3
���h�x � @ s� d Z dZddlZddljjZddlm Z m
Z
m Z d!dd�Z dd� Z
d d
� Zd d � Zd"dd�ZG dd� d�ZG dd� d�Zdd� ZG dd� de�ZG dd� de�ZG dd� de�ZG d d � d �Zd#d d �ZdS )$zBA collection of functions designed to help I/O with ascii files.
zrestructuredtext en� N)�asbytes� asunicode�bytesc C s. t | �tkr*|dkr | jd�} n
| j|�} | S )an Decode bytes from binary input streams.
Defaults to decoding from 'latin1'. That differs from the behavior of
np.compat.asunicode that decodes from 'ascii'.
Parameters
----------
line : str or bytes
Line to be decoded.
Returns
-------
decoded_line : unicode
Unicode in Python 2, a str (unicode) in Python 3.
N�latin1)�typer �decode)�line�encoding� r
�3/tmp/pip-build-5_djhm0z/numpy/numpy/lib/_iotools.py� _decode_line s
r c C s* y | d W n t tfk
r$ dS X dS )z2
Check whether obj behaves like a string.
� FT)� TypeError�
ValueError)�objr
r
r �_is_string_like% s
r c C s* y | d W n t tfk
r$ dS X dS )z8
Check whether obj behaves like a bytes object.
� FT)r r )r r
r
r �_is_bytes_like0 s
r c C s* x$| j p
f D ]}| | j dk r dS q W dS )a�
Returns whether one or several fields of a dtype are nested.
Parameters
----------
ndtype : dtype
Data-type of a structured array.
Raises
------
AttributeError
If `ndtype` does not have a `names` attribute.
Examples
--------
>>> dt = np.dtype([('name', 'S4'), ('x', float), ('y', float)])
>>> np.lib._iotools.has_nested_fields(dt)
False
NTF)�names)�ndtype�namer
r
r �has_nested_fields; s r Fc C sn | j }|dkr2|r*| jgttj| j�� S | jgS g }x.|D ]&}| j| }t|d |�}|j|� q<W |S dS )aX
Unpack a structured data-type by collapsing nested fields and/or fields
with a shape.
Note that the field names are lost.
Parameters
----------
ndtype : dtype
The datatype to collapse
flatten_base : bool, optional
If True, transform a field with a shape into several fields. Default is
False.
Examples
--------
>>> dt = np.dtype([('name', 'S4'), ('x', float), ('y', float),
... ('block', int, (2, 3))])
>>> np.lib._iotools.flatten_dtype(dt)
[dtype('S4'), dtype('float64'), dtype('float64'), dtype('int64')]
>>> np.lib._iotools.flatten_dtype(dt, flatten_base=True)
[dtype('S4'),
dtype('float64'),
dtype('float64'),
dtype('int64'),
dtype('int64'),
dtype('int64'),
dtype('int64'),
dtype('int64'),
dtype('int64')]
Nr ) r �base�int�np�prod�shape�fields�
flatten_dtype�extend)r Z flatten_baser �types�field�infoZflat_dtr
r
r r V s !
r c @ sB e Zd ZdZdd� Zddd�Zd d
� Zd d � Zd
d� Zdd� Z dS )� LineSplittera�
Object to split a string at a given delimiter or at given places.
Parameters
----------
delimiter : str, int, or sequence of ints, optional
If a string, character used to delimit consecutive fields.
If an integer or a sequence of integers, width(s) of each field.
comments : str, optional
Character used to mark the beginning of a comment. Default is '#'.
autostrip : bool, optional
Whether to strip each individual field. Default is True.
c s � fdd�S )a�
Wrapper to strip each member of the output of `method`.
Parameters
----------
method : function
Function that takes a single argument and returns a sequence of
strings.
Returns
-------
wrapped : function
The result of wrapping `method`. `wrapped` takes a single input
argument and returns a list of strings that are stripped of
white-space.
c s dd� � | �D �S )Nc S s g | ] }|j � �qS r
)�strip)�.0�_r
r
r �
<listcomp>� s z<LineSplitter.autostrip.<locals>.<lambda>.<locals>.<listcomp>r
)�input)�methodr
r �<lambda>� s z(LineSplitter.autostrip.<locals>.<lambda>r
)�selfr) r
)r) r � autostrip� s zLineSplitter.autostripN�#Tc C s� t |�}t |�}|| _|d ks(t|t�r8|p.d }| j}npt|d�r�| j}tjdgt |� �}dd� t
|d d� |dd � �D �}n&t |�r�| j t |� }}n | jd }}|| _
|r�| j|�| _n|| _|| _d S )N�__iter__r c S s g | ]\}}t ||��qS r
)�slice)r% �i�jr
r
r r' � s z)LineSplitter.__init__.<locals>.<listcomp>� ���)r �comments�
isinstance�str�_delimited_splitter�hasattr�_variablewidth_splitterr Zcumsum�list�zipr �_fixedwidth_splitter� delimiterr, � _handymanr )r+ r= r4 r, r r> �idxr
r
r �__init__� s$
& zLineSplitter.__init__c C s8 | j dk r|j| j �d }|jd�}|s,g S |j| j�S )z2Chop off comments, strip, and split at delimiter. Nr z
)r4 �splitr$ r= )r+ r r
r
r r7 � s
z LineSplitter._delimited_splitterc sb | j d k r�j| j �d ��jd���s,g S | j� � fdd�tdt��� �D �}�fdd�|D �S )Nr z
c s g | ]}t ||� ��qS r
)r/ )r% r0 )�fixedr
r r' � s z5LineSplitter._fixedwidth_splitter.<locals>.<listcomp>c s g | ] }� | �qS r
r
)r% �s)r r
r r' � s )r4 rA r$ r= �range�len)r+ r �slicesr
)rB r r r< � s
z!LineSplitter._fixedwidth_splitterc s: | j d k r� j| j �d � � s"g S | j}� fdd�|D �S )Nr c s g | ] }� | �qS r
r
)r% rC )r r
r r' � s z8LineSplitter._variablewidth_splitter.<locals>.<listcomp>)r4 rA r= )r+ r rF r
)r r r9 � s
z$LineSplitter._variablewidth_splitterc C s | j t|| j��S )N)r> r r )r+ r r
r
r �__call__� s zLineSplitter.__call__)Nr- TN)
�__name__�
__module__� __qualname__�__doc__r, r@ r7 r< r9 rG r
r
r
r r# � s
r# c @ s@ e Zd ZdZdddgZed�Zddd �Zdd d �Zdd
d�Z dS )�
NameValidatora"
Object to validate a list of strings to use as field names.
The strings are stripped of any non alphanumeric character, and spaces
are replaced by '_'. During instantiation, the user can define a list
of names to exclude, as well as a list of invalid characters. Names in
the exclusion list are appended a '_' character.
Once an instance has been created, it can be called with a list of
names, and a list of valid names will be created. The `__call__`
method accepts an optional keyword "default" that sets the default name
in case of ambiguity. By default this is 'f', so that names will
default to `f0`, `f1`, etc.
Parameters
----------
excludelist : sequence, optional
A list of names to exclude. This list is appended to the default
list ['return', 'file', 'print']. Excluded names are appended an
underscore: for example, `file` becomes `file_` if supplied.
deletechars : str, optional
A string combining invalid characters that must be deleted from the
names.
case_sensitive : {True, False, 'upper', 'lower'}, optional
* If True, field names are case-sensitive.
* If False or 'upper', field names are converted to upper case.
* If 'lower', field names are converted to lower case.
The default value is True.
replace_space : '_', optional
Character(s) used in replacement of white spaces.
Notes
-----
Calling an instance of `NameValidator` is the same as calling its
method `validate`.
Examples
--------
>>> validator = np.lib._iotools.NameValidator()
>>> validator(['file', 'field2', 'with space', 'CaSe'])
('file_', 'field2', 'with_space', 'CaSe')
>>> validator = np.lib._iotools.NameValidator(excludelist=['excl'],
... deletechars='q',
... case_sensitive=False)
>>> validator(['excl', 'field2', 'no_q', 'with space', 'CaSe'])
('EXCL', 'FIELD2', 'NO_Q', 'WITH_SPACE', 'CASE')
�return�file�printz ~!@#$%^&*()-=+~\|]}[{';: /?.>,<Nr& c C s� |d kr g }|j | j� || _|d kr.| j}nt|�}|jd� || _|d ksV|dkrbdd� | _nD|dkst|jd�r�dd� | _n&|jd�r�d d� | _nd
| }t |��|| _
d S ) N�"Tc S s | S )Nr
)�xr
r
r r* , s z(NameValidator.__init__.<locals>.<lambda>F�uc S s | j � S )N)�upper)rQ r
r
r r* . s �lc S s | j � S )N)�lower)rQ r
r
r r* 0 s z%unrecognized case_sensitive value %s.) r �defaultexcludelist� excludelist�defaultdeletechars�set�add� deletechars�case_converter�
startswithr �
replace_space)r+ rW r[ Zcase_sensitiver^ �delete�msgr
r
r r@ s$
zNameValidator.__init__�f%ic
sh |dkr|dkrdS g }t |t�r(|g}|dk rlt|�}||k rXt|�dg|| }n||krl|d|� }| j� | j}| j}| j}g }t� } d}
x�|D ]�} || �j � } |r�| j
d|�} dj � fdd�| D ��} | dk�r
||
} x | |kr�|
d7 }
||
} q�W |
d7 }
n| |k�r | d7 } | j | d�} | dk�rF|j
| d | � n
|j
| � | d | | < q�W t|�S )
a
Validate a list of strings as field names for a structured array.
Parameters
----------
names : sequence of str
Strings to be validated.
defaultfmt : str, optional
Default format string, used if validating a given string
reduces its length to zero.
nbfields : integer, optional
Final number of validated names, used to expand or shrink the
initial list of names.
Returns
-------
validatednames : list of str
The list of validated field names.
Notes
-----
A `NameValidator` instance can be called directly, which is the
same as calling `validate`. For examples, see `NameValidator`.
Nr
r � c s g | ]}|� kr|�qS r
r
)r% �c)r[ r
r r' l s z*NameValidator.validate.<locals>.<listcomp>r2 r& z_%d)r5 r6 rE r: r[ rW r\ r^ �dictr$ �replace�join�get�append�tuple)
r+ r �
defaultfmt�nbfieldsZnbnamesrW r\ r^ Zvalidatednames�seenZnbempty�itemZcntr
)r[ r �validate7 sL
zNameValidator.validatec C s | j |||d�S )N)rj rk )rn )r+ r rj rk r
r
r rG } s zNameValidator.__call__)NNNr& )ra N)ra N)
rH rI rJ rK rV rY rX r@ rn rG r
r
r
r rL � s 2
FrL c C s, | j � } | dkrdS | dkr dS td��dS )a�
Tries to transform a string supposed to represent a boolean to a boolean.
Parameters
----------
value : str
The string that is transformed to a boolean.
Returns
-------
boolval : bool
The boolean representation of `value`.
Raises
------
ValueError
If the string is not 'True' or 'False' (case independent)
Examples
--------
>>> np.lib._iotools.str2bool('TRUE')
True
>>> np.lib._iotools.str2bool('false')
False
�TRUET�FALSEFzInvalid booleanN)rS r )�valuer
r
r �str2bool� s rr c @ s e Zd ZdZdS )�ConverterErrorzR
Exception raised when an error occurs in a converter for string values.
N)rH rI rJ rK r
r
r
r rs � s rs c @ s e Zd ZdZdS )�ConverterLockErrorzR
Exception raised when an attempt is made to upgrade a locked converter.
