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('--skip-misc-fixups', action='store_true', default=False,
  22                         help='Skip miscellaneous fixup/shrink fixups')
  23     parser.add_argument('--number-lines', action='store_true', default=False,
  24                         help='Number the lines')
  25     parser.add_argument('--keep-labels', action='store_true', default=False,
  26                         help='Keep string labels instead of replacing with line numbers')
  27     parser.add_argument('--combine-lines', action='store_true', default=False,
  28                         help='Combine lines using the ":" separator')
  29
  30     args = parser.parse_args()
  31     if args.combine_lines and args.keep_rems:
  32         parser.error("--combine-lines and --keep-rems are mutually exclusive")
  33
  34     return args
  35
  36 # pull in include files
  37 def resolve_includes(orig_lines, keep_rems=0):
  38     included = {}
  39     lines = []
  40     for line in orig_lines:
  41         m = re.match(r"^ *REM \$INCLUDE: '([^']*)' *$", line)
  42         if m and m.group(1) not in included:
  43             f = m.group(1)
  44             if f not in included:
  45                 ilines = [l.rstrip() for l in open(f).readlines()]
  46                 if keep_rems: lines.append("REM vvv BEGIN '%s' vvv" % f)
  47                 lines.extend(ilines)
  48                 if keep_rems: lines.append("REM ^^^ END '%s' ^^^" % f)
  49             else:
  50                 debug("Ignoring already included file: %s" % f)
  51         else:
  52             lines.append(line)
  53     return lines
  54
  55 def drop_blank_lines(orig_lines):
  56     lines = []
  57     for line in orig_lines:
  58         if re.match(r"^\w*$", line): continue
  59         lines.append(line)
  60     return lines
  61
  62
  63 def drop_rems(orig_lines):
  64     lines = []
  65     for line in orig_lines:
  66         if re.match(r"^ *REM", line):
  67             continue
  68         m = re.match(r"^(.*): *REM .*$", line)
  69         if m:
  70             lines.append(m.group(1))
  71         else:
  72             lines.append(line)
  73     return lines
  74
  75 def remove_indent(orig_lines):
  76     lines = []
  77     for line in orig_lines:
  78         m = re.match(r"^ *([^ ].*)$", line)
  79         lines.append(m.group(1))
  80     return lines
  81
  82 def misc_fixups(orig_lines):
  83     text = "\n".join(orig_lines)
  84     text = re.sub(r"\bTHEN GOTO\b", "THEN", text)
  85     text = re.sub(r"\bPRINT \"", "PRINT\"", text)
  86     text = re.sub(r"\bIF ", "IF", text)
  87     return text.split("\n")
  88
  89 def finalize(lines, args):
  90     labels_lines = {}
  91     lines_labels = {}
  92
  93     # number lines
  94     if args.number_lines:
  95         src_lines = lines
  96         lines = []
  97         lnum=1
  98         for line in src_lines:
  99             if not args.keep_labels:
 100                 m = re.match(r"^ *([^ ]*): *$", line)
 101                 if m:
 102                     labels_lines[m.groups(1)[0]] = lnum
 103                     lines_labels[lnum] = m.groups(1)[0]
 104                     continue
 105             lines.append("%s %s" % (lnum, line))
 106             lnum += 1
 107
 108     def update_labels_lines(text, a,b):
 109         stext = ""
 110         while stext != text:
 111             stext = text
 112             text = re.sub(r"(THEN) %s\b" % a, r"THEN %s" % b, stext)
 113             #text = re.sub(r"(THEN)%s\b" % a, r"THEN%s" % b, stext)
 114             text = re.sub(r"(ON [^:\n]* GOTO [^:\n]*)\b%s\b" % a, r"\g<1>%s" % b, text)
 115             text = re.sub(r"(ON [^:\n]* GOSUB [^:\n]*)\b%s\b" % a, r"\g<2>%s" % b, text)
 116             text = re.sub(r"(GOSUB) %s\b" % a, r"\1 %s" % b, text)
 117             text = re.sub(r"(GOTO) %s\b" % a, r"\1 %s" % b, text)
 118             #text = re.sub(r"(GOTO)%s\b" % a, r"\1%s" % b, text)
