From 39867908f7e04ccdf7b44ed67957d1a9bb719415 Mon Sep 17 00:00:00 2001
From: HiveBeats <e1lama@protonmail.com>
Date: Sun, 7 Dec 2025 00:32:24 +0700
Subject: [PATCH] initial commit

---
 .gitignore      |  28 ++++++++++++
 go.mod          |   3 ++
 lexer/lexer.go  | 113 ++++++++++++++++++++++++++++++++++++++++++++++++
 lexer/tokens.go |  49 +++++++++++++++++++++
 main.go         |   5 +++
 5 files changed, 198 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 go.mod
 create mode 100644 lexer/lexer.go
 create mode 100644 lexer/tokens.go
 create mode 100644 main.go

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..062d547
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,28 @@
+# Binaries for the current project
+*.exe
+*.dll
+*.so
+*.dylib
+
+# Go build cache
+.cache/go-build/
+
+# IDE-specific files and directories
+.idea/
+.vscode/
+*.iml
+*.ipr
+*.iws
+
+# Operating system specific files
+.DS_Store
+Thumbs.db
+
+# Test coverage output
+*.out
+
+# Dependency management tools (if not vendoring)
+vendor/ # Uncomment if you are not vendoring dependencies
+
+# Log files
+*.log
\ No newline at end of file
diff --git a/go.mod b/go.mod
new file mode 100644
index 0000000..a221834
--- /dev/null
+++ b/go.mod
@@ -0,0 +1,3 @@
+module github.com/e1lama/spl
+
+go 1.25.1
diff --git a/lexer/lexer.go b/lexer/lexer.go
new file mode 100644
index 0000000..ed68864
--- /dev/null
+++ b/lexer/lexer.go
@@ -0,0 +1,113 @@
+package lexer
+
+import (
+	//"fmt"
+	"regexp"
+)
+
+type regexPattern struct {
+	regex   *regexp.Regexp
+	handler regexHandler
+}
+
+type lexer struct {
+	patterns []regexPattern
+	Tokens   []Token
+	source   string
+	position int
+}
+
+func createLexer(source string) *lexer {
+	lex := &lexer{
+		position: 0,
+		source:   source,
+		Tokens:   make([]Token, 0),
+		patterns: []regexPattern{
+			{regexp.MustCompile(`\s+`), defaultHandler(SPACE, " ")},
+			{regexp.MustCompile(`\:`), defaultHandler(COLON, ":")},
+			{regexp.MustCompile(`>=`), defaultHandler(MORE_EQUAL, ">=")},
+			{regexp.MustCompile(`>`), defaultHandler(MORE, ">")},
+			{regexp.MustCompile(`<=`), defaultHandler(LESS_EQUAL, "<=")},
+			{regexp.MustCompile(`<`), defaultHandler(LESS, "<")},
+			{regexp.MustCompile(`!=`), defaultHandler(NOT_EQUAL, "!=")},
+			{regexp.MustCompile(`=`), defaultHandler(EQUAL, "=")},
+			{regexp.MustCompile(`!`), defaultHandler(EXCLAMATION, "!")},
+			{regexp.MustCompile(`\band\b|\bAND\b`), defaultHandler(AND, "and")},
+			{regexp.MustCompile(`\bnot\b|\bNOT\b`), defaultHandler(NOT, "not")},
+			{regexp.MustCompile(`\bor\b|\bOR\b`), defaultHandler(OR, "or")},
+			{regexp.MustCompile(`\(`), defaultHandler(OPEN_BRACE, "(")},
+			{regexp.MustCompile(`\)`), defaultHandler(CLOSED_BRACE, ")")},
+			{regexp.MustCompile(`\|`), defaultHandler(PIPE, "|")},
+			{regexp.MustCompile(`//(.*)$`), commentHandler},         //defaultHandler(COMMENT, value string)},
