some improvement

converters/template.py

@@ -1,277 +1,289 b''
 """Base classes for the notebook conversion pipeline.
 
 This module defines Converter, from which all objects designed to implement
 a conversion of IPython notebooks to some other format should inherit.
 """
 #-----------------------------------------------------------------------------
 # Copyright (c) 2012, the IPython Development Team.
 #
 # Distributed under the terms of the Modified BSD License.
 #
 # The full license is in the file COPYING.txt, distributed with this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 from __future__ import print_function, absolute_import
 
 # Stdlib imports
 import io
 import os
 import re
 from IPython.utils import path
 
 from jinja2 import Environment, FileSystemLoader
 env = Environment(
         loader=FileSystemLoader('./templates/'),
         extensions=['jinja2.ext.loopcontrols']
         )
 
 texenv = Environment(
         loader=FileSystemLoader('./templates/tex/'),
         extensions=['jinja2.ext.loopcontrols']
         )
 
 # IPython imports
 from IPython.nbformat import current as nbformat
 from IPython.config.configurable import Configurable
 from IPython.utils.traitlets import ( Unicode, Any, List)
 
 # Our own imports
 from IPython.utils.text import indent
 from .utils import remove_ansi
 from markdown import markdown
 from .utils import highlight, ansi2html
 from .utils import markdown2latex
 #-----------------------------------------------------------------------------
 # Class declarations
 #-----------------------------------------------------------------------------
 def rm_fake(strng):
     return strng.replace('/files/', '')
 
 class ConversionException(Exception):
     pass
 
 
 def python_comment(string):
     return '# '+'\n# '.join(string.split('\n'))
 
 
 
 def header_body():
     """Return the body of the header as a list of strings."""
 
     from pygments.formatters import HtmlFormatter
 
     header = []
     static = os.path.join(path.get_ipython_package_dir(),
     'frontend', 'html', 'notebook', 'static',
     )
     here = os.path.split(os.path.realpath(__file__))[0]
     css = os.path.join(static, 'css')
     for sheet in [
         # do we need jquery and prettify?
         # os.path.join(static, 'jquery', 'css', 'themes', 'base',
         # 'jquery-ui.min.css'),
         # os.path.join(static, 'prettify', 'prettify.css'),
         os.path.join(css, 'boilerplate.css'),
         os.path.join(css, 'fbm.css'),
         os.path.join(css, 'notebook.css'),
         os.path.join(css, 'renderedhtml.css'),
         # our overrides:
         os.path.join(here, '..', 'css', 'static_html.css'),
     ]:
 
         with io.open(sheet, encoding='utf-8') as f:
             s = f.read()
             header.append(s)
 
     pygments_css = HtmlFormatter().get_style_defs('.highlight')
     header.append(pygments_css)
     return header
 
-
+# todo, make the key part configurable.
 def _new_figure(data, fmt, count):
     """Create a new figure file in the given format.
 
     Returns a path relative to the input file.
     """
     figname = '_fig_%02i.%s' % (count, fmt)
 
     # Binary files are base64-encoded, SVG is already XML
     if fmt in ('png', 'jpg', 'pdf'):
         data = data.decode('base64')
 
     return figname,data
 
 
 
 
 inlining = {}
 inlining['css'] = header_body()
 
 
 
 
 
 
 env.filters['pycomment'] = python_comment
 env.filters['indent'] = indent
 env.filters['rm_fake'] = rm_fake
 env.filters['rm_ansi'] = remove_ansi
 env.filters['markdown'] = markdown
 env.filters['highlight'] = highlight
 env.filters['ansi2html'] = ansi2html
 
 
 
