1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304
|
# -*- coding -*-
"""
Provides some command utility functions.
TODO:
matcher that ignores empty lines and whitespace and has contains comparison
"""
from __future__ import absolute_import, print_function
from hamcrest import assert_that, is_not, equal_to, contains_string
# DISABLED: from behave4cmd.hamcrest_text import matches_regexp
import codecs
DEBUG = False
# -----------------------------------------------------------------------------
# CLASS: TextProxy
# -----------------------------------------------------------------------------
# class TextProxy(object):
# """
# Simplifies conversion between (Unicode) string and its byte representation.
# Provides a ValueObject to store a string or its byte representation.
# Afterwards you can explicitly access both representations by using:
#
# EXAMPLE:
#
# .. testcode::
#
# from behave4cmd.textutil import TextProxy
# message = TextProxy("Hello world", encoding="UTF-8")
# assert message.data == "Hello world" # -- RAW DATA access.
# assert isinstance(message.text, basestring)
# assert isinstance(message.bytes, bytes)
# assert message == "Hello world"
# assert len(message) == len(message.data) == 11
# """
# encoding_errors = "strict"
# default_encoding = "UTF-8"
#
# def __init__(self, data=None, encoding=None, errors=None):
# self.encoding = encoding or self.default_encoding
# self.errors = errors or self.encoding_errors
# self.set(data)
#
# def get(self):
# return self.data
#
# def set(self, data):
# self.data = data or ""
# self._text = None
# self._bytes = None
#
# def clear(self):
# self.set(None)
#
# @property
# def text(self):
# """Provide access to string-representation of the data."""
# if self._text is None:
# if isinstance(self.data, basestring):
# _text = self.data
# elif isinstance(self.data, bytes):
# _text = codecs.decode(self.data, self.encoding, self.errors)
# else:
# _text = str(self.data)
# self._text = _text
# assert isinstance(self._text, basestring)
# return self._text
#
# @property
# def bytes(self):
# """Provide access to byte-representation of the data."""
# if self._bytes is None:
# if isinstance(self.data, bytes) and not isinstance(self.data, str):
# self._bytes = self.data
# else:
# text = self.data
# if not isinstance(text, basestring):
# text = unicode(text)
# assert isinstance(text, basestring)
# self._bytes = codecs.encode(text, self.encoding, self.errors)
# assert isinstance(self._bytes, bytes)
# return self._bytes
#
# def __repr__(self):
# """Textual representation of this object."""
# data = self.data or ""
# prefix = ""
# if isinstance(data, bytes) and not isinstance(data, basestring):
# prefix= u"b"
# # str(self.text)
# # str(self.encoding)
# # str(prefix)
# # _ = u"<TextProxy data[size=%d]=x'x', encoding=x>" % len(self)
# # _ = u"<TextProxy data[size=x]=%s'x', encoding=x>" % prefix
# # _ = u"<TextProxy data[size=x]=x'%s', encoding=x>" % self.text
# # _ = u"<TextProxy data[size=x]=x'x', encoding=%s>" % self.encoding
# return u"<TextProxy data[size=%d]=%s'%s', encoding=%s>" %\
# (len(self), prefix, self.text, self.encoding)
#
# def __str__(self):
# """Conversion into str() object."""
# return self.text
#
# def __bytes__(self):
# """Conversion into bytes() object."""
# return self.bytes
#
# def __bool__(self):
# """Conversion into a bool value, used for truth testing."""
# return bool(self.data)
#
# def __iter__(self):
# """Conversion into an iterator."""
# return iter(self.data)
#
# def __contains__(self, item):
# """Check if item is contained in raw data."""
# if isinstance(item, basestring):
# return item in self.text
# elif isinstance(item, bytes):
# return item in self.bytes
# else:
# return item in self.data
#
# def __len__(self):
# if self.data is None:
# return 0
# return len(self.data)
#
# def __nonzero__(self):
# return len(self) > 0
#
# def __eq__(self, other):
# if isinstance(other, basestring):
# return self.text == other
# elif isinstance(other, bytes):
# return self.bytes == other
# else:
# return self.data == other
#
# def __ne__(self, other):
# return not (self == other)
#
# -----------------------------------------------------------------------------
# UTILITY FUNCTIONS:
# -----------------------------------------------------------------------------
def template_substitute(text, **kwargs):
"""
Replace placeholders in text by using the data mapping.
Other placeholders that is not represented by data is left untouched.
:param text: Text to search and replace placeholders.
:param data: Data mapping/dict for placeholder key and values.
:return: Potentially modified text with replaced placeholders.
"""
for name, value in kwargs.items():
placeholder_pattern = "{%s}" % name
if placeholder_pattern in text:
text = text.replace(placeholder_pattern, value)
return text
def text_remove_empty_lines(text):
"""
Whitespace normalization:
- Strip empty lines
- Strip trailing whitespace
"""
lines = [ line.rstrip() for line in text.splitlines() if line.strip() ]
return "\n".join(lines)
def text_normalize(text):
"""
Whitespace normalization:
- Strip empty lines
- Strip leading whitespace in a line
- Strip trailing whitespace in a line
- Normalize line endings
"""
# if not isinstance(text, str):
if isinstance(text, bytes):
# -- MAYBE: command.ouput => bytes, encoded stream output.
text = codecs.decode(text)
lines = [ line.strip() for line in text.splitlines() if line.strip() ]
return "\n".join(lines)
# -----------------------------------------------------------------------------
# ASSERTIONS:
# -----------------------------------------------------------------------------
from hamcrest.library.text.substringmatcher import SubstringMatcher
from hamcrest.core.helpers.hasmethod import hasmethod
class StringContainsMultipleTimes(SubstringMatcher):
def __init__(self, substring, expected_count):
super(StringContainsMultipleTimes, self).__init__(substring)
self.expected_count = expected_count
self.actual_count = 0
def describe_to(self, description):
description.append_text('a string ') \
.append_text(self.relationship()) \
.append_text(" ") \
.append_description_of(self.substring) \
.append_text(" ") \
.append_description_of(self.expected_count) \
.append_text(" times instead of ") \
.append_description_of(self.actual_count)
def _matches(self, item):
if not hasmethod(item, "count"):
return False
self.actual_count = item.count(self.substring)
return self.actual_count == self.expected_count
def relationship(self):
return "containing"
def contains_substring_multiple_times(substring, expected_count):
return StringContainsMultipleTimes(substring, expected_count)
# -----------------------------------------------------------------------------
# ASSERTIONS:
# -----------------------------------------------------------------------------
def assert_text_should_equal(actual_text, expected_text):
assert_that(actual_text, equal_to(expected_text))
def assert_text_should_not_equal(actual_text, expected_text):
assert_that(actual_text, is_not(equal_to(expected_text)))
def assert_text_should_contain_exactly(text, expected_part):
assert_that(text, contains_string(expected_part))
def assert_text_should_not_contain_exactly(text, expected_part):
assert_that(text, is_not(contains_string(expected_part)))
def assert_text_should_contain(text, expected_part):
assert_that(text, contains_string(expected_part))
def assert_normtext_should_contain_multiple_times(text, expected_text, count):
assert_that(text, contains_substring_multiple_times(expected_text, count))
def assert_text_should_not_contain(text, unexpected_part):
assert_that(text, is_not(contains_string(unexpected_part)))
def assert_normtext_should_equal(actual_text, expected_text):
expected_text2 = text_normalize(expected_text.strip())
actual_text2 = text_normalize(actual_text.strip())
assert_that(actual_text2, equal_to(expected_text2))
def assert_normtext_should_not_equal(actual_text, expected_text):
expected_text2 = text_normalize(expected_text.strip())
actual_text2 = text_normalize(actual_text.strip())
assert_that(actual_text2, is_not(equal_to(expected_text2)))
def assert_normtext_should_contain(text, expected_part):
expected_part2 = text_normalize(expected_part)
actual_text = text_normalize(text.strip())
if DEBUG:
print("expected:\n{0}".format(expected_part2))
print("actual:\n{0}".format(actual_text))
assert_text_should_contain(actual_text, expected_part2)
def assert_normtext_should_not_contain(text, unexpected_part):
unexpected_part2 = text_normalize(unexpected_part)
actual_text = text_normalize(text.strip())
if DEBUG:
print("expected:\n{0}".format(unexpected_part2))
print("actual:\n{0}".format(actual_text))
assert_text_should_not_contain(actual_text, unexpected_part2)
# def assert_text_should_match_pattern(text, pattern):
# """
# Assert that the :attr:`text` matches the regular expression :attr:`pattern`.
#
# :param text: Multi-line text (as string).
# :param pattern: Regular expression pattern (as string, compiled regexp).
# :raise: AssertionError, if text matches not the pattern.
# """
# assert_that(text, matches_regexp(pattern))
#
# def assert_text_should_not_match_pattern(text, pattern):
# """
# Assert that the :attr:`text` matches not the regular expression
# :attr:`pattern`.
#
# :param text: Multi-line text (as string).
# :param pattern: Regular expression pattern (as string, compiled regexp).
# :raise: AssertionError, if text matches the pattern.
# """
# assert_that(text, is_not(matches_regexp(pattern)))
#
# -----------------------------------------------------------------------------
# MAIN:
# -----------------------------------------------------------------------------
if __name__ == "__main__":
import doctest
doctest.testmod()
|