Unpack the string at grapheme boundaries instead of codepoint boundaries
# File activesupport/lib/active_support/multibyte/handlers/utf8_handler.rb, line 307
def g_unpack(str)
codepoints = u_unpack(str)
unpacked = []
pos = 0
marker = 0
eoc = codepoints.length
while(pos < eoc)
pos += 1
previous = codepoints[pos-1]
current = codepoints[pos]
if (
# CR X LF
one = ( previous == UCD.boundary[:cr] and current == UCD.boundary[:lf] ) or
# L X (L|V|LV|LVT)
two = ( UCD.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) ) or
# (LV|V) X (V|T)
three = ( in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) ) or
# (LVT|T) X (T)
four = ( in_char_class?(previous, [:lvt,:t]) and UCD.boundary[:t] === current ) or
# X Extend
five = (UCD.boundary[:extend] === current)
)
else
unpacked << codepoints[marker..pos-1]
marker = pos
end
end
unpacked
end
