Mac/Contrib/Tabcleaner/Tabcleaner.py

   1 #!/usr/bin/python
   2
   3 import tokenize
   4 import string
   5
   6 TABSONLY = 'TABSONLY'
   7 SPACESONLY = 'SPACESONLY'
   8 MIXED = 'MIXED'
   9
  10 class PyText:
  11         def __init__(self, fnm, optdict):
  12                 self.optdict = optdict
  13                 self.fnm = fnm
  14                 self.txt = open(self.fnm, 'r').readlines()
  15                 self.indents = [(0, 0, )]
  16                 self.lnndx = 0
  17                 self.indentndx = 0
  18         def getline(self):
  19                 if self.lnndx < len(self.txt):
  20                         txt = self.txt[self.lnndx]
  21                         self.lnndx = self.lnndx + 1
  22                 else:
  23                         txt = ''
  24                 return txt
  25         def tokeneater(self, type, token, start, end, line):
  26                 if type == tokenize.INDENT:
  27                         (lvl, s) = self.indents[-1]
  28                         self.indents[-1] = (lvl, s, start[0]-1)
  29                         self.indents.append((lvl+1, start[0]-1,))
  30                 elif type == tokenize.DEDENT:
  31                         (lvl, s) = self.indents[-1]
  32                         self.indents[-1] = (lvl, s, start[0]-1)
  33                         self.indents.append((lvl-1, start[0]-1,))
  34                 elif type == tokenize.ENDMARKER:
  35                         (lvl, s) = self.indents[-1]
  36                         self.indents[-1] = (lvl, s, len(self.txt))
  37         def split(self, ln):
  38                 content = string.lstrip(ln)
  39                 if not content:
  40                         return ('', '\n')
  41                 lead = ln[:len(ln) - len(content)]
  42                 lead = string.expandtabs(lead)
  43                 return (lead, content)
  44
  45         def process(self):
  46                 style = self.optdict.get('style', TABSONLY)
  47                 indent = string.atoi(self.optdict.get('indent', '4'))
  48                 tabsz = string.atoi(self.optdict.get('tabs', '8'))
  49                 print 'file %s -> style %s, tabsize %d, indent %d' % (self.fnm, style, tabsz, indent)
  50                 tokenize.tokenize(self.getline, self.tokeneater)
  51                 #import pprint
  52                 #pprint.pprint(self.indents)
  53                 new = []
  54                 for (lvl, s, e) in self.indents:
  55                         if s >= len(self.txt):
  56                                 break
  57                         if s == e:
  58                                 continue
  59                         oldlead, content = self.split(self.txt[s])
  60                         #print "oldlead", len(oldlead), `oldlead`
  61                         if style == TABSONLY:
  62                                 newlead = '\t'*lvl
  63                         elif style == SPACESONLY:
  64                                 newlead = ' '*(indent*lvl)
  65                         else:
  66                                 sz = indent*lvl
  67                                 t,spcs = divmod(sz, tabsz)
  68                                 newlead = '\t'*t + ' '*spcs
  69                         new.append(newlead + content)
  70                         for ln in self.txt[s+1:e]:
  71                                 lead, content = self.split(ln)
  72                                 #print "lead:", len(lead)
  73                                 new.append(newlead + lead[len(oldlead):] + content)
  74                 self.save(new)
  75                 #print "---", self.fnm
  76                 #for ln in new:
  77                 #    print ln,
  78                 #print
  79
  80         def save(self, txt):
  81                 bakname = os.path.splitext(self.fnm)[0]+'.bak'
  82                 print "backing up", self.fnm, "to", bakname
  83                 #print os.getcwd()
  84                 try:
  85                         os.rename(self.fnm, bakname)
  86                 except os.error:
  87                         os.remove(bakname)
  88                         os.rename(self.fnm, bakname)
  89                 open(self.fnm, 'w').writelines(txt)
  90
  91 def test():
  92         tc = PyText('test1.py')
  93         tc.process()
  94         tc = PyText('test1.py')
  95         tc.process(style=TABSONLY)
  96         tc = PyText('test1.py')
  97         tc.process(style=MIXED, indent=4, tabs=8)
  98         tc = PyText('test1.py')
  99         tc.process(style=MIXED, indent=2, tabs=8)
 100
 101 def cleanfile(fnm, d):
 102         if os.path.isdir(fnm) and not os.path.islink(fnm):
 103                 names = os.listdir(fnm)
 104                 for name in names:
 105                         fullnm = os.path.join(fnm, name)
 106                         if (os.path.isdir(fullnm) and not os.path.islink(fullnm)) or \
 107                             os.path.normcase(fullnm[-3:]) == ".py":
 108                                 cleanfile(fullnm, d)
 109                 return
 110         tc = PyText(fnm, d)
 111         tc.process()
 112
 113 usage="""\
 114 %s [options] [path...]
 115  options
 116   -T : reformat to TABS ONLY
 117   -S : reformat to SPACES ONLY ( -i option is important)
 118   -M : reformat to MIXED SPACES / TABS ( -t and -i options important)
 119   -t<n> : tab is worth <n> characters
 120   -i<n> : indents should be <n> characters
 121   -h : print this text
 122  path is file or directory
 123 """
 124 if __name__ == '__main__':
 125         import sys, getopt, os
 126         opts, args = getopt.getopt(sys.argv[1:], "TSMht:i:")
 127         d = {}
 128         print `opts`
 129         for opt in opts:
 130                 if opt[0] == '-T':
 131                         d['style'] = TABSONLY
 132                 elif opt[0] == '-S':
 133                         d['style'] = SPACESONLY
 134                 elif opt[0] == '-M':
 135                         d['style'] = MIXED
 136                 elif opt[0] == '-t':
 137                         d['tabs'] = opt[1]
 138                 elif opt[0] == '-i':
 139                         d['indent'] = opt[1]
 140                 elif opt[0] == '-h':
 141                         print usage % sys.argv[0]
 142                         sys.exit(0)
 143         if not args:
 144                 print usage % sys.argv[0]
 145         for arg in args:
 146                 cleanfile(arg, d)
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160