cleanfuture.py 8.38 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
#! /usr/bin/env python

"""cleanfuture [-d][-r][-v] path ...

-d  Dry run.  Analyze, but don't make any changes to, files.
-r  Recurse.  Search for all .py files in subdirectories too.
-v  Verbose.  Print informative msgs.

Search Python (.py) files for future statements, and remove the features
from such statements that are already mandatory in the version of Python
you're using.

Pass one or more file and/or directory paths.  When a directory path, all
.py files within the directory will be examined, and, if the -r option is
given, likewise recursively for subdirectories.

Overwrites files in place, renaming the originals with a .bak extension. If
cleanfuture finds nothing to change, the file is left alone.  If cleanfuture
does change a file, the changed file is a fixed-point (i.e., running
cleanfuture on the resulting .py file won't change it again, at least not
21
until you try it again with a later Python release).
22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51

Limitations:  You can do these things, but this tool won't help you then:

+ A future statement cannot be mixed with any other statement on the same
  physical line (separated by semicolon).

+ A future statement cannot contain an "as" clause.

Example:  Assuming you're using Python 2.2, if a file containing

from __future__ import nested_scopes, generators

is analyzed by cleanfuture, the line is rewritten to

from __future__ import generators

because nested_scopes is no longer optional in 2.2 but generators is.
"""

import __future__
import tokenize
import os
import sys

dryrun  = 0
recurse = 0
verbose = 0

def errprint(*args):
    strings = map(str, args)
52 53 54 55
    msg = ' '.join(strings)
    if msg[-1:] != '\n':
        msg += '\n'
    sys.stderr.write(msg)
56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98

def main():
    import getopt
    global verbose, recurse, dryrun
    try:
        opts, args = getopt.getopt(sys.argv[1:], "drv")
    except getopt.error, msg:
        errprint(msg)
        return
    for o, a in opts:
        if o == '-d':
            dryrun += 1
        elif o == '-r':
            recurse += 1
        elif o == '-v':
            verbose += 1
    if not args:
        errprint("Usage:", __doc__)
        return
    for arg in args:
        check(arg)

def check(file):
    if os.path.isdir(file) and not os.path.islink(file):
        if verbose:
            print "listing directory", file
        names = os.listdir(file)
        for name in names:
            fullname = os.path.join(file, name)
            if ((recurse and os.path.isdir(fullname) and
                 not os.path.islink(fullname))
                or name.lower().endswith(".py")):
                check(fullname)
        return

    if verbose:
        print "checking", file, "...",
    try:
        f = open(file)
    except IOError, msg:
        errprint("%r: I/O Error: %s" % (file, str(msg)))
        return

99
    ff = FutureFinder(f, file)
100
    changed = ff.run()
101 102 103
    if changed:
        ff.gettherest()
    f.close()
104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
    if changed:
        if verbose:
            print "changed."
            if dryrun:
                print "But this is a dry run, so leaving it alone."
        for s, e, line in changed:
            print "%r lines %d-%d" % (file, s+1, e+1)
            for i in range(s, e+1):
                print ff.lines[i],
            if line is None:
                print "-- deleted"
            else:
                print "-- change to:"
                print line,
        if not dryrun:
            bak = file + ".bak"
            if os.path.exists(bak):
                os.remove(bak)
            os.rename(file, bak)
            if verbose:
                print "renamed", file, "to", bak
125 126 127
            g = open(file, "w")
            ff.write(g)
            g.close()
128 129 130 131 132 133 134 135
            if verbose:
                print "wrote new", file
    else:
        if verbose:
            print "unchanged."

class FutureFinder:

136 137 138 139 140
    def __init__(self, f, fname):
        self.f = f
        self.fname = fname
        self.ateof = 0
        self.lines = [] # raw file lines
141 142 143 144 145 146

