diff options
| -rw-r--r-- | coverage/parser.py | 86 | ||||
| -rw-r--r-- | coverage/python.py | 11 | ||||
| -rw-r--r-- | lab/parser.py | 19 | ||||
| -rw-r--r-- | tests/test_parser.py | 11 | ||||
| -rw-r--r-- | tox.ini | 5 |
5 files changed, 63 insertions, 69 deletions
diff --git a/coverage/parser.py b/coverage/parser.py index a5e96237..111826da 100644 --- a/coverage/parser.py +++ b/coverage/parser.py @@ -12,7 +12,7 @@ import tokenize from coverage.backward import range # pylint: disable=redefined-builtin from coverage.backward import bytes_to_ints from coverage.bytecode import ByteCodes, CodeObjects -from coverage.misc import contract, nice_pair, expensive, join_regex +from coverage.misc import contract, nice_pair, join_regex from coverage.misc import CoverageException, NoSource, NotPython from coverage.phystokens import compile_unicode, generate_tokens @@ -42,25 +42,39 @@ class PythonParser(object): self.exclude = exclude - self.show_tokens = False - # The text lines of the parsed code. self.lines = self.text.split('\n') - # The line numbers of excluded lines of code. + # The normalized line numbers of the statements in the code. Exclusions + # are taken into account, and statements are adjusted to their first + # lines. + self.statements = set() + + # The normalized line numbers of the excluded lines in the code, + # adjusted to their first lines. self.excluded = set() - # The line numbers of docstring lines. - self.docstrings = set() + # The raw_* attributes are only used in this class, and in + # lab/parser.py to show how this class is working. + + # The line numbers that start statements, as reported by the line + # number table in the bytecode. + self.raw_statements = set() + + # The raw line numbers of excluded lines of code, as marked by pragmas. + self.raw_excluded = set() # The line numbers of class definitions. - self.classdefs = set() + self.raw_classdefs = set() - # A dict mapping line numbers to (lo,hi) for multi-line statements. - self.multiline = {} + # The line numbers of docstring lines. + self.raw_docstrings = set() + + # Internal detail, used by lab/parser.py. + self.show_tokens = False - # The line numbers that start statements. - self.statement_starts = set() + # A dict mapping line numbers to (lo,hi) for multi-line statements. + self._multiline = {} # Lazily-created ByteParser and arc data. self._byte_parser = None @@ -91,12 +105,12 @@ class PythonParser(object): def _raw_parse(self): """Parse the source to find the interesting facts about its lines. - A handful of member fields are updated. + A handful of attributes are updated. """ # Find lines which match an exclusion pattern. if self.exclude: - self.excluded = self.lines_matching(self.exclude) + self.raw_excluded = self.lines_matching(self.exclude) # Tokenize, to find excluded suites, to find docstrings, and to find # multi-line statements. @@ -122,9 +136,9 @@ class PythonParser(object): # Class definitions look like branches in the byte code, so # we need to exclude them. The simplest way is to note the # lines with the 'class' keyword. - self.classdefs.add(slineno) + self.raw_classdefs.add(slineno) elif toktype == token.OP and ttext == ':': - if not excluding and elineno in self.excluded: + if not excluding and elineno in self.raw_excluded: # Start excluding a suite. We trigger off of the colon # token so that the #pragma comment will be recognized on # the same line as the colon. @@ -135,14 +149,14 @@ class PythonParser(object): # (a trick from trace.py in the stdlib.) This works for # 99.9999% of cases. For the rest (!) see: # http://stackoverflow.com/questions/1769332/x/1769794#1769794 - self.docstrings.update(range(slineno, elineno+1)) + self.raw_docstrings.update(range(slineno, elineno+1)) elif toktype == token.NEWLINE: if first_line is not None and elineno != first_line: # We're at the end of a line, and we've ended on a # different line than the first line of the statement, # so record a multi-line range. for l in range(first_line, elineno+1): - self.multiline[l] = first_line + self._multiline[l] = first_line first_line = None if ttext.strip() and toktype != tokenize.COMMENT: @@ -156,17 +170,17 @@ class PythonParser(object): if excluding and indent <= exclude_indent: excluding = False if excluding: - self.excluded.add(elineno) + self.raw_excluded.add(elineno) prev_toktype = toktype # Find the starts of the executable statements. if not empty: - self.statement_starts.update(self.byte_parser._find_statements()) + self.raw_statements.update(self.byte_parser._find_statements()) def first_line(self, line): """Return the first line number of the statement including `line`.""" - first_line = self.multiline.get(line) + first_line = self._multiline.get(line) if first_line: return first_line else: @@ -187,20 +201,13 @@ class PythonParser(object): def translate_arcs(self, arcs): """Implement `FileReporter.translate_arcs`.""" - return [ - (self.first_line(a), self.first_line(b)) - for (a, b) in arcs - ] + return [(self.first_line(a), self.first_line(b)) for (a, b) in arcs] - @expensive def parse_source(self): """Parse source text to find executable lines, excluded lines, etc. - Return values are 1) a set of executable line numbers, and 2) a set of - excluded line numbers. - - Reported line numbers are normalized to the first line of multi-line - statements. + Sets the .excluded and .statements attributes, normalized to the first + line of multi-line statements. """ try: @@ -216,15 +223,11 @@ class PythonParser(object): ) ) - excluded_lines = self.first_lines(self.excluded) - ignore = set() - ignore.update(excluded_lines) - ignore.update(self.docstrings) - starts = self.statement_starts - ignore - lines = self.first_lines(starts) - lines -= ignore + self.excluded = self.first_lines(self.raw_excluded) - return lines, excluded_lines + ignore = self.excluded | self.raw_docstrings + starts = self.raw_statements - ignore + self.statements = self.first_lines(starts) - ignore def arcs(self): """Get information about the arcs available in the code. @@ -248,22 +251,21 @@ class PythonParser(object): Excluded lines are excluded. """ - excluded_lines = self.first_lines(self.excluded) exit_counts = collections.defaultdict(int) for l1, l2 in self.arcs(): if l1 < 0: # Don't ever report -1 as a line number continue - if l1 in excluded_lines: + if l1 in self.excluded: # Don't report excluded lines as line numbers. continue - if l2 in excluded_lines: + if l2 in self.excluded: # Arcs to excluded lines shouldn't count. continue exit_counts[l1] += 1 # Class definitions have one extra exit, so remove one for each: - for l in self.classdefs: + for l in self.raw_classdefs: # Ensure key is there: class definitions can include excluded lines. if l in exit_counts: exit_counts[l] -= 1 diff --git a/coverage/python.py b/coverage/python.py index 4f589735..5e563828 100644 --- a/coverage/python.py +++ b/coverage/python.py @@ -130,21 +130,16 @@ class PythonFileReporter(FileReporter): filename=self.filename, exclude=self.coverage._exclude_regex('exclude'), ) + self._parser.parse_source() return self._parser - @expensive def lines(self): """Return the line numbers of statements in the file.""" - if self._statements is None: - self._statements, self._excluded = self.parser.parse_source() - return self._statements + return self.parser.statements - @expensive def excluded_lines(self): """Return the line numbers of statements in the file.""" - if self._excluded is None: - self._statements, self._excluded = self.parser.parse_source() - return self._excluded + return self.parser.excluded def translate_lines(self, lines): return self.parser.translate_lines(lines) diff --git a/lab/parser.py b/lab/parser.py index 97c81d89..bb593f8f 100644 --- a/lab/parser.py +++ b/lab/parser.py @@ -17,6 +17,7 @@ from coverage.python import get_python_source opcode_counts = collections.Counter() + class ParserMain(object): """A main for code parsing experiments.""" @@ -69,7 +70,6 @@ class ParserMain(object): for opcode, number in opcode_counts.most_common(): print("{0:20s} {1:6d} {2:.1%}".format(opcode, number, number/total)) - def one_file(self, options, filename): """Process just one file.""" @@ -85,7 +85,7 @@ class ParserMain(object): self.disassemble(bp, histogram=options.histogram) arcs = bp._all_arcs() - if options.chunks:# and not options.dis: + if options.chunks: chunks = bp._all_chunks() if options.recursive: print("%6d: %s" % (len(chunks), filename)) @@ -96,7 +96,7 @@ class ParserMain(object): if options.source or options.tokens: cp = PythonParser(filename=filename, exclude=r"no\s*cover") cp.show_tokens = options.tokens - cp._raw_parse() + cp.parse_source() if options.source: if options.chunks: @@ -108,21 +108,19 @@ class ParserMain(object): for lineno, ltext in enumerate(cp.lines, start=1): m0 = m1 = m2 = m3 = a = ' ' - if lineno in cp.statement_starts: + if lineno in cp.raw_statements: m0 = '-' exits = exit_counts.get(lineno, 0) if exits > 1: m1 = str(exits) - if lineno in cp.docstrings: + if lineno in cp.raw_docstrings: m2 = '"' - if lineno in cp.classdefs: + if lineno in cp.raw_classdefs: m2 = 'C' - if lineno in cp.excluded: + if lineno in cp.raw_excluded: m3 = 'x' a = arc_chars[lineno].ljust(arc_width) - print("%4d %s%s%s%s%s %s" % - (lineno, m0, m1, m2, m3, a, ltext) - ) + print("%4d %s%s%s%s%s %s" % (lineno, m0, m1, m2, m3, a, ltext)) def disassemble(self, byte_parser, histogram=False): """Disassemble code, for ad-hoc experimenting.""" @@ -199,4 +197,3 @@ class ParserMain(object): if __name__ == '__main__': ParserMain().main(sys.argv[1:]) - diff --git a/tests/test_parser.py b/tests/test_parser.py index 84b9a214..372bf79b 100644 --- a/tests/test_parser.py +++ b/tests/test_parser.py @@ -142,9 +142,8 @@ class ParserFileTest(CoverageTest): def parse_file(self, filename): """Parse `text` as source, and return the `PythonParser` used.""" - # pylint: disable=attribute-defined-outside-init parser = PythonParser(filename=filename, exclude="nocover") - self.statements, self.excluded = parser.parse_source() + parser.parse_source() return parser def test_line_endings(self): @@ -191,8 +190,8 @@ class ParserFileTest(CoverageTest): stderr=subprocess.PIPE).communicate() """) - self.parse_file("normal.py") - self.assertEqual(self.statements, set([1])) + parser = self.parse_file("normal.py") + self.assertEqual(parser.statements, set([1])) self.make_file("abrupt.py", """\ out, err = subprocess.Popen( @@ -204,5 +203,5 @@ class ParserFileTest(CoverageTest): with open("abrupt.py") as f: self.assertEqual(f.read()[-1], ")") - self.parse_file("abrupt.py") - self.assertEqual(self.statements, set([1])) + parser = self.parse_file("abrupt.py") + self.assertEqual(parser.statements, set([1])) @@ -65,9 +65,10 @@ commands = # Yes, pep8 will read its settings from tox.ini! [pep8] -# E265: block comment should start with '# ' +# E265 block comment should start with '# ' +# E266 too many leading '#' for block comment # E301 expected 1 blank line, found 0 # E401 multiple imports on one line # The rest are the default ignored warnings. -ignore = E265,E123,E133,E226,E241,E242,E301,E401 +ignore = E265,E266,E123,E133,E226,E241,E242,E301,E401 max-line-length = 100 |