--- /dev/null
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""markupper2.py - markupper v2."""
+
+import sys
+import os
+import re
+import codecs
+import pickle
+
+import deterfile
+
+class MarkUpper2(object):
+ """
+ """
+ def __init__(self):
+ self._vars = {}
+ self._anchor = ""
+
+ def markup(self, input_iter):
+ """
+ Do markup.
+
+ @param input_iter: iterator to use as input
+ @type input_iter: iterator
+ """
+ self.input = input_iter
+
+ for line in self.input:
+ if re.search(ur"^☆{{{$", line):
+ self._inline(line)
+ continue
+ elif re.search(ur'^\set{([A-Za-z0-9_]+)\s*,\s*"([^"]*)"\s*}', line):
+ g = re.search(ur'^\set{([A-Za-z0-9_]+)\s*,\s*"([^"]*)"\s*}', line)
+ self._vars[g.group(1)] = g.group(2)
+ continue
+ elif re.search(ur"^☆image_border:\s(on|On|ON)", line):
+ self._image_border = 1
+ continue
+ elif re.search(ur"^☆comment\s{{{$", line):
+ self._comment(line)
+ continue
+ elif re.search(ur"^☆\*", line):
+ self._anchor = re.sub(ur"^☆\*", "", line).strip()
+ continue
+ elif re.search(ur"^☆clear\s+", line):
+ self._clear(line)
+ continue
+ elif re.search(ur"^・", line):
+ self._ulist(line)
+ continue
+ elif re.search(ur"^[0-9]\.", line):
+ self._olist(line)
+ continue
+ elif re.search(ur"^☆begin-column:", line):
+ self._begin_column(line)
+ continue
+ elif re.search(ur"^☆end-column", line):
+ self._end_column(line)
+ continue
+ elif re.search(ur"^☆space", line):
+ self._space(line)
+ continue
+ elif re.search(ur"^☆call_tables", line):
+ self._call_tables(line)
+ continue
+ elif re.search(ur"^●", line):
+ self._head_l(line)
+ continue
+ elif re.search(ur"^○", line):
+ self._head_m(line)
+ continue
+ elif re.search(ur"^☆----", line):
+ self._newpage(line)
+ continue
+ elif re.search(ur"^☆\+---", line):
+ self._code(line)
+ continue
+ elif re.search(ur"^☆表", line):
+ self._table(line)
+ continue
+ elif re.search(ur"^☆図", line):
+ self._fig(line)
+ continue
+ elif re.search(ur"^☆写真", line):
+ self._photo(line)
+ continue
+ elif re.search(ur"^☆リスト", line):
+ self._list(line)
+ continue
+ elif re.search(ur"^☆flow", line):
+ self._flow(line)
+ continue
+
+ if re.search(ur"^ ", line):
+ self._paragraph(line)
+ continue
+
+
+ if re.search(r"^\s*$", line):
+ line = ""
+
+ line = line.strip()
+ print line
+
+ # end-of-loop
+
+ def _clear(self, line):
+ print """<div style="clear:left;"> </div>
+"""
+
+ def _head_l(self, line):
+ line = line.rstrip()
+ if re.search(ur"\*{[a-zA-Z0-9_]*}\s*$", line):
+ self._anchor = re.search(ur"\*\{([a-zA-Z0-9_]*)\}\s*$", line).group(1)
+ line = re.sub(ur"\s*\*\{[a-zA-Z0-9_]*\}\s*$", "", line)
+
+ line = self._default_markup_rule(line)
+ if self._anchor != "":
+ line = re.sub(ur"^●(.*)$", ur'<div id="%s"><h3>\1</h3></div>' % self._anchor, line)
+ self._anchor = ""
+ else:
+ line = re.sub(ur"^●(.*)$", ur"<h3>\1</h3>", line)
+ print line
+
+ def _head_m(self, line):
+ line = line.rstrip()
+ if re.search(ur"\*{[a-zA-Z0-9_]*}\s*$", line):
+ self._anchor = re.search(ur"\*\{([a-zA-Z0-9_]*)\}\s*$", line).group(1)
+ line = re.sub(ur"\s*\*\{[a-zA-Z0-9_]*\}\s*$", "", line)
+
+ line = self._default_markup_rule(line)
+ if self._anchor != "":
+ line = re.sub(ur"^○(.*)$", ur'<div id="%s"><h4>\1</h4></div>' % self._anchor, line)
+ self._anchor = ""
+ else:
+ line = re.sub(ur"^○(.*)$", ur"<h4>\1</h4>", line)
+ print line
+
+ def _paragraph(self, line):
+ line = self._default_markup_rule(line)
+ line = "<p>" + line + "</p>"
+ print line
+
+ def _newpage(self, line):
+ line = re.sub(ur"☆----.*-{0,1}", u"<hr>", line)
+ print line
+
+ def make_hashlist(self, path_to_hashfile):
+ """
+ create hash list.
