')
s = s.replace('<', '<')
s = s.replace('&', '&')
s = s.replace(' ', ' ')
return s
def text(html):
html = r_tag.sub('', html)
html = r_whitespace.sub(' ', html)
return unescape(html).strip()
def search(term):
try: import search
except ImportError, e:
print e
return term
if isinstance(term, unicode):
term = term.encode('utf-8')
else: term = term.decode('utf-8')
term = term.replace('_', ' ')
try: uri = search.result('site:en.wikipedia.org %s' % term)
except IndexError: return term
if uri:
return uri[len('http://en.wikipedia.org/wiki/'):]
else: return term
def wikipedia(term, last=False):
global wikiuri
if not '%' in term:
if isinstance(term, unicode):
t = term.encode('utf-8')
else: t = term
q = urllib.quote(t)
u = wikiuri % q
bytes = web.get(u)
else: bytes = web.get(wikiuri % term)
bytes = r_tr.sub('', bytes)
if not last:
r = r_redirect.search(bytes[:4096])
if r:
term = urllib.unquote(r.group(1))
return wikipedia(term, last=True)
paragraphs = r_paragraph.findall(bytes)
if not paragraphs:
if not last:
term = search(term)
return wikipedia(term, last=True)
return None
# Pre-process
paragraphs = [para for para in paragraphs
if (para and 'technical limitations' not in para
and 'window.showTocToggle' not in para
and 'Deletion_policy' not in para
and 'Template:AfD_footer' not in para
and not (para.startswith('') and
para.endswith('
'))
and not 'disambiguation)"' in para)
and not '(images and media)' in para
and not 'This article contains a' in para
and not 'id="coordinates"' in para
and not 'class="thumb' in para]
# and not 'style="display:none"' in para]
for i, para in enumerate(paragraphs):
para = para.replace('', '|')
para = para.replace('', '|')
paragraphs[i] = text(para).strip()
# Post-process
paragraphs = [para for para in paragraphs if
(para and not (para.endswith(':') and len(para) < 150))]
para = text(paragraphs[0])
m = r_sentence.match(para)
if not m:
if not last:
term = search(term)
return wikipedia(term, last=True)
return None
sentence = m.group(0)
maxlength = 275
if len(sentence) > maxlength:
sentence = sentence[:maxlength]
words = sentence[:-5].split(' ')
words.pop()
sentence = ' '.join(words) + ' [...]'
if ((sentence == 'Wikipedia does not have an article with this exact name.')
or (sentence == 'Wikipedia does not have a page with this exact name.')):
if not last:
term = search(term)
return wikipedia(term, last=True)
return None
sentence = '"' + sentence.replace('"', "'") + '"'
sentence = sentence.decode('utf-8').encode('utf-8')
wikiuri = wikiuri.decode('utf-8').encode('utf-8')
term = term.decode('utf-8').encode('utf-8')
return sentence + ' - ' + (wikiuri % term)
def wik(phenny, input):
origterm = input.groups()[1]
if not origterm:
return phenny.say('Perhaps you meant ".wik Zen"?')
origterm = origterm.encode('utf-8')
term = urllib.unquote(origterm)
term = term[0].upper() + term[1:]
term = term.replace(' ', '_')
try: result = wikipedia(term)
except IOError:
error = "Can't connect to en.wikipedia.org (%s)" % (wikiuri % term)
return phenny.say(error)
if result is not None:
phenny.say(result)
else: phenny.say('Can\'t find anything in Wikipedia for "%s".' % origterm)
wik.commands = ['wik']
wik.priority = 'high'
if __name__ == '__main__':
print __doc__.strip()
phenny-2~hg28/modules/wiktionary.py 0000755 0001750 0001750 00000005126 11265666065 016707 0 ustar morph morph #!/usr/bin/env python
"""
wiktionary.py - Phenny Wiktionary Module
Copyright 2009, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
"""
import re
import web
uri = 'http://en.wiktionary.org/w/index.php?title=%s&printable=yes'
r_tag = re.compile(r'<[^>]+>')
r_ul = re.compile(r'(?ims)')
def text(html):
text = r_tag.sub('', html).strip()
text = text.replace('\n', ' ')
text = text.replace('\r', '')
text = text.replace('(intransitive', '(intr.')
text = text.replace('(transitive', '(trans.')
