Viewing file:  defchararray.py (68.31 KB) -rw-r--r--
Select action/file-type:
 (+) |  (+) |  (+) | Code (+) | Session (+) |  (+) | SDB (+) |  (+) |  (+) |  (+) |  (+) |  (+) |
"""
This module contains a set of functions for vectorized string
operations and methods.
.. note::
The `chararray` class exists for backwards compatibility with
Numarray, it is not recommended for new development. If one needs
arrays of strings, use arrays of `dtype` `object_`, `string_` or
`unicode_`, and use the free functions in the `numpy.char` module
for fast vectorized string operations.
Some methods will only be available if the corresponding str method is
available in your version of Python.
The preferred alias for `defchararray` is `numpy.char`.
"""
import sys
from numerictypes import string_, unicode_, integer, object_, bool_, character
from numeric import ndarray, compare_chararrays
from numeric import array as narray
from numpy.core.multiarray import _vec_string
import numpy
__all__ = ['chararray',
'equal', 'not_equal', 'greater_equal', 'less_equal', 'greater', 'less',
'str_len', 'add', 'multiply', 'mod', 'capitalize', 'center', 'count',
'decode', 'encode', 'endswith', 'expandtabs', 'find', 'format',
'index', 'isalnum', 'isalpha', 'isdigit', 'islower', 'isspace',
'istitle', 'isupper', 'join', 'ljust', 'lower', 'lstrip',
'partition', 'replace', 'rfind', 'rindex', 'rjust', 'rpartition',
'rsplit', 'rstrip', 'split', 'splitlines', 'startswith', 'strip',
'swapcase', 'title', 'translate', 'upper', 'zfill',
'isnumeric', 'isdecimal',
'array', 'asarray']
_globalvar = 0
_unicode = unicode
_len = len
def _use_unicode(*args):
"""
Helper function for determining the output type of some string
operations.
For an operation on two ndarrays, if at least one is unicode, the
result should be unicode.
"""
for x in args:
if (isinstance(x, _unicode)
or issubclass(numpy.asarray(x).dtype.type, unicode_)):
return unicode_
return string_
def _to_string_or_unicode_array(result):
"""
Helper function to cast a result back into a string or unicode array
if an object array must be used as an intermediary.
"""
return numpy.asarray(result.tolist())
def _clean_args(*args):
"""
Helper function for delegating arguments to Python string
functions.
Many of the Python string operations that have optional arguments
do not use 'None' to indicate a default value. In these cases,
we need to remove all `None` arguments, and those following them.
"""
newargs = []
for chk in args:
if chk is None:
break
newargs.append(chk)
return newargs
def _get_num_chars(a):
"""
Helper function that returns the number of characters per field in
a string or unicode array. This is to abstract out the fact that
for a unicode array this is itemsize / 4.
"""
if issubclass(a.dtype.type, unicode_):
return a.itemsize / 4
return a.itemsize
def equal(x1, x2):
"""
Return (x1 == x2) element-wise.
Unlike `numpy.equal`, this comparison is performed by first
stripping whitespace characters from the end of the string. This
behavior is provided for backward-compatibility with numarray.
Parameters
----------
x1, x2 : array_like of str or unicode
Input arrays of the same shape.
Returns
-------
out : {ndarray, bool}
Output array of bools, or a single bool if x1 and x2 are scalars.
See Also
--------
not_equal, greater_equal, less_equal, greater, less
"""
return compare_chararrays(x1, x2, '==', True)
def not_equal(x1, x2):
"""
Return (x1 != x2) element-wise.
Unlike `numpy.not_equal`, this comparison is performed by first
stripping whitespace characters from the end of the string. This
behavior is provided for backward-compatibility with numarray.
Parameters
----------
x1, x2 : array_like of str or unicode
Input arrays of the same shape.
Returns
-------
out : {ndarray, bool}
Output array of bools, or a single bool if x1 and x2 are scalars.
See Also
--------
equal, greater_equal, less_equal, greater, less
"""
return compare_chararrays(x1, x2, '!=', True)
def greater_equal(x1, x2):
"""
Return (x1 >= x2) element-wise.
Unlike `numpy.greater_equal`, this comparison is performed by
first stripping whitespace characters from the end of the string.
This behavior is provided for backward-compatibility with
numarray.
Parameters
----------
x1, x2 : array_like of str or unicode
Input arrays of the same shape.
Returns
-------
out : {ndarray, bool}
Output array of bools, or a single bool if x1 and x2 are scalars.
See Also
--------
equal, not_equal, less_equal, greater, less
"""
return compare_chararrays(x1, x2, '>=', True)
def less_equal(x1, x2):
"""
Return (x1 <= x2) element-wise.
Unlike `numpy.less_equal`, this comparison is performed by first
stripping whitespace characters from the end of the string. This
behavior is provided for backward-compatibility with numarray.
Parameters
----------
x1, x2 : array_like of str or unicode
Input arrays of the same shape.
Returns
-------
out : {ndarray, bool}
Output array of bools, or a single bool if x1 and x2 are scalars.
See Also
--------
equal, not_equal, greater_equal, greater, less
"""
return compare_chararrays(x1, x2, '<=', True)
def greater(x1, x2):
"""
Return (x1 > x2) element-wise.
Unlike `numpy.greater`, this comparison is performed by first
stripping whitespace characters from the end of the string. This
behavior is provided for backward-compatibility with numarray.
Parameters
----------
x1, x2 : array_like of str or unicode
Input arrays of the same shape.
Returns
-------
out : {ndarray, bool}
Output array of bools, or a single bool if x1 and x2 are scalars.
See Also
--------
equal, not_equal, greater_equal, less_equal, less
"""
return compare_chararrays(x1, x2, '>', True)
def less(x1, x2):
"""
Return (x1 < x2) element-wise.
Unlike `numpy.greater`, this comparison is performed by first
stripping whitespace characters from the end of the string. This
behavior is provided for backward-compatibility with numarray.
Parameters
----------
x1, x2 : array_like of str or unicode
Input arrays of the same shape.
Returns
-------
out : {ndarray, bool}
Output array of bools, or a single bool if x1 and x2 are scalars.
See Also
--------
equal, not_equal, greater_equal, less_equal, greater
"""
return compare_chararrays(x1, x2, '<', True)
def str_len(a):
"""
Return len(a) element-wise.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of integers
See also
--------
__builtin__.len
"""
return _vec_string(a, integer, '__len__')
def add(x1, x2):
"""
Return (x1 + x2), that is string concatenation, element-wise for a
pair of array_likes of str or unicode.
