def isWordBreakAfter(glyphNames, index, reversedCMAP):
"""
Returns a boolean declaring if the position
after index can be considered a word break.
"""
# End of line
if index == len(glyphNames) - 1:
return True
# get the unicode values and word break properties
# for the previous, current and next two glyphs.
unicodeValue = reversedCMAP.get(glyphNames[index], [None])[0]
wordBreakProperty = wordBreakProperties.get(unicodeValue)
forwardOneUnicodeValue = reversedCMAP.get(glyphNames[index + 1], [None])[0]
forwardOneWordBreakProperty = wordBreakProperties.get(
forwardOneUnicodeValue)
if index > 0:
backOneUnicodeValue = reversedCMAP.get(glyphNames[index - 1],
[None])[0]
backOneWordBreakProperty = wordBreakProperties.get(backOneUnicodeValue)
else:
backOneUnicodeValue = None
backOneWordBreakProperty = None
if index < len(glyphNames) - 2:
forwardTwoUnicodeValue = reversedCMAP.get(glyphNames[index + 2],
[None])[0]
forwardTwoWordBreakProperty = wordBreakProperties.get(
forwardTwoUnicodeValue)
else:
forwardTwoUnicodeValue = None
forwardTwoWordBreakProperty = None
# test the current and next unicode values
if (unicodeValue, forwardOneUnicodeValue) in _notBreakAfter:
return False
# test the current and next word break properties
if (wordBreakProperty, forwardOneWordBreakProperty) in _notBreakAfter:
return False
# test the previous, current and next word break properties
if (backOneWordBreakProperty, wordBreakProperty,
forwardOneWordBreakProperty) in _notBreakAfter:
return False
# test the current and next two word break properties
if (wordBreakProperty, forwardOneWordBreakProperty,
forwardTwoWordBreakProperty) in _notBreakAfter:
return False
# Otherwise, break everywhere (including around ideographs).
return True
def isWordBreakBefore(glyphNames, index, reversedCMAP):
"""
Returns a boolean declaring if the position
before index can be considered a word break.
"""
# Start of line
if index == 0:
return True
# get the unicode values and word break properties
# for the previous two, current and next glyphs.
unicodeValue = reversedCMAP.get(glyphNames[index], [None])[0]
wordBreakProperty = wordBreakProperties.get(unicodeValue)
backOneUnicodeValue = reversedCMAP.get(glyphNames[index - 1], [None])[0]
backOneWordBreakProperty = wordBreakProperties.get(backOneUnicodeValue)
if index > 1:
backTwoUnicodeValue = reversedCMAP.get(glyphNames[index - 2],
[None])[0]
backTwoWordBreakProperty = wordBreakProperties.get(backTwoUnicodeValue)
else:
backTwoUnicodeValue = False
backTwoWordBreakProperty = False
if index < len(glyphNames) - 1:
forwardOneUnicodeValue = reversedCMAP.get(glyphNames[index + 1],
[None])[0]
forwardOneWordBreakProperty = wordBreakProperties.get(
forwardOneUnicodeValue)
else:
forwardOneUnicodeValue = None
forwardOneWordBreakProperty = None
# test the previous and current unicode values
if (backOneUnicodeValue, unicodeValue) in _notBreakBefore:
return False
# test the previous and current word break properties
if (backOneWordBreakProperty, wordBreakProperty) in _notBreakBefore:
return False
# test the previous, current and next word break properties
if (backOneWordBreakProperty, wordBreakProperty,
forwardOneWordBreakProperty) in _notBreakBefore:
return False
# test the previous, current and next word break properties
if (backTwoWordBreakProperty, backOneWordBreakProperty,
wordBreakProperty) in _notBreakBefore:
return False
# Otherwise, break everywhere (including around ideographs).
return True
def isWordBreakAfter(glyphNames, index, reversedCMAP):
"""
Returns a boolean declaring if the position
after index can be considered a word break.
"""
# End of line
if index == len(glyphNames) - 1:
return True
# get the unicode values and word break properties
# for the previous, current and next two glyphs.
unicodeValue = reversedCMAP.get(glyphNames[index], [None])[0]
wordBreakProperty = wordBreakProperties.get(unicodeValue)
forwardOneUnicodeValue = reversedCMAP.get(glyphNames[index + 1], [None])[0]
forwardOneWordBreakProperty = wordBreakProperties.get(forwardOneUnicodeValue)
if index > 0:
backOneUnicodeValue = reversedCMAP.get(glyphNames[index - 1], [None])[0]
backOneWordBreakProperty = wordBreakProperties.get(backOneUnicodeValue)
else:
backOneUnicodeValue = None
backOneWordBreakProperty = None
if index < len(glyphNames) - 2:
forwardTwoUnicodeValue = reversedCMAP.get(glyphNames[index + 2], [None])[0]
forwardTwoWordBreakProperty = wordBreakProperties.get(forwardTwoUnicodeValue)
else:
forwardTwoUnicodeValue = None
forwardTwoWordBreakProperty = None
# test the current and next unicode values
if (unicodeValue, forwardOneUnicodeValue) in _notBreakAfter:
return False
# test the current and next word break properties
if (wordBreakProperty, forwardOneWordBreakProperty) in _notBreakAfter:
return False
# test the previous, current and next word break properties
if (backOneWordBreakProperty, wordBreakProperty, forwardOneWordBreakProperty) in _notBreakAfter:
return False
# test the current and next two word break properties
if (wordBreakProperty, forwardOneWordBreakProperty, forwardTwoWordBreakProperty) in _notBreakAfter:
return False
# Otherwise, break everywhere (including around ideographs).
return True
def isWordBreakBefore(glyphNames, index, reversedCMAP):
"""
Returns a boolean declaring if the position
before index can be considered a word break.
"""
# Start of line
if index == 0:
return True
# get the unicode values and word break properties
# for the previous two, current and next glyphs.
unicodeValue = reversedCMAP.get(glyphNames[index], [None])[0]
wordBreakProperty = wordBreakProperties.get(unicodeValue)
backOneUnicodeValue = reversedCMAP.get(glyphNames[index - 1], [None])[0]
backOneWordBreakProperty = wordBreakProperties.get(backOneUnicodeValue)
if index > 1:
backTwoUnicodeValue = reversedCMAP.get(glyphNames[index - 2], [None])[0]
backTwoWordBreakProperty = wordBreakProperties.get(backTwoUnicodeValue)
else:
backTwoUnicodeValue = False
backTwoWordBreakProperty = False
if index < len(glyphNames) - 1:
forwardOneUnicodeValue = reversedCMAP.get(glyphNames[index + 1], [None])[0]
forwardOneWordBreakProperty = wordBreakProperties.get(forwardOneUnicodeValue)
else:
forwardOneUnicodeValue = None
forwardOneWordBreakProperty = None
# test the previous and current unicode values
if (backOneUnicodeValue, unicodeValue) in _notBreakBefore:
return False
# test the previous and current word break properties
if (backOneWordBreakProperty, wordBreakProperty) in _notBreakBefore:
return False
# test the previous, current and next word break properties
if (backOneWordBreakProperty, wordBreakProperty, forwardOneWordBreakProperty) in _notBreakBefore:
return False
# test the previous, current and next word break properties
if (backTwoWordBreakProperty, backOneWordBreakProperty, wordBreakProperty) in _notBreakBefore:
return False
# Otherwise, break everywhere (including around ideographs).
return True