def load_test_data(f, optsplit=[]):
testRe1 = re.compile(
r"^÷\s+([^\s].*[^\s])\s+÷\s+#\s+÷\s+\[0.2\].*?([÷×].*)\s+÷\s+\[0.3\]\s*$"
)
unicode.fetch(f)
data = []
for line in fileinput.input(os.path.basename(f)):
# lines that include a test start with the ÷ character
if len(line) < 2 or not line.startswith('÷'):
continue
m = testRe1.match(line)
if not m:
print("error: no match on line where test was expected: %s" % line)
continue
# process the characters in this test case
chars = process_split_string(m.group(1))
# skip test case if it contains invalid characters (viz., surrogates)
if not chars:
continue
# now process test cases
(chars, info) = process_split_info(m.group(2), chars, optsplit)
# make sure that we have break info for each break!
assert len(chars) - 1 == len(info)
data.append((chars, info))
return data
def load_test_data(f, optsplit=[]):
outls = []
testRe1 = re.compile("^÷\s+([^\s].*[^\s])\s+÷\s+#\s+÷\s+\[0.2\].*?([÷×].*)\s+÷\s+\[0.3\]\s*$")
unicode.fetch(f)
data = []
for line in fileinput.input(os.path.basename(f)):
# lines that include a test start with the ÷ character
if len(line) < 2 or line[0:2] != '÷':
continue
m = testRe1.match(line)
if not m:
print "error: no match on line where test was expected: %s" % line
continue
# process the characters in this test case
chars = process_split_string(m.group(1))
# skip test case if it contains invalid characters (viz., surrogates)
if not chars:
continue
# now process test cases
(chars, info) = process_split_info(m.group(2), chars, optsplit)
# make sure that we have break info for each break!
assert len(chars) - 1 == len(info)
outls.append((chars, info))
return outls
def load_test_data(f):
outls = []
testRe = re.compile("^(.*?);(.*?);(.*?);(.*?);(.*?);\s+#.*$")
unicode.fetch(f)
for line in fileinput.input(os.path.basename(f)):
# comment and header lines start with # and @ respectively
if len(line) < 1 or line[0:1] == '#' or line[0:1] == '@':
continue
m = testRe.match(line)
groups = []
if not m:
print "error: no match on line where test was expected: %s" % line
continue
has_surrogates = False
for i in range(1, 6):
group = []
chs = m.group(i).split()
for ch in chs:
intch = int(ch, 16)
if unicode.is_surrogate(intch):
has_surrogates = True
break
group.append(intch)
if has_surrogates:
break
groups.append(group)
if has_surrogates:
continue
outls.append(groups)
return outls
def load_test_data(f):
outls = []
testRe = re.compile("^(.*?);(.*?);(.*?);(.*?);(.*?);\s+#.*$")
unicode.fetch(f)
for line in fileinput.input(os.path.basename(f)):
# comment and header lines start with # and @ respectively
if len(line) < 1 or line[0:1] == "#" or line[0:1] == "@":
continue
m = testRe.match(line)
groups = []
if not m:
print "error: no match on line where test was expected: %s" % line
continue
has_surrogates = False
for i in range(1, 6):
group = []
chs = m.group(i).split()
for ch in chs:
intch = int(ch, 16)
if unicode.is_surrogate(intch):
has_surrogates = True
break
group.append(intch)
if has_surrogates:
break
groups.append(group)
if has_surrogates:
continue
outls.append(groups)
return outls