N)rH rI rJ rK r
r
r
r rt � s rt c @ s e Zd ZdZdS )�ConversionWarningz�
Warning issued when a string converter has a problem.
Notes
-----
In `genfromtxt` a `ConversionWarning` is issued if raising exceptions
is explicitly suppressed with the "invalid_raise" keyword.
N)rH rI rJ rK r
r
r
r ru � s ru c @ sF e Zd ZdZejedfejed"fgZ ej
ej�j ej
ej �j k rRe j
ej ed#f� e jejeejfejeejd fejejejfejed$fejeejfejeejd fejedfejedfg� e dd� �Z e dd � �Z e d
d � �Z e d%d
d��Z e dd� �Z!d&dd�Z"dd� Z#dd� Z$dd� Z%dd� Z&dd � Z'd d � Z(d'd d!�Z)d S )(�StringConverterab
Factory class for function transforming a string into another object
(int, float).
After initialization, an instance can be called to transform a string
into another object. If the string is recognized as representing a
missing value, a default value is returned.
Attributes
----------
func : function
Function used for the conversion.
default : any
Default value to return when the input corresponds to a missing
value.
type : type
Type of the output.
_status : int
Integer representing the order of the conversion.
_mapper : sequence of tuples
Sequence of tuples (dtype, function, default value) to evaluate in
order.
_locked : bool
Holds `locked` parameter.
Parameters
----------
dtype_or_func : {None, dtype, function}, optional
If a `dtype`, specifies the input data type, used to define a basic
function and a default value for missing data. For example, when
`dtype` is float, the `func` attribute is set to `float` and the
default value to `np.nan`. If a function, this function is used to
convert a string to another object. In this case, it is recommended
to give an associated default value as input.
default : any, optional
Value to return by default, that is, when the string to be
converted is flagged as missing. If not given, `StringConverter`
tries to supply a reasonable default value.
missing_values : {None, sequence of str}, optional
``None`` or sequence of strings indicating a missing value. If ``None``
then missing values are indicated by empty entries. The default is
``None``.
locked : bool, optional
Whether the StringConverter should be locked to prevent automatic
upgrade or not. Default is False.
Fr2 y z???c C s t j|�jS )z(Returns the dtype of the input variable.)r �array�dtype)�cls�valr
r
r � _getdtype s zStringConverter._getdtypec C s t j|�jjS )z4Returns the type of the dtype of the input variable.)r rw rx r )ry rz r
r
r � _getsubdtype
s z StringConverter._getsubdtypec C s |j tjkr|S |j S )z9Returns dtype for datetime64 and type of dtype otherwise.)r r Z
datetime64)ry rx r
r
r � _dtypeortype s z StringConverter._dtypeortypeNc C s� t |d�r(| jjd| j|�||f� dS t |d�r�t|d ttf�rdx|D ]}| jjd|� qJW dS |dkr|dgt|� }n$t|�}|jdgt|�t|� � x0t ||�D ]"\}}| jjd| j|�||f� q�W dS ) a�
Upgrade the mapper of a StringConverter by adding a new function and
its corresponding default.
The input function (or sequence of functions) and its associated
default value (if any) is inserted in penultimate position of the
mapper. The corresponding type is estimated from the dtype of the
default value.
Parameters
----------
func : var
Function, or sequence of functions
Examples
--------
>>> import dateutil.parser
>>> import datetime
>>> dateparser = dateutil.parser.parse
>>> defaultdate = datetime.date(2000, 1, 1)
>>> StringConverter.upgrade_mapper(dateparser, default=defaultdate)
rG r2 Nr. r r3 r3 r3 )
r8 �_mapper�insertr| r5 ri r: rE rh r; )ry �func�defaultr& ZfctZdftr
r
r �upgrade_mapper s
z StringConverter.upgrade_mapperc C sx x4t | j�D ]&\}\}}}|j|kr ||||ffS q W x8t | j�D ]*\}\}}}tj|j|�rB||||ffS qBW t�d S )N)� enumerater~ r r Z
issubdtype� LookupError)ry rx r0 �deftyper� � default_defr
r
r �_find_map_entryG s
z StringConverter._find_map_entryc
C s� t |�| _|d kr6t| _d| _|p$d| _tjd�}�nTyd | _tj|�}W nr tk
r� t |d�sxd}t|t
|� ��|| _|d kr�y| jd�}W n t k
r� d }Y nX | j |�}Y nX y| j
|�\| _\}}} W n2 tk
�r
|| _| jd \}}}d| _Y nX |d k�r | | _n|| _| jd k�r6|| _| j| jd d k�r�t|j
tj��rftj| _n$t|j
tj��r�tj| _n
dd � | _|d k�r�d
h| _n*t|t��r�|jd �}tt|�d
g �| _| j| _| j|�| _
d| _ || _ d S )
Nr F�boolrG zOThe input argument `dtype` is neither a function nor a dtype (got '%s' instead)�0r2 c S s t t| ��S )N)r �float)rQ r
r
r r* � s z*StringConverter.__init__.<locals>.<lambda>r
�,r3 ) r� �_lockedrr r� �_statusr� r rx r r8 r r r{ r� r� r~ �
issubclassZuint64�int64�missing_valuesr5 r6 rA rY r: � _strict_call�_callingfunctionr} �_checked�_initial_default)
r+ Z
dtype_or_funcr� r� �lockedrx �errmsgr& r� r� r
r
r r@ U s\
zStringConverter.__init__c C s& y
| j |�S tk
r | jS X d S )N)r� r r� )r+ rq r
r
r � _loose_call� s
zStringConverter._loose_callc C s� yF| j |�}| j tkrDytj|| jd� W n tk
rB t�Y nX |S tk
r� |j� | jkrv| j spd| _
| j S td| ��Y nX d S )N)rx FzCannot convert string '%s') r� r r rw r �
OverflowErrorr r$ r� r� r� r� )r+ rq Z new_valuer
r
r r� � s
z StringConverter._strict_callc C s
| j |�S )N)r� )r+ rq r
r
r rG � s zStringConverter.__call__c C s� | j rd}t|��t| j�}| j}||kr8d}t|��n||d k rL|d7 }| j| \| _| _}|| _| jd k rz| j| _ n|| _ d S )Nz*Converter is locked and cannot be upgradedz*Could not find a valid conversion functionr2 )
r� rt rE r~ r� rs r r� r� r� )r+ r� Z
_statusmaxr� r� r
r
r � _do_upgrade� s
zStringConverter._do_upgradec C s8 d| _ y
| j|�S tk
r2 | j� | j|�S X dS )a�
Find the best converter for a given string, and return the result.
The supplied string `value` is converted by testing different
converters in order. First the `func` method of the
`StringConverter` instance is tried, if this fails other available
converters are tried. The order in which these other converters
are tried is determined by the `_status` attribute of the instance.
Parameters
----------
value : str
The string to convert.
Returns
-------
out : any
The result of converting `value` with the appropriate converter.
TN)r� r� r r� �upgrade)r+ rq r
r
r r� � s
zStringConverter.upgradec C sb d| _ t|d�s|f}| j}yx|D ] }||� q$W W n& tk
r\ | j� | j|� Y nX d S )NTr. )r� r8 r� r r� � iterupgrade)r+ rq r� �_mr
r
r r� � s
zStringConverter.iterupgrader
c C s� || _ || _|dk r.|| _| j| j|��| _n@y||p8d�}W n ttfk
rZ d}Y nX | j| j|��| _|dkr�t� | _ n6t
j |�s�|g}t dd� |D ��s�td��| j j
|� dS )a�
Set StringConverter attributes directly.
