.. Copyright (C) 2001-2012 NLTK Project
.. For license information, see LICENSE.TXT

    >>> from nltk.tokenize import *

Regression Tests: Treebank Tokenizer
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Some test strings.

    >>> s1 = "On a $50,000 mortgage of 30 years at 8 percent, the monthly payment would be $366.88."
    >>> print word_tokenize(s1)
    ['On', 'a', '$', '50,000', 'mortgage', 'of', '30', 'years', 'at', '8', 'percent', ',', 'the', 'monthly', 'payment', 'would', 'be', '$', '366.88', '.']
    >>> s2 = "\"We beat some pretty good teams to get here,\" Slocum said."
    >>> print word_tokenize(s2)
    ['``', 'We', 'beat', 'some', 'pretty', 'good', 'teams', 'to', 'get', 'here', ',', "''", 'Slocum', 'said', '.']
    >>> s3 = "Well, we couldn't have this predictable, cliche-ridden, \"Touched by an Angel\" (a show creator John Masius worked on) wanna-be if she didn't."
    >>> print word_tokenize(s3)
    ['Well', ',', 'we', 'could', "n't", 'have', 'this', 'predictable', ',', 'cliche-ridden', ',', '``', 'Touched', 'by', 'an', 'Angel', "''", '(', 'a', 'show', 'creator', 'John', 'Masius', 'worked', 'on', ')', 'wanna-be', 'if', 'she', 'did', "n't", '.']
    >>> s4 = "I cannot cannot work under these conditions!"
    >>> print word_tokenize(s4)
    ['I', 'can', 'not', 'can', 'not', 'work', 'under', 'these', 'conditions', '!']
    >>> s5 = "The company spent $30,000,000 last year."
    >>> print word_tokenize(s5)
    ['The', 'company', 'spent', '$', '30,000,000', 'last', 'year', '.']
    >>> s6 = "The company spent 40.75% of its income last year."
    >>> print word_tokenize(s6)
    ['The', 'company', 'spent', '40.75', '%', 'of', 'its', 'income', 'last', 'year', '.']
    >>> s7 = "He arrived at 3:00 pm."
    >>> print word_tokenize(s7)
    ['He', 'arrived', 'at', '3:00', 'pm', '.']
    >>> s8 = "I bought these items: books, pencils, and pens."
    >>> print word_tokenize(s8)
    ['I', 'bought', 'these', 'items', ':', 'books', ',', 'pencils', ',', 'and', 'pens', '.']
    >>> s9 = "Though there were 150, 100 of them were old."
    >>> print word_tokenize(s9)
    ['Though', 'there', 'were', '150', ',', '100', 'of', 'them', 'were', 'old', '.']
    >>> s10 = "There were 300,000, but that wasn't enough."
    >>> print word_tokenize(s10)
    ['There', 'were', '300,000', ',', 'but', 'that', 'was', "n't", 'enough', '.']
    
Regression Tests: Regexp Tokenizer
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Some additional test strings.

    >>> s = ("Good muffins cost $3.88\nin New York.  Please buy me\n"
    ...      "two of them.\n\nThanks.")
    >>> s2 = ("Alas, it has not rained today. When, do you think, "
    ...       "will it rain again?")
    >>> s3 = ("<p>Although this is <b>not</b> the case here, we must "
    ...       "not relax our vigilance!</p>")

    >>> print regexp_tokenize(s2, r'[,\.\?!"]\s*', gaps=False)
    [', ', '. ', ', ', ', ', '?']
    >>> print regexp_tokenize(s2, r'[,\.\?!"]\s*', gaps=True)
    ['Alas', 'it has not rained today', 'When', 'do you think',
     'will it rain again']

Make sure that grouping parentheses don't confuse the tokenizer:

    >>> print regexp_tokenize(s3, r'</?(b|p)>', gaps=False)
    ['<p>', '<b>', '</b>', '</p>']
    >>> print regexp_tokenize(s3, r'</?(b|p)>', gaps=True)
    ['Although this is ', 'not',
     ' the case here, we must not relax our vigilance!']

Make sure that named groups don't confuse the tokenizer:

    >>> print regexp_tokenize(s3, r'</?(?P<named>b|p)>', gaps=False)
    ['<p>', '<b>', '</b>', '</p>']
    >>> print regexp_tokenize(s3, r'</?(?P<named>b|p)>', gaps=True)
    ['Although this is ', 'not',
     ' the case here, we must not relax our vigilance!']

Make sure that nested groups don't confuse the tokenizer:

    >>> print regexp_tokenize(s2, r'(h|r|l)a(s|(i|n0))', gaps=False)
    ['las', 'has', 'rai', 'rai']
    >>> print regexp_tokenize(s2, r'(h|r|l)a(s|(i|n0))', gaps=True)
    ['A', ', it ', ' not ', 'ned today. When, do you think, will it ',
     'n again?']

The tokenizer should reject any patterns with backreferences:

    >>> print regexp_tokenize(s2, r'(.)\1')
    Traceback (most recent call last):
       ...
    ValueError: Regular expressions with back-references are
    not supported: '(.)\\1'
    >>> print regexp_tokenize(s2, r'(?P<foo>)(?P=foo)')
    Traceback (most recent call last):
       ...
    ValueError: Regular expressions with back-references are
    not supported: '(?P<foo>)(?P=foo)'

A simple sentence tokenizer '\.(\s+|$)'

    >>> print regexp_tokenize(s, pattern=r'\.(\s+|$)', gaps=True)
    ['Good muffins cost $3.88\nin New York',
     'Please buy me\ntwo of them', 'Thanks']