarian/pypdf.py b/librarian/pypdf.py
index edd1f6d..256bc34 100644
--- a/librarian/pypdf.py
+++ b/librarian/pypdf.py
@@ -18,8 +18,7 @@ from urllib2 import urlopen
 
 from lxml import etree
 
-from xmlutils import Xmill, tag, tagged, ifoption, tag_open_close
-from librarian.dcparser import Person
+from xmlutils import Xmill, ifoption, tag_open_close
 from librarian import DCNS, get_resource, IOFile
 from librarian import functions
 from pdf import PDFFormat, substitute_hyphens, fix_hanging
@@ -30,10 +29,11 @@ def escape(really):
         def _wrap(*args, **kw):
             value = f(*args, **kw)
 
-            prefix = (u'<TeXML escape="%d">' % (really and 1 or 0))
+            prefix = (u'<TeXML escape="%d">' % (1 if really else 0))
             postfix = u'</TeXML>'
             if isinstance(value, list):
-                import pdb; pdb.set_trace()
+                import pdb
+                pdb.set_trace()
             if isinstance(value, tuple):
                 return prefix + value[0], value[1] + postfix
             else:
@@ -69,6 +69,7 @@ class EduModule(Xmill):
     def __init__(self, options=None, state=None):
         super(EduModule, self).__init__(options, state)
         self.activity_counter = 0
+        self.activity_last = None
         self.exercise_counter = 0
 
         def swap_endlines(txt):
@@ -82,20 +83,19 @@ class EduModule(Xmill):
     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}))
         if single:
-            return values[0]
+            return values[0] if len(values) else ''
         return values
 
     def handle_rdf__RDF(self, _):
-        "skip metadata in generation"
+        """skip metadata in generation"""
         return
 
     @escape(True)
     def get_rightsinfo(self, element):
         rights_lic = self.get_dc(element, 'rights.license', True)
-        return u'<cmd name="rightsinfostr">' + \
-          (rights_lic and u'<opt>%s</opt>' % rights_lic or '') +\
-          u'<parm>%s</parm>' % self.get_dc(element, 'rights', True) +\
-          u'</cmd>'
+        return u'<cmd name="rightsinfostr">' + (u'<opt>%s</opt>' % rights_lic if rights_lic else '') + \
+            u'<parm>%s</parm>' % self.get_dc(element, 'rights', True) + \
+            u'</cmd>'
 
     @escape(True)
     def get_authors(self, element, which=None):
@@ -106,110 +106,153 @@ class EduModule(Xmill):
                 dc.authors_expert
         else:
             authors = getattr(dc, "authors_%s" % which)
-        return u', '.join(author.readable() for author in authors)
+        return u', '.join(author.readable() for author in authors if author)
 
-    @escape(1)
+    @escape(True)
     def get_title(self, element):
         return self.get_dc(element, 'title', True)
 
+    @escape(True)
+    def get_description(self, element):
+        desc = self.get_dc(element, 'description', single=True)
+        if not desc:
+            print '!! no description'
+        return desc
+
+    @escape(True)
+    def get_curriculum(self, element):
+        ret = []
+        for dc_tag, new in [('subject.curriculum', False), ('subject.curriculum.new', True)]:
+            identifiers = self.get_dc(element, dc_tag)
+            if not identifiers:
+                continue
+            try:
+                from curriculum.templatetags.curriculum_tags import curriculum
+                curr_elements = curriculum(identifiers)
+            except ImportError:
+                curr_elements = {'identifiers': identifiers}
+            items = ['Podstawa programowa 2017:' if new else 'Podstawa programowa:']
+            newline = '<ctrl ch="\\"/>\n'
+            if 'currset' in curr_elements:
+                for (course, level), types in curr_elements['currset'].iteritems():
+                    lines = [u'%s, %s' % (course, level)]
+                    for type, currs in types.iteritems():
+                        lines.append(type)
+                        lines += [curr.title for curr in currs]
+                    items.append(newline.join(lines))
+            else:
+                items += identifiers
+            ret.append('\n<cmd name="vspace"><parm>.6em</parm></cmd>\n'.join(
+                '<cmd name="akap"><parm>%s</parm></cmd>' % item for item in items))
+        return '\n<cmd name="vspace"><parm>1em</parm></cmd>\n'.join(ret)
+
     def handle_utwor(self, element):
         lines = [
             u'''
-    <TeXML xmlns="http://getfo.sourceforge.net/texml/ns1">
-        <TeXML escape="0">
-        \\documentclass[%s]{wl}
-        \\usepackage{style}''' % self.options['customization_str'],
-    self.options['has_cover'] and '\usepackage{makecover}',
-    (self.options['morefloats'] == 'new' and '\usepackage[maxfloats=64]{morefloats}') or
-    (self.options['morefloats'] == 'old' and '\usepackage{morefloats}') or
-    (self.options['morefloats'] == 'none' and
-     u'''\\IfFileExists{morefloats.sty}{
-            \\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.options['wldoc'].book_info.url.canonical(),
-    u'''\\def\\rightsinfo{%s}''' % self.get_rightsinfo(element),
-    u'</TeXML>']
+                <TeXML xmlns="http://getfo.sourceforge.net/texml/ns1">
+                <TeXML escape="0">
+                \\documentclass[%s]{wl}
+                \\usepackage{style}''' % self.options['customization_str'],
+            self.options['has_cover'] and '\usepackage{makecover}',
+            (self.options['morefloats'] == 'new' and '\usepackage[maxfloats=64]{morefloats}') or
+            (self.options['morefloats'] == 'old' and '\usepackage{morefloats}') or
+            (self.options['morefloats'] == 'none' and
+                u'''\\IfFileExists{morefloats.sty}{
+                \\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'''\\def\\description{%s}''' % self.get_description(element),
+
+            u'''\\author{\\authors}''',
+            u'''\\title{%s}''' % self.get_title(element),
+            u'''\\def\\bookurl{%s}''' % self.options['wldoc'].book_info.url.canonical(),
+            u'''\\def\\rightsinfo{%s}''' % self.get_rightsinfo(element),
+            u'''\\def\\curriculum{%s}''' % self.get_curriculum(element),
+            u'</TeXML>'
+        ]
 
