summaryrefslogtreecommitdiff
path: root/ext/ripper
diff options
context:
space:
mode:
authorNobuyoshi Nakada <nobu@ruby-lang.org>2019-10-21 11:45:54 +0900
committerNobuyoshi Nakada <nobu@ruby-lang.org>2019-10-21 11:45:54 +0900
commit44da5a1c872879b05acab045263d0d4f906f04ba (patch)
treed0265a3a6c2728e4fd17959d23bed88fca61fb86 /ext/ripper
parent375124be51c796a53cce9716e83003ef37c7bcf5 (diff)
Look up event ID offsets by token as index
Diffstat (limited to 'ext/ripper')
-rw-r--r--ext/ripper/eventids2.c332
1 files changed, 164 insertions, 168 deletions
diff --git a/ext/ripper/eventids2.c b/ext/ripper/eventids2.c
index fd59f1b39ff..3a5f955f476 100644
--- a/ext/ripper/eventids2.c
+++ b/ext/ripper/eventids2.c
@@ -128,180 +128,176 @@ ripper_init_eventids2(void)
STATIC_ASSERT(k__END___range, k__END__ < SHRT_MAX);
STATIC_ASSERT(ripper_scanner_ids_size, sizeof(ripper_scanner_ids) < SHRT_MAX);
-#define O(member) (int)offsetof(ripper_scanner_ids_t, ripper_id_##member)
-
-static const struct token_assoc {
- unsigned short token;
- unsigned short id_offset;
-} token_to_eventid[] = {
- {' ', O(words_sep)},
- {'!', O(op)},
- {'%', O(op)},
- {'&', O(op)},
- {'*', O(op)},
- {'+', O(op)},
- {'-', O(op)},
- {'/', O(op)},
- {'<', O(op)},
- {'=', O(op)},
- {'>', O(op)},
- {'?', O(op)},
- {'^', O(op)},
- {'|', O(op)},
- {'~', O(op)},
- {':', O(op)},
- {',', O(comma)},
- {'.', O(period)},
- {';', O(semicolon)},
- {'`', O(backtick)},
- {'\n', O(nl)},
- {keyword_alias, O(kw)},
- {keyword_and, O(kw)},
- {keyword_begin, O(kw)},
- {keyword_break, O(kw)},
- {keyword_case, O(kw)},
- {keyword_class, O(kw)},
- {keyword_def, O(kw)},
- {keyword_defined, O(kw)},
- {keyword_do, O(kw)},
- {keyword_do_block, O(kw)},
- {keyword_do_cond, O(kw)},
- {keyword_else, O(kw)},
- {keyword_elsif, O(kw)},
- {keyword_end, O(kw)},
- {keyword_ensure, O(kw)},
- {keyword_false, O(kw)},
- {keyword_for, O(kw)},
- {keyword_if, O(kw)},
- {modifier_if, O(kw)},
- {keyword_in, O(kw)},
- {keyword_module, O(kw)},
- {keyword_next, O(kw)},
- {keyword_nil, O(kw)},
- {keyword_not, O(kw)},
- {keyword_or, O(kw)},
- {keyword_redo, O(kw)},
- {keyword_rescue, O(kw)},
- {modifier_rescue, O(kw)},
- {keyword_retry, O(kw)},
- {keyword_return, O(kw)},
- {keyword_self, O(kw)},
- {keyword_super, O(kw)},
- {keyword_then, O(kw)},
- {keyword_true, O(kw)},
- {keyword_undef, O(kw)},
- {keyword_unless, O(kw)},
- {modifier_unless, O(kw)},
- {keyword_until, O(kw)},
- {modifier_until, O(kw)},
- {keyword_when, O(kw)},
- {keyword_while, O(kw)},
- {modifier_while, O(kw)},
- {keyword_yield, O(kw)},
- {keyword__FILE__, O(kw)},
- {keyword__LINE__, O(kw)},
- {keyword__ENCODING__, O(kw)},
- {keyword_BEGIN, O(kw)},
- {keyword_END, O(kw)},
- {keyword_do_LAMBDA, O(kw)},
- {tAMPER, O(op)},
- {tANDOP, O(op)},
- {tAREF, O(op)},
- {tASET, O(op)},
- {tASSOC, O(op)},
- {tBACK_REF, O(backref)},
- {tCHAR, O(CHAR)},
- {tCMP, O(op)},
- {tCOLON2, O(op)},
- {tCOLON3, O(op)},
- {tCONSTANT, O(const)},
- {tCVAR, O(cvar)},
- {tDOT2, O(op)},
- {tDOT3, O(op)},
- {tBDOT2, O(op)},
- {tBDOT3, O(op)},
- {tEQ, O(op)},
- {tEQQ, O(op)},
- {tFID, O(ident)},
- {tFLOAT, O(float)},
- {tGEQ, O(op)},
- {tGVAR, O(gvar)},
- {tIDENTIFIER, O(ident)},
- {tIMAGINARY, O(imaginary)},
- {tINTEGER, O(int)},
- {tIVAR, O(ivar)},
- {tLBRACE, O(lbrace)},
- {tLBRACE_ARG, O(lbrace)},
- {'{', O(lbrace)},
- {'}', O(rbrace)},
- {tLBRACK, O(lbracket)},
- {'[', O(lbracket)},
- {']', O(rbracket)},
- {tLEQ, O(op)},
- {tLPAREN, O(lparen)},
- {tLPAREN_ARG, O(lparen)},
- {'(', O(lparen)},
- {')', O(rparen)},
- {tLSHFT, O(op)},
- {tMATCH, O(op)},
- {tNEQ, O(op)},
- {tNMATCH, O(op)},
- {tNTH_REF, O(backref)},
- {tOP_ASGN, O(op)},
- {tOROP, O(op)},
- {tPOW, O(op)},
- {tQWORDS_BEG, O(qwords_beg)},
- {tQSYMBOLS_BEG, O(qsymbols_beg)},
- {tSYMBOLS_BEG, O(symbols_beg)},
- {tRATIONAL, O(rational)},
- {tREGEXP_BEG, O(regexp_beg)},
- {tREGEXP_END, O(regexp_end)},
- {tRPAREN, O(rparen)},
- {tRSHFT, O(op)},
- {tSTAR, O(op)},
- {tDSTAR, O(op)},
- {tANDDOT, O(op)},
- {tMETHREF, O(op)},
- {tSTRING_BEG, O(tstring_beg)},
- {tSTRING_CONTENT, O(tstring_content)},
- {tSTRING_DBEG, O(embexpr_beg)},
- {tSTRING_DEND, O(embexpr_end)},
- {tSTRING_DVAR, O(embvar)},
- {tSTRING_END, O(tstring_end)},
- {tSYMBEG, O(symbeg)},
- {tUMINUS, O(op)},
- {tUMINUS_NUM, O(op)},
- {tUPLUS, O(op)},
- {tWORDS_BEG, O(words_beg)},
- {tXSTRING_BEG, O(backtick)},
- {tLABEL, O(label)},
- {tLABEL_END, O(label_end)},
- {tLAMBDA, O(tlambda)},
- {tLAMBEG, O(tlambeg)},
-
- /* ripper specific tokens */
- {tIGNORED_NL, O(ignored_nl)},
- {tCOMMENT, O(comment)},
- {tEMBDOC_BEG, O(embdoc_beg)},
- {tEMBDOC, O(embdoc)},
- {tEMBDOC_END, O(embdoc_end)},
- {tSP, O(sp)},
- {tHEREDOC_BEG, O(heredoc_beg)},
- {tHEREDOC_END, O(heredoc_end)},
- {k__END__, O(__end__)},
-};
static ID
ripper_token2eventid(enum yytokentype tok)
{
- int i;
+#define O(member) (int)offsetof(ripper_scanner_ids_t, ripper_id_##member)+1
+ static const unsigned short offsets[] = {
+ [' '] = O(words_sep),
+ ['!'] = O(op),
+ ['%'] = O(op),
+ ['&'] = O(op),
+ ['*'] = O(op),
+ ['+'] = O(op),
+ ['-'] = O(op),
+ ['/'] = O(op),
+ ['<'] = O(op),
+ ['='] = O(op),
+ ['>'] = O(op),
+ ['?'] = O(op),
+ ['^'] = O(op),
+ ['|'] = O(op),
+ ['~'] = O(op),
+ [':'] = O(op),
+ [','] = O(comma),
+ ['.'] = O(period),
+ [';'] = O(semicolon),
+ ['`'] = O(backtick),
+ ['\n'] = O(nl),
+ [keyword_alias] = O(kw),
+ [keyword_and] = O(kw),
+ [keyword_begin] = O(kw),
+ [keyword_break] = O(kw),
+ [keyword_case] = O(kw),
+ [keyword_class] = O(kw),
+ [keyword_def] = O(kw),
+ [keyword_defined] = O(kw),
+ [keyword_do] = O(kw),
+ [keyword_do_block] = O(kw),
+ [keyword_do_cond] = O(kw),
+ [keyword_else] = O(kw),
+ [keyword_elsif] = O(kw),
+ [keyword_end] = O(kw),
+ [keyword_ensure] = O(kw),
+ [keyword_false] = O(kw),
+ [keyword_for] = O(kw),
+ [keyword_if] = O(kw),
+ [modifier_if] = O(kw),
+ [keyword_in] = O(kw),
+ [keyword_module] = O(kw),
+ [keyword_next] = O(kw),
+ [keyword_nil] = O(kw),
+ [keyword_not] = O(kw),
+ [keyword_or] = O(kw),
+ [keyword_redo] = O(kw),
+ [keyword_rescue] = O(kw),
+ [modifier_rescue] = O(kw),
+ [keyword_retry] = O(kw),
+ [keyword_return] = O(kw),
+ [keyword_self] = O(kw),
+ [keyword_super] = O(kw),
+ [keyword_then] = O(kw),
+ [keyword_true] = O(kw),
+ [keyword_undef] = O(kw),
+ [keyword_unless] = O(kw),
+ [modifier_unless] = O(kw),
+ [keyword_until] = O(kw),
+ [modifier_until] = O(kw),
+ [keyword_when] = O(kw),
+ [keyword_while] = O(kw),
+ [modifier_while] = O(kw),
+ [keyword_yield] = O(kw),
+ [keyword__FILE__] = O(kw),
+ [keyword__LINE__] = O(kw),
+ [keyword__ENCODING__] = O(kw),
+ [keyword_BEGIN] = O(kw),
+ [keyword_END] = O(kw),
+ [keyword_do_LAMBDA] = O(kw),
+ [tAMPER] = O(op),
+ [tANDOP] = O(op),
+ [tAREF] = O(op),
+ [tASET] = O(op),
+ [tASSOC] = O(op),
+ [tBACK_REF] = O(backref),
+ [tCHAR] = O(CHAR),
+ [tCMP] = O(op),
+ [tCOLON2] = O(op),
+ [tCOLON3] = O(op),
+ [tCONSTANT] = O(const),
+ [tCVAR] = O(cvar),
+ [tDOT2] = O(op),
+ [tDOT3] = O(op),
+ [tBDOT2] = O(op),
+ [tBDOT3] = O(op),
+ [tEQ] = O(op),
+ [tEQQ] = O(op),
+ [tFID] = O(ident),
+ [tFLOAT] = O(float),
+ [tGEQ] = O(op),
+ [tGVAR] = O(gvar),
+ [tIDENTIFIER] = O(ident),
+ [tIMAGINARY] = O(imaginary),
+ [tINTEGER] = O(int),
+ [tIVAR] = O(ivar),
+ [tLBRACE] = O(lbrace),
+ [tLBRACE_ARG] = O(lbrace),
+ ['{'] = O(lbrace),
+ ['}'] = O(rbrace),
+ [tLBRACK] = O(lbracket),
+ ['['] = O(lbracket),
+ [']'] = O(rbracket),
+ [tLEQ] = O(op),
+ [tLPAREN] = O(lparen),
+ [tLPAREN_ARG] = O(lparen),
+ ['('] = O(lparen),
+ [')'] = O(rparen),
+ [tLSHFT] = O(op),
+ [tMATCH] = O(op),
+ [tNEQ] = O(op),
+ [tNMATCH] = O(op),
+ [tNTH_REF] = O(backref),
+ [tOP_ASGN] = O(op),
+ [tOROP] = O(op),
+ [tPOW] = O(op),
+ [tQWORDS_BEG] = O(qwords_beg),
+ [tQSYMBOLS_BEG] = O(qsymbols_beg),
+ [tSYMBOLS_BEG] = O(symbols_beg),
+ [tRATIONAL] = O(rational),
+ [tREGEXP_BEG] = O(regexp_beg),
+ [tREGEXP_END] = O(regexp_end),
+ [tRPAREN] = O(rparen),
+ [tRSHFT] = O(op),
+ [tSTAR] = O(op),
+ [tDSTAR] = O(op),
+ [tANDDOT] = O(op),
+ [tMETHREF] = O(op),
+ [tSTRING_BEG] = O(tstring_beg),
+ [tSTRING_CONTENT] = O(tstring_content),
+ [tSTRING_DBEG] = O(embexpr_beg),
+ [tSTRING_DEND] = O(embexpr_end),
+ [tSTRING_DVAR] = O(embvar),
+ [tSTRING_END] = O(tstring_end),
+ [tSYMBEG] = O(symbeg),
+ [tUMINUS] = O(op),
+ [tUMINUS_NUM] = O(op),
+ [tUPLUS] = O(op),
+ [tWORDS_BEG] = O(words_beg),
+ [tXSTRING_BEG] = O(backtick),
+ [tLABEL] = O(label),
+ [tLABEL_END] = O(label_end),
+ [tLAMBDA] = O(tlambda),
+ [tLAMBEG] = O(tlambeg),
+
+ /* ripper specific tokens */
+ [tIGNORED_NL] = O(ignored_nl),
+ [tCOMMENT] = O(comment),
+ [tEMBDOC_BEG] = O(embdoc_beg),
+ [tEMBDOC] = O(embdoc),
+ [tEMBDOC_END] = O(embdoc_end),
+ [tSP] = O(sp),
+ [tHEREDOC_BEG] = O(heredoc_beg),
+ [tHEREDOC_END] = O(heredoc_end),
+ [k__END__] = O(__end__),
+ };
+#undef O
- for (i = 0; i < numberof(token_to_eventid); i++) {
- const struct token_assoc *const a = &token_to_eventid[i];
- if ((enum yytokentype)a->token == tok)
- return *(const ID *)((const char *)&ripper_scanner_ids + a->id_offset);
+ int i = (int)tok;
+ if (i >= 0 && i < numberof(offsets) && (i = offsets[i]) > 0) {
+ return *(const ID *)((const char *)&ripper_scanner_ids-1+i);
}
- if (tok < 256) {
+ /* 128..256 are used as operator tokens */
+ if (tok < 128) {
return ripper_scanner_ids.ripper_id_CHAR;
}
rb_raise(rb_eRuntimeError, "[Ripper FATAL] unknown token %d", tok);