From 5d3ab5b9642b3cf3ec557ff72fa72ec9e6ab5195 Mon Sep 17 00:00:00 2001
From: Barry Steyn <barry.steyn@gmail.com>
Date: Wed, 19 Feb 2014 08:18:43 -0800
Subject: [PATCH 1/2] Logic for MathMl; Fixed Bug; Updated Readme

---
 latex/Readme.md | 40 ++++++++++++++++++++++++++---------
 latex/latex.py  | 56 +++++++++++++++++++++++++++++++++----------------
 2 files changed, 68 insertions(+), 28 deletions(-)

diff --git a/latex/Readme.md b/latex/Readme.md
index 49888b8..8ee917d 100644
--- a/latex/Readme.md
+++ b/latex/Readme.md
@@ -1,10 +1,20 @@
 Latex Plugin For Pelican
 ========================
 
-This plugin allows you to write mathematical equations in your articles using Latex.
-It uses the MathJax Latex JavaScript library to render latex that is embedded in
-between `$..$` for inline math and `$$..$$` for displayed math. It also allows for
-writing equations in by using `\begin{equation}`...`\end{equation}`.
+This plugin allows you to write mathematical equations in your articles using Latex and MathMl.
+It uses the MathJax Latex JavaScript library to render *Latex* and *MathMl* that is embedded in
+your site.
+
+### Latex
+Anything between `$..$` (inline math) and `$$..$$` (displayed math) will be recognized as
+Latex. In addition, anything between between `\begin` and `\end` macros will also be 
+recognized as Latex. For example, `\begin{equation}`...`\end{equation}` would be used to 
+render math equations with numbering.
+
+Within recognized Latex as described above, Latex macros can be used.
+
+### MathMl
+Anything between `<math>` and `</math>` tags will be recognized as *MathMl*.
 
 Installation
 ------------
@@ -13,7 +23,7 @@ Then use as follows by adding the following to your settings.py:
 
     PLUGINS = ["latex"]
 
-Your site is now capable of rendering latex math using the mathjax JavaScript
+Your site is now capable of rendering math math using the mathjax JavaScript
 library. No alterations to the template file is needed.
 
 ### Typogrify
@@ -22,15 +32,24 @@ and Latex will be rendered correctly). In order for this to happen,
 version 2.07 (or above) of typogrify is required. In fact, this plugin expects
 that at least version 2.07 is present and will fail without it.
 
+### Summaries
+Summaries that contain math are processed to ensure that math is not off. If
+math is cut off, it will add it back into the summary.
+
+### Templates
+No alteration is needed to a template for this plugin to work. Just install
+the plugin and start writing your Math.
+
 Usage
 -----
 ### Backward Compatibility
 This plugin is backward compatible in the sense that it
-accompishes what previous versions did without needing any setup in the
-metadata or settings files.
+will render previous setups correctly. This is because those
+settings and metadata information is ignored by this version. Therefore
+you can remove them to neaten up your site
 
 ### Settings File
-Extra options regarding how mathjax renders latex can be set in the settings
+Extra options regarding how mathjax renders math can be set in the settings
 file. These options are in a dictionary variable called `LATEX` in the pelican
 settings file.
 
@@ -40,7 +59,8 @@ The dictionary can be set with the following keys:
 html. For example, setting `wrap` to `'mathjax'` would wrap all math inside
 `<mathjax>...</mathjax>` tags. If typogrify is set to True, then math needs
 to be wrapped in tags and `wrap` will therefore default to `mathjax` if not
-set.
+set. `wrap` cannot be set to `'math'` because this tag is reserved for 
+mathml notation
  * `align`: controls how displayed math will be aligned. Can be set to either
 `left`, `right` or `center` (default is `center`).
  * `indent`: if `align` not set to `center`, then this controls the indent
@@ -51,7 +71,7 @@ level (default is `0em`).
 loading.
  * `color`: controls the color of the mathjax rendered font.
 