 LATEX_SUBS = (
     (re.compile(r'\\'), r'\\textbackslash'),
     (re.compile(r'([{}_#%&$])'), r'\\\1'),
     (re.compile(r'~'), r'\~{}'),
     (re.compile(r'\^'), r'\^{}'),
     (re.compile(r'"'), r"''"),
     (re.compile(r'\.\.\.+'), r'\\ldots'),
 )
 
 def escape_tex(value):
     newval = value
     for pattern, replacement in LATEX_SUBS:
         newval = pattern.sub(replacement, newval)
     return newval
 
 texenv.block_start_string = '((*'
 texenv.block_end_string = '*))'
 texenv.variable_start_string = '((('
 texenv.variable_end_string = ')))'
 texenv.comment_start_string = '((='
 texenv.comment_end_string = '=))'
 texenv.filters['escape_tex'] = escape_tex
 
 texenv.filters['pycomment'] = python_comment
 texenv.filters['indent'] = indent
 texenv.filters['rm_fake'] = rm_fake
 texenv.filters['rm_ansi'] = remove_ansi
 texenv.filters['markdown'] = markdown
 texenv.filters['highlight'] = highlight
 texenv.filters['ansi2html'] = ansi2html
 texenv.filters['markdown2latex'] = markdown2latex
-markdown2latex
 
+def cell_preprocessor(function):
+    """ wrap a function to be executed on all cells of a notebook
 
-def haspyout_transformer(nb,_):
+    wrapped function  parameters :
+    cell  : the cell
+    other : external resources
+    index : index of the cell
+    """
+    def wrappedfunc(nb,other):
     for worksheet in nb.worksheets:
-        for cell in worksheet.cells:
+            for index, cell in enumerate(worksheet.cells):
+                worksheet.cells[index],other= function(cell,other,index)
+        return nb,other
+    return wrappedfunc
+
+
+
+@cell_preprocessor
+def haspyout_transformer(cell, other, count):
+    """
+    Add a haspyout flag to cell that have it
+    
+    Easier for templating, where you can't know in advance
+    wether to write the out prompt
+
+    """
             cell.type = cell.cell_type
             cell.haspyout = False
             for out in cell.get('outputs', []):
                 if out.output_type == 'pyout':
                     cell.haspyout = True
                     break
-    return nb,_
+    return cell,other
 
 
-def outline_figure_transformer(nb,other):
-    count=0
-    for worksheet in nb.worksheets:
-        for cell in worksheet.cells:
-            cell.type = cell.cell_type
+@cell_preprocessor
+def outline_figure_transformer(cell,other,count):
             for i,out in enumerate(cell.get('outputs', [])):
-                print('loop outputs',out.output_type) 
                 for type in ['html', 'pdf', 'svg', 'latex', 'png', 'jpg', 'jpeg']:
                     if out.hasattr(type):
                         figname,data = _new_figure(out[type], type,count)
                         cell.outputs[i][type] = figname
-                        out[type] = figname
-                        print('set',type, 'to' ,figname)
+                out['key_'+type] = figname
                         other[figname] = data
                         count = count+1
     return nb,other
 
 
-def print_transformer(nb,other):
-    count=0
-    for worksheet in nb.worksheets:
-        for cell in worksheet.cells:
-            cell.type = cell.cell_type
-            for i,out in enumerate(cell.get('outputs', [])):
-                print(cell.outputs) 
-    return nb,other
-
 class ConverterTemplate(Configurable):
     """ A Jinja2 base converter templates"""
 
     display_data_priority = List(['html', 'pdf', 'svg', 'latex', 'png', 'jpg', 'jpeg' , 'text'],
             config=True,
               help= """
                     A list of ast.NodeTransformer subclass instances, which will be applied
                     to user input before code is run.
                     """
             )
+
+    extract_figures = Bool(False,
+            config=True,
+              help= """
+                    wether to remove figure data from ipynb and store them in auxiliary
+                    dictionnary
+                    """
+            )
     #-------------------------------------------------------------------------
     # Instance-level attributes that are set in the constructor for this
     # class.
     #-------------------------------------------------------------------------
     infile = Any()
 
 
     infile_dir = Unicode()
-    def display_data_priority_changed(self, name, old, new):
-        print('== changed', name,old,new)
 
     def filter_data_type(self,output):
         for fmt in self.display_data_priority:
             if fmt in output:
                 return [fmt]
 
     def __init__(self, tplfile='fullhtml', preprocessors=[], config=None,tex_environement=False, **kw):
         """
         tplfile : jinja template file to process.
 
         config: the Configurable confg object to pass around
 
         preprocessors: list of function to run on ipynb json data before conversion
         to extract/inline file,
 
