[45] | 1 | # -*- coding: utf-8 -*- |
---|
[71] | 2 | # |
---|
| 3 | # Copyright (C) 2010 by Atzm WATANABE <atzm@atzm.org> |
---|
| 4 | # |
---|
| 5 | # This program is free software; you can redistribute it and/or modify it |
---|
| 6 | # under the terms of the GNU General Public License (version 2) as |
---|
| 7 | # published by the Free Software Foundation. It is distributed in the |
---|
| 8 | # hope that it will be useful, but WITHOUT ANY WARRANTY; without even the |
---|
| 9 | # implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR |
---|
| 10 | # PURPOSE. See the GNU General Public License for more details. |
---|
| 11 | # |
---|
[47] | 12 | # $Id$ |
---|
[71] | 13 | # |
---|
[45] | 14 | |
---|
| 15 | import os |
---|
| 16 | import sys |
---|
[52] | 17 | import zlib |
---|
[45] | 18 | import token |
---|
| 19 | import parser |
---|
| 20 | |
---|
| 21 | import cc |
---|
| 22 | import pep8 |
---|
| 23 | |
---|
| 24 | |
---|
[52] | 25 | def _compseq(seq, level): |
---|
| 26 | c = zlib.compressobj(level) |
---|
| 27 | return ''.join([c.compress(chunk) for chunk in seq] + [c.flush()]) |
---|
| 28 | |
---|
| 29 | |
---|
| 30 | def _maxstrlen(seq, iferr=0): |
---|
| 31 | try: |
---|
| 32 | return max(len(l) for l in seq) |
---|
| 33 | except: |
---|
| 34 | return iferr |
---|
| 35 | |
---|
| 36 | |
---|
[45] | 37 | class Scorer: |
---|
[70] | 38 | def __init__(self, lines, compress_level=9): |
---|
[52] | 39 | self._code = ''.join(lines) |
---|
[70] | 40 | self._ccode = _compseq(lines, compress_level) |
---|
[45] | 41 | self._lines = lines |
---|
[52] | 42 | self._nlines = [l for l in lines |
---|
| 43 | if l.strip() and not l.strip().startswith('#')] |
---|
[45] | 44 | |
---|
[52] | 45 | self._astpl = parser.suite(self.code()).totuple() |
---|
| 46 | self._token_cache = {} |
---|
[45] | 47 | |
---|
[52] | 48 | self.complexity() |
---|
| 49 | self.style_errors() |
---|
[45] | 50 | |
---|
[52] | 51 | def tupletree(self): |
---|
| 52 | return self._astpl |
---|
| 53 | |
---|
| 54 | def code(self): |
---|
| 55 | return self._code |
---|
| 56 | |
---|
| 57 | def lines(self): |
---|
| 58 | return self._lines |
---|
| 59 | |
---|
| 60 | def uncommented_lines(self): |
---|
| 61 | return self._nlines |
---|
| 62 | |
---|
| 63 | def bytes(self): |
---|
| 64 | return len(self.code()) or 1 |
---|
| 65 | |
---|
| 66 | def uncommented_bytes(self): |
---|
| 67 | return sum(len(l) for l in self.uncommented_lines()) or 1 |
---|
| 68 | |
---|
| 69 | def rows(self): |
---|
| 70 | return len(self.lines()) or 1 |
---|
| 71 | |
---|
| 72 | def uncommented_rows(self): |
---|
| 73 | return len(self.uncommented_lines()) or 1 |
---|
| 74 | |
---|
[70] | 75 | def compressibility(self): |
---|
[52] | 76 | return float(len(self._ccode)) / self.bytes() |
---|
| 77 | |
---|
| 78 | def token_bytes(self, types): |
---|
| 79 | def _bytes(stp, bytes=0): |
---|
| 80 | if not stp: |
---|
| 81 | return bytes |
---|
| 82 | if stp[0] in types: |
---|
| 83 | bytes += len(stp[1]) |
---|
| 84 | else: |
---|
| 85 | for p in stp[1:]: |
---|
| 86 | bytes = _bytes(p, bytes) |
---|
| 87 | return bytes |
---|
| 88 | |
---|
| 89 | types = tuple(types) |
---|
| 90 | |
---|
[45] | 91 | try: |
---|
[52] | 92 | ret = self._token_cache[types] |
---|
| 93 | except KeyError: |
---|
| 94 | ret = self._token_cache[types] = _bytes(self.tupletree()) |
---|
| 95 | |
---|
| 96 | return ret |
---|
| 97 | |
---|
| 98 | def complexity(self, item='all', iferr=(256, 1)): |
---|
| 99 | try: |
---|
[45] | 100 | stat = cc.measure_complexity(self._code, item) |
---|
| 101 | ccpp = cc.PrettyPrinter(None, True) |
---|
| 102 | cplx = zip(*ccpp.flatten_stats(stat))[-1] |
---|
[52] | 103 | self._ccsum = sum(cplx) or 1 |
---|
| 104 | self._cclen = len(cplx) or 1 |
---|
[45] | 105 | except: |
---|
[52] | 106 | self._ccsum, self._cclen = iferr |
---|
| 107 | return self._ccsum, self._cclen |
---|
[45] | 108 | |
---|
[52] | 109 | def style_errors(self, name='', iferr=256): |
---|
[45] | 110 | pep8.process_options([name]) |
---|
| 111 | p8ck = pep8.Checker(None) |
---|
| 112 | p8ck.lines = self._lines |
---|
| 113 | p8ck.filename = name |
---|
| 114 | |
---|
| 115 | try: |
---|
| 116 | tmpfp = sys.stdout |
---|
| 117 | sys.stdout = open(os.devnull, 'w') |
---|
[52] | 118 | self._estyle = p8ck.check_all() or 1 |
---|
| 119 | except: |
---|
| 120 | self._estyle = iferr |
---|
[45] | 121 | finally: |
---|
| 122 | sys.stdout = tmpfp |
---|
[52] | 123 | return self._estyle |
---|
[45] | 124 | |
---|
[54] | 125 | def complex_score(self, coefficient=48): |
---|
[52] | 126 | maxlen = _maxstrlen(self.lines(), 256) |
---|
| 127 | score = self._cclen * coefficient |
---|
| 128 | score /= (maxlen / (coefficient * 2)) or 1 |
---|
| 129 | score /= (self._ccsum / ((coefficient / 3) or 1)) or 1 |
---|
| 130 | score *= self.compressibility() |
---|
| 131 | return int(score) or 1 |
---|
[45] | 132 | |
---|
[52] | 133 | def style_score(self, coefficient=64): |
---|
| 134 | data_bytes = self.token_bytes([token.NUMBER, token.STRING, |
---|
| 135 | token.NAME, token.COLON]) |
---|
| 136 | score = self.uncommented_bytes() - data_bytes |
---|
[79] | 137 | if score < 1: |
---|
| 138 | score = 1 |
---|
[52] | 139 | score /= (self.uncommented_rows() / coefficient) or 1 |
---|
| 140 | score /= self._estyle |
---|
| 141 | score *= (coefficient / 12) or 1 |
---|
| 142 | score *= self.compressibility() |
---|
| 143 | return int(score) or 1 |
---|
[45] | 144 | |
---|
[53] | 145 | def lines_score(self, coefficient=2.5): |
---|
[52] | 146 | maxlen = _maxstrlen(self.lines(), 256) |
---|
| 147 | data_bytes = self.token_bytes([token.NUMBER, token.STRING, |
---|
| 148 | token.NAME, token.COLON]) |
---|
| 149 | score = self.uncommented_bytes() - data_bytes |
---|
[79] | 150 | if score < 1: |
---|
| 151 | score = 1 |
---|
[52] | 152 | score /= (maxlen / self.uncommented_rows()) or 1 |
---|
| 153 | score /= self.uncommented_rows() |
---|
| 154 | score *= coefficient |
---|
| 155 | score *= self.compressibility() |
---|
| 156 | return int(score) or 1 |
---|
[45] | 157 | |
---|
[52] | 158 | def const_score(self, coefficient=2): |
---|
| 159 | const_bytes = self.token_bytes([token.NUMBER, token.STRING]) or 1 |
---|
| 160 | score = self.uncommented_bytes() / const_bytes |
---|
| 161 | score *= coefficient |
---|
| 162 | score *= self.compressibility() |
---|
| 163 | return int(score) or 1 |
---|
[45] | 164 | |
---|
[56] | 165 | def colon_score(self, coefficient=1.5): |
---|
[52] | 166 | colon_bytes = self.token_bytes([token.COLON]) or 1 |
---|
[56] | 167 | score = self.uncommented_bytes() / colon_bytes |
---|
[52] | 168 | score *= coefficient |
---|
| 169 | score *= self.compressibility() |
---|
| 170 | return int(score) or 1 |
---|
[45] | 171 | |
---|
[56] | 172 | def name_score(self, coefficient=48): |
---|
[52] | 173 | name_bytes = self.token_bytes([token.NAME]) or 1 |
---|
| 174 | score = self.uncommented_bytes() |
---|
| 175 | score /= (name_bytes / coefficient) or 1 |
---|
| 176 | score *= self.compressibility() |
---|
| 177 | return int(score) or 1 |
---|