-For example, in settings.py, the following would make latex render in blue and
+For example, in settings.py, the following would make math render in blue and
 displaymath align to the left:
 
     LATEX = {'color':'blue','align':left}
diff --git a/latex/latex.py b/latex/latex.py
index b1022e0..f0570be 100644
--- a/latex/latex.py
+++ b/latex/latex.py
@@ -28,11 +28,12 @@ from pelican import contents
 import re
 
 # Global Variables
+_TYPOGRIFY = False  # used to determine if we should process typogrify
 _WRAP_TAG = None  # the tag to wrap mathjax in (needed to play nicely with typogrify or for template designers)
-_LATEX_REGEX = re.compile(r'(\$\$|\$|\\begin\{(.+?)\}).*?\1|\\end\{\2\}', re.DOTALL | re.IGNORECASE) #  used to detect latex
+_LATEX_REGEX = re.compile(r'(\$\$|\$|\\begin\{(.+?)\}|<(math).*?>).*?(\1|\\end\{\2\}|</\3>)', re.DOTALL | re.IGNORECASE) #  used to detect latex
 _LATEX_SUMMARY_REGEX = None  # used to match latex in summary
 _LATEX_PARTIAL_REGEX = None  # used to match latex that has been cut off in summary
-_MATHJAX_SETTINGS = {}  # Settings that can be specified by the user, used to control mathjax script settings
+_MATHJAX_SETTINGS = {}  # settings that can be specified by the user, used to control mathjax script settings
 _MATHJAX_SCRIPT="""
 <script type= "text/javascript">
     if (!document.getElementById('mathjaxscript_pelican')) {{
@@ -124,7 +125,11 @@ def wrap_latex(content, ignore_within):
         # determine if the tags are within <pre> and <code> blocks
         ignore = binary_search(match.span(1), ignore_within) and binary_search(match.span(2), ignore_within)
 
-        if ignore:
+        if ignore or match.group(3) == 'math':
+            if match.group(3) == 'math':
+                # Will detect mml, but not wrap anything around it
+                wrap_latex.foundlatex = True
+
             return match.group(0)
         else:
             wrap_latex.foundlatex = True
@@ -142,7 +147,7 @@ def process_summary(instance, ignore_within):
 
     process_summary.altered_summary = False
     insert_mathjax_script = False
-    endtag = '</%s>' % _WRAP_TAG if _WRAP_TAG != None else ''
+    end_tag = '</%s>' % _WRAP_TAG if _WRAP_TAG != None else ''
 
     # use content's _get_summary method to obtain summary
     summary = instance._get_summary()
@@ -158,23 +163,33 @@ def process_summary(instance, ignore_within):
 
     # Repair the latex if it was cut off mathitem will be the final latex
     # code  matched that is not within <pre> or <code> tags
-    if mathitem and mathitem.group(4) == ' ...':
-        end = r'\end{%s}' % mathitem.group(3) if mathitem.group(3) is not None else mathitem.group(2)
-        latex_match = re.search('%s.*?%s' % (re.escape(mathitem.group(1)), re.escape(end)), instance._content, re.DOTALL | re.IGNORECASE)
-        new_summary = summary.replace(mathitem.group(0), latex_match.group(0)+'%s ...' % endtag)
+    if mathitem and '...' in mathitem.group(6):
+        if mathitem.group(3) is not None:
+            end = r'\end{%s}' % mathitem.group(3)
+        elif mathitem.group(4) is not None:
+            end = r'</math>'
+        elif mathitem.group(2) is not None:
+            end = mathitem.group(2)
 
-        if new_summary != summary:
-            return new_summary+_MATHJAX_SCRIPT.format(**_MATHJAX_SETTINGS)
+        search_regex = r'%s(%s.*?%s)' % (re.escape(instance._content[0:mathitem.start(1)]), re.escape(mathitem.group(1)), re.escape(end))
+        latex_match = re.search(search_regex, instance._content, re.DOTALL | re.IGNORECASE)
+
+        if latex_match:
+            new_summary = summary.replace(mathitem.group(0), latex_match.group(1)+'%s ...' % end_tag)
+
+            if new_summary != summary:
+                return new_summary+_MATHJAX_SCRIPT.format(**_MATHJAX_SETTINGS)
 
     def partial_regex(match):
         """function for use in re.sub"""
-        if binary_search(match.span(), ignore_within):
+        if binary_search(match.span(3), ignore_within):
             return match.group(0)
 
         process_summary.altered_summary = True
         return match.group(1) + match.group(4)
 
