pastebin - collaborative debugging

#!/usr/bin/env python2.5

import os, re, cgi, datetime, time, sys, urllib

import cgitb

from xml.etree.ElementTree import Element, SubElement, ElementTree,\
    ProcessingInstruction
import xml.etree.ElementTree as ElementTreex


NEW_GUID_DATE = datetime.datetime(2005,  7,  6)
PUBLISHED_FLAG_DATE = datetime.datetime(2007, 7, 12)


class ParsedArgs:
    def __init__(self, argStr):
        for pair in (argStr or '').split('&'):
            if '=' in pair:
                key, value = pair.split('=', 1)
                value = urllib.unquote(value)
            else:
                key = pair
                value = True

            setattr(self, urllib.unquote(key), value)


    def __getattr__(self, key):
        return False


def myfilter(filter_func, sequence):
    '''
    As with the filter() built-in, except return a list of
    (fn_result, <object>) tuples rather than simply a list of <object>s.
    '''

    output = []

    for item in sequence:
        result = filter_func(item)
        if result:
            output.append((result, item))

    return output


class Entry:
    XMLNS = 'http://www.w3.org/2005/Atom'

    def __init__(self, create_date):
        self.create_date = create_date
        self.title = None
        self.html = False
        self.tags = []

        if create_date < NEW_GUID_DATE:
            s = create_date.strftime('%Y-%m-%d-%H:%M:%S')
            self.guid = cgi.escape(s.replace(' ', '_'))
        else:
            self.guid = 'entry_' + str(int(time.mktime(create_date.timetuple())))

        if create_date < PUBLISHED_FLAG_DATE:
            self.hidden = False
        else:
            self.hidden = True

        self.filename = create_date.strftime('%Y-%m-%d-%H:%M:%S')
        pathname = os.path.join(entries_dir, self.filename)
        self.fp = fp = file(pathname)

        ts = os.fstat(fp.fileno()).st_mtime
        self.edit_date = create_date
        #self.edit_date = datetime.datetime.fromtimestamp(ts)

        fileIter = iter(file(pathname))

        for line in fileIter:
            line = line.rstrip()

            if ': ' in line:
                key, value = line.split(': ', 1)
                key = key.lower()

                if key in ('category', 'tags'):
                    self.tags = value.split(', ')
                elif key == 'title':
                    self.title = value
            elif not line:
                break
            elif not self.title:
                self.title = line.rstrip()
            else:
                if line == 'hidden':
                    self.hidden = True
                elif line == 'published':
                    self.hidden = False
                elif line == 'html':
                    self.html = True

        self.body = ''.join([ x for x in fileIter ])


    def format_body(self, bodyOnly = False):
        if bodyOnly:
            if self.html:
                return self.body
            else:
                return self.format_quicktext()

        cdate = self.create_date.strftime('%a %d %B %Y, %H:%M')
        mdate = self.edit_date.strftime('%a %d %B %Y, %H:%M')

        bits = [
            '<a name="%s"></a>' % self.guid,
            '<div class="entry">',
            '<h2>%s</h2>\n' % cgi.escape(self.title),
            '<p class="date">',
            #'<em>Modified:</em> %s<br />' % mdate,
            '<em>Created:</em> %s' % cdate,
            '</p>\n',
            '<div class="paras">'
        ]

        if self.html:
            bits.append(self.body)
        else:
            bits.append(self.format_quicktext())

        bits.append('</div>')
        bits.append('''<div id="disqus_thread"></div><script type="text/javascript" src="http://disqus.com/forums/dmw/embed.js"></script><noscript><a href="http://dmw.disqus.com/?url=ref">View the discussion thread.</a></noscript><a class="dsq-brlink"><span class="logo-disqus"></span></a>''')
        bits.append('</div>')

        return '\n'.join(bits)


    def format_quicktext(self):
        paras = map(htmlise, map(cgi.escape, self.body.split('\n\n')))

        data = []
        for para in paras:
            if para.startswith('<'):
                data.append(para)
            elif para:
                data.append("<p>\n" + para + "</p>\n")

        return '\n'.join(data)


    def get_dates(cls, substr = None):
        dateRe = re.compile(
            r'^(\d\d\d\d)-(\d\d)-(\d\d)-(\d\d):(\d\d):(\d\d)'
            '(?:.html)?$')
        entries = []

        for match, item in myfilter(dateRe.match, os.listdir(entries_dir)):
            if substr is not None and substr not in item:
                continue
            entries.append(datetime.datetime(*map(int, match.groups())))

        entries.sort()
        return entries

    get_dates = classmethod(get_dates)


def format_entry_rss(entry, chan, idx):
    cdate = entry.create_date.strftime('%a %d %B %Y, %H:%M')
    link = 'http://dmw.me.uk/weblog#' + entry.guid

    item = SubElement(chan, 'item')
    SubElement(item, 'title').text = entry.title
    SubElement(item, 'description').text = entry.format_body(bodyOnly = True)
    SubElement(item, 'link').text = link
    SubElement(item, 'guid').text = link

