diff -pruN mozc-2.23.2815.102.orig/base/gen_character_set.py mozc-2.23.2815.102/base/gen_character_set.py
--- mozc-2.23.2815.102.orig/base/gen_character_set.py 2019-08-02 14:22:24.490255547 +0900
+++ mozc-2.23.2815.102/base/gen_character_set.py 2019-08-01 21:53:12.997788806 +0900
@@ -250,7 +250,7 @@ def GenerateCategoryBitmap(category_list
# (at most) four code points.
bit_list = []
for _, group in itertools.groupby(enumerate(category_list),
- lambda (codepoint, _): codepoint / 4):
+ lambda codepoint: int(codepoint[0] / 4)):
# Fill bits from LSB to MSB for each group.
bits = 0
for index, (_, category) in enumerate(group):
@@ -263,7 +263,7 @@ def GenerateCategoryBitmap(category_list
# Output the content. Each line would have (at most) 16 bytes.
for _, group in itertools.groupby(enumerate(bit_list),
- lambda (index, _): index / 16):
+ lambda index: int(index[0] / 16)):
line = [' \"']
for _, bits in group:
line.append('\\x%02X' % bits)
@@ -386,7 +386,7 @@ def GenerateGetCharacterSet(category_lis
# Bitmap lookup.
# TODO(hidehiko): the bitmap has two huge 0-bits ranges. Reduce them.
category_map = [
- (bits, category) for category, bits in CATEGORY_BITMAP.iteritems()]
+ (bits, category) for category, bits in CATEGORY_BITMAP.items()]
category_map.sort()
lines.extend([
@@ -451,7 +451,7 @@ def main():
options.jisx0213file)
category_list = [
categorizer.GetCategory(codepoint)
- for codepoint in xrange(categorizer.MaxCodePoint() + 1)]
+ for codepoint in range(categorizer.MaxCodePoint() + 1)]
generated_character_set_header = GenerateCharacterSetHeader(category_list)
# Write the result.
diff -pruN mozc-2.23.2815.102.orig/base/gen_config_file_stream_data.py mozc-2.23.2815.102/base/gen_config_file_stream_data.py
--- mozc-2.23.2815.102.orig/base/gen_config_file_stream_data.py 2019-08-02 14:22:24.490255547 +0900
+++ mozc-2.23.2815.102/base/gen_config_file_stream_data.py 2019-08-01 21:53:12.998788807 +0900
@@ -58,7 +58,7 @@ def GenerateFileData(path):
result = []
result.append(' { "%s", "' % os.path.basename(path))
with open(path, 'rb') as stream:
- result.extend(r'\x%02X' % ord(byte) for byte in stream.read())
+ result.extend(r'\x%02X' % byte for byte in stream.read())
result.append('", %d }' % os.path.getsize(path))
return ''.join(result)
@@ -93,8 +93,8 @@ def OutputConfigFileStreamData(path_list
def main():
(options, args) = ParseOptions()
if not options.output:
- print >>sys.stderr, (
- 'usage: gen_config_file_stream_data.py --output=filepath input ...')
+ print(
+ 'usage: gen_config_file_stream_data.py --output=filepath input ...', file=sys.stderr)
sys.exit(2)
with open(options.output, 'w') as output:
diff -pruN mozc-2.23.2815.102.orig/build_mozc.py mozc-2.23.2815.102/build_mozc.py
--- mozc-2.23.2815.102.orig/build_mozc.py 2019-08-02 14:22:24.491255546 +0900
+++ mozc-2.23.2815.102/build_mozc.py 2019-08-01 21:53:12.998788807 +0900
@@ -943,7 +943,7 @@ def RunTests(target_platform, configurat
logging.info('running %s...', binary)
try:
test_function(binary, gtest_report_dir, options)
- except RunOrDieError, e:
+ except RunOrDieError as e:
logging.error(e)
failed_tests.append(binary)
else:
@@ -1082,7 +1082,7 @@ def RunTestsMain(options, args):
# and '-c' and 'Release' are build options.
targets = []
build_options = []
- for i in xrange(len(args)):
+ for i in range(len(args)):
if args[i].startswith('-'):
# starting with build options
build_options = args[i:]
@@ -1099,7 +1099,7 @@ def RunTestsMain(options, args):
# configuration flags are shared among runtests options and
# build options.
- if 'jobs' in vars(options).keys():
+ if 'jobs' in list(vars(options).keys()):
build_options.extend(['-j', options.jobs])
if options.configuration:
build_options.extend(['-c', options.configuration])
@@ -1190,14 +1190,14 @@ def CleanMain(options, unused_args):
def ShowHelpAndExit():
"""Shows the help message."""
- print 'Usage: build_mozc.py COMMAND [ARGS]'
- print 'Commands: '
- print ' gyp Generate project files.'
- print ' build Build the specified target.'
- print ' runtests Build all tests and run them.'
- print ' clean Clean all the build files and directories.'
- print ''
- print 'See also the comment in the script for typical usage.'
+ print('Usage: build_mozc.py COMMAND [ARGS]')
+ print('Commands: ')
+ print(' gyp Generate project files.')
+ print(' build Build the specified target.')
+ print(' runtests Build all tests and run them.')
+ print(' clean Clean all the build files and directories.')
+ print('')
+ print('See also the comment in the script for typical usage.')
sys.exit(1)
diff -pruN mozc-2.23.2815.102.orig/build_tools/android_util.py mozc-2.23.2815.102/build_tools/android_util.py
--- mozc-2.23.2815.102.orig/build_tools/android_util.py 2019-08-02 14:22:24.491255546 +0900
+++ mozc-2.23.2815.102/build_tools/android_util.py 2019-08-01 21:53:12.999788807 +0900
@@ -548,7 +548,7 @@ def GetAvailableEmulatorPorts(android_ho
(devices_result, _) = process.communicate()
used_ports = set(int(port) for port
in re.findall(r'emulator-(\d+)', devices_result))
- return [port for port in xrange(5554, 5586, 2) if port not in used_ports]
+ return [port for port in range(5554, 5586, 2) if port not in used_ports]
def SetUpTestingSdkHomeDirectory(dest_android_sdk_home,
@@ -575,7 +575,7 @@ def SetUpTestingSdkHomeDirectory(dest_an
'create', 'avd',
'--force',
'--sdcard', '512M',]
- for key, value in options.iteritems():
+ for key, value in options.items():
args.extend([key, value])
env = {'ANDROID_SDK_HOME': os.path.abspath(dest_android_sdk_home)}
logging.info('Creating AVD: %s', args)
@@ -615,7 +615,7 @@ def GetAvdProperties(android_sdk_home, a
def main():
for arg in sys.argv[1:]:
for item in sorted(GetApkProperties(arg).items()):
- print '%s: %s' % item
+ print('%s: %s' % item)
if __name__ == '__main__':
diff -pruN mozc-2.23.2815.102.orig/build_tools/code_generator_util.py mozc-2.23.2815.102/build_tools/code_generator_util.py
--- mozc-2.23.2815.102.orig/build_tools/code_generator_util.py 2019-08-02 14:22:24.491255546 +0900
+++ mozc-2.23.2815.102/build_tools/code_generator_util.py 2019-08-01 21:53:12.999788807 +0900
@@ -46,14 +46,14 @@ def ToCppStringLiteral(s):
return '"%s"' % s.replace('\\', r'\\').replace('"', r'\"')
else:
# One or more characters are non-ascii.
- return '"%s"' % ''.join(r'\x%02X' % ord(c) for c in s)
+ return '"%s"' % ''.join(r'\x%02X' % c for c in s.encode())
def FormatWithCppEscape(format_text, *args):
"""Returns a string filling format with args."""
