3
d%                 @   s&   d dl mZmZ G dd dedZdS )    )ABCMetaabstractmethodc               @   s   e Zd ZdZdZdZd!ddZdd Zedd	 Z	d
d Z
ed"ddZdd Zdd Zdd Zdd Zdd Zdd Zdd Zdd Zeedd  ZdS )#Featurea  
    An abstract base class for Features. A Feature is a combination of
    a specific property-computing method and a list of relative positions
    to apply that method to.

    The property-computing method, M{extract_property(tokens, index)},
    must be implemented by every subclass. It extracts or computes a specific
    property for the token at the current index. Typical extract_property()
    methods return features such as the token text or tag; but more involved
    methods may consider the entire sequence M{tokens} and
    for instance compute the length of the sentence the token belongs to.

    In addition, the subclass may have a PROPERTY_NAME, which is how
    it will be printed (in Rules and Templates, etc). If not given, defaults
    to the classname.

    znltk.tbl.FeatureNc             C   s   d| _ |dkr(ttdd |D | _ nZy$||kr6ttt||d | _ W n4 tk
r } ztdj|||W Y dd}~X nX | jjp| jj	| _dS )al  
        Construct a Feature which may apply at C{positions}.

        >>> # For instance, importing some concrete subclasses (Feature is abstract)
        >>> from nltk.tag.brill import Word, Pos

        >>> # Feature Word, applying at one of [-2, -1]
        >>> Word([-2,-1])
        Word([-2, -1])

        >>> # Positions need not be contiguous
        >>> Word([-2,-1, 1])
        Word([-2, -1, 1])

        >>> # Contiguous ranges can alternatively be specified giving the
        >>> # two endpoints (inclusive)
        >>> Pos(-3, -1)
        Pos([-3, -2, -1])

        >>> # In two-arg form, start <= end is enforced
        >>> Pos(2, 1)
        Traceback (most recent call last):
          File "<stdin>", line 1, in <module>
          File "nltk/tbl/template.py", line 306, in __init__
            raise TypeError
        ValueError: illegal interval specification: (start=2, end=1)

        :type positions: list of int
        :param positions: the positions at which this features should apply
        :raises ValueError: illegal position specifications

        An alternative calling convention, for contiguous positions only,
        is Feature(start, end):

        :type start: int
        :param start: start of range where this feature should apply
        :type end: int
        :param end: end of range (NOTE: inclusive!) where this feature should apply
        Nc             S   s   h | ]}t |qS  )int).0ir   r   0/tmp/pip-build-v9q4h5k9/nltk/nltk/tbl/feature.py	<setcomp>M   s    z#Feature.__init__.<locals>.<setcomp>   z2illegal interval specification: (start={}, end={}))
	positionstuplesorted	TypeErrorrange
ValueErrorformat	__class__PROPERTY_NAME__name__)selfr   ender   r   r	   __init__#   s    (zFeature.__init__c             C   s   | j S )N)r   )r   r   r   r	   encode_json_obj^   s    zFeature.encode_json_objc             C   s   |}| |S )Nr   )clsobjr   r   r   r	   decode_json_obja   s    zFeature.decode_json_objc             C   s   | j j dt| jdS )N())r   r   listr   )r   r   r   r	   __repr__f   s    zFeature.__repr__Fc                sF   t dd |D s td| fdd|D } fdd|D S )a  
        Return a list of features, one for each start point in starts
        and for each window length in winlen. If excludezero is True,
        no Features containing 0 in its positions will be generated
        (many tbl trainers have a special representation for the
        target feature at [0])

        For instance, importing a concrete subclass (Feature is abstract)

        >>> from nltk.tag.brill import Word

        First argument gives the possible start positions, second the
        possible window lengths

        >>> Word.expand([-3,-2,-1], [1])
        [Word([-3]), Word([-2]), Word([-1])]

        >>> Word.expand([-2,-1], [1])
        [Word([-2]), Word([-1])]

        >>> Word.expand([-3,-2,-1], [1,2])
        [Word([-3]), Word([-2]), Word([-1]), Word([-3, -2]), Word([-2, -1])]

        >>> Word.expand([-2,-1], [1])
        [Word([-2]), Word([-1])]

        A third optional argument excludes all Features whose positions contain zero

        >>> Word.expand([-2,-1,0], [1,2], excludezero=False)
        [Word([-2]), Word([-1]), Word([0]), Word([-2, -1]), Word([-1, 0])]

        >>> Word.expand([-2,-1,0], [1,2], excludezero=True)
        [Word([-2]), Word([-1]), Word([-2, -1])]

        All window lengths must be positive

        >>> Word.expand([-2,-1], [0])
        Traceback (most recent call last):
          File "<stdin>", line 1, in <module>
          File "nltk/tag/tbl/template.py", line 371, in expand
            :param starts: where to start looking for Feature
        ValueError: non-positive window length in [0]

        :param starts: where to start looking for Feature
        :type starts: list of ints
        :param winlens: window lengths where to look for Feature
        :type starts: list of ints
        :param excludezero: do not output any Feature with 0 in any of its positions.
        :type excludezero: bool
        :returns: list of Features
        :raises ValueError: for non-positive window lengths
        c             s   s   | ]}|d kV  qdS )r   Nr   )r   xr   r   r	   	<genexpr>   s    z!Feature.expand.<locals>.<genexpr>znon-positive window length in c             3   s8   | ]0}t t | d  D ]} |||  V  qqdS )r   N)r   len)r   wr   )startsr   r	   r#      s    c                s    g | ]}od |ks |qS )r   r   )r   r"   )r   excludezeror   r	   
<listcomp>   s    z"Feature.expand.<locals>.<listcomp>)allr   )r   r&   Zwinlensr'   xsr   )r   r'   r&   r	   expandi   s    6zFeature.expandc             C   s    | j |j kot| jt|jkS )aQ  
        Return True if this Feature always returns True when other does

        More precisely, return True if this feature refers to the same property as other;
        and this Feature looks at all positions that other does (and possibly
        other positions in addition).

        #For instance, importing a concrete subclass (Feature is abstract)
        >>> from nltk.tag.brill import Word, Pos

        >>> Word([-3,-2,-1]).issuperset(Word([-3,-2]))
        True

        >>> Word([-3,-2,-1]).issuperset(Word([-3,-2, 0]))
        False

        #Feature subclasses must agree
        >>> Word([-3,-2,-1]).issuperset(Pos([-3,-2]))
        False

        :param other: feature with which to compare
        :type other: (subclass of) Feature
        :return: True if this feature is superset, otherwise False
        :rtype: bool


        )r   setr   )r   otherr   r   r	   
issuperset   s    zFeature.issupersetc             C   s$   t | j|jko t| jt|j@ S )a  
        Return True if the positions of this Feature intersects with those of other

        More precisely, return True if this feature refers to the same property as other;
        and there is some overlap in the positions they look at.

        #For instance, importing a concrete subclass (Feature is abstract)
        >>> from nltk.tag.brill import Word, Pos

        >>> Word([-3,-2,-1]).intersects(Word([-3,-2]))
        True

        >>> Word([-3,-2,-1]).intersects(Word([-3,-2, 0]))
        True

        >>> Word([-3,-2,-1]).intersects(Word([0]))
        False

        #Feature subclasses must agree
        >>> Word([-3,-2,-1]).intersects(Pos([-3,-2]))
        False

        :param other: feature with which to compare
        :type other: (subclass of) Feature
        :return: True if feature classes agree and there is some overlap in the positions they look at
        :rtype: bool
        )boolr   r,   r   )r   r-   r   r   r	   
intersects   s    zFeature.intersectsc             C   s   | j |j ko| j|jkS )N)r   r   )r   r-   r   r   r	   __eq__   s    zFeature.__eq__c             C   s   | j j|j jk p| j|jk S )N)r   r   r   )r   r-   r   r   r	   __lt__   s    zFeature.__lt__c             C   s
   | |k S )Nr   )r   r-   r   r   r	   __ne__   s    zFeature.__ne__c             C   s   || k S )Nr   )r   r-   r   r   r	   __gt__   s    zFeature.__gt__c             C   s
   | |k  S )Nr   )r   r-   r   r   r	   __ge__   s    zFeature.__ge__c             C   s   | |k p| |kS )Nr   )r   r-   r   r   r	   __le__   s    zFeature.__le__c             C   s   dS )a@  
        Any subclass of Feature must define static method extract_property(tokens, index)

        :param tokens: the sequence of tokens
        :type tokens: list of tokens
        :param index: the current index
        :type index: int
        :return: feature value
        :rtype: any (but usually scalar)
        Nr   )tokensindexr   r   r	   extract_property   s    zFeature.extract_property)N)F)r   
__module____qualname____doc__Zjson_tagr   r   r   classmethodr   r!   r+   r.   r0   r1   r2   r3   r4   r5   r6   staticmethodr   r9   r   r   r   r	   r      s&   
;: $r   )	metaclassN)abcr   r   r   r   r   r   r	   <module>
   s   