Skip to content

C
cpython
Kaydet (Commit) f4b44fa6 authored tarafından Guido van Rossum's avatar Guido van Rossum
Dosyalara gözat
Seçenekler

Tim's latest version (supports old and new tokenize modules)

üst 5d97ebf2
Hide whitespace changes
Inline Side-by-side
Showing with 384 additions and 231 deletions
Lib/tabnanny.py
Dosyayı görüntüle @ f4b44fa6
#! /home/guido/python/src/sparc/python
#! /usr/bin/env python #! /usr/bin/env python
"""The Tab Nanny despises ambiguous indentation. She knows no mercy. """The Tab Nanny despises ambiguous indentation. She knows no mercy."""
CAUTION: this version requires Guido's "NL" patch to lib/tokenize.py, # Released to the public domain, by Tim Peters, 4 April 1998.
posted 30-Mar-98. This version will not run at all with an unpatched
tokenize (it will raise AttributeError while loading), while previous
versions will run incorrectly with the patched tokenize.
"""
# Released to the public domain, by Tim Peters, 30 March 1998. __version__ = "3"
__version__ = "2"
import os import os
import sys import sys
import getopt import getopt
import tokenize import tokenize
try:
tokenize.NL
except AttributeError:
raise AttributeError, "Sorry, I need a version of tokenize.py " \
"that supports the NL pseudo-token."
verbose = 0 verbose = 0
def main(): def main():
...@@ -235,67 +222,131 @@ def format_witnesses(w): ...@@ -235,67 +222,131 @@ def format_witnesses(w):
prefix = prefix + "s" prefix = prefix + "s"
return prefix + " " + string.join(firsts, ', ') return prefix + " " + string.join(firsts, ', ')
indents = [] # The collection of globals, the reset_globals() function, and the
check_equal = 0 # tokeneater() function, depend on which version of tokenize is
# in use.
def reset_globals():
global indents, check_equal if hasattr(tokenize, 'NL'):
check_equal = 0 # take advantage of Guido's patch!
indents = [Whitespace("")]
indents = []
def tokeneater(type, token, start, end, line, check_equal = 0
INDENT=tokenize.INDENT,
DEDENT=tokenize.DEDENT, def reset_globals():
NEWLINE=tokenize.NEWLINE, global indents, check_equal
COMMENT=tokenize.COMMENT, check_equal = 0
NL=tokenize.NL): indents = [Whitespace("")]
global indents, check_equal
def tokeneater(type, token, start, end, line,
# test in decreasing order of frequency, although the check_equal INDENT=tokenize.INDENT,
# test *must* be last; INDENT and DEDENT appear equally often DEDENT=tokenize.DEDENT,
NEWLINE=tokenize.NEWLINE,
if type in (COMMENT, NL): COMMENT=tokenize.COMMENT,
# the indentation of these guys is meaningless NL=tokenize.NL):
pass global indents, check_equal
elif type == NEWLINE: # test in decreasing order of frequency, although the check_equal
# a program statement, or ENDMARKER, will eventually follow, # test *must* be last; INDENT and DEDENT appear equally often
# after some (possibly empty) run of tokens of the form
# (NL | COMMENT)* (INDENT | DEDENT+)? if type in (COMMENT, NL):
# If an INDENT appears, setting check_equal is wrong, and will # the indentation of these guys is meaningless
# be undone when we see the INDENT. pass
check_equal = 1
elif type == NEWLINE:
elif type == INDENT: # a program statement, or ENDMARKER, will eventually follow,
check_equal = 0 # after some (possibly empty) run of tokens of the form
thisguy = Whitespace(token) # (NL | COMMENT)* (INDENT | DEDENT+)?
if not indents[-1].less(thisguy): # If an INDENT appears, setting check_equal is wrong, and will
witness = indents[-1].not_less_witness(thisguy) # be undone when we see the INDENT.
