NEW: Add a html2reStructuredText converter

2 files changed, 156 insertions, 41 deletions

diff --git a/creole/shared/markup_table.py b/creole/shared/markup_table.py
index 476047d..abda575 100644
--- a/creole/shared/markup_table.py
+++ b/creole/shared/markup_table.py
@@ -3,30 +3,6 @@ class MarkupTable(object):
     """
     Container for holding table data and render the data in creole markup.
     Format every cell width to the same col width.
-    
-    >>> def debug_msg(*args): pass
-    >>> t = MarkupTable(head_prefix="* ", debug_msg=debug_msg)
-    >>> t.add_tr()
-    >>> t.add_th(u"head1")
-    >>> t.add_th(u"head2")
-    >>> t.add_tr()
-    >>> t.add_td(u"1.1.")
-    >>> t.add_td(u"1.2.")
-    >>> t.add_tr()
-    >>> t.add_td(u"2.1.")
-    >>> t.add_td(u"2.2.")
-    >>> t.get_table_markup().splitlines()
-    [u'|* head1 |* head2 |', u'| 1.1.   | 1.2.   |', u'| 2.1.   | 2.2.   |']
-    
-    >>> t = MarkupTable(head_prefix="_. ", auto_width=False, debug_msg=debug_msg)
-    >>> t.add_tr()
-    >>> t.add_th(u"head1")
-    >>> t.add_th(u"head2")
-    >>> t.add_tr()
-    >>> t.add_td(u"1.1.")
-    >>> t.add_td(u"1.2.")
-    >>> t.get_table_markup().splitlines()
-    [u'|_. head1|_. head2|', u'|1.1.|1.2.|']
     """
     def __init__(self, head_prefix="= ", auto_width=True, debug_msg=None):
         self.head_prefix = head_prefix
@@ -58,30 +34,34 @@ class MarkupTable(object):
         self.debug_msg("Table.add_td", text)
         self.rows[self.row_index].append(text)
 
+    def _get_preformat_info(self):
+        cells = []
+        for row in self.rows:
+            line_cells = []
+            for cell in row:
+                cell = cell.strip()
+                if cell != "":
+                    if self.head_prefix and cell.startswith(self.head_prefix):
+                        cell += " " # Headline
+                    else:
+                        cell = " %s " % cell # normal cell
+                line_cells.append(cell)
+            cells.append(line_cells)
+
+        # Build a list of max len for every column
+        widths = [max(map(len, col)) for col in zip(*cells)]
+
+        return cells, widths
+
     def get_table_markup(self):
-        """ return the table data in creole markup. """
+        """ return the table data in creole/textile markup. """
         if not self.auto_width:
-            #
             lines = []
             for row in self.rows:
                 lines.append("|" + "|".join([cell for cell in row]) + "|")
         else:
             # preformat every table cell
-            cells = []
-            for row in self.rows:
-                line_cells = []
-                for cell in row:
-                    cell = cell.strip()
-                    if cell != "":
-                        if cell.startswith(self.head_prefix):
-                            cell += " " # Headline
-                        else:
-                            cell = " %s " % cell # normal cell
-                    line_cells.append(cell)
-                cells.append(line_cells)
-
-            # Build a list of max len for every column
-            widths = [max(map(len, col)) for col in zip(*cells)]
+            cells, widths = self._get_preformat_info()
 
             # Join every line with ljust
             lines = []
@@ -94,6 +74,29 @@ class MarkupTable(object):
         self.debug_msg("Table.get_table_markup", result)
         return result
 
+    def get_rest_table(self):
+        """ return the table data in ReSt markup. """
+        # preformat every table cell
+        cells, widths = self._get_preformat_info()
+
+        separator_line = "+%s+" % "+".join(["-"*width for width in widths])
+        headline_separator = "+%s+" % "+".join(["="*width for width in widths])
+
+        lines = []
+        for no, row in enumerate(cells):
+            if no == 1:
+                lines.append(headline_separator)
+            else:
+                lines.append(separator_line)
+
+            # Join every line with ljust
+            cells = [cell.ljust(width) for cell, width in zip(row, widths)]
+            lines.append("|" + "|".join(cells) + "|")
+
+        lines.append(separator_line)
+
+        return "\n".join(lines)
+
 if __name__ == '__main__':
     import doctest
     print doctest.testmod()
diff --git a/creole/shared/rest.py b/creole/shared/rest.py
new file mode 100644
index 0000000..15c7d0b
--- /dev/null
+++ b/creole/shared/rest.py
@@ -0,0 +1,112 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+"""
+    Some code stolen from:
+    http://www.arnebrodowski.de/blog/write-your-own-restructuredtext-writer.html
+"""
+
+
+import warnings
+
+
+try:
+    from docutils.core import publish_parts
+except ImportError:
+    REST_INSTALLED = False
+    warnings.warn(
+        "Markup error: 'Python Documentation Utilities' isn't installed. Can't test reStructuredText."
+        " Download: http://pypi.python.org/pypi/docutils"
+    )
+else:
+    REST_INSTALLED = True
+
+
+from docutils.writers import html4css1
+
+
+DEBUG = False
+#DEBUG = True
+
+IGNORE_ATTR = (
+    "class",
+)
+
+
+class CleanHTMLWriter(html4css1.Writer):
+    """
+    This docutils writer will use the CleanHTMLTranslator class below.
+    """
+    def __init__(self):
+        html4css1.Writer.__init__(self)
+        self.translator_class = CleanHTMLTranslator
+
+class CleanHTMLTranslator(html4css1.HTMLTranslator):
+    """
+    This is a translator class for the docutils system.
+    It will produce a minimal set of html output.
+    (No extry divs, classes oder ids.)
+    """
+    def starttag(self, node, tagname, suffix='\n', empty=0, **attributes):
+        if DEBUG:
+            print "ids: %r" % getattr(node, "ids", "-")
+        node.ids = []
+        if DEBUG:
+            print "attributes: %r" % attributes
+        for attr in IGNORE_ATTR:
+            for attr2 in (attr, attr.lower(), attr.upper()):
+                if attr2 in attributes:
+                    del(attributes[attr2])
+
+        return html4css1.HTMLTranslator.starttag(self, node, tagname, suffix, empty, **attributes)
+
+    def visit_section(self, node):
+        self.section_level += 1
+
+    def depart_section(self, node):
+        self.section_level -= 1
+
+    #__________________________________________________________________________
+    # Clean table:
+
+    def do_nothing(self, node):
+        pass
+    visit_thead = do_nothing
+    depart_thead = do_nothing
+    visit_tbody = do_nothing
+    depart_tbody = do_nothing
+
+    def visit_table(self, node):
+        self.body.append(self.starttag(node, 'table'))
+
+    def visit_tgroup(self, node):
+        node.stubs = []
+
+def rest2html(content):
+    """
+    >>> rest2html(u"- bullet list")
+    u'<ul>\\n<li>bullet list</li>\\n</ul>\\n'
+    """
+    parts = publish_parts(
+        source=content,
+#        writer_name="html4css1",
+        writer=CleanHTMLWriter(),
+        settings_overrides={
+            "input_encoding": "unicode",
+            "doctitle_xform": False,
+        },
+    )
+    return parts["fragment"]
+
+
+if __name__ == '__main__':
+    import doctest
+    print doctest.testmod()
+
+    print rest2html(u"""
++------------+------------+
+| Headline 1 | Headline 2 |
++============+============+
+| cell one   | cell two   |
++------------+------------+
+    """)