Massive identifier substitution on C source files
"""
PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
--------------------------------------------
1. This LICENSE AGREEMENT is between the Python Software Foundation
("PSF"), and the Individual or Organization ("Licensee") accessing and
otherwise using this software ("Python") in source or binary form and
its associated documentation.
2. Subject to the terms and conditions of this License Agreement, PSF
hereby grants Licensee a nonexclusive, royalty-free, world-wide
license to reproduce, analyze, test, perform and/or display publicly,
prepare derivative works, distribute, and otherwise use Python
alone or in any derivative version, provided, however, that PSF's
License Agreement and PSF's notice of copyright, i.e., "Copyright (c)
2001, 2002, 2003, 2004 Python Software Foundation; All Rights Reserved"
are retained in Python alone or in any derivative version prepared
by Licensee.
3. In the event Licensee prepares a derivative work that is based on
or incorporates Python or any part thereof, and wants to make
the derivative work available to others as provided herein, then
Licensee hereby agrees to include in any such work a brief summary of
the changes made to Python.
4. PSF is making Python available to Licensee on an "AS IS"
basis. PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON,
OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
6. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
7. Nothing in this License Agreement shall be deemed to create any
relationship of agency, partnership, or joint venture between PSF and
Licensee. This License Agreement does not grant permission to use PSF
trademarks or trade name in a trademark sense to endorse or promote
products or services of Licensee, or any third party.
8. By copying, installing or otherwise using Python, Licensee
agrees to be bound by the terms and conditions of this License
Agreement.
"""
#! /usr/bin/env python
# Perform massive identifier substitution on C source files.
# This actually tokenizes the files (to some extent) so it can
# avoid making substitutions inside strings or comments.
# Inside strings, substitutions are never made; inside comments,
# it is a user option (off by default).
#
# The substitutions are read from one or more files whose lines,
# when not empty, after stripping comments starting with #,
# must contain exactly two words separated by whitespace: the
# old identifier and its replacement.
#
# The option -r reverses the sense of the substitutions (this may be
# useful to undo a particular substitution).
#
# If the old identifier is prefixed with a '*' (with no intervening
# whitespace), then it will not be substituted inside comments.
#
# Command line arguments are files or directories to be processed.
# Directories are searched recursively for files whose name looks
# like a C file (ends in .h or .c). The special filename '-' means
# operate in filter mode: read stdin, write stdout.
#
# Symbolic links are always ignored (except as explicit directory
# arguments).
#
# The original files are kept as back-up with a "~" suffix.
#
# Changes made are reported to stdout in a diff-like format.
#
# NB: by changing only the function fixline() you can turn this
# into a program for different changes to C source files; by
# changing the function wanted() you can make a different selection of
# files.
import sys
import regex
import os
from stat import *
import getopt
err = sys.stderr.write
dbg = err
rep = sys.stdout.write
def usage():
progname = sys.argv[0]
err('Usage: ' + progname +
' [-c] [-r] [-s file] ... file-or-directory ...\n')
err('\n')
err('-c : substitute inside comments\n')
err('-r : reverse direction for following -s options\n')
err('-s substfile : add a file of substitutions\n')
err('\n')
err('Each non-empty non-comment line in a substitution file must\n')
err('contain exactly two words: an identifier and its replacement.\n')
err('Comments start with a # character and end at end of line.\n')
err('If an identifier is preceded with a *, it is not substituted\n')
err('inside a comment even when -c is specified.\n')
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], 'crs:')
except getopt.error, msg:
err('Options error: ' + str(msg) + '\n')
usage()
sys.exit(2)
bad = 0
if not args: # No arguments
usage()
sys.exit(2)
for opt, arg in opts:
if opt == '-c':
setdocomments()
if opt == '-r':
setreverse()
if opt == '-s':
addsubst(arg)
for arg in args:
if os.path.isdir(arg):
if recursedown(arg): bad = 1
elif os.path.islink(arg):
err(arg + ': will not process symbolic links\n')
bad = 1
else:
if fix(arg): bad = 1
sys.exit(bad)
# Change this regular expression to select a different set of files
Wanted = '^[a-zA-Z0-9_]+\.[ch]$'
def wanted(name):
return regex.match(Wanted, name) >= 0
def recursedown(dirname):
dbg('recursedown(%r)\n' % (dirname,))
bad = 0
try:
names = os.listdir(dirname)
except os.error, msg:
err(dirname + ': cannot list directory: ' + str(msg) + '\n')
return 1
names.sort()
subdirs = []
for name in names:
if name in (os.curdir, os.pardir): continue
fullname = os.path.join(dirname, name)
if os.path.islink(fullname): pass
elif os.path.isdir(fullname):
subdirs.append(fullname)
elif wanted(name):
if fix(fullname): bad = 1
for fullname in subdirs:
if recursedown(fullname): bad = 1
return bad
def fix(filename):
## dbg('fix(%r)\n' % (filename,))
if filename == '-':
# Filter mode
f = sys.stdin
g = sys.stdout
else:
# File replacement mode
try:
f = open(filename, 'r')
except IOError, msg:
err(filename + ': cannot open: ' + str(msg) + '\n')
return 1
head, tail = os.path.split(filename)
tempname = os.path.join(head, '@' + tail)
g = None
# If we find a match, we rewind the file and start over but
# now copy everything to a temp file.
lineno = 0
initfixline()
while 1:
line = f.readline()
if not line: break
lineno = lineno + 1
while line[-2:] == '\\\n':
nextline = f.readline()
if not nextline: break
line = line + nextline
lineno = lineno + 1
newline = fixline(line)
if newline != line:
if g is None:
try:
g = open(tempname, 'w')
except IOError, msg:
f.close()
err(tempname+': cannot create: '+
str(msg)+'\n')
return 1
f.seek(0)
lineno = 0
initfixline()
rep(filename + ':\n')
continue # restart from the beginning
rep(repr(lineno) + '\n')
rep('< ' + line)
rep('> ' + newline)
if g is not None:
g.write(newline)
# End of file
if filename == '-': return 0 # Done in filter mode
f.close()
if not g: return 0 # No changes
# Finishing touch -- move files
# First copy the file's mode to the temp file
try:
statbuf = os.stat(filename)
os.chmod(tempname, statbuf[ST_MODE] & 07777)
except os.error, msg:
err(tempname + ': warning: chmod failed (' + str(msg) + ')\n')
# Then make a backup of the original file as filename~
try:
os.rename(filename, filename + '~')
except os.error, msg:
err(filename + ': warning: backup failed (' + str(msg) + ')\n')
# Now move the temp file to the original file
try:
os.rename(tempname, filename)
except os.error, msg:
err(filename + ': rename failed (' + str(msg) + ')\n')
return 1
# Return succes
return 0
# Tokenizing ANSI C (partly)
Identifier = '\(struct \)?[a-zA-Z_][a-zA-Z0-9_]+'
String = '"\([^\n\\"]\|\\\\.\)*"'
Char = '\'\([^\n\\\']\|\\\\.\)*\''
CommentStart = '/\*'
CommentEnd = '\*/'
Hexnumber = '0[xX][0-9a-fA-F]*[uUlL]*'
Octnumber = '0[0-7]*[uUlL]*'
Decnumber = '[1-9][0-9]*[uUlL]*'
Intnumber = Hexnumber + '\|' + Octnumber + '\|' + Decnumber
Exponent = '[eE][-+]?[0-9]+'
Pointfloat = '\([0-9]+\.[0-9]*\|\.[0-9]+\)\(' + Exponent + '\)?'
Expfloat = '[0-9]+' + Exponent
Floatnumber = Pointfloat + '\|' + Expfloat
Number = Floatnumber + '\|' + Intnumber
# Anything else is an operator -- don't list this explicitly because of '/*'
OutsideComment = (Identifier, Number, String, Char, CommentStart)
OutsideCommentPattern = '\(' + '\|'.join(OutsideComment) + '\)'
OutsideCommentProgram = regex.compile(OutsideCommentPattern)
InsideComment = (Identifier, Number, CommentEnd)
InsideCommentPattern = '\(' + '\|'.join(InsideComment) + '\)'
InsideCommentProgram = regex.compile(InsideCommentPattern)
def initfixline():
global Program
Program = OutsideCommentProgram
def fixline(line):
global Program
## print '-->', repr(line)
i = 0
while i < len(line):
i = Program.search(line, i)
if i < 0: break
found = Program.group(0)
## if Program is InsideCommentProgram: print '...',
## else: print ' ',
## print found
if len(found) == 2:
if found == '/*':
Program = InsideCommentProgram
elif found == '*/':
Program = OutsideCommentProgram
n = len(found)
if Dict.has_key(found):
subst = Dict[found]
if Program is InsideCommentProgram:
if not Docomments:
print 'Found in comment:', found
i = i + n
continue
if NotInComment.has_key(found):
## print 'Ignored in comment:',
## print found, '-->', subst
## print 'Line:', line,
subst = found
## else:
## print 'Substituting in comment:',
## print found, '-->', subst
## print 'Line:', line,
line = line[:i] + subst + line[i+n:]
n = len(subst)
i = i + n
return line
Docomments = 0
def setdocomments():
global Docomments
Docomments = 1
Reverse = 0
def setreverse():
global Reverse
Reverse = (not Reverse)
Dict = {}
NotInComment = {}
def addsubst(substfile):
try:
fp = open(substfile, 'r')
except IOError, msg:
err(substfile + ': cannot read substfile: ' + str(msg) + '\n')
sys.exit(1)
lineno = 0
while 1:
line = fp.readline()
if not line: break
lineno = lineno + 1
try:
i = line.index('#')
except ValueError:
i = -1 # Happens to delete trailing \n
words = line[:i].split()
if not words: continue
if len(words) == 3 and words[0] == 'struct':
words[:2] = [words[0] + ' ' + words[1]]
elif len(words) <> 2:
err(substfile + '%s:%r: warning: bad line: %r' % (substfile, lineno, line))
continue
if Reverse:
[value, key] = words
else:
[key, value] = words
if value[0] == '*':
value = value[1:]
if key[0] == '*':
key = key[1:]
NotInComment[key] = value
if Dict.has_key(key):
err('%s:%r: warning: overriding: %r %r\n' % (substfile, lineno, key, value))
err('%s:%r: warning: previous: %r\n' % (substfile, lineno, Dict[key]))
Dict[key] = value
fp.close()
if __name__ == '__main__':
main()
Related examples in the same category