+
+ @param path_to_hashfile: hashfile's path
+ @type path_to_hashfile: string
+ """
+ try:
+ file_img_hash = open(path_to_hashfile, "r")
+ except IOError:
+ sys.stderr.write("cannot open file: %s" % path_img_hash)
+ return None;
+
+ self.hashlist = {};
+ for line in file_img_hash:
+ splited = line.strip().split("\t", 2)
+ # hashlist's format: <hash> \t <filename>
+ self.hashlist[splited[1]] = splited[0]
+
+ def _call_tagles(self):
+ pass
+
+ def _escape(self, line):
+ line = re.sub(ur"&", ur"&", line)
+ line = re.sub(ur"<", ur"<", line)
+ line = re.sub(ur">", ur">", line)
+ return line
+
+ def _default_markup_rule(self, line):
+ """
+ apply default markup rules.
+
+ @param line: string to apply markup
+ @type line: string
+ """
+ line = self._escape(line)
+
+ # apply filter
+ # line = tag_filter.apply(line)
+
+ line = re.sub(ur"[★*](表[0-9~、]+)", ur"<b>\1</b>", line)
+ line = re.sub(ur"[★*](図[0-9~、]+)", ur"<b>\1</b>", line)
+ line = re.sub(ur"[★*](写真[0-9~、]+)", ur"<b>\1</b>", line)
+ line = re.sub(ur"[★*](リスト[0-9~、]+)", ur"<b>\1</b>", line)
+ line = re.sub(ur"[★*]b\[(.*?)\]", ur"<b>\1</b>", line)
+ line = re.sub(ur"[★*]b\{(.*?)\}", ur"<b>\1</b>", line)
+ line = re.sub(ur"[★*]\[(\S*) (.*?)\]", r'<a href="\1">\2</a>', line)
+ line = re.sub(ur"[★*]\[(\S*)\]", r'<a href="\1">\1</a>', line)
+
+ # comment
+ if re.search(ur"^☆#", line):
+ line = ""
+
+ return line
+
+
+ def _ulist(self, line):
+ """Proccess ul"""
+ print "<ul>"
+ while re.search(ur"^・", line):
+ line = self._default_markup_rule(line)
+ print re.sub(ur"^・(.*)$", ur"<li>\1</li>", line.strip())
+ line = self.input.next()
+ print "</ul>\n"
+
+ def _olist(self, line):
+ """Proccess ul"""
+ print "<ol>"
+ while re.search(ur"^[0-9]+\.", line):
+ line = self._default_markup_rule(line)
+ print re.sub(ur"^[0-9]+\.(.*)$", ur"<li>\1</li>", line.strip())
+ line = self.input.next()
+ print "</ol>\n"
+
+
+
+ def _begin_column(self, line):
+ """Proccess column"""
+ try:
+ str_title = re.search(ur"^☆begin-column:(.*)$", line).group(1)
+ except AttributeError:
+ str_title = ""
+
+ html = """<table bgcolor="#DDDDDD" border="0" cellpadding="6" width="95%%">
+ <tr><th>%s</th></tr>
+ <tr><td><span style="font-size: 85%%;">
+ """ % (str_title)
+ print html
+
+ def _end_column(self, line):
+ print """</span></td></tr>
+ </table>
+ """
+
+ def _list_start(self):
+ return "<pre>"
+
+ def _list_end(self):
+ return "</pre>"
+
+ def _list(self, line):
+ try:
+ str_title = re.search(ur"^☆(リスト.*)$", line).group(1)
+ except AttributeError:
+ str_title = ""
+ print "<p><b>%s</b></p>" % (str_title)
+ print self._list_start()
+
+ for line in self.input:
+ line = line.strip("\n\r")
+ line = self._escape(line)
+ line = line = re.sub(ur"[★*]b\[(.*?)]", ur"<b>\1</b>", line)
+ line = line = re.sub(ur"[★*]b{(.*?)}", ur"<b>\1</b>", line)
+ 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:
+ line = self._escape(line)
+ line = line = re.sub(ur"[★*]b\[(.*?)]", ur"<b>\1</b>", line)
+ line = line = re.sub(ur"[★*]b{(.*?)}", ur"<b>\1</b>", line)
+
+ if re.search(ur"^☆\+---$", line):
+ break
+ print line,
+ print self._list_end()
+
+ def _inline(self, line):
+ for line in self.input:
+ # line = line.strip()