literal_list = []
for arg in args:
- if isinstance(arg, (types.StringType, types.NoneType)):
+ if isinstance(arg, (bytes, type(None))):
arg = ToCppStringLiteral(arg)
literal_list.append(arg)
@@ -95,7 +95,7 @@ def WriteCppDataArray(data, variable_nam
if target_compiler and target_compiler.startswith('msvs'):
stream.write('const uint64 k%s_data_wordtype[] = {\n' % variable_name)
- for word_index in xrange(0, len(data), 8):
+ for word_index in range(0, len(data), 8):
word_chunk = data[word_index:word_index + 8].ljust(8, '\x00')
stream.write('0x%016X, ' % struct.unpack('<Q', word_chunk))
if (word_index / 8) % 4 == 3:
@@ -108,17 +108,17 @@ def WriteCppDataArray(data, variable_nam
'reinterpret_cast<const char *>(k%s_data_wordtype);\n' % (
variable_name, variable_name))
else:
- stream.write('const char k%s_data[] =\n' % variable_name)
+ stream.write(('const char k%s_data[] =\n' % variable_name).encode())
# Output 16bytes per line.
chunk_size = 16
- for index in xrange(0, len(data), chunk_size):
+ for index in range(0, len(data), chunk_size):
chunk = data[index:index + chunk_size]
- stream.write('"')
- stream.writelines(r'\x%02X' % ord(c) for c in chunk)
- stream.write('"\n')
- stream.write(';\n')
+ stream.write('"'.encode())
+ stream.writelines(br'\x%02X' % c for c in chunk)
+ stream.write('"\n'.encode())
+ stream.write(';\n'.encode())
- stream.write('const size_t k%s_size = %d;\n' % (variable_name, len(data)))
+ stream.write(('const size_t k%s_size = %d;\n' % (variable_name, len(data))).encode())
def ToJavaStringLiteral(codepoint_list):
@@ -129,7 +129,7 @@ def ToJavaStringLiteral(codepoint_list):
return 'null'
result = r'"'
for codepoint in codepoint_list:
- utf16_string = unichr(codepoint).encode('utf-16be')
+ utf16_string = chr(codepoint).encode('utf-16be')
if len(utf16_string) == 2:
(u0, l0) = utf16_string
result += r'\u%02X%02X' % (ord(u0), ord(l0))
@@ -172,5 +172,5 @@ def SplitChunk(iterable, n):
grouper extends the last chunk to make it an n-element chunk by adding
appropriate value, but this returns truncated chunk.
"""
- for index in xrange(0, len(iterable), n):
+ for index in range(0, len(iterable), n):
yield iterable[index:index + n]
diff -pruN mozc-2.23.2815.102.orig/build_tools/embed_file.py mozc-2.23.2815.102/build_tools/embed_file.py
--- mozc-2.23.2815.102.orig/build_tools/embed_file.py 2019-08-02 14:22:24.491255546 +0900
+++ mozc-2.23.2815.102/build_tools/embed_file.py 2019-08-01 21:53:12.999788807 +0900
@@ -46,33 +46,33 @@ def _ParseOption():
def _FormatAsUint64LittleEndian(s):
"""Formats a string as uint64 value in little endian order."""
- for _ in xrange(len(s), 8):
- s += '\0'
+ for _ in range(len(s), 8):
+ s += '\0'.encode()
s = s[::-1] # Reverse the string
- return '0x%s' % binascii.b2a_hex(s)
+ return '0x%s' % binascii.b2a_hex(s).decode()
def main():
opts = _ParseOption()
with open(opts.input, 'rb') as infile:
with open(opts.output, 'wb') as outfile:
- outfile.write(
+ outfile.write((
'#ifdef MOZC_EMBEDDED_FILE_%(name)s\n'
'#error "%(name)s was already included or defined elsewhere"\n'
'#else\n'
'#define MOZC_EMBEDDED_FILE_%(name)s\n'
'const uint64 %(name)s_data[] = {\n'
- % {'name': opts.name})
+ % {'name': opts.name}).encode())
while True:
chunk = infile.read(8)
if not chunk:
break
- outfile.write(' ')
- outfile.write(_FormatAsUint64LittleEndian(chunk))
- outfile.write(',\n')
+ outfile.write(' '.encode())
+ outfile.write(_FormatAsUint64LittleEndian(chunk).encode())
+ outfile.write(',\n'.encode())
- outfile.write(
+ outfile.write((
'};\n'
'const EmbeddedFile %(name)s = {\n'
' %(name)s_data,\n'
@@ -80,7 +80,7 @@ def main():
'};\n'
'#endif // MOZC_EMBEDDED_FILE_%(name)s\n'
% {'name': opts.name,
- 'size': os.stat(opts.input).st_size})
+ 'size': os.stat(opts.input).st_size}).encode())
if __name__ == '__main__':
diff -pruN mozc-2.23.2815.102.orig/build_tools/redirect.py mozc-2.23.2815.102/build_tools/redirect.py
--- mozc-2.23.2815.102.orig/build_tools/redirect.py 2019-08-02 14:22:24.492255546 +0900
+++ mozc-2.23.2815.102/build_tools/redirect.py 2019-08-01 21:53:12.999788807 +0900
@@ -58,9 +58,9 @@ def main():
process = subprocess.Popen(sys.argv, stdout=subprocess.PIPE,
universal_newlines=True)
except:
- print '=========='
- print ' ERROR: %s' % ' '.join(sys.argv)
- print '=========='
+ print('==========')
+ print(' ERROR: %s' % ' '.join(sys.argv))
+ print('==========')
raise
(stdout_content, _) = process.communicate()
# Write the stdout content to the output file.
diff -pruN mozc-2.23.2815.102.orig/build_tools/serialized_string_array_builder.py mozc-2.23.2815.102/build_tools/serialized_string_array_builder.py
--- mozc-2.23.2815.102.orig/build_tools/serialized_string_array_builder.py 2019-08-02 14:22:24.492255546 +0900
+++ mozc-2.23.2815.102/build_tools/serialized_string_array_builder.py 2019-08-01 21:53:13.000788808 +0900
@@ -33,7 +33,7 @@
import struct
-def SerializeToFile(strings, filename):
+def SerializeToFile(strings_, filename):
"""Builds a binary image of strings.
For file format, see base/serialized_string_array.h.
@@ -42,12 +42,13 @@ def SerializeToFile(strings, filename):
strings: A list of strings to be serialized.
filename: Output binary file.
