basic/basicpp.py

   1 #!/usr/bin/env python
   2
   3 from __future__ import print_function
   4 import argparse
   5 import re
   6 import sys
   7
   8 def debug(*args, **kwargs):
   9     print(*args, file=sys.stderr, **kwargs)
  10
  11 def parse_args():
  12     parser = argparse.ArgumentParser(description='Preprocess Basic code.')
  13     parser.add_argument('infile', type=str,
  14                         help='the Basic file to preprocess')
  15     parser.add_argument('--keep-rems', action='store_true', default=False,
  16                         help='The type of REMs to keep (0 (none) -> 4 (all)')
  17     parser.add_argument('--keep-blank-lines', action='store_true', default=False,
  18                         help='Keep blank lines from the original file')
  19     parser.add_argument('--keep-indent', action='store_true', default=False,
  20                         help='Keep line identing')
  21     parser.add_argument('--number-lines', action='store_true', default=False,
  22                         help='Number the lines')
  23     parser.add_argument('--keep-labels', action='store_true', default=False,
  24                         help='Keep string labels instead of replacing with line numbers')
  25
  26     return parser.parse_args()
  27
  28 # pull in include files
  29 def resolve_includes(orig_lines, keep_rems=0):
  30     included = {}
  31     lines = []
  32     for line in orig_lines:
  33         m = re.match(r"^ *REM \$INCLUDE: '([^']*)' *$", line)
  34         if m and m.group(1) not in included:
  35             f = m.group(1)
  36             if f not in included:
  37                 ilines = [l.rstrip() for l in open(f).readlines()]
  38                 if keep_rems: lines.append("REM vvv BEGIN '%s' vvv" % f)
  39                 lines.extend(ilines)
  40                 if keep_rems: lines.append("REM ^^^ END '%s' ^^^" % f)
  41             else:
  42                 debug("Ignoring already included file: %s" % f)
  43         else:
  44             lines.append(line)
  45     return lines
  46
  47 def drop_blank_lines(orig_lines):
  48     lines = []
  49     for line in orig_lines:
  50         if re.match(r"^\w*$", line): continue
  51         lines.append(line)
  52     return lines
  53
  54
  55 def drop_rems(orig_lines):
  56     lines = []
  57     for line in orig_lines:
  58         if re.match(r"^ *REM", line):
  59             continue
  60         m = re.match(r"^(.*): *REM .*$", line)
  61         if m:
  62             lines.append(m.group(1))
  63         else:
  64             lines.append(line)
  65     return lines
  66
  67 def remove_indent(orig_lines):
  68     lines = []
  69     for line in orig_lines:
  70         m = re.match(r"^ *([^ ].*)$", line)
  71         lines.append(m.group(1))
  72     return lines
  73
  74 def number_lines(orig_lines, keep_labels=True):
  75     # number lines
  76     lnum=1
  77     labels = {}
  78     lines = []
  79     for line in orig_lines:
  80         if not keep_labels:
  81             m = re.match(r"^ *([^ ]*): *$", line)
  82             if m:
  83                 labels[m.groups(1)] = lnum
  84                 continue
  85         lines.append("%s %s" % (lnum, line))
  86         lnum += 1
  87
  88     if not keep_labels:
  89         text = "\n".join(lines)
  90         # search for and replace GOTO/GOSUBs
  91         for label, lnum in labels.items():
  92             text = re.sub(r"(THEN) %s\b" % label, r"THEN %s" % lnum, text)
  93             text = re.sub(r"(ON [^:]* GOTO [^:]*) %s\b" % label, r"\1 %s" % lnum, text)
  94             text = re.sub(r"(ON [^:]* GOSUB [^:]*) %s\b" % label, r"\2 %s" % lnum, text)
  95             text = re.sub(r"(GOSUB) %s\b" % label, r"\1 %s" % lnum, text)
  96             text = re.sub(r"(GOTO) %s\b" % label, r"\1 %s" % lnum, text)
  97         return text.split("\n")
  98     else:
  99         return lines
 100
 101 if __name__ == '__main__':
 102     args = parse_args()
 103
 104     debug("Preprocessing basic file '"+args.infile+"'")
 105
 106     # read in lines
 107     lines = [l.rstrip() for l in open(args.infile).readlines()]
 108     debug("Number of original lines: %s" % len(lines))
 109
 110     # pull in include files
 111     lines = resolve_includes(lines, keep_rems=args.keep_rems)
 112     debug("Number of lines after includes: %s" % len(lines))
 113
 114     # drop blank lines
 115     if not args.keep_blank_lines:
 116         lines = drop_blank_lines(lines)
 117         debug("Number of lines after dropping blank lines: %s" % len(lines))
 118
 119     # keep/drop REMs
 120     if not args.keep_rems:
 121         lines = drop_rems(lines)
 122         debug("Number of lines after dropping REMs: %s" % len(lines))
 123
 124     # keep/remove the indenting
 125     if not args.keep_indent:
 126         lines = remove_indent(lines)
 127
 128     # number lines
 129     if args.number_lines:
 130         lines = number_lines(lines, keep_labels=args.keep_labels)
 131
 132     print("\n".join(lines))