 119         return text
 120
 121     if not args.keep_labels:
 122         src_lines = lines
 123         text = "\n".join(lines)
 124         # search for and replace GOTO/GOSUBs
 125         for label, lnum in labels_lines.items():
 126             text = update_labels_lines(text, label, lnum)
 127         lines = text.split("\n")
 128
 129     if args.combine_lines:
 130         renumber = {}
 131         src_lines = lines
 132         lines = []
 133         pos = 0
 134         acc_line = ""
 135         def renum(line):
 136             lnum = len(lines)+1
 137             renumber[old_num] = lnum
 138             return "%s %s" % (lnum, line)
 139         while pos < len(src_lines):
 140             line = src_lines[pos]
 141             # TODO: handle args.keep_labels and (not args.number_lines)
 142             m = re.match(r"^([0-9]*) (.*)$", line)
 143             old_num = int(m.group(1))
 144             line = m.group(2)
 145
 146             if acc_line == "":
 147                 # Starting a new line
 148                 acc_line = renum(line)
 149             elif old_num in lines_labels or re.match(r"^ *FOR\b.*", line):
 150                 # This is a GOTO/GOSUB target or FOR loop so it must
 151                 # be on a line by itself
 152                 lines.append(acc_line)
 153                 acc_line = renum(line)
 154             elif re.match(r".*\b(?:GOTO|THEN|RETURN)\b.*", acc_line):
 155                 # GOTO/THEN/RETURN are last thing on the line
 156                 lines.append(acc_line)
 157                 acc_line = renum(line)
 158             # TODO: not sure why this is 88 rather than 80
 159             elif len(acc_line) + 1 + len(line) < 88:
 160                 # Continue building up the line
 161                 acc_line = acc_line + ":" + line
 162                 # GOTO/IF/RETURN must be the last things on a line so
 163                 # start a new line
 164                 if re.match(r".*\b(?:GOTO|THEN|RETURN)\b.*", line):
 165                     lines.append(acc_line)
 166                     acc_line = ""
 167             else:
 168                 # Too long so start a new line
 169                 lines.append(acc_line)
 170                 acc_line = renum(line)
 171             pos += 1
 172         if acc_line != "":
 173             lines.append(acc_line)
 174
 175         # Finally renumber GOTO/GOSUBS
 176         src_lines = lines
 177         text = "\n".join(lines)
 178         # search for and replace GOTO/GOSUBs
 179         for a in sorted(renumber.keys()):
 180             b = renumber[a]
 181             text = update_labels_lines(text, a, b)
 182         lines = text.split("\n")
 183
 184
 185     return lines
 186
 187 if __name__ == '__main__':
 188     args = parse_args()
 189
 190     debug("Preprocessing basic file '"+args.infile+"'")
 191
 192     # read in lines
 193     lines = [l.rstrip() for l in open(args.infile).readlines()]
 194     debug("Number of original lines: %s" % len(lines))
 195
 196     # pull in include files
 197     lines = resolve_includes(lines, keep_rems=args.keep_rems)
 198     debug("Number of lines after includes: %s" % len(lines))
 199
 200     # drop blank lines
 201     if not args.keep_blank_lines:
 202         lines = drop_blank_lines(lines)
 203         debug("Number of lines after dropping blank lines: %s" % len(lines))
 204
 205     # keep/drop REMs
 206     if not args.keep_rems:
 207         lines = drop_rems(lines)
 208         debug("Number of lines after dropping REMs: %s" % len(lines))
 209
 210     # keep/remove the indenting
 211     if not args.keep_indent:
 212         lines = remove_indent(lines)
 213
 214     # apply some miscellaneous simple fixups/regex transforms
 215     if not args.skip_misc_fixups:
 216         lines = misc_fixups(lines)
 217
 218     # number lines, drop/keep labels, combine lines
 219     lines = finalize(lines, args)
 220
 221     print("\n".join(lines))