    SubElement(item, 'pubDate').text =\
        entry.create_date.strftime('%a, %d %b %Y %H:%M:%S GMT')


def format_blog(id = None, hidden = False):
    entries = Entry.get_dates(substr = id)
    entries.reverse() # newest first.
    entries = entries[:10]

    output = ''

    for date in entries:
        entry = Entry(date)
        if (not entry.hidden) or hidden or 1:
            output += entry.format_body()

    return output


def format_index():
    title_links = []

    for dt in Entry.get_dates():
        entry = Entry(dt)
        title_links.append(
                            '%s: '
                            '<code>%s%s</code> '
                            '<a href="%s">%s</a><br />' %
            (entry.create_date,
             ['.', 'P'][int('private' in entry.tags)],
             ['.', 'H'][int(entry.hidden)],
             "/weblog/%s" % entry.filename,
             cgi.escape(str(entry.title))))

    return '\n'.join(title_links)


def format_rss(hidden):
    entries = Entry.get_dates()
    entries.reverse() # newest first.
    entries = entries[:1]

    strip = str.strip

    # RSS header.
    doc = Element('rss', version = '2.0')
    chan = SubElement(doc, 'channel')

    SubElement(chan, 'title').text = 'David Wilson\'s Weblog'

    SubElement(chan, 'link').text = 'http://dmw.me.uk/weblog/rss'

    SubElement(chan, 'description').text = strip('''
        Random musings and thoughts from David Wilson, a programmer/geek of
        sorts from Belfast, Northern Ireland.
    ''')

    SubElement(chan, 'copyright').text = strip('''
        Copyright 2004-2007, David Wilson.
    ''')

    SubElement(chan, 'lastBuildDate').text =\
        time.strftime('%a, %d %b %Y %H:%M:%S GMT')

    SubElement(chan, 'generator').text =\
        'Python%s; ElementTree %s; blog.py 0.3' %\
        (str(sys.version_info), ElementTreex.VERSION)

    SubElement(chan, 'docs').text =\
        'http://blogs.law.harvard.edu/tech/rss'


    for idx, date in enumerate(entries):
        entry = Entry(date)
        if (not entry.hidden) or hidden:
            format_entry_rss(entry, chan, idx)

    return ElementTreex.tostring(doc)


def htmlise(text):
    if text == '--':
        return '<div class="divider">&nbsp;</div>'

    lines = text.split("\n")
    list_re = re.compile(r'^    - (.+)')
    bleh = myfilter(list_re.match, lines)

    if len(bleh) == len(lines):
        out = [ '<ul>\n' ]
        out += [ '<li>' + htmlise(match.groups()[0]) + '</li>' for match,line in bleh ]
        out.append('</ul>\n\n')

        return '\n'.join(out)


    R0 = re.compile(r'^&gt;&gt;(.+)&lt;&lt;$')
    bleh = R0.match(text)

    if bleh:
        return '<h3>' + bleh.groups()[0] + '</h3>\n'

    Rimg = re.compile(r'&lt;img (http[^&]+)&gt;')
    text = Rimg.sub(r'<img src="\1" alt="" />', text)

    Rimg = re.compile(r'&lt;img ([^&]+)&gt;')
    text = Rimg.sub(r'<img src="\1" alt="" />', text)

    R1 = re.compile(r'&lt;(http://[^&]+)&gt;([^\n]+?)&lt;/a&gt;', re.M)
    text = R1.sub(r'<a href="\1">\2</a>', text)

    R2 = re.compile(r'&lt;(http://[^&]+)&gt;', re.M)
    return R2.sub(r'<a href="\1">\1</a>', text)


def get_header():
    return file(os.path.join(blog_dir, 'header.html')).read()


def get_footer():
    return file(os.path.join(blog_dir, 'footer.html')).read()


def RunCGI():
    global blog_dir, entries_dir

    cgitb.enable(display=1, logdir="/tmp")

    # Directory where blog.py is stored.
    blog_dir = os.path.dirname(os.environ['SCRIPT_FILENAME'])
    entries_dir = os.path.join(blog_dir, 'entries')
    args = ParsedArgs(os.environ['QUERY_STRING'])

    print 'Content-type: text/html'
    print

    if args.id:
        sys.stdout.write(format_blog(id = args.id))
    elif args.index:
        sys.stdout.write(format_index())
    elif args.body_only:
        sys.stdout.write(format_blog(hidden = args.hidden != False))
    elif args.rss:
        sys.stdout.write(format_rss(hidden = args.hidden != False))
    else:
        sys.stdout.write(get_header())
        sys.stdout.write(format_blog())
        sys.stdout.write(get_footer())


if __name__ == '__main__':
    RunCGI()