"""
- array_size = len(strings)
+ array_size = len(strings_)
# Precompute offsets and lengths.
offsets = []
lengths = []
offset = 4 + 8 * array_size # The start offset of strings chunk
+ strings = list(map(lambda s: s.encode(), strings_))
for s in strings:
offsets.append(offset)
lengths.append(len(s))
@@ -58,11 +59,11 @@ def SerializeToFile(strings, filename):
f.write(struct.pack('<I', array_size))
# Offset and length array of (4 + 4) * array_size bytes.
- for i in xrange(array_size):
+ for i in range(array_size):
f.write(struct.pack('<I', offsets[i]))
f.write(struct.pack('<I', lengths[i]))
# Strings chunk.
- for i in xrange(array_size):
+ for i in range(array_size):
f.write(strings[i])
- f.write('\0')
+ f.write('\0'.encode())
diff -pruN mozc-2.23.2815.102.orig/build_tools/test_tools/test_launcher.py mozc-2.23.2815.102/build_tools/test_tools/test_launcher.py
--- mozc-2.23.2815.102.orig/build_tools/test_tools/test_launcher.py 2019-08-02 14:22:24.492255546 +0900
+++ mozc-2.23.2815.102/build_tools/test_tools/test_launcher.py 2019-08-01 21:53:13.000788808 +0900
@@ -101,11 +101,11 @@ class PathDeleter(object):
time.sleep(1)
try:
shutil.rmtree(self._path)
- except OSError, e:
+ except OSError as e:
logging.error('Failed to remove %s. error: %s', self._path, e)
-def _ExecuteTest((command, gtest_report_dir)):
+def _ExecuteTest(xxx_todo_changeme):
"""Executes tests with specified Test command.
Args:
@@ -122,6 +122,7 @@ def _ExecuteTest((command, gtest_report_
module, which is used in multiprocessing module.
(http://docs.python.org/library/pickle.html)
"""
+ (command, gtest_report_dir) = xxx_todo_changeme
binary = command[0]
binary_filename = os.path.basename(binary)
tmp_dir = tempfile.mkdtemp()
diff -pruN mozc-2.23.2815.102.orig/build_tools/util.py mozc-2.23.2815.102/build_tools/util.py
--- mozc-2.23.2815.102.orig/build_tools/util.py 2019-08-02 14:22:24.492255546 +0900
+++ mozc-2.23.2815.102/build_tools/util.py 2019-08-01 21:53:13.000788808 +0900
@@ -73,11 +73,11 @@ def GetNumberOfProcessors():
return 1
-class RunOrDieError(StandardError):
+class RunOrDieError(Exception):
"""The exception class for RunOrDie."""
def __init__(self, message):
- StandardError.__init__(self, message)
+ Exception.__init__(self, message)
def RunOrDie(argv):
@@ -105,7 +105,7 @@ def RemoveFile(file_name):
return # Do nothing if not exist.
if IsWindows():
# Read-only files cannot be deleted on Windows.
- os.chmod(file_name, 0700)
+ os.chmod(file_name, 0o700)
logging.debug('Removing file: %s', file_name)
os.unlink(file_name)
diff -pruN mozc-2.23.2815.102.orig/composer/internal/gen_typing_model.py mozc-2.23.2815.102/composer/internal/gen_typing_model.py
--- mozc-2.23.2815.102.orig/composer/internal/gen_typing_model.py 2019-08-02 14:22:24.492255546 +0900
+++ mozc-2.23.2815.102/composer/internal/gen_typing_model.py 2019-08-01 21:53:13.001788809 +0900
@@ -60,8 +60,8 @@ import optparse
import struct
UNDEFINED_COST = -1
-MAX_UINT16 = struct.unpack('H', '\xFF\xFF')[0]
-MAX_UINT8 = struct.unpack('B', '\xFF')[0]
+MAX_UINT16 = struct.unpack('H', b'\xFF\xFF')[0]
+MAX_UINT8 = struct.unpack('B', b'\xFF')[0]
def ParseArgs():
@@ -113,7 +113,7 @@ def GetMappingTable(values, mapping_tabl
sorted_values = list(sorted(set(values)))
mapping_table = sorted_values[0]
mapping_table_size_without_special_value = mapping_table_size - 1
- span = len(sorted_values) / (mapping_table_size_without_special_value - 1)
+ span = int(len(sorted_values) / (mapping_table_size_without_special_value - 1))
mapping_table = [sorted_values[i * span]
for i
in range(0, mapping_table_size_without_special_value - 1)]
@@ -150,7 +150,7 @@ def GetNearestMappingTableIndex(mapping_
def GetValueTable(unique_characters, mapping_table, dictionary):
result = []
- for key, value in dictionary.iteritems():
+ for key, value in dictionary.items():
index = GetIndexFromKey(unique_characters, key)
while len(result) <= index:
result.append(len(mapping_table) - 1)
@@ -160,20 +160,20 @@ def GetValueTable(unique_characters, map
def WriteResult(romaji_transition_cost, output_path):
- unique_characters = GetUniqueCharacters(romaji_transition_cost.keys())
- mapping_table = GetMappingTable(romaji_transition_cost.values(),
+ unique_characters = GetUniqueCharacters(list(romaji_transition_cost.keys()))
+ mapping_table = GetMappingTable(list(romaji_transition_cost.values()),
MAX_UINT8 + 1)
value_list = GetValueTable(unique_characters, mapping_table,
romaji_transition_cost)
with open(output_path, 'wb') as f:
f.write(struct.pack('<I', len(unique_characters)))
- f.write(''.join(unique_characters))
+ f.write(''.join(unique_characters).encode())
offset = 4 + len(unique_characters)
# Add padding to place value list size at 4-byte boundary.
if offset % 4:
padding_size = 4 - offset % 4
- f.write('\x00' * padding_size)
+ f.write(('\x00' * padding_size).encode())
offset += padding_size
f.write(struct.pack('<I', len(value_list)))
