Run pyupgrade

chardet · Dec 10, 2020 · 8a67090 · 8a67090
1 parent c248586
commit 8a67090
Show file tree

Hide file tree

Showing 37 changed files with 126 additions and 152 deletions.
diff --git a/bench.py b/bench.py
@@ -5,13 +5,11 @@
 :author: Ian Cordasco
 """
 
-from __future__ import print_function, with_statement
 
 import argparse
 import sys
 import time
 from collections import defaultdict
-from io import open
 from os import listdir
 from os.path import dirname, isdir, join, realpath, relpath, splitext
 

diff --git a/chardet/big5prober.py b/chardet/big5prober.py
@@ -33,7 +33,7 @@
 
 class Big5Prober(MultiByteCharSetProber):
     def __init__(self):
-        super(Big5Prober, self).__init__()
+        super().__init__()
         self.coding_sm = CodingStateMachine(BIG5_SM_MODEL)
         self.distribution_analyzer = Big5DistributionAnalysis()
         self.reset()

diff --git a/chardet/chardistribution.py b/chardet/chardistribution.py
@@ -37,7 +37,7 @@
                       JIS_TYPICAL_DISTRIBUTION_RATIO)
 
 
-class CharDistributionAnalysis(object):
+class CharDistributionAnalysis:
     ENOUGH_DATA_THRESHOLD = 1024
     SURE_YES = 0.99
     SURE_NO = 0.01
@@ -112,7 +112,7 @@ def get_order(self, byte_str):
 
 class EUCTWDistributionAnalysis(CharDistributionAnalysis):
     def __init__(self):
-        super(EUCTWDistributionAnalysis, self).__init__()
+        super().__init__()
         self._char_to_freq_order = EUCTW_CHAR_TO_FREQ_ORDER
         self._table_size = EUCTW_TABLE_SIZE
         self.typical_distribution_ratio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
@@ -131,7 +131,7 @@ def get_order(self, byte_str):
 
 class EUCKRDistributionAnalysis(CharDistributionAnalysis):
     def __init__(self):
-        super(EUCKRDistributionAnalysis, self).__init__()
+        super().__init__()
         self._char_to_freq_order = EUCKR_CHAR_TO_FREQ_ORDER
         self._table_size = EUCKR_TABLE_SIZE
         self.typical_distribution_ratio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
@@ -150,7 +150,7 @@ def get_order(self, byte_str):
 
 class GB2312DistributionAnalysis(CharDistributionAnalysis):
     def __init__(self):
-        super(GB2312DistributionAnalysis, self).__init__()
+        super().__init__()
         self._char_to_freq_order = GB2312_CHAR_TO_FREQ_ORDER
         self._table_size = GB2312_TABLE_SIZE
         self.typical_distribution_ratio = GB2312_TYPICAL_DISTRIBUTION_RATIO
@@ -169,7 +169,7 @@ def get_order(self, byte_str):
 
 class Big5DistributionAnalysis(CharDistributionAnalysis):
     def __init__(self):
-        super(Big5DistributionAnalysis, self).__init__()
+        super().__init__()
         self._char_to_freq_order = BIG5_CHAR_TO_FREQ_ORDER
         self._table_size = BIG5_TABLE_SIZE
         self.typical_distribution_ratio = BIG5_TYPICAL_DISTRIBUTION_RATIO
@@ -191,7 +191,7 @@ def get_order(self, byte_str):
 
 class SJISDistributionAnalysis(CharDistributionAnalysis):
     def __init__(self):
-        super(SJISDistributionAnalysis, self).__init__()
+        super().__init__()
         self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
         self._table_size = JIS_TABLE_SIZE
         self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO
@@ -216,7 +216,7 @@ def get_order(self, byte_str):
 
 class EUCJPDistributionAnalysis(CharDistributionAnalysis):
     def __init__(self):
-        super(EUCJPDistributionAnalysis, self).__init__()
+        super().__init__()
         self._char_to_freq_order = JIS_CHAR_TO_FREQ_ORDER
         self._table_size = JIS_TABLE_SIZE
         self.typical_distribution_ratio = JIS_TYPICAL_DISTRIBUTION_RATIO

diff --git a/chardet/charsetgroupprober.py b/chardet/charsetgroupprober.py
@@ -31,13 +31,13 @@
 
 class CharSetGroupProber(CharSetProber):
     def __init__(self, lang_filter=None):
-        super(CharSetGroupProber, self).__init__(lang_filter=lang_filter)
+        super().__init__(lang_filter=lang_filter)
         self._active_num = 0
         self.probers = []
         self._best_guess_prober = None
 
     def reset(self):
-        super(CharSetGroupProber, self).reset()
+        super().reset()
         self._active_num = 0
         for prober in self.probers:
             if prober:

diff --git a/chardet/charsetprober.py b/chardet/charsetprober.py
@@ -32,7 +32,7 @@
 from .enums import ProbingState
 
 
-class CharSetProber(object):
+class CharSetProber:
 
