blob: 8d9d2fdcd2e320769854af0d3223f56cd92f57b5 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
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
52
53
54
55
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
|
sc=
sgetc()
{
sc="$(dd bs=1 count=1 2>/dev/null; printf '.')"
sc="${sc%.}"
}
codegen_sub()
{
local array="${1}"
shift 1
IFS="${RS}"
for t in ${array}; do
toktext "${t}"
case "${t%${US}*}" in
T_NEWLINE)
;;
*)
printf ' '
;;
esac
done
unset IFS
}
# The token stack is encoded in a string in the following grammar:
# Terminal symbols:
# TOKEN
# Production rules:
# stack = tokens [ '<SOH>' type '<STX>' stack '<ETX>' [ tokens ] ] ;
# tokens = TOKEN { '<RS>' TOKEN } ;
# type = 'C' ;
# We need to recurse through this stack to get to all the tokens.
# Each element in the stack (an array of tokens) gets run through the codegen to
# become text that is inserted into the array below.
parse_stack()
{
local array=
array=''
while :; do
sgetc
case "${sc}" in
'')
# EOF
break
;;
"${SOH}")
# New stack element
sgetc
case "${sc}" in
'C')
# Command substitution
sgetc # STX
array="${array}$(parse_stack)."
array="${array%.}"
;;
esac
;;
"${ETX}")
# End of stack element
break
;;
*)
# Token character
array="${array}${sc}"
;;
esac
done
codegen_sub "${array}"
}
codegen()
{
local toks="${1}"
shift 1
if printf '%s' "${toks}" | parse_stack; then
return 0
else
return 1
fi
}
|
