summaryrefslogtreecommitdiff
path: root/regcomp.c
diff options
context:
space:
mode:
authorkosako <kosako@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2006-08-27 12:58:22 +0000
committerkosako <kosako@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2006-08-27 12:58:22 +0000
commit0046f355c1109dfc2883f1a3c64c61222aab0ce9 (patch)
treed34f69aed5086221b4a8b29e65f9306aa99721df /regcomp.c
parent0384b2330ca1b8461c86b9cd2ddae234f75c8417 (diff)
merge Oniguruma 4.4.0
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@10782 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'regcomp.c')
-rw-r--r--regcomp.c587
1 files changed, 519 insertions, 68 deletions
diff --git a/regcomp.c b/regcomp.c
index 530237c..844f4f7 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -186,6 +186,17 @@ add_opcode(regex_t* reg, int opcode)
return 0;
}
+#ifdef USE_COMBINATION_EXPLOSION_CHECK
+static int
+add_state_check_num(regex_t* reg, int num)
+{
+ StateCheckNumType n = (StateCheckNumType )num;
+
+ BBUF_ADD(reg, &n, SIZE_STATE_CHECK_NUM);
+ return 0;
+}
+#endif
+
static int
add_rel_addr(regex_t* reg, int addr)
{
@@ -644,7 +655,7 @@ entry_repeat_range(regex_t* reg, int id, int lower, int upper)
}
p[id].lower = lower;
- p[id].upper = upper;
+ p[id].upper = (IS_REPEAT_INFINITE(upper) ? 0x7fffffff : upper);
return 0;
}
@@ -684,7 +695,254 @@ compile_range_repeat_node(QualifierNode* qn, int target_len, int empty_info,
return r;
}
+static int
+is_anychar_star_qualifier(QualifierNode* qn)
+{
+ if (qn->greedy && IS_REPEAT_INFINITE(qn->upper) &&
+ NTYPE(qn->target) == N_ANYCHAR)
+ return 1;
+ else
+ return 0;
+}
+
#define QUALIFIER_EXPAND_LIMIT_SIZE 50
+#define CKN_ON (ckn > 0)
+
+#ifdef USE_COMBINATION_EXPLOSION_CHECK
+
+static int
+compile_length_qualifier_node(QualifierNode* qn, regex_t* reg)
+{
+ int len, mod_tlen, cklen;
+ int ckn;
+ int infinite = IS_REPEAT_INFINITE(qn->upper);
+ int empty_info = qn->target_empty_info;
+ int tlen = compile_length_tree(qn->target, reg);
+
+ if (tlen < 0) return tlen;
+
+ ckn = ((reg->num_comb_exp_check > 0) ? qn->comb_exp_check_num : 0);
+
+ cklen = (CKN_ON ? SIZE_STATE_CHECK_NUM: 0);
+
+ /* anychar repeat */
+ if (NTYPE(qn->target) == N_ANYCHAR) {
+ if (qn->greedy && infinite) {
+ if (IS_NOT_NULL(qn->next_head_exact) && !CKN_ON)
+ return SIZE_OP_ANYCHAR_STAR_PEEK_NEXT + tlen * qn->lower + cklen;
+ else
+ return SIZE_OP_ANYCHAR_STAR + tlen * qn->lower + cklen;
+ }
+ }
+
+ if (empty_info != 0)
+ mod_tlen = tlen + (SIZE_OP_NULL_CHECK_START + SIZE_OP_NULL_CHECK_END);
+ else
+ mod_tlen = tlen;
+
+ if (infinite && qn->lower <= 1) {
+ if (qn->greedy) {
+ if (qn->lower == 1)
+ len = SIZE_OP_JUMP;
+ else
+ len = 0;
+
+ len += SIZE_OP_PUSH + cklen + mod_tlen + SIZE_OP_JUMP;
+ }
+ else {
+ if (qn->lower == 0)
+ len = SIZE_OP_JUMP;
+ else
+ len = 0;
+
+ len += mod_tlen + SIZE_OP_PUSH + cklen;
+ }
+ }
+ else if (qn->upper == 0) {
+ if (qn->is_refered != 0) /* /(?<n>..){0}/ */
+ len = SIZE_OP_JUMP + tlen;
+ else
+ len = 0;
+ }
+ else if (qn->upper == 1 && qn->greedy) {
+ if (qn->lower == 0) {
+ if (CKN_ON) {
+ len = SIZE_OP_STATE_CHECK_PUSH + tlen;
+ }
+ else {
+ len = SIZE_OP_PUSH + tlen;
+ }
+ }
+ else {
+ len = tlen;
+ }
+ }
+ else if (!qn->greedy && qn->upper == 1 && qn->lower == 0) { /* '??' */
+ len = SIZE_OP_PUSH + cklen + SIZE_OP_JUMP + tlen;
+ }
+ else {
+ len = SIZE_OP_REPEAT_INC
+ + mod_tlen + SIZE_OPCODE + SIZE_RELADDR + SIZE_MEMNUM;
+ if (CKN_ON)
+ len += SIZE_OP_STATE_CHECK;
+ }
+
+ return len;
+}
+
+static int
+compile_qualifier_node(QualifierNode* qn, regex_t* reg)
+{
+ int r, mod_tlen;
+ int ckn;
+ int infinite = IS_REPEAT_INFINITE(qn->upper);
+ int empty_info = qn->target_empty_info;
+ int tlen = compile_length_tree(qn->target, reg);
+
+ if (tlen < 0) return tlen;
+
+ ckn = ((reg->num_comb_exp_check > 0) ? qn->comb_exp_check_num : 0);
+
+ if (is_anychar_star_qualifier(qn)) {
+ r = compile_tree_n_times(qn->target, qn->lower, reg);
+ if (r) return r;
+ if (IS_NOT_NULL(qn->next_head_exact) && !CKN_ON) {
+ if (IS_MULTILINE(reg->options))
+ r = add_opcode(reg, OP_ANYCHAR_ML_STAR_PEEK_NEXT);
+ else
+ r = add_opcode(reg, OP_ANYCHAR_STAR_PEEK_NEXT);
+ if (r) return r;
+ if (CKN_ON) {
+ r = add_state_check_num(reg, ckn);
+ if (r) return r;
+ }
+
+ return add_bytes(reg, NSTRING(qn->next_head_exact).s, 1);
+ }
+ else {
+ if (IS_MULTILINE(reg->options)) {
+ r = add_opcode(reg, (CKN_ON ?
+ OP_STATE_CHECK_ANYCHAR_ML_STAR
+ : OP_ANYCHAR_ML_STAR));
+ }
+ else {
+ r = add_opcode(reg, (CKN_ON ?
+ OP_STATE_CHECK_ANYCHAR_STAR
+ : OP_ANYCHAR_STAR));
+ }
+ if (r) return r;
+ if (CKN_ON)
+ r = add_state_check_num(reg, ckn);
+
+ return r;
+ }
+ }
+
+ if (empty_info != 0)
+ mod_tlen = tlen + (SIZE_OP_NULL_CHECK_START + SIZE_OP_NULL_CHECK_END);
+ else
+ mod_tlen = tlen;
+
+ if (infinite && qn->lower <= 1) {
+ if (qn->greedy) {
+ if (qn->lower == 1) {
+ r = add_opcode_rel_addr(reg, OP_JUMP,
+ (CKN_ON ? SIZE_OP_STATE_CHECK_PUSH : SIZE_OP_PUSH));
+ if (r) return r;
+ }
+
+ if (CKN_ON) {
+ r = add_opcode(reg, OP_STATE_CHECK_PUSH);
+ if (r) return r;
+ r = add_state_check_num(reg, ckn);
+ if (r) return r;
+ r = add_rel_addr(reg, mod_tlen + SIZE_OP_JUMP);
+ }
+ else {
+ r = add_opcode_rel_addr(reg, OP_PUSH, mod_tlen + SIZE_OP_JUMP);
+ }
+ if (r) return r;
+ r = compile_tree_empty_check(qn->target, reg, empty_info);
+ if (r) return r;
+ r = add_opcode_rel_addr(reg, OP_JUMP,
+ -(mod_tlen + (int )SIZE_OP_JUMP
+ + (int )(CKN_ON ? SIZE_OP_STATE_CHECK_PUSH : SIZE_OP_PUSH)));
+ }
+ else {
+ if (qn->lower == 0) {
+ r = add_opcode_rel_addr(reg, OP_JUMP, mod_tlen);
+ if (r) return r;
+ }
+ r = compile_tree_empty_check(qn->target, reg, empty_info);
+ if (r) return r;
+ if (CKN_ON) {
+ r = add_opcode(reg, OP_STATE_CHECK_PUSH_OR_JUMP);
+ if (r) return r;
+ r = add_state_check_num(reg, ckn);
+ if (r) return r;
+ r = add_rel_addr(reg,
+ -(mod_tlen + (int )SIZE_OP_STATE_CHECK_PUSH_OR_JUMP));
+ }
+ else
+ r = add_opcode_rel_addr(reg, OP_PUSH, -(mod_tlen + (int )SIZE_OP_PUSH));
+ }
+ }
+ else if (qn->upper == 0) {
+ if (qn->is_refered != 0) { /* /(?<n>..){0}/ */
+ r = add_opcode_rel_addr(reg, OP_JUMP, tlen);
+ if (r) return r;
+ r = compile_tree(qn->target, reg);
+ }
+ else
+ r = 0;
+ }
+ else if (qn->upper == 1 && qn->greedy) {
+ if (qn->lower == 0) {
+ if (CKN_ON) {
+ r = add_opcode(reg, OP_STATE_CHECK_PUSH);
+ if (r) return r;
+ r = add_state_check_num(reg, ckn);
+ if (r) return r;
+ r = add_rel_addr(reg, tlen);
+ }
+ else {
+ r = add_opcode_rel_addr(reg, OP_PUSH, tlen);
+ }
+ if (r) return r;
+ }
+
+ r = compile_tree(qn->target, reg);
+ }
+ else if (!qn->greedy && qn->upper == 1 && qn->lower == 0) { /* '??' */
+ if (CKN_ON) {
+ r = add_opcode(reg, OP_STATE_CHECK_PUSH);
+ if (r) return r;
+ r = add_state_check_num(reg, ckn);
+ if (r) return r;
+ r = add_rel_addr(reg, SIZE_OP_JUMP);
+ }
+ else {
+ r = add_opcode_rel_addr(reg, OP_PUSH, SIZE_OP_JUMP);
+ }
+
+ if (r) return r;
+ r = add_opcode_rel_addr(reg, OP_JUMP, tlen);
+ if (r) return r;
+ r = compile_tree(qn->target, reg);
+ }
+ else {
+ r = compile_range_repeat_node(qn, mod_tlen, empty_info, reg);
+ if (CKN_ON) {
+ if (r) return r;
+ r = add_opcode(reg, OP_STATE_CHECK);
+ if (r) return r;
+ r = add_state_check_num(reg, ckn);
+ }
+ }
+ return r;
+}
+
+#else /* USE_COMBINATION_EXPLOSION_CHECK */
static int
compile_length_qualifier_node(QualifierNode* qn, regex_t* reg)
@@ -752,16 +1010,6 @@ compile_length_qualifier_node(QualifierNode* qn, regex_t* reg)
}
static int
-is_anychar_star_qualifier(QualifierNode* qn)
-{
- if (qn->greedy && IS_REPEAT_INFINITE(qn->upper) &&
- NTYPE(qn->target) == N_ANYCHAR)
- return 1;
- else
- return 0;
-}
-
-static int
compile_qualifier_node(QualifierNode* qn, regex_t* reg)
{
int i, r, mod_tlen;
@@ -887,6 +1135,7 @@ compile_qualifier_node(QualifierNode* qn, regex_t* reg)
}
return r;
}
+#endif /* USE_COMBINATION_EXPLOSION_CHECK */
static int
compile_length_option_node(EffectNode* node, regex_t* reg)
@@ -1276,7 +1525,7 @@ compile_length_tree(Node* node, regex_t* reg)
else
#endif
if (br->back_num == 1) {
- r = ((!IS_IGNORECASE(reg->options) && br->back_static[0] <= 3)
+ r = ((!IS_IGNORECASE(reg->options) && br->back_static[0] <= 2)
? SIZE_OPCODE : (SIZE_OPCODE + SIZE_MEMNUM));
}
else {
@@ -1414,7 +1663,6 @@ compile_tree(Node* node, regex_t* reg)
switch (n) {
case 1: r = add_opcode(reg, OP_BACKREF1); break;
case 2: r = add_opcode(reg, OP_BACKREF2); break;
- case 3: r = add_opcode(reg, OP_BACKREF3); break;
default:
r = add_opcode(reg, OP_BACKREFN);
if (r) return r;
@@ -1435,7 +1683,9 @@ compile_tree(Node* node, regex_t* reg)
}
if (r) return r;
+#ifdef USE_BACKREF_AT_LEVEL
add_bacref_mems:
+#endif
r = add_length(reg, br->back_num);
if (r) return r;
p = BACKREFS_P(br);
@@ -3040,6 +3290,146 @@ divide_ambig_string_node(Node* node, regex_t* reg)
return 0;
}
+#ifdef USE_COMBINATION_EXPLOSION_CHECK
+
+#define CEC_THRES_NUM_BIG_REPEAT 512
+#define CEC_INFINITE_NUM 0x7fffffff
+
+#define CEC_IN_INFINITE_REPEAT (1<<0)
+#define CEC_IN_FINITE_REPEAT (1<<1)
+#define CEC_CONT_BIG_REPEAT (1<<2)
+
+static int
+setup_comb_exp_check(Node* node, int state, ScanEnv* env)
+{
+ int type;
+ int r = state;
+
+ type = NTYPE(node);
+ switch (type) {
+ case N_LIST:
+ {
+ Node* prev = NULL_NODE;
+ do {
+ r = setup_comb_exp_check(NCONS(node).left, r, env);
+ prev = NCONS(node).left;
+ } while (r >= 0 && IS_NOT_NULL(node = NCONS(node).right));
+ }
+ break;
+
+ case N_ALT:
+ {
+ int ret;
+ do {
+ ret = setup_comb_exp_check(NCONS(node).left, state, env);
+ r |= ret;
+ } while (ret >= 0 && IS_NOT_NULL(node = NCONS(node).right));
+ }
+ break;
+
+ case N_QUALIFIER:
+ {
+ int child_state = state;
+ int add_state = 0;
+ QualifierNode* qn = &(NQUALIFIER(node));
+ Node* target = qn->target;
+ int var_num;
+
+ if (! IS_REPEAT_INFINITE(qn->upper)) {
+ if (qn->upper > 1) {
+ /* {0,1}, {1,1} are allowed */
+ child_state |= CEC_IN_FINITE_REPEAT;
+
+ /* check (a*){n,m}, (a+){n,m} => (a*){n,n}, (a+){n,n} */
+ if (env->backrefed_mem == 0) {
+ if (NTYPE(qn->target) == N_EFFECT) {
+ EffectNode* en = &(NEFFECT(qn->target));
+ if (en->type == EFFECT_MEMORY) {
+ if (NTYPE(en->target) == N_QUALIFIER) {
+ QualifierNode* q = &(NQUALIFIER(en->target));
+ if (IS_REPEAT_INFINITE(q->upper)
+ && q->greedy == qn->greedy) {
+ qn->upper = (qn->lower == 0 ? 1 : qn->lower);
+ if (qn->upper == 1)
+ child_state = state;
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+
+ if (state & CEC_IN_FINITE_REPEAT) {
+ qn->comb_exp_check_num = -1;
+ }
+ else {
+ if (IS_REPEAT_INFINITE(qn->upper)) {
+ var_num = CEC_INFINITE_NUM;
+ child_state |= CEC_IN_INFINITE_REPEAT;
+ }
+ else {
+ var_num = qn->upper - qn->lower;
+ }
+
+ if (var_num >= CEC_THRES_NUM_BIG_REPEAT)
+ add_state |= CEC_CONT_BIG_REPEAT;
+
+ if (((state & CEC_IN_INFINITE_REPEAT) != 0 && var_num != 0) ||
+ ((state & CEC_CONT_BIG_REPEAT) != 0 &&
+ var_num >= CEC_THRES_NUM_BIG_REPEAT)) {
+ if (qn->comb_exp_check_num == 0) {
+ env->num_comb_exp_check++;
+ qn->comb_exp_check_num = env->num_comb_exp_check;
+ if (env->curr_max_regnum > env->comb_exp_max_regnum)
+ env->comb_exp_max_regnum = env->curr_max_regnum;
+ }
+ }
+ }
+
+ r = setup_comb_exp_check(target, child_state, env);
+ r |= add_state;
+ }
+ break;
+
+ case N_EFFECT:
+ {
+ EffectNode* en = &(NEFFECT(node));
+
+ switch (en->type) {
+ case EFFECT_MEMORY:
+ {
+ if (env->curr_max_regnum < en->regnum)
+ env->curr_max_regnum = en->regnum;
+
+ r = setup_comb_exp_check(en->target, state, env);
+ }
+ break;
+
+ default:
+ r = setup_comb_exp_check(en->target, state, env);
+ break;
+ }
+ }
+ break;
+
+#ifdef USE_SUBEXP_CALL
+ case N_CALL:
+ if (IS_CALL_RECURSION(&(NCALL(node))))
+ env->has_recursion = 1;
+ else
+ r = setup_comb_exp_check(NCALL(node).target, state, env);
+ break;
+#endif
+
+ default:
+ break;
+ }
+
+ return r;
+}
+#endif
+
#define IN_ALT (1<<0)
#define IN_NOT (1<<1)
#define IN_REPEAT (1<<2)
@@ -4746,6 +5136,9 @@ onig_compile(regex_t* reg, const UChar* pattern, const UChar* pattern_end,
reg->num_null_check = 0;
reg->repeat_range_alloc = 0;
reg->repeat_range = (OnigRepeatRange* )NULL;
+#ifdef USE_COMBINATION_EXPLOSION_CHECK
+ reg->num_comb_exp_check = 0;
+#endif
r = onig_parse_make_tree(&root, pattern, pattern_end, reg, &scan_env);
if (r != 0) goto err;
@@ -4799,6 +5192,33 @@ onig_compile(regex_t* reg, const UChar* pattern, const UChar* pattern_end,
reg->bt_mem_end |= reg->capture_history;
}
+#ifdef USE_COMBINATION_EXPLOSION_CHECK
+ if (scan_env.backrefed_mem == 0
+#ifdef USE_SUBEXP_CALL
+ || scan_env.num_call == 0
+#endif
+ ) {
+ setup_comb_exp_check(root, 0, &scan_env);
+#ifdef USE_SUBEXP_CALL
+ if (scan_env.has_recursion != 0) {
+ scan_env.num_comb_exp_check = 0;
+ }
+ else
+#endif
+ if (scan_env.comb_exp_max_regnum > 0) {
+ int i;
+ for (i = 1; i <= scan_env.comb_exp_max_regnum; i++) {
+ if (BIT_STATUS_AT(scan_env.backrefed_mem, i) != 0) {
+ scan_env.num_comb_exp_check = 0;
+ break;
+ }
+ }
+ }
+ }
+
+ reg->num_comb_exp_check = scan_env.num_comb_exp_check;
+#endif
+
clear_optimize_info(reg);
#ifndef ONIG_DONT_OPTIMIZE
r = set_optimize_info_from_tree(root, reg, &scan_env);
@@ -5008,6 +5428,16 @@ onig_end()
#ifdef ONIG_DEBUG
+/* arguments type */
+#define ARG_SPECIAL -1
+#define ARG_NON 0
+#define ARG_RELADDR 1
+#define ARG_ABSADDR 2
+#define ARG_LENGTH 3
+#define ARG_MEMNUM 4
+#define ARG_OPTION 5
+#define ARG_STATE_CHECK 6
+
OnigOpInfoType OnigOpInfo[] = {
{ OP_FINISH, "finish", ARG_NON },
{ OP_END, "end", ARG_NON },
@@ -5038,63 +5468,68 @@ OnigOpInfoType OnigOpInfo[] = {
{ OP_ANYCHAR_ML_STAR, "anychar-ml*", ARG_NON },
{ OP_ANYCHAR_STAR_PEEK_NEXT, "anychar*-peek-next", ARG_SPECIAL },
{ OP_ANYCHAR_ML_STAR_PEEK_NEXT, "anychar-ml*-peek-next", ARG_SPECIAL },
- { OP_WORD, "word", ARG_NON },
- { OP_NOT_WORD, "not-word", ARG_NON },
- { OP_WORD_SB, "word-sb", ARG_NON },
- { OP_WORD_MB, "word-mb", ARG_NON },
- { OP_WORD_BOUND, "word-bound", ARG_NON },
- { OP_NOT_WORD_BOUND, "not-word-bound", ARG_NON },
- { OP_WORD_BEGIN, "word-begin", ARG_NON },
- { OP_WORD_END, "word-end", ARG_NON },
- { OP_BEGIN_BUF, "begin-buf", ARG_NON },
- { OP_END_BUF, "end-buf", ARG_NON },
- { OP_BEGIN_LINE, "begin-line", ARG_NON },
- { OP_END_LINE, "end-line", ARG_NON },
- { OP_SEMI_END_BUF, "semi-end-buf", ARG_NON },
- { OP_BEGIN_POSITION, "begin-position", ARG_NON },
- { OP_BACKREF1, "backref1", ARG_NON },
- { OP_BACKREF2, "backref2", ARG_NON },
- { OP_BACKREF3, "backref3", ARG_NON },
- { OP_BACKREFN, "backrefn", ARG_MEMNUM },
- { OP_BACKREFN_IC, "backrefn-ic", ARG_SPECIAL },
- { OP_BACKREF_MULTI, "backref_multi", ARG_SPECIAL },
- { OP_BACKREF_MULTI_IC, "backref_multi-ic", ARG_SPECIAL },
- { OP_BACKREF_AT_LEVEL, "backref_at_level", ARG_SPECIAL },
- { OP_MEMORY_START_PUSH, "mem-start-push", ARG_MEMNUM },
- { OP_MEMORY_START, "mem-start", ARG_MEMNUM },
- { OP_MEMORY_END_PUSH, "mem-end-push", ARG_MEMNUM },
- { OP_MEMORY_END_PUSH_REC, "mem-end-push-rec", ARG_MEMNUM },
- { OP_MEMORY_END, "mem-end", ARG_MEMNUM },
- { OP_MEMORY_END_REC, "mem-end-rec", ARG_MEMNUM },
- { OP_SET_OPTION_PUSH, "set-option-push", ARG_OPTION },
- { OP_SET_OPTION, "set-option", ARG_OPTION },
- { OP_FAIL, "fail", ARG_NON },
- { OP_JUMP, "jump", ARG_RELADDR },
- { OP_PUSH, "push", ARG_RELADDR },
- { OP_POP, "pop", ARG_NON },
- { OP_PUSH_OR_JUMP_EXACT1, "push-or-jump-e1", ARG_SPECIAL },
- { OP_PUSH_IF_PEEK_NEXT, "push-if-peek-next", ARG_SPECIAL },
- { OP_REPEAT, "repeat", ARG_SPECIAL },
- { OP_REPEAT_NG, "repeat-ng", ARG_SPECIAL },
- { OP_REPEAT_INC, "repeat-inc", ARG_MEMNUM },
- { OP_REPEAT_INC_NG, "repeat-inc-ng", ARG_MEMNUM },
- { OP_REPEAT_INC_SG, "repeat-inc-sg", ARG_MEMNUM },
- { OP_REPEAT_INC_NG_SG, "repeat-inc-ng-sg", ARG_MEMNUM },
- { OP_NULL_CHECK_START, "null-check-start", ARG_MEMNUM },
- { OP_NULL_CHECK_END, "null-check-end", ARG_MEMNUM },
- { OP_NULL_CHECK_END_MEMST,"null-check-end-memst", ARG_MEMNUM },
- { OP_NULL_CHECK_END_MEMST_PUSH,"null-check-end-memst-push", ARG_MEMNUM },
- { OP_PUSH_POS, "push-pos", ARG_NON },
- { OP_POP_POS, "pop-pos", ARG_NON },
- { OP_PUSH_POS_NOT, "push-pos-not", ARG_RELADDR },
- { OP_FAIL_POS, "fail-pos", ARG_NON },
- { OP_PUSH_STOP_BT, "push-stop-bt", ARG_NON },
- { OP_POP_STOP_BT, "pop-stop-bt", ARG_NON },
- { OP_LOOK_BEHIND, "look-behind", ARG_SPECIAL },
+ { OP_WORD, "word", ARG_NON },
+ { OP_NOT_WORD, "not-word", ARG_NON },
+ { OP_WORD_SB, "word-sb", ARG_NON },
+ { OP_WORD_MB, "word-mb", ARG_NON },
+ { OP_WORD_BOUND, "word-bound", ARG_NON },
+ { OP_NOT_WORD_BOUND, "not-word-bound", ARG_NON },
+ { OP_WORD_BEGIN, "word-begin", ARG_NON },
+ { OP_WORD_END, "word-end", ARG_NON },
+ { OP_BEGIN_BUF, "begin-buf", ARG_NON },
+ { OP_END_BUF, "end-buf", ARG_NON },
+ { OP_BEGIN_LINE, "begin-line", ARG_NON },
+ { OP_END_LINE, "end-line", ARG_NON },
+ { OP_SEMI_END_BUF, "semi-end-buf", ARG_NON },
+ { OP_BEGIN_POSITION, "begin-position", ARG_NON },
+ { OP_BACKREF1, "backref1", ARG_NON },
+ { OP_BACKREF2, "backref2", ARG_NON },
+ { OP_BACKREFN, "backrefn", ARG_MEMNUM },
+ { OP_BACKREFN_IC, "backrefn-ic", ARG_SPECIAL },
+ { OP_BACKREF_MULTI, "backref_multi", ARG_SPECIAL },
+ { OP_BACKREF_MULTI_IC, "backref_multi-ic", ARG_SPECIAL },
+ { OP_BACKREF_AT_LEVEL, "backref_at_level", ARG_SPECIAL },
+ { OP_MEMORY_START_PUSH, "mem-start-push", ARG_MEMNUM },
+ { OP_MEMORY_START, "mem-start", ARG_MEMNUM },
+ { OP_MEMORY_END_PUSH, "mem-end-push", ARG_MEMNUM },
+ { OP_MEMORY_END_PUSH_REC, "mem-end-push-rec", ARG_MEMNUM },
+ { OP_MEMORY_END, "mem-end", ARG_MEMNUM },
+ { OP_MEMORY_END_REC, "mem-end-rec", ARG_MEMNUM },
+ { OP_SET_OPTION_PUSH, "set-option-push", ARG_OPTION },
+ { OP_SET_OPTION, "set-option", ARG_OPTION },
+ { OP_FAIL, "fail", ARG_NON },
+ { OP_JUMP, "jump", ARG_RELADDR },
+ { OP_PUSH, "push", ARG_RELADDR },
+ { OP_POP, "pop", ARG_NON },
