-
-
Save watzon/dede910f771fd8fe3801c1d898eb40cf to your computer and use it in GitHub Desktop.
CLTK Lexer for Crystal
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require "./ctype" | |
require "cltk/streamposition" | |
require "cltk/token" | |
require "cltk/scanner" | |
module Pool | |
class Lexer < CLTK::Scanner | |
# extend CLTK::Scanner::LexerCompatibility | |
# Skip whitespace | |
rule("\n") { { :CR } } | |
rule(" ") | |
# Keywords | |
rule("abstract") { { :ABSTRACT } } | |
rule("alias") { { :ALIAS } } | |
rule("asm") { { :ASM } } | |
rule("class") { { :CLASS } } | |
rule("def") { { :DEF } } | |
rule("end") { { :END } } | |
rule("include") { { :INCLUDE } } | |
rule("extend") { { :EXTEND } } | |
rule("module") { { :MODULE } } | |
rule("nil") { { :NIL } } | |
rule("private") { { :PRIVATE } } | |
rule("protected") { { :PROTECTED } } | |
rule("require") { { :REQUIRE } } | |
rule("return") { { :RETURN } } | |
rule("self") { { :SELF } } | |
rule("struct") { { :STRUCT } } | |
rule("super") { { :SUPER } } | |
rule("type") { { :TYPE } } | |
rule("typeof") { { :TYPEOF } } | |
rule("uninitialized") { { :UNINITIALIZED } } | |
rule("annotation") { { :ANNOTATION } } | |
rule("union") { { :UNION } } | |
# Blocks | |
rule("do") { { :DO } } | |
rule("yield") { { :WITH } } | |
rule("with") { { :WITH } } | |
rule("->") { { :"->" } } | |
# Exception handling | |
rule("begin") { { :BEGIN } } | |
rule("raise") { { :RAISE } } | |
rule("rescue") { { :RESCUE } } | |
# Control flow | |
rule("if") { { :IF } } | |
rule("else") { { :ELSE } } | |
rule("unless") { { :UNLESS } } | |
rule("elsif") { { :ELSIF } } | |
rule("then") { { :ELSIF } } | |
rule("case") { { :CASE } } | |
rule("next") { { :NEXT } } | |
rule("break") { { :BREAK } } | |
rule("for") { { :FOR } } | |
# Loops | |
rule("while") { { :WHILE } } | |
rule("loop") { { :LOOP } } | |
rule("until") { { :UNTIL } } | |
# Arithmetic Operators | |
rule("+") { { :"+" } } | |
rule("-") { { :"-" } } | |
rule("\*") { { :"*" } } | |
rule("/") { { :"/" } } | |
rule("%") { { :"%" } } | |
rule("\*\*") { { :"**" } } | |
# Comparison Operators | |
rule("==") { { :"==" } } | |
rule("!=") { { :"!=" } } | |
rule("<") { { :"<" } } | |
rule(">") { { :">" } } | |
rule(">=") { { :">=" } } | |
rule("<=") { { :"<=" } } | |
rule("<=>") { { :"<=>" } } | |
rule("===") { { :"===" } } | |
# Assignment Operators | |
rule("=") { { :"=" } } | |
rule("+=") { { :"+=" } } | |
rule("-=") { { :"-=" } } | |
rule("\*=") { { :"*=" } } | |
rule("/=") { { :"/=" } } | |
rule("%=") { { :"%=" } } | |
rule("%=") { { :"%=" } } | |
rule("\*\*=") { { :"**=" } } | |
# Bitwise Operators | |
rule("&") { { :"&" } } | |
rule("|") { { :"|" } } | |
rule("^") { { :"^" } } | |
rule("~") { { :"~" } } | |
rule("<<") { { :"<<" } } | |
rule(">>") { { :">>" } } | |
# Logical Operators | |
rule("&&") { { :"&&" } } | |
rule("&&=") { { :"&&=" } } | |
rule("&+=") { { :"&+=" } } | |
rule("&-=") { { :"&-=" } } | |
rule("&**") { { :"&**" } } | |
rule("&*=") { { :"&*=" } } | |
rule("||") { { :"||" } } | |
rule("!") { { :"!" } } | |
# Range Operators | |
rule("..") { { :".." } } | |
rule("...") { { :"..." } } | |
# Uncategorized Operators | |
rule("::") { { :"::" } } | |
rule(".") { { :"." } } | |
# Separators | |
rule("(") { { :"(" } } | |
rule(")") { { :")" } } | |
rule("[") { { :"[" } } | |
rule("]") { { :"]" } } | |
rule("@[") { { :"@[" } } | |
rule("{") { { :"{" } } | |
rule("}") { { :"}" } } | |
rule(":") { { :":" } } | |
rule("?") { { :"?" } } | |
rule(";") { { :";" } } | |
rule(",") { { :"," } } | |
# Identifiers | |
rule(/".*"/) { |t| { :STRING, t[1..-2] } } | |
rule(/'[^\']{1,1}'/) { |t| { :CHAR, t[1] } } | |
rule(/[A-Z][_A-Za-z0-9]*/) { |t| { :CONST, t } } | |
rule(/:[\S]*/) { |t| { :SYMBOL, t } } | |
rule(/@[a-z0-9_]*/) { |t| { :INSTANCE_VAR, t } } | |
rule(/@@[a-z0-9_]*/) { |t| { :CLASS_VAR, t } } | |
rule(/[a-z][_A-Za-z0-9]*/) { |t| { :IDENT, t } } | |
# Macros | |
rule(/%[iqQrxw]\(.*\)/) { |t| { :MACRO, t } } | |
rule(/%[iqQrxw]\[.*\]/) { |t| { :MACRO, t } } | |
rule(/%[iqQrxw]\{.*\}/) { |t| { :MACRO, t } } | |
rule(/%[iqQrxw]\<.*\>/) { |t| { :MACRO, t } } | |
rule(/%[iqQrxw]\|.*\|/) { |t| { :MACRO, t } } | |
# Numbers | |
rule(/\d+/) { |t| { :NUMBER, t.to_f } } | |
rule(/\.\d+/) { |t| { :NUMBER, t.to_f } } | |
rule(/\d+\.\d+/) { |t| { :NUMBER, t.to_f } } | |
# Comments | |
rule(/#\s*/) { push_state(:comment) } | |
rule(/[^\n]+/, :comment) { |t| { :COMMENT, t } } | |
rule("\n", :comment) { pop_state } | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment