Mercurial > cpython-lru_cache-weakref

annotate Demo/scripts/markov.py @ 58925:eecf1bef052d 2.6

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Merged revisions 78207 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r78207 | ezio.melotti | 2010-02-17 01:26:09 +0200 (Wed, 17 Feb 2010) | 1 line #7930: fix stripid ........
author Ezio Melotti <ezio.melotti@gmail.com>
date Tue, 16 Feb 2010 23:29:44 +0000
parents 41524f9e2a2f
children 3130b7e812b0
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
4573
73758db2f464 /usr/local/bin/python -> /usr/bin/env python
Guido van Rossum <guido@python.org>
parents: 1421
diff changeset
1 #! /usr/bin/env python
1421
fe7298813f17 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
2
fe7298813f17 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
3 class Markov:
32735
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
4 def __init__(self, histsize, choice):
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
5 self.histsize = histsize
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
6 self.choice = choice
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
7 self.trans = {}
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
8 def add(self, state, next):
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
9 if not self.trans.has_key(state):
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
10 self.trans[state] = [next]
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
11 else:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
12 self.trans[state].append(next)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
13 def put(self, seq):
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
14 n = self.histsize
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
15 add = self.add
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
16 add(None, seq[:0])
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
17 for i in range(len(seq)):
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
18 add(seq[max(0, i-n):i], seq[i:i+1])
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
19 add(seq[len(seq)-n:], None)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
20 def get(self):
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
21 choice = self.choice
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
22 trans = self.trans
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
23 n = self.histsize
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
24 seq = choice(trans[None])
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
25 while 1:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
26 subseq = seq[max(0, len(seq)-n):]
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
27 options = trans[subseq]
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
28 next = choice(options)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
29 if not next: break
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
30 seq = seq + next
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
31 return seq
1421
fe7298813f17 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
32
fe7298813f17 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
33 def test():
32735
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
34 import sys, string, random, getopt
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
35 args = sys.argv[1:]
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
36 try:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
37 opts, args = getopt.getopt(args, '0123456789cdw')
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
38 except getopt.error:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
39 print 'Usage: markov [-#] [-cddqw] [file] ...'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
40 print 'Options:'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
41 print '-#: 1-digit history size (default 2)'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
42 print '-c: characters (default)'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
43 print '-w: words'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
44 print '-d: more debugging output'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
45 print '-q: no debugging output'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
46 print 'Input files (default stdin) are split in paragraphs'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
47 print 'separated blank lines and each paragraph is split'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
48 print 'in words by whitespace, then reconcatenated with'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
49 print 'exactly one space separating words.'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
50 print 'Output consists of paragraphs separated by blank'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
51 print 'lines, where lines are no longer than 72 characters.'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
52 histsize = 2
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
53 do_words = 0
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
54 debug = 1
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
55 for o, a in opts:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
56 if '-0' <= o <= '-9': histsize = eval(o[1:])
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
57 if o == '-c': do_words = 0
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
58 if o == '-d': debug = debug + 1
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
59 if o == '-q': debug = 0
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
60 if o == '-w': do_words = 1
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
61 if not args: args = ['-']
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
62 m = Markov(histsize, random.choice)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
63 try:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
64 for filename in args:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
65 if filename == '-':
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
66 f = sys.stdin
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
67 if f.isatty():
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
68 print 'Sorry, need stdin from file'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
69 continue
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
70 else:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
71 f = open(filename, 'r')
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
72 if debug: print 'processing', filename, '...'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
73 text = f.read()
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
74 f.close()
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
75 paralist = string.splitfields(text, '\n\n')
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
76 for para in paralist:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
77 if debug > 1: print 'feeding ...'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
78 words = string.split(para)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
79 if words:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
80 if do_words: data = tuple(words)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
81 else: data = string.joinfields(words, ' ')
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
82 m.put(data)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
83 except KeyboardInterrupt:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
84 print 'Interrupted -- continue with data read so far'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
85 if not m.trans:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
86 print 'No valid input files'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
87 return
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
88 if debug: print 'done.'
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
89 if debug > 1:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
90 for key in m.trans.keys():
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
91 if key is None or len(key) < histsize:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
92 print repr(key), m.trans[key]
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
93 if histsize == 0: print repr(''), m.trans['']
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
94 print
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
95 while 1:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
96 data = m.get()
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
97 if do_words: words = data
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
98 else: words = string.split(data)
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
99 n = 0
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
100 limit = 72
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
101 for w in words:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
102 if n + len(w) > limit:
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
103 print
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
104 n = 0
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
105 print w,
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
106 n = n + len(w) + 1
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
107 print
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
108 print
1421
fe7298813f17 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
109
fe7298813f17 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
110 def tuple(list):
32735
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
111 if len(list) == 0: return ()
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
112 if len(list) == 1: return (list[0],)
49164
41524f9e2a2f #687648 from Robert Schuppenies: use classic division.
Andrew M. Kuchling <amk@amk.ca>
parents: 33456
diff changeset
113 i = len(list)//2
32735
2bc66f1df7cc Whitespace normalization. Ran reindent.py over the entire source tree.
Tim Peters <tim.peters@gmail.com>
parents: 31515
diff changeset
114 return tuple(list[:i]) + tuple(list[i:])
1421
fe7298813f17 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
115
33456
487280cf71b9 Add 'if __name__ == "__main__":' to files already as a usable as a module.
Johannes Gijsbers <jlg@dds.nl>
parents: 32735
diff changeset
116 if __name__ == "__main__":
487280cf71b9 Add 'if __name__ == "__main__":' to files already as a usable as a module.
Johannes Gijsbers <jlg@dds.nl>
parents: 32735
diff changeset
117 test()