     SHORTCUT_THRESHOLD = 0.95
 

diff --git a/chardet/cli/__init__.py b/chardet/cli/__init__.py
@@ -1 +0,0 @@
-

diff --git a/chardet/cli/chardetect.py b/chardet/cli/chardetect.py
@@ -12,7 +12,6 @@
 
 """
 
-from __future__ import absolute_import, print_function, unicode_literals
 
 import argparse
 import sys

diff --git a/chardet/codingstatemachine.py b/chardet/codingstatemachine.py
@@ -30,7 +30,7 @@
 from .enums import MachineState
 
 
-class CodingStateMachine(object):
+class CodingStateMachine:
     """
     A state machine to verify a byte sequence for a particular encoding. For
     each byte the detector receives, it will feed that byte to every active

diff --git a/chardet/compat.py b/chardet/compat.py
@@ -22,15 +22,8 @@
 import sys
 
 
-if sys.version_info < (3, 0):
-    PY2 = True
-    PY3 = False
-    string_types = (str, unicode)
-    text_type = unicode
-    iteritems = dict.iteritems
-else:
-    PY2 = False
-    PY3 = True
-    string_types = (bytes, str)
-    text_type = str
-    iteritems = dict.items
+PY2 = False
+PY3 = True
+string_types = (bytes, str)
+text_type = str
+iteritems = dict.items
diff --git a/chardet/cp949prober.py b/chardet/cp949prober.py
@@ -33,7 +33,7 @@
 
 class CP949Prober(MultiByteCharSetProber):
     def __init__(self):
-        super(CP949Prober, self).__init__()
+        super().__init__()
         self.coding_sm = CodingStateMachine(CP949_SM_MODEL)
         # NOTE: CP949 is a superset of EUC-KR, so the distribution should be
         #       not different.

diff --git a/chardet/enums.py b/chardet/enums.py
@@ -5,7 +5,7 @@
 """
 
 
-class InputState(object):
+class InputState:
     """
     This enum represents the different states a universal detector can be in.
     """
@@ -14,7 +14,7 @@ class InputState(object):
     HIGH_BYTE = 2
 
 
-class LanguageFilter(object):
+class LanguageFilter:
     """
     This enum represents the different language filters we can apply to a
     ``UniversalDetector``.
@@ -29,7 +29,7 @@ class LanguageFilter(object):
     CJK = CHINESE | JAPANESE | KOREAN
 
 
-class ProbingState(object):
+class ProbingState:
     """
     This enum represents the different states a prober can be in.
     """
@@ -38,7 +38,7 @@ class ProbingState(object):
     NOT_ME = 2
 
 
-class MachineState(object):
+class MachineState:
     """
     This enum represents the different states a state machine can be in.
     """
@@ -47,7 +47,7 @@ class MachineState(object):
     ITS_ME = 2
 
 
-class SequenceLikelihood(object):
+class SequenceLikelihood:
     """
     This enum represents the likelihood of a character following the previous one.
     """
@@ -62,7 +62,7 @@ def get_num_categories(cls):
         return 4
 
 
-class CharacterCategory(object):
+class CharacterCategory:
     """
     This enum represents the different categories language models for
     ``SingleByteCharsetProber`` put characters into.

diff --git a/chardet/escprober.py b/chardet/escprober.py
@@ -40,7 +40,7 @@ class EscCharSetProber(CharSetProber):
     """
 
     def __init__(self, lang_filter=None):
-        super(EscCharSetProber, self).__init__(lang_filter=lang_filter)
+        super().__init__(lang_filter=lang_filter)
         self.coding_sm = []
         if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED:
             self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL))
@@ -56,7 +56,7 @@ def __init__(self, lang_filter=None):
         self.reset()
 
     def reset(self):
-        super(EscCharSetProber, self).reset()
+        super().reset()
         for coding_sm in self.coding_sm:
             if not coding_sm:
                 continue

diff --git a/chardet/eucjpprober.py b/chardet/eucjpprober.py
@@ -35,14 +35,14 @@
 
 class EUCJPProber(MultiByteCharSetProber):
     def __init__(self):
-        super(EUCJPProber, self).__init__()
+        super().__init__()
         self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL)
         self.distribution_analyzer = EUCJPDistributionAnalysis()
         self.context_analyzer = EUCJPContextAnalysis()
         self.reset()
 
     def reset(self):
-        super(EUCJPProber, self).reset()
+        super().reset()
         self.context_analyzer.reset()
 
