summaryrefslogtreecommitdiffhomepage
path: root/src
diff options
context:
space:
mode:
authorYukihiro "Matz" Matsumoto <[email protected]>2021-01-06 17:14:12 +0900
committerYukihiro "Matz" Matsumoto <[email protected]>2021-01-06 17:14:12 +0900
commit8e048ae25db2c00e983bb75f915058844a50c0cb (patch)
tree4dbf22f15e482bf082712286bcf0daa5e51aa41c /src
parent1341e53961b3e99ac67d803e5ead677e976d18c4 (diff)
parent74c9502bd45fd70926c86ce564c2d5d1df9a6dd0 (diff)
downloadmruby-8e048ae25db2c00e983bb75f915058844a50c0cb.tar.gz
mruby-8e048ae25db2c00e983bb75f915058844a50c0cb.zip
Merge branch 'shuujii-improve-source-scanning-for-presym'
Diffstat (limited to 'src')
-rw-r--r--src/class.c4
-rw-r--r--src/debug.c2
-rw-r--r--src/dump.c201
-rw-r--r--src/symbol.c18
4 files changed, 199 insertions, 26 deletions
diff --git a/src/class.c b/src/class.c
index 270d8885f..85a26d343 100644
--- a/src/class.c
+++ b/src/class.c
@@ -2792,7 +2792,8 @@ static const mrb_code new_iseq[] = {
OP_RETURN, 0x0 /* OP_RETURN R0 */
};
-const mrb_sym new_syms[] = { MRB_SYM(allocate), MRB_SYM(initialize) };
+MRB_PRESYM_DEFINE_VAR_AND_INITER(new_syms, 2, MRB_SYM(allocate), MRB_SYM(initialize))
+
static const mrb_irep new_irep = {
3, 6, 0, MRB_IREP_STATIC,
new_iseq, NULL, new_syms, NULL, NULL, NULL,
@@ -2805,6 +2806,7 @@ init_class_new(mrb_state *mrb, struct RClass *cls)
struct RProc *p;
mrb_method_t m;
+ init_new_syms(mrb);
p = mrb_proc_new(mrb, &new_irep);
MRB_METHOD_FROM_PROC(m, p);
mrb_define_method_raw(mrb, cls, MRB_SYM(new), m);
diff --git a/src/debug.c b/src/debug.c
index c03c91cf5..2f9320ac9 100644
--- a/src/debug.c
+++ b/src/debug.c
@@ -66,7 +66,7 @@ mrb_debug_get_filename(mrb_state *mrb, const mrb_irep *irep, uint32_t pc)
MRB_API int32_t
mrb_debug_get_line(mrb_state *mrb, const mrb_irep *irep, uint32_t pc)
{
- if (irep && pc < irep->ilen) {
+ if (irep && pc >= 0 && pc < irep->ilen) {
mrb_irep_debug_info_file* f = NULL;
if (!irep->debug_info) {
return -1;
diff --git a/src/dump.c b/src/dump.c
index 40f149f5d..3464f08b9 100644
--- a/src/dump.c
+++ b/src/dump.c
@@ -10,7 +10,6 @@
#include <mruby/dump.h>
#include <mruby/string.h>
#include <mruby/irep.h>
-#include <mruby/numeric.h>
#include <mruby/debug.h>
#ifndef MRB_NO_FLOAT
@@ -24,6 +23,45 @@ static size_t get_irep_record_size_1(mrb_state *mrb, const mrb_irep *irep);
# error This code cannot be built on your environment.
#endif
+#define OPERATOR_SYMBOL(sym_name, name) {name, sym_name, sizeof(sym_name)-1}
+struct operator_symbol {
+ const char *name;
+ const char *sym_name;
+ uint16_t sym_name_len;
+};
+static const struct operator_symbol operator_table[] = {
+ OPERATOR_SYMBOL("!", "not"),
+ OPERATOR_SYMBOL("%", "mod"),
+ OPERATOR_SYMBOL("&", "and"),
+ OPERATOR_SYMBOL("*", "mul"),
+ OPERATOR_SYMBOL("+", "add"),
+ OPERATOR_SYMBOL("-", "sub"),
+ OPERATOR_SYMBOL("/", "div"),
+ OPERATOR_SYMBOL("<", "lt"),
+ OPERATOR_SYMBOL(">", "gt"),
+ OPERATOR_SYMBOL("^", "xor"),
+ OPERATOR_SYMBOL("`", "tick"),
+ OPERATOR_SYMBOL("|", "or"),
+ OPERATOR_SYMBOL("~", "neg"),
+ OPERATOR_SYMBOL("!=", "neq"),
+ OPERATOR_SYMBOL("!~", "nmatch"),
+ OPERATOR_SYMBOL("&&", "andand"),
+ OPERATOR_SYMBOL("**", "pow"),
+ OPERATOR_SYMBOL("+@", "plus"),
+ OPERATOR_SYMBOL("-@", "minus"),
+ OPERATOR_SYMBOL("<<", "lshift"),
+ OPERATOR_SYMBOL("<=", "le"),
+ OPERATOR_SYMBOL("==", "eq"),
+ OPERATOR_SYMBOL("=~", "match"),
+ OPERATOR_SYMBOL(">=", "ge"),
+ OPERATOR_SYMBOL(">>", "rshift"),
+ OPERATOR_SYMBOL("[]", "aref"),
+ OPERATOR_SYMBOL("||", "oror"),
+ OPERATOR_SYMBOL("<=>", "cmp"),
+ OPERATOR_SYMBOL("===", "eqq"),
+ OPERATOR_SYMBOL("[]=", "aset"),
+};
+
static size_t
get_irep_header_size(mrb_state *mrb)
{
@@ -888,6 +926,8 @@ mrb_dump_irep_cfunc(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *f
return MRB_DUMP_WRITE_FAULT;
}
if (fprintf(fp,
+ "#include <mruby.h>\n"
+ "#include <mruby/proc.h>\n"
"#ifdef __cplusplus\n"
"extern const uint8_t %s[];\n"
"#endif\n"
@@ -960,26 +1000,132 @@ dump_pool(mrb_state *mrb, const mrb_pool_value *p, FILE *fp)
return MRB_DUMP_OK;
}
-mrb_bool mrb_sym_static_p(mrb_state *mrb, mrb_sym sym);
+static mrb_bool
+sym_name_word_p(const char *name, mrb_int len)
+{
+ if (len == 0) return FALSE;
+ if (name[0] != '_' && !ISALPHA(name[0])) return FALSE;
+ for (int i = 1; i < len; i++) {
+ if (name[i] != '_' && !ISALNUM(name[i])) return FALSE;
+ }
+ return TRUE;
+}
+
+static mrb_bool
+sym_name_with_equal_p(const char *name, mrb_int len)
+{
+ return len >= 2 && name[len-1] == '=' && sym_name_word_p(name, len-1);
+}
+
+static mrb_bool
+sym_name_with_question_mark_p(const char *name, mrb_int len)
+{
+ return len >= 2 && name[len-1] == '?' && sym_name_word_p(name, len-1);
+}
+
+static mrb_bool
+sym_name_with_bang_p(const char *name, mrb_int len)
+{
+ return len >= 2 && name[len-1] == '!' && sym_name_word_p(name, len-1);
+}
+
+static mrb_bool
+sym_name_ivar_p(const char *name, mrb_int len)
+{
+ return len >= 2 && name[0] == '@' && sym_name_word_p(name+1, len-1);
+}
+
+static mrb_bool
+sym_name_cvar_p(const char *name, mrb_int len)
+{
+ return len >= 3 && name[0] == '@' && sym_name_ivar_p(name+1, len-1);
+}
+
+const char *
+sym_operator_p(const char *name, mrb_int len)
+{
+ mrb_sym start, idx;
+ mrb_sym table_size = sizeof(operator_table)/sizeof(struct operator_symbol);
+ int cmp;
+ const struct operator_symbol *op_sym;
+ for (start = 0; table_size != 0; table_size/=2) {
+ idx = start+table_size/2;
+ op_sym = &operator_table[idx];
+ cmp = len-op_sym->sym_name_len;
+ if (cmp == 0) {
+ cmp = memcmp(name, op_sym->sym_name, len);
+ if (cmp == 0) return op_sym->name;
+ }
+ if (0 < cmp) {
+ start = ++idx;
+ --table_size;
+ }
+ }
+ return NULL;
+}
static int
-dump_sym(mrb_state *mrb, mrb_sym sym, FILE *fp)
+dump_sym(mrb_state *mrb, mrb_sym sym, const char *var_name, int idx, mrb_value init_syms_code, FILE *fp, mrb_bool *presymp)
{
- const char *name;
if (sym == 0) return MRB_DUMP_INVALID_ARGUMENT;
- name = mrb_sym_name(mrb, sym);
- if (!name) {
- fprintf(stderr, "undefined symbol (%d) - define presym\n", sym);
+
+ mrb_int len;
+ const char *name = mrb_sym_name_len(mrb, sym, &len), *op_name;
+ if (!name) return MRB_DUMP_INVALID_ARGUMENT;
+ if (presymp) *presymp = TRUE;
+ if (sym_name_word_p(name, len)) {
+ fprintf(fp, "MRB_SYM(%s)", name);
+ }
+ else if (sym_name_with_equal_p(name, len)) {
+ fprintf(fp, "MRB_SYM_E(%.*s)", (int)(len-1), name);
+ }
+ else if (sym_name_with_question_mark_p(name, len)) {
+ fprintf(fp, "MRB_SYM_Q(%.*s)", (int)(len-1), name);
+ }
+ else if (sym_name_with_bang_p(name, len)) {
+ fprintf(fp, "MRB_SYM_B(%.*s)", (int)(len-1), name);
}
- if (!mrb_sym_static_p(mrb, sym)) {
- fprintf(stderr, "no static symbol (%s) - define presym\n", name);
+ else if (sym_name_ivar_p(name, len)) {
+ fprintf(fp, "MRB_IVSYM(%s)", name+1);
}
- fprintf(fp, "%d /* %s */,", sym, name);
+ else if (sym_name_cvar_p(name, len)) {
+ fprintf(fp, "MRB_CVSYM(%s)", name+2);
+ }
+ else if ((op_name = sym_operator_p(name, len))) {
+ fprintf(fp, "MRB_OPSYM(%s)", op_name);
+ }
+ else {
+ mrb_assert(var_name);
+ char buf[32];
+ mrb_str_cat_lit(mrb, init_syms_code, " ");
+ mrb_str_cat_cstr(mrb, init_syms_code, var_name);
+ snprintf(buf, sizeof(buf), "[%d] = ", idx);
+ mrb_str_cat_cstr(mrb, init_syms_code, buf);
+ mrb_str_cat_lit(mrb, init_syms_code, "mrb_intern_lit(mrb, \"");
+ mrb_str_cat_cstr(mrb, init_syms_code, mrb_sym_dump(mrb, sym));
+ mrb_str_cat_lit(mrb, init_syms_code, "\");\n");
+ *presymp = FALSE;
+ fputs("0", fp);
+ }
+ fputs(", ", fp);
return MRB_DUMP_OK;
}
+static const char*
+sym_var_name(mrb_state *mrb, const char *initname, const char *key, int n)
+{
+ char buf[32];
+ mrb_value s = mrb_str_new_cstr(mrb, initname);
+ mrb_str_cat_lit(mrb, s, "_");
+ mrb_str_cat_cstr(mrb, s, key);
+ mrb_str_cat_lit(mrb, s, "_");
+ snprintf(buf, sizeof(buf), "%d", n);
+ mrb_str_cat_cstr(mrb, s, buf);
+ return RSTRING_PTR(s);
+}
+
static int
-dump_irep_struct(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *fp, const char *name, int n, int *mp)
+dump_irep_struct(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *fp, const char *name, int n, mrb_value init_syms_code, int *mp)
{
int i, len;
int max = *mp;
@@ -988,7 +1134,7 @@ dump_irep_struct(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *fp,
if (irep->reps) {
for (i=0,len=irep->rlen; i<len; i++) {
*mp += len;
- if (dump_irep_struct(mrb, irep->reps[i], flags, fp, name, max+i, mp) != MRB_DUMP_OK)
+ if (dump_irep_struct(mrb, irep->reps[i], flags, fp, name, max+i, init_syms_code, mp) != MRB_DUMP_OK)
return MRB_DUMP_INVALID_ARGUMENT;
}
fprintf(fp, "static const mrb_irep *%s_reps_%d[%d] = {\n", name, n, len);
@@ -1009,12 +1155,19 @@ dump_irep_struct(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *fp,
}
/* dump syms */
if (irep->syms) {
+ int ai = mrb_gc_arena_save(mrb);
+ const char *var_name = sym_var_name(mrb, name, "syms", n);
+ mrb_bool all_presym = TRUE, presym;
len=irep->slen;
- fprintf(fp, "static const mrb_sym %s_syms_%d[%d] = {", name, n, len);
+ fprintf(fp, "mrb_DEFINE_SYMS_VAR(%s, %d, (", var_name, len);
for (i=0; i<len; i++) {
- dump_sym(mrb, irep->syms[i], fp);
+ dump_sym(mrb, irep->syms[i], var_name, i, init_syms_code, fp, &presym);
+ all_presym &= presym;
}
- fputs("};\n", fp);
+ fputs("), ", fp);
+ if (all_presym) fputs("const", fp);
+ fputs(");\n", fp);
+ mrb_gc_arena_restore(mrb, ai);
}
/* dump iseq */
len=irep->ilen+sizeof(struct mrb_irep_catch_handler)*irep->clen;
@@ -1029,7 +1182,7 @@ dump_irep_struct(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *fp,
len=irep->nlocals;
fprintf(fp, "static const mrb_sym %s_lv_%d[%d] = {", name, n, len-1);
for (i=0; i+1<len; i++) {
- fprintf(fp, "%uU, ", irep->lv[i]);
+ dump_sym(mrb, irep->lv[i], NULL, 0, mrb_nil_value(), fp, NULL);
}
fputs("};\n", fp);
}
@@ -1070,20 +1223,28 @@ dump_irep_struct(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *fp,
int
mrb_dump_irep_cstruct(mrb_state *mrb, const mrb_irep *irep, uint8_t flags, FILE *fp, const char *initname)
{
- int max = 1;
- int n;
-
if (fp == NULL || initname == NULL || initname[0] == '\0') {
return MRB_DUMP_INVALID_ARGUMENT;
}
if (fprintf(fp, "#include <mruby.h>\n" "#include <mruby/proc.h>\n\n") < 0) {
return MRB_DUMP_WRITE_FAULT;
}
- n = dump_irep_struct(mrb, irep, flags, fp, initname, 0, &max);
+ fputs("#define mrb_BRACED(...) {__VA_ARGS__}\n", fp);
+ fputs("#define mrb_DEFINE_SYMS_VAR(name, len, syms, qualifier) \\\n", fp);
+ fputs(" static qualifier mrb_sym name[len] = mrb_BRACED syms\n", fp);
+ fputs("\n", fp);
+ mrb_value init_syms_code = mrb_str_new_capa(mrb, 0);
+ int max = 1;
+ int n = dump_irep_struct(mrb, irep, flags, fp, initname, 0, init_syms_code, &max);
if (n != MRB_DUMP_OK) return n;
fprintf(fp, "#ifdef __cplusplus\nextern const struct RProc %s[];\n#endif\n", initname);
fprintf(fp, "const struct RProc %s[] = {{\n", initname);
fprintf(fp, "NULL,NULL,MRB_TT_PROC,7,0,{&%s_irep_0},NULL,{NULL},\n}};\n", initname);
+ fputs("static void\n", fp);
+ fprintf(fp, "%s_init_syms(mrb_state *mrb)\n", initname);
+ fputs("{\n", fp);
+ fputs(RSTRING_PTR(init_syms_code), fp);
+ fputs("}\n", fp);
return MRB_DUMP_OK;
}
diff --git a/src/symbol.c b/src/symbol.c
index c78f41f63..58decc1f1 100644
--- a/src/symbol.c
+++ b/src/symbol.c
@@ -12,15 +12,19 @@
#include <mruby/dump.h>
#include <mruby/class.h>
-#undef MRB_PRESYM_MAX
-#define MRB_PRESYM_NAMED(lit, num, type, name) {lit, sizeof(lit)-1},
-#define MRB_PRESYM_UNNAMED(lit, num) {lit, sizeof(lit)-1},
+#ifndef MRB_NO_PRESYM
+
+# undef MRB_PRESYM_MAX
+# define MRB_PRESYM_NAMED(lit, num, type, name) {lit, sizeof(lit)-1},
+# define MRB_PRESYM_UNNAMED(lit, num) {lit, sizeof(lit)-1},
static const struct {
const char *name;
uint16_t len;
} presym_table[] = {
-#include <../build/presym.inc>
+#ifndef MRB_PRESYM_SCANNING
+# include <mruby/presym.inc>
+#endif
};
static mrb_sym
@@ -51,6 +55,8 @@ presym_sym2name(mrb_sym sym, mrb_int *lenp)
return presym_table[sym-1].name;
}
+#endif /* MRB_NO_PRESYM */
+
/* ------------------------------------------------------ */
typedef struct symbol_name {
mrb_bool lit : 1;
@@ -147,9 +153,11 @@ find_symbol(mrb_state *mrb, const char *name, size_t len, uint8_t *hashp)
symbol_name *sname;
uint8_t hash;
+#ifndef MRB_NO_PRESYM
/* presym */
i = presym_find(name, len);
if (i > 0) return i<<SYMBOL_SHIFT;
+#endif
/* inline symbol */
i = sym_inline_pack(name, len);
@@ -306,10 +314,12 @@ sym2name_len(mrb_state *mrb, mrb_sym sym, char *buf, mrb_int *lenp)
if (SYMBOL_INLINE_P(sym)) return sym_inline_unpack(sym, buf, lenp);
sym >>= SYMBOL_SHIFT;
+#ifndef MRB_NO_PRESYM
{
const char *name = presym_sym2name(sym, lenp);
if (name) return name;
}
+#endif
sym -= MRB_PRESYM_MAX;
if (sym == 0 || mrb->symidx < sym) {