+ { OP_PUSH_OR_JUMP_EXACT1, "push-or-jump-e1", ARG_SPECIAL },
+ { OP_PUSH_IF_PEEK_NEXT, "push-if-peek-next", ARG_SPECIAL },
+ { OP_REPEAT, "repeat", ARG_SPECIAL },
+ { OP_REPEAT_NG, "repeat-ng", ARG_SPECIAL },
+ { OP_REPEAT_INC, "repeat-inc", ARG_MEMNUM },
+ { OP_REPEAT_INC_NG, "repeat-inc-ng", ARG_MEMNUM },
+ { OP_REPEAT_INC_SG, "repeat-inc-sg", ARG_MEMNUM },
+ { OP_REPEAT_INC_NG_SG, "repeat-inc-ng-sg", ARG_MEMNUM },
+ { OP_NULL_CHECK_START, "null-check-start", ARG_MEMNUM },
+ { OP_NULL_CHECK_END, "null-check-end", ARG_MEMNUM },
+ { OP_NULL_CHECK_END_MEMST,"null-check-end-memst", ARG_MEMNUM },
+ { OP_NULL_CHECK_END_MEMST_PUSH,"null-check-end-memst-push", ARG_MEMNUM },
+ { OP_PUSH_POS, "push-pos", ARG_NON },
+ { OP_POP_POS, "pop-pos", ARG_NON },
+ { OP_PUSH_POS_NOT, "push-pos-not", ARG_RELADDR },
+ { OP_FAIL_POS, "fail-pos", ARG_NON },
+ { OP_PUSH_STOP_BT, "push-stop-bt", ARG_NON },
+ { OP_POP_STOP_BT, "pop-stop-bt", ARG_NON },
+ { OP_LOOK_BEHIND, "look-behind", ARG_SPECIAL },
{ OP_PUSH_LOOK_BEHIND_NOT, "push-look-behind-not", ARG_SPECIAL },
{ OP_FAIL_LOOK_BEHIND_NOT, "fail-look-behind-not", ARG_NON },
- { OP_CALL, "call", ARG_ABSADDR },
- { OP_RETURN, "return", ARG_NON },
+ { OP_CALL, "call", ARG_ABSADDR },
+ { OP_RETURN, "return", ARG_NON },
+ { OP_STATE_CHECK_PUSH, "state-check-push", ARG_SPECIAL },
+ { OP_STATE_CHECK_PUSH_OR_JUMP, "state-check-push-or-jump", ARG_SPECIAL },
+ { OP_STATE_CHECK, "state-check", ARG_STATE_CHECK },
+ { OP_STATE_CHECK_ANYCHAR_STAR, "state-check-anychar*", ARG_STATE_CHECK },
+ { OP_STATE_CHECK_ANYCHAR_ML_STAR,
+ "state-check-anychar-ml*", ARG_STATE_CHECK },
{ -1, "", ARG_NON }
};
@@ -5153,6 +5588,7 @@ onig_print_compiled_byte_code(FILE* f, UChar* bp, UChar** nextp,
RelAddrType addr;
LengthType len;
MemNumType mem;
+ StateCheckNumType scn;
OnigCodePoint code;
UChar *q;
@@ -5187,6 +5623,12 @@ onig_print_compiled_byte_code(FILE* f, UChar* bp, UChar** nextp,
fprintf(f, ":%d", option);
}
break;
+
+ case ARG_STATE_CHECK:
+ scn = *((StateCheckNumType* )bp);
+ bp += SIZE_STATE_CHECK_NUM;
+ fprintf(f, ":%d", scn);
+ break;
}
}
else {
@@ -5364,6 +5806,15 @@ onig_print_compiled_byte_code(FILE* f, UChar* bp, UChar** nextp,
fprintf(f, ":%d:(%d)", len, addr);
break;
+ case OP_STATE_CHECK_PUSH:
+ case OP_STATE_CHECK_PUSH_OR_JUMP:
+ scn = *((StateCheckNumType* )bp);
+ bp += SIZE_STATE_CHECK_NUM;
+ addr = *((RelAddrType* )bp);
+ bp += SIZE_RELADDR;
+ fprintf(f, ":%d:(%d)", scn, addr);
+ break;
+
default:
fprintf(stderr, "onig_print_compiled_byte_code: undefined code %d\n",
*--bp);