from . import tool import datetime import html import re def table_parser(data, cel_data, start_data, num = 0): table_class = 'class="' all_table = 'style="' cel_style = 'style="' row_style = 'style="' row = '' cel = '' table_width = re.search("<table ?width=((?:(?!>).)*)>", data) if table_width: if re.search('^[0-9]+$', table_width.groups()[0]): all_table += 'width: ' + table_width.groups()[0] + 'px;' else: all_table += 'width: ' + table_width.groups()[0] + ';' table_height = re.search("<table ?height=((?:(?!>).)*)>", data) if table_height: if re.search('^[0-9]+$', table_height.groups()[0]): all_table += 'height: ' + table_height.groups()[0] + 'px;' else: all_table += 'height: ' + table_height.groups()[0] + ';' table_align = re.search("<table ?align=((?:(?!>).)*)>", data) if table_align: if table_align.groups()[0] == 'right': all_table += 'float: right;' elif table_align.groups()[0] == 'center': all_table += 'margin: auto;' table_text_align = re.search("<table ?textalign=((?:(?!>).)*)>", data) if table_text_align: num = 1 if table_text_align.groups()[0] == 'right': all_table += 'text-align: right;' elif table_text_align.groups()[0] == 'center': all_table += 'text-align: center;' row_table_align = re.search("<row ?textalign=((?:(?!>).)*)>", data) if row_table_align: if row_table_align.groups()[0] == 'right': row_style += 'text-align: right;' elif row_table_align.groups()[0] == 'center': row_style += 'text-align: center;' else: row_style += 'text-align: left;' table_cel = re.search("<-((?:(?!>).)*)>", data) if table_cel: cel = 'colspan="' + table_cel.groups()[0] + '"' else: cel = 'colspan="' + str(round(len(start_data) / 2)) + '"' table_row = re.search("<\|((?:(?!>).)*)>", data) if table_row: row = 'rowspan="' + table_row.groups()[0] + '"' row_bgcolor = re.search("<rowbgcolor=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)>", data) if row_bgcolor: row_style += 'background: ' + row_bgcolor.groups()[0] + ';' table_border = re.search("<table ?bordercolor=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)>", data) if table_border: all_table += 'border: ' + table_border.groups()[0] + ' 2px solid;' table_bgcolor = re.search("<table ?bgcolor=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)>", data) if table_bgcolor: all_table += 'background: ' + table_bgcolor.groups()[0] + ';' bgcolor = re.search("<bgcolor=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)>", data) if bgcolor: cel_style += 'background: ' + bgcolor.groups()[0] + ';' cel_width = re.search("<width=((?:(?!>).)*)>", data) if cel_width: cel_style += 'width: ' + cel_width.groups()[0] + 'px;' cel_height = re.search("<height=((?:(?!>).)*)>", data) if cel_height: cel_style += 'height: ' + cel_height.groups()[0] + 'px;' text_right = re.search("<\)>", data) text_center = re.search("<:>", data) text_left = re.search("<\(>", data) if text_right: cel_style += 'text-align: right;' elif text_center: cel_style += 'text-align: center;' elif text_left: cel_style += 'text-align: left;' elif num == 0: if re.search('^ ', cel_data) and re.search(' $', cel_data): cel_style += 'text-align: center;' elif re.search('^ ', cel_data): cel_style += 'text-align: right;' elif re.search(' $', cel_data): cel_style += 'text-align: left;' text_class = re.search("<table ?class=((?:(?!>).)+)>", data) if text_class: table_class += text_class.groups()[0] all_table += '"' cel_style += '"' row_style += '"' table_class += '"' return [all_table, row_style, cel_style, row, cel, table_class, num] def table_start(data): while 1: table = re.search('\n((?:(?:(?:(?:\|\|)+(?:(?:(?!\|\|).(?:\n)*)*))+)\|\|(?:\n)?)+)', data) if table: table = table.groups()[0] while 1: all_table = re.search('^((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*((?:(?!\|\|).\n*)*)', table) if all_table: all_table = all_table.groups() return_table = table_parser(all_table[1], all_table[2], all_table[0]) number = return_table[6] table = re.sub('^((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*', '\n
', table, 1) else: break table = re.sub('\|\|\n?$', '
', table) while 1: row_table = re.search('\|\|\n((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*((?:(?!\|\||<\/td>).\n*)*)', table) if row_table: row_table = row_table.groups() return_table = table_parser(row_table[1], row_table[2], row_table[0], number) table = re.sub('\|\|\n((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*', '', table, 1) else: break while 1: cel_table = re.search('((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*((?:(?:(?!\|\||<\/td>).)|\n)*\n*)', table) if cel_table: cel_table = cel_table.groups() return_table = table_parser(cel_table[1], re.sub('\n', ' ', cel_table[2]), cel_table[0], number) table = re.sub('((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*', '', table, 1) else: break data = re.sub('\n((?:(?:(?:(?:\|\|)+(?:(?:(?!\|\|).(?:\n)*)*))+)\|\|(?:\n)?)+)', table, data, 1) else: break return data def middle_parser(data): global end_data middle_stack = 0 middle_list = [] middle_number = 0 fol_num = 0 while 1: middle_data = re.search('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', data) if middle_data: middle_data = middle_data.groups() if not middle_data[1]: if middle_stack > 0: middle_stack += 1 data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*)(?P ?)|(}}}))', '{{{' + middle_data[0] + '\g', data, 1) else: if re.search('^(#|@|\+|\-)', middle_data[0]) and not re.search('^(#|@|\+|\-){2}', middle_data[0]): middle_search = re.search('^(#(?:[0-9a-f-A-F]{3}){1,2})', middle_data[0]) if middle_search: middle_list += ['span'] data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', '', data, 1) else: middle_search = re.search('^(?:#(\w+))', middle_data[0]) if middle_search: middle_list += ['span'] data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', '', data, 1) else: middle_search = re.search('^(?:@((?:[0-9a-f-A-F]{3}){1,2}))', middle_data[0]) if middle_search: middle_list += ['span'] data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', '', data, 1) else: middle_search = re.search('^(?:@(\w+))', middle_data[0]) if middle_search: middle_list += ['span'] data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', '', data, 1) else: middle_search = re.search('^(\+|-)([1-5])', middle_data[0]) if middle_search: middle_search = middle_search.groups() if middle_search[0] == '+': font_size = str(int(middle_search[1]) * 20 + 100) else: font_size = str(100 - int(middle_search[1]) * 10) middle_list += ['span'] data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', '', data, 1) else: middle_search = re.search('^#!wiki', middle_data[0]) if middle_search: middle_data_2 = re.search('{{{#!wiki(?: style=(?:"|')((?:(?!"|').)*)(?:"|'))?\n?', data) if middle_data_2: middle_data_2 = middle_data_2.groups() else: middle_data_2 = [''] middle_list += ['div_end'] data = re.sub('{{{#!wiki(?: style=(?:"|')((?:(?!"|').)*)(?:"|'))?\n?', '
', data, 1) else: middle_search = re.search('^#!syntax', middle_data[0]) if middle_search: middle_data_2 = re.search('{{{#!syntax ((?:(?!\n).)+)\n?', data) if middle_data_2: middle_data_2 = middle_data_2.groups() else: middle_data_2 = ['python'] middle_list += ['pre'] data = re.sub('{{{#!syntax ?((?:(?!\n).)*)\n?', '
