1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55

# Natural Language Toolkit (NLTK) Help
#
# Copyright (C) 2001-2011 NLTK Project
# Authors: Steven Bird <sb@csse.unimelb.edu.au>
# URL: <http://www.nltk.org/>
# For license information, see LICENSE.TXT

"""
Provide structured access to documentation.
"""

import re
from textwrap import wrap

from nltk.data import load

def brown_tagset(tagpattern=None):
    _format_tagset("brown_tagset", tagpattern)

def claws5_tagset(tagpattern=None):
    _format_tagset("claws5_tagset", tagpattern)

def upenn_tagset(tagpattern=None):
    _format_tagset("upenn_tagset", tagpattern)

#####################################################################
# UTILITIES
#####################################################################

def _print_entries(tags, tagdict):
    for tag in tags:
        entry = tagdict[tag]
        defn = [tag + ": " + entry[0]]
        examples = wrap(entry[1], width=75, initial_indent='    ', subsequent_indent='    ')
        print "\n".join(defn + examples) 

def _format_tagset(tagset, tagpattern=None):
    tagdict = load("help/tagsets/" + tagset + ".pickle")
    if not tagpattern:
        _print_entries(sorted(tagdict), tagdict)
    elif tagpattern in tagdict:
        _print_entries([tagpattern], tagdict)
    else:
        tagpattern = re.compile(tagpattern)
        tags = [tag for tag in sorted(tagdict) if tagpattern.match(tag)]
        if tags:
            _print_entries(tags, tagdict)
        else:
            print "No matching tags found."

if __name__ == '__main__':
    brown_tagset(r'NN.*')
    upenn_tagset(r'.*\$')
    claws5_tagset('UNDEFINED')
    brown_tagset(r'NN')