@@ -184,7 +184,7 @@ def WriteResult(romaji_transition_cost,
# Add padding to place mapping_table at 4-byte boundary.
if offset % 4:
padding_size = 4 - offset % 4
- f.write('\x00' * padding_size)
+ f.write(('\x00' * padding_size).encode())
offset += padding_size
for v in mapping_table:
diff -pruN mozc-2.23.2815.102.orig/converter/gen_boundary_data.py mozc-2.23.2815.102/converter/gen_boundary_data.py
--- mozc-2.23.2815.102.orig/converter/gen_boundary_data.py 2019-08-02 14:22:24.493255546 +0900
+++ mozc-2.23.2815.102/converter/gen_boundary_data.py 2019-08-01 21:53:13.001788809 +0900
@@ -84,7 +84,7 @@ def LoadPatterns(file):
elif label == 'SUFFIX':
suffix.append([re.compile(PatternToRegexp(feature)), cost])
else:
- print 'format error %s' % (line)
+ print('format error %s' % (line))
sys.exit(0)
return (prefix, suffix)
@@ -141,7 +141,7 @@ def main():
f.write(struct.pack('<H', GetCost(prefix, feature)))
f.write(struct.pack('<H', GetCost(suffix, feature)))
- for _ in xrange(num_special_pos):
+ for _ in range(num_special_pos):
f.write(struct.pack('<H', 0))
f.write(struct.pack('<H', 0))
diff -pruN mozc-2.23.2815.102.orig/converter/gen_segmenter_code.py mozc-2.23.2815.102/converter/gen_segmenter_code.py
--- mozc-2.23.2815.102.orig/converter/gen_segmenter_code.py 2019-08-02 14:22:24.493255546 +0900
+++ mozc-2.23.2815.102/converter/gen_segmenter_code.py 2019-08-01 21:53:13.002788809 +0900
@@ -79,7 +79,7 @@ def GetRange(pos, pattern, name):
pat = re.compile(PatternToRegexp(pattern))
min = -1;
max = -1;
- keys = pos.keys()
+ keys = list(pos.keys())
keys.sort()
range = []
@@ -107,7 +107,7 @@ def GetRange(pos, pattern, name):
tmp.append("(%s >= %s && %s <= %s)" % (name, r[0], name, r[1]))
if len(tmp) == 0:
- print "FATAL: No rule fiind %s" % (pattern)
+ print("FATAL: No rule fiind %s" % (pattern))
sys.exit(-1)
return " || ".join(tmp)
@@ -115,7 +115,7 @@ def GetRange(pos, pattern, name):
def main():
pos = ReadPOSID(sys.argv[1], sys.argv[2])
- print HEADER % (len(pos.keys()), len(pos.keys()))
+ print(HEADER % (len(pos.keys()), len(pos.keys())))
for line in open(sys.argv[3], "r"):
if len(line) <= 1 or line[0] == '#':
@@ -124,10 +124,10 @@ def main():
result = result.lower()
lcond = GetRange(pos, l, "rid") or "true";
rcond = GetRange(pos, r, "lid") or "true";
- print " // %s %s %s" % (l, r, result)
- print " if ((%s) && (%s)) { return %s; }" % (lcond, rcond, result)
+ print(" // %s %s %s" % (l, r, result))
+ print(" if ((%s) && (%s)) { return %s; }" % (lcond, rcond, result))
- print FOOTER
+ print(FOOTER)
if __name__ == "__main__":
main()
diff -pruN mozc-2.23.2815.102.orig/data_manager/gen_connection_data.py mozc-2.23.2815.102/data_manager/gen_connection_data.py
--- mozc-2.23.2815.102.orig/data_manager/gen_connection_data.py 2019-08-02 14:22:24.493255546 +0900
+++ mozc-2.23.2815.102/data_manager/gen_connection_data.py 2019-08-01 21:53:13.002788809 +0900
@@ -32,7 +32,7 @@
__author__ = "hidehiko"
-import cStringIO as StringIO
+import io as BytesIO
import itertools
import logging
import optparse
@@ -45,7 +45,7 @@ from build_tools import code_generator_u
INVALID_COST = 30000
INVALID_1BYTE_COST = 255
RESOLUTION_FOR_1BYTE = 64
-FILE_MAGIC = '\xAB\xCD'
+FILE_MAGIC = b'\xAB\xCD'
FALSE_VALUES = ['f', 'false', '0']
TRUE_VALUES = ['t', 'true', '1']
@@ -79,28 +79,28 @@ def ParseConnectionFile(text_connection_
# The result is a square matrix.
mat_size = pos_size + special_pos_size
- matrix = [[0] * mat_size for _ in xrange(mat_size)]
+ matrix = [[0] * mat_size for _ in range(mat_size)]
with open(text_connection_file) as stream:
stream = code_generator_util.SkipLineComment(stream)
# The first line contains the matrix column/row size.
- size = stream.next().rstrip()
+ size = next(stream).rstrip()
assert (int(size) == pos_size), '%s != %d' % (size, pos_size)
for array_index, cost in enumerate(stream):
cost = int(cost.rstrip())
- rid = array_index / pos_size
+ rid = int(array_index / pos_size)
lid = array_index % pos_size
if rid == 0 and lid == 0:
cost = 0
matrix[rid][lid] = cost
# Fill INVALID_COST in matrix elements for special POS.
- for rid in xrange(pos_size, mat_size):
- for lid in xrange(1, mat_size): # Skip EOS
+ for rid in range(pos_size, mat_size):
+ for lid in range(1, mat_size): # Skip EOS
matrix[rid][lid] = INVALID_COST
- for lid in xrange(pos_size, mat_size):
- for rid in xrange(1, mat_size): # Skip BOS
+ for lid in range(pos_size, mat_size):
+ for rid in range(1, mat_size): # Skip BOS
matrix[rid][lid] = INVALID_COST
return matrix
@@ -116,7 +116,7 @@ def CreateModeValueList(matrix):
# Heuristically, we do not compress INVALID_COST.
continue
m[cost] = m.get(cost, 0) + 1
- mode_value = max(m.iteritems(), key=lambda (_, count): count)[0]
+ mode_value = max(iter(m.items()), key=lambda _: _[1])[0]
result.append(mode_value)
return result
@@ -126,8 +126,8 @@ def CompressMatrixByModeValue(matrix, mo
# list, and fill None into the matrix if it equals to the corresponding
# mode value.
assert len(matrix) == len(mode_value_list)
- for row, mode_value in itertools.izip(matrix, mode_value_list):
- for index in xrange(len(row)):
+ for row, mode_value in zip(matrix, mode_value_list):
+ for index in range(len(row)):
if row[index] == mode_value:
row[index] = None
@@ -179,7 +179,7 @@ def BuildBinaryData(matrix, mode_value_l
resolution = RESOLUTION_FOR_1BYTE
else:
resolution = 1
- stream = StringIO.StringIO()
+ stream = BytesIO.BytesIO()
# Output header.
stream.write(FILE_MAGIC)
@@ -194,7 +194,7 @@ def BuildBinaryData(matrix, mode_value_l
# 4 bytes alignment.
if len(mode_value_list) % 2:
- stream.write('\x00\x00')
+ stream.write('\x00\x00'.encode())
# Process each row:
for row in matrix:
@@ -237,7 +237,7 @@ def BuildBinaryData(matrix, mode_value_l
values_size = len(values) * 2
# Output the bits for a row.
- stream.write(struct.pack('<HH', len(compact_bits) / 8, values_size))
+ stream.write(struct.pack('<HH', int(len(compact_bits) / 8), values_size))
OutputBitList(chunk_bits, stream)
OutputBitList(compact_bits, stream)
if use_1byte_cost:
diff -pruN mozc-2.23.2815.102.orig/dictionary/gen_pos_map.py mozc-2.23.2815.102/dictionary/gen_pos_map.py
--- mozc-2.23.2815.102.orig/dictionary/gen_pos_map.py 2019-08-02 14:22:24.493255546 +0900
+++ mozc-2.23.2815.102/dictionary/gen_pos_map.py 2019-08-01 21:53:13.002788809 +0900