Parameters
----------
x1 : array_like of str or unicode
x2 : array_like of str or unicode
Returns
-------
out : ndarray
Output array of string_ or unicode_, depending on input types
"""
arr1 = numpy.asarray(x1)
arr2 = numpy.asarray(x2)
out_size = _get_num_chars(arr1) + _get_num_chars(arr2)
dtype = _use_unicode(arr1, arr2)
return _vec_string(arr1, (dtype, out_size), '__add__', (arr2,))
def multiply(a, i):
"""
Return (a * i), that is string multiple concatenation,
element-wise.
Values in `i` of less than 0 are treated as 0 (which yields an
empty string).
Parameters
----------
a : array_like of str or unicode
i : array_like of ints
Returns
-------
out : ndarray
Output array of str or unicode, depending on input types
"""
a_arr = numpy.asarray(a)
i_arr = numpy.asarray(i)
if not issubclass(i_arr.dtype.type, integer):
raise ValueError, "Can only multiply by integers"
out_size = _get_num_chars(a_arr) * max(long(i_arr.max()), 0)
return _vec_string(
a_arr, (a_arr.dtype.type, out_size), '__mul__', (i_arr,))
def mod(a, values):
"""
Return (a % i), that is pre-Python 2.6 string formatting
(iterpolation), element-wise for a pair of array_likes of str
or unicode.
Parameters
----------
a : array_like of str or unicode
values : array_like of values
These values will be element-wise interpolated into the string.
Returns
-------
out : ndarray
Output array of str or unicode, depending on input types
See also
--------
str.__mod__
"""
return _to_string_or_unicode_array(
_vec_string(a, object_, '__mod__', (values,)))
def capitalize(a):
"""
Return a copy of `a` with only the first character of each element
capitalized.
Calls `str.capitalize` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of str or unicode, depending on input
types
See also
--------
str.capitalize
Examples
--------
>>> c = np.array(['a1b2','1b2a','b2a1','2a1b'],'S4'); c
array(['a1b2', '1b2a', 'b2a1', '2a1b'],
dtype='|S4')
>>> np.char.capitalize(c)
array(['A1b2', '1b2a', 'B2a1', '2a1b'],
dtype='|S4')
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'capitalize')
if sys.version_info >= (2, 4):
def center(a, width, fillchar=' '):
"""
Return a copy of `a` with its elements centered in a string of
length `width`.
Calls `str.center` element-wise.
Parameters
----------
a : array_like of str or unicode
width : int
The length of the resulting strings
fillchar : str or unicode, optional
The padding character to use (default is space).
Returns
-------
out : ndarray
Output array of str or unicode, depending on input
types
See also
--------
str.center
"""
a_arr = numpy.asarray(a)
width_arr = numpy.asarray(width)
size = long(numpy.max(width_arr.flat))
return _vec_string(
a_arr, (a_arr.dtype.type, size), 'center', (width_arr, fillchar))
else:
def center(a, width):
"""
Return an array with the elements of `a` centered in a string
of length width.
Calls `str.center` element-wise.
Parameters
----------
a : array_like of str or unicode
width : int
The length of the resulting strings
Returns
-------
out : ndarray, str or unicode
Output array of str or unicode, depending on input types
See also
--------
str.center
"""
a_arr = numpy.asarray(a)
width_arr = numpy.asarray(width)
size = long(numpy.max(width_arr.flat))
return _vec_string(
a_arr, (a_arr.dtype.type, size), 'center', (width_arr,))
def count(a, sub, start=0, end=None):
"""
Returns an array with the number of non-overlapping occurrences of
substring `sub` in the range [`start`, `end`].
Calls `str.count` element-wise.
Parameters
----------
a : array_like of str or unicode
sub : str or unicode
The substring to search for.
start, end : int, optional
Optional arguments `start` and `end` are interpreted as slice
notation to specify the range in which to count.
Returns
-------
out : ndarray
Output array of ints.
See also
--------
str.count
Examples
--------
>>> c = np.array(['aAaAaA', ' aA ', 'abBABba'])
>>> c
array(['aAaAaA', ' aA', 'abBABba'],
dtype='|S7')
>>> np.char.count(c, 'A')
array([3, 1, 1])
>>> np.char.count(c, 'aA')
array([3, 1, 0])
>>> np.char.count(c, 'A', start=1, end=4)
array([2, 1, 1])
>>> np.char.count(c, 'A', start=1, end=3)
array([1, 0, 0])
"""
return _vec_string(a, integer, 'count', [sub, start] + _clean_args(end))
def decode(a, encoding=None, errors=None):
"""
Calls `str.decode` element-wise.
The set of available codecs comes from the Python standard library,
and may be extended at runtime. For more information, see the
:mod:`codecs` module.
Parameters
----------
a : array_like of str or unicode
encoding : str, optional
The name of an encoding
errors : str, optional
Specifies how to handle encoding errors
Returns
-------
out : ndarray
See also
--------
str.decode
Notes
-----
The type of the result will depend on the encoding specified.
Examples
--------
>>> c = np.array(['aAaAaA', ' aA ', 'abBABba'])
>>> c
array(['aAaAaA', ' aA', 'abBABba'],
dtype='|S7')
>>> np.char.encode(c, encoding='cp037')
array(['\\x81\\xc1\\x81\\xc1\\x81\\xc1', '@@\\x81\\xc1@@',
'\\x81\\x82\\xc2\\xc1\\xc2\\x82\\x81'],
dtype='|S7')
"""
return _to_string_or_unicode_array(
_vec_string(a, object_, 'decode', _clean_args(encoding, errors)))
def encode(a, encoding=None, errors=None):
"""
Calls `str.encode` element-wise.
The set of available codecs comes from the Python standard library,
and may be extended at runtime. For more information, see the codecs
module.
Parameters
----------
a : array_like of str or unicode
encoding : str, optional
The name of an encoding
errors : str, optional
Specifies how to handle encoding errors
Returns
-------
out : ndarray
See also
--------
str.encode
Notes
-----
The type of the result will depend on the encoding specified.
"""
return _to_string_or_unicode_array(
_vec_string(a, object_, 'encode', _clean_args(encoding, errors)))
def endswith(a, suffix, start=0, end=None):
"""
Returns a boolean array which is `True` where the string element
in `a` ends with `suffix`, otherwise `False`.
Calls `str.endswith` element-wise.
Parameters
----------
a : array_like of str or unicode
suffix : str
start, end : int, optional
With optional `start`, test beginning at that position. With
optional `end`, stop comparing at that position.
Returns
-------
out : ndarray
Outputs an array of bools.
See also
--------
str.endswith
Examples
--------
>>> s = np.array(['foo', 'bar'])
>>> s[0] = 'foo'
>>> s[1] = 'bar'
>>> s
array(['foo', 'bar'],
dtype='|S3')
>>> np.charendswith(s, 'ar')
array([False, True], dtype=bool)
>>> s.endswith(s, 'a', start=1, end=2)
array([False, True], dtype=bool)
"""
return _vec_string(
a, bool_, 'endswith', [suffix, start] + _clean_args(end))
def expandtabs(a, tabsize=8):
"""
Return a copy of each string element where all tab characters are
replaced by one or more spaces.