         """
         self.env = texenv if tex_environement else env
         self.ext = '.tplx' if tex_environement else '.tpl' 
         self.nb = None
         self.preprocessors = preprocessors
         self.preprocessors.append(haspyout_transformer)
         self.preprocessors.append(outline_figure_transformer)
-        self.preprocessors.append(print_transformer)
         super(ConverterTemplate, self).__init__(config=config, **kw)
         self.env.filters['filter_data_type'] = self.filter_data_type
         self.template = self.env.get_template(tplfile+self.ext)
 
 
 
     def process(self):
         """
         preprocess the notebook json for easier use with the templates. 
         will call all the `preprocessor`s in order before returning it. 
         """
         nb = self.nb
 
         for preprocessor in self.preprocessors:
             nb,others = preprocessor(nb,{})
 
         return nb
 
     def convert(self):
         """ convert the ipynb file
 
         return both the converted ipynb file and a dict containing potential
         other resources
         """
         return self.template.render(nb=self.process(), inlining=inlining), {}
 
 
     def read(self, filename):
         "read and parse notebook into NotebookNode called self.nb"
         with io.open(filename) as f:
             self.nb = nbformat.read(f, 'json')
 

templates/tex/latex_base.tplx

@@ -1,208 +1,207 b''
 ((*- extends 'display_priority.tplx' -*))
 
 ((* block in_prompt *))((* endblock in_prompt *))
 
 ((* block output_prompt *))((* endblock output_prompt *))
 
 ((* block codecell *))\begin{codecell}((( super() )))
 \end{codecell}
 ((* endblock *))
 
 ((* block input *))
 \begin{codeinput}
 \begin{lstlisting}
 ((( cell.input )))
 \end{lstlisting}
 \end{codeinput}
 ((* endblock input *))
 
 
 ((= Those Two are for error displaying
 even if the first one seem to do nothing, 
 it introduces a new line
 
 =))
 ((* block pyerr *))((( super() )))
 ((* endblock pyerr *))
 
 ((* block traceback_line *))
 ((( line |indent| rm_ansi )))((* endblock traceback_line *))
 ((= .... =))
 
 
 ((*- block output_group -*))
 \begin{codeoutput}
 ((( super() )))
 \end{codeoutput}((* endblock *))
 
 ((*- block data_png -*))
-++(((output.png)))++
 \begin{center}
 \includegraphics[width=0.7\textwidth]{(((output.png)))}
 \par
 \end{center}
 ((*- endblock -*))
 
 ((* block pyout *))
 ((( output.text)))
 ((* endblock pyout *))
 
 ((* block data_text *))
 \begin{verbatim}
 ((( output.text )))
 \end{verbatim}
 ((* endblock *))
 
 ((* block stream *))
 \begin{verbatim}
 ((( output.text)))
 \end{verbatim}
 ((* endblock stream *))
 
 
 
 
 ((* block markdowncell scoped *))((( cell.source | markdown2latex )))
 ((* endblock markdowncell *))
 
 ((* block headingcell scoped *))
 \section{((( cell.source)))}
 ((* endblock headingcell *))
 
 ((* block rawcell scoped *))
 ((( cell.source | pycomment )))
 ((* endblock rawcell *))
 
 ((* block unknowncell scoped *))
 unknown type  (((cell.type)))
 ((* endblock unknowncell *))
 
 
 
 ((* block body *))\begin{document}
 ((( super() )))
 \end{document}
 ((* endblock*))
 
 ((* block header *))
 %% This file was auto-generated by IPython.
 %% Conversion from the original notebook file:
 %% tests/ipynbref/Gun_Data.orig.ipynb
 %%
 \documentclass[11pt,english]{article}
 
 %% This is the automatic preamble used by IPython.  Note that it does *not*
 %% include a documentclass declaration, that is added at runtime to the overall
 %% document.
 
 \usepackage{amsmath}
 \usepackage{amssymb}
 \usepackage{graphicx}
 \usepackage{ucs}
 \usepackage[utf8x]{inputenc}
 
 % needed for markdown enumerations to work
 \usepackage{enumerate}
 
 % Slightly bigger margins than the latex defaults
 \usepackage{geometry}
 \geometry{verbose,tmargin=3cm,bmargin=3cm,lmargin=2.5cm,rmargin=2.5cm}
 
 % Define a few colors for use in code, links and cell shading
 \usepackage{color}
 \definecolor{orange}{cmyk}{0,0.4,0.8,0.2}
 \definecolor{darkorange}{rgb}{.71,0.21,0.01}
 \definecolor{darkgreen}{rgb}{.12,.54,.11}
 \definecolor{myteal}{rgb}{.26, .44, .56}
 \definecolor{gray}{gray}{0.45}
 \definecolor{lightgray}{gray}{.95}
 \definecolor{mediumgray}{gray}{.8}
 \definecolor{inputbackground}{rgb}{.95, .95, .85}
 \definecolor{outputbackground}{rgb}{.95, .95, .95}
 \definecolor{traceback}{rgb}{1, .95, .95}
 
 % Framed environments for code cells (inputs, outputs, errors, ...).  The
 % various uses of \unskip (or not) at the end were fine-tuned by hand, so don't
 % randomly change them unless you're sure of the effect it will have.
 \usepackage{framed}
 
 % remove extraneous vertical space in boxes
 \setlength\fboxsep{0pt}
 
 % codecell is the whole input+output set of blocks that a Code cell can
 % generate.
 
 % TODO: unfortunately, it seems that using a framed codecell environment breaks
 % the ability of the frames inside of it to be broken across pages.  This
 % causes at least the problem of having lots of empty space at the bottom of
 % pages as new frames are moved to the next page, and if a single frame is too
 % long to fit on a page, will completely stop latex from compiling the
 % document.  So unless we figure out a solution to this, we'll have to instead
 % leave the codecell env. as empty.  I'm keeping the original codecell
 % definition here (a thin vertical bar) for reference, in case we find a
 % solution to the page break issue.
 
 %% \newenvironment{codecell}{%
 %%     \def\FrameCommand{\color{mediumgray} \vrule width 1pt \hspace{5pt}}%
 %%    \MakeFramed{\vspace{-0.5em}}}
 %%  {\unskip\endMakeFramed}
 
 % For now, make this a no-op...
 \newenvironment{codecell}{}
 
  \newenvironment{codeinput}{%
    \def\FrameCommand{\colorbox{inputbackground}}%
    \MakeFramed{\advance\hsize-\width \FrameRestore}}
  {\unskip\endMakeFramed}
 
 \newenvironment{codeoutput}{%
    \def\FrameCommand{\colorbox{outputbackground}}%
    \vspace{-1.4em}
    \MakeFramed{\advance\hsize-\width \FrameRestore}}
  {\unskip\medskip\endMakeFramed}
 
 \newenvironment{traceback}{%
    \def\FrameCommand{\colorbox{traceback}}%
    \MakeFramed{\advance\hsize-\width \FrameRestore}}
  {\endMakeFramed}
 
 % Use and configure listings package for nicely formatted code
 \usepackage{listingsutf8}
 \lstset{
   language=python,
   inputencoding=utf8x,
   extendedchars=\true,
   aboveskip=\smallskipamount,
   belowskip=\smallskipamount,
   xleftmargin=2mm,
   breaklines=true,
   basicstyle=\small \ttfamily,
   showstringspaces=false,
   keywordstyle=\color{blue}\bfseries,
   commentstyle=\color{myteal},
   stringstyle=\color{darkgreen},
   identifierstyle=\color{darkorange},
   columns=fullflexible,  % tighter character kerning, like verb
 }
 
 % The hyperref package gives us a pdf with properly built
 % internal navigation ('pdf bookmarks' for the table of contents,
 % internal cross-reference links, web links for URLs, etc.)
 \usepackage{hyperref}
 \hypersetup{
   breaklinks=true,  % so long urls are correctly broken across lines
   colorlinks=true,
   urlcolor=blue,
   linkcolor=darkorange,
   citecolor=darkgreen,
   }
 
 % hardcode size of all verbatim environments to be a bit smaller
 \makeatletter 
 \g@addto@macro\@verbatim\small\topsep=0.5em\partopsep=0pt
 \makeatother 
 
 % Prevent overflowing lines due to urls and other hard-to-break entities.
 \sloppy
 
 ((* endblock *))