@@ -78,7 +78,7 @@ def GeneratePosMap(third_party_pos_map_f
result[third_party_pos_name] = mozc_pos
# Create mozc_pos to mozc_pos map.
- for key, value in user_pos_map.iteritems():
+ for key, value in user_pos_map.items():
if key in result:
assert (result[key] == value)
continue
diff -pruN mozc-2.23.2815.102.orig/dictionary/gen_pos_rewrite_rule.py mozc-2.23.2815.102/dictionary/gen_pos_rewrite_rule.py
--- mozc-2.23.2815.102.orig/dictionary/gen_pos_rewrite_rule.py 2019-08-02 14:22:24.494255545 +0900
+++ mozc-2.23.2815.102/dictionary/gen_pos_rewrite_rule.py 2019-08-01 21:53:13.003788810 +0900
@@ -112,7 +112,7 @@ def main():
ids.append(id)
with open(opts.output, 'wb') as f:
- f.write(''.join(chr(id) for id in ids))
+ f.write((''.join(chr(id) for id in ids)).encode())
if __name__ == '__main__':
diff -pruN mozc-2.23.2815.102.orig/dictionary/gen_user_pos_data.py mozc-2.23.2815.102/dictionary/gen_user_pos_data.py
--- mozc-2.23.2815.102.orig/dictionary/gen_user_pos_data.py 2019-08-02 14:22:24.494255545 +0900
+++ mozc-2.23.2815.102/dictionary/gen_user_pos_data.py 2019-08-01 21:53:13.003788810 +0900
@@ -64,7 +64,7 @@ def OutputUserPosData(user_pos_data, out
f.write(struct.pack('<H', conjugation_id))
serialized_string_array_builder.SerializeToFile(
- sorted(string_index.iterkeys()), output_string_array)
+ sorted(string_index.keys()), output_string_array)
def ParseOptions():
diff -pruN mozc-2.23.2815.102.orig/dictionary/gen_zip_code_seed.py mozc-2.23.2815.102/dictionary/gen_zip_code_seed.py
--- mozc-2.23.2815.102.orig/dictionary/gen_zip_code_seed.py 2019-08-02 14:22:24.494255545 +0900
+++ mozc-2.23.2815.102/dictionary/gen_zip_code_seed.py 2019-08-01 21:53:13.003788810 +0900
@@ -83,7 +83,7 @@ class ZipEntry(object):
address = unicodedata.normalize('NFKC', self.address)
line = '\t'.join([zip_code, '0', '0', str(ZIP_CODE_COST),
address, ZIP_CODE_LABEL])
- print line.encode('utf-8')
+ print(line)
def ProcessZipCodeCSV(file_name):
diff -pruN mozc-2.23.2815.102.orig/dictionary/zip_code_util.py mozc-2.23.2815.102/dictionary/zip_code_util.py
--- mozc-2.23.2815.102.orig/dictionary/zip_code_util.py 2018-01-26 18:48:12.000000000 +0900
+++ mozc-2.23.2815.102/dictionary/zip_code_util.py 2019-08-02 14:22:32.959252641 +0900
@@ -38,7 +38,7 @@ def ReadCSV(file_name):
# Do not use csv reader module because it does not support unicode
return [GetCells(line) for line in codecs.open(file_name,
'r',
- 'shift_jis',
+ 'cp932',
errors='replace')]
diff -pruN mozc-2.23.2815.102.orig/gui/character_pad/data/gen_cp932_map.py mozc-2.23.2815.102/gui/character_pad/data/gen_cp932_map.py
--- mozc-2.23.2815.102.orig/gui/character_pad/data/gen_cp932_map.py 2019-08-02 14:22:24.494255545 +0900
+++ mozc-2.23.2815.102/gui/character_pad/data/gen_cp932_map.py 2019-08-01 21:53:13.003788810 +0900
@@ -44,7 +44,7 @@ def main():
for line in fh.readlines():
if line[0] is '#':
continue
- array = string.split(line)
+ array = line.split()
sjis = array[0]
ucs2 = array[1]
if eval(sjis) < 32 or not IsValidUnicode(ucs2):
@@ -53,17 +53,17 @@ def main():
keys = sorted(result.keys())
- print "struct CP932MapData {"
- print " unsigned int ucs4;"
- print " unsigned short int sjis;"
- print "};"
- print ""
- print "static const size_t kCP932MapDataSize = %d;" % (len(keys))
- print "static const CP932MapData kCP932MapData[] = {"
+ print("struct CP932MapData {")
+ print(" unsigned int ucs4;")
+ print(" unsigned short int sjis;")
+ print("};")
+ print("")
+ print("static const size_t kCP932MapDataSize = %d;" % (len(keys)))
+ print("static const CP932MapData kCP932MapData[] = {")
for n in keys:
- print " { %s, %s }," % (n ,result[n])
- print " { 0, 0 }";
- print "};"
+ print(" { %s, %s }," % (n ,result[n]))
+ print(" { 0, 0 }");
+ print("};")
if __name__ == "__main__":
main()
diff -pruN mozc-2.23.2815.102.orig/gui/character_pad/data/gen_local_character_map.py mozc-2.23.2815.102/gui/character_pad/data/gen_local_character_map.py
--- mozc-2.23.2815.102.orig/gui/character_pad/data/gen_local_character_map.py 2019-08-02 14:22:24.494255545 +0900
+++ mozc-2.23.2815.102/gui/character_pad/data/gen_local_character_map.py 2019-08-01 21:53:13.003788810 +0900
@@ -45,7 +45,7 @@ def LoadJISX0201(filename):
for line in fh.readlines():
if line[0] is '#':
continue
- array = string.split(line)
+ array = line.split()
jis = array[0].replace('0x', '')
ucs2 = array[1].replace('0x', '')
if len(jis) == 2:
@@ -106,13 +106,13 @@ def LoadCP932(filename):
def Output(arg):
name = arg[0]
result = arg[1]
- print "static const size_t k%sMapSize = %d;" % (name, len(result))
- print "static const mozc::gui::CharacterPalette::LocalCharacterMap k%sMap[] = {" % (name)
+ print("static const size_t k%sMapSize = %d;" % (name, len(result)))
+ print("static const mozc::gui::CharacterPalette::LocalCharacterMap k%sMap[] = {" % (name))
for n in result:
- print " { 0x%s, 0x%s }," % (n[0] ,n[1])
- print " { 0, 0 }";
- print "};"
- print ""
+ print(" { 0x%s, 0x%s }," % (n[0] ,n[1]))
+ print(" { 0, 0 }");
+ print("};")
+ print("")
if __name__ == "__main__":
Output(LoadJISX0201(sys.argv[1]))
diff -pruN mozc-2.23.2815.102.orig/gui/character_pad/data/gen_unicode_blocks.py mozc-2.23.2815.102/gui/character_pad/data/gen_unicode_blocks.py
--- mozc-2.23.2815.102.orig/gui/character_pad/data/gen_unicode_blocks.py 2019-08-02 14:22:24.494255545 +0900
+++ mozc-2.23.2815.102/gui/character_pad/data/gen_unicode_blocks.py 2019-08-01 21:53:13.004788811 +0900
@@ -36,7 +36,7 @@ import re
re = re.compile('^(.....?)\.\.(.....?); (.+)')
def main():
- print "static const mozc::gui::CharacterPalette::UnicodeBlock kUnicodeBlockTable[] = {"
+ print("static const mozc::gui::CharacterPalette::UnicodeBlock kUnicodeBlockTable[] = {")