msg = "indent not greater e.g. " + format_witnesses(witness) check_equal = 1
raise NannyNag(start[0], msg, line)
indents.append(thisguy) elif type == INDENT:
check_equal = 0
elif type == DEDENT: thisguy = Whitespace(token)
# there's nothing we need to check here! what's important is if not indents[-1].less(thisguy):
# that when the run of DEDENTs ends, the indentation of the witness = indents[-1].not_less_witness(thisguy)
# program statement (or ENDMARKER) that triggered the run is msg = "indent not greater e.g. " + format_witnesses(witness)
# equal to what's left at the top of the indents stack raise NannyNag(start[0], msg, line)
assert check_equal # else no earlier NEWLINE, or an earlier INDENT indents.append(thisguy)
del indents[-1]
elif type == DEDENT:
elif check_equal: # there's nothing we need to check here! what's important is
# this is the first "real token" following a NEWLINE, so it # that when the run of DEDENTs ends, the indentation of the
# must be the first token of the next program statment, or an # program statement (or ENDMARKER) that triggered the run is
# ENDMARKER; the "line" argument exposes the leading whitespace # equal to what's left at the top of the indents stack
# for this statement; in the case of ENDMARKER, line is an empty assert check_equal # else no earlier NEWLINE, or an earlier INDENT
# string, so will properly match the empty string with which the del indents[-1]
# "indents" stack was seeded
check_equal = 0 elif check_equal:
thisguy = Whitespace(line) # this is the first "real token" following a NEWLINE, so it
if not indents[-1].equal(thisguy): # must be the first token of the next program statement, or an
witness = indents[-1].not_equal_witness(thisguy) # ENDMARKER; the "line" argument exposes the leading whitespace
msg = "indent not equal e.g. " + format_witnesses(witness) # for this statement; in the case of ENDMARKER, line is an empty
raise NannyNag(start[0], msg, line) # string, so will properly match the empty string with which the
# "indents" stack was seeded
check_equal = 0
thisguy = Whitespace(line)
if not indents[-1].equal(thisguy):
witness = indents[-1].not_equal_witness(thisguy)
msg = "indent not equal e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
else:
# unpatched version of tokenize
nesting_level = 0
indents = []
check_equal = 0
def reset_globals():
global nesting_level, indents, check_equal
nesting_level = check_equal = 0
indents = [Whitespace("")]
def tokeneater(type, token, start, end, line,
INDENT=tokenize.INDENT,
DEDENT=tokenize.DEDENT,
NEWLINE=tokenize.NEWLINE,
COMMENT=tokenize.COMMENT,
OP=tokenize.OP):
global nesting_level, indents, check_equal
if type == INDENT:
check_equal = 0
thisguy = Whitespace(token)
if not indents[-1].less(thisguy):
witness = indents[-1].not_less_witness(thisguy)
msg = "indent not greater e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
indents.append(thisguy)
elif type == DEDENT:
del indents[-1]
elif type == NEWLINE:
if nesting_level == 0:
check_equal = 1
elif type == COMMENT:
pass
elif check_equal:
check_equal = 0
thisguy = Whitespace(line)
if not indents[-1].equal(thisguy):
witness = indents[-1].not_equal_witness(thisguy)
msg = "indent not equal e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
if type == OP and token in ('{', '[', '('):
nesting_level = nesting_level + 1
elif type == OP and token in ('}', ']', ')'):
if nesting_level == 0:
raise NannyNag(start[0],
"unbalanced bracket '" + token + "'",
line)
nesting_level = nesting_level - 1
if __name__ == '__main__': if __name__ == '__main__':
main() main()
......
Tools/idle/tabnanny.py
Dosyayı görüntüle @ f4b44fa6
#! /home/guido/python/src/sparc/python
#! /usr/bin/env python #! /usr/bin/env python
"""The Tab Nanny despises ambiguous indentation. She knows no mercy. """The Tab Nanny despises ambiguous indentation. She knows no mercy."""
CAUTION: this version requires Guido's "NL" patch to lib/tokenize.py, # Released to the public domain, by Tim Peters, 4 April 1998.
posted 30-Mar-98. This version will not run at all with an unpatched
tokenize (it will raise AttributeError while loading), while previous
versions will run incorrectly with the patched tokenize.
"""
# Released to the public domain, by Tim Peters, 30 March 1998. __version__ = "3"
__version__ = "2"
import os import os
import sys import sys
import getopt import getopt
import tokenize import tokenize
try:
tokenize.NL
except AttributeError:
raise AttributeError, "Sorry, I need a version of tokenize.py " \
"that supports the NL pseudo-token."
verbose = 0 verbose = 0
def main(): def main():
...@@ -235,67 +222,131 @@ def format_witnesses(w): ...@@ -235,67 +222,131 @@ def format_witnesses(w):
prefix = prefix + "s" prefix = prefix + "s"
return prefix + " " + string.join(firsts, ', ') return prefix + " " + string.join(firsts, ', ')
indents = [] # The collection of globals, the reset_globals() function, and the
check_equal = 0 # tokeneater() function, depend on which version of tokenize is
# in use.
def reset_globals():
global indents, check_equal if hasattr(tokenize, 'NL'):
check_equal = 0 # take advantage of Guido's patch!
indents = [Whitespace("")]
indents = []
def tokeneater(type, token, start, end, line, check_equal = 0
INDENT=tokenize.INDENT,
DEDENT=tokenize.DEDENT, def reset_globals():
NEWLINE=tokenize.NEWLINE, global indents, check_equal
COMMENT=tokenize.COMMENT, check_equal = 0
NL=tokenize.NL): indents = [Whitespace("")]
global indents, check_equal
def tokeneater(type, token, start, end, line,
# test in decreasing order of frequency, although the check_equal INDENT=tokenize.INDENT,
# test *must* be last; INDENT and DEDENT appear equally often DEDENT=tokenize.DEDENT,
NEWLINE=tokenize.NEWLINE,
if type in (COMMENT, NL): COMMENT=tokenize.COMMENT,
# the indentation of these guys is meaningless NL=tokenize.NL):
pass global indents, check_equal
elif type == NEWLINE: # test in decreasing order of frequency, although the check_equal
# a program statement, or ENDMARKER, will eventually follow, # test *must* be last; INDENT and DEDENT appear equally often
# after some (possibly empty) run of tokens of the form
# (NL | COMMENT)* (INDENT | DEDENT+)? if type in (COMMENT, NL):
# If an INDENT appears, setting check_equal is wrong, and will # the indentation of these guys is meaningless
# be undone when we see the INDENT. pass
check_equal = 1
elif type == NEWLINE:
elif type == INDENT: # a program statement, or ENDMARKER, will eventually follow,
check_equal = 0 # after some (possibly empty) run of tokens of the form
thisguy = Whitespace(token) # (NL | COMMENT)* (INDENT | DEDENT+)?
if not indents[-1].less(thisguy): # If an INDENT appears, setting check_equal is wrong, and will
witness = indents[-1].not_less_witness(thisguy) # be undone when we see the INDENT.
msg = "indent not greater e.g. " + format_witnesses(witness) check_equal = 1
raise NannyNag(start[0], msg, line)
indents.append(thisguy) elif type == INDENT:
check_equal = 0
elif type == DEDENT: thisguy = Whitespace(token)
# there's nothing we need to check here! what's important is if not indents[-1].less(thisguy):
# that when the run of DEDENTs ends, the indentation of the witness = indents[-1].not_less_witness(thisguy)
# program statement (or ENDMARKER) that triggered the run is msg = "indent not greater e.g. " + format_witnesses(witness)
# equal to what's left at the top of the indents stack raise NannyNag(start[0], msg, line)
assert check_equal # else no earlier NEWLINE, or an earlier INDENT indents.append(thisguy)
del indents[-1]
elif type == DEDENT:
elif check_equal: # there's nothing we need to check here! what's important is
# this is the first "real token" following a NEWLINE, so it # that when the run of DEDENTs ends, the indentation of the
# must be the first token of the next program statment, or an # program statement (or ENDMARKER) that triggered the run is
# ENDMARKER; the "line" argument exposes the leading whitespace # equal to what's left at the top of the indents stack
# for this statement; in the case of ENDMARKER, line is an empty assert check_equal # else no earlier NEWLINE, or an earlier INDENT
# string, so will properly match the empty string with which the del indents[-1]
# "indents" stack was seeded
check_equal = 0 elif check_equal:
thisguy = Whitespace(line) # this is the first "real token" following a NEWLINE, so it
if not indents[-1].equal(thisguy): # must be the first token of the next program statement, or an
witness = indents[-1].not_equal_witness(thisguy) # ENDMARKER; the "line" argument exposes the leading whitespace
msg = "indent not equal e.g. " + format_witnesses(witness) # for this statement; in the case of ENDMARKER, line is an empty
raise NannyNag(start[0], msg, line) # string, so will properly match the empty string with which the
# "indents" stack was seeded
check_equal = 0
thisguy = Whitespace(line)
if not indents[-1].equal(thisguy):
witness = indents[-1].not_equal_witness(thisguy)
msg = "indent not equal e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
else:
# unpatched version of tokenize
nesting_level = 0
indents = []
check_equal = 0
def reset_globals():
global nesting_level, indents, check_equal
nesting_level = check_equal = 0
indents = [Whitespace("")]
def tokeneater(type, token, start, end, line,
INDENT=tokenize.INDENT,
DEDENT=tokenize.DEDENT,
NEWLINE=tokenize.NEWLINE,
COMMENT=tokenize.COMMENT,
OP=tokenize.OP):
global nesting_level, indents, check_equal
if type == INDENT:
check_equal = 0
thisguy = Whitespace(token)
if not indents[-1].less(thisguy):
witness = indents[-1].not_less_witness(thisguy)
msg = "indent not greater e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
indents.append(thisguy)
elif type == DEDENT:
del indents[-1]
elif type == NEWLINE:
if nesting_level == 0:
check_equal = 1
elif type == COMMENT:
pass
elif check_equal:
check_equal = 0
thisguy = Whitespace(line)
if not indents[-1].equal(thisguy):
witness = indents[-1].not_equal_witness(thisguy)
msg = "indent not equal e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
if type == OP and token in ('{', '[', '('):
nesting_level = nesting_level + 1
elif type == OP and token in ('}', ']', ')'):
if nesting_level == 0:
raise NannyNag(start[0],
"unbalanced bracket '" + token + "'",
line)
nesting_level = nesting_level - 1
if __name__ == '__main__': if __name__ == '__main__':
main() main()
......
Tools/scripts/tabnanny.py
Dosyayı görüntüle @ f4b44fa6
#! /home/guido/python/src/sparc/python
#! /usr/bin/env python #! /usr/bin/env python
"""The Tab Nanny despises ambiguous indentation. She knows no mercy. """The Tab Nanny despises ambiguous indentation. She knows no mercy."""
CAUTION: this version requires Guido's "NL" patch to lib/tokenize.py, # Released to the public domain, by Tim Peters, 4 April 1998.
posted 30-Mar-98. This version will not run at all with an unpatched
tokenize (it will raise AttributeError while loading), while previous
versions will run incorrectly with the patched tokenize.
"""
# Released to the public domain, by Tim Peters, 30 March 1998. __version__ = "3"
__version__ = "2"
import os import os
import sys import sys
import getopt import getopt
import tokenize import tokenize
try:
tokenize.NL
except AttributeError:
raise AttributeError, "Sorry, I need a version of tokenize.py " \
"that supports the NL pseudo-token."
verbose = 0 verbose = 0
def main(): def main():
...@@ -235,67 +222,131 @@ def format_witnesses(w): ...@@ -235,67 +222,131 @@ def format_witnesses(w):
prefix = prefix + "s" prefix = prefix + "s"
return prefix + " " + string.join(firsts, ', ') return prefix + " " + string.join(firsts, ', ')
indents = [] # The collection of globals, the reset_globals() function, and the
check_equal = 0 # tokeneater() function, depend on which version of tokenize is
# in use.
def reset_globals():
global indents, check_equal if hasattr(tokenize, 'NL'):
check_equal = 0 # take advantage of Guido's patch!
indents = [Whitespace("")]
indents = []
def tokeneater(type, token, start, end, line, check_equal = 0
INDENT=tokenize.INDENT,
DEDENT=tokenize.DEDENT, def reset_globals():
NEWLINE=tokenize.NEWLINE, global indents, check_equal
COMMENT=tokenize.COMMENT, check_equal = 0
NL=tokenize.NL): indents = [Whitespace("")]
global indents, check_equal
def tokeneater(type, token, start, end, line,
# test in decreasing order of frequency, although the check_equal INDENT=tokenize.INDENT,
# test *must* be last; INDENT and DEDENT appear equally often DEDENT=tokenize.DEDENT,
NEWLINE=tokenize.NEWLINE,
if type in (COMMENT, NL): COMMENT=tokenize.COMMENT,
# the indentation of these guys is meaningless NL=tokenize.NL):
pass global indents, check_equal
elif type == NEWLINE: # test in decreasing order of frequency, although the check_equal
# a program statement, or ENDMARKER, will eventually follow, # test *must* be last; INDENT and DEDENT appear equally often
# after some (possibly empty) run of tokens of the form
# (NL | COMMENT)* (INDENT | DEDENT+)? if type in (COMMENT, NL):
# If an INDENT appears, setting check_equal is wrong, and will # the indentation of these guys is meaningless
# be undone when we see the INDENT. pass
check_equal = 1
elif type == NEWLINE:
elif type == INDENT: # a program statement, or ENDMARKER, will eventually follow,
check_equal = 0 # after some (possibly empty) run of tokens of the form
thisguy = Whitespace(token) # (NL | COMMENT)* (INDENT | DEDENT+)?
if not indents[-1].less(thisguy): # If an INDENT appears, setting check_equal is wrong, and will
witness = indents[-1].not_less_witness(thisguy) # be undone when we see the INDENT.
msg = "indent not greater e.g. " + format_witnesses(witness) check_equal = 1
raise NannyNag(start[0], msg, line)
indents.append(thisguy) elif type == INDENT:
check_equal = 0
elif type == DEDENT: thisguy = Whitespace(token)
# there's nothing we need to check here! what's important is if not indents[-1].less(thisguy):
# that when the run of DEDENTs ends, the indentation of the witness = indents[-1].not_less_witness(thisguy)
# program statement (or ENDMARKER) that triggered the run is msg = "indent not greater e.g. " + format_witnesses(witness)
# equal to what's left at the top of the indents stack raise NannyNag(start[0], msg, line)
assert check_equal # else no earlier NEWLINE, or an earlier INDENT indents.append(thisguy)
del indents[-1]
elif type == DEDENT:
elif check_equal: # there's nothing we need to check here! what's important is
# this is the first "real token" following a NEWLINE, so it # that when the run of DEDENTs ends, the indentation of the
# must be the first token of the next program statment, or an # program statement (or ENDMARKER) that triggered the run is
# ENDMARKER; the "line" argument exposes the leading whitespace # equal to what's left at the top of the indents stack
# for this statement; in the case of ENDMARKER, line is an empty assert check_equal # else no earlier NEWLINE, or an earlier INDENT
# string, so will properly match the empty string with which the del indents[-1]
# "indents" stack was seeded
check_equal = 0 elif check_equal:
thisguy = Whitespace(line) # this is the first "real token" following a NEWLINE, so it
if not indents[-1].equal(thisguy): # must be the first token of the next program statement, or an
witness = indents[-1].not_equal_witness(thisguy) # ENDMARKER; the "line" argument exposes the leading whitespace
msg = "indent not equal e.g. " + format_witnesses(witness) # for this statement; in the case of ENDMARKER, line is an empty
raise NannyNag(start[0], msg, line) # string, so will properly match the empty string with which the
# "indents" stack was seeded
check_equal = 0
thisguy = Whitespace(line)
if not indents[-1].equal(thisguy):
witness = indents[-1].not_equal_witness(thisguy)
msg = "indent not equal e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
else:
# unpatched version of tokenize
nesting_level = 0
indents = []
check_equal = 0
def reset_globals():
global nesting_level, indents, check_equal
nesting_level = check_equal = 0
indents = [Whitespace("")]
def tokeneater(type, token, start, end, line,
INDENT=tokenize.INDENT,
DEDENT=tokenize.DEDENT,
NEWLINE=tokenize.NEWLINE,
COMMENT=tokenize.COMMENT,
OP=tokenize.OP):
global nesting_level, indents, check_equal
if type == INDENT:
check_equal = 0
thisguy = Whitespace(token)
if not indents[-1].less(thisguy):
witness = indents[-1].not_less_witness(thisguy)
msg = "indent not greater e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
indents.append(thisguy)
elif type == DEDENT:
del indents[-1]
elif type == NEWLINE:
if nesting_level == 0:
check_equal = 1
elif type == COMMENT:
pass
elif check_equal:
check_equal = 0
thisguy = Whitespace(line)
if not indents[-1].equal(thisguy):
witness = indents[-1].not_equal_witness(thisguy)
msg = "indent not equal e.g. " + format_witnesses(witness)
raise NannyNag(start[0], msg, line)
if type == OP and token in ('{', '[', '('):
nesting_level = nesting_level + 1
elif type == OP and token in ('}', ']', ')'):
if nesting_level == 0:
raise NannyNag(start[0],
"unbalanced bracket '" + token + "'",
line)
nesting_level = nesting_level - 1
if __name__ == '__main__': if __name__ == '__main__':
main() main()
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment