mirror of
https://github.com/ruby/ruby.git
synced 2025-08-15 05:29:10 +02:00
[ruby/prism] Optimize context_terminator with a lookup table
483aa89234This commit is contained in:
Kevin Newton
parent
3ef8d833ab
commit
18e37ac430
2 changed files with 96 additions and 112 deletions
|
|
@ -322,13 +322,42 @@ warnings:
|
|||
- UNUSED_LOCAL_VARIABLE
|
||||
- VOID_STATEMENT
|
||||
tokens:
|
||||
# The order of the tokens at the beginning is important, because we use them
|
||||
# for a lookup table.
|
||||
- name: EOF
|
||||
value: 1
|
||||
comment: final token in the file
|
||||
- name: MISSING
|
||||
comment: "a token that was expected but not found"
|
||||
- name: NOT_PROVIDED
|
||||
comment: "a token that was not present but it is okay"
|
||||
- name: BRACE_RIGHT
|
||||
comment: "}"
|
||||
- name: COMMA
|
||||
comment: ","
|
||||
- name: EMBEXPR_END
|
||||
comment: "}"
|
||||
- name: KEYWORD_DO
|
||||
comment: "do"
|
||||
- name: KEYWORD_ELSE
|
||||
comment: "else"
|
||||
- name: KEYWORD_ELSIF
|
||||
comment: "elsif"
|
||||
- name: KEYWORD_END
|
||||
comment: "end"
|
||||
- name: KEYWORD_ENSURE
|
||||
comment: "ensure"
|
||||
- name: KEYWORD_IN
|
||||
comment: "in"
|
||||
- name: KEYWORD_RESCUE
|
||||
comment: "rescue"
|
||||
- name: KEYWORD_THEN
|
||||
comment: "then"
|
||||
- name: KEYWORD_WHEN
|
||||
comment: "when"
|
||||
- name: NEWLINE
|
||||
comment: "a newline character outside of other tokens"
|
||||
- name: PARENTHESIS_RIGHT
|
||||
comment: ")"
|
||||
- name: SEMICOLON
|
||||
comment: ";"
|
||||
# Tokens from here on are not used for lookup, and can be in any order.
|
||||
- name: AMPERSAND
|
||||
comment: "&"
|
||||
- name: AMPERSAND_AMPERSAND
|
||||
|
|
@ -351,8 +380,6 @@ tokens:
|
|||
comment: "!~"
|
||||
- name: BRACE_LEFT
|
||||
comment: "{"
|
||||
- name: BRACE_RIGHT
|
||||
comment: "}"
|
||||
- name: BRACKET_LEFT
|
||||
comment: "["
|
||||
- name: BRACKET_LEFT_ARRAY
|
||||
|
|
@ -375,8 +402,6 @@ tokens:
|
|||
comment: ":"
|
||||
- name: COLON_COLON
|
||||
comment: "::"
|
||||
- name: COMMA
|
||||
comment: ","
|
||||
- name: COMMENT
|
||||
comment: "a comment"
|
||||
- name: CONSTANT
|
||||
|
|
@ -395,8 +420,6 @@ tokens:
|
|||
comment: "a line inside of embedded documentation"
|
||||
- name: EMBEXPR_BEGIN
|
||||
comment: "#{"
|
||||
- name: EMBEXPR_END
|
||||
comment: "}"
|
||||
- name: EMBVAR
|
||||
comment: "#"
|
||||
- name: EQUAL
|
||||
|
|
@ -463,20 +486,10 @@ tokens:
|
|||
comment: "def"
|
||||
- name: KEYWORD_DEFINED
|
||||
comment: "defined?"
|
||||
- name: KEYWORD_DO
|
||||
comment: "do"
|
||||
- name: KEYWORD_DO_LOOP
|
||||
comment: "do keyword for a predicate in a while, until, or for loop"
|
||||
- name: KEYWORD_ELSE
|
||||
comment: "else"
|
||||
- name: KEYWORD_ELSIF
|
||||
comment: "elsif"
|
||||
- name: KEYWORD_END
|
||||
comment: "end"
|
||||
- name: KEYWORD_END_UPCASE
|
||||
comment: "END"
|
||||
- name: KEYWORD_ENSURE
|
||||
comment: "ensure"
|
||||
- name: KEYWORD_FALSE
|
||||
comment: "false"
|
||||
- name: KEYWORD_FOR
|
||||
|
|
@ -485,8 +498,6 @@ tokens:
|
|||
comment: "if"
|
||||
- name: KEYWORD_IF_MODIFIER
|
||||
comment: "if in the modifier form"
|
||||
- name: KEYWORD_IN
|
||||
comment: "in"
|
||||
- name: KEYWORD_MODULE
|
||||
comment: "module"
|
||||
- name: KEYWORD_NEXT
|
||||
|
|
@ -499,8 +510,6 @@ tokens:
|
|||
comment: "or"
|
||||
- name: KEYWORD_REDO
|
||||
comment: "redo"
|
||||
- name: KEYWORD_RESCUE
|
||||
comment: "rescue"
|
||||
- name: KEYWORD_RESCUE_MODIFIER
|
||||
comment: "rescue in the modifier form"
|
||||
- name: KEYWORD_RETRY
|
||||
|
|
@ -511,8 +520,6 @@ tokens:
|
|||
comment: "self"
|
||||
- name: KEYWORD_SUPER
|
||||
comment: "super"
|
||||
- name: KEYWORD_THEN
|
||||
comment: "then"
|
||||
- name: KEYWORD_TRUE
|
||||
comment: "true"
|
||||
- name: KEYWORD_UNDEF
|
||||
|
|
@ -525,8 +532,6 @@ tokens:
|
|||
comment: "until"
|
||||
- name: KEYWORD_UNTIL_MODIFIER
|
||||
comment: "until in the modifier form"
|
||||
- name: KEYWORD_WHEN
|
||||
comment: "when"
|
||||
- name: KEYWORD_WHILE
|
||||
comment: "while"
|
||||
- name: KEYWORD_WHILE_MODIFIER
|
||||
|
|
@ -563,16 +568,12 @@ tokens:
|
|||
comment: "-="
|
||||
- name: MINUS_GREATER
|
||||
comment: "->"
|
||||
- name: NEWLINE
|
||||
comment: "a newline character outside of other tokens"
|
||||
- name: NUMBERED_REFERENCE
|
||||
comment: "a numbered reference to a capture group in the previous regular expression match"
|
||||
- name: PARENTHESIS_LEFT
|
||||
comment: "("
|
||||
- name: PARENTHESIS_LEFT_PARENTHESES
|
||||
comment: "( for a parentheses node"
|
||||
- name: PARENTHESIS_RIGHT
|
||||
comment: ")"
|
||||
- name: PERCENT
|
||||
comment: "%"
|
||||
- name: PERCENT_EQUAL
|
||||
|
|
@ -605,8 +606,6 @@ tokens:
|
|||
comment: "the beginning of a regular expression"
|
||||
- name: REGEXP_END
|
||||
comment: "the end of a regular expression"
|
||||
- name: SEMICOLON
|
||||
comment: ";"
|
||||
- name: SLASH
|
||||
comment: "/"
|
||||
- name: SLASH_EQUAL
|
||||
|
|
@ -651,6 +650,10 @@ tokens:
|
|||
comment: "a separator between words in a list"
|
||||
- name: __END__
|
||||
comment: "marker for the point in the file at which the parser should stop"
|
||||
- name: MISSING
|
||||
comment: "a token that was expected but not found"
|
||||
- name: NOT_PROVIDED
|
||||
comment: "a token that was not present but it is okay"
|
||||
flags:
|
||||
- name: ArgumentsNodeFlags
|
||||
values:
|
||||
|
|
|
|||
137
prism/prism.c
137
prism/prism.c
|
|
@ -8586,85 +8586,66 @@ parser_lex_magic_comment(pm_parser_t *parser, bool semantic_token_seen) {
|
|||
/* Context manipulations */
|
||||
/******************************************************************************/
|
||||
|
||||
static bool
|
||||
context_terminator(pm_context_t context, pm_token_t *token) {
|
||||
switch (context) {
|
||||
case PM_CONTEXT_MAIN:
|
||||
case PM_CONTEXT_DEF_PARAMS:
|
||||
case PM_CONTEXT_DEFINED:
|
||||
case PM_CONTEXT_MULTI_TARGET:
|
||||
case PM_CONTEXT_TERNARY:
|
||||
case PM_CONTEXT_RESCUE_MODIFIER:
|
||||
return token->type == PM_TOKEN_EOF;
|
||||
case PM_CONTEXT_DEFAULT_PARAMS:
|
||||
return token->type == PM_TOKEN_COMMA || token->type == PM_TOKEN_PARENTHESIS_RIGHT;
|
||||
case PM_CONTEXT_PREEXE:
|
||||
