smartquotes: Skip emtpy text tokens without updating the last character.

git-svn-id: http://svn.code.sf.net/p/docutils/code/trunk@7585 929543f6-e4f2-0310-98a6-ba3bd3dd1d04

3 files changed, 20 insertions, 7 deletions

diff --git a/docutils/docutils/transforms/universal.py b/docutils/docutils/transforms/universal.py
index 75a47fcd6..76f08db02 100644
--- a/docutils/docutils/transforms/universal.py
+++ b/docutils/docutils/transforms/universal.py
@@ -261,7 +261,7 @@ class SmartQuotes(Transform):
                         if not isinstance(txtnode.parent,
                                           nodes.option_string)]
 
-            # language: use smart-quotes for language "lang"
+            # language: use typographical quotes for language "lang"
             lang = node.get_language_code(document_language)
             # use alternative form if `smart-quotes` setting starts with "alt":
             if alternative:
diff --git a/docutils/docutils/utils/smartquotes.py b/docutils/docutils/utils/smartquotes.py
index e5deea3ac..b5449fd5f 100644
--- a/docutils/docutils/utils/smartquotes.py
+++ b/docutils/docutils/utils/smartquotes.py
@@ -382,7 +382,7 @@ class smartchars(object):
     # For other languages see:
     # http://en.wikipedia.org/wiki/Non-English_usage_of_quotation_marks
     # http://de.wikipedia.org/wiki/Anf%C3%BChrungszeichen#Andere_Sprachen
-    quotes = {'af':        u'“”‘’',
+    quotes = {'af':           u'“”‘’',
               'af-x-altquot': u'„”‚’',
               'ca':           u'«»“”',
               'ca-x-altquot': u'“”‘’',
@@ -507,14 +507,15 @@ def educate_tokens(text_tokens, attr=default_smartypants_attr, language='en'):
 
     for (ttype, text) in text_tokens:
 
-        # skip HTML and/or XML tags (do not update last character)
-        if ttype == 'tag':
+        # skip HTML and/or XML tags as well as emtpy text tokens
+        # without updating the last character
+        if ttype == 'tag' or not text:
             yield text
             continue
 
         # skip literal text (math, literal, raw, ...)
         if ttype == 'literal':
-            prev_token_last_char = text[-1]
+            prev_token_last_char = text[-1:]
             yield text
             continue
 
diff --git a/docutils/test/test_transforms/test_smartquotes.py b/docutils/test/test_transforms/test_smartquotes.py
index 14332d2e1..3c059133a 100644
--- a/docutils/test/test_transforms/test_smartquotes.py
+++ b/docutils/test/test_transforms/test_smartquotes.py
@@ -95,9 +95,12 @@ u"""\
 Quotes and inline-elements:
 
 * Around "_`targets`", "*emphasized*" or "``literal``" text
-  and links to "targets_".                                          
+  and links to "targets_".
 
 * Inside *"emphasized"* or other `inline "roles"`
+
+Do not drop characters from intra-word inline markup like
+*re*\ ``Structured``\ *Text*.
 """,
 u"""\
 <document source="test data">
@@ -127,7 +130,16 @@ u"""\
                     “emphasized”
                  or other \n\
                 <title_reference>
-                    inline “roles”\
+                    inline “roles”
+    <paragraph>
+        Do not drop characters from intra-word inline markup like
+        <emphasis>
+            re
+        <literal>
+            Structured
+        <emphasis>
+            Text
+        .\
 """],
 ["""\
 .. class:: language-de