Don't validate <uwaga> contents

[librarian.git] / src / librarian / pdf.py

diff --git a/src/librarian/pdf.py b/src/librarian/pdf.py
index cad66a4..b32395f 100644 (file)
--- a/src/librarian/pdf.py
+++ b/src/librarian/pdf.py
@@ -284,6 +284,14 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
         elif package_available('morefloats', 'maxfloats=19'):
             root.set('morefloats', 'new')
 
         elif package_available('morefloats', 'maxfloats=19'):
             root.set('morefloats', 'new')
 

+        if customizations is None:
+            customizations = []
+        else:
+            customizations = list(customizations)
+
+        if book_info.endnotes:
+            customizations.append('endnotes')
+

         # add customizations
         if customizations is not None:
             root.set('customizations', u','.join(customizations))
         # add customizations
         if customizations is not None:
             root.set('customizations', u','.join(customizations))


@@ -306,6 +314,7 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
         fix_hanging(document.edoc)
         fix_tables(document.edoc)
         mark_subauthors(document.edoc)
         fix_hanging(document.edoc)
         fix_tables(document.edoc)
         mark_subauthors(document.edoc)

+        document.fix_pa_akap()

 
         # wl -> TeXML
         style_filename = get_stylesheet("wl2tex")
 
         # wl -> TeXML
         style_filename = get_stylesheet("wl2tex")


@@ -320,8 +329,8 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
                 base_url,
                 ilustr.get('src')
             )
                 base_url,
                 ilustr.get('src')
             )

-            with six.moves.urllib.request.urlopen(url) as imgfile:
-                img = Image.open(imgfile)
+            imgfile = six.moves.urllib.request.urlopen(url)
+            img = Image.open(imgfile)

 
             th_format, ext, media_type = {
                 'GIF': ('GIF', 'gif', 'image/gif'),
 
             th_format, ext, media_type = {
                 'GIF': ('GIF', 'gif', 'image/gif'),


@@ -338,6 +347,8 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
             th.save(os.path.join(temp, file_name))
             ilustr.set('src', file_name)
 
             th.save(os.path.join(temp, file_name))
             ilustr.set('src', file_name)
 

+            imgfile.close()
+

         for sponsor in book_info.sponsors:
             ins = etree.Element("data-sponsor", name=sponsor)
             logo = sponsor_logo(sponsor)
         for sponsor in book_info.sponsors:
             ins = etree.Element("data-sponsor", name=sponsor)
             logo = sponsor_logo(sponsor)


@@ -414,7 +425,7 @@ def load_including_children(wldoc=None, provider=None, uri=None):
     """
 
     if uri and provider:
     """
 
     if uri and provider:

-        f = provider.by_uri(uri)
+        f = provider.by_slug(uri.slug)

         text = f.read().decode('utf-8')
         f.close()
     elif wldoc is not None:
         text = f.read().decode('utf-8')
         f.close()
     elif wldoc is not None:


@@ -425,7 +436,10 @@ def load_including_children(wldoc=None, provider=None, uri=None):
             'Neither a WLDocument, nor provider and URI were provided.'
         )
 
             'Neither a WLDocument, nor provider and URI were provided.'
         )
 

+    # Cyrrilic

     text = re.sub(r"([\u0400-\u04ff]+)", r"<alien>\1</alien>", text)
     text = re.sub(r"([\u0400-\u04ff]+)", r"<alien>\1</alien>", text)

+    # Geometric shapes.
+    text = re.sub(r"([\u25a0-\u25ff]+)", r"<alien>\1</alien>", text)

 
     document = WLDocument.from_bytes(text.encode('utf-8'),
                                      parse_dublincore=True, provider=provider)
 
     document = WLDocument.from_bytes(text.encode('utf-8'),
                                      parse_dublincore=True, provider=provider)