', data, 1)
                                                else:
                                                    middle_search = re.search('^#!html', middle_data[0])
                                                    if middle_search:
                                                        middle_list += ['span']
                                                        
                                                        data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', '', data, 1)
                                                    else:
                                                        middle_search = re.search('^#!folding', middle_data[0])
                                                        if middle_search:
                                                            middle_list += ['2div']
                                                            
                                                            folding_data = re.search('{{{#!folding ?((?:(?!\n).)*)\n?', data)
                                                            if folding_data:
                                                                folding_data = folding_data.groups()
                                                            else:
                                                                folding_data = ['Test']
                                                            
                                                            data = re.sub('{{{#!folding ?((?:(?!\n).)*)\n?', '
' + str(folding_data[0]) + ' 
[do]
', data, 1) else: data = re.sub('(?:{{{((?:(?! |{{{|}}}|<).)*) ?|(}}}))', '', data, 1) del(middle_list[middle_number]) else: break num = 0 while 1: nowiki_data = re.search('((?:(?:(?!<\/code>).)*\n*)*)<\/code>', data) if nowiki_data: nowiki_data = nowiki_data.groups() num += 1 end_data += [['nowiki_' + str(num), nowiki_data[0], 'code']] data = re.sub('((?:(?:(?!<\/code>).)*\n*)*)<\/code>', '', data, 1) else: break num = 0 while 1: syntax_data = re.search('((?:(?:(?:(?!<\/code>|((?:(?:(?:(?!<\/code>|', data, 1) else: break while 1: html_data = re.search('((?:(?:(?:(?!<\/span>)).)+\n*)+)<\/span>', data) if html_data: html_data = html_data.groups() html_data_2 = html_data[0] can_html = ['b', 'span'] dic = {} for i in can_html: while 1: test = re.search('<' + i + '((?:(?!>).)*)>', html_data_2) if test: test = test.groups()[0] test = re.sub('"', '"', test) html_data_2 = re.sub('<' + i + '((?:(?!>).)*)>', '<' + i + test + '>', html_data_2, 1) else: break for i in can_html: span_num = re.findall('<' + i + '(?:(?:(?!>).)*)>', html_data_2) span_num = len(span_num) span_end_num = re.findall('<\/' + i + '>', html_data_2) span_end_num = len(span_end_num) dic[i] = span_num - span_end_num for i in can_html: html_data_2 += ('' * dic[i]) data = re.sub('((?:(?:(?:(?!<\/span>)).)+\n*)+)<\/span>', '' + html_data_2 + '<\/span>', data, 1) else: break return data def link_fix(main_link): if re.search('^:', main_link): main_link = re.sub('^:', '', main_link) main_link = re.sub('^사용자:', 'user:', main_link) main_link = re.sub('^파일:', 'file:', main_link) main_link = re.sub('^분류:', 'category:', main_link) other_link = re.search('(#.+)$', main_link) if other_link: other_link = other_link.groups()[0] main_link = re.sub('(#.+)$', '', main_link) else: other_link = '' return [main_link, other_link] def namu(conn, data, title, main_num): curs = conn.cursor() data = '\n' + data + '\n' backlink = [] plus_data = ''' ''' global end_data end_data = [] data = html.escape(data) data = re.sub('\r\n', '\n', data) data = middle_parser(data) include_re = re.compile('\[include\(((?:(?!