case PM_CONTEXT_POSTEXE:
|
||||
return token->type == PM_TOKEN_BRACE_RIGHT;
|
||||
case PM_CONTEXT_MODULE:
|
||||
case PM_CONTEXT_CLASS:
|
||||
case PM_CONTEXT_SCLASS:
|
||||
case PM_CONTEXT_LAMBDA_DO_END:
|
||||
case PM_CONTEXT_DEF:
|
||||
case PM_CONTEXT_BLOCK_KEYWORDS:
|
||||
return token->type == PM_TOKEN_KEYWORD_END || token->type == PM_TOKEN_KEYWORD_RESCUE || token->type == PM_TOKEN_KEYWORD_ENSURE;
|
||||
case PM_CONTEXT_WHILE:
|
||||
case PM_CONTEXT_UNTIL:
|
||||
case PM_CONTEXT_ELSE:
|
||||
case PM_CONTEXT_FOR:
|
||||
case PM_CONTEXT_BEGIN_ENSURE:
|
||||
case PM_CONTEXT_BLOCK_ENSURE:
|
||||
case PM_CONTEXT_CLASS_ENSURE:
|
||||
case PM_CONTEXT_DEF_ENSURE:
|
||||
case PM_CONTEXT_LAMBDA_ENSURE:
|
||||
case PM_CONTEXT_MODULE_ENSURE:
|
||||
case PM_CONTEXT_SCLASS_ENSURE:
|
||||
return token->type == PM_TOKEN_KEYWORD_END;
|
||||
case PM_CONTEXT_LOOP_PREDICATE:
|
||||
return token->type == PM_TOKEN_KEYWORD_DO || token->type == PM_TOKEN_KEYWORD_THEN;
|
||||
case PM_CONTEXT_FOR_INDEX:
|
||||
return token->type == PM_TOKEN_KEYWORD_IN;
|
||||
case PM_CONTEXT_CASE_WHEN:
|
||||
return token->type == PM_TOKEN_KEYWORD_WHEN || token->type == PM_TOKEN_KEYWORD_END || token->type == PM_TOKEN_KEYWORD_ELSE;
|
||||
case PM_CONTEXT_CASE_IN:
|
||||
return token->type == PM_TOKEN_KEYWORD_IN || token->type == PM_TOKEN_KEYWORD_END || token->type == PM_TOKEN_KEYWORD_ELSE;
|
||||
case PM_CONTEXT_IF:
|
||||
case PM_CONTEXT_ELSIF:
|
||||
return token->type == PM_TOKEN_KEYWORD_ELSE || token->type == PM_TOKEN_KEYWORD_ELSIF || token->type == PM_TOKEN_KEYWORD_END;
|
||||
case PM_CONTEXT_UNLESS:
|
||||
return token->type == PM_TOKEN_KEYWORD_ELSE || token->type == PM_TOKEN_KEYWORD_END;
|
||||
case PM_CONTEXT_EMBEXPR:
|
||||
return token->type == PM_TOKEN_EMBEXPR_END;
|
||||
case PM_CONTEXT_BLOCK_BRACES:
|
||||
return token->type == PM_TOKEN_BRACE_RIGHT;
|
||||
case PM_CONTEXT_PARENS:
|
||||
return token->type == PM_TOKEN_PARENTHESIS_RIGHT;
|
||||
case PM_CONTEXT_BEGIN:
|
||||
case PM_CONTEXT_BEGIN_RESCUE:
|
||||
case PM_CONTEXT_BLOCK_RESCUE:
|
||||
case PM_CONTEXT_CLASS_RESCUE:
|
||||
case PM_CONTEXT_DEF_RESCUE:
|
||||
case PM_CONTEXT_LAMBDA_RESCUE:
|
||||
case PM_CONTEXT_MODULE_RESCUE:
|
||||
case PM_CONTEXT_SCLASS_RESCUE:
|
||||
return token->type == PM_TOKEN_KEYWORD_ENSURE || token->type == PM_TOKEN_KEYWORD_RESCUE || token->type == PM_TOKEN_KEYWORD_ELSE || token->type == PM_TOKEN_KEYWORD_END;
|
||||
case PM_CONTEXT_BEGIN_ELSE:
|
||||
case PM_CONTEXT_BLOCK_ELSE:
|
||||
case PM_CONTEXT_CLASS_ELSE:
|
||||
case PM_CONTEXT_DEF_ELSE:
|
||||
case PM_CONTEXT_LAMBDA_ELSE:
|
||||
case PM_CONTEXT_MODULE_ELSE:
|
||||
case PM_CONTEXT_SCLASS_ELSE:
|
||||
return token->type == PM_TOKEN_KEYWORD_ENSURE || token->type == PM_TOKEN_KEYWORD_END;
|
||||
case PM_CONTEXT_LAMBDA_BRACES:
|
||||
return token->type == PM_TOKEN_BRACE_RIGHT;
|
||||
case PM_CONTEXT_PREDICATE:
|
||||
return token->type == PM_TOKEN_KEYWORD_THEN || token->type == PM_TOKEN_NEWLINE || token->type == PM_TOKEN_SEMICOLON;
|
||||
case PM_CONTEXT_NONE:
|
||||
return false;
|
||||
}
|
||||
static const uint32_t context_terminators[] = {
|
||||
[PM_CONTEXT_NONE] = 0,
|
||||
[PM_CONTEXT_BEGIN] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_BEGIN_ENSURE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_BEGIN_ELSE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_BEGIN_RESCUE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_BLOCK_BRACES] = (1 << PM_TOKEN_BRACE_RIGHT),
|
||||
[PM_CONTEXT_BLOCK_KEYWORDS] = (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ENSURE),
|
||||