+			{regexp.MustCompile(`[-+]?[0-9]`), numberHandler},       //NUMBER,
+			{regexp.MustCompile(`([0-9]*\.?[0-9]+)`), floatHandler}, //FLOAT_NUMBER
+			{regexp.MustCompile(`"([^"]*)"`), stringHandler},        //STRING_LITERAL,
+			{regexp.MustCompile(`\b\w+\b`), symbolHandler},          //SYMBOL
+		},
+	}
+	return lex
+}
+
+func (this *lexer) incrementPosition(n int) {
+	this.position += n
+}
+
+func (this *lexer) push(token Token) {
+	this.Tokens = append(this.Tokens, token)
+	this.incrementPosition(len(token.value))
+}
+
+func (lex *lexer) at() byte {
+	return lex.source[lex.position]
+}
+
+func (lex *lexer) currentString() string {
+	return lex.source[lex.position:]
+}
+
+func (lex *lexer) atEof() bool {
+	return lex.position >= len(lex.source)
+}
+
+type regexHandler func(lex *lexer, regex *regexp.Regexp)
+
+func defaultHandler(tokenType TokenType, value string) regexHandler {
+	return func(lex *lexer, regex *regexp.Regexp) {
+		lex.push(Token{tokenType, value})
+	}
+}
+
+func stringHandler(lex *lexer, regex *regexp.Regexp) {
+	match := regex.FindStringIndex(lex.currentString())
+	stringLiteral := lex.currentString()[match[0]:match[1]]
+
+	lex.push(Token{STRING_LITERAL, stringLiteral})
+}
+
+func numberHandler(lex *lexer, regex *regexp.Regexp) {
+	match := regex.FindString(lex.currentString())
+	lex.push(Token{NUMBER, match})
+}
+
+func floatHandler(lex *lexer, regex *regexp.Regexp) {
+	match := regex.FindString(lex.currentString())
+	lex.push(Token{NUMBER, match})
+}
+
+func symbolHandler(lex *lexer, regex *regexp.Regexp) {
+	//todo: if reserved keyword, insert "IDENTIFIER" token
+	match := regex.FindString(lex.currentString())
+	lex.push(Token{SYMBOL, match})
+}
+
+func skipHandler(lex *lexer, regex *regexp.Regexp) {
+	match := regex.FindStringIndex(lex.currentString())
+	lex.incrementPosition(match[1])
+}
+
+func commentHandler(lex *lexer, regex *regexp.Regexp) {
+	match := regex.FindStringIndex(lex.currentString())
+	if match != nil {
+		lex.incrementPosition(match[1])
+	}
+}
diff --git a/lexer/tokens.go b/lexer/tokens.go
new file mode 100644
index 0000000..183c7fb
--- /dev/null
+++ b/lexer/tokens.go
@@ -0,0 +1,49 @@
+package lexer
+
+// что есть в запросе?
+// строковые литералы
+// двоеточия
+// знак равенства
+// знак неравенства
+// AND
+// NOT
+// открытые скобки
+// закрытые скобки
+// комментарии
+// пайп-символы
+// числа
+// строки
+
+type TokenType int
+
+const (
+	SYMBOL TokenType = iota
+	COLON
+	EXCLAMATION
+	EQUAL
+	NOT_EQUAL
+	AND
+	NOT
+	OR
+	MORE
+	LESS
+	MORE_EQUAL
+	LESS_EQUAL
+	OPEN_BRACE
+	CLOSED_BRACE
+	COMMENT
+	PIPE
+	NUMBER
+	FLOAT_NUMBER
+	STRING_LITERAL
+	SPACE
+)
+
+type Token struct {
+	tokenType TokenType
+	value     string
+}
+
+func Parse(str string) {
+
+}
diff --git a/main.go b/main.go
new file mode 100644
index 0000000..7905807
--- /dev/null
+++ b/main.go
@@ -0,0 +1,5 @@
+package main
+
+func main() {
+
+}