def contract_rosetta_escapes(text):
"""Replace Rosetta escape sequences with the real characters."""
return helpers.text_replaced(text, {'[tab]': '\t',
r'\[tab]': '[tab]',
'[nbsp]': u'\u00a0',
r'\[nbsp]': '[nbsp]',
'[nnbsp]': u'\u202f',
r'\[nnbsp]': '[nnbsp]'})
def expand_rosetta_escapes(unicode_text):
"""Replace characters needing a Rosetta escape sequences."""
escapes = {u'\t': TranslationConstants.TAB_CHAR,
u'[tab]': TranslationConstants.TAB_CHAR_ESCAPED,
u'\u00a0': TranslationConstants.NO_BREAK_SPACE_CHAR,
u'[nbsp]': TranslationConstants.NO_BREAK_SPACE_CHAR_ESCAPED,
u'\u202f': TranslationConstants.NARROW_NO_BREAK_SPACE_CHAR,
u'[nnbsp]':
TranslationConstants.NARROW_NO_BREAK_SPACE_CHAR_ESCAPED}
return helpers.text_replaced(unicode_text, escapes)
def convert_newlines_to_web_form(unicode_text):
"""Convert Unicode string to CR/LF line endings as used in web forms.
Any style of line endings is accepted: MacOS-style CR, MS-DOS-style
CR/LF, or rest-of-world-style LF.
"""
if unicode_text is None:
return None
assert isinstance(unicode_text, unicode), (
"The given text must be unicode instead of %s" % type(unicode_text))
if unicode_text is None:
return None
elif u'\r\n' in unicode_text:
# The text is already using the windows newline chars
return unicode_text
elif u'\n' in unicode_text:
return helpers.text_replaced(unicode_text, {u'\n': u'\r\n'})
else:
return helpers.text_replaced(unicode_text, {u'\r': u'\r\n'})