+ if re.search(ur"^☆}}}", line):
+ break
+ print line
+
+ def _comment(self, line):
+ for line in self.input:
+ line = line.strip()
+ if re.search(ur"^☆}}}", line):
+ break
+
+ def _space(self, line):
+ print "<br><br>"
+
+ def _flow(self, line):
+ down_arrow = "http://static.sourceforge.jp/crystal/22x22/actions/1downarrow.png"
+ flow_header = """<div style="text-align:center; border: 1px solid; background-color:#EFF2F0; width:90%; margin: 0 auto 1em;">
+"""
+ flow_title = """<div style="text-align:left; padding:4px 4px 4px 1em; margin-bottom: 1em; border-bottom: 1px solid; font-weight: bold; background-color:#BCD;">
+%s
+</div>"""
+ flow_footer = """</div>
+"""
+ flow_item = """<div>
+%s
+<p>%s</p>
+</div>
+
+"""
+ arrow = '<div style="margin:1em auto;"><img src="%s"></div>\n' % (down_arrow,)
+
+ rex_title = re.compile(ur"^☆flow\s+(.*)$")
+ if rex_title.search(line):
+ title = rex_title.search(line).group(1)
+ else:
+ title = ""
+
+ rex_file = re.compile(ur"^([^:]*):(.*)$")
+ outputs = []
+ for line in self.input:
+ if re.search(r"^\s*$", line):
+ break
+ match = rex_file.search(line)
+ if match:
+ file = os.path.join(self._image_dir, match.group(1))
+ cap = self._default_markup_rule(match.group(2))
+ else:
+ continue
+ fig = self._anchored_fig(file, cap)
+ outputs.append(flow_item % (fig, cap))
+
+ print flow_header
+ print flow_title % (title,)
+ print arrow.join(outputs)
+ print flow_footer
+
+
+ def _fig_start(self, cap="", styles=[], width=0, height=0):
+ params = dict(style="", tablewidth="")
+ if width != 0:
+ params["style"] = "width:%d;" % (width,)
+ params["tablewidth"] = 'width="%d"' % (width,)
+
+ if "lfloat" in styles:
+ return """<table %(tablewidth)s align="center" border="0" cellpadding="0" cellspacing="0" style="float:left; padding-left: 0.5em; %(style)s">
+ <tr> <td valign="top" align="center">
+ """ % params
+ elif "left" in styles:
+ return """<table %(tablewidth)s border="0" cellpadding="0" cellspacing="0" style="padding-left: 0.5em; %(style)s">
+ <tr> <td valign="top" align="center">
+ """ %params
+ else:
+ return """<table %(tablewidth)s align="center" border="0" cellpadding="0" cellspacing="0">
+ <tr> <td valign="top" align="center">
+ """ % params
+
+ def _fig_end(self, cap="", styles=[]):
+ return """</td> </tr>
+ <tr> <td><span style="font-size: 80%%; font-weight: bold;">
+ %s
+ </span></td> </tr>
+ </table>
+ """ % (cap)
+
+ def _get_png_geom(self, filepath):
+ desc = deterfile.file(filepath)
+ try:
+ m = re.match(r"([0-9]+)\s*x\s*([0-9]+)", desc[1])
+ except IndexError:
+ err = ",".join(desc)
+ raise Exception("deterfile error: %s, file: %s" % (err,filepath))
+ if m:
+ w = m.group(1)
+ h = m.group(2)
+ return (int(w), int(h))
+ else:
+ return None
+
+ def _fig(self, line):
+ try:
+ str_title = re.search(ur"^☆(図.*)$", line).group(1)
+ except AttributeError:
+ str_title = ""
+ if str_title.find(u"図*") == 0:
+ str_title = str_title.replace(u"図*", "")
+ line = self.input.next()
+ styles = []
+ if line.find("@") == 0:
+ styles = line.strip().replace("@", "").split(",")
+ line = self.input.next()
+
+ if line[0] == "<":
+ imgname = ""
+ imgname_s = ""
+ hash = ""
+ hash_s = ""
+ match_o1 = re.search(ur"<([^,]*?)>", line)
