From 636fd6cc380f2537924532a587c70e96a386e25c Mon Sep 17 00:00:00 2001
From: Dirkjan Ochtman <dirkjan@ochtman.nl>
Date: Tue, 17 Jul 2012 13:30:06 +0200
Subject: [PATCH] Add support for abbreviations to reST translator (fixes
 #395).

---
 pelican/readers.py        | 13 +++++++++++++
 pelican/rstdirectives.py  | 20 ++++++++++++++++++--
 tests/content/article.rst |  2 ++
 tests/test_readers.py     |  8 ++++++--
 4 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/pelican/readers.py b/pelican/readers.py
index 83565918..3591c1b8 100644
--- a/pelican/readers.py
+++ b/pelican/readers.py
@@ -63,6 +63,18 @@ def render_node_to_html(document, node):
     return visitor.astext()
 
 
+class PelicanHTMLTranslator(HTMLTranslator):
+
+    def visit_abbreviation(self, node):
+        attrs = {}
+        if node.hasattr('explanation'):
+            attrs['title'] = node['explanation']
+        self.body.append(self.starttag(node, 'abbr', '', **attrs))
+
+    def depart_abbreviation(self, node):
+        self.body.append('</abbr>')
+
+
 class RstReader(Reader):
     enabled = bool(docutils)
     file_extensions = ['rst']
@@ -92,6 +104,7 @@ class RstReader(Reader):
         pub = docutils.core.Publisher(
                 destination_class=docutils.io.StringOutput)
         pub.set_components('standalone', 'restructuredtext', 'html')
+        pub.writer.translator_class = PelicanHTMLTranslator
         pub.process_programmatic_settings(None, extra_params, None)
         pub.set_source(source_path=filename)
         pub.publish()
diff --git a/pelican/rstdirectives.py b/pelican/rstdirectives.py
index 9c821310..b1f1242c 100644
--- a/pelican/rstdirectives.py
+++ b/pelican/rstdirectives.py
@@ -1,9 +1,10 @@
 # -*- coding: utf-8 -*-
-from docutils import nodes
-from docutils.parsers.rst import directives, Directive
+from docutils import nodes, utils
+from docutils.parsers.rst import directives, roles, Directive
 from pygments.formatters import HtmlFormatter
 from pygments import highlight
 from pygments.lexers import get_lexer_by_name, TextLexer
+import re
 
 INLINESTYLES = False
 DEFAULT = HtmlFormatter(noclasses=INLINESTYLES)
@@ -94,3 +95,18 @@ class YouTube(Directive):
             nodes.raw('', '</div>', format='html')]
 
 directives.register_directive('youtube', YouTube)
+
+_abbr_re = re.compile('\((.*)\)$')
+
+class abbreviation(nodes.Inline, nodes.TextElement): pass
+
+def abbr_role(typ, rawtext, text, lineno, inliner, options={}, content=[]):
+	text = utils.unescape(text)
+	m = _abbr_re.search(text)
+	if m is None:
+		return [abbreviation(text, text)], []
+	abbr = text[:m.start()].strip()
+	expl = m.group(1)
+	return [abbreviation(abbr, abbr, explanation=expl)], []
+
+roles.register_local_role('abbr', abbr_role)
diff --git a/tests/content/article.rst b/tests/content/article.rst
index 1707ab03..7109c29b 100644
--- a/tests/content/article.rst
+++ b/tests/content/article.rst
@@ -2,3 +2,5 @@ Article title
 #############
 
 This is some content. With some stuff to "typogrify".
+
+Now with added support for :abbr:`TLA (three letter acronym)`.
diff --git a/tests/test_readers.py b/tests/test_readers.py
index a921cfc2..02d6c122 100644
--- a/tests/test_readers.py
+++ b/tests/test_readers.py
@@ -47,7 +47,9 @@ class RstReaderTest(unittest.TestCase):
         # unmodified
         content, _ = readers.read_file(_filename('article.rst'))
         expected = "<p>This is some content. With some stuff to "\
-                   "&quot;typogrify&quot;.</p>\n"
+                   "&quot;typogrify&quot;.</p>\n<p>Now with added "\
+                   'support for <abbr title="three letter acronym">'\
+                   'TLA</abbr>.</p>\n'
 
         self.assertEqual(content, expected)
 
@@ -56,7 +58,9 @@ class RstReaderTest(unittest.TestCase):
             content, _ = readers.read_file(_filename('article.rst'),
                                            settings={'TYPOGRIFY': True})
             expected = "<p>This is some content. With some stuff to&nbsp;"\
-                       "&#8220;typogrify&#8221;.</p>\n"
+                       "&#8220;typogrify&#8221;.</p>\n<p>Now with added "\
+                       'support for <abbr title="three letter acronym">'\
+                       'TLA</abbr>.</p>\n'
 
             self.assertEqual(content, expected)
         except ImportError: