diff options
Diffstat (limited to 'numpy')
| -rw-r--r-- | numpy/core/_string_helpers.py | 100 | ||||
| -rw-r--r-- | numpy/core/numerictypes.py | 102 |
2 files changed, 105 insertions, 97 deletions
diff --git a/numpy/core/_string_helpers.py b/numpy/core/_string_helpers.py new file mode 100644 index 000000000..45e6a739e --- /dev/null +++ b/numpy/core/_string_helpers.py @@ -0,0 +1,100 @@ +""" +String-handling utilities to avoid locale-dependence. + +Used primarily to generate type name aliases. +""" +# "import string" is costly to import! +# Construct the translation tables directly +# "A" = chr(65), "a" = chr(97) +_all_chars = [chr(_m) for _m in range(256)] +_ascii_upper = _all_chars[65:65+26] +_ascii_lower = _all_chars[97:97+26] +LOWER_TABLE = "".join(_all_chars[:65] + _ascii_lower + _all_chars[65+26:]) +UPPER_TABLE = "".join(_all_chars[:97] + _ascii_upper + _all_chars[97+26:]) + + +def english_lower(s): + """ Apply English case rules to convert ASCII strings to all lower case. + + This is an internal utility function to replace calls to str.lower() such + that we can avoid changing behavior with changing locales. In particular, + Turkish has distinct dotted and dotless variants of the Latin letter "I" in + both lowercase and uppercase. Thus, "I".lower() != "i" in a "tr" locale. + + Parameters + ---------- + s : str + + Returns + ------- + lowered : str + + Examples + -------- + >>> from numpy.core.numerictypes import english_lower + >>> english_lower('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_') + 'abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz0123456789_' + >>> english_lower('') + '' + """ + lowered = s.translate(LOWER_TABLE) + return lowered + + +def english_upper(s): + """ Apply English case rules to convert ASCII strings to all upper case. + + This is an internal utility function to replace calls to str.upper() such + that we can avoid changing behavior with changing locales. In particular, + Turkish has distinct dotted and dotless variants of the Latin letter "I" in + both lowercase and uppercase. Thus, "i".upper() != "I" in a "tr" locale. + + Parameters + ---------- + s : str + + Returns + ------- + uppered : str + + Examples + -------- + >>> from numpy.core.numerictypes import english_upper + >>> english_upper('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_') + 'ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_' + >>> english_upper('') + '' + """ + uppered = s.translate(UPPER_TABLE) + return uppered + + +def english_capitalize(s): + """ Apply English case rules to convert the first character of an ASCII + string to upper case. + + This is an internal utility function to replace calls to str.capitalize() + such that we can avoid changing behavior with changing locales. + + Parameters + ---------- + s : str + + Returns + ------- + capitalized : str + + Examples + -------- + >>> from numpy.core.numerictypes import english_capitalize + >>> english_capitalize('int8') + 'Int8' + >>> english_capitalize('Int8') + 'Int8' + >>> english_capitalize('') + '' + """ + if s: + return english_upper(s[0]) + s[1:] + else: + return s diff --git a/numpy/core/numerictypes.py b/numpy/core/numerictypes.py index 259aef2c6..1cb32a0ec 100644 --- a/numpy/core/numerictypes.py +++ b/numpy/core/numerictypes.py @@ -102,6 +102,11 @@ __all__ = ['sctypeDict', 'sctypeNA', 'typeDict', 'typeNA', 'sctypes', 'busday_offset', 'busday_count', 'is_busday', 'busdaycalendar', ] +# we don't need all these imports, but we need to keep them for compatibility +# for users using np.core.numerictypes.UPPER_TABLE +from ._string_helpers import ( + english_lower, english_upper, english_capitalize, LOWER_TABLE, UPPER_TABLE +) # we don't export these for import *, but we do want them accessible # as numerictypes.bool, etc. @@ -112,103 +117,6 @@ else: from __builtin__ import bool, int, float, complex, object, unicode, str -# String-handling utilities to avoid locale-dependence. - -# "import string" is costly to import! -# Construct the translation tables directly -# "A" = chr(65), "a" = chr(97) -_all_chars = [chr(_m) for _m in range(256)] -_ascii_upper = _all_chars[65:65+26] -_ascii_lower = _all_chars[97:97+26] -LOWER_TABLE = "".join(_all_chars[:65] + _ascii_lower + _all_chars[65+26:]) -UPPER_TABLE = "".join(_all_chars[:97] + _ascii_upper + _all_chars[97+26:]) - - -def english_lower(s): - """ Apply English case rules to convert ASCII strings to all lower case. - - This is an internal utility function to replace calls to str.lower() such - that we can avoid changing behavior with changing locales. In particular, - Turkish has distinct dotted and dotless variants of the Latin letter "I" in - both lowercase and uppercase. Thus, "I".lower() != "i" in a "tr" locale. - - Parameters - ---------- - s : str - - Returns - ------- - lowered : str - - Examples - -------- - >>> from numpy.core.numerictypes import english_lower - >>> english_lower('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_') - 'abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz0123456789_' - >>> english_lower('') - '' - """ - lowered = s.translate(LOWER_TABLE) - return lowered - -def english_upper(s): - """ Apply English case rules to convert ASCII strings to all upper case. - - This is an internal utility function to replace calls to str.upper() such - that we can avoid changing behavior with changing locales. In particular, - Turkish has distinct dotted and dotless variants of the Latin letter "I" in - both lowercase and uppercase. Thus, "i".upper() != "I" in a "tr" locale. - - Parameters - ---------- - s : str - - Returns - ------- - uppered : str - - Examples - -------- - >>> from numpy.core.numerictypes import english_upper - >>> english_upper('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_') - 'ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789_' - >>> english_upper('') - '' - """ - uppered = s.translate(UPPER_TABLE) - return uppered - -def english_capitalize(s): - """ Apply English case rules to convert the first character of an ASCII - string to upper case. - - This is an internal utility function to replace calls to str.capitalize() - such that we can avoid changing behavior with changing locales. - - Parameters - ---------- - s : str - - Returns - ------- - capitalized : str - - Examples - -------- - >>> from numpy.core.numerictypes import english_capitalize - >>> english_capitalize('int8') - 'Int8' - >>> english_capitalize('Int8') - 'Int8' - >>> english_capitalize('') - '' - """ - if s: - return english_upper(s[0]) + s[1:] - else: - return s - - sctypeDict = {} # Contains all leaf-node scalar types with aliases class TypeNADict(dict): def __getitem__(self, key): |