fh = open(sys.argv[1])
for line in fh.readlines():
if line[0] is '#':
@@ -47,11 +47,11 @@ def main():
end = int(m.group(2), 16)
name = m.group(3)
if start <= 0x2FFFF and end <= 0x2FFFF:
- print " { \"%s\", { %d, %d } }," % (name, start, end)
+ print(" { \"%s\", { %d, %d } }," % (name, start, end))
- print " { NULL, { 0, 0 } }"
- print "};"
- print ""
+ print(" { NULL, { 0, 0 } }")
+ print("};")
+ print("")
if __name__ == "__main__":
main()
diff -pruN mozc-2.23.2815.102.orig/gui/character_pad/data/gen_unicode_data.py mozc-2.23.2815.102/gui/character_pad/data/gen_unicode_data.py
--- mozc-2.23.2815.102.orig/gui/character_pad/data/gen_unicode_data.py 2019-08-02 14:22:24.495255545 +0900
+++ mozc-2.23.2815.102/gui/character_pad/data/gen_unicode_data.py 2019-08-01 21:53:13.004788811 +0900
@@ -47,17 +47,17 @@ def main():
if code < 0x2FFFF:
results.append(" { %d, \"%s\" }," % (code, desc))
- print "struct UnicodeData {";
- print " char32 ucs4;";
- print " const char *description;";
- print "};";
- print ""
- print "static const size_t kUnicodeDataSize = %d;" % (len(results))
- print "static const UnicodeData kUnicodeData[] = {";
+ print("struct UnicodeData {");
+ print(" char32 ucs4;");
+ print(" const char *description;");
+ print("};");
+ print("")
+ print("static const size_t kUnicodeDataSize = %d;" % (len(results)))
+ print("static const UnicodeData kUnicodeData[] = {");
for line in results:
- print line;
- print " { 0, NULL }";
- print "};";
+ print(line);
+ print(" { 0, NULL }");
+ print("};");
if __name__ == "__main__":
main()
diff -pruN mozc-2.23.2815.102.orig/gui/character_pad/data/gen_unihan_data.py mozc-2.23.2815.102/gui/character_pad/data/gen_unihan_data.py
--- mozc-2.23.2815.102.orig/gui/character_pad/data/gen_unihan_data.py 2019-08-02 14:22:24.495255545 +0900
+++ mozc-2.23.2815.102/gui/character_pad/data/gen_unihan_data.py 2019-08-01 21:53:13.004788811 +0900
@@ -43,12 +43,12 @@ def Escape(n):
def GetCode(n):
if n is not "NULL":
- n = string.replace(n, '0-', 'JIS X 0208: 0x')
- n = string.replace(n, '1-', 'JIS X 0212: 0x')
- n = string.replace(n, '3-', 'JIS X 0213: 0x')
- n = string.replace(n, '4-', 'JIS X 0213: 0x')
- n = string.replace(n, 'A-', 'Vendors Ideographs: 0x')
- n = string.replace(n, '3A', 'JIS X 0213 2000: 0x')
+ n = n.replace('0-', 'JIS X 0208: 0x')
+ n = n.replace('1-', 'JIS X 0212: 0x')
+ n = n.replace('3-', 'JIS X 0213: 0x')
+ n = n.replace('4-', 'JIS X 0213: 0x')
+ n = n.replace('A-', 'Vendors Ideographs: 0x')
+ n = n.replace('3A', 'JIS X 0213 2000: 0x')
return "\"%s\"" % n
else:
return "NULL"
@@ -59,7 +59,7 @@ def GetRadical(n):
m = pat.match(n)
if m:
result = rs[m.group(1)]
- return "\"%s\"" % (result.encode('string_escape'))
+ return "\"%s\"" % (''.join(r'\x%02x' % c for c in result.encode()))
else:
return "NULL"
else:
@@ -89,20 +89,20 @@ def main():
keys = sorted(dic.keys())
- print "struct UnihanData {";
- print " unsigned int ucs4;";
+ print("struct UnihanData {");
+ print(" unsigned int ucs4;");
# Since the total strokes defined in Unihan data is Chinese-based
# number, we can't use it.
-# print " unsigned char total_strokes;";
- print " const char *japanese_kun;";
- print " const char *japanese_on;";
+# print(" unsigned char total_strokes;");
+ print(" const char *japanese_kun;");
+ print(" const char *japanese_on;");
# Since the radical information defined in Unihan data is Chinese-based
# number, we can't use it.
-# print " const char *radical;";
- print " const char *IRG_jsource;";
- print "};"
- print "static const size_t kUnihanDataSize = %d;" % (len(keys))
- print "static const UnihanData kUnihanData[] = {"
+# print(" const char *radical;");
+ print(" const char *IRG_jsource;");
+ print("};")
+ print("static const size_t kUnihanDataSize = %d;" % (len(keys)))
+ print("static const UnihanData kUnihanData[] = {")
for key in keys:
total_strokes = dic[key].get("kTotalStrokes", "0")
@@ -110,10 +110,10 @@ def main():
on = Escape(dic[key].get("kJapaneseOn", "NULL"))
rad = GetRadical(dic[key].get("kRSUnicode", "NULL"))
code = GetCode(dic[key].get("kIRG_JSource", "NULL"))
-# print " { 0x%s, %s, %s, %s, %s, %s }," % (key, total_strokes, kun, on, rad, code)
- print " { 0x%s, %s, %s, %s }," % (key, kun, on, code)
+# print(" { 0x%s, %s, %s, %s, %s, %s }," % (key, total_strokes, kun, on, rad, code))
+ print(" { 0x%s, %s, %s, %s }," % (key, kun, on, code))
- print "};"
+ print("};")
if __name__ == "__main__":
main()
diff -pruN mozc-2.23.2815.102.orig/prediction/gen_zero_query_data.py mozc-2.23.2815.102/prediction/gen_zero_query_data.py
--- mozc-2.23.2815.102.orig/prediction/gen_zero_query_data.py 2019-08-02 14:22:24.495255545 +0900
+++ mozc-2.23.2815.102/prediction/gen_zero_query_data.py 2019-08-01 21:53:13.005788811 +0900
@@ -66,7 +66,7 @@ def ParseCodePoint(s):
def NormalizeString(string):
return unicodedata.normalize(
- 'NFKC', string.decode('utf-8')).encode('utf-8').replace('~', '〜')
+ 'NFKC', string).replace('~', '〜')
def RemoveTrailingNumber(string):
@@ -84,7 +84,7 @@ def GetReadingsFromDescription(descripti
# - ビル・建物
# \xE3\x83\xBB : "・"
return [RemoveTrailingNumber(token) for token
- in re.split(r'(?:\(|\)|/|\xE3\x83\xBB)+', normalized)]
+ in re.split(r'(?:\(|\)|/|・)+', normalized)]
def ReadEmojiTsv(stream):
@@ -119,7 +119,7 @@ def ReadEmojiTsv(stream):
reading_list = []
# \xe3\x80\x80 is a full-width space
- for reading in re.split(r'(?: |\xe3\x80\x80)+', NormalizeString(readings)):
+ for reading in re.split(r'(?: | )+', NormalizeString(readings)):
if not reading:
continue
reading_list.append(reading)
@@ -147,7 +147,7 @@ def ReadEmojiTsv(stream):
emoji, emoji_type, android_pua))
