usr/src/bin/sh/mktokens

#!/bin/sh -
#
# Copyright (c) 1991 The Regents of the University of California.
# All rights reserved.
#
# This code is derived from software contributed to Berkeley by
# Kenneth Almquist.
#
# %sccs.include.redist.sh%
#
#       @(#)mktokens    5.1 (Berkeley) %G%

# The following is a list of tokens.  The second column is nonzero if the
# token marks the end of a list.  The third column is the name to print in
# error messages.

cat > /tmp/ka$$ <<\!
TEOF    1       end of file
TNL     0       newline
TSEMI   0       ";"
TBACKGND 0      "&"
TAND    0       "&&"
TOR     0       "||"
TPIPE   0       "|"
TLP     0       "("
TRP     1       ")"
TENDCASE 1      ";;"
TENDBQUOTE 1    "`"
TREDIR  0       redirection
TWORD   0       word
TIF     0       "if"
TTHEN   1       "then"
TELSE   1       "else"
TELIF   1       "elif"
TFI     1       "fi"
TWHILE  0       "while"
TUNTIL  0       "until"
TFOR    0       "for"
TDO     1       "do"
TDONE   1       "done"
TBEGIN  0       "{"
TEND    1       "}"
TCASE   0       "case"
TESAC   1       "esac"
!
nl=`wc -l /tmp/ka$$`
exec > token.def
awk '{print "#define " $1 " " NR-1}' /tmp/ka$$
echo '
/* Array indicating which tokens mark the end of a list */
const char tokendlist[] = {'
awk '{print "\t" $2 ","}' /tmp/ka$$
echo '};

char *const tokname[] = {'
sed -e 's/"/\\"/g' \
    -e 's/[^     ]*[     ][      ]*[^    ]*[     ][      ]*\(.*\)/      "\1",/' \
    /tmp/ka$$
echo '};
'
sed 's/"//g' /tmp/ka$$ | awk '
/TIF/{print "#define KWDOFFSET " NR-1; print ""; print "char *const parsekwd[] = {"}
/TIF/,/neverfound/{print "      \"" $3 "\","}'
echo '  0
};'

rm /tmp/ka$$