source: vendor/python/2.5/Lib/tabnanny.py@ 3298

#! /usr/bin/env python

"""The Tab Nanny despises ambiguous indentation.  She knows no mercy.

tabnanny -- Detection of ambiguous indentation

For the time being this module is intended to be called as a script.
However it is possible to import it into an IDE and use the function
check() described below.

Warning: The API provided by this module is likely to change in future
releases; such changes may not be backward compatible.
"""

# Released to the public domain, by Tim Peters, 15 April 1998.

# XXX Note: this is now a standard library module.
# XXX The API needs to undergo changes however; the current code is too
# XXX script-like.  This will be addressed later.

__version__ = "6"

import os
import sys
import getopt
import tokenize
if not hasattr(tokenize, 'NL'):
    raise ValueError("tokenize.NL doesn't exist -- tokenize module too old")

__all__ = ["check", "NannyNag", "process_tokens"]

verbose = 0
filename_only = 0

def errprint(*args):
    sep = ""
    for arg in args:
        sys.stderr.write(sep + str(arg))
        sep = " "
    sys.stderr.write("\n")

def main():
    global verbose, filename_only
    try:
        opts, args = getopt.getopt(sys.argv[1:], "qv")
    except getopt.error, msg:
        errprint(msg)
        return
    for o, a in opts:
        if o == '-q':
            filename_only = filename_only + 1
        if o == '-v':
            verbose = verbose + 1
    if not args:
        errprint("Usage:", sys.argv[0], "[-v] file_or_directory ...")
        return
    for arg in args:
        check(arg)

class NannyNag(Exception):
    """
    Raised by tokeneater() if detecting an ambiguous indent.
    Captured and handled in check().
    """
    def __init__(self, lineno, msg, line):
        self.lineno, self.msg, self.line = lineno, msg, line
    def get_lineno(self):
        return self.lineno
    def get_msg(self):
        return self.msg
    def get_line(self):
        return self.line

def check(file):
    """check(file_or_dir)

    If file_or_dir is a directory and not a symbolic link, then recursively
    descend the directory tree named by file_or_dir, checking all .py files
    along the way. If file_or_dir is an ordinary Python source file, it is
    checked for whitespace related problems. The diagnostic messages are
    written to standard output using the print statement.
    """

    if os.path.isdir(file) and not os.path.islink(file):
        if verbose:
            print "%r: listing directory" % (file,)
        names = os.listdir(file)
        for name in names:
            fullname = os.path.join(file, name)
            if (os.path.isdir(fullname) and
                not os.path.islink(fullname) or
                os.path.normcase(name[-3:]) == ".py"):
                check(fullname)
        return

    try:
        f = open(file)
    except IOError, msg:
        errprint("%r: I/O Error: %s" % (file, msg))
        return

    if verbose > 1:
        print "checking %r ..." % file

    try:
        process_tokens(tokenize.generate_tokens(f.readline))

    except tokenize.TokenError, msg:
        errprint("%r: Token Error: %s" % (file, msg))
        return

    except IndentationError, msg:
        errprint("%r: Indentation Error: %s" % (file, msg))
        return

    except NannyNag, nag:
        badline = nag.get_lineno()
        line = nag.get_line()
        if verbose:
            print "%r: *** Line %d: trouble in tab city! ***" % (file, badline)
            print "offending line: %r" % (line,)
            print nag.get_msg()
        else:
            if ' ' in file: file = '"' + file + '"'
            if filename_only: print file
            else: print file, badline, repr(line)
        return

    if verbose:
        print "%r: Clean bill of health." % (file,)

class Whitespace:
    # the characters used for space and tab
    S, T = ' \t'

    # members:
    #   raw
    #       the original string
    #   n
    #       the number of leading whitespace characters in raw
    #   nt
    #       the number of tabs in raw[:n]
    #   norm
    #       the normal form as a pair (count, trailing), where:
    #       count
    #           a tuple such that raw[:n] contains count[i]
    #           instances of S * i + T
    #       trailing
    #           the number of trailing spaces in raw[:n]
    #       It's A Theorem that m.indent_level(t) ==
    #       n.indent_level(t) for all t >= 1 iff m.norm == n.norm.
    #   is_simple
    #       true iff raw[:n] is of the form (T*)(S*)

    def __init__(self, ws):
        self.raw  = ws
        S, T = Whitespace.S, Whitespace.T
        count = []
        b = n = nt = 0
        for ch in self.raw:
            if ch == S:
                n = n + 1
                b = b + 1
            elif ch == T:
                n = n + 1
                nt = nt + 1
                if b >= len(count):
                    count = count + [0] * (b - len(count) + 1)
                count[b] = count[b] + 1
                b = 0
            else:
                break
        self.n    = n
        self.nt   = nt
        self.norm = tuple(count), b
        self.is_simple = len(count) <= 1