# Sort emoji for each reading.
- for key in zero_query_dict.keys():
+ for key in list(zero_query_dict.keys()):
zero_query_dict[key].sort(key=lambda e: (e.value, e.emoji_android_pua))
return zero_query_dict
@@ -188,7 +188,7 @@ def ReadEmoticonTsv(stream):
readings = columns[2]
# \xe3\x80\x80 is a full-width space
- for reading in re.split(r'(?: |\xe3\x80\x80)+', readings.strip()):
+ for reading in re.split(r'(?: | )+', readings.strip()):
if not reading:
continue
zero_query_dict[reading].append(
@@ -210,7 +210,7 @@ def ReadSymbolTsv(stream):
symbol = columns[1]
readings = columns[2]
- symbol_unicode = symbol.decode('utf-8')
+ symbol_unicode = symbol #.decode('utf-8')
if len(symbol_unicode) != 1:
continue
@@ -222,7 +222,7 @@ def ReadSymbolTsv(stream):
continue
# \xe3\x80\x80 is a full-width space
- for reading in re.split(r'(?: |\xe3\x80\x80)+', readings.strip()):
+ for reading in re.split(r'(?: | )+', readings.strip()):
if not reading:
continue
zero_query_dict[reading].append(
@@ -254,10 +254,10 @@ def IsValidKeyForZeroQuery(key):
def MergeZeroQueryData(rule_dict, symbol_dict, emoji_dict, emoticon_dict):
"""Returnes merged zero query data."""
merged = defaultdict(list)
- for key in rule_dict.keys():
+ for key in list(rule_dict.keys()):
merged[key].extend(rule_dict[key])
- for key in emoji_dict.keys():
+ for key in list(emoji_dict.keys()):
if not IsValidKeyForZeroQuery(key):
continue
# Skips aggressive emoji candidates.
@@ -266,14 +266,14 @@ def MergeZeroQueryData(rule_dict, symbol
continue
merged[key].extend(emoji_dict[key])
- for key in emoticon_dict.keys():
+ for key in list(emoticon_dict.keys()):
if not IsValidKeyForZeroQuery(key):
continue
# Merges only up to 3 emoticons.
# Example: "にこにこ" have many candidates.
merged[key].extend(emoticon_dict[key][:3])
- for key in symbol_dict.keys():
+ for key in list(symbol_dict.keys()):
if not IsValidKeyForZeroQuery(key):
continue
# Skip aggressive emoji candidates.
diff -pruN mozc-2.23.2815.102.orig/prediction/gen_zero_query_util.py mozc-2.23.2815.102/prediction/gen_zero_query_util.py
--- mozc-2.23.2815.102.orig/prediction/gen_zero_query_util.py 2019-08-02 14:22:24.495255545 +0900
+++ mozc-2.23.2815.102/prediction/gen_zero_query_util.py 2019-08-01 21:53:13.005788811 +0900
@@ -69,7 +69,7 @@ def WriteZeroQueryData(zero_query_dict,
output_string_array):
# Collect all the strings and assing index in ascending order
string_index = {}
- for key, entry_list in zero_query_dict.iteritems():
+ for key, entry_list in list(zero_query_dict.items()):
string_index[key] = 0
for entry in entry_list:
string_index[entry.value] = 0
@@ -78,7 +78,7 @@ def WriteZeroQueryData(zero_query_dict,
string_index[s] = i
with open(output_token_array, 'wb') as f:
- for key in sorted(zero_query_dict):
+ for key in sorted(zero_query_dict, key=lambda x: x.encode()):
for entry in zero_query_dict[key]:
f.write(struct.pack('<I', string_index[key]))
f.write(struct.pack('<I', string_index[entry.value]))
diff -pruN mozc-2.23.2815.102.orig/rewriter/gen_counter_suffix_array.py mozc-2.23.2815.102/rewriter/gen_counter_suffix_array.py
--- mozc-2.23.2815.102.orig/rewriter/gen_counter_suffix_array.py 2019-08-02 14:22:24.496255545 +0900
+++ mozc-2.23.2815.102/rewriter/gen_counter_suffix_array.py 2019-08-01 21:53:13.005788811 +0900
@@ -63,7 +63,7 @@ def ReadCounterSuffixes(dictionary_files
for x, lid, rid, y, value in stream:
if (lid == rid) and (lid in ids) and (rid in ids):
suffixes.add(value)
- return sorted(s.encode('utf-8') for s in suffixes)
+ return sorted(s for s in suffixes)
def ParseOptions():
diff -pruN mozc-2.23.2815.102.orig/rewriter/gen_emoji_rewriter_data.py mozc-2.23.2815.102/rewriter/gen_emoji_rewriter_data.py
--- mozc-2.23.2815.102.orig/rewriter/gen_emoji_rewriter_data.py 2019-08-02 14:22:24.496255545 +0900
+++ mozc-2.23.2815.102/rewriter/gen_emoji_rewriter_data.py 2019-08-01 21:53:13.005788811 +0900
@@ -79,14 +79,13 @@ def ParseCodePoint(s):
return int(s, 16)
-_FULLWIDTH_RE = re.compile(ur'[！-～]') # U+FF01 - U+FF5E
+_FULLWIDTH_RE = re.compile(r'[！-～]') # U+FF01 - U+FF5E
def NormalizeString(string):
"""Normalize full width ascii characters to half width characters."""
- offset = ord(u'Ａ') - ord(u'A')
- return _FULLWIDTH_RE.sub(lambda x: unichr(ord(x.group(0)) - offset),
- unicode(string, 'utf-8')).encode('utf-8')
+ offset = ord('Ａ') - ord('A')
+ return _FULLWIDTH_RE.sub(lambda x: chr(ord(x.group(0)) - offset), string)
def ReadEmojiTsv(stream):
@@ -159,7 +158,7 @@ def ReadEmojiTsv(stream):
def OutputData(emoji_data_list, token_dict,
token_array_file, string_array_file):
"""Output token and string arrays to files."""
