fixes for edge cases

[librarian.git] / src / librarian / elements / poetry / strofa.py

diff --git a/src/librarian/elements/poetry/strofa.py b/src/librarian/elements/poetry/strofa.py
index 7df549f..e925571 100644 (file)
--- a/src/librarian/elements/poetry/strofa.py
+++ b/src/librarian/elements/poetry/strofa.py
@@ -1,16 +1,30 @@
 from copy import copy
 from copy import copy

+import re

 from ..base import WLElement
 from .wers import Wers
 
 
 class Strofa(WLElement):
 from ..base import WLElement
 from .wers import Wers
 
 
 class Strofa(WLElement):

+    SHOULD_HAVE_ID = True
+

     TXT_TOP_MARGIN = 2
     TXT_BOTTOM_MARGIN = 2
     TXT_LEGACY_TOP_MARGIN = 1
     TXT_LEGACY_BOTTOM_MARGIN = 0
 
     TXT_TOP_MARGIN = 2
     TXT_BOTTOM_MARGIN = 2
     TXT_LEGACY_TOP_MARGIN = 1
     TXT_LEGACY_BOTTOM_MARGIN = 0
 

-    HTML_TAG = 'div'
-    HTML_CLASS = 'stanza'
+    EPUB_TAG = HTML_TAG = 'div'
+    EPUB_CLASS = HTML_CLASS = 'stanza'
+
+    def epub_build(self, builder):
+        super().epub_build(builder)
+        builder.start_element(
+            'div',
+            {
+                'class': 'stanza-spacer'
+            }
+        )
+        builder.push_text('\u00a0');
+        builder.end_element()

     
     def get_verses(self):
         from librarian.parser import parser
     
     def get_verses(self):
         from librarian.parser import parser


@@ -20,7 +34,7 @@ class Strofa(WLElement):
         ]
         if self.text:
             # Before any tags. These are text-only verses.
         ]
         if self.text:
             # Before any tags. These are text-only verses.

-            pieces = self.text.split('/')
+            pieces = re.split(r"/\s+", self.text)

             for piece in pieces[:-1]:
                 verses[-1].text = piece
                 verses.append(parser.makeelement('wers'))
             for piece in pieces[:-1]:
                 verses[-1].text = piece
                 verses.append(parser.makeelement('wers'))


@@ -28,7 +42,7 @@ class Strofa(WLElement):
 
         for child in self:
             if child.tail:
 
         for child in self:
             if child.tail:

-                pieces = child.tail.split('/')
+                pieces = re.split(r"/\s+", child.tail)

                 child_copy = copy(child)
                 child_copy.tail = pieces[0]
                 verses[-1].append(child_copy)
                 child_copy = copy(child)
                 child_copy.tail = pieces[0]
                 verses[-1].append(child_copy)