return text
def wiktionary(word):
bytes = web.get(uri % word)
bytes = r_ul.sub('', bytes)
mode = None
etymology = None
definitions = {}
for line in bytes.splitlines():
if 'id="Etymology"' in line:
mode = 'etymology'
elif 'id="Noun"' in line:
mode = 'noun'
elif 'id="Verb"' in line:
mode = 'verb'
elif 'id="Adjective"' in line:
mode = 'adjective'
elif 'id="Adverb"' in line:
mode = 'adverb'
elif 'id="Interjection"' in line:
mode = 'interjection'
elif 'id="Particle"' in line:
mode = 'particle'
elif 'id="Preposition"' in line:
mode = 'preposition'
elif 'id="' in line:
mode = None
elif (mode == 'etmyology') and ('' in line):
etymology = text(line)
elif (mode is not None) and ('
' in line):
definitions.setdefault(mode, []).append(text(line))
if ' 300:
result = result[:295] + '[...]'
phenny.say(result)
w.commands = ['w']
w.example = '.w bailiwick'
if __name__ == '__main__':
print __doc__.strip()
phenny-2~hg28/opt/ 0000755 0001750 0001750 00000000000 11265666065 013260 5 ustar morph morph phenny-2~hg28/opt/__init__.py 0000755 0001750 0001750 00000000000 11265666065 015362 0 ustar morph morph phenny-2~hg28/opt/freenode.py 0000755 0001750 0001750 00000002740 11265666065 015427 0 ustar morph morph #!/usr/bin/env python
"""
freenode.py - Freenode Specific Stuff
Copyright 2008, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
"""
def replaced(phenny, input):
command = input.group(1)
responses = {
'cp': '.cp has been replaced by .u',
'pc': '.pc has been replaced by .u',
'unicode': '.unicode has been replaced by .u',
'compare': '.compare has been replaced by .gcs (googlecounts)',
'map': 'the .map command has been removed; ask sbp for details',
'acronym': 'the .acronym command has been removed; ask sbp for details',
# 'img': 'the .img command has been removed; ask sbp for details',
'v': '.v has been replaced by .val',
'validate': '.validate has been replaced by .validate',
'thesaurus': ".thesaurus hasn't been ported to my new codebase yet",
# 'rates': "moon wanter. moOOoon wanter!",
'web': 'the .web command has been removed; ask sbp for details',
'origin': ".origin hasn't been ported to my new codebase yet",
# 'gs': 'sorry, .gs no longer works',
'swhack': 'sorry, .swhack no longer works'
}
try: response = responses[command]
except KeyError: return
else: phenny.reply(response)
replaced.commands = [
'cp', 'pc', 'unicode', 'compare', 'map', 'acronym',
'v', 'validate', 'thesaurus', 'web', 'mangle', 'origin',
'swhack'
]
replaced.priority = 'low'
if __name__ == '__main__':
print __doc__.strip()
phenny-2~hg28/opt/swhack.py 0000755 0001750 0001750 00000001402 11265666065 015112 0 ustar morph morph #!/usr/bin/env python
"""
swhack.py - Phenny Swhack Module
Copyright 2008, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
"""
import urllib
def swhack(phenny, input):
if not input.sender in ('#swhack', '#inamidst'):
return
query = input.group(2)
pattern = urllib.quote(query, safe='./')
u = urllib.urlopen('http://swhack.com/scripts/tail/' + pattern)
i = None
for i, line in enumerate(u.readlines()):
line = line.rstrip('\r\n')
if i == 0:
phenny.reply(line)
else: phenny.say('[off] ' + line)
if i is None:
phenny.reply('Sorry, no results found.')
u.close()
# swhack.commands = ['swhack']
if __name__ == '__main__':
print __doc__.strip()
phenny-2~hg28/phenny 0000755 0001750 0001750 00000010451 11265666065 013706 0 ustar morph morph #!/usr/bin/env python
"""
phenny - An IRC Bot
Copyright 2008, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
Note: DO NOT EDIT THIS FILE.
Run ./phenny, then edit ~/.phenny/default.py
Then run ./phenny again
"""
import sys, os, imp, optparse
from textwrap import dedent as trim
dotdir = os.path.expanduser('~/.phenny')
def check_python_version():
if sys.version_info < (2, 4):
error = 'Error: Requires Python 2.4 or later, from www.python.org'
print >> sys.stderr, error
sys.exit(1)
def create_default_config(fn):
f = open(fn, 'w')
print >> f, trim("""\
nick = 'phenny'
host = 'irc.example.net'
channels = ['#example', '#test']
owner = 'yournickname'
# This isn't implemented yet:
# serverpass = 'yourserverpassword'
# These are people who will be able to use admin.py's functions...
admins = [owner, 'someoneyoutrust']
# But admin.py is disabled by default, as follows:
exclude = ['admin']
# If you want to enumerate a list of modules rather than disabling
# some, use "enable = ['example']", which takes precedent over exclude
#
# enable = []
# Modules to load from the opt directory
extra = []
# EOF
""")
f.close()
def create_dotdir(dotdir):
print 'Creating a config directory at ~/.phenny...'