- sorted_token_dict = sorted(token_dict.iteritems())
+ sorted_token_dict = sorted(token_dict.items())
strings = {}
for reading, _ in sorted_token_dict:
@@ -171,7 +170,7 @@ def OutputData(emoji_data_list, token_di
strings[docomo_description] = 0
strings[softbank_description] = 0
strings[kddi_description] = 0
- sorted_strings = sorted(strings.iterkeys())
+ sorted_strings = sorted(strings.keys())
for index, s in enumerate(sorted_strings):
strings[s] = index
diff -pruN mozc-2.23.2815.102.orig/rewriter/gen_reading_correction_data.py mozc-2.23.2815.102/rewriter/gen_reading_correction_data.py
--- mozc-2.23.2815.102.orig/rewriter/gen_reading_correction_data.py 2019-08-02 14:22:24.496255545 +0900
+++ mozc-2.23.2815.102/rewriter/gen_reading_correction_data.py 2019-08-01 21:53:13.005788811 +0900
@@ -60,6 +60,9 @@ def ParseOptions():
return parser.parse_args()[0]
+def cmp(a, b):
+ return (a > b) - (a < b)
+
def WriteData(input_path, output_value_array_path, output_error_array_path,
output_correction_array_path):
outputs = []
@@ -73,7 +76,7 @@ def WriteData(input_path, output_value_a
# In order to lookup the entries via |error| with binary search,
# sort outputs here.
- outputs.sort(lambda x, y: cmp(x[1], y[1]) or cmp(x[0], y[0]))
+ outputs.sort(key=lambda z: cmp(z[0][1], z[1][1]) or cmp(z[0][0], z[1][0]))
serialized_string_array_builder.SerializeToFile(
[value for (value, _, _) in outputs], output_value_array_path)
diff -pruN mozc-2.23.2815.102.orig/rewriter/gen_single_kanji_rewriter_data.py mozc-2.23.2815.102/rewriter/gen_single_kanji_rewriter_data.py
--- mozc-2.23.2815.102.orig/rewriter/gen_single_kanji_rewriter_data.py 2019-08-02 14:22:24.496255545 +0900
+++ mozc-2.23.2815.102/rewriter/gen_single_kanji_rewriter_data.py 2019-08-01 21:53:13.006788812 +0900
@@ -46,13 +46,16 @@ from build_tools import code_generator_u
from build_tools import serialized_string_array_builder
+def cmp(a, b):
+ return (a > b) - (a < b)
+
def ReadSingleKanji(stream):
"""Parses single kanji dictionary data from stream."""
stream = code_generator_util.SkipLineComment(stream)
stream = code_generator_util.ParseColumnStream(stream, num_column=2)
outputs = list(stream)
# For binary search by |key|, sort outputs here.
- outputs.sort(lambda x, y: cmp(x[0], y[0]))
+ outputs.sort(key=lambda z: cmp(z[0][0], z[1][0]))
return outputs
@@ -72,7 +75,7 @@ def ReadVariant(stream):
variant_items.append([target, original, len(variant_types) - 1])
# For binary search by |target|, sort variant items here.
- variant_items.sort(lambda x, y: cmp(x[0], y[0]))
+ variant_items = sorted(variant_items, key=lambda z: z[0].encode())
return (variant_types, variant_items)
diff -pruN mozc-2.23.2815.102.orig/unix/ibus/gen_mozc_xml.py mozc-2.23.2815.102/unix/ibus/gen_mozc_xml.py
--- mozc-2.23.2815.102.orig/unix/ibus/gen_mozc_xml.py 2019-08-02 14:22:24.496255545 +0900
+++ mozc-2.23.2815.102/unix/ibus/gen_mozc_xml.py 2019-08-01 21:53:13.006788812 +0900
@@ -74,7 +74,7 @@ CPP_FOOTER = """} // namespace
def OutputXmlElement(param_dict, element_name, value):
- print ' <%s>%s</%s>' % (element_name, (value % param_dict), element_name)
+ print(' <%s>%s</%s>' % (element_name, (value % param_dict), element_name))
def OutputXml(param_dict, component, engine_common, engines, setup_arg):
@@ -90,26 +90,26 @@ def OutputXml(param_dict, component, eng
engines: A dictionary from a property name to a list of property values of
engines. For example, {'name': ['mozc-jp', 'mozc', 'mozc-dv']}.
"""
- print '<component>'
+ print('<component>')
for key in component:
OutputXmlElement(param_dict, key, component[key])
- print '<engines>'
+ print('<engines>')
for i in range(len(engines['name'])):
- print '<engine>'
+ print('<engine>')
for key in engine_common:
OutputXmlElement(param_dict, key, engine_common[key])
if setup_arg:
OutputXmlElement(param_dict, 'setup', ' '.join(setup_arg))
for key in engines:
OutputXmlElement(param_dict, key, engines[key][i])
- print '</engine>'
- print '</engines>'
- print '</component>'
+ print('</engine>')
+ print('</engines>')
+ print('</component>')
def OutputCppVariable(param_dict, prefix, variable_name, value):
- print 'const char k%s%s[] = "%s";' % (prefix, variable_name.capitalize(),
- (value % param_dict))
+ print('const char k%s%s[] = "%s";' % (prefix, variable_name.capitalize(),
+ (value % param_dict)))
def OutputCpp(param_dict, component, engine_common, engines):
@@ -122,18 +122,18 @@ def OutputCpp(param_dict, component, eng
engines: ditto.
"""
guard_name = 'MOZC_UNIX_IBUS_MAIN_H_'
- print CPP_HEADER % (guard_name, guard_name)
+ print(CPP_HEADER % (guard_name, guard_name))
for key in component:
OutputCppVariable(param_dict, 'Component', key, component[key])
for key in engine_common:
OutputCppVariable(param_dict, 'Engine', key, engine_common[key])
for key in engines:
- print 'const char* kEngine%sArray[] = {' % key.capitalize()
+ print('const char* kEngine%sArray[] = {' % key.capitalize())
for i in range(len(engines[key])):
- print '"%s",' % (engines[key][i] % param_dict)
- print '};'
- print 'const size_t kEngineArrayLen = %s;' % len(engines['name'])
- print CPP_FOOTER % guard_name
+ print('"%s",' % (engines[key][i] % param_dict))
+ print('};')
+ print('const size_t kEngineArrayLen = %s;' % len(engines['name']))
+ print(CPP_FOOTER % guard_name)
def CheckIBusVersion(options, minimum_version):
diff -pruN mozc-2.23.2815.102.orig/usage_stats/gen_stats_list.py mozc-2.23.2815.102/usage_stats/gen_stats_list.py
--- mozc-2.23.2815.102.orig/usage_stats/gen_stats_list.py 2019-08-02 14:22:24.496255545 +0900
+++ mozc-2.23.2815.102/usage_stats/gen_stats_list.py 2019-08-01 21:53:13.006788812 +0900
@@ -47,13 +47,13 @@ def GetStatsNameList(filename):
def main():
stats_list = GetStatsNameList(sys.argv[1])
- print '// This header file is generated by gen_stats_list.py'
+ print('// This header file is generated by gen_stats_list.py')
for stats in stats_list:
- print 'const char k%s[] = "%s";' % (stats, stats)
- print 'const char *kStatsList[] = {'
+ print('const char k%s[] = "%s";' % (stats, stats))
+ print('const char *kStatsList[] = {')
for stats in stats_list:
- print ' k%s,' % (stats)
- print '};'
+ print(' k%s,' % (stats))
+ print('};')
if __name__ == '__main__':