ファイルのコンテンツ

from DocumentTemplate.ustr import ustr
from StructuredText.STletters import letters, dbl_quoted_punc
from cgi import escape
import re

# matches an "xxxx://yyyy" URL at the start of a line, or after a space.
# xxxx can only be alpha characters.
# yyyy is anything up to the first space, newline, comma, double quote or <
#re1 = re.compile("(^|[\n ])([\w]+?://[^ \"\n\r\t<]*)")
query = "[\w\-_\.!~*'+%#/,]*(\?[\w\-_\.!~*';\\/:@&=+$,%#]*)?"
re1 = re.compile("(^|[^\"\w])((ftp|http)s?://[\w.-]+\.[a-zA-Z]{2,3}(:[\w]*)?" + query + ")")

# matches a "www|ftp.xxxx.yyyy[/zzzz]" kinda lazy URL thing
# Must contain at least 2 dots. xxxx contains either alphanum, or "-"
# zzzz is optional.. will contain everything up to the first space, newline,
# comma, double quote or <.
#re2 = re.compile("(^|[\n ])((www|ftp)\.[^ \"\t\n\r<]*)")
re2 = re.compile("(^|[^\w/])(www\.[\w.-]+\.[a-zA-Z]{2,3}(:[\w]*)?" + query + ")")

# matches an email@domain type address at the start of a line, or after a space.
# Note: Only the followed chars are valid; alphanums, "-", "_" and or ".".
#re3 = re.compile("(^|[\n ])([A-Za-z0-9&\-_.]+?)@([\w\-]+\.([\w\-\.]+\.)*[\w]+)")
re3 = re.compile("(^|[\W])(\w[\w&\-_.+]*)@(([\w]+[-\w]*\.)+[a-zA-Z]{2,9})")

# id:XXXXXX
re_id = re.compile("id:(\w+)")

# asin:XXXXXXXXXX
re_asin = re.compile("(isbn|asin):([\w-]+)")

# structure text, image link
re_link = re.compile(r'"([ %s0-9\n\r%s]+)"' % (letters,dbl_quoted_punc) + ":"
		+ r'([%s0-9_\@\.\,\?\!\/\:\;\-\#\~\=\&\%%\+]+)' % letters)
re_image = re.compile(r'"([ %s0-9\n\r%s]+)"' % (letters,dbl_quoted_punc) 
		+ ':img:([a-zA-Z0-9%\_\-.:/\?=;,\n\~]+)')

def comment_parser(content):

    try:
        content = escape(ustr(content), 0)

        end = 0
        new_content = ''
        for m in re_image.finditer(content):
            new_content += content[end:m.start()]
            grps = m.groups()
	    new_content += '<img src="%s" alt="%s" />'%(grps[1],grps[0])
            end = m.end()

        new_content += content[end:]
        content = new_content

        end = 0
        new_content = ''
        for m in re_link.finditer(content):
            new_content += content[end:m.start()]
            grps = m.groups()
	    new_content += '<a href="%s">%s</a>'%(grps[1],grps[0])
            end = m.end()

        new_content += content[end:]
        content = new_content

        end = 0
        new_content = ''
        for m in re1.finditer(content):
            new_content += content[end:m.start()]
            grps = m.groups()
            new_content += '%s<a href="%s">%s</a>'%(grps[0],grps[1],grps[1])
            end = m.end()
    
        new_content += content[end:]
        content = new_content
    
        end = 0
        new_content = ''
        for m in re2.finditer(content):
            new_content += content[end:m.start()]
            grps = m.groups()
            new_content += '%s<a href="http://%s">%s</a>'%(grps[0],grps[1],grps[1])
            end = m.end()

        new_content += content[end:]
        content = new_content

        end = 0
        new_content = ''
        for m in re3.finditer(content):
            new_content += content[end:m.start()]
            grps = m.groups()
            new_content += '%s<a href="mailto:%s@%s">%s@%s</a>'%(grps[0],grps[1],grps[2],grps[1],grps[2])
            end = m.end()

            new_content += content[end:]
            content = new_content

        end = 0
        new_content = ''
        for m in re_id.finditer(content):
            new_content += content[end:m.start()]
            grps = m.groups()
	    new_content += '<a href="/Members/%s">id:%s</a>'%(grps[0],grps[0])
            end = m.end()

        new_content += content[end:]
        content = new_content

        end = 0
        new_content = ''
        for m in re_asin.finditer(content):
            new_content += content[end:m.start()]
            grps = m.groups()
	    new_content += '<a href="http://www.amazon.co.jp/exec/obidos/ASIN/%s">%s:%s</a>'%(grps[1].replace("-", "").upper(),grps[0],grps[1])
            end = m.end()

        new_content += content[end:]
        content = new_content
    except:
        pass

    content = content.replace('\n', '<br/>')
    return content