\)\]).)+)\)\]', re.I) while 1: include = include_re.search(data) if include: include = include.groups()[0] include_data = re.search('^((?:(?!,).)+)', include) if include_data: include_data = include_data.groups()[0] else: include_data = 'Test' include_link = include_data backlink += [[title, include_link, 'include']] include = re.sub('^((?:(?!,).)+)', '', include) num = 0 while 1: include_one_nowiki = re.search('(?:\\\\){2}(.)', include) if include_one_nowiki: include_one_nowiki = include_one_nowiki.groups() num += 1 end_data += [['include_one_nowiki_' + str(num), include_one_nowiki[0], 'normal']] include = re.sub('(?:\\\\){2}(.)', '', include, 1) else: break curs.execute("select data from data where title = ?", [include_data]) include_data = curs.fetchall() if include_data: include_parser = include_data[0][0] while 1: include_plus = re.search(', ?((?:(?!=).)+)=((?:(?!,).)+)', include) if include_plus: include_plus = include_plus.groups() include_parser = re.sub('@' + include_plus[0] + '@', include_plus[1], include_parser) include = re.sub(', ?((?:(?!=).)+)=((?:(?!,).)+)', '', include, 1) else: break include_parser = re.sub('\[\[(?:category|분류):(((?!\]\]|#include).)+)\]\]', '', include_parser) include_parser = html.escape(include_parser) data = include_re.sub('\n[' + include_link + ']\n' + include_parser + '\n', data, 1) else: data = include_re.sub('' + include_link + '', data, 1) else: break data = re.sub('\r\n', '\n', data) data = middle_parser(data) data = re.sub('&', '&', data) curs.execute('select html from html_filter where kind = ""') html_db = curs.fetchall() src_list = ["www.youtube.com", "serviceapi.nmv.naver.com", "tv.kakao.com", "www.google.com", "serviceapi.rmcnmv.naver.com"] html_list = ['div', 'span', 'embed', 'iframe', 'ruby', 'rp', 'rt'] html_data = re.findall('<(\/)?((?:(?!>| ).)+)( (?:(?:(?!>).)+)?)?>', data) for in_data in html_data: if in_data[0] == '': if in_data[1] in html_list or (html_db and in_data[1] in html_db[0]): if re.search('<\/' + in_data[1] + '>', data): src = re.search('src=([^ ]*)', in_data[2]) if src: v_src = re.search('http(?:s)?:\/\/([^/\'" ]*)', src.groups()[0]) if v_src: if not v_src.groups()[0] in src_list: and_data = re.sub(''', '\'', re.sub('"', '"', re.sub('src=([^ ]*)', '', in_data[2]))) else: and_data = re.sub(''', '\'', re.sub('"', '"', in_data[2])) else: and_data = re.sub(''', '\'', re.sub('"', '"', re.sub('src=([^ ]*)', '', in_data[2]))) else: and_data = re.sub(''', '\'', re.sub('"', '"', in_data[2])) data = data.replace('<' + in_data[1] + in_data[2] + '>', '<' + in_data[1] + and_data + '>', 1) data = re.sub('<\/' + in_data[1] + '>', '', data, 1) position = re.compile('position', re.I) data = position.sub('', data) data = re.sub('\n( +)\|\|', '\n||', data) data = re.sub('\|\|( +)\n', '||\n', data) data = re.sub('\n##(((?!\n).)+)', '', data) while 1: wiki_table_data = re.search('
).)+)>((?:(?!
).\n*)+)<\/div_end>', data) if wiki_table_data: wiki_table_data = wiki_table_data.groups() if re.search('\|\|', wiki_table_data[1]): end_parser = re.sub('\n$', '', re.sub('^\n', '', table_start('\n' + wiki_table_data[1] + '\n'))) else: end_parser = wiki_table_data[1] data = re.sub('
).)+)>((?:(?!
).\n*)+)<\/div_end>', '
' + end_parser + '
', data, 1) else: break data = re.sub('<\/div_end>', '
