don't textsc in headers
[librarian.git] / librarian / pypdf.py
index 387f647..6d6e0aa 100644 (file)
@@ -20,6 +20,7 @@ import re
 import random
 from copy import deepcopy
 from subprocess import call, PIPE
 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 Texml.processor import process
 from lxml import etree
@@ -52,7 +53,7 @@ def escape(really):
 
 
 def cmd(name, parms=None):
 
 
 def cmd(name, parms=None):
-    def wrap(self, element):
+    def wrap(self, element=None):
         pre, post = tag_open_close('cmd', name=name)
 
         if parms:
         pre, post = tag_open_close('cmd', name=name)
 
         if parms:
@@ -60,9 +61,12 @@ def cmd(name, parms=None):
                 e = etree.Element("parm")
                 e.text = parm
                 pre += etree.tostring(e)
                 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
 
 
     return wrap
 
 
@@ -104,11 +108,15 @@ class EduModule(Xmill):
           u'</cmd>'
 
     @escape(True)
           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):
 
     @escape(1)
     def get_title(self, element):
@@ -129,9 +137,13 @@ class EduModule(Xmill):
             \\usepackage{morefloats}
         }{}'''),
     u'''\\def\\authors{%s}''' % self.get_authors(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'''\\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>']
 
     u'''\\def\\rightsinfo{%s}''' % self.get_rightsinfo(element),
     u'</TeXML>']
 
@@ -143,7 +155,7 @@ class EduModule(Xmill):
         return u"""
     <env name="document">
     <cmd name="maketitle"/>
         return u"""
     <env name="document">
     <cmd name="maketitle"/>
-    """, """</env>"""
+    """, """<cmd name="editorialsection" /></env>"""
 
     @escape(1)
     def handle_texcommand(self, element):
 
     @escape(1)
     def handle_texcommand(self, element):
@@ -227,7 +239,7 @@ class EduModule(Xmill):
         counter = self.activity_counter
 
         return u"""
         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>
 <cmd name="activitycounter"><parm>%(counter)d.</parm></cmd>
 <cmd name="activityinfo"><parm>
  <cmd name="activitytime"><parm>%(czas)s</parm></cmd>
@@ -259,10 +271,13 @@ class EduModule(Xmill):
             return None
         ltype = element.attrib.get('typ', 'punkt')
         if ltype == 'slowniczek':
             return None
         ltype = element.attrib.get('typ', 'punkt')
         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/slowniczek'
             sxml = None
             if surl:
             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',
             self.options = {'slowniczek': True, 'slowniczek_xml': sxml }
 
         listcmd = {'num': 'enumerate',
@@ -301,7 +316,7 @@ class EduModule(Xmill):
         definiens_s = ''
 
         # let's pull definiens from another document
         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)
             sxml = self.options['slowniczek_xml']
             assert element.text != ''
             defloc = sxml.xpath("//definiendum[text()='%s']" % element.text)
@@ -348,9 +363,38 @@ class EduModule(Xmill):
 
     def handle_link(self, element):
         if element.attrib.get('url'):
 
     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:
         else:
-            return cmd('em')(self, element)
+            return cmd('emph')(self, element)
+
+    def handle_obraz(self, element):
+        frmt = self.options['format']
+        name = element.attrib['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):
 
 
 class Exercise(EduModule):
@@ -547,9 +591,27 @@ def fix_lists(tree):
 
 
 class EduModulePDFFormat(PDFFormat):
 
 
 class EduModulePDFFormat(PDFFormat):
+    style = get_resource('res/styles/edumed/pdf/edumed.sty')
+
     def get_texml(self):
     def get_texml(self):
-        edumod = EduModule({"teacher": self.customization.get('teacher')})
+        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
         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]
+