from . import tool import datetime import html import re 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 = '' main_link = re.sub('\\\\#', '%23', main_link) return [main_link, other_link] def table_parser(data, cel_data, start_data, num = 0): table_class = 'class="' div_style = 'style="' 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]+$', table_width.groups()[0]): div_style += 'width: ' + table_width.groups()[0] + 'px;' else: div_style += 'width: ' + table_width.groups()[0] + ';' all_table += 'width: 100%;' table_height = re.search("<table ?height=((?:(?!>).)*)>", data) if table_height: if re.search('^[0-9]+$', table_height.groups()[0]): all_table += 'height: ' + table_height.groups()[0] + 'px;' else: all_table += 'height: ' + table_height.groups()[0] + ';' # width, height table_align = re.search("<table ?align=((?:(?!>).)*)>", data) if table_align: if table_align.groups()[0] == 'right': div_style += '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;' # align 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+)(?:,(#(?:[0-9a-f-A-F]{3}){1,2}|\w+))?>", data) if row_bgcolor: row_style += 'background: ' + row_bgcolor.groups()[0] + ';' row_bgcolor = re.search("<rowcolor=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)(?:,(#(?:[0-9a-f-A-F]{3}){1,2}|\w+))?>", data) if row_bgcolor: row_style += 'color: ' + row_bgcolor.groups()[0] + ';' # row table_border = re.search("<table ?bordercolor=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)(?:,(#(?:[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+)(?:,(#(?:[0-9a-f-A-F]{3}){1,2}|\w+))?>", data) if table_bgcolor: all_table += 'background: ' + table_bgcolor.groups()[0] + ';' table_bgcolor = re.search("<table ?color=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)(?:,(#(?:[0-9a-f-A-F]{3}){1,2}|\w+))?>", data) if table_bgcolor: all_table += 'color: ' + table_bgcolor.groups()[0] + ';' # all bgcolor = re.search("<(?:bgcolor=)?(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)(?:,(#(?:[0-9a-f-A-F]{3}){1,2}|\w+))?>", data) if bgcolor: cel_style += 'background: ' + bgcolor.groups()[0] + ';' bgcolor = re.search("<color=(#(?:[0-9a-f-A-F]{3}){1,2}|\w+)(?:,(#(?:[0-9a-f-A-F]{3}){1,2}|\w+))?>", data) if bgcolor: cel_style += 'color: ' + bgcolor.groups()[0] + ';' cel_width = re.search("<width=((?:(?!>).)*)>", data) if cel_width: if re.search('^[0-9]+$', cel_width.groups()[0]): cel_style += 'width: ' + cel_width.groups()[0] + 'px;' else: cel_style += 'width: ' + cel_width.groups()[0] + ';' cel_height = re.search("<height=((?:(?!>).)*)>", data) if cel_height: if re.search('^[0-9]+$', cel_height.groups()[0]): cel_style += 'height: ' + cel_height.groups()[0] + 'px;' else: cel_style += 'height: ' + cel_height.groups()[0] + ';' # cel 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(' $', cel_data): cel_style += 'text-align: left;' text_class = re.search("<table ?class=((?:(?!>).)+)>", data) if text_class: table_class += text_class.groups()[0] div_style += '"' all_table += '"' cel_style += '"' row_style += '"' table_class += '"' return [all_table, row_style, cel_style, row, cel, table_class, num, div_style] def table_start(data): while 1: table = re.search('\n((?:(?:(?:(?:\|\|)+(?:(?:(?!\|\|).(?:\n)*)*))+)\|\|(?:\n)?)+)', data) if table: table = table.groups()[0] while 1: all_table = re.search('^((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*((?:(?!\|\|).\n*)*)', table) if all_table: all_table = all_table.groups() return_table = table_parser(all_table[1], all_table[2], all_table[0]) number = return_table[6] table = re.sub( '^((?:\|\|)+)((?:<(?:(?:(?!>).)+)>)*)\n*', '\n' + \ '
' + \ '' + \ '' + \ '' + \ '
', table, 1 ) else: break table = re.sub('\|\|\n?$', '
', 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, fol_num, syntax_num, folding_num, include_num): global end_data global plus_data middle_stack = 0 middle_list = [] middle_number = 0 html_number = 0 middle_re = re.compile('(?:{{{((?:(?:(?! |{{{|}}}|<).)*) ?)|(}}}))') middle_all_data = middle_re.findall(data) for middle_data in middle_all_data: 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]): if re.search('^(#(?:[0-9a-f-A-F]{3}){1,2})', middle_data[0]): middle_search = re.search('^(#(?:[0-9a-f-A-F]{3}){1,2})', middle_data[0]) middle_list += ['span'] data = middle_re.sub('', data, 1) elif re.search('^(?:#(\w+))', middle_data[0]): middle_search = re.search('^(?:#(\w+))', middle_data[0]) middle_list += ['span'] data = middle_re.sub('', data, 1) elif re.search('^(?:@((?:[0-9a-f-A-F]{3}){1,2}))', middle_data[0]): middle_search = re.search('^(?:@((?:[0-9a-f-A-F]{3}){1,2}))', middle_data[0]) middle_list += ['span'] data = middle_re.sub('', data, 1) elif re.search('^(?:@(\w+))', middle_data[0]): middle_search = re.search('^(?:@(\w+))', middle_data[0]) middle_list += ['span'] data = middle_re.sub('', data, 1) elif re.search('^(\+|-)([1-5])', middle_data[0]): middle_search = re.search('^(\+|-)([1-5])', middle_data[0]) 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 = middle_re.sub('', data, 1) elif re.search('^#!wiki', middle_data[0]): 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_1'] data = re.sub( '{{{#!wiki(?: style=(?:"|')((?:(?!"|').)*)(?:"|'))?(?: *)\n?', '
', data, 1 ) elif re.search('^#!syntax', middle_data[0]): 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'] if syntax_num == 0: plus_data += '' syntax_num = 1 middle_list += ['pre'] data = re.sub( '{{{#!syntax ?((?:(?!\n).)*)\n?', '
',
                            data,
                            1
                        )
                    elif re.search('^#!folding', middle_data[0]):
                        middle_list += ['2div']

                        folding_data = re.search('{{{#!folding ?((?:(?!\n).)*)\n?', data)
                        if folding_data:
                            folding_data = folding_data.groups()
                        else:
                            folding_data = ['Test']

                        if folding_num == 0:
                            folding_num = 1

                        data = re.sub(
                            '{{{#!folding ?((?:(?!\n).)*)\n?', '' + \
                            '
' + \ str(folding_data[0]) + ' ' + \ '
' + \ '' + \ '[+]' + \ '' + \ '' + \ '
', data, 1) else: data = middle_re.sub('', data, 1) del(middle_list[middle_number]) while 1: if middle_stack == 0: break else: if middle_list == []: data += '}}}' else: if middle_stack > 0: middle_stack -= 1 if middle_stack > 0: data += '}}}' else: if middle_number > 0: middle_number -= 1 if middle_list[middle_number] == '2div': data += '' elif middle_list[middle_number] == 'pre': data += '' else: data += '' del(middle_list[middle_number]) 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 return [data, [fol_num, syntax_num, folding_num]] def namumark(conn, data, title, main_num, include_num): curs = conn.cursor() global plus_data global end_data data = '\n' + data + '\n' plus_data = '' backlink = [] end_data = {} include_num = include_num + '_' if include_num else '' data = re.sub('(?P(?:(?!<\/math>).)+)<\/math>', '[math(\g)]', data) data = html.escape(data) data = re.sub('\r\n', '\n', data) first = 0 math_re = re.compile('\[math\(((?:(?!\)\]).)+)\)\]', re.I) while 1: math = math_re.search(data) if math: math = math.groups()[0] first += 1 data = math_re.sub('', data, 1) plus_data += ''' ''' else: break data = re.sub('\\\\{', '', data) data = middle_parser(data, 0, 0, 0, include_num)[0] data = re.sub('', '\\{', data) 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 include_re = re.compile('\[include\(((?:(?!\)\]).)+)\)\]', re.I) i = 0 while 1: i += 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']] curs.execute(tool.db_change("select title from data where title = ?"), [include_data]) if curs.fetchall(): data = include_re.sub('' + \ '[' + include_link + ']
' + \ '', data, 1) include_plus_data = [] while 1: include_plus = re.search(', ?((?:(?!=).)+)=((?:(?!,).)+)', include) if include_plus: include_plus = include_plus.groups() include_data_set = include_plus[1] find_data = re.findall('', include_data_set) for j in find_data: include_data_set = include_data_set.replace('', end_data[j][0]) include_plus_data += [[include_plus[0], include_data_set]] include = re.sub(', ?((?:(?!=).)+)=((?:(?!,).)+)', '', include, 1) else: break plus_data += '' else: data = include_re.sub('[' + include_link + ']', data, 1) else: break data = re.sub('\r\n', '\n', data) data = re.sub('&', '&', data) data = re.sub('\n( +)\|\|', '\n||', data) data = re.sub('\|\|( +)\n', '||\n', data) data = re.sub('\n##(((?!\n).)+)', '', data) data = re.sub('
\n', '
', data) while 1: wiki_table_data = re.search('
).)+)>((?:(?!
).\n*)+)<\/div_1>', 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_1>', '
' + end_parser + '', data, 1) else: break data = re.sub('<\/div_2>', '
', data) data = re.sub('<\/td>', '', data) data += '\n' data = data.replace('\\', '\') 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 + other_link, 'redirect']] data = redirect_re.sub( '\n' + \ '' + \ '\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) data = '
' + 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).)+) ?(?:={1,6})\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) all_stack = re.sub('\.$', '', all_stack) new_toc_data = re.sub('=*$', '', toc[1]) new_toc_data = re.sub(' +$', '', new_toc_data) if re.search('^# ?(?P[^#]+) ?#$', new_toc_data): fol_head = '+' new_toc_data = re.sub('^# ?(?P[^#]+) ?#$', '\g', new_toc_data) else: fol_head = '-' data = re.sub( '\n(={1,6}) ?((?:(?!\n).)+) ?\n', '\n' + \ '
' '' + \ '' + all_stack + '. ' + new_toc_data + ' ' + \ '' + \ '(Edit)' + \ ' ' + \ '' + \ '[' + fol_head + ']' + \ '' + \ '' + \ '' + \ '' data = toc_re.sub(toc_data, data) data = tool.savemark(data) data = re.sub("\[anchor\((?P(?:(?!\)\]).)+)\)\]", '', data, flags = re.I) ruby_all = re.findall("\[ruby\(((?:(?:(?!\)\]).)+))\)\]", data, flags = re.I) for i in ruby_all: ruby_code = re.search('^([^,]+)', i) if ruby_code: ruby_code = ruby_code.groups()[0] else: ruby_code = 'Test' ruby_top = re.search('ruby=([^,]+)', i, flags = re.I) if ruby_top: ruby_top = ruby_top.groups()[0] else: ruby_top = 'Test' ruby_color = re.search('color=([^,]+)', i, flags = re.I) if ruby_color: ruby_color = 'color: ' + ruby_color.groups()[0] + ';' else: ruby_color = '' ruby_data = '' + \ '' + \ ruby_code \ + '(' + \ '' + ruby_top + '' + \ ')' + \ '' + \ '' data = re.sub("\[ruby\(((?:(?:(?!\)\]).)+))\)\]", ruby_data, data, 1, flags = re.I) curs.execute(tool.db_change('select data from other where name = "count_all_title"')) all_title = curs.fetchall() data = re.sub('\[pagecount\]', all_title[0][0], data, flags = re.I) now_time = tool.get_time() data = re.sub('\[date\]', now_time, data, flags = re.I) 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] try: 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) except: data = age_re.sub('age-error', 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] try: 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) except: data = dday_re.sub('dday-error', 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] if re.search('^[0-9]+$', video_width): video_width += 'px' else: video_width = '560px' height = re.search(', ?height=((?:(?!,).)+)', video[1]) if height: video_height = height.groups()[0] if re.search('^[0-9]+$', video_height): video_height += 'px' else: video_height = '315px' code = re.search('^((?:(?!,).)+)', video[1]) if code: video_code = code.groups()[0] else: video_code = '' video_start = '' if youtube_re.search(video[0]): start = re.search(', ?(start=(?:(?!,).)+)', video[1]) if start: video_start = '?' + start.groups()[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$', '', block) data = re.sub('(\n(?:> ?(?:(?:(?!\n).)+)?\n)+)', '\n
' + block + '
\n', data, 1) else: break while 1: hr = re.search('\n-{4,9}\n', data) if hr: data = re.sub('\n-{4,9}\n', '\n
\n', data, 1) else: break data = re.sub('(?P\n +\* ?(?:(?:(?!\|\|).)+))\|\|', '\g\n ||', data) data = re.sub('(?P
' category = re.sub(' \| <\/div><\/div>$', '
', category) if category == '

Category :
': category = '' data += category for i in end_data: if end_data[i][1] == 'normal': data = data.replace('', end_data[i][0]) data = data.replace(tool.url_pas(''), tool.url_pas(end_data[i][0])) else: if re.search('\n', end_data[i][0]): data = data.replace('', '\n
' + re.sub('^\n', '', end_data[i][0]) + '
') else: data = data.replace('', '' + end_data[i][0] + '') if main_num == 1: i = 0 while 1: try: _ = backlink[i][0] except: break find_data = re.findall('', backlink[i][1]) for j in find_data: if backlink[i][2] != 'redirect': backlink[i][1] = backlink[i][1].replace('', end_data[j][0]) else: backlink[i][1] = backlink[i][1].replace('', '\\' + end_data[j][0]) i += 1 data = re.sub('<\/td_1>', '', data) data = re.sub('<\/ul>\n?', '', data) data = re.sub('<\/pre>\n?', '', data) data = re.sub('(?P
)(\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('<\/ul>\n
            ', '
            ', data) data = re.sub('\n<\/ul>', '
          ', data) data = re.sub('\n', '
          ', data) plus_data = '' + plus_data return [data, plus_data, backlink]