omicron
242fd9baa5
When two identifiers follow eachother it could be two instruction mnemonics or one instruction mnemonic and one operand. To fix this TOKEN_NEWLINE has been reintroduced as a semantic token. The grammar has been changed to allow empty statements and every instruction and directive has to end in a newline. Labels do not have to end in a newline. In addition to updating the grammar, the implementation of tokenlist, ast and parser has been updated to reflect these changes.
40 lines
1.1 KiB
Plaintext
40 lines
1.1 KiB
Plaintext
<program> ::= <statement>*
|
|
<statement> ::= <label> | <directive> | <instruction> | <newline>
|
|
|
|
<label> ::= <identifier> <colon>
|
|
|
|
<directive> ::= <dot> <section_directive> <newline>
|
|
|
|
<section_directive> ::= "section" <identifier>
|
|
|
|
<instruction> ::= <identifier> <operands> <newline>
|
|
|
|
<operands> ::= <operand> ( <comma> <operand> )*
|
|
|
|
<operand> ::= <register> | <immediate> | <memory>
|
|
|
|
<immediate> ::= <number> | <label_reference>
|
|
|
|
<number> ::= <octal> | <binary> | <decimal> | <hexadecimal>
|
|
|
|
<label_reference> ::= <identifier>
|
|
|
|
<memory> ::= <lbracket> <memory_expression> <rbracket>
|
|
|
|
<memory_expression> ::= <label_reference> | <register_expression>
|
|
|
|
<register_expression> ::= <register> <register_index>? <register_offset>?
|
|
|
|
<register_index> ::= <plus> <register> <asterisk> <number>
|
|
|
|
<register_offset> ::= <plus_or_minus> <number>
|
|
|
|
<plus_or_minus> ::= <plus> | <minus>
|
|
|
|
|
|
/* These are lexer identifiers with the correct string value */
|
|
<section> ::= "section"
|
|
|
|
<register> ::= "rax" | "rbx" | "rcx" | "rdx" | "rsi" | "rdi" | "rbp" | "rsp" |
|
|
"r8" | "r9" | "r10" | "r11" | "r12" | "r13" | "r14" | "r15"
|