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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
|
include <ctype.h>
include <lexnum.h>
include "../lib/lexer.h"
include "../lib/prtoken.h"
# PR_LEXER - Lexical analizer for the parser of the configuration file.
int procedure pr_lexer (fd, yylval)
int fd # input file descriptor
pointer yylval # YYLVAL token pointer
char key[SZ_LINE]
int tok # next token
int ip, n
include "lexer.com"
bool strne()
int ctor()
int strdic(), strlen()
int lexnum()
int getline()
begin
# Stay scanning the input file until a valid or
# error token is found
repeat {
# Skip whitespaces and blank lines
while (line[pos] == '\n' || IS_WHITE (line[pos])) {
# If next character is a newline count
# lines, and read a new line from file
if (line[pos] == '\n') {
nlines = nlines + 1
pos = 1
if (getline (fd, line) == EOF) {
call strcpy ("EOF", LEX_ID (yylval), SZ_LINE)
return (EOFILE)
}
} else
pos = pos + 1
}
# Test first valid character
if (IS_ALPHA (line[pos])) { # identifier or keyword
# Read identifier
for (ip=1; IS_ALNUM (line[pos]); ip=ip+1) {
id[ip] = line[pos]
pos = pos + 1
}
id[ip] = EOS
# Check for keyword. Abreviations of keywords are allowed
# to up to a certain number of characters, but the
# identifier returned by the lexer should contain the full
# keyword name.
n = strdic (id, key, SZ_LINE, KEYWORDS)
if (n > 0 && strlen (id) >= ABBREVIATE) {
call strcpy (key, id, SZ_LINE)
switch (n) {
case K_CATALOG:
tok = CATSECT
break
case K_OBSERVATION:
tok = OBSSECT
break
case K_EXTINCTION:
tok = EXTSECT
break
case K_TRANSFORMATION:
tok = TRNSECT
break
case K_FIT:
tok = FITID
break
case K_CONSTANT:
tok = CONSTID
break
case K_DELTA:
tok = DELTAID
break
case K_ERROR:
tok = ERRORID
break
case K_WEIGHT:
tok = WEIGHTID
break
case K_MIN:
tok = MINID
break
case K_MAX:
tok = MAXID
break
case K_SET:
tok = SETID
break
case K_DERIVATIVE:
tok = DERIVID
break
case K_PLOT:
tok = PLOTID
break
default:
call error (0, "pr_lexxer: Unknown keyword token")
}
}
# Check for function. Anything abbreviated,
# or not matching is and identifier.
n = strdic (id, key, SZ_LINE, FUNCTIONS)
if (n == 0) {
tok = IDENTIFIER
break
} else if (strne (id, key)) {
tok = IDENTIFIER
break
}
switch (n) {
case K_ABS: # absolute value
tok = F_ABS
break
case K_ACOS: # arc cosine
tok = F_ACOS
break
case K_ASIN: # arc sine
tok = F_ASIN
break
case K_ATAN: # arc tangent
tok = F_ATAN
break
case K_COS: # cosine
tok = F_COS
break
case K_EXP: # exponential
tok = F_EXP
break
case K_LOG: # natural logarithm
tok = F_LOG
break
case K_LOG10: # decimal logarithm
tok = F_LOG10
break
case K_SIN: # sine
tok = F_SIN
break
case K_SQRT: # square root
tok = F_SQRT
break
case K_TAN: # tangent
tok = F_TAN
break
default:
call error (0, "pr_lexer: Unknown identifier")
}
} else if (IS_DIGIT (line[pos]) || line[pos] == '.') { # number
# Process number
switch (lexnum (line, pos, n)) {
case LEX_DECIMAL:
tok = INUMBER
case LEX_REAL:
tok = RNUMBER
default:
tok = ERR
}
# Copy whatever was processed
# to the identifier
do ip = 1, n
id[ip] = line[pos + ip - 1]
id[n + 1] = EOS
# Advance to next token and
# break the loop
pos = pos + n
break
} else if (line[pos] == '(') { # left parenthesis
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy ("(", id, SZ_LINE)
tok = LPAR
pos = pos + 1
break
} else if (line[pos] == ')') { # right parenthesis
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy (")", id, SZ_LINE)
tok = RPAR
pos = pos + 1
break
} else if (line[pos] == '+') { # plus
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy ("+", id, SZ_LINE)
tok = PLUS
pos = pos + 1
break
} else if (line[pos] == '-') { # minus
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy ("-", id, SZ_LINE)
tok = MINUS
pos = pos + 1
break
} else if (line[pos] == '*') { # star and double star
# Advance to next character to see if
# it's another star
pos = pos + 1
if (line[pos] == '*') {
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy ("**", id, SZ_LINE)
tok = EXPON
pos = pos + 1
break
} else {
# Copy input characters to identifier, set
# token, and break the loop
call strcpy ("*", id, SZ_LINE)
tok = STAR
break
}
} else if (line[pos] == '/') { # slash
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy ("/", id, SZ_LINE)
tok = SLASH
pos = pos + 1
break
} else if (line[pos] == '=') { # equal
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy ("=", id, SZ_LINE)
tok = EQUAL
pos = pos + 1
break
} else if (line[pos] == ',') { # comma
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy (",", id, SZ_LINE)
tok = COMMA
pos = pos + 1
break
} else if (line[pos] == ':') { # colon
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy (":", id, SZ_LINE)
tok = COLON
pos = pos + 1
break
} else if (line[pos] == ';') { # semicolon
# Copy input character to identifier, set
# token, and advance to next character before
# breaking the loop
call strcpy (";", id, SZ_LINE)
tok = SEMICOLON
pos = pos + 1
break
} else if (line[pos] == '#') { # comment
# Skip current line
pos = strlen (line)
} else { # none of the above
# All characters not included in the previous
# categories are treated as errors
id[1] = line[pos]
id[2] = EOS
tok = ERR
# Advance to next character before
# breaking the loop
pos = pos + 1
break
}
} # repeat
# Update yylval structure
LEX_TOK (yylval) = tok
call strcpy (id, LEX_ID (yylval), SZ_LINE)
if (tok == INUMBER || tok == RNUMBER) {
ip = 1
n = ctor (LEX_ID (yylval), ip, LEX_VAL (yylval))
} else
LEX_VAL (yylval) = INDEFR
# Debug
#call eprintf ("(tok=%d) (id=%s) (rval=%g)\n")
#call pargi (LEX_TOK (yylval))
#call pargstr (LEX_ID (yylval))
#call pargi (LEX_VAL (yylval))
# Return token value
return (tok)
end
|
