def prepare(A_list, B_list):
A = NumberSet()
B = NumberSet()
for begin, end in A_list:
A.add_interval(Interval(begin, end))
for begin, end in B_list:
B.add_interval(Interval(begin, end))
A.assert_consistency()
B.assert_consistency()
return A, B
def verify(A, TrafoInfo):
result = NumberSet()
for interval in A.get_intervals():
for x in range(interval.begin, interval.end):
for source_begin, source_end, target_begin in TrafoInfo:
if x >= source_begin and x < source_end:
offset = x - source_begin
y = target_begin + offset
result.add_interval(Interval(y))
result.assert_consistency()
return result
def verify(A, TrafoInfo):
result = NumberSet()
for interval in A.get_intervals():
for x in range(interval.begin, interval.end):
for source_begin, source_end, target_begin in TrafoInfo:
if x >= source_begin and x < source_end:
offset = x - source_begin
y = target_begin + offset
result.add_interval(Interval(y))
result.assert_consistency()
return result
def prepare(A_list, B_list):
A = NumberSet()
B = NumberSet()
for begin, end in A_list:
A.add_interval(Interval(begin, end))
for begin, end in B_list:
B.add_interval(Interval(begin, end))
A.assert_consistency()
B.assert_consistency()
return A, B
class Tracker:
def __init__(self):
self.match_set = NumberSet()
self.negation_f = False
def consider_interval(self, Begin, End):
if Begin > End:
raise RegularExpressionException("Character range: '-' requires character with 'lower code' to preceed\n" + \
"found range '%s-%s' which corresponds to %i-%i as unicode code points." % \
(utf8.map_unicode_to_utf8(Begin), utf8.map_unicode_to_utf8(End), Begin, End))
self.match_set.add_interval(Interval(Begin, End))
def consider_letter(self, CharCode):
self.consider_interval(CharCode, CharCode + 1)
class Tracker:
def __init__(self):
self.match_set = NumberSet()
self.negation_f = False
def consider_interval(self, Begin, End):
if Begin > End:
raise RegularExpressionException("Character range: '-' requires character with 'lower code' to preceed\n" + \
"found range '%s-%s' which corresponds to %i-%i as unicode code points." % \
(utf8.map_unicode_to_utf8(Begin), utf8.map_unicode_to_utf8(End), Begin, End))
self.match_set.add_interval(Interval(Begin, End))
def consider_letter(self, CharCode):
self.consider_interval(CharCode, CharCode+1)
def do(section_list, fh):
"""Parses a codec information file. The described codec can only be
a 'static character length' encoding. That is every character in the
code occupies the same number of bytes.
RETURNS: [0] Set of characters in unicode which are covered by the
described codec.
[1] Range of values in the codec elements.
"""
source_set = NumberSet()
drain_set = NumberSet()
error_str = None
try:
while error_str is None:
skip_whitespace(fh)
source_begin = read_integer(fh)
if source_begin is None:
error_str = "Missing integer (source interval begin) in codec file."
continue
skip_whitespace(fh)
source_size = read_integer(fh)
if source_size is None:
error_str = "Missing integer (source interval size) in codec file."
continue
skip_whitespace(fh)
target_begin = read_integer(fh)
if target_begin is None:
error_str = "Missing integer (target interval begin) in codec file."
continue
source_end = source_begin + source_size
list.append(section_list, [source_begin, source_end, target_begin])
source_set.add_interval(Interval(source_begin, source_end))
drain_set.add_interval(
Interval(target_begin, target_begin + source_size))
except EndOfStreamException:
pass
return source_set, drain_set, error_str
def do(section_list, fh):
"""Parses a codec information file. The described codec can only be
a 'static character length' encoding. That is every character in the
code occupies the same number of bytes.
RETURNS: [0] Set of characters in unicode which are covered by the
described codec.
[1] Range of values in the codec elements.
"""
source_set = NumberSet()
drain_set = NumberSet()
error_str = None
try:
while error_str is None:
skip_whitespace(fh)
source_begin = read_integer(fh)
if source_begin is None:
error_str = "Missing integer (source interval begin) in codec file."
continue
skip_whitespace(fh)
source_size = read_integer(fh)
if source_size is None:
error_str = "Missing integer (source interval size) in codec file."
continue
skip_whitespace(fh)
target_begin = read_integer(fh)
if target_begin is None:
error_str = "Missing integer (target interval begin) in codec file."
continue
source_end = source_begin + source_size
list.append(section_list, [source_begin, source_end, target_begin])
source_set.add_interval(Interval(source_begin, source_end))
drain_set.add_interval(Interval(target_begin, target_begin + source_size))
except EndOfStreamException:
pass
return source_set, drain_set, error_str
