diff options
Diffstat (limited to 'coverage/parser.py')
| -rw-r--r-- | coverage/parser.py | 60 |
1 files changed, 34 insertions, 26 deletions
diff --git a/coverage/parser.py b/coverage/parser.py index f488367d..a2b1b610 100644 --- a/coverage/parser.py +++ b/coverage/parser.py @@ -1,4 +1,7 @@ -"""Code parsing for Coverage.""" +# Licensed under the Apache License: http://www.apache.org/licenses/LICENSE-2.0 +# For details: https://bitbucket.org/ned/coveragepy/src/default/NOTICE.txt + +"""Code parsing for coverage.py.""" import collections import dis @@ -9,9 +12,9 @@ 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 nice_pair, expensive, join_regex +from coverage.misc import contract, nice_pair, expensive, join_regex from coverage.misc import CoverageException, NoSource, NotPython -from coverage.phystokens import generate_tokens +from coverage.phystokens import compile_unicode, generate_tokens class CodeParser(object): @@ -34,6 +37,7 @@ class CodeParser(object): class PythonParser(CodeParser): """Parse code to find executable lines, excluded lines, etc.""" + @contract(text='unicode|None') def __init__(self, text=None, filename=None, exclude=None): """ Source can be provided as `text`, the text itself, or `filename`, from @@ -53,14 +57,6 @@ class PythonParser(CodeParser): "No source for code: '%s': %s" % (self.filename, err) ) - if self.text: - assert isinstance(self.text, str) - # Scrap the BOM if it exists. - # (Used to do this, but no longer. Not sure what bad will happen - # if we don't do it.) - # if ord(self.text[0]) == 0xfeff: - # self.text = self.text[1:] - self.exclude = exclude self.show_tokens = False @@ -334,7 +330,7 @@ OPS_NO_JUMP = OPS_PUSH_BLOCK OP_BREAK_LOOP = _opcode('BREAK_LOOP') OP_END_FINALLY = _opcode('END_FINALLY') OP_COMPARE_OP = _opcode('COMPARE_OP') -COMPARE_EXCEPTION = 10 # just have to get this const from the code. +COMPARE_EXCEPTION = 10 # just have to get this constant from the code. OP_LOAD_CONST = _opcode('LOAD_CONST') OP_RETURN_VALUE = _opcode('RETURN_VALUE') @@ -342,13 +338,14 @@ OP_RETURN_VALUE = _opcode('RETURN_VALUE') class ByteParser(object): """Parse byte codes to understand the structure of code.""" + @contract(text='unicode') def __init__(self, text, code=None, filename=None): self.text = text if code: self.code = code else: try: - self.code = compile(text, filename, "exec") + self.code = compile_unicode(text, filename, "exec") except SyntaxError as synerr: raise NotPython( "Couldn't parse '%s' as Python source: '%s' at line %d" % ( @@ -460,7 +457,7 @@ class ByteParser(object): # Walk the byte codes building chunks. for bc in bytecodes: - # Maybe have to start a new chunk + # Maybe have to start a new chunk. start_new_chunk = False first_chunk = False if bc.offset in bytes_lines_map: @@ -481,9 +478,13 @@ class ByteParser(object): if chunk: chunk.exits.add(bc.offset) chunk = Chunk(bc.offset, chunk_lineno, first_chunk) + if not chunks: + # The very first chunk of a code object is always an + # entrance. + chunk.entrance = True chunks.append(chunk) - # Look at the opcode + # Look at the opcode. if bc.jump_to >= 0 and bc.op not in OPS_NO_JUMP: if ignore_branch: # Someone earlier wanted us to ignore this branch. @@ -570,15 +571,15 @@ class ByteParser(object): """ chunks = self._split_into_chunks() - # A map from byte offsets to chunks jumped into. + # A map from byte offsets to the chunk starting at that offset. byte_chunks = dict((c.byte, c) for c in chunks) - # There's always an entrance at the first chunk. - yield (-1, byte_chunks[0].line) - # Traverse from the first chunk in each line, and yield arcs where # the trace function will be invoked. for chunk in chunks: + if chunk.entrance: + yield (-1, chunk.line) + if not chunk.first: continue @@ -586,7 +587,7 @@ class ByteParser(object): chunks_to_consider = [chunk] while chunks_to_consider: # Get the chunk we're considering, and make sure we don't - # consider it again + # consider it again. this_chunk = chunks_to_consider.pop() chunks_considered.add(this_chunk) @@ -649,6 +650,8 @@ class Chunk(object): .. _basic block: http://en.wikipedia.org/wiki/Basic_block + `byte` is the offset to the bytecode starting this chunk. + `line` is the source line number containing this chunk. `first` is true if this is the first chunk in the source line. @@ -656,19 +659,24 @@ class Chunk(object): An exit < 0 means the chunk can leave the code (return). The exit is the negative of the starting line number of the code block. + The `entrance` attribute is a boolean indicating whether the code object + can be entered at this chunk. + """ def __init__(self, byte, line, first): self.byte = byte self.line = line self.first = first self.length = 0 + self.entrance = False self.exits = set() def __repr__(self): - if self.first: - bang = "!" - else: - bang = "" - return "<%d+%d @%d%s %r>" % ( - self.byte, self.length, self.line, bang, list(self.exits) + return "<%d+%d @%d%s%s %r>" % ( + self.byte, + self.length, + self.line, + "!" if self.first else "", + "v" if self.entrance else "", + list(self.exits), ) |