try: os.mkdir(dotdir)
except Exception, e:
print >> sys.stderr, 'There was a problem creating %s:' % dotdir
print >> sys.stderr, e.__class__, str(e)
print >> sys.stderr, 'Please fix this and then run phenny again.'
sys.exit(1)
print 'Creating a default config file at ~/.phenny/default.py...'
default = os.path.join(dotdir, 'default.py')
create_default_config(default)
print 'Done; now you can edit default.py, and run phenny! Enjoy.'
sys.exit(0)
def check_dotdir():
if not os.path.isdir(dotdir):
create_dotdir(dotdir)
def config_names(config):
config = config or 'default'
def files(d):
names = os.listdir(d)
return list(os.path.join(d, fn) for fn in names if fn.endswith('.py'))
here = os.path.join('.', config)
if os.path.isfile(here):
return [here]
if os.path.isfile(here + '.py'):
return [here + '.py']
if os.path.isdir(here):
return files(here)
there = os.path.join(dotdir, config)
if os.path.isfile(there):
return [there]
if os.path.isfile(there + '.py'):
return [there + '.py']
if os.path.isdir(there):
return files(there)
print >> sys.stderr, "Error: Couldn't find a config file!"
print >> sys.stderr, 'What happened to ~/.phenny/default.py?'
sys.exit(1)
def main(argv=None):
# Step One: Check Dependencies
check_python_version() # require python2.4 or later
check_dotdir() # require ~/.phenny, or make it and exit
# Step Two: Parse The Command Line
parser = optparse.OptionParser('%prog [options]')
parser.add_option('-c', '--config', metavar='fn',
help='use this configuration file or directory')
opts, args = parser.parse_args(argv)
if args: print >> sys.stderr, 'Warning: ignoring spurious arguments'
# Step Three: Load The Configurations
config_modules = []
for config_name in config_names(opts.config):
name = os.path.basename(config_name).split('.')[0] + '_config'
module = imp.load_source(name, config_name)
module.filename = config_name
if not hasattr(module, 'prefix'):
module.prefix = r'\.'
if not hasattr(module, 'name'):
module.name = 'Phenny Palmersbot, http://inamidst.com/phenny/'
if not hasattr(module, 'port'):
module.port = 6667
if module.host == 'irc.example.net':
error = ('Error: you must edit the config file first!\n' +
"You're currently using %s" % module.filename)
print >> sys.stderr, error
sys.exit(1)
config_modules.append(module)
# Step Four: Load Phenny
try: from __init__ import run
except ImportError:
try: from phenny import run
except ImportError:
print >> sys.stderr, "Error: Couldn't find phenny to import"
sys.exit(1)
# Step Five: Initialise And Run The Phennies
# @@ ignore SIGHUP
for config_module in config_modules:
run(config_module) # @@ thread this
if __name__ == '__main__':
main()
phenny-2~hg28/tools.py 0000755 0001750 0001750 00000001144 11265666065 014173 0 ustar morph morph #!/usr/bin/env python
"""
tools.py - Phenny Tools
Copyright 2008, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
"""
def deprecated(old):
def new(phenny, input, old=old):
self = phenny
origin = type('Origin', (object,), {
'sender': input.sender,
'nick': input.nick
})()
match = input.match
args = [input.bytes, input.sender, '@@']
old(self, origin, match, args)
new.__module__ = old.__module__
new.__name__ = old.__name__
return new
if __name__ == '__main__':
print __doc__.strip()
phenny-2~hg28/web.py 0000755 0001750 0001750 00000001703 11265666065 013611 0 ustar morph morph #!/usr/bin/env python
"""
web.py - Web Facilities
Author: Sean B. Palmer, inamidst.com
About: http://inamidst.com/phenny/
"""
import urllib
class Grab(urllib.URLopener):
def __init__(self, *args):
self.version = 'Mozilla/5.0 (Phenny)'
urllib.URLopener.__init__(self, *args)
def http_error_default(self, url, fp, errcode, errmsg, headers):
return urllib.addinfourl(fp, [headers, errcode], "http:" + url)
urllib._urlopener = Grab()
def get(uri):
if not uri.startswith('http'):
return
u = urllib.urlopen(uri)
bytes = u.read()
u.close()
return bytes
def head(uri):
if not uri.startswith('http'):
return
u = urllib.urlopen(uri)
info = u.info()
u.close()
return info
def post(uri, query):
if not uri.startswith('http'):
return
data = urllib.urlencode(query)
u = urllib.urlopen(uri, data)
bytes = u.read()
u.close()
return bytes
if __name__=="__main__":
main()