+ match_o2 = re.search(ur"<(.*?),\s*(.*?)>", line)
+ if not match_o1 == None:
+ imgname = match_o1.group(1)
+ imgname = os.path.join(self._image_dir, imgname)
+ imgname_s = re.sub(r"(.[A-Za-z0-9_]+)$", r"_s\1", imgname)
+ elif not match_o2 == None:
+ imgname = match_o2.group(1)
+ imgname = os.path.join(self._image_dir, imgname)
+ imgname_s = match_o2.group(2)
+ imgname_s = os.path.join(self._image_dir, imgname_s)
+
+ geom = self._get_png_geom(imgname_s)
+ if geom:
+ w = geom[0]
+ h = geom[1]
+ print self._fig_start("", styles, width=w, height=h)
+ else:
+ print self._fig_start("", styles)
+ print self._anchored_fig(imgname, str_title, imgname_s)
+ print self._fig_end(str_title, styles);
+ else:
+ hash = ""
+ hash_s = ""
+ match_o = re.search(ur"\[(.*?),\s*(.*?)\]", line)
+ try:
+ print """<table width="500" align="center" border="0" cellpadding="0" cellspacing="0">
+ <tr> <td valign="top" align="center">
+"""
+ print """<a href="/blob.pl?id=%s">
+ <slash-image id="%s" title="%s">
+</a>""" % (match_o.group(1), match_o.group(2), str_title)
+ print """</td> </tr>
+ <tr> <td><span style="font-size: 80%%; font-weight: bold;">
+ %s
+ </span></td> </tr>
+ </table>
+""" % (str_title)
+ except IndexError:
+ print >> sys.stderr, "error:cannot parse id. " + line
+
+ def _photo(self, line):
+ try:
+ str_title = re.search(ur"^☆(写真.*)$", line).group(1)
+ except AttributeError:
+ str_title = ""
+ if str_title.find(u"写真*") == 0:
+ str_title = str_title.replace(u"写真*", "")
+ line = self.input.next()
+ styles = []
+ if line.find("@") == 0:
+ styles = line.strip().replace("@", "").split(",")
+ line = self.input.next()
+
+ imgname = ""
+ imgname_s = ""
+ hash = ""
+ hash_s = ""
+ match_o1 = re.search(ur"<([^,]*?)>", line)
+ match_o2 = re.search(ur"<(.*?),\s*(.*?)>", line)
+ if not match_o1 == None:
+ imgname = match_o1.group(1)
+ imgname = os.path.join(self._image_dir, imgname)
+ imgname_s = re.sub(r"(.[A-Za-z0-9_]+)$", r"_s\1", imgname)
+ elif not match_o2 == None:
+ imgname = match_o2.group(1)
+ imgname = os.path.join(self._image_dir, imgname)
+ imgname_s = match_o2.group(2)
+ imgname_s = os.path.join(self._image_dir, imgname_s)
+
+ geom = self._get_png_geom(imgname_s)
+ if geom:
+ w = geom[0]
+ h = geom[1]
+ print self._fig_start("", styles, width=w, height=h)
+ else:
+ print self._fig_start("", styles)
+ print self._anchored_fig(imgname, str_title, imgname_s)
+ print self._fig_end(str_title, styles);
+
+
+
+ def _anchored_fig(self, file, alt, file_s=""):
+
+ if file_s == "":
+ file_s = re.sub(r"(.[A-Za-z0-9_]+)$", r"_s\1", file)
+
+ if not os.path.isfile(file_s):
+ file_s = file
+
+ alt = re.sub(r"""<[A-Za-z0-9!/]+.*?>""", "", alt)
+
+ ret = """<a href="%s">
+ <img src="%s" alt="%s">
+</a>
+""" % (file, file_s, alt)
+
+
+ return ret
+
+
+ def _fig_release(self, line):
+ try:
+ str_title = re.search(ur"^☆(図.*)$", line).group(1)
+ except AttributeError:
+ str_title = ""
+ print self._fig_start()
+
+ line = self.input.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_]+)$", r"_s\1", match_o1.group(1))
+ elif not match_o2 == None:
+ imgname = match_o1.group(1)
+ imgname_s = match_o1.group(2)
+
+
+ hash = self.hashlist.get(imgname, "")
+ hash_s = self.hashlist.get(imgname_s, "")
+ if hash_s == "":
+ hash_s = hash
+
+ print """<a href="/blob.pl?id=%s">
+ <slash type="image" id="%s" title="%s">
+ </a>
+ """ % (hash, hash_s, str_title)
+
+
+
+ print self._fig_end(str_title);
+
+
+ def _table_start(self, cap):
+ return """<div style="width:90%%; margin-left:auto;margin-right:auto;"><table align="center" border="1" class="table" width="100%%">
+ <caption><b>%s</b></caption>
+ """ % cap
+
+ def _table_end(self, footnote=""):
+ return "</table>\n%s</div>\n" % (footnote,)
+
+ def _table(self, line):
+ str_title = ""
+ self._table_buf1 = ""
+
+ try:
+ str_title = re.search(ur"^☆(表.*)$", line).group(1)
+ fig_name = re.search(ur"^☆(表[0-9A-Z]*)", line).group(1)
+ except AttributeError:
+ str_title = ""
+ fig_name = ""
+ if str_title.find(u"表*") == 0:
+ str_title = str_title.replace(u"表*", "")
+
+ print self._table_start(str_title)
+ self._table_buf1 = self._table_start(str_title)
+
+ num_row = 0
+ table_contents = []
+ footnote = ""
+ for line in self.input:
+ line = line.strip(" \n")
+ line = self._default_markup_rule(line)
+ if re.search(ur"^\s*$", line):
+ break
+ if re.search(ur"^※", line):
+ footnote = re.search(ur"^(※.*)$", line).group(1)
+ break
+ if re.search(ur"^〓", line):
+ line = re.sub(ur"^〓", "", line)
+ tag_mode = "th"
+ else:
+ tag_mode = "td"
+ table_contents.append([])
+ num_col = 0
+ for item in line.split("\t"):
+ if item == "":
+ if num_col == 0:
+ n = 1
+ try:
+ while table_contents[num_row-n][num_col]["item"] == "":
+ n += 1
+ table_contents[num_row-n][num_col]["row"] += 1
+ except IndexError:
+ pass
+ else:
+ n = 1
+ try:
+ while table_contents[num_row][num_col-n]["item"] == "":
+ n += 1
+ table_contents[num_row][num_col-n]["col"] += 1
+ except IndexError:
+ pass
+ if item == u"↓":
+ n = 1
+ try:
+ while table_contents[num_row-n][num_col]["item"] == "":
+ n += 1
+ table_contents[num_row-n][num_col]["row"] += 1
+ item = ""
+ except IndexError:
+ pass
+
+ if re.search(r'^".*"$', item):
+ item = re.search(r'^"(.*)"$', item).group(1)
+ table_contents[num_row].append({"tag":"th","item":item,"row":1,"col":1})
+ else:
+ table_contents[num_row].append({"tag":tag_mode,"item":item,"row":1,"col":1})
+ num_col = num_col + 1
+ num_row = num_row + 1
+
+ for row_item in table_contents:
+ line = "<tr>"
+ for item in row_item:
+ if item["item"] == "":
+ continue
+ line = line + "<" + item["tag"]
+ if not item["row"] == 1:
+ line = line + (' rowspan="%s"' % item["row"])
+ if not item["col"] == 1:
+ line = line + (' colspan="%s"' % item["col"])
+ line = line + ">"
+ line = line + item["item"]
+ line = line + "</" + item["tag"] + ">"
+ line = line + "</tr>\n"
+ print line,
+ self._table_buf1 = self._table_buf1 + line
+
+ # line = "<tr><th>" + re.sub(ur"^〓", "", line) + "</th></tr>"
+ # line = line.replace("\t", "</th><th>")
+ # print line
+ # else:
+ # line = "<tr><td>" + line + "</td></tr>"
+ # line = line.replace("\t", "</td><td>")
+ # print line
+
+ print self._table_end(footnote)
+ self._table_buf1 = self._table_buf1 + self._table_end()
+
+ def _call_tables(self, line):
+ try:
+ fig_name = re.search(ur"^☆call_tables\((表[0-9A-Z]+)", line).group(1)
+ except AttributeError:
+ return