mirror of
https://github.com/codespell-project/codespell.git
synced 2025-08-06 09:40:56 +08:00
ENH: Add Python2.7 support
This commit is contained in:
Eric Larson
@ -20,6 +20,7 @@ Copyright (C) 2011 ProFUSION embedded systems
|
||||
|
||||
from __future__ import print_function
|
||||
|
||||
import codecs
|
||||
import sys
|
||||
import re
|
||||
from optparse import OptionParser
|
||||
@ -50,7 +51,7 @@ default_dictionary = os.path.join(os.path.dirname(os.path.realpath(__file__)),
|
||||
# file1 .. fileN Files to check spelling
|
||||
|
||||
|
||||
class QuietLevels:
|
||||
class QuietLevels(object):
|
||||
NONE = 0
|
||||
ENCODING = 1
|
||||
BINARY_FILE = 2
|
||||
@ -59,7 +60,7 @@ class QuietLevels:
|
||||
FIXES = 16
|
||||
|
||||
|
||||
class GlobMatch:
|
||||
class GlobMatch(object):
|
||||
def __init__(self, pattern):
|
||||
if pattern:
|
||||
self.pattern_list = pattern.split(',')
|
||||
@ -77,14 +78,14 @@ class GlobMatch:
|
||||
return False
|
||||
|
||||
|
||||
class Misspelling:
|
||||
class Misspelling(object):
|
||||
def __init__(self, data, fix, reason):
|
||||
self.data = data
|
||||
self.fix = fix
|
||||
self.reason = reason
|
||||
|
||||
|
||||
class TermColors:
|
||||
class TermColors(object):
|
||||
def __init__(self):
|
||||
self.FILE = '\033[33m'
|
||||
self.WWORD = '\033[31m'
|
||||
@ -98,7 +99,7 @@ class TermColors:
|
||||
self.DISABLE = ''
|
||||
|
||||
|
||||
class Summary:
|
||||
class Summary(object):
|
||||
def __init__(self):
|
||||
self.summary = {}
|
||||
|
||||
@ -118,7 +119,7 @@ class Summary:
|
||||
width=15 - len(key)) for key in keys])
|
||||
|
||||
|
||||
class FileOpener:
|
||||
class FileOpener(object):
|
||||
def __init__(self, use_chardet):
|
||||
self.use_chardet = use_chardet
|
||||
if use_chardet:
|
||||
@ -142,7 +143,7 @@ class FileOpener:
|
||||
|
||||
def open_with_chardet(self, filename):
|
||||
self.encdetector.reset()
|
||||
with open(filename, 'rb') as f:
|
||||
with codecs.open(filename, 'rb') as f:
|
||||
for line in f:
|
||||
self.encdetector.feed(line)
|
||||
if self.encdetector.done:
|
||||
@ -151,8 +152,7 @@ class FileOpener:
|
||||
encoding = self.encdetector.result['encoding']
|
||||
|
||||
try:
|
||||
f = open(filename, 'r', encoding=encoding, newline='')
|
||||
lines = f.readlines()
|
||||
f = codecs.open(filename, 'r', encoding=encoding)
|
||||
except UnicodeDecodeError:
|
||||
print('ERROR: Could not detect encoding: %s' % filename,
|
||||
file=sys.stderr)
|
||||
@ -161,7 +161,8 @@ class FileOpener:
|
||||
print('ERROR: %s -- Don\'t know how to handle encoding %s'
|
||||
% (filename, encoding), file=sys.stderr)
|
||||
raise
|
||||
finally:
|
||||
else:
|
||||
lines = f.readlines()
|
||||
f.close()
|
||||
|
||||
return lines, encoding
|
||||
@ -172,9 +173,7 @@ class FileOpener:
|
||||
|
||||
while True:
|
||||
try:
|
||||
f = open(filename, 'r', encoding=encodings[curr], newline='')
|
||||
lines = f.readlines()
|
||||
break
|
||||
f = codecs.open(filename, 'r', encoding=encodings[curr])
|
||||
except UnicodeDecodeError:
|
||||
if not quiet_level & QuietLevels.ENCODING:
|
||||
print('WARNING: Decoding file %s' % filename,
|
||||
@ -188,10 +187,10 @@ class FileOpener:
|
||||
pass
|
||||
|
||||
curr += 1
|
||||
|
||||
finally:
|
||||
else:
|
||||
lines = f.readlines()
|
||||
f.close()
|
||||
|
||||
break
|
||||
if not lines:
|
||||
raise Exception('Unknown encoding')
|
||||
|
||||
@ -265,25 +264,20 @@ def parse_options(args):
|
||||
|
||||
(o, args) = parser.parse_args(list(args))
|
||||
|
||||
if not os.path.exists(o.dictionary):
|
||||
print('ERROR: cannot find dictionary file!', file=sys.stderr)
|
||||
parser.print_help()
|
||||
sys.exit(1)
|
||||
|
||||
if not args:
|
||||
args.append('.')
|
||||
|
||||
return o, args
|
||||
return o, args, parser
|
||||
|
||||
|
||||
def build_exclude_hashes(filename):
|
||||
with open(filename, 'r') as f:
|
||||
with codecs.open(filename, 'r') as f:
|
||||
for line in f:
|
||||
exclude_lines.add(line)
|
||||
|
||||
|
||||
def build_dict(filename):
|
||||
with open(filename, 'r', 1, 'utf-8') as f:
|
||||
with codecs.open(filename, mode='r', buffering=1, encoding='utf-8') as f:
|
||||
for line in f:
|
||||
[key, data] = line.split('->')
|
||||
data = data.strip()
|
||||
@ -317,10 +311,9 @@ def is_hidden(filename):
|
||||
def is_text_file(filename):
|
||||
with open(filename, mode='rb') as f:
|
||||
s = f.read(1024)
|
||||
if 0 in s:
|
||||
return False
|
||||
|
||||
return True
|
||||
if b'\x00' in s:
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def fix_case(word, fixword):
|
||||
@ -399,25 +392,22 @@ def parse_file(filename, colors, summary):
|
||||
lines = f.readlines()
|
||||
else:
|
||||
# ignore binary files
|
||||
try:
|
||||
text = is_text_file(filename)
|
||||
except FileNotFoundError:
|
||||
if not os.path.isfile(filename):
|
||||
return 0
|
||||
text = is_text_file(filename)
|
||||
if not text:
|
||||
if not quiet_level & QuietLevels.BINARY_FILE:
|
||||
print("WARNING: Binary file: %s " % filename, file=sys.stderr)
|
||||
return 0
|
||||
try:
|
||||
lines, encoding = file_opener.open(filename)
|
||||
except:
|
||||
except Exception:
|
||||
return 0
|
||||
|
||||
i = 1
|
||||
bad_count = 0
|
||||
rx = re.compile(r"[\w\-']+")
|
||||
for line in lines:
|
||||
for i, line in enumerate(lines):
|
||||
if line in exclude_lines:
|
||||
i += 1
|
||||
continue
|
||||
|
||||
fixed_words = set()
|
||||
@ -438,7 +428,7 @@ def parse_file(filename, colors, summary):
|
||||
if summary and fix:
|
||||
summary.update(lword)
|
||||
|
||||
if word in fixed_words:
|
||||
if word in fixed_words: # can skip because of re.sub below
|
||||
continue
|
||||
|
||||
if options.write_changes and fix:
|
||||
@ -487,7 +477,6 @@ def parse_file(filename, colors, summary):
|
||||
% {'LINE': cline, 'STRLINE': line.strip(),
|
||||
'WRONGWORD': cwrongword,
|
||||
'RIGHTWORD': crightword, 'REASON': creason})
|
||||
i += 1
|
||||
|
||||
if changed:
|
||||
if filename == '-':
|
||||
@ -499,18 +488,25 @@ def parse_file(filename, colors, summary):
|
||||
print("%sFIXED:%s %s"
|
||||
% (colors.FWORD, colors.DISABLE, filename),
|
||||
file=sys.stderr)
|
||||
f = open(filename, 'w', encoding=encoding)
|
||||
f.writelines(lines)
|
||||
f.close()
|
||||
with codecs.open(filename, 'w', encoding=encoding) as f:
|
||||
f.writelines(lines)
|
||||
return bad_count
|
||||
|
||||
|
||||
def main(*args):
|
||||
"""Contains flow control"""
|
||||
global options
|
||||
global quiet_level
|
||||
global file_opener
|
||||
|
||||
(options, args) = parse_options(args)
|
||||
options, args, parser = parse_options(args)
|
||||
|
||||
if not os.path.exists(options.dictionary):
|
||||
print(default_dictionary)
|
||||
print('ERROR: cannot find dictionary file:\n%s' % options.dictionary,
|
||||
file=sys.stderr)
|
||||
parser.print_help()
|
||||
sys.exit(1)
|
||||
|
||||
build_dict(options.dictionary)
|
||||
colors = TermColors()
|
||||
@ -540,26 +536,24 @@ def main(*args):
|
||||
|
||||
if os.path.isdir(filename):
|
||||
for root, dirs, files in os.walk(filename):
|
||||
i = 0
|
||||
for d in dirs:
|
||||
if is_hidden(d):
|
||||
del dirs[i]
|
||||
else:
|
||||
i += 1
|
||||
|
||||
for file in files:
|
||||
fname = os.path.join(root, file)
|
||||
# i = 0
|
||||
# for d in dirs:
|
||||
# if is_hidden(d):
|
||||
# del dirs[i]
|
||||
# else:
|
||||
# i += 1
|
||||
for file_ in files:
|
||||
fname = os.path.join(root, file_)
|
||||
if not os.path.isfile(fname):
|
||||
continue
|
||||
if not os.path.getsize(fname):
|
||||
continue
|
||||
if glob_match.match(file):
|
||||
if glob_match.match(file_):
|
||||
continue
|
||||
bad_count += parse_file(fname, colors, summary)
|
||||
|
||||
continue
|
||||
|
||||
bad_count += parse_file(filename, colors, summary)
|
||||
else:
|
||||
bad_count += parse_file(filename, colors, summary)
|
||||
|
||||
if summary:
|
||||
print("\n-------8<-------\nSUMMARY:")
|
||||
|
||||
Reference in New Issue
Block a user