cpython/Demo/scripts/markov.py

118 lines
3.7 KiB
Python
Raw Normal View History

#! /usr/bin/env python
1993-12-14 18:08:02 +08:00
class Markov:
def __init__(self, histsize, choice):
self.histsize = histsize
self.choice = choice
self.trans = {}
def add(self, state, next):
if state not in self.trans:
self.trans[state] = [next]
else:
self.trans[state].append(next)
def put(self, seq):
n = self.histsize
add = self.add
add(None, seq[:0])
for i in range(len(seq)):
add(seq[max(0, i-n):i], seq[i:i+1])
add(seq[len(seq)-n:], None)
def get(self):
choice = self.choice
trans = self.trans
n = self.histsize
seq = choice(trans[None])
while 1:
subseq = seq[max(0, len(seq)-n):]
options = trans[subseq]
next = choice(options)
if not next: break
seq = seq + next
return seq
1993-12-14 18:08:02 +08:00
def test():
import sys, string, random, getopt
args = sys.argv[1:]
try:
opts, args = getopt.getopt(args, '0123456789cdw')
except getopt.error:
print('Usage: markov [-#] [-cddqw] [file] ...')
print('Options:')
print('-#: 1-digit history size (default 2)')
print('-c: characters (default)')
print('-w: words')
print('-d: more debugging output')
print('-q: no debugging output')
print('Input files (default stdin) are split in paragraphs')
print('separated blank lines and each paragraph is split')
print('in words by whitespace, then reconcatenated with')
print('exactly one space separating words.')
print('Output consists of paragraphs separated by blank')
print('lines, where lines are no longer than 72 characters.')
histsize = 2
do_words = 0
debug = 1
for o, a in opts:
if '-0' <= o <= '-9': histsize = eval(o[1:])
if o == '-c': do_words = 0
if o == '-d': debug = debug + 1
if o == '-q': debug = 0
if o == '-w': do_words = 1
if not args: args = ['-']
m = Markov(histsize, random.choice)
try:
for filename in args:
if filename == '-':
f = sys.stdin
if f.isatty():
print('Sorry, need stdin from file')
continue
else:
f = open(filename, 'r')
if debug: print('processing', filename, '...')
text = f.read()
f.close()
paralist = string.splitfields(text, '\n\n')
for para in paralist:
if debug > 1: print('feeding ...')
words = string.split(para)
if words:
if do_words: data = tuple(words)
else: data = string.joinfields(words, ' ')
m.put(data)
except KeyboardInterrupt:
print('Interrupted -- continue with data read so far')
if not m.trans:
print('No valid input files')
return
if debug: print('done.')
if debug > 1:
for key in m.trans.keys():
if key is None or len(key) < histsize:
print(repr(key), m.trans[key])
if histsize == 0: print(repr(''), m.trans[''])
print()
while 1:
data = m.get()
if do_words: words = data
else: words = string.split(data)
n = 0
limit = 72
for w in words:
if n + len(w) > limit:
print()
n = 0
print(w, end=' ')
n = n + len(w) + 1
print()
print()
1993-12-14 18:08:02 +08:00
def tuple(list):
if len(list) == 0: return ()
if len(list) == 1: return (list[0],)
Merged revisions 66394,66404,66412,66414,66424-66436 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r66394 | benjamin.peterson | 2008-09-11 17:04:02 -0500 (Thu, 11 Sep 2008) | 1 line fix typo ........ r66404 | gerhard.haering | 2008-09-12 08:54:06 -0500 (Fri, 12 Sep 2008) | 2 lines sqlite3 module: Mark iterdump() method as "Non-standard" like all the other methods not found in DB-API. ........ r66412 | gerhard.haering | 2008-09-12 13:58:57 -0500 (Fri, 12 Sep 2008) | 2 lines Fixes issue #3103. In the sqlite3 module, made one more function static. All renaming public symbos now have the pysqlite prefix to avoid name clashes. This at least once created problems where the same symbol name appeared somewhere in Apache and the sqlite3 module was used from mod_python. ........ r66414 | gerhard.haering | 2008-09-12 17:33:22 -0500 (Fri, 12 Sep 2008) | 2 lines Issue #3846: Release GIL during calls to sqlite3_prepare. This improves concurrent access to the same database file from multiple threads/processes. ........ r66424 | andrew.kuchling | 2008-09-12 20:22:08 -0500 (Fri, 12 Sep 2008) | 1 line #687648 from Robert Schuppenies: use classic division. (RM Barry gave permission to update the demos.) ........ r66425 | andrew.kuchling | 2008-09-12 20:27:33 -0500 (Fri, 12 Sep 2008) | 1 line #687648 from Robert Schuppenies: use classic division. From me: don't use string exception; flush stdout after printing ........ r66426 | andrew.kuchling | 2008-09-12 20:34:41 -0500 (Fri, 12 Sep 2008) | 1 line #687648 from Robert Schuppenies: use classic division. From me: don't use string exception; add __main__ section ........ r66427 | andrew.kuchling | 2008-09-12 20:42:55 -0500 (Fri, 12 Sep 2008) | 1 line #687648 from Robert Schuppenies: use classic division. From me: remove two stray semicolons ........ r66428 | andrew.kuchling | 2008-09-12 20:43:28 -0500 (Fri, 12 Sep 2008) | 1 line #687648 from Robert Schuppenies: use classic division. ........ r66429 | andrew.kuchling | 2008-09-12 20:47:02 -0500 (Fri, 12 Sep 2008) | 1 line Remove semicolon ........ r66430 | andrew.kuchling | 2008-09-12 20:48:36 -0500 (Fri, 12 Sep 2008) | 1 line Subclass exception ........ r66431 | andrew.kuchling | 2008-09-12 20:56:56 -0500 (Fri, 12 Sep 2008) | 1 line Fix SyntaxError ........ r66432 | andrew.kuchling | 2008-09-12 20:57:25 -0500 (Fri, 12 Sep 2008) | 1 line Update uses of string exceptions ........ r66433 | andrew.kuchling | 2008-09-12 21:08:30 -0500 (Fri, 12 Sep 2008) | 1 line Use title case ........ r66434 | andrew.kuchling | 2008-09-12 21:09:15 -0500 (Fri, 12 Sep 2008) | 1 line Remove extra 'the'; the following title includes it ........ r66435 | andrew.kuchling | 2008-09-12 21:11:51 -0500 (Fri, 12 Sep 2008) | 1 line #3288: Document as_integer_ratio ........ r66436 | andrew.kuchling | 2008-09-12 21:14:15 -0500 (Fri, 12 Sep 2008) | 1 line Use title case ........
2008-09-13 23:58:53 +08:00
i = len(list)//2
return tuple(list[:i]) + tuple(list[i:])
1993-12-14 18:08:02 +08:00
if __name__ == "__main__":
test()