        # List of (start_index, end_index, new_line) triples.
        self.changed = []

    # Line-getter for tokenize.
    def getline(self):
147 148 149 150 151
        if self.ateof:
            return ""
        line = self.f.readline()
        if line == "":
            self.ateof = 1
152
        else:
153
            self.lines.append(line)
154 155 156 157 158 159 160 161 162 163 164 165 166 167
        return line

    def run(self):
        STRING = tokenize.STRING
        NL = tokenize.NL
        NEWLINE = tokenize.NEWLINE
        COMMENT = tokenize.COMMENT
        NAME = tokenize.NAME
        OP = tokenize.OP

        changed = self.changed
        get = tokenize.generate_tokens(self.getline).next
        type, token, (srow, scol), (erow, ecol), line = get()

168 169 170 171 172 173
        # Chew up initial comments and blank lines (if any).
        while type in (COMMENT, NL, NEWLINE):
            type, token, (srow, scol), (erow, ecol), line = get()

        # Chew up docstring (if any -- and it may be implicitly catenated!).
        while type is STRING:
174 175 176
            type, token, (srow, scol), (erow, ecol), line = get()

        # Analyze the future stmts.
177 178 179 180 181 182 183
        while 1:
            # Chew up comments and blank lines (if any).
            while type in (COMMENT, NL, NEWLINE):
                type, token, (srow, scol), (erow, ecol), line = get()

            if not (type is NAME and token == "from"):
                break
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211
            startline = srow - 1    # tokenize is one-based
            type, token, (srow, scol), (erow, ecol), line = get()

            if not (type is NAME and token == "__future__"):
                break
            type, token, (srow, scol), (erow, ecol), line = get()

            if not (type is NAME and token == "import"):
                break
            type, token, (srow, scol), (erow, ecol), line = get()

            # Get the list of features.
            features = []
            while type is NAME:
                features.append(token)
                type, token, (srow, scol), (erow, ecol), line = get()

                if not (type is OP and token == ','):
                    break
                type, token, (srow, scol), (erow, ecol), line = get()

            # A trailing comment?
            comment = None
            if type is COMMENT:
                comment = token
                type, token, (srow, scol), (erow, ecol), line = get()

            if type is not NEWLINE:
212 213
                errprint("Skipping file %r; can't parse line %d:\n%s" %
                         (self.fname, srow, line))
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234
                return []

            endline = srow - 1

            # Check for obsolete features.
            okfeatures = []
            for f in features:
                object = getattr(__future__, f, None)
                if object is None:
                    # A feature we don't know about yet -- leave it in.
                    # They'll get a compile-time error when they compile
                    # this program, but that's not our job to sort out.
                    okfeatures.append(f)
                else:
                    released = object.getMandatoryRelease()
                    if released is None or released <= sys.version_info:
                        # Withdrawn or obsolete.
                        pass
                    else:
                        okfeatures.append(f)

235
            # Rewrite the line if at least one future-feature is obsolete.
236 237 238 239 240 241 242 243 244 245 246
            if len(okfeatures) < len(features):
                if len(okfeatures) == 0:
                    line = None
                else:
                    line = "from __future__ import "
                    line += ', '.join(okfeatures)
                    if comment is not None:
                        line += ' ' + comment
                    line += '\n'
                changed.append((startline, endline, line))

247
            # Loop back for more future statements.
248 249 250

        return changed

251 252 253 254 255 256
    def gettherest(self):
        if self.ateof:
            self.therest = ''
        else:
            self.therest = self.f.read()

257 258 259 260 261 262 263 264 265 266 267 268 269 270
    def write(self, f):
        changed = self.changed
        assert changed
        # Prevent calling this again.
        self.changed = []
        # Apply changes in reverse order.
        changed.reverse()
        for s, e, line in changed:
            if line is None:
                # pure deletion
                del self.lines[s:e+1]
            else:
                self.lines[s:e+1] = [line]
        f.writelines(self.lines)
271 272 273
        # Copy over the remainder of the file.
        if self.therest:
            f.write(self.therest)
274 275 276

if __name__ == '__main__':
    main()