samp and tt as skipped elements, compile regular expression from tags_to_skip list

3 files changed, 65 insertions, 11 deletions

diff --git a/CHANGES.rst b/CHANGES.rst
index 201a7c5..07c0b3f 100644
--- a/CHANGES.rst
+++ b/CHANGES.rst
@@ -13,6 +13,9 @@ development:
     - add ``--version``
     - add ``install_test`` target for checking package installation
     - add ``test`` target for all tests
+    - add ``samp`` and ``tt`` to be skipped HTML elements
+    - remove ``tags_to_skip_regex`` and add ``tags_to_skip`` as a list of
+      skipped HTML with a helper function to compile a regular expreesion
     - deprecate str-type ``attr`` with:
         - redesign attr input with new ``Attr`` object
             - ``"-1"`` now is ``Attr.s`` (``"s"``)
diff --git a/README.rst b/README.rst
index cb5cc23..2a46a32 100644
--- a/README.rst
+++ b/README.rst
@@ -7,6 +7,8 @@ smartypants.py is a Python port of SmartyPants_.
 .. _SmartyPants: http://daringfireball.net/projects/smartypants/
 
 .. contents:: **Contents**
+  :local:
+  :backlinks: top
 
 
 Description
@@ -24,10 +26,10 @@ ASCII straight quotes, plain dashes, and plain dots, but your published
 posts (and final HTML output) will appear with smart quotes, em-dashes,
 and proper ellipses.
 
-SmartyPants does not modify characters within ``<pre>``, ``<code>``, ``<kbd>``,
-``<math>`` or ``<script>`` tag blocks. Typically, these tags are used to
-display text where smart quotes and other "smart punctuation" would not be
-appropriate, such as source code or example markup.
+SmartyPants does not modify contents in some HTML element, see `Skipped HTML
+Elements`_. Typically, these tags are used to display text where smart quotes
+and other "smart punctuation" would not be appropriate, such as source code or
+example markup.
 
 
 Installation
@@ -93,7 +95,10 @@ foot and inch marks: 6'2" tall; a 17" iMac.
 Options
 =======
 
-smartypants.py only accepts SmartyPants attributes, which are accessible via
+Attributes
+----------
+
+``smartypants()`` only accepts SmartyPants attributes, which are accessible via
 ``smartypants.Attr``:
 
 ``Attr.q``
@@ -181,6 +186,31 @@ When using in command-line, use only the attribute names and drop ``set``:
   echo "$text" | smartypants -a "$attrs"
 
 
+Skipped HTML elements
+---------------------
+
+By default, there are a few HTML elements that ``smartypants()`` do not try to
+be smart with them:
+
+.. code:: python
+
+  tags_to_skip = ['pre', 'samp', 'code', 'tt', 'kbd', 'script', 'math']
+
+If you need to change, for example, adding additional tags and remove one of
+them:
+
+.. code:: python
+
+  >>> from smartypants import tags_to_skip as tags
+  >>> tags.append('a')
+  >>> tags.remove('code')
+  >>> tags
+  ['pre', 'samp', 'tt', 'kbd', 'script', 'math', 'a']
+
+The ``tags_to_skip`` is compiled into a regular expression for being used by
+``smartypants()``. You could actually overwrite ``_tags_to_skip_regex()`` and
+return your own regular expression.
+
 Bugs
 ====
 
@@ -195,6 +225,8 @@ to illustrate.
 History
 =======
 
+*For changelog, please see CHANGES.rst*
+
 `John Gruber`_ did all of the hard work of writing this software in Perl for
 `Movable Type`_ and almost all of this useful documentation.  `Chad Miller`_
 ported it to Python to use with Pyblosxom_.
@@ -227,8 +259,8 @@ package ownership on PyPI. It has also officially supported Python 3.
 .. _Yu-Jie Lin: http://yjl.im/
 
 
-Copyright and License
-=====================
+Copyright
+=========
 
 ::
 
diff --git a/smartypants.py b/smartypants.py
index fdee3b4..9b0df5b 100755
--- a/smartypants.py
+++ b/smartypants.py
@@ -54,10 +54,29 @@ class _Attr(object):
 
 
 Attr = _Attr()
-
 default_smartypants_attr = Attr.set1
 
-tags_to_skip_regex = re.compile('<(/)?(pre|code|kbd|script|math)[^>]*>', re.I)
+
+tags_to_skip = ['pre', 'samp', 'code', 'tt', 'kbd', 'script', 'math']
+
+
+def _tags_to_skip_regex(tags=None):
+    """
+    Convert a list of skipped tags into regular expression
+
+    >>> f = _tags_to_skip_regex
+    >>> print(f().pattern)
+    <(/)?(pre|code|tt|kbd|script|math)[^>]*>
+    >>> print(f(['foo', 'bar']).pattern)
+    <(/)?(foo|bar)[^>]*>
+    """
+    if tags is None:
+        tags = tags_to_skip
+
+    if isinstance(tags, (list, tuple)):
+        tags = '|'.join(tags)
+
+    return re.compile('<(/)?(%s)[^>]*>' % tags, re.I)
 
 
 def verify_installation(request):
@@ -104,8 +123,6 @@ def cb_story(args):
     args["entry"]["title"] = smartypants(args["entry"]["title"], attributes)
 
 
-### interal functions below here
-
 def _str_attr_to_int(str_attr):
     """
     Convert deprecated str-type attr into int
@@ -183,6 +200,8 @@ def smartypants(text, attr=None):
     # token, to use as context to curl single-
     # character quote tokens correctly.
 
+    tags_to_skip_regex = _tags_to_skip_regex()
+
     for cur_token in tokens:
         if cur_token[0] == "tag":
             # Don't mess with quotes inside some tags.  This does not handle