5 files changed, 309 insertions, 126 deletions

diff --git a/wiki2html.py b/wiki2html.py
index 441bc76..66939c4 100644
--- a/wiki2html.py
+++ b/wiki2html.py
@@ -172,25 +172,21 @@ class HtmlWikiMarkup (WikiMarkup):
                                 self.envt[type]["hdr"])
         return string
 
-    supported_tags = [ 'nowiki', 'code' ]
-    def input_tag(self, tag):
-        return tag['tag'] in self.supported_tags
-    
     def str_tag(self, elt):
         if elt['tag'] == 'nowiki':
-            return '<pre>' + elt['content'] + '</pre>'
+            return '<pre>' + self.format(elt['content']) + '</pre>'
         elif elt['tag'] == 'code':
-            kwdict = {
-                'nested': self.nested + 1,
-                'lang': self.lang,
-                'text': elt['content'],
-                'html_base': self.html_base,
-                'image_base': self.image_base,
-                'media_base': self.media_base }
-            markup = HtmlWiktionaryMarkup(**kwdict)
-            markup.debug_level = self.debug_level
-            markup.parse()
-            return '<pre><code>' + str(markup) + '</code></pre>' #FIXME
+            self.nested += 1
+            s = self.format(elt['content'])
+            self.nested -= 1
+            return '<pre><code>' + s + '</code></pre>' #FIXME
+        else:
+            s = '<' + elt['tag']
+            if elt['args']:
+                s += ' ' + elt['args']
+            s += '>'
+            s += self.format(elt['content'])
+            return s + '</' + elt['tag'] + '>'
     
     def str_para(self, elt):
         string = "";
diff --git a/wiki2texi.py b/wiki2texi.py
index 7cc67bd..0b3eb77 100644
--- a/wiki2texi.py
+++ b/wiki2texi.py
@@ -119,29 +119,28 @@ class TexiWikiMarkup (WikiMarkup):
         else:
             return str(elt)
 
-    supported_tags = [ 'nowiki', 'code' ]
-    def input_tag(self, tag):
-        return tag['tag'] in self.supported_tags
-    
     def str_tag(self, elt):
         if elt['tag'] == 'nowiki':
-            return '@example\n' + elt['content'] + '@end example\n'
+            return '@example\n' + self.format(elt['content']) + '@end example\n'
         elif elt['tag'] == 'code':
-            kwdict = {
-                'nested': self.nested + 1,
-                'lang': self.lang,
-                'text': elt['content'],
-                'html_base': self.html_base,
-                'image_base': self.image_base,
-                'media_base': self.media_base }
-            markup = TexiWikiMarkup(**kwdict)
-            markup.debug_level = self.debug_level
-            markup.parse()
-            s = str(markup)
+            self.nested += 1
+            s = self.format(elt['content'])
+            self.nested -= 1
             if not s.endswith("\n"):
-                s += "\n";
+                s += "\n"            
             return '@example\n' + s + '@end example\n'
-
+        elif elt['tag'] == 'tt':
+            self.nested += 1
+            s = self.format(elt['content'])
+            self.nested -= 1
+            return "@code{%s}" % s
+        else:
+            s = '<' + elt['tag']
+            if elt['args']:
+                s += ' ' + elt['args']
+            s += '>' + self.format(elt['content']) + '</' + elt['tag'] + '>'
+            return s
+ 
     def str_para(self, elt):
         string = "";
         for x in elt['content']:
@@ -156,7 +155,7 @@ class TexiWikiMarkup (WikiMarkup):
             return string
         if not string.endswith("\n"):
             string += "\n";
-        return '@example\n' + string + '@end example\n'
+        return '\n@example\n' + string + '@end example\n'
 
     def concat(self, eltlist):
         string = ""
diff --git a/wiki2text.py b/wiki2text.py
index 27a7051..d4cab81 100644
--- a/wiki2text.py
+++ b/wiki2text.py
@@ -142,25 +142,20 @@ class TextWikiMarkup (WikiMarkup):
             length += wsc + wlen
         return output + linebuf
         
-    supported_tags = [ 'nowiki', 'code' ]
-    def input_tag(self, tag):
-        return tag['tag'] in self.supported_tags
-    
     def str_tag(self, elt):
         if elt['tag'] == 'nowiki':
-            return elt['content']
+            return self.format(elt['content'])
         elif elt['tag'] == 'code':
-            kwdict = {
-                'nested': self.nested + 1,
-                'lang': self.lang,
-                'text': elt['content'],
-                'html_base': self.html_base,
-                'image_base': self.image_base,
-                'media_base': self.media_base }
-            markup = TextWiktionaryMarkup(**kwdict)
-            markup.debug_level = self.debug_level
-            markup.parse()
-            return str(markup)
+            self.nested += 1
+            s = self.format(elt['content'])
+            self.nested -= 1
+            return s #FIXME
+        else:
+            s = '<' + elt['tag']
+            if elt['args']:
+                s += ' ' + elt['args']
+            s += '>' + self.format(elt['content']) + '</' + elt['tag'] + '>'
+            return s            
         
     def format(self, elt):
         if elt['type'] == 'TEXT':
diff --git a/wikicvt.py b/wikicvt.py
index e61e28b..c8ca887 100755
--- a/wikicvt.py
+++ b/wikicvt.py
@@ -17,10 +17,20 @@
 
 import sys
 import getopt
+import StringIO
 from wiki2html import *
 from wiki2text import *
 from wiki2texi import *
 
+class DumpWikiMarkup (WikiMarkup):
+    def __str__(self):
+        if self.tree:
+            s = StringIO.StringIO()
+            self.dump(self.tree, 0, s)
+            return s.getvalue()
+        else:
+            return ""
+
 def usage(code=0):
     print """
 usage: %s [-hvt] [-I INTYPE] [-l lang] [-o kw=val] [--lang=lang] [--option kw=val]
@@ -29,6 +39,9 @@ usage: %s [-hvt] [-I INTYPE] [-l lang] [-o kw=val] [--lang=lang] [--option kw=va
     sys.exit(code)
 
 handlers = {
+    'dump': {
+        'default': DumpWikiMarkup
+    },
     'html': {
         'default': HtmlWikiMarkup,
         'wiktionary': HtmlWiktionaryMarkup
@@ -51,9 +64,10 @@ def main():
     debug = 0
     
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "d:I:hl:o:t:v",
-                                   ["debug=", "help", "lang=", "option=",
-                                    "to", "type", "input-text", "input-type",
+        opts, args = getopt.getopt(sys.argv[1:], "Dd:I:hl:o:t:v",
+                                   ["dump",
+                                    "debug=", "help", "lang=", "option=",
+                                    "to=", "type=", "input-text", "input-type=",
                                     "verbose" ])
     except getopt.GetoptError:
         usage(1)
@@ -77,6 +91,8 @@ def main():
             input_text = True
         elif o in ("-d", "--debug"):
             debug = eval(a)
+        elif o in ("-D", "--dump"):
+            otype = 'dump'
 
     if len(args) == 1:
         if args[0] == '-':
@@ -88,8 +104,8 @@ def main():
 
     kwdict['lang']=lang
 
-    if handlers.has_key(otype):
-        if handlers[otype].has_key(itype):
+    if otype in handlers:
+        if itype in handlers[otype]:
             markup = handlers[otype][itype](**kwdict)
             markup.debug_level = debug
             markup.parse()
diff --git a/wikimarkup.py b/wikimarkup.py
index fde1ec1..9a79d1e 100644
--- a/wikimarkup.py
+++ b/wikimarkup.py
@@ -22,9 +22,9 @@ from types import *
 __all__ = [ "BaseWikiMarkup", "WikiMarkup",
             "envtypes" ]
 
-delim = re.compile("^==+|==+[ \\t]*$|(^----$)|^\\*+|^#+|^[;:]+|(\\[\\[)|\\[|(\\{\\{)|(\\]\\])|\\]|(\\}\\})|\\||(\\'\\'\\'?)")
-otag = re.compile("^\s*<(?P<tag>[a-zA-Z0-9_]+)(?:\s+(?P<args>.+))?\s*(?P<closed>/)?>")
-ctag = re.compile("^\s*</(?P<tag>[a-zA-Z0-9_]+)\s*>")
+delim = re.compile("^==+|==+[ \\t]*$|(^----$)|^\\*+|^#+|^[;:]+|(\\[\\[)|\\[|(\\{\\{)|(\\]\\])|\\]|(\\}\\})|\\||(\\'\\'\\'?)|<")
+otag = re.compile("(?P<pfx>[^<]*)<(?P<tag>[a-zA-Z0-9_]+)(?:\s+(?P<args>.+))?\s*(?P<closed>/)?>")
+ctag = re.compile("(?P<pfx>[^<]*)</(?P<tag>[a-zA-Z0-9_]+)\s*>")