ecal/parser/const.go

/*
 * ECAL
 *
 * Copyright 2020 Matthias Ladkau. All rights reserved.
 *
 * This Source Code Form is subject to the terms of the MIT
 * License, If a copy of the MIT License was not distributed with this
 * file, You can obtain one at https://opensource.org/licenses/MIT.
 */

/*
Package parser contains a ECAL parser.

Lexer for Source Text

Lex() is a lexer function to convert a given search query into a list of tokens.

Based on a talk by Rob Pike: Lexical Scanning in Go

https://www.youtube.com/watch?v=HxaD_trXwRE

The lexer's output is pushed into a channel which is consumed by the parser.
This design enables the concurrent processing of the input text by lexer and
parser.

Parser

Parse() is a parser which produces a parse tree from a given set of lexer tokens.

Based on an article by Douglas Crockford: Top Down Operator Precedence

http://crockford.com/javascript/tdop/tdop.html

which is based on the ideas of Vaughan Pratt and his paper: Top Down Operator Precedence

http://portal.acm.org/citation.cfm?id=512931
https://tdop.github.io/

ParseWithRuntime() parses a given input and decorates the resulting parse tree
with runtime components which can be used to interpret the parsed query.
*/
package parser

/*
LexTokenID represents a unique lexer token ID
*/
type LexTokenID int

/*
Available meta data types
*/
const (
	MetaDataPreComment  = "MetaDataPreComment"
	MetaDataPostComment = "MetaDataPostComment"
	MetaDataGeneral     = "MetaDataGeneral"
)

/*
Available lexer token types
*/
const (
	TokenError LexTokenID = iota // Lexing error token with a message as val
	TokenEOF                     // End-of-file token
	TokenANY                     // Unspecified token (used when building an AST from a Go map structure)

	TokenPRECOMMENT  // Comment /* ... */
	TokenPOSTCOMMENT // Comment # ...

	// Value tokens

	TokenSTRING     // String constant
	TokenNUMBER     // Number constant
	TokenIDENTIFIER // Idendifier

	// Constructed tokens which are generated by the parser not the lexer

	TokenSTATEMENTS // A code block
	TokenFUNCCALL   // A function call
	TokenCOMPACCESS // Access to a composition structure
	TokenLIST       // List value
	TokenMAP        // MAP value
	TokenPARAMS     // Function parameters
	TokenGUARD      // Conditional statements

	TOKENodeSYMBOLS // Used to separate symbols from other tokens in this list

	// Condition operators

	TokenGEQ
	TokenLEQ
	TokenNEQ
	TokenEQ
	TokenGT
	TokenLT

	// Grouping symbols

	TokenLPAREN
	TokenRPAREN
	TokenLBRACK
	TokenRBRACK
	TokenLBRACE
	TokenRBRACE

	// Separators

	TokenDOT
	TokenCOMMA
	TokenSEMICOLON

	// Grouping

	TokenCOLON
	TokenEQUAL

	// Arithmetic operators

	TokenPLUS
	TokenMINUS
	TokenTIMES
	TokenDIV
	TokenDIVINT
	TokenMODINT

	// Assignment statement

	TokenASSIGN
	TokenLET

	TOKENodeKEYWORDS // Used to separate keywords from other tokens in this list

	// Import statement

	TokenIMPORT
	TokenAS

	// Sink definition

	TokenSINK
	TokenKINDMATCH
	TokenSCOPEMATCH
	TokenSTATEMATCH
	TokenPRIORITY
	TokenSUPPRESSES

	// Function definition

	TokenFUNC
	TokenRETURN

	// Boolean operators

	TokenAND
	TokenOR
	TokenNOT

	// Condition operators

	TokenLIKE
	TokenIN
	TokenHASPREFIX
	TokenHASSUFFIX
	TokenNOTIN

	// Constant terminals

	TokenFALSE
	TokenTRUE
	TokenNULL

	// Conditional statements

	TokenIF
	TokenELIF
	TokenELSE

	// Loop statements

	TokenFOR
	TokenBREAK
	TokenCONTINUE

	// Try block

	TokenTRY
	TokenEXCEPT
	TokenFINALLY

	// Mutex block

	TokenMUTEX

	TokenENDLIST
)

/*
IsValidTokenID check if a given token ID is valid.
*/
func IsValidTokenID(value int) bool {
	return value < int(TokenENDLIST)
}

/*
Available parser AST node types
*/
const (
	NodeEOF = "EOF"

	NodeSTRING     = "string"     // String constant
	NodeNUMBER     = "number"     // Number constant
	NodeIDENTIFIER = "identifier" // Idendifier

	// Constructed tokens

	NodeSTATEMENTS = "statements" // List of statements
	NodeFUNCCALL   = "funccall"   // Function call
	NodeCOMPACCESS = "compaccess" // Composition structure access
	NodeLIST       = "list"       // List value
	NodeMAP        = "map"        // Map value
	NodePARAMS     = "params"     // Function parameters
	NodeGUARD      = "guard"      // Guard expressions for conditional statements

	// Condition operators

	NodeGEQ = ">="
	NodeLEQ = "<="
	NodeNEQ = "!="
	NodeEQ  = "=="
	NodeGT  = ">"
	NodeLT  = "<"

	// Separators

	NodeKVP    = "kvp"    // Key-value pair
	NodePRESET = "preset" // Preset value

	// Arithmetic operators

	NodePLUS   = "plus"
	NodeMINUS  = "minus"
	NodeTIMES  = "times"
	NodeDIV    = "div"
	NodeMODINT = "modint"
	NodeDIVINT = "divint"

	// Assignment statement

	NodeASSIGN = ":="
	NodeLET    = "let"

	// Import statement

	NodeIMPORT = "import"

	// Sink definition

	NodeSINK       = "sink"
	NodeKINDMATCH  = "kindmatch"
	NodeSCOPEMATCH = "scopematch"
	NodeSTATEMATCH = "statematch"
	NodePRIORITY   = "priority"
	NodeSUPPRESSES = "suppresses"

	// Function definition

	NodeFUNC   = "function"
	NodeRETURN = "return"

	// Boolean operators

	NodeAND = "and"
	NodeOR  = "or"
	NodeNOT = "not"

	// Condition operators

	NodeLIKE      = "like"
	NodeIN        = "in"
	NodeHASPREFIX = "hasprefix"
	NodeHASSUFFIX = "hassuffix"
	NodeNOTIN     = "notin"

	// Constant terminals

	NodeTRUE  = "true"
	NodeFALSE = "false"
	NodeNULL  = "null"

	// Conditional statements

	NodeIF = "if"

	// Loop statements

	NodeLOOP     = "loop"
	NodeBREAK    = "break"
	NodeCONTINUE = "continue"

	// Try block

	NodeTRY     = "try"
	NodeEXCEPT  = "except"
	NodeAS      = "as"
	NodeFINALLY = "finally"

	// Mutex block

	NodeMUTEX = "mutex"
)