diff -r f1cbc18f88b2 -r fac17a82b431 DebugClients/Python/coverage/phystokens.py
--- a/DebugClients/Python/coverage/phystokens.py Fri Apr 04 22:57:07 2014 +0200
+++ b/DebugClients/Python/coverage/phystokens.py Thu Apr 10 23:02:20 2014 +0200
@@ -1,7 +1,9 @@
"""Better tokenizing for coverage.py."""
-import keyword, re, token, tokenize
-from .backward import StringIO # pylint: disable-msg=W0622
+import codecs, keyword, re, sys, token, tokenize
+from .backward import set # pylint: disable=W0622
+from .parser import generate_tokens
+
def phys_tokens(toks):
"""Return all physical tokens, even line continuations.
@@ -18,7 +20,7 @@
last_ttype = None
for ttype, ttext, (slineno, scol), (elineno, ecol), ltext in toks:
if last_lineno != elineno:
- if last_line and last_line[-2:] == "\\\n":
+ if last_line and last_line.endswith("\\\n"):
# We are at the beginning of a new line, and the last line
# ended with a backslash. We probably have to inject a
# backslash token into the stream. Unfortunately, there's more
@@ -74,10 +76,11 @@
is indistinguishable from a final line with a newline.
"""
- ws_tokens = [token.INDENT, token.DEDENT, token.NEWLINE, tokenize.NL]
+ ws_tokens = set([token.INDENT, token.DEDENT, token.NEWLINE, tokenize.NL])
line = []
col = 0
- tokgen = tokenize.generate_tokens(StringIO(source.expandtabs(8)).readline)
+ source = source.expandtabs(8).replace('\r\n', '\n')
+ tokgen = generate_tokens(source)
for ttype, ttext, (_, scol), (_, ecol), _ in phys_tokens(tokgen):
mark_start = True
for part in re.split('(\n)', ttext):
@@ -106,5 +109,102 @@
if line:
yield line
-#
-# eflag: FileType = Python2
+def source_encoding(source):
+ """Determine the encoding for `source` (a string), according to PEP 263.
+
+ Returns a string, the name of the encoding.
+
+ """
+ # Note: this function should never be called on Python 3, since py3 has
+ # built-in tools to do this.
+ assert sys.version_info < (3, 0)
+
+ # This is mostly code adapted from Py3.2's tokenize module.
+
+ cookie_re = re.compile(r"coding[:=]\s*([-\w.]+)")
+
+ # Do this so the detect_encode code we copied will work.
+ readline = iter(source.splitlines(True)).next
+
+ def _get_normal_name(orig_enc):
+ """Imitates get_normal_name in tokenizer.c."""
+ # Only care about the first 12 characters.
+ enc = orig_enc[:12].lower().replace("_", "-")
+ if re.match(r"^utf-8($|-)", enc):
+ return "utf-8"
+ if re.match(r"^(latin-1|iso-8859-1|iso-latin-1)($|-)", enc):
+ return "iso-8859-1"
+ return orig_enc
+
+ # From detect_encode():
+ # It detects the encoding from the presence of a utf-8 bom or an encoding
+ # cookie as specified in pep-0263. If both a bom and a cookie are present,
+ # but disagree, a SyntaxError will be raised. If the encoding cookie is an
+ # invalid charset, raise a SyntaxError. Note that if a utf-8 bom is found,
+ # 'utf-8-sig' is returned.
+
+ # If no encoding is specified, then the default will be returned. The
+ # default varied with version.
+
+ if sys.version_info <= (2, 4):
+ default = 'iso-8859-1'
+ else:
+ default = 'ascii'
+
+ bom_found = False
+ encoding = None
+
+ def read_or_stop():
+ """Get the next source line, or ''."""
+ try:
+ return readline()
+ except StopIteration:
+ return ''
+
+ def find_cookie(line):
+ """Find an encoding cookie in `line`."""
+ try:
+ line_string = line.decode('ascii')
+ except UnicodeDecodeError:
+ return None
+
+ matches = cookie_re.findall(line_string)
+ if not matches:
+ return None
+ encoding = _get_normal_name(matches[0])
+ try:
+ codec = codecs.lookup(encoding)
+ except LookupError:
+ # This behaviour mimics the Python interpreter
+ raise SyntaxError("unknown encoding: " + encoding)
+
+ if bom_found:
+ # codecs in 2.3 were raw tuples of functions, assume the best.
+ codec_name = getattr(codec, 'name', encoding)
+ if codec_name != 'utf-8':
+ # This behaviour mimics the Python interpreter
+ raise SyntaxError('encoding problem: utf-8')
+ encoding += '-sig'
+ return encoding
+
+ first = read_or_stop()
+ if first.startswith(codecs.BOM_UTF8):
+ bom_found = True
+ first = first[3:]
+ default = 'utf-8-sig'
+ if not first:
+ return default
+
+ encoding = find_cookie(first)
+ if encoding:
+ return encoding
+
+ second = read_or_stop()
+ if not second:
+ return default
+
+ encoding = find_cookie(second)
+ if encoding:
+ return encoding
+
+ return default
