5. `parser_run` is a library function intended to be linked together
with the generated parser tables to complete the implementation of
a parser.
-6. `calc.cgm` is a test grammar for a simple calculator.
+6. Finally `calc` is a test grammar for a simple calculator. The
+ `parsergen` program built from the C code in this file can extract
+ that grammar directly from this file and process it.
+
###### File: parsergen.c
#include <unistd.h>
## parser includes
## parser functions
## parser_run
-###### File: calc.cgm
- ## demo grammar
###### File: parsergen.mk
CFLAGS += -Wall -g
all :: parsergen calc
- parsergen.c parsergen.mk calc.cgm libparser.c parser.h : parsergen.mdc
+ parsergen.c parsergen.mk libparser.c parser.h : parsergen.mdc
./md2c parsergen.mdc
## Reading the grammar
literally copied into the generated `.c` and `.h`. files. The last
contains the grammar. This is tokenised with "[scanner][]".
+If the `--tag` option is given, then any top level header that doesn't
+start with the tag is ignored, and the tag is striped from the rest. So
+`--tag Foo`
+means that the three needed sections must be `Foo: header`, `Foo: code`,
+and `Foo: grammar`.
+
[mdcode]: mdcode.html
[scanner]: scanner.html
`mdcode`. `scanner` does provide `text_dump` which is useful for strings
which might contain control characters.
+`strip_tag` is a bit like `strncmp`, but adds a test for a colon,
+because that is what we need to detect tags.
+
###### functions
static int text_is(struct text t, char *s)
{
printf("%.*s", t.len, t.txt);
}
+ static int strip_tag(struct text *t, char *tag)
+ {
+ int skip = strlen(tag) + 1;
+ if (skip >= t->len ||
+ strncmp(t->txt, tag, skip-1) != 0 ||
+ t->txt[skip-1] != ':')
+ return 0;
+ while (skip < t->len && t->txt[skip] == ' ')
+ skip++;
+ t->len -= skip;
+ t->txt += skip;
+ return 1;
+ }
+
### Symbols
Productions are comprised primarily of symbols - terminal and
};
struct token_state *state = token_open(code, &conf);
- struct token tk = token_next(state);
+ struct token tk;
struct symbol *head = NULL;
struct grammar *g;
char *err = NULL;
### Building the `first` sets
When calculating what can follow a particular non-terminal, we will need to
-know what the "first" terminal in an subsequent non-terminal might be. So
+know what the "first" terminal in any subsequent non-terminal might be. So
we calculate the `first` set for every non-terminal and store them in an
array. We don't bother recording the "first" set for terminals as they are
trivial.
{ "SLR", 0, NULL, 'S' },
{ "LALR", 0, NULL, 'L' },
{ "LR1", 0, NULL, '1' },
+ { "tag", 1, NULL, 't' },
{ "report", 0, NULL, 'R' },
{ "output", 1, NULL, 'o' },
{ NULL, 0, NULL, 0 }
};
- const char *options = "05SL1Ro:";
+ const char *options = "05SL1t:Ro:";
###### process arguments
int opt;
char *outfile = NULL;
char *infile;
char *name;
+ char *tag = NULL;
int report = 1;
enum grammar_type type = LR05;
while ((opt = getopt_long(argc, argv, options,
report = 2; break;
case 'o':
outfile = optarg; break;
+ case 't':
+ tag = optarg; break;
default:
fprintf(stderr, "Usage: parsergen ...\n");
exit(1);
struct code_node *code = NULL;
struct code_node *gram = NULL;
for (s = table; s; s = s->next) {
- if (text_is(s->section, "header"))
+ struct text sec = s->section;
+ if (tag && !strip_tag(&sec, tag))
+ continue;
+ if (text_is(sec, "header"))
hdr = s->code;
- else if (text_is(s->section, "code"))
+ else if (text_is(sec, "code"))
code = s->code;
- else if (text_is(s->section, "grammar"))
+ else if (text_is(sec, "grammar"))
gram = s->code;
else {
fprintf(stderr, "Unknown content section: %.*s\n",
short sym;
short starts_indented;
short indents;
+ short newline_permitted;
} *stack, next;
void **asn_stack;
int stack_size;
function reports if it could.
So `shift` finds the next state. If that succeed it extends the allocations
-if needed and pushed all the information onto the stacks.
+if needed and pushes all the information onto the stacks.
###### parser functions
p->next.state = newstate;
p->next.indents = 0;
p->next.starts_indented = 0;
+ // if new state doesn't start a line, we inherit newline_permitted status
+ if (states[newstate].starts_line)
+ p->next.newline_permitted = 1;
return 1;
}
if (num) {
p->next.state = p->stack[p->tos].state;
p->next.starts_indented = p->stack[p->tos].starts_indented;
+ p->next.newline_permitted = p->stack[p->tos].newline_permitted;
+ if (p->next.indents > p->next.starts_indented)
+ p->next.newline_permitted = 0;
}
}
int accepted = 0;
void *ret;
+ p.next.newline_permitted = states[0].starts_line;
while (!accepted) {
struct token *err_tk;
if (!tk)
(p.stack[p.tos-1].indents == 1 &&
states[p.next.state].reduce_size > 1)) {
p.stack[p.tos-1].indents -= 1;
+ if (p.stack[p.tos-1].indents == p.stack[p.tos-1].starts_indented) {
+ // no internal indent any more, reassess 'newline_permitted'
+ if (states[p.stack[p.tos-1].state].starts_line)
+ p.stack[p.tos-1].newline_permitted = 1;
+ else if (p.tos > 1)
+ p.stack[p.tos-1].newline_permitted = p.stack[p.tos-2].newline_permitted;
+ }
free(tk);
tk = NULL;
continue;
// fall through and force a REDUCE (as 'shift'
// will fail).
}
+ if (p.next.sym == TK_newline) {
+ if (!p.tos || ! p.stack[p.tos-1].newline_permitted) {
+ free(tk);
+ tk = NULL;
+ continue;
+ }
+ }
if (shift(&p, tk, states)) {
tk = NULL;
continue;
[TK_newline] = "NEWLINE",
[TK_eof] = "$eof",
};
+ static void parser_trace_state(FILE *trace, struct frame *f, const struct state states[])
+ {
+ fprintf(trace, "(%d", f->state);
+ if (f->indents)
+ fprintf(trace, "%c%d", f->starts_indented?':':'.',
+ f->indents);
+ if (states[f->state].starts_line)
+ fprintf(trace, "s");
+ if (f->newline_permitted)
+ fprintf(trace, "n");
+ fprintf(trace, ") ");
+ }
+
void parser_trace(FILE *trace, struct parser *p,
struct token *tk, const struct state states[],
const char *non_term[], int knowns)
int i;
for (i = 0; i < p->tos; i++) {
int sym = p->stack[i].sym;
- fprintf(trace, "(%d) ", p->stack[i].state);
+ parser_trace_state(trace, &p->stack[i], states);
if (sym < TK_reserved &&
reserved_words[sym] != NULL)
fputs(reserved_words[sym], trace);
trace);
fputs(" ", trace);
}
- fprintf(trace, "(%d) [", p->next.state);
+ parser_trace_state(trace, &p->next, states);
+ fprintf(trace, " [");
if (tk->num < TK_reserved &&
reserved_words[tk->num] != NULL)
fputs(reserved_words[tk->num], trace);
something like this.
###### File: parsergen.mk
- calc.c : parsergen calc.cgm
- ./parsergen -o calc calc.cgm
+ calc.c calc.h : parsergen parsergen.mdc
+ ./parsergen --tag calc -o calc parsergen.mdc
calc : calc.o libparser.o libscanner.o libmdcode.o libnumber.o
$(CC) $(CFLAGS) -o calc calc.o libparser.o libscanner.o libmdcode.o libnumber.o -licuuc -lgmp
-###### demo grammar
-
- # header
- ~~~~~
+# calc: header
#include "number.h"
// what do we use for a demo-grammar? A calculator of course.
int err;
};
- ~~~~~
- # code
- ~~~~~
+# calc: code
#include <stdlib.h>
#include <unistd.h>
exit(0);
}
- ~~~~~
- # grammar
- ~~~~~
+# calc: grammar
Session -> Session Line
| Line
code / ocean / blobdiff