         return u"".join(filter(None, lines)), u'</TeXML>'
 
-
-    @escape(1)
+    @escape(True)
     def handle_powiesc(self, element):
         return u"""
     <env name="document">
     <cmd name="maketitle"/>
     """, """<cmd name="editorialsection" /></env>"""
 
-    @escape(1)
+    @escape(True)
     def handle_texcommand(self, element):
         cmd = functions.texcommand(element.tag)
         return u'<TeXML escape="1"><cmd name="%s"><parm>' % cmd, u'</parm></cmd></TeXML>'
 
     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
+        handle_akap_cd = \
+        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_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']:
-            print element.text
-            if element.text.startswith((u'Wiedza', u'Zadania', u'Słowniczek')):
-                print 'not mute'
+            if element.text.startswith((u'Wiedza', u'Zadania', u'Słowniczek', u'Dla ucznia')):
                 self.state['mute'] = False
             else:
-                print 'mute'
                 self.state['mute'] = True
                 return None
         return self.handle_texcommand(element)
     handle_naglowek_rozdzial.unmuter = True
 
+    def handle_naglowek_podrozdzial(self, element):
+        self.activity_counter = 0
+        if not self.options['teacher']:
+            if element.text.startswith(u'Dla ucznia'):
+                self.state['mute'] = False
+                return None
+            elif element.text.startswith(u'Dla nauczyciela'):
+                self.state['mute'] = True
+                return None
+            elif self.state['mute']:
+                return None
+        return self.handle_texcommand(element)
+    handle_naglowek_podrozdzial.unmuter = True
 
     def handle_uwaga(self, _e):
         return None
+
     def handle_extra(self, _e):
         return None
 
@@ -237,13 +280,16 @@ class EduModule(Xmill):
             opis = ''
 
         n = element.xpath('wskazowki')
-        if n: wskazowki = submill.generate(n[0])
-
-        else: wskazowki = ''
+        if n:
+            wskazowki = submill.generate(n[0])
+        else:
+            wskazowki = ''
         n = element.xpath('pomoce')
 
-        if n: pomoce = submill.generate(n[0])
-        else: pomoce = ''
+        if n:
+            pomoce = submill.generate(n[0])
+        else:
+            pomoce = ''
 
         forma = ''.join(element.xpath('forma/text()'))
 
@@ -251,9 +297,16 @@ class EduModule(Xmill):
 
         counter = self.activity_counter
 
+        if element.getnext().tag == 'aktywnosc' or (len(self.activity_last) and self.activity_last.getnext() == element):
+            counter_tex = """<cmd name="activitycounter"><parm>%(counter)d.</parm></cmd>""" % locals()
+        else:
+            counter_tex = ''
+
+        self.activity_last = element
+
         return u"""
 <cmd name="noindent" />
-<cmd name="activitycounter"><parm>%(counter)d.</parm></cmd>
+%(counter_tex)s
 <cmd name="activityinfo"><parm>
  <cmd name="activitytime"><parm>%(czas)s</parm></cmd>
  <cmd name="activityform"><parm>%(forma)s</parm></cmd>
@@ -279,7 +332,7 @@ class EduModule(Xmill):
     def handle_forma(self, *_):
         return
 
-    def handle_lista(self, element, attrs={}):
+    def handle_lista(self, element, attrs=None):
         ltype = element.attrib.get('typ', 'punkt')
         if not element.findall("punkt"):
             if ltype == 'czytelnia':
@@ -291,16 +344,16 @@ class EduModule(Xmill):
             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['wldoc'].provider.by_uri(surl).get_string())
-            self.options = {'slowniczek': True, 'slowniczek_xml': sxml }
+            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]
+        listcmd = {
+            'num': 'enumerate',
+            'punkt': 'itemize',
+            'alfa': 'itemize',
+            'slowniczek': 'itemize',
+            'czytelnia': 'itemize'
+        }[ltype]
 
         return u'<env name="%s">' % listcmd, u'</env>'
 
@@ -319,7 +372,7 @@ class EduModule(Xmill):
 
         typ = element.attrib['typ']
         self.exercise_counter += 1
-        if not typ in exercise_handlers:
+        if typ not in exercise_handlers:
             return '(no handler)'
         self.options = {'exercise_counter': self.exercise_counter}
         handler = exercise_handlers[typ](self.options, self.state)
@@ -335,7 +388,10 @@ class EduModule(Xmill):
         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 "'" in (element.text or ''):
+                defloc = sxml.xpath("//definiendum[text()=\"%s\"]" % (element.text or '').strip())
+            else:
+                defloc = sxml.xpath("//definiendum[text()='%s']" % (element.text or '').strip())
             if defloc:
                 definiens = defloc[0].getnext()
                 if definiens.tag == 'definiens':
@@ -358,20 +414,19 @@ class EduModule(Xmill):
                 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"""<table class="%s">""" % frames_c, u"</table>"
+        #     has_frames = int(element.attrib.get("ramki", "0"))
+        #     if has_frames: frames_c = "framed"
+        #     else: frames_c = ""
+        #     return u"""<table class="%s">""" % frames_c, u"</table>"
         return u'''
 <cmd name="begin"><parm>tabular</parm><parm>%s</parm></cmd>
-    ''' % ('l' * max_col), \
-    u'''<cmd name="end"><parm>tabular</parm></cmd>'''
+    ''' % ('l' * max_col), u'''<cmd name="end"><parm>tabular</parm></cmd>'''
 
-    @escape(1)
+    @escape(True)
     def handle_wiersz(self, element):
         return u"", u'<ctrl ch="\\"/>'
 
-    @escape(1)
+    @escape(True)
     def handle_kol(self, element):
         if element.getnext() is not None:
             return u"", u'<spec cat="align" />'
@@ -391,6 +446,7 @@ class EduModule(Xmill):
         frmt = self.options['format']
         name = element.attrib.get('nazwa', '').strip()
         image = frmt.get_image(name.strip())
+        name = image.get_filename().rsplit('/', 1)[-1]
         img_path = "obraz/%s" % name.replace("_", "")
         frmt.attachments[img_path] = image
         return cmd("obraz", parms=[img_path])(self)
@@ -405,8 +461,7 @@ class EduModule(Xmill):
             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())
+        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
@@ -417,6 +472,7 @@ class Exercise(EduModule):
     def __init__(self, *args, **kw):
         self.question_counter = 0
         super(Exercise, self).__init__(*args, **kw)
+        self.piece_counter = None
 
     handle_rozw_kom = ifoption(teacher=True)(cmd('akap'))
 
@@ -438,7 +494,7 @@ class Exercise(EduModule):
         # Add a single <pytanie> tag if it's not there
         if not element.xpath(".//pytanie"):
             qpre, qpost = self.handle_pytanie(element)
-            pre = pre + qpre
+            pre += qpre
             post = qpost + post
         return pre, post
 
@@ -474,7 +530,6 @@ class Exercise(EduModule):
             return self.solution_header() + etree.tostring(par)
 
 
-
 class Wybor(Exercise):
     def handle_cwiczenie(self, element):
         pre, post = super(Wybor, self).handle_cwiczenie(element)
@@ -483,23 +538,19 @@ class Wybor(Exercise):
         if not pytania:
             pytania = [element]
         for p in pytania:
-            solutions = re.split(r"[, ]+", p.attrib.get('rozw', ''))
+            solutions = p.xpath(".//punkt[@rozw='prawda']")
             if len(solutions) != 1:
                 is_single_choice = False
                 break
-            choices = p.xpath(".//*[@nazwa]")
-            uniq = set()
-            for n in choices: uniq.add(n.attrib.get('nazwa', ''))
-            if len(choices) != len(uniq):
-                is_single_choice = False
-                break
 
         self.options = {'single': is_single_choice}
         return pre, post
 
     def handle_punkt(self, element):
-        if self.options['exercise'] and element.attrib.get('nazwa', None):
+        if self.options['exercise'] and element.attrib.get('rozw', None):
             cmd = 'radio' if self.options['single'] else 'checkbox'
+            if self.options['teacher'] and element.attrib['rozw'] == 'prawda':
+                cmd += 'checked'
             return u'<cmd name="%s"/>' % cmd, ''
         else:
             return super(Wybor, self).handle_punkt(element)
@@ -589,18 +640,19 @@ class PrawdaFalsz(Exercise):
         return pre, post
 
 
-
 def fix_lists(tree):
     lists = tree.xpath(".//lista")
     for l in lists:
         if l.text:
             p = l.getprevious()
             if p is not None:
-                if p.tail is None: p.tail = ''
+                if p.tail is None:
+                    p.tail = ''
                 p.tail += l.text
             else:
                 p = l.getparent()
-                if p.text is None: p.text = ''
+                if p.text is None:
+                    p.text = ''
                 p.text += l.text
             l.text = ''
     return tree
@@ -633,4 +685,3 @@ class EduModulePDFFormat(PDFFormat):
 
     def get_image(self, name):
         return self.wldoc.source.attachments[name]
-