     # check for partial latex tags at end. These must be removed
+
     summary = _LATEX_PARTIAL_REGEX.sub(partial_regex, summary)
 
     if process_summary.altered_summary:
@@ -252,9 +267,10 @@ def process_content(instance):
     # with latex, we set it to False. This means that the default reader will
     # not call typogrify, so it is called here, where we are able to control
     # logic for it ignore latex if necessary
-    if process_content.typogrify:
+    if _TYPOGRIFY:
         # Tell typogrify to ignore the tags that latex has been wrapped in
-        ignore_tags = [_WRAP_TAG] if _WRAP_TAG else None
+        # also, typogrify must always ignore mml (math) tags
+        ignore_tags = [_WRAP_TAG,'math'] if _WRAP_TAG else ['math']
 
         # Exact copy of the logic as found in the default reader
         from typogrify.filters import typogrify
@@ -278,6 +294,7 @@ def pelican_init(pelicanobj):
     False should it be set to True.
     """
 
+    global _TYPOGRIFY
     global _WRAP_TAG
     global _LATEX_SUMMARY_REGEX
     global _LATEX_PARTIAL_REGEX
@@ -298,7 +315,7 @@ def pelican_init(pelicanobj):
         if pelicanobj.settings['TYPOGRIFY'] == True:
             pelicanobj.settings['TYPOGRIFY'] = False
             _WRAP_TAG = 'mathjax' # default to wrap mathjax content inside of
-            process_content.typogrify = True
+            _TYPOGRIFY = True
     except KeyError:
         pass
 
@@ -311,10 +328,13 @@ def pelican_init(pelicanobj):
         pass
 
     # regular expressions that depend on _WRAP_TAG are set here
-    tagstart = r'<%s>' % _WRAP_TAG if not _WRAP_TAG is None else ''
-    tagend = r'</%s>' % _WRAP_TAG if not _WRAP_TAG is None else ''
-    latex_summary_regex = r'((\$\$|\$|\\begin\{(.+?)\}).+?)(\2|\\end\{\3\}|\s?\.\.\.)(%s)?' % tagend
-    latex_partial_regex = r'(.*)(%s)(\\.*?|\$.*?)(\s?\.\.\.)(%s)' % (tagstart, tagend)
+    tag_start= r'<%s>' % _WRAP_TAG if not _WRAP_TAG is None else ''
+    tag_end = r'</%s>' % _WRAP_TAG if not _WRAP_TAG is None else ''
+    latex_summary_regex = r'((\$\$|\$|\\begin\{(.+?)\}|<(math)(\s.*?)?>).+?)(\2|\\end\{\3\}|\s?\.\.\.)(%s|</\4>)?' % tag_end
+
+    # NOTE: The logic in _get_summary will handle <math> correctly because it
+    # is perceived as an html tag. Therefore we are only interested in handling non mml
+    latex_partial_regex = r'(.*)(%s)(\\\S*?|\$)\s*?(\s?\.\.\.)(%s)?$' % (tag_start, tag_end)
 
     _LATEX_SUMMARY_REGEX = re.compile(latex_summary_regex, re.DOTALL | re.IGNORECASE)
     _LATEX_PARTIAL_REGEX = re.compile(latex_partial_regex, re.DOTALL | re.IGNORECASE)

From 64dca25e86aac21eec593574231f8be9447a13a2 Mon Sep 17 00:00:00 2001
From: Barry Steyn <barry.steyn@gmail.com>
Date: Wed, 19 Feb 2014 10:19:49 -0800
Subject: [PATCH 2/2] Fixed slight error with mathml regex in summary

---
 latex/latex.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/latex/latex.py b/latex/latex.py
index f0570be..930e686 100644
--- a/latex/latex.py
+++ b/latex/latex.py
@@ -330,7 +330,7 @@ def pelican_init(pelicanobj):
     # regular expressions that depend on _WRAP_TAG are set here
     tag_start= r'<%s>' % _WRAP_TAG if not _WRAP_TAG is None else ''
     tag_end = r'</%s>' % _WRAP_TAG if not _WRAP_TAG is None else ''
-    latex_summary_regex = r'((\$\$|\$|\\begin\{(.+?)\}|<(math)(\s.*?)?>).+?)(\2|\\end\{\3\}|\s?\.\.\.)(%s|</\4>)?' % tag_end
+    latex_summary_regex = r'((\$\$|\$|\\begin\{(.+?)\}|<(math)(\s.*?)?>).+?)(\2|\\end\{\3\}|</\4>|\s?\.\.\.)(%s|</\4>)?' % tag_end
 
     # NOTE: The logic in _get_summary will handle <math> correctly because it
     # is perceived as an html tag. Therefore we are only interested in handling non mml