', data) data = re.sub('<\/td>', '', data) first = 0 math_re = re.compile('\[math\(((?:(?!\)\]).)+)\)\]', re.I) while 1: math = math_re.search(data) if math: if first == 0: plus_data += ''' ''' math = math.groups()[0] first += 1 data = math_re.sub('', data, 1) plus_data += '' else: break num = 0 while 1: one_nowiki = re.search('(?:\\\\)(.)', data) if one_nowiki: one_nowiki = one_nowiki.groups() num += 1 end_data += [['one_nowiki_' + str(num), one_nowiki[0], 'normal']] data = re.sub('(?:\\\\)(.)', '', data, 1) else: break while 1: hr = re.search('\n-{4,9}\n', data) if hr: data = re.sub('\n-{4,9}\n', '\n
\n', data, 1) else: break data += '\n' data = data.replace('\\', '\') data = re.sub(''''(?P((?!''').)+)'''', '\g', data) data = re.sub('''(?P((?!'').)+)''', '\g', data) data = re.sub('~~(?P(?:(?!~~).)+)~~', '\g', data) data = re.sub('--(?P(?:(?!~~).)+)--', '\g', data) data = re.sub('__(?P(?:(?!__).)+)__', '\g', data) data = re.sub('\^\^(?P(?:(?!\^\^).)+)\^\^', '\g', data) data = re.sub(',,(?P(?:(?!,,).)+),,', '\g', data) redirect_re = re.compile('\n#(?:redirect|넘겨주기) ((?:(?!\n).)+)\n', re.I) redirect = redirect_re.search(data) if redirect: redirect = redirect.groups()[0] return_link = link_fix(redirect) main_link = return_link[0] other_link = return_link[1] backlink += [[title, main_link, 'redirect']] data = redirect_re.sub('\n * ' + title + ' - [[' + main_link + ']]\n', data, 1) no_toc_re = re.compile('\[(?:목차|toc)\((?:no)\)\]\n', re.I) toc_re = re.compile('\[(?:목차|toc)\]', re.I) if not no_toc_re.search(data): if not toc_re.search(data): data = re.sub('\n(?P={1,6}) ?(?P(?:(?!=).)+) ?={1,6}\n', '\n[toc]\n\g \g \g\n', data, 1) else: data = no_toc_re.sub('', data) toc_full = 0 toc_top_stack = 6 toc_stack = [0, 0, 0, 0, 0, 0] edit_number = 0 toc_data = '
toc\n\n' while 1: toc = re.search('\n(={1,6}) ?((?:(?!\n).)+) ?\n', data) if toc: toc = toc.groups() toc_number = len(toc[0]) edit_number += 1 if toc_full > toc_number: for i in range(toc_number, 6): toc_stack[i] = 0 if toc_top_stack > toc_number: toc_top_stack = toc_number toc_full = toc_number toc_stack[toc_number - 1] += 1 toc_number = str(toc_number) all_stack = '' for i in range(0, 6): all_stack += str(toc_stack[i]) + '.' while 1: if re.search('[^0-9]0\.', all_stack): all_stack = re.sub('[^0-9]0\.', '.', all_stack) else: break all_stack = re.sub('^0\.', '', all_stack) data = re.sub('\n(={1,6}) ?((?:(?!\n).)+) ?\n', '\n' + all_stack + ' ' + re.sub('=*$', '', toc[1]) + ' (Edit)\n', data, 1) toc_main_data = toc[1] toc_main_data = re.sub('=*$', '', toc_main_data) toc_main_data = re.sub('\[\*((?:(?! |\]).)*)(?: ((?:(?!(\[\*(?:(?:(?!\]).)+)\]|\])).)+))?\]', '', toc_main_data) toc_main_data = re.sub('<\/span>', '(수식)', toc_main_data) toc_data += '' + all_stack + ' ' + toc_main_data + '\n' else: break toc_data += '
' data = toc_re.sub(toc_data, data) data = tool.savemark(data) anchor_re = re.compile("\[anchor\((?P(?:(?!\)\]).)+)\)\]", re.I) data = anchor_re.sub('', data) ruby_re = re.compile("\[ruby\((?P(?:(?!,).)+)\, ?(?P(?:(?!\)\]).)+)\)\]", re.I) data = ruby_re.sub('\g(\g)', data) now_time = tool.get_time() date_re = re.compile('\[date\]', re.I) data = date_re.sub(now_time, data) time_data = re.search('^([0-9]{4}-[0-9]{2}-[0-9]{2})', now_time) time = time_data.groups() age_re = re.compile('\[age\(([0-9]{4}-[0-9]{2}-[0-9]{2})\)\]', re.I) while 1: age_data = age_re.search(data) if age_data: age = age_data.groups()[0] old = datetime.datetime.strptime(time[0], '%Y-%m-%d') will = datetime.datetime.strptime(age, '%Y-%m-%d') e_data = old - will data = age_re.sub(str(int(e_data.days / 365)), data, 1) else: break dday_re = re.compile('\[dday\(([0-9]{4}-[0-9]{2}-[0-9]{2})\)\]', re.I) while 1: dday_data = dday_re.search(data) if dday_data: dday = dday_data.groups()[0] old = datetime.datetime.strptime(time[0], '%Y-%m-%d') will = datetime.datetime.strptime(dday, '%Y-%m-%d') e_data = old - will if re.search('^-', str(e_data.days)): e_day = str(e_data.days) else: e_day = '+' + str(e_data.days) data = dday_re.sub(e_day, data, 1) else: break video_re = re.compile('\[(youtube|kakaotv|nicovideo)\(((?:(?!