Calls `str.expandtabs` element-wise.
Return a copy of each string element where all tab characters are
replaced by one or more spaces, depending on the current column
and the given `tabsize`. The column number is reset to zero after
each newline occurring in the string. If `tabsize` is not given, a
tab size of 8 characters is assumed. This doesn't understand other
non-printing characters or escape sequences.
Parameters
----------
a : array_like of str or unicode
tabsize : int, optional
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.expandtabs
"""
return _to_string_or_unicode_array(
_vec_string(a, object_, 'expandtabs', (tabsize,)))
def find(a, sub, start=0, end=None):
"""
For each element, return the lowest index in the string where
substring `sub` is found.
Calls `str.find` element-wise.
For each element, return the lowest index in the string where
substring `sub` is found, such that `sub` is contained in the
range [`start`, `end`].
Parameters
----------
a : array_like of str or unicode
sub : str or unicode
start, end : int, optional
Optional arguments `start` and `end` are interpreted as in
slice notation.
Returns
-------
out : ndarray or int
Output array of ints. Returns -1 if `sub` is not found.
See also
--------
str.find
"""
return _vec_string(
a, integer, 'find', [sub, start] + _clean_args(end))
# if sys.version_info >= (2.6):
# def format(a, *args, **kwargs):
# # _vec_string doesn't support kwargs at present
# raise NotImplementedError
def index(a, sub, start=0, end=None):
"""
Like `find`, but raises `ValueError` when the substring is not found.
Calls `str.index` element-wise.
Parameters
----------
a : array_like of str or unicode
sub : str or unicode
start, end : int, optional
Returns
-------
out : ndarray
Output array of ints. Returns -1 if `sub` is not found.
See also
--------
find, str.find
"""
return _vec_string(
a, integer, 'index', [sub, start] + _clean_args(end))
def isalnum(a):
"""
Returns true for each element if all characters in the string are
alphanumeric and there is at least one character, false otherwise.
Calls `str.isalnum` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.isalnum
"""
return _vec_string(a, bool_, 'isalnum')
def isalpha(a):
"""
Returns true for each element if all characters in the string are
alphabetic and there is at least one character, false otherwise.
Calls `str.isalpha` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of bools
See also
--------
str.isalpha
"""
return _vec_string(a, bool_, 'isalpha')
def isdigit(a):
"""
Returns true for each element if all characters in the string are
digits and there is at least one character, false otherwise.
Calls `str.isdigit` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of bools
See also
--------
str.isdigit
"""
return _vec_string(a, bool_, 'isdigit')
def islower(a):
"""
Returns true for each element if all cased characters in the
string are lowercase and there is at least one cased character,
false otherwise.
Calls `str.islower` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of bools
See also
--------
str.islower
"""
return _vec_string(a, bool_, 'islower')
def isspace(a):
"""
Returns true for each element if there are only whitespace
characters in the string and there is at least one character,
false otherwise.
Calls `str.isspace` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of bools
See also
--------
str.isspace
"""
return _vec_string(a, bool_, 'isspace')
def istitle(a):
"""
Returns true for each element if the element is a titlecased
string and there is at least one character, false otherwise.
Call `str.istitle` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of bools
See also
--------
str.istitle
"""
return _vec_string(a, bool_, 'istitle')
def isupper(a):
"""
Returns true for each element if all cased characters in the
string are uppercase and there is at least one character, false
otherwise.
Call `str.isupper` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array_like of str or unicode
Returns
-------
out : ndarray
Output array of bools
See also
--------
str.isupper
"""
return _vec_string(a, bool_, 'isupper')
def join(sep, seq):
"""
Return a string which is the concatenation of the strings in the
sequence `seq`.
Calls `str.join` element-wise.
Parameters
----------
sep : array_like of str or unicode
seq : array_like of str or unicode
Returns
-------
out : ndarray
Output array of str or unicode, depending on input types
See also
--------
str.join
"""
return _to_string_or_unicode_array(
_vec_string(sep, object_, 'join', (seq,)))
if sys.version_info >= (2, 4):
def ljust(a, width, fillchar=' '):
"""
Return an array with the elements of `a` left-justified in a
string of length `width`.
Calls `str.ljust` element-wise.
Parameters
----------
a : array_like of str or unicode
width : int
The length of the resulting strings
fillchar : str or unicode, optional
The character to use for padding
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.ljust
"""
a_arr = numpy.asarray(a)
width_arr = numpy.asarray(width)
size = long(numpy.max(width_arr.flat))
return _vec_string(
a_arr, (a_arr.dtype.type, size), 'ljust', (width_arr, fillchar))
else:
def ljust(a, width):
"""
Return an array with the elements of `a` left-justified in a
string of length `width`.
Calls `str.ljust` element-wise.
Parameters
----------
a : array_like of str or unicode
width : int
The length of the resulting strings
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.ljust
"""
a_arr = numpy.asarray(a)
width_arr = numpy.asarray(width)
size = long(numpy.max(width_arr.flat))
return _vec_string(
a_arr, (a_arr.dtype.type, size), 'ljust', (width_arr,))
def lower(a):
"""
Return an array with the elements of `a` converted to lowercase.
Call `str.lower` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array-like of str or unicode
Returns
-------
out : ndarray, str or unicode
Output array of str or unicode, depending on input type
See also
--------
str.lower
Examples
--------
>>> c = np.array(['A1B C', '1BCA', 'BCA1']); c
array(['A1B C', '1BCA', 'BCA1'],
dtype='|S5')
>>> np.char.lower(c)
array(['a1b c', '1bca', 'bca1'],
dtype='|S5')
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'lower')
def lstrip(a, chars=None):
"""
For each element in `a`, return a copy with the leading characters
removed.
Calls `str.lstrip` element-wise.
Parameters
----------
a : array-like of str or unicode
chars : str or unicode, optional
The `chars` argument is a string specifying the set of
characters to be removed. If omitted or None, the `chars`
argument defaults to removing whitespace. The `chars` argument
is not a prefix; rather, all combinations of its values are
stripped.
Returns
-------
out : ndarray, str or unicode
Output array of str or unicode, depending on input type
See also
--------
str.lstrip
Examples
--------
>>> c = np.array(['aAaAaA', ' aA ', 'abBABba'])
>>> c
array(['aAaAaA', ' aA', 'abBABba'],
dtype='|S7')
>>> np.char.lstrip(c, 'a') # 'a' unstripped from c[1] because whitespace leading
array(['AaAaA', ' aA', 'bBABba'],
dtype='|S6')
>>> np.char.lstrip(c, 'A') # leaves c unchanged
array(['aAaAaA', ' aA', 'abBABba'],
dtype='|S7')
>>> (np.char.lstrip(c, ' ') == np.char.lstrip(c, '')).all()
True
>>> (np.char.lstrip(c, ' ') == np.char.lstrip(c, None)).all()
True
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'lstrip', (chars,))
if sys.version_info >= (2, 5):
def partition(a, sep):
"""
Partition each element in `a` around `sep`.
Calls `str.partition` element-wise.
For each element in `a`, split the element as the first
occurrence of `sep`, and return 3 strings containing the part
before the separator, the separator itself, and the part after
the separator. If the separator is not found, return 3 strings
containing the string itself, followed by two empty strings.
Parameters
----------
a : array-like of str or unicode
sep : str or unicode
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type.
The output array will have an extra dimension with 3
elements per input element.
See also
--------
str.partition
"""
return _to_string_or_unicode_array(
_vec_string(a, object_, 'partition', (sep,)))
def replace(a, old, new, count=None):
"""
For each element in `a`, return a copy of the string with all
occurrences of substring `old` replaced by `new`.
Calls `str.replace` element-wise.
Parameters
----------
a : array-like of str or unicode
old, new : str or unicode
count : int, optional
If the optional argument `count` is given, only the first
`count` occurrences are replaced.
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.replace
"""
return _to_string_or_unicode_array(
_vec_string(
a, object_, 'replace', [old, new] +_clean_args(count)))
def rfind(a, sub, start=0, end=None):
"""
For each element in `a`, return the highest index in the string
where substring `sub` is found, such that `sub` is contained
within [`start`, `end`].
Calls `str.rfind` element-wise.
Parameters
----------
a : array-like of str or unicode
sub : str or unicode
start, end : int, optional
Optional arguments `start` and `end` are interpreted as in
slice notation.
Returns
-------
out : ndarray
Output array of ints. Return -1 on failure.
See also
--------
str.rfind
"""
return _vec_string(
a, integer, 'rfind', [sub, start] + _clean_args(end))
def rindex(a, sub, start=0, end=None):
"""
Like `rfind`, but raises `ValueError` when the substring `sub` is
not found.
Calls `str.rindex` element-wise.
Parameters
----------
a : array-like of str or unicode
sub : str or unicode
start, end : int, optional
Returns
-------
out : ndarray
Output array of ints.
See also
--------
rfind, str.rindex
"""
return _vec_string(
a, integer, 'rindex', [sub, start] + _clean_args(end))
if sys.version_info >= (2, 4):
def rjust(a, width, fillchar=' '):
"""
Return an array with the elements of `a` right-justified in a
string of length `width`.
Calls `str.rjust` element-wise.
Parameters
----------
a : array_like of str or unicode
width : int
The length of the resulting strings
fillchar : str or unicode, optional
The character to use for padding
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.rjust
"""
a_arr = numpy.asarray(a)
width_arr = numpy.asarray(width)
size = long(numpy.max(width_arr.flat))
return _vec_string(
a_arr, (a_arr.dtype.type, size), 'rjust', (width_arr, fillchar))
else:
def rjust(a, width):
"""
Return an array with the elements of `a` right-justified in a
string of length `width`.
Calls `str.rjust` element-wise.
Parameters
----------
a : array_like of str or unicode
width : int
The length of the resulting strings
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.rjust
"""
a_arr = numpy.asarray(a)
width_arr = numpy.asarray(width)
size = long(numpy.max(width_arr.flat))
return _vec_string(
a_arr, (a_arr.dtype.type, size), 'rjust', (width,))
if sys.version_info >= (2, 5):
def rpartition(a, sep):
"""
Partition each element in `a` around `sep`.
Calls `str.rpartition` element-wise.
For each element in `a`, split the element as the last
occurrence of `sep`, and return 3 strings containing the part
before the separator, the separator itself, and the part after
the separator. If the separator is not found, return 3 strings
containing the string itself, followed by two empty strings.
Parameters
----------
a : array-like of str or unicode
sep : str or unicode
Returns
-------
out : ndarray
Output array of string or unicode, depending on input
type. The output array will have an extra dimension with
3 elements per input element.
See also
--------
str.rpartition
"""
return _to_string_or_unicode_array(
_vec_string(a, object_, 'rpartition', (sep,)))
if sys.version_info >= (2, 4):
def rsplit(a, sep=None, maxsplit=None):
"""
For each element in `a`, return a list of the words in the
string, using `sep` as the delimiter string.
Calls `str.rsplit` element-wise.
Except for splitting from the right, `rsplit`
behaves like `split`.
Parameters
----------
a : array_like of str or unicode
sep : str or unicode, optional
If `sep` is not specified or `None`, any whitespace string
is a separator.
maxsplit : int, optional
If `maxsplit` is given, at most `maxsplit` splits are done,
the rightmost ones.
Returns
-------
out : ndarray
Array of list objects
See also
--------
str.rsplit, split
"""
# This will return an array of lists of different sizes, so we
# leave it as an object array
return _vec_string(
a, object_, 'rsplit', [sep] + _clean_args(maxsplit))
def rstrip(a, chars=None):
"""
For each element in `a`, return a copy with the trailing
characters removed.
Calls `str.rstrip` element-wise.
Parameters
----------
a : array-like of str or unicode
chars : str or unicode, optional
The `chars` argument is a string specifying the set of
characters to be removed. If omitted or None, the `chars`
argument defaults to removing whitespace. The `chars` argument
is not a suffix; rather, all combinations of its values are
stripped.
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.rstrip
Examples
--------
>>> c = np.array(['aAaAaA', 'abBABba'], dtype='S7'); c
array(['aAaAaA', 'abBABba'],
dtype='|S7')
>>> np.char.rstrip(c, 'a')
array(['aAaAaA', 'abBABb'],
dtype='|S6')
>>> np.char.rstrip(c, 'A')
array(['aAaAa', 'abBABba'],
dtype='|S7')
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'rstrip', (chars,))
def split(a, sep=None, maxsplit=None):
"""
For each element in `a`, return a list of the words in the
string, using `sep` as the delimiter string.
Calls `str.rsplit` element-wise.
Parameters
----------
a : array_like of str or unicode
sep : str or unicode, optional
If `sep` is not specified or `None`, any whitespace string is a
separator.
maxsplit : int, optional
If `maxsplit` is given, at most `maxsplit` splits are done.
Returns
-------
out : ndarray
Array of list objects
See also
--------
str.split, rsplit
"""
# This will return an array of lists of different sizes, so we
# leave it as an object array
return _vec_string(
a, object_, 'split', [sep] + _clean_args(maxsplit))
def splitlines(a, keepends=None):
"""
For each element in `a`, return a list of the lines in the
element, breaking at line boundaries.
Calls `str.splitlines` element-wise.
Parameters
----------
a : array_like of str or unicode
keepends : bool, optional
Line breaks are not included in the resulting list unless
keepends is given and true.
Returns
-------
out : ndarray
Array of list objects
See also
--------
str.splitlines
"""
return _vec_string(
a, object_, 'splitlines', _clean_args(keepends))
def startswith(a, prefix, start=0, end=None):
"""
Returns a boolean array which is `True` where the string element
in `a` starts with `prefix`, otherwise `False`.
Calls `str.startswith` element-wise.
Parameters
----------
a : array_like of str or unicode
suffix : str
start, end : int, optional
With optional `start`, test beginning at that position. With
optional `end`, stop comparing at that position.
Returns
-------
out : ndarray
Array of booleans
See also
--------
str.startswith
"""
return _vec_string(
a, bool_, 'startswith', [prefix, start] + _clean_args(end))
def strip(a, chars=None):
"""
For each element in `a`, return a copy with the leading and
trailing characters removed.
Calls `str.rstrip` element-wise.
Parameters
----------
a : array-like of str or unicode
chars : str or unicode, optional
The `chars` argument is a string specifying the set of
characters to be removed. If omitted or None, the `chars`
argument defaults to removing whitespace. The `chars` argument
is not a prefix or suffix; rather, all combinations of its
values are stripped.
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.strip
Examples
--------
>>> c = np.array(['aAaAaA', ' aA ', 'abBABba'])
>>> c
array(['aAaAaA', ' aA', 'abBABba'],
dtype='|S7')
>>> np.char.strip(c)
array(['aAaAaA', 'aA', 'abBABba'],
dtype='|S7')
>>> np.char.strip(c, 'a') # 'a' unstripped from c[1] because whitespace leads
array(['AaAaA', ' aA', 'bBABb'],
dtype='|S6')
>>> np.char.strip(c, 'A') # 'A' unstripped from c[1] because (unprinted) ws trails
array(['aAaAa', ' aA', 'abBABba'],
dtype='|S7')
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'strip', _clean_args(chars))
def swapcase(a):
"""
For each element in `a`, return a copy of the string with
uppercase characters converted to lowercase and vice versa.
Calls `str.swapcase` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array-like of str or unicode
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.swapcase
Examples
--------
>>> c=np.array(['a1B c','1b Ca','b Ca1','cA1b'],'S5'); c
array(['a1B c', '1b Ca', 'b Ca1', 'cA1b'],
dtype='|S5')
>>> np.char.swapcase(c)
array(['A1b C', '1B cA', 'B cA1', 'Ca1B'],
dtype='|S5')
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'swapcase')
def title(a):
"""
For each element in `a`, return a titlecased version of the
string: words start with uppercase characters, all remaining cased
characters are lowercase.
Calls `str.title` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array-like of str or unicode
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.title
Examples
--------
>>> c=np.array(['a1b c','1b ca','b ca1','ca1b'],'S5'); c
array(['a1b c', '1b ca', 'b ca1', 'ca1b'],
dtype='|S5')
>>> np.char.title(c)
chararray(['A1B C', '1B Ca', 'B Ca1', 'Ca1B'],
dtype='|S5')
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'title')
def translate(a, table, deletechars=None):
"""
For each element in `a`, return a copy of the string where all
characters occurring in the optional argument `deletechars` are
removed, and the remaining characters have been mapped through the
given translation table.
Calls `str.translate` element-wise.
Parameters
----------
a : array-like of str or unicode
table : str of length 256
deletechars : str
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.translate
"""
a_arr = numpy.asarray(a)
if issubclass(a_arr.dtype.type, unicode_):
return _vec_string(
a_arr, a_arr.dtype, 'translate', (table,))
else:
return _vec_string(
a_arr, a_arr.dtype, 'translate', [table] + _clean_args(deletechars))
def upper(a):
"""
Return an array with the elements of `a` converted to uppercase.
Calls `str.upper` element-wise.
For 8-bit strings, this method is locale-dependent.
Parameters
----------
a : array-like of str or unicode
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.upper
Examples
--------
>>> c = np.array(['a1b c', '1bca', 'bca1']); c
array(['a1b c', '1bca', 'bca1'],
dtype='|S5')
>>> numpy.char.upper(c)
array(['A1B C', '1BCA', 'BCA1'],
dtype='|S5')
"""
a_arr = numpy.asarray(a)
return _vec_string(a_arr, a_arr.dtype, 'upper')
def zfill(a, width):
"""
Return the numeric string left-filled with zeros in a string of
length `width`.
Calls `str.zfill` element-wise.
Parameters
----------
a : array-like of str or unicode
width : int
Returns
-------
out : ndarray
Output array of str or unicode, depending on input type
See also
--------
str.zfill
"""
a_arr = numpy.asarray(a)
width_arr = numpy.asarray(width)
size = long(numpy.max(width_arr.flat))
return _vec_string(
a_arr, (a_arr.dtype.type, size), 'zfill', (width_arr,))
def isnumeric(a):
"""
For each element in `a`, return True if there are only numeric
characters in the element.
Calls `unicode.isnumeric` element-wise.
Numeric characters include digit characters, and all characters
that have the Unicode numeric value property, e.g. ``U+2155,
VULGAR FRACTION ONE FIFTH``.
Parameters
----------
a : array-like of unicode
Returns
-------
out : ndarray
Array of booleans
See also
--------
unicode.isnumeric
"""
if _use_unicode(a) != unicode_:
raise TypeError, "isnumeric is only available for Unicode strings and arrays"
return _vec_string(a, bool_, 'isnumeric')
def isdecimal(a):
"""
For each element in `a`, return True if there are only decimal
characters in the element.
Calls `unicode.isdecimal` element-wise.
Decimal characters include digit characters, and all characters
that that can be used to form decimal-radix numbers,
e.g. ``U+0660, ARABIC-INDIC DIGIT ZERO``.
Parameters
----------
a : array-like of unicode
Returns
-------
out : ndarray
Array of booleans
See also
--------
unicode.isdecimal
"""
if _use_unicode(a) != unicode_:
raise TypeError, "isnumeric is only available for Unicode strings and arrays"
return _vec_string(a, bool_, 'isdecimal')
class chararray(ndarray):
"""
chararray(shape, itemsize=1, unicode=False, buffer=None, offset=0,
strides=None, order=None)
Provides a convenient view on arrays of string and unicode values.
.. note::
The `chararray` class exists for backwards compatibility with
Numarray, it is not recommended for new development. If one needs
arrays of strings, use arrays of `dtype` `object_`, `string_` or
`unicode_`, and use the free functions in the `numpy.char` module
for fast vectorized string operations.
Versus a regular Numpy array of type `str` or `unicode`, this
class adds the following functionality:
1) values automatically have whitespace removed from the end
when indexed
2) comparison operators automatically remove whitespace from the
end when comparing values
3) vectorized string operations are provided as methods
(e.g. `.endswith`) and infix operators (e.g. ``"+", "*", "%"``)
chararrays should be created using `numpy.char.array` or
`numpy.char.asarray`, rather than this constructor directly.
This constructor creates the array, using `buffer` (with `offset`
and `strides`) if it is not ``None``. If `buffer` is ``None``, then
constructs a new array with `strides` in "C order", unless both
``len(shape) >= 2`` and ``order='Fortran'``, in which case `strides`
is in "Fortran order".
Parameters
----------
shape : tuple
Shape of the array.
itemsize : int, optional
Length of each array element, in number of characters. Default is 1.
unicode : bool, optional
Are the array elements of type unicode (True) or string (False).
Default is False.
buffer : int, optional
Memory address of the start of the array data. Default is None,
in which case a new array is created.
offset : int, optional
Fixed stride displacement from the beginning of an axis?
Default is 0. Needs to be >=0.
strides : array_like of ints, optional
Strides for the array (see `ndarray.strides` for full description).
Default is None.
order : {'C', 'F'}, optional
The order in which the array data is stored in memory: 'C' ->
"row major" order (the default), 'F' -> "column major"
(Fortran) order.
Examples
--------
>>> charar = np.chararray((3, 3))
>>> charar[:, :] = 'abc'
>>> charar
chararray([['a', 'a', 'a'],
['a', 'a', 'a'],
['a', 'a', 'a']],
dtype='|S1')
>>> charar = np.chararray(charar.shape, itemsize=5)
>>> charar[:, :] = 'abc'
>>> charar
chararray([['abc', 'abc', 'abc'],
['abc', 'abc', 'abc'],
['abc', 'abc', 'abc']],
dtype='|S5')
"""
def __new__(subtype, shape, itemsize=1, unicode=False, buffer=None,
offset=0, strides=None, order='C'):
global _globalvar
if unicode:
dtype = unicode_
else:
dtype = string_
# force itemsize to be a Python long, since using Numpy integer
# types results in itemsize.itemsize being used as the size of
# strings in the new array.
itemsize = long(itemsize)
_globalvar = 1
if buffer is None:
self = ndarray.__new__(subtype, shape, (dtype, itemsize),
order=order)
else:
self = ndarray.__new__(subtype, shape, (dtype, itemsize),
buffer=buffer,
offset=offset, strides=strides,
order=order)
_globalvar = 0
return self
def __array_finalize__(self, obj):
# The b is a special case because it is used for reconstructing.
if not _globalvar and self.dtype.char not in 'SUbc':
raise ValueError, "Can only create a chararray from string data."
def __getitem__(self, obj):
val = ndarray.__getitem__(self, obj)
if issubclass(val.dtype.type, character):
temp = val.rstrip()
if _len(temp) == 0:
val = ''
else:
val = temp
return val
# IMPLEMENTATION NOTE: Most of the methods of this class are
# direct delegations to the free functions in this module.
# However, those that return an array of strings should instead
# return a chararray, so some extra wrapping is required.
def __eq__(self, other):
"""
Return (self == other) element-wise.
See also
--------
equal
"""
return equal(self, other)
def __ne__(self, other):
"""
Return (self != other) element-wise.
See also
--------
not_equal
"""
return not_equal(self, other)
def __ge__(self, other):
"""
Return (self >= other) element-wise.
See also
--------
greater_equal
"""
return greater_equal(self, other)
def __le__(self, other):
"""
Return (self <= other) element-wise.
See also
--------
less_equal
"""
return less_equal(self, other)
def __gt__(self, other):
"""
Return (self > other) element-wise.
See also
--------
greater
"""
return greater(self, other)
def __lt__(self, other):
"""
Return (self < other) element-wise.
See also
--------
less
"""
return less(self, other)
def __add__(self, other):
"""
Return (self + other), that is string concatenation,
element-wise for a pair of array_likes of str or unicode.
See also
--------
add
"""
return asarray(add(self, other))
def __radd__(self, other):
"""
Return (other + self), that is string concatenation,
element-wise for a pair of array_likes of string_ or unicode_.
See also
--------
add
"""
return asarray(add(numpy.asarray(other), self))
def __mul__(self, i):
"""
Return (self * i), that is string multiple concatenation,
element-wise.
See also
--------
multiply
"""
return asarray(multiply(self, i))
def __rmul__(self, i):
"""
Return (self * i), that is string multiple concatenation,
element-wise.
See also
--------
multiply
"""
return asarray(multiply(self, i))
def __mod__(self, i):
"""
Return (self % i), that is pre-Python 2.6 string formatting
(iterpolation), element-wise for a pair of array_likes of string_
or unicode_.
See also
--------
mod
"""
return asarray(mod(self, i))
def __rmod__(self, other):
return NotImplemented
def argsort(self, axis=-1, kind='quicksort', order=None):
"""
Return the indices that sort the array lexicographically.
For full documentation see `numpy.argsort`, for which this method is
in fact merely a "thin wrapper."
Examples
--------
>>> c = np.array(['a1b c', '1b ca', 'b ca1', 'Ca1b'], 'S5')
>>> c = c.view(np.chararray); c
chararray(['a1b c', '1b ca', 'b ca1', 'Ca1b'],
dtype='|S5')
>>> c[c.argsort()]
chararray(['1b ca', 'Ca1b', 'a1b c', 'b ca1'],
dtype='|S5')
"""
return self.__array__().argsort(axis, kind, order)
argsort.__doc__ = ndarray.argsort.__doc__
def capitalize(self):
"""
Return a copy of `self` with only the first character of each element
capitalized.
See also
--------
char.capitalize
"""
return asarray(capitalize(self))
if sys.version_info >= (2, 4):
def center(self, width, fillchar=' '):
"""
Return a copy of `self` with its elements centered in a
string of length `width`.
See also
--------
center
"""
return asarray(center(self, width, fillchar))
else:
def center(self, width):
"""
Return a copy of `self` with its elements centered in a
string of length `width`.
See also
--------
center
"""
return asarray(center(self, width))
def count(self, sub, start=0, end=None):
"""
Returns an array with the number of non-overlapping occurrences of
substring `sub` in the range [`start`, `end`].
See also
--------
char.count
"""
return count(self, sub, start, end)
def decode(self, encoding=None, errors=None):
"""
Calls `str.decode` element-wise.
See also
--------
char.decode
"""
return decode(self, encoding, errors)
def encode(self, encoding=None, errors=None):
"""
Calls `str.encode` element-wise.
See also
--------
char.encode
"""
return encode(self, encoding, errors)
def endswith(self, suffix, start=0, end=None):
"""
Returns a boolean array which is `True` where the string element
in `self` ends with `suffix`, otherwise `False`.
See also
--------
char.endswith
"""
return endswith(self, suffix, start, end)
def expandtabs(self, tabsize=8):
"""
Return a copy of each string element where all tab characters are
replaced by one or more spaces.
See also
--------
char.expandtabs
"""
return asarray(expandtabs(self, tabsize))
def find(self, sub, start=0, end=None):
"""
For each element, return the lowest index in the string where
substring `sub` is found.
See also
--------
char.find
"""
return find(self, sub, start, end)
def index(self, sub, start=0, end=None):
"""
Like `find`, but raises `ValueError` when the substring is not found.
See also
--------
char.index
"""
return index(self, sub, start, end)
def isalnum(self):
"""
Returns true for each element if all characters in the string
are alphanumeric and there is at least one character, false
otherwise.
See also
--------
char.isalnum
"""
return isalnum(self)
def isalpha(self):
"""
Returns true for each element if all characters in the string
are alphabetic and there is at least one character, false
otherwise.
See also
--------
char.isalpha
"""
return isalpha(self)
def isdigit(self):
"""
Returns true for each element if all characters in the string are
digits and there is at least one character, false otherwise.
See also
--------
char.isdigit
"""
return isdigit(self)
def islower(self):
"""
Returns true for each element if all cased characters in the
string are lowercase and there is at least one cased character,
false otherwise.
See also
--------
char.islower
"""
return islower(self)
def isspace(self):
"""
Returns true for each element if there are only whitespace
characters in the string and there is at least one character,
false otherwise.
See also
--------
char.isspace
"""
return isspace(self)
def istitle(self):
"""
Returns true for each element if the element is a titlecased
string and there is at least one character, false otherwise.
See also
--------
char.istitle
"""
return istitle(self)
def isupper(self):
"""
Returns true for each element if all cased characters in the
string are uppercase and there is at least one character, false
otherwise.
See also
--------
char.isupper
"""
return isupper(self)
def join(self, seq):
"""
Return a string which is the concatenation of the strings in the
sequence `seq`.
See also
--------
char.join
"""
return join(self, seq)
if sys.version_info >= (2, 4):
def ljust(self, width, fillchar=' '):
"""
Return an array with the elements of `self` left-justified in a
string of length `width`.
See also
--------
char.ljust
"""
return asarray(ljust(self, width, fillchar))
else:
def ljust(self, width):
"""
Return an array with the elements of `self` left-justified in a
string of length `width`.
See also
--------
ljust
"""
return asarray(ljust(self, width))
def lower(self):
"""
Return an array with the elements of `self` converted to
lowercase.
See also
--------
char.lower
"""
return asarray(lower(self))
def lstrip(self, chars=None):
"""
For each element in `self`, return a copy with the leading characters
removed.
See also
--------
char.lstrip
"""
return asarray(lstrip(self, chars))
if sys.version_info >= (2, 5):
def partition(self, sep):
"""
Partition each element in `self` around `sep`.
See also
--------
partition
"""
return asarray(partition(self, sep))
def replace(self, old, new, count=None):
"""
For each element in `self`, return a copy of the string with all
occurrences of substring `old` replaced by `new`.
See also
--------
char.replace
"""
return asarray(replace(self, old, new, count))
def rfind(self, sub, start=0, end=None):
"""
For each element in `self`, return the highest index in the string
where substring `sub` is found, such that `sub` is contained
within [`start`, `end`].
See also
--------
char.rfind
"""
return rfind(self, sub, start, end)
def rindex(self, sub, start=0, end=None):
"""
Like `rfind`, but raises `ValueError` when the substring `sub` is
not found.
See also
--------
char.rindex
"""
return rindex(self, sub, start, end)
if sys.version_info >= (2, 4):
def rjust(self, width, fillchar=' '):
"""
Return an array with the elements of `self`
right-justified in a string of length `width`.
See also
--------
char.rjust
"""
return asarray(rjust(self, width, fillchar))
else:
def rjust(self, width):
"""
Return an array with the elements of `self`
right-justified in a string of length `width`.
See also
--------
rjust
"""
return asarray(rjust(self, width))
if sys.version_info >= (2, 5):
def rpartition(self, sep):
"""
Partition each element in `self` around `sep`.
See also
--------
rpartition
"""
return asarray(rpartition(self, sep))
if sys.version_info >= (2, 4):
def rsplit(self, sep=None, maxsplit=None):
"""
For each element in `self`, return a list of the words in
the string, using `sep` as the delimiter string.
See also
--------
char.rsplit
"""
return rsplit(self, sep, maxsplit)
def rstrip(self, chars=None):
"""
For each element in `self`, return a copy with the trailing
characters removed.
See also
--------
char.rstrip
"""
return asarray(rstrip(self, chars))
def split(self, sep=None, maxsplit=None):
"""
For each element in `self`, return a list of the words in the
string, using `sep` as the delimiter string.
See also
--------
char.split
"""
return split(self, sep, maxsplit)
def splitlines(self, keepends=None):
"""
For each element in `self`, return a list of the lines in the
element, breaking at line boundaries.
See also
--------
char.splitlines
"""
return splitlines(self, keepends)
def startswith(self, prefix, start=0, end=None):
"""
Returns a boolean array which is `True` where the string element
in `self` starts with `prefix`, otherwise `False`.
See also
--------
char.startswith
"""
return startswith(self, prefix, start, end)
def strip(self, chars=None):
"""
For each element in `self`, return a copy with the leading and
trailing characters removed.
See also
--------
char.strip
"""
return asarray(strip(self, chars))
def swapcase(self):
"""
For each element in `self`, return a copy of the string with
uppercase characters converted to lowercase and vice versa.
See also
--------
char.swapcase
"""
return asarray(swapcase(self))
def title(self):
"""
For each element in `self`, return a titlecased version of the
string: words start with uppercase characters, all remaining cased
characters are lowercase.
See also
--------
char.title
"""
return asarray(title(self))
def translate(self, table, deletechars=None):
"""
For each element in `self`, return a copy of the string where
all characters occurring in the optional argument
`deletechars` are removed, and the remaining characters have
been mapped through the given translation table.
See also
--------
char.translate
"""
return asarray(translate(self, table, deletechars))
def upper(self):
"""
Return an array with the elements of `self` converted to
uppercase.
See also
--------
char.upper
"""
return asarray(upper(self))
def zfill(self, width):
"""
Return the numeric string left-filled with zeros in a string of
length `width`.
See also
--------
char.zfill
"""
return asarray(zfill(self, width))
def isnumeric(self):
"""
For each element in `self`, return True if there are only
numeric characters in the element.
See also
--------
char.isnumeric
"""
return isnumeric(self)
def isdecimal(self):
"""
For each element in `self`, return True if there are only
decimal characters in the element.
See also
--------
char.isdecimal
"""
return isdecimal(self)
def array(obj, itemsize=None, copy=True, unicode=None, order=None):
"""
Create a `chararray`.
.. note::
This class is provided for numarray backward-compatibility.
New code (not concerned with numarray compatibility) should use
arrays of type string_ or unicode_ and use the free functions
in :mod:`numpy.char <numpy.core.defchararray>` for fast
vectorized string operations instead.
Versus a regular Numpy array of type `str` or `unicode`, this
class adds the following functionality:
1) values automatically have whitespace removed from the end
when indexed
2) comparison operators automatically remove whitespace from the
end when comparing values
3) vectorized string operations are provided as methods
(e.g. `str.endswith`) and infix operators (e.g. +, *, %)
Parameters
----------
obj : array of str or unicode-like
itemsize : int, optional
`itemsize` is the number of characters per scalar in the
resulting array. If `itemsize` is None, and `obj` is an
object array or a Python list, the `itemsize` will be
automatically determined. If `itemsize` is provided and `obj`
is of type str or unicode, then the `obj` string will be
chunked into `itemsize` pieces.
copy : bool, optional
If true (default), then the object is copied. Otherwise, a copy
will only be made if __array__ returns a copy, if obj is a
nested sequence, or if a copy is needed to satisfy any of the other
requirements (`itemsize`, unicode, `order`, etc.).
unicode : bool, optional
When true, the resulting `chararray` can contain Unicode
characters, when false only 8-bit characters. If unicode is
`None` and `obj` is one of the following:
- a `chararray`,
- an ndarray of type `str` or `unicode`
- a Python str or unicode object,
then the unicode setting of the output array will be
automatically determined.
order : {'C', 'F', 'A'}, optional
Specify the order of the array. If order is 'C' (default), then the
array will be in C-contiguous order (last-index varies the
fastest). If order is 'F', then the returned array
will be in Fortran-contiguous order (first-index varies the
fastest). If order is 'A', then the returned array may
be in any order (either C-, Fortran-contiguous, or even
discontiguous).
"""
if isinstance(obj, (str, _unicode)):
if unicode is None:
if isinstance(obj, _unicode):
unicode = True
else:
unicode = False
if itemsize is None:
itemsize = _len(obj)
shape = _len(obj) / itemsize
if unicode:
if sys.maxunicode == 0xffff:
# On a narrow Python build, the buffer for Unicode
# strings is UCS2, which doesn't match the buffer for
# Numpy Unicode types, which is ALWAYS UCS4.
# Therefore, we need to convert the buffer. On Python
# 2.6 and later, we can use the utf_32 codec. Earlier
# versions don't have that codec, so we convert to a
# numerical array that matches the input buffer, and
# then use Numpy to convert it to UCS4. All of this
# should happen in native endianness.
if sys.hexversion >= 0x2060000:
obj = obj.encode('utf_32')
else:
if isinstance(obj, str):
ascii = numpy.frombuffer(obj, 'u1')
ucs4 = numpy.array(ascii, 'u4')
obj = ucs4.data
else:
ucs2 = numpy.frombuffer(obj, 'u2')
ucs4 = numpy.array(ucs2, 'u4')
obj = ucs4.data
else:
obj = _unicode(obj)
else:
# Let the default Unicode -> string encoding (if any) take
# precedence.
obj = str(obj)
return chararray(shape, itemsize=itemsize, unicode=unicode,
buffer=obj, order=order)
if isinstance(obj, (list, tuple)):
obj = numpy.asarray(obj)
if isinstance(obj, ndarray) and issubclass(obj.dtype.type, character):
# If we just have a vanilla chararray, create a chararray
# view around it.
if not isinstance(obj, chararray):
obj = obj.view(chararray)
if itemsize is None:
itemsize = obj.itemsize
# itemsize is in 8-bit chars, so for Unicode, we need
# to divide by the size of a single Unicode character,
# which for Numpy is always 4
if issubclass(obj.dtype.type, unicode_):
itemsize /= 4
if unicode is None:
if issubclass(obj.dtype.type, unicode_):
unicode = True
else:
unicode = False
if unicode:
dtype = unicode_
else:
dtype = string_
if order is not None:
obj = numpy.asarray(obj, order=order)
if (copy
or (itemsize != obj.itemsize)
or (not unicode and isinstance(obj, unicode_))
or (unicode and isinstance(obj, string_))):
obj = obj.astype((dtype, long(itemsize)))
return obj
if isinstance(obj, ndarray) and issubclass(obj.dtype.type, object):
if itemsize is None:
# Since no itemsize was specified, convert the input array to
# a list so the ndarray constructor will automatically
# determine the itemsize for us.
obj = obj.tolist()
# Fall through to the default case
if unicode:
dtype = unicode_
else:
dtype = string_
if itemsize is None:
val = narray(obj, dtype=dtype, order=order, subok=True)
else:
val = narray(obj, dtype=(dtype, itemsize), order=order, subok=True)
return val.view(chararray)
def asarray(obj, itemsize=None, unicode=None, order=None):
"""
Convert the input to a `chararray`, copying the data only if
necessary.
Versus a regular Numpy array of type `str` or `unicode`, this
class adds the following functionality:
1) values automatically have whitespace removed from the end
when indexed
2) comparison operators automatically remove whitespace from the
end when comparing values
3) vectorized string operations are provided as methods
(e.g. `str.endswith`) and infix operators (e.g. +, *, %)
Parameters
----------
obj : array of str or unicode-like
itemsize : int, optional
`itemsize` is the number of characters per scalar in the
resulting array. If `itemsize` is None, and `obj` is an
object array or a Python list, the `itemsize` will be
automatically determined. If `itemsize` is provided and `obj`
is of type str or unicode, then the `obj` string will be
chunked into `itemsize` pieces.
unicode : bool, optional
When true, the resulting `chararray` can contain Unicode
characters, when false only 8-bit characters. If unicode is
`None` and `obj` is one of the following:
- a `chararray`,
- an ndarray of type `str` or 'unicode`
- a Python str or unicode object,
then the unicode setting of the output array will be
automatically determined.
order : {'C', 'F'}, optional
Specify the order of the array. If order is 'C' (default), then the
array will be in C-contiguous order (last-index varies the
fastest). If order is 'F', then the returned array
will be in Fortran-contiguous order (first-index varies the
fastest).
"""
return array(obj, itemsize, copy=False,
unicode=unicode, order=order)
|