     @property

diff --git a/chardet/euckrprober.py b/chardet/euckrprober.py
@@ -33,7 +33,7 @@
 
 class EUCKRProber(MultiByteCharSetProber):
     def __init__(self):
-        super(EUCKRProber, self).__init__()
+        super().__init__()
         self.coding_sm = CodingStateMachine(EUCKR_SM_MODEL)
         self.distribution_analyzer = EUCKRDistributionAnalysis()
         self.reset()

diff --git a/chardet/euctwprober.py b/chardet/euctwprober.py
@@ -32,7 +32,7 @@
 
 class EUCTWProber(MultiByteCharSetProber):
     def __init__(self):
-        super(EUCTWProber, self).__init__()
+        super().__init__()
         self.coding_sm = CodingStateMachine(EUCTW_SM_MODEL)
         self.distribution_analyzer = EUCTWDistributionAnalysis()
         self.reset()

diff --git a/chardet/gb2312prober.py b/chardet/gb2312prober.py
@@ -32,7 +32,7 @@
 
 class GB2312Prober(MultiByteCharSetProber):
     def __init__(self):
-        super(GB2312Prober, self).__init__()
+        super().__init__()
         self.coding_sm = CodingStateMachine(GB2312_SM_MODEL)
         self.distribution_analyzer = GB2312DistributionAnalysis()
         self.reset()

diff --git a/chardet/hebrewprober.py b/chardet/hebrewprober.py
@@ -152,7 +152,7 @@ class HebrewProber(CharSetProber):
     LOGICAL_HEBREW_NAME = "windows-1255"
 
     def __init__(self):
-        super(HebrewProber, self).__init__()
+        super().__init__()
         self._final_char_logical_score = None
         self._final_char_visual_score = None
         self._prev = None

diff --git a/chardet/jpcntx.py b/chardet/jpcntx.py
@@ -113,7 +113,7 @@
 (0,4,0,3,0,3,0,3,0,3,5,5,3,3,3,3,4,3,4,3,3,3,4,4,4,3,3,3,3,4,3,5,3,3,1,3,2,4,5,5,5,5,4,3,4,5,5,3,2,2,3,3,3,3,2,3,3,1,2,3,2,4,3,3,3,4,0,4,0,2,0,4,3,2,2,1,2,0,3,0,0,4,1),
 )
 
-class JapaneseContextAnalysis(object):
+class JapaneseContextAnalysis:
     NUM_OF_CATEGORY = 6
     DONT_KNOW = -1
     ENOUGH_REL_THRESHOLD = 100
@@ -182,7 +182,7 @@ def get_order(self, byte_str):
 
 class SJISContextAnalysis(JapaneseContextAnalysis):
     def __init__(self):
-        super(SJISContextAnalysis, self).__init__()
+        super().__init__()
         self._charset_name = "SHIFT_JIS"
 
     @property

diff --git a/chardet/langbulgarianmodel.py b/chardet/langbulgarianmodel.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 from chardet.sbcharsetprober import SingleByteCharSetModel
 

diff --git a/chardet/langgreekmodel.py b/chardet/langgreekmodel.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 from chardet.sbcharsetprober import SingleByteCharSetModel
 

diff --git a/chardet/langhebrewmodel.py b/chardet/langhebrewmodel.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 from chardet.sbcharsetprober import SingleByteCharSetModel
 

diff --git a/chardet/langhungarianmodel.py b/chardet/langhungarianmodel.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 from chardet.sbcharsetprober import SingleByteCharSetModel
 

diff --git a/chardet/langrussianmodel.py b/chardet/langrussianmodel.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 from chardet.sbcharsetprober import SingleByteCharSetModel
 

diff --git a/chardet/langthaimodel.py b/chardet/langthaimodel.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 from chardet.sbcharsetprober import SingleByteCharSetModel
 

diff --git a/chardet/langturkishmodel.py b/chardet/langturkishmodel.py
@@ -1,5 +1,4 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
 from chardet.sbcharsetprober import SingleByteCharSetModel
 

diff --git a/chardet/latin1prober.py b/chardet/latin1prober.py
@@ -95,7 +95,7 @@
 
 class Latin1Prober(CharSetProber):
     def __init__(self):
-        super(Latin1Prober, self).__init__()
+        super().__init__()
         self._last_char_class = None
         self._freq_counter = None
         self.reset()

diff --git a/chardet/mbcharsetprober.py b/chardet/mbcharsetprober.py
@@ -37,13 +37,13 @@ class MultiByteCharSetProber(CharSetProber):
     """
 
     def __init__(self, lang_filter=None):
-        super(MultiByteCharSetProber, self).__init__(lang_filter=lang_filter)
+        super().__init__(lang_filter=lang_filter)
         self.distribution_analyzer = None
         self.coding_sm = None
         self._last_char = [0, 0]
 
     def reset(self):
-        super(MultiByteCharSetProber, self).reset()
+        super().reset()
         if self.coding_sm:
             self.coding_sm.reset()
         if self.distribution_analyzer:

diff --git a/chardet/mbcsgroupprober.py b/chardet/mbcsgroupprober.py
@@ -40,7 +40,7 @@
 
 class MBCSGroupProber(CharSetGroupProber):
     def __init__(self, lang_filter=None):
-        super(MBCSGroupProber, self).__init__(lang_filter=lang_filter)
+        super().__init__(lang_filter=lang_filter)
         self.probers = [
             UTF8Prober(),
             SJISProber(),