[PM_CONTEXT_BLOCK_ENSURE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_BLOCK_ELSE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_BLOCK_RESCUE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_CASE_WHEN] = (1 << PM_TOKEN_KEYWORD_WHEN) | (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_ELSE),
|
||||
[PM_CONTEXT_CASE_IN] = (1 << PM_TOKEN_KEYWORD_IN) | (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_ELSE),
|
||||
[PM_CONTEXT_CLASS] = (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ENSURE),
|
||||
[PM_CONTEXT_CLASS_ENSURE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_CLASS_ELSE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_CLASS_RESCUE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_DEF] = (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ENSURE),
|
||||
[PM_CONTEXT_DEF_ENSURE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_DEF_ELSE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_DEF_RESCUE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_DEF_PARAMS] = (1 << PM_TOKEN_EOF),
|
||||
[PM_CONTEXT_DEFINED] = (1 << PM_TOKEN_EOF),
|
||||
[PM_CONTEXT_DEFAULT_PARAMS] = (1 << PM_TOKEN_COMMA) | (1 << PM_TOKEN_PARENTHESIS_RIGHT),
|
||||
[PM_CONTEXT_ELSE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_ELSIF] = (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_ELSIF) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_EMBEXPR] = (1 << PM_TOKEN_EMBEXPR_END),
|
||||
[PM_CONTEXT_FOR] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_FOR_INDEX] = (1 << PM_TOKEN_KEYWORD_IN),
|
||||
[PM_CONTEXT_IF] = (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_ELSIF) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_LAMBDA_BRACES] = (1 << PM_TOKEN_BRACE_RIGHT),
|
||||
[PM_CONTEXT_LAMBDA_DO_END] = (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ENSURE),
|
||||
[PM_CONTEXT_LAMBDA_ENSURE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_LAMBDA_ELSE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_LAMBDA_RESCUE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_LOOP_PREDICATE] = (1 << PM_TOKEN_KEYWORD_DO) | (1 << PM_TOKEN_KEYWORD_THEN),
|
||||
[PM_CONTEXT_MAIN] = (1 << PM_TOKEN_EOF),
|
||||
[PM_CONTEXT_MODULE] = (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ENSURE),
|
||||
[PM_CONTEXT_MODULE_ENSURE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_MODULE_ELSE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_MODULE_RESCUE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_MULTI_TARGET] = (1 << PM_TOKEN_EOF),
|
||||
[PM_CONTEXT_PARENS] = (1 << PM_TOKEN_PARENTHESIS_RIGHT),
|
||||
[PM_CONTEXT_POSTEXE] = (1 << PM_TOKEN_BRACE_RIGHT),
|
||||
[PM_CONTEXT_PREDICATE] = (1 << PM_TOKEN_KEYWORD_THEN) | (1 << PM_TOKEN_NEWLINE) | (1 << PM_TOKEN_SEMICOLON),
|
||||
[PM_CONTEXT_PREEXE] = (1 << PM_TOKEN_BRACE_RIGHT),
|
||||
[PM_CONTEXT_RESCUE_MODIFIER] = (1 << PM_TOKEN_EOF),
|
||||
[PM_CONTEXT_SCLASS] = (1 << PM_TOKEN_KEYWORD_END) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ENSURE),
|
||||
[PM_CONTEXT_SCLASS_ENSURE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_SCLASS_ELSE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_SCLASS_RESCUE] = (1 << PM_TOKEN_KEYWORD_ENSURE) | (1 << PM_TOKEN_KEYWORD_RESCUE) | (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_TERNARY] = (1 << PM_TOKEN_EOF),
|
||||
[PM_CONTEXT_UNLESS] = (1 << PM_TOKEN_KEYWORD_ELSE) | (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_UNTIL] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
[PM_CONTEXT_WHILE] = (1 << PM_TOKEN_KEYWORD_END),
|
||||
};
|
||||
|
||||
return false;
|
||||
static inline bool
|
||||
context_terminator(pm_context_t context, pm_token_t *token) {
|
||||
return token->type < 32 && (context_terminators[context] & (1 << token->type));
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue