Mercurial Repositories > eric / file comparison
comparison: eric6/Plugins/CheckerPlugins/CodeStyleChecker/eradicate.py
eric6/Plugins/CheckerPlugins/CodeStyleChecker/eradicate.py
- changeset 7040
- f89952e5fc11
- child 7639
- 422fd05e9c91
equal
deleted
inserted
replaced
| 7039:73cb6384a71f | 7040:f89952e5fc11 |
|---|---|
| 1 # Copyright (C) 2012-2015 Steven Myint | |
| 2 # | |
| 3 # Permission is hereby granted, free of charge, to any person obtaining | |
| 4 # a copy of this software and associated documentation files (the | |
| 5 # "Software"), to deal in the Software without restriction, including | |
| 6 # without limitation the rights to use, copy, modify, merge, publish, | |
| 7 # distribute, sublicense, and/or sell copies of the Software, and to | |
| 8 # permit persons to whom the Software is furnished to do so, subject to | |
| 9 # the following conditions: | |
| 10 # | |
| 11 # The above copyright notice and this permission notice shall be included | |
| 12 # in all copies or substantial portions of the Software. | |
| 13 # | |
| 14 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, | |
| 15 # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF | |
| 16 # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. | |
| 17 # IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY | |
| 18 # CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, | |
| 19 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE | |
| 20 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. | |
| 21 | |
| 22 """Removes commented-out Python code.""" | |
| 23 | |
| 24 from __future__ import print_function | |
| 25 from __future__ import unicode_literals | |
| 26 | |
| 27 import difflib | |
| 28 import io | |
| 29 import os | |
| 30 import re | |
| 31 import tokenize | |
| 32 | |
| 33 __version__ = '1.0' | |
| 34 | |
| 35 | |
| 36 MULTILINE_ASSIGNMENT_REGEX = re.compile(r'^\s*\w+\s*=.*[(\[{]$') | |
| 37 PARTIAL_DICTIONARY_REGEX = re.compile(r'^\s*[\'"]\w+[\'"]\s*:.+[,{]\s*$') | |
| 38 | |
| 39 | |
| 40 def comment_contains_code(line, aggressive=True): | |
| 41 """Return True comment contains code.""" | |
| 42 line = line.lstrip() | |
| 43 if not line.startswith('#'): | |
| 44 return False | |
| 45 | |
| 46 line = line.lstrip(' \t\v\n#').strip() | |
| 47 | |
| 48 # Ignore non-comment related hashes. For example, "# Issue #999". | |
| 49 if re.search('#[0-9]', line): | |
| 50 return False | |
| 51 | |
| 52 if line.startswith('pylint:'): | |
| 53 return False | |
| 54 | |
| 55 if re.match(r'.*?coding[:=][ \t]*([-_.a-zA-Z0-9]+)', line): | |
| 56 return False | |
| 57 | |
| 58 # Check that this is possibly code. | |
| 59 for symbol in list('()[]{}:=%') + ['print', 'return', 'break', 'continue', | |
| 60 'import']: | |
| 61 if symbol in line: | |
| 62 break | |
| 63 else: | |
| 64 return False | |
| 65 | |
| 66 if multiline_case(line, aggressive=aggressive): | |
| 67 return True | |
| 68 | |
| 69 symbol_list = [r'elif\s+.*', 'else', 'try', | |
| 70 'finally', r'except\s+.*'] | |
| 71 if aggressive: | |
| 72 symbol_list.append(r'if\s+.*') | |
| 73 | |
| 74 for symbol in symbol_list: | |
| 75 if re.match(r'^\s*' + symbol + r'\s*:\s*$', line): | |
| 76 return True | |
| 77 | |
| 78 line = re.sub(r'^(print|return)\b\s*', '', line) | |
| 79 | |
| 80 if re.match(PARTIAL_DICTIONARY_REGEX, line): | |
| 81 return True | |
| 82 | |
| 83 try: | |
| 84 compile(line, '<string>', 'exec') | |
| 85 return True | |
| 86 except (SyntaxError, TypeError, UnicodeDecodeError): | |
| 87 return False | |
| 88 | |
| 89 | |
| 90 def multiline_case(line, aggressive=True): | |
| 91 """Return True if line is probably part of some multiline code.""" | |
| 92 if aggressive: | |
| 93 for ending in ')]}': | |
| 94 if line.endswith(ending + ':'): | |
| 95 return True | |
| 96 | |
| 97 if line.strip() == ending + ',': | |
| 98 return True | |
| 99 | |
| 100 # Check whether a function/method definition with return value | |
| 101 # annotation | |
| 102 if re.search(r"def .+\)[\s]+->[\s]+[a-zA-Z_][a-zA-Z0-9_]*:$", line): | |
| 103 return True | |
| 104 | |
| 105 # Check weather a with statement | |
| 106 if re.search(r"with .+ as [a-zA-Z_][a-zA-Z0-9_]*:$", line): | |
| 107 return True | |
| 108 | |
| 109 # Check weather a for statement | |
| 110 if re.search(r"for [a-zA-Z_][a-zA-Z0-9_]* in .+:$", line): | |
| 111 return True | |
| 112 | |
| 113 if line.endswith('\\'): | |
| 114 return True | |
| 115 | |
| 116 if re.match(MULTILINE_ASSIGNMENT_REGEX, line): | |
| 117 return True | |
| 118 | |
| 119 if re.match(r'^[()\[\]{}\s]+$', line): | |
| 120 return True | |
| 121 | |
| 122 return False | |
| 123 | |
| 124 | |
| 125 def commented_out_code_line_numbers(source, aggressive=True): | |
| 126 """Yield line numbers of commented-out code.""" | |
| 127 sio = io.StringIO(source) | |
| 128 try: | |
| 129 for token in tokenize.generate_tokens(sio.readline): | |
| 130 token_type = token[0] | |
| 131 start_row = token[2][0] | |
| 132 line = token[4] | |
| 133 | |
| 134 if (token_type == tokenize.COMMENT and | |
| 135 line.lstrip().startswith('#') and | |
| 136 not line.lstrip().startswith('##') and | |
| 137 # modified from original file (line added) | |
| 138 comment_contains_code(line, aggressive)): | |
| 139 yield start_row | |
| 140 except (tokenize.TokenError, IndentationError): | |
| 141 pass | |
| 142 | |
| 143 | |
| 144 def filter_commented_out_code(source, aggressive=True): | |
| 145 """Yield code with commented out code removed.""" | |
| 146 marked_lines = list(commented_out_code_line_numbers(source, | |
| 147 aggressive)) | |
| 148 sio = io.StringIO(source) | |
| 149 previous_line = '' | |
| 150 for line_number, line in enumerate(sio.readlines(), start=1): | |
| 151 if (line_number not in marked_lines or | |
| 152 previous_line.rstrip().endswith('\\')): | |
| 153 yield line | |
| 154 previous_line = line | |
| 155 | |
| 156 | |
| 157 def fix_file(filename, args, standard_out): | |
| 158 """Run filter_commented_out_code() on file.""" | |
| 159 encoding = detect_encoding(filename) | |
| 160 with open_with_encoding(filename, encoding=encoding) as input_file: | |
| 161 source = input_file.read() | |
| 162 | |
| 163 filtered_source = ''.join(filter_commented_out_code(source, | |
| 164 args.aggressive)) | |
| 165 | |
| 166 if source != filtered_source: | |
| 167 if args.in_place: | |
| 168 with open_with_encoding(filename, mode='w', | |
| 169 encoding=encoding) as output_file: | |
| 170 output_file.write(filtered_source) | |
| 171 else: | |
| 172 diff = difflib.unified_diff( | |
| 173 source.splitlines(), | |
| 174 filtered_source.splitlines(), | |
| 175 'before/' + filename, | |
| 176 'after/' + filename, | |
| 177 lineterm='') | |
| 178 standard_out.write('\n'.join(list(diff) + [''])) | |
| 179 | |
| 180 | |
| 181 def open_with_encoding(filename, encoding, mode='r'): | |
| 182 """Return opened file with a specific encoding.""" | |
| 183 return io.open(filename, mode=mode, encoding=encoding, | |
| 184 newline='') # Preserve line endings | |
| 185 | |
| 186 | |
| 187 def detect_encoding(filename): | |
| 188 """Return file encoding.""" | |
| 189 try: | |
| 190 with open(filename, 'rb') as input_file: | |
| 191 from lib2to3.pgen2 import tokenize as lib2to3_tokenize | |
| 192 encoding = lib2to3_tokenize.detect_encoding(input_file.readline)[0] | |
| 193 | |
| 194 # Check for correctness of encoding. | |
| 195 with open_with_encoding(filename, encoding) as input_file: | |
| 196 input_file.read() | |
| 197 | |
| 198 return encoding | |
| 199 except (SyntaxError, LookupError, UnicodeDecodeError): | |
| 200 return 'latin-1' | |
| 201 | |
| 202 | |
| 203 def main(argv, standard_out, standard_error): | |
| 204 """Main entry point.""" | |
| 205 import argparse | |
| 206 parser = argparse.ArgumentParser(description=__doc__, prog='eradicate') | |
| 207 parser.add_argument('-i', '--in-place', action='store_true', | |
| 208 help='make changes to files instead of printing diffs') | |
| 209 parser.add_argument('-r', '--recursive', action='store_true', | |
| 210 help='drill down directories recursively') | |
| 211 parser.add_argument('-a', '--aggressive', action='store_true', | |
| 212 help='make more aggressive changes; ' | |
| 213 'this may result in false positives') | |
| 214 parser.add_argument('--version', action='version', | |
| 215 version='%(prog)s ' + __version__) | |
| 216 parser.add_argument('files', nargs='+', help='files to format') | |
| 217 | |
| 218 args = parser.parse_args(argv[1:]) | |
| 219 | |
| 220 filenames = list(set(args.files)) | |
| 221 while filenames: | |
| 222 name = filenames.pop(0) | |
| 223 if args.recursive and os.path.isdir(name): | |
| 224 for root, directories, children in os.walk('{}'.format(name)): | |
| 225 filenames += [os.path.join(root, f) for f in children | |
| 226 if f.endswith('.py') and | |
| 227 not f.startswith('.')] | |
| 228 directories[:] = [d for d in directories | |
| 229 if not d.startswith('.')] | |
| 230 else: | |
| 231 try: | |
| 232 fix_file(name, args=args, standard_out=standard_out) | |
| 233 except IOError as exception: | |
| 234 print('{}'.format(exception), file=standard_error) |