\)\]).)+)\)\]', re.I) youtube_re = re.compile('youtube', re.I) kakaotv_re = re.compile('kakaotv', re.I) while 1: video = video_re.search(data) if video: video = video.groups() width = re.search(', ?width=((?:(?!,).)+)', video[1]) if width: video_width = width.groups()[0] else: video_width = '560' height = re.search(', ?height=((?:(?!,).)+)', video[1]) if height: video_height = height.groups()[0] else: video_height = '315' code = re.search('^((?:(?!,).)+)', video[1]) if code: video_code = code.groups()[0] else: video_code = '' if youtube_re.search(video[0]): video_code = re.sub('^https:\/\/www\.youtube\.com\/watch\?v=', '', video_code) video_code = re.sub('^https:\/\/youtu\.be\/', '', video_code) video_src = 'https://www.youtube.com/embed/' + video_code elif kakaotv_re.search(video[0]): video_code = re.sub('^https:\/\/tv\.kakao\.com\/channel\/9262\/cliplink\/', '', video_code) video_code = re.sub('^http:\/\/tv\.kakao\.com\/v\/', '', video_code) video_src = 'https://tv.kakao.com/embed/player/cliplink/' + video_code +'?service=kakao_tv' else: video_src = 'https://embed.nicovideo.jp/watch/' + video_code data = video_re.sub('', data, 1) else: break while 1: block = re.search('(\n(?:> ?(?:(?:(?!\n).)+)?\n)+)', data) if block: block = block.groups()[0] block = re.sub('^\n> ?', '', block) block = re.sub('\n> ?', '\n', block) block = re.sub('\n$', '', block) data = re.sub('(\n(?:> ?(?:(?:(?!\n).)+)?\n)+)', '\n
' + block + '
\n', data, 1) else: break data = re.sub('(?P\n +\* ?(?:(?:(?!\|\|).)+))\|\|', '\g\n ||', data) while 1: li = re.search('(\n(?:(?: *)\* ?(?:(?:(?!\n).)+)\n)+)', data) if li: li = li.groups()[0] while 1: sub_li = re.search('\n(?:( *)\* ?((?:(?!\n).)+))', li) if sub_li: sub_li = sub_li.groups() if len(sub_li[0]) == 0: margin = 20 else: margin = len(sub_li[0]) * 20 li = re.sub('\n(?:( *)\* ?((?:(?!\n).)+))', '
  • ' + sub_li[1] + '
    • ', li, 1) else: break data = re.sub('(\n(?:(?: *)\* ?(?:(?:(?!\n).)+)\n)+)', '\n\n
      ' + li + '
    \n', data, 1) else: break data = re.sub('<\/ul>\n \|\|', '||', data) while 1: indent = re.search('\n( +)', data) if indent: indent = len(indent.groups()[0]) margin = '' * indent data = re.sub('\n( +)', '\n' + margin, data, 1) else: break data = table_start(data) category = '\n
    category : ' category_re = re.compile('^(?:category|분류):', re.I) while 1: link = re.search('\[\[((?:(?!\[\[|\]\]).)+)\]\]', data) if link: link = link.groups()[0] link_split = re.search('((?:(?!\|).)+)(?:\|((?:(?!\|).)+))', link) if link_split: link_split = link_split.groups() main_link = link_split[0] see_link = link_split[1] else: main_link = link see_link = link if re.search('^((?:file|파일)|(?:out|외부)):', main_link): file_style = '' width = re.search('width=((?:(?!&).)+)', see_link) if width: file_width = width.groups()[0] if re.search('px$', file_width): file_style += 'width: ' + file_width + ';' else: file_style += 'width: ' + file_width + 'px;' height = re.search('height=((?:(?!&).)+)', see_link) if height: file_height = height.groups()[0] if re.search('px$', file_height): file_style += 'height: ' + file_height + ';' else: file_style += 'height: ' + file_height + 'px;' align = re.search('align=((?:(?!&).)+)', see_link) if align: file_align = align.groups()[0] if file_align == 'center': file_align = 'display: block; text-align: center;' else: file_align = 'float: ' + file_align + ';' else: file_align = '' if re.search('^(?:out|외부):', main_link): file_src = re.sub('^(?:out|외부):', '', main_link) file_alt = main_link exist = 'Yes' else: file_data = re.search('^(?:file|파일):((?:(?!\.).)+)\.(.+)$', main_link) if file_data: file_data = file_data.groups() file_name = file_data[0] file_end = file_data[1] backlink += [[title, main_link, 'file']] else: file_name = 'TEST' file_end = 'jpg' file_src = '/image/' + tool.sha224(file_name) + '.' + file_end file_alt = 'file:' + file_name + '.' + file_end curs.execute("select title from data where title = ?", [file_alt]) exist = curs.fetchall() if exist: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + file_alt + '', data, 1) else: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + file_alt + '', data, 1) elif category_re.search(main_link): see_link = re.sub('#include', '', see_link) main_link = re.sub('#include', '', category_re.sub('category:', main_link)) if re.search('#blur', main_link): see_link = 'Hidden' link_id = 'id="inside"' main_link = re.sub('#blur', '', main_link) else: link_id = '' backlink += [[title, main_link, 'cat']] category += '' + category_re.sub('', see_link) + ' / ' data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '', data, 1) elif re.search('^wiki:', main_link): data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + see_link + '', data, 1) elif re.search('^inter:((?:(?!:).)+):', main_link): inter_data = re.search('^inter:((?:(?!:).)+):((?:(?!\]\]|\|).)+)', main_link) inter_data = inter_data.groups() curs.execute('select link from inter where title = ?', [inter_data[0]]) inter = curs.fetchall() if inter: if see_link != main_link: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + inter_data[0] + ':' + see_link + '', data, 1) else: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + inter_data[0] + ':' + inter_data[1] + '', data, 1) else: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', 'Not exist', data, 1) elif re.search('^\/', main_link): under_title = re.search('^(\/(?:.+))$', main_link) under_title = under_title.groups()[0] if see_link != main_link: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '[[' + title + under_title + '|' + see_link + ']]', data, 1) else: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '[[' + title + under_title + ']]', data, 1) elif re.search('^http(s)?:\/\/', main_link): data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + see_link + '', data, 1) else: return_link = link_fix(main_link) main_link = return_link[0] other_link = return_link[1] if re.search('^\/', main_link): main_link = re.sub('^\/', title + '/', main_link) elif re.search('\.\.\/\/', main_link): main_link = re.sub('\.\.\/\/', '/', main_link) elif re.search('^\.\.\/', main_link): main_link = re.sub('^\.\.\/', re.sub('(?P.+)\/.*$', '\g', title), main_link) if not re.search('^\|', main_link): if main_link != title: if main_link != '': curs.execute("select title from data where title = ?", [main_link]) if not curs.fetchall(): link_id = 'id="not_thing"' backlink += [[title, main_link, 'no']] else: link_id = '' backlink += [[title, main_link, '']] data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + see_link + '', data, 1) else: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + see_link + '', data, 1) else: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '' + see_link + '', data, 1) else: data = re.sub('\[\[((?:(?!\[\[|\]\]).)+)\]\]', '[[' + link + ']]', data, 1) else: break br_re = re.compile('\[br\]', re.I) data = br_re.sub('