Parameters
----------
func : function
Conversion function.
default : any, optional
Value to return by default, that is, when the string to be
converted is flagged as missing. If not given,
`StringConverter` tries to supply a reasonable default value.
testing_value : str, optional
A string representing a standard input value of the converter.
This string is used to help defining a reasonable default
value.
missing_values : {sequence of str, None}, optional
Sequence of strings indicating a missing value. If ``None``, then
the existing `missing_values` are cleared. The default is `''`.
locked : bool, optional
Whether the StringConverter should be locked to prevent
automatic upgrade or not. Default is False.
Notes
-----
`update` takes the same parameters as the constructor of
`StringConverter`, except that `func` does not accept a `dtype`
whereas `dtype_or_func` in the constructor does.
N�1c s s | ]}t |t�V qd S )N)r5 r6 )r% �vr
r
r � <genexpr>1 s z)StringConverter.update.<locals>.<genexpr>z)missing_values must be strings or unicode)r� r� r� r} r{ r r r rY r� r �iterable�all�update)r+ r� r� Z
testing_valuer� r� �testerr
r
r r� � s"
zStringConverter.updater3 r3 r3 )N)NNNF)NNr
F)*rH rI rJ rK �nxZbool_rr �int_r r~ rx �itemsizer� rh r Zfloat64r� �nanZ
complex128�complexZ
longdouble�integerZfloatingZcomplexfloatingZunicode_r Zstring_r � classmethodr{ r| r} r� r� r@ r� r� rG r� r� r� r� r
r
r
r rv � s: /
(
H rv �f%ic
K sz yt j| �} W nr tk
r� tf |�}t| �}|dkrHdgt| � }nt|t�r\|jd�}||||d�}t jt| |d��} Y n�X |dk �rtf |�}t|t�r�|jd�}| j dkr�t
| j gt|� �}|||d�}t jt t
||���} n||t| j �|d�| _ nt| j dk �rvtf |�}t
dd� tt| j ��D ��}| j |k�rf|d k�rf|dgt| j � |d�| _ n|| j |d�| _ | S )
a6
Convenience function to create a `np.dtype` object.
The function processes the input `dtype` and matches it with the given
names.
Parameters
----------
ndtype : var
Definition of the dtype. Can be any string or dictionary recognized
by the `np.dtype` function, or a sequence of types.
names : str or sequence, optional
Sequence of strings to use as field names for a structured dtype.
For convenience, `names` can be a string of a comma-separated list
of names.
defaultfmt : str, optional
Format string used to define missing names, such as ``"f%i"``
(default) or ``"fields_%02i"``.
validationargs : optional
A series of optional arguments used to initialize a
`NameValidator`.
Examples
--------
>>> np.lib._iotools.easy_dtype(float)
dtype('float64')
>>> np.lib._iotools.easy_dtype("i4, f8")
dtype([('f0', '<i4'), ('f1', '<f8')])
>>> np.lib._iotools.easy_dtype("i4, f8", defaultfmt="field_%03i")
dtype([('field_000', '<i4'), ('field_001', '<f8')])
>>> np.lib._iotools.easy_dtype((int, float, float), names="a,b,c")
dtype([('a', '<i8'), ('b', '<f8'), ('c', '<f8')])
>>> np.lib._iotools.easy_dtype(float, names="a,b,c")
dtype([('a', '<f8'), ('b', '<f8'), ('c', '<f8')])
Nr
r� )rk rj )�formatsr )rj c s s | ]}d | V qdS )zf%iNr
)r% r0 r
r
r r� z s z easy_dtype.<locals>.<genexpr>zf%i)r rx r rL rE r5 r6 rA rd r ri r r: r; rD )r r rj Zvalidationargsrn rk r� Znumbered_namesr
r
r �
easy_dtype6 s: &
r� )N)F)Nr� )rK Z
__docformat__Znumpyr Znumpy.core.numeric�core�numericr� Z numpy.compatr r r r r r r r r# rL rr � Exceptionrs rt � UserWarningru rv r� r
r
r
r �<module> s(
/` $
v |