X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/dd3939e62196740f3c4eecf62a57f2d38a91a6f0..e5c95de3a288109e039276eeb2cac65cf8b0080e:/librarian/epub.py?ds=sidebyside

diff --git a/librarian/epub.py b/librarian/epub.py
index b079d65..08e181e 100644
--- a/librarian/epub.py
+++ b/librarian/epub.py
@@ -47,9 +47,8 @@ def set_hyph_language(source_tree):
         pass
     
 def hyphenate_and_fix_conjunctions(source_tree, hyph):
-    """ hyphenate only powiesc, opowiadanie and wywiad tag"""
     if hyph is not None:
-        texts = etree.XPath('//*[self::powiesc|self::opowiadanie|self::wywiad]//text()')(source_tree)
+        texts = etree.XPath('/utwor/*[2]//text()')(source_tree)
         for t in texts:
             parent = t.getparent()
             newt = ''
@@ -285,7 +284,10 @@ class TOC(object):
 
             nav_label = nav_map.makeelement(NCXNS('navLabel'))
             text = nav_map.makeelement(NCXNS('text'))
-            text.text = re.sub(r'\n', ' ', child.name)
+            if child.name is not None:
+                text.text = re.sub(r'\n', ' ', child.name)
+            else:
+                text.text = child.name
             nav_label.append(text)
             nav_point.append(nav_label)
 
@@ -388,7 +390,7 @@ def transform_chunk(chunk_xml, chunk_no, annotations, empty=False, _empty_html_s
         replace_by_verse(chunk_xml)
         html_tree = xslt(chunk_xml, get_resource('epub/xsltScheme.xsl'))
         chars = used_chars(html_tree.getroot())
-        output_html = etree.tostring(html_tree, method="html", pretty_print=True)
+        output_html = etree.tostring(html_tree, method="html", encoding='UTF-8', pretty_print=True)
     return output_html, toc, chars
 
 
@@ -420,7 +422,7 @@ def transform(wldoc, verbose=False,
             html_tree = xslt(wldoc.edoc, get_resource('epub/xsltTitle.xsl'))
             chars = used_chars(html_tree.getroot())
             zip.writestr('OPS/title.html',
-                 etree.tostring(html_tree, method="html", pretty_print=True))
+                 etree.tostring(html_tree, method="html", encoding='UTF-8', pretty_print=True))
             # add a title page TOC entry
             toc.add(u"Strona tytułowa", "title.html")
         elif wldoc.book_info.parts:
@@ -431,7 +433,7 @@ def transform(wldoc, verbose=False,
             else:
                 html_tree = xslt(wldoc.edoc, get_resource('epub/xsltChunkTitle.xsl'))
                 chars = used_chars(html_tree.getroot())
-                html_string = etree.tostring(html_tree, method="html", pretty_print=True)
+                html_string = etree.tostring(html_tree, method="html", encoding='UTF-8', pretty_print=True)
             zip.writestr('OPS/part%d.html' % chunk_counter, html_string)
             add_to_manifest(manifest, chunk_counter)
             add_to_spine(spine, chunk_counter)
@@ -527,7 +529,7 @@ def transform(wldoc, verbose=False,
         cover_tree = etree.parse(get_resource('epub/cover.html'))
         cover_tree.find('//' + XHTMLNS('img')).set('src', cover_name)
         zip.writestr('OPS/cover.html', etree.tostring(
-                        cover_tree, method="html", pretty_print=True))
+                        cover_tree, method="html", encoding='UTF-8', pretty_print=True))
 
         if bound_cover.uses_dc_cover:
             if document.book_info.cover_by:
@@ -576,7 +578,7 @@ def transform(wldoc, verbose=False,
         html_tree = xslt(annotations, get_resource('epub/xsltAnnotations.xsl'))
         chars = chars.union(used_chars(html_tree.getroot()))
         zip.writestr('OPS/annotations.html', etree.tostring(
-                            html_tree, method="html", pretty_print=True))
+                            html_tree, method="html", encoding='UTF-8', pretty_print=True))
 
     toc.add("Wesprzyj Wolne Lektury", "support.html")
     manifest.append(etree.fromstring(
@@ -595,7 +597,7 @@ def transform(wldoc, verbose=False,
     html_tree = xslt(document.edoc, get_resource('epub/xsltLast.xsl'))
     chars.update(used_chars(html_tree.getroot()))
     zip.writestr('OPS/last.html', etree.tostring(
-                        html_tree, method="html", pretty_print=True))
+                        html_tree, method="html", encoding='UTF-8', pretty_print=True))
 
     if not flags or not 'without-fonts' in flags:
         # strip fonts