    ', data) footnote_number = 0 footnote_all = [] footnote_dict = {} footnote_re = {} footdata_all = '\n
      ' while 1: footnote = re.search('(?:\[\*((?:(?! |\]).)*)(?: ((?:(?!(?:\[\*(?:(?:(?!\]).)+)\]|\])).)+))?\]|(\[(?:각주|footnote)\]))', data) if footnote: footnote_data = footnote.groups() if footnote_data[2]: footnote_all.sort() for footdata in footnote_all: if footdata[2] == 0: footdata_in = '' else: footdata_in = footdata[2] footdata_all += '
    • (' + footdata[1] + ') ' + footdata_in + '
      • ' data = re.sub('(?:\[\*((?:(?! ).)*) ((?:(?!\]).)+)\]|(\[(?:각주|footnote)\]))', footdata_all + '
    ', data, 1) footnote_all = [] footdata_all = '\n
      ' else: footnote = footnote_data[1] footnote_name = footnote_data[0] if footnote_name and not footnote: if footnote_name in footnote_dict: footnote_re[footnote_name] += 1 foot_plus_num = str(footnote_re[footnote_name]) footshort = footnote_dict[footnote_name] + '.' + foot_plus_num footnote_all += [[float(footshort), footshort, 0]] data = re.sub('(?:\[\*((?:(?! |\]).)*)(?: ((?:(?!(?:\[\*(?:(?:(?!\]).)+)\]|\])).)+))?\]|(\[(?:각주|footnote)\]))', '(' + footshort + ')', data, 1) else: data = re.sub('(?:\[\*((?:(?! |\]).)*)(?: ((?:(?!(?:\[\*(?:(?:(?!\]).)+)\]|\])).)+))?\]|(\[(?:각주|footnote)\]))', '(' + footnote_name + ')', data, 1) else: footnote_number += 1 if not footnote_name: footnote_name = str(footnote_number) footnote_dict.update({ footnote_name : str(footnote_number) }) if not footnote_name in footnote_re: footnote_re.update({ footnote_name : 0 }) else: footnote_re[footnote_name] += 1 footnote_all += [[footnote_number, footnote_name, footnote]] data = re.sub('(?:\[\*((?:(?! |\]).)*)(?: ((?:(?!(?:\[\*(?:(?:(?!\]).)+)\]|\])).)+))?\]|(\[(?:각주|footnote)\]))', '(' + footnote_name + ')', data, 1) else: break data = re.sub('\n+$', '', data) footnote_all.sort() for footdata in footnote_all: if footdata[2] == 0: footdata_in = '' else: footdata_in = footdata[2] footdata_all += '
    • (' + footdata[1] + ') ' + footdata_in + '
      • ' footdata_all += '
    ' if footdata_all == '\n
      ': footdata_all = '' data = re.sub('\n$', footdata_all, data + '\n', 1) category += '
      ' category = re.sub(' / <\/div>$', '
      ', category) if category == '\n
      category :
      ': category = '' data += category i = 0 while 1: try: _ = end_data[i][0] except: break if end_data[i][2] == 'normal': data = data.replace('', end_data[i][1]) data = data.replace(tool.url_pas(''), tool.url_pas(end_data[i][1])) else: if re.search('\n', end_data[i][1]): data = data.replace('', '\n
      ' + re.sub('^\n', '', end_data[i][1]) + '
      ') else: data = data.replace('', '' + end_data[i][1] + '') i += 1 if main_num == 1: i = 0 while 1: try: _ = backlink[i][0] except: break find_data = re.search('', backlink[i][1]) if find_data: j = 0 find_data = find_data.groups()[0] while 1: try: _ = end_data[j][0] except: break if end_data[j][0] == find_data: backlink[i][1] = backlink[i][1].replace('', end_data[j][1]) j += 1 i += 1 data = re.sub('<\/td_end>', '', data) data = re.sub('\n', '', data) data = re.sub('\n<\/include>', '', data) data = re.sub('(?P<\/h[0-9]>)(\n)+', '\g', data) data = re.sub('\n\n
        ', '\n
          ', data) data = re.sub('<\/ul>\n\n', '
        ', data) data = re.sub('^(\n)+', '', data) data = re.sub('(\n)+
          ', '
            ', data) data = re.sub('(?P).)*)>)\n', '\g', data) data = re.sub('(\n)?
            (\n)?', '
            ', data) data = re.sub('<\/ul>\n\n
              ', '
            \n
              ', data) data = re.sub('\n', '
              ', data) return [data, plus_data, backlink]