add wiki-style markup

diff --git a/wikimarkupper.py b/wikimarkupper.py
new file mode 100755 (executable)
index 0000000..8031eed
--- /dev/null
+++ b/wikimarkupper.py
@@ -0,0 +1,344 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+ 
+import sys
+import os
+import re
+import codecs
+import pickle
+import markupper
+import HTMLTagFilter
+
+#sys.stdin = codecs.getreader('utf_8')(sys.stdin)
+#sys.stdout = codecs.getwriter('utf_8')(sys.stdout)
+
+class WikiMarkupper(markupper.Markupper):
+    def _head_l(self, line):
+        if self._anchor != "":
+            line = re.sub(ur"^●(.*)$", ur'== \1 == #%s' % self._anchor, line)
+            self._anchor = ""
+        else:
+            line = re.sub(ur"^●(.*)$", ur"== \1 ==", line)
+        print line
+
+    def _head_m(self, line):
+        if self._anchor != "":
+            line = re.sub(ur"^○(.*)$", ur'=== \1 === #%s' % self._anchor, line)
+            self._anchor = ""
+        else:
+            line = re.sub(ur"^○(.*)$", ur"=== \1 ===", line)
+        print line
+
+    def _paragraph(self, line):
+        print line
+
+    def _newpage(self, line):
+        pass
+
+    def _default_markup_rule(self, line):
+        """
+        apply default markup rules.
+
+        @param line: string to apply markup
+        @type line: string
+        """
+        # line = re.sub(ur"&", ur"&amp", line)
+        # line = re.sub(ur"<", ur"&lt;", line)
+        # line = re.sub(ur">", ur"&gt;", line)
+
+        # apply filter
+        # line = tag_filter.apply(line)
+
+        line = re.sub(ur"[★*](表[0-9～、]+)", ur"'''\1'''", line)
+        line = re.sub(ur"[★*](図[0-9～、]+)", ur"'''\1'''", line)
+        line = re.sub(ur"[★*](リスト[0-9～、]+)", ur"'''\1'''", line)
+        line = re.sub(ur"[★*]b\[(.*?)\]", ur"'''\1'''", line)
+        line = re.sub(ur"[★*]b\{(.*?)\}", ur"'''\1'''", line)
+        line = re.sub(ur"[★*]\[(\S*) (.*?)\]", r'<a href="\1">\2</a>', line)
+
+        # comment
+        if re.search(ur"^☆#", line):
+            line = ""
+
+        return line
+
+
+    def _ulist(self, line):
+        """Proccess ul"""
+        while re.search(ur"^・", line):
+            print re.sub(ur"^・(.*)$", ur" * \1", line.strip())
+            line = self.input_iter.next()
+
+    def _begin_column(self, line):
+        """Proccess column"""
+        try:
+            str_title = re.search(ur"^☆begin-column:(.*)$", line).group(1)
+        except AttributeError:
+            str_title = ""
+
+        html = """=== %s ===""" % (str_title)
+        print html
+
+    def _end_column(self, line):
+        pass
+
+    def _list_start(self):
+        return "{{{"
+
+    def _list_end(self):
+        return "}}}"
+
+    def _list(self, line):
+        try:
+            str_title = re.search(ur"^☆(リスト.*)$", line).group(1)
+        except AttributeError:
+            str_title = ""
+        print "'''%s'''" % (str_title)
+        print self._list_start()
+
+        for line in self.input_iter:
+            line = line.strip("\n\r")
+            if re.search(ur"""^☆\+---""", line):
+                break
+            print line
+        print self._list_end()
+
+    def _code(self, line):
+        print self._list_start()
+
+        for line in self.input_iter:
+            #        line = line.strip()
+            line = line = re.sub(ur"[★*]b\[(.*?)]", ur"\1", line)
+            line = line = re.sub(ur"[★*]b{(.*?)}", ur"\1", line)
+
+            if re.search(ur"^☆\+---$", line):
+                break
+            print line,
+        print self._list_end()
+
+
+    def _inline(self, line):
+        print "{{{ html"
+        for line in self.input_iter:
+            #        line = line.strip()
+            if re.search(ur"^☆}}}", line):
+                break
+            print line,
+        print "}}}"
+
+    def _comment(self, line):
+        for line in self.input_iter:
+            line = line.strip()
+            if re.search(ur"^☆}}}", line):
+                break
+
+    def _space(self, line):
+        print "[[BR]]"
+
+    def _flow(self, line):
+        flow_header = """{{{ html
+<div style="text-align:center; border: 1px solid; background-color:#EFF2F0; width:90%; margin: 0 auto 1em;">
+"""
+        flow_title = """<div style="text-align:left; padding:4px 4px 4px 1em; margin-bottom: 1em; border-bottom: 1px solid; font-weight: bold; background-color:#BCD;">
+%s
+</div>"""
+        flow_footer = """</div>
+}}}
+"""
+        flow_item = """<div>
+}}}
+%s
+{{{ html
+</div>
+
+"""
+        down_arrow = "http://static.sourceforge.jp/crystal/22x22/actions/1downarrow.png"
+
+        rex_title = re.compile(ur"^☆flow\s+(.*)$")
+        if rex_title.search(line):
+            title = rex_title.search(line).group(1)
+        else:
+            title = ""
+
+        rex_file = re.compile(ur"^([^:]*):(.*)$")
+        outputs = []
+        for line in self.input_iter:
+            if re.search(r"^\s*$", line):
+                break
+            match = rex_file.search(line)
+            if match:
+                file = os.path.join(self._image_dir, match.group(1))
+                cap = match.group(2)
+            else:
+                continue
+            fig = self._anchored_fig(file, cap)
+            outputs.append(flow_item % (fig))
+
+        arrow = '<img src="%s">\n' % (down_arrow,)
+        print flow_header
+        print flow_title % (title,)
+        print arrow.join(outputs)
+        print flow_footer
+        
+
+    def _fig_start(self, cap=""):
+        return ""
+
+    def _fig_end(self, cap=""):
+        return ""
+
+    def _fig(self, line):
+        if self._release == 1:
+            self._fig_release(line)
+        else:
+            self._fig_org(line)
+
+
+    def _fig_org(self, line):
+        try:
+            str_title = re.search(ur"^☆(図.*)$", line).group(1)
+        except AttributeError:
+            str_title = ""
+        print self._fig_start()
+
+        line = self.input_iter.next()
+        imgname = ""
+        imgname_s = ""
+        hash = ""
+        hash_s = ""
+        match_o1 = re.search(ur"<([^,]*?)>", line)
+        match_o2 = re.search(ur"<(.*?),\s*(.*?)>", line)
+        if not match_o1 == None:
+            imgname = match_o1.group(1)
+            imgname = os.path.join(self._image_dir, imgname)
+            imgname_s = re.sub(r"(.[A-Za-z0-9_]+)$", r"_s\1", imgname)
+        elif not match_o2 == None:
+            imgname = match_o1.group(1)
+            imgname = os.path.join(self._image_dir, imgname)
+            imgname_s = match_o1.group(2)
+
+        print self._anchored_fig(imgname, str_title, imgname_s)
+
+#         if not os.path.isfile(imgname_s):
+#             imgname_s = imgname
+
+#         print """<a href="%s">
+#      <img src="%s" alt="%s">
+# </a>
+#      """ % (imgname, imgname_s, str_title)
+
+        dic = self.index("figs")
+        dic.append(imgname)
+        if imgname_s != "":
+            dic.append(imgname_s)
+
+        print self._fig_end(str_title);
+        
+    def _anchored_fig(self, file, alt, file_s=""):
+
+        if file_s == "":
+            file_s = re.sub(r"(.[A-Za-z0-9_]+)$", r"_s\1", file)
+
+        if not os.path.isfile(file_s):
+            file_s = file
+
+        return """[[Thumb(%s, caption=%s)]]""" % (file, alt)
+        
+
+    def _fig_release(self, line):
+        try:
+            str_title = re.search(ur"^☆(図.*)$", line).group(1)
+        except AttributeError:
+            str_title = ""
+        print self._fig_start()
+
+        line = self.input_iter.next()
+        imgname = ""
+        imgname_s = ""
+        hash = ""
+        hash_s = ""
+        match_o1 = re.search(ur"<([^,]*?)>", line)
+        match_o2 = re.search(ur"<(.*?),\s*(.*?)>", line)
+        if not match_o1 == None:
+            imgname = match_o1.group(1)
+            imgname_s = re.sub(r"(.[A-Za-z0-9_]+)$", r"_s\1", match_o1.group(1))
+        elif not match_o2 == None:
+            imgname = match_o1.group(1)
+            imgname_s = match_o1.group(2)
+
+
+        hash = self.hashlist.get(imgname, "")
+        hash_s = self.hashlist.get(imgname_s, "")
+        if hash_s == "":
+            hash_s = hash
+
+        print """<a href="/blob.pl?id=%s">
+     <slash type="image" id="%s" title="%s">
+     </a>
+     """ % (hash, hash_s, str_title)
+        
+
+        dic = self.index("figs")
+        dic.append(imgname)
+        if imgname_s != "":
+            dic.append(imgname_s)
+
+        print self._fig_end(str_title);
+
+
+    def _table_start(self, cap):
+        return "'''%s'''" % (cap,)
+
+    def _table_end(self, footnote=""):
+        return "%s" % (footnote,)
+
+    def _table(self, line):
+        str_title = ""
+        self._table_buf1 = ""
+
+        try:
+            str_title = re.search(ur"^☆(表.*)$", line).group(1)
+            fig_name =  re.search(ur"^☆(表[0-9A-Z]*)", line).group(1)
+        except AttributeError:
+            str_title = ""
+            fig_name = ""
+#        print self._table_start(str_title)
+        self._table_buf1 =  self._table_start(str_title) + "\n"
+
+        num_row = 0
+        table_contents = []
+        footnote = ""
+        for line in self.input_iter:
+            line = line.strip(" \n")
+            if re.search(ur"^\s*$", line):
+                break
+            if re.search(ur"^※", line):
+                footnote = re.search(ur"^(※.*)$", line).group(1)
+                break
+            line = self._default_markup_rule(line)
+            if re.search(ur"^〓", line):
+                line = re.sub(ur"^〓", "", line)
+                tag_mode = "th"
+            else:
+                tag_mode = "td"
+            self._table_buf1 = self._table_buf1 + "||"
+            for item in line.split("\t"):
+                if tag_mode == "th":
+                    self._table_buf1 = self._table_buf1 + "'''%s'''||" % (item,)
+                else:
+                    self._table_buf1 = self._table_buf1 + "%s||" % (item,)
+            self._table_buf1 = self._table_buf1 + "\n"
+
+        self._table_buf1 = self._table_buf1 + self._table_end(footnote)
+        print self._table_buf1
+        if self.index_haskey("tables"):
+            self.index("tables")[fig_name] = self._table_buf1
+        else:
+            self.index_add("tables", {fig_name:self._table_buf1})
+
+    def _call_tables(self, line):
+        try:
+            fig_name =  re.search(ur"^☆call_tables\((表[0-9A-Z]+)", line).group(1)
+        except AttributeError:
+            return
+        print self.index("tables")[fig_name]

diff --git a/wmarkup.py b/wmarkup.py
new file mode 100755 (executable)
index 0000000..b5fb587
--- /dev/null
+++ b/wmarkup.py
@@ -0,0 +1,39 @@
+#!/usr/bin/env python\r
+# -*- coding: utf-8 -*-\r
+ \r
+import sys\r
+import os\r
+import codecs\r
+\r
+rootpath = r"C:\Users\hirom\bin\otptools"\r
+sys.path.insert(0, rootpath)\r
+\r
+import wikimarkupper\r
+\r
+\r
+str_usage = "markup.pl hashfile targetfile\n"\r
+path_to_index = "./_markup_index"\r
+\r
+sys.stdin = codecs.getreader('utf_8')(sys.stdin)\r
+sys.stdout = codecs.getwriter('utf_8')(sys.stdout)\r
+\r
+try:\r
+#    path_img_hash = sys.argv[1]\r
+    path_target = sys.argv[1]\r
+except IndexError:\r
+    sys.exit(str_usage)\r
+\r
+markupper = wikimarkupper.WikiMarkupper()\r
+#markupper.make_hashlist(path_img_hash)\r
+markupper.load_index(path_to_index)\r
+\r
+file_target = codecs.open(path_target, "r", "utf_8" )\r
+# file_target = open(path_target, "r")\r
+\r
+markupper.index_add("file", path_target)\r
+markupper.index_add("anchors", [])\r
+\r
+markupper.markup(file_target, 0)\r
+\r
+markupper.save_index(path_to_index)\r
+\r