// Copyright 2011 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package syntax

// Note to implementers:
// In this package, re is always a *Regexp and r is always a rune.

import (
	
	
	
)

// A Regexp is a node in a regular expression syntax tree.
type Regexp struct {
	Op       Op // operator
	Flags    Flags
	Sub      []*Regexp  // subexpressions, if any
	Sub0     [1]*Regexp // storage for short Sub
	Rune     []rune     // matched runes, for OpLiteral, OpCharClass
	Rune0    [2]rune    // storage for short Rune
	Min, Max int        // min, max for OpRepeat
	Cap      int        // capturing index, for OpCapture
	Name     string     // capturing name, for OpCapture
}

//go:generate stringer -type Op -trimprefix Op

// An Op is a single regular expression operator.
type Op uint8

// Operators are listed in precedence order, tightest binding to weakest.
// Character class operators are listed simplest to most complex
// (OpLiteral, OpCharClass, OpAnyCharNotNL, OpAnyChar).

const (
	OpNoMatch        Op = 1 + iota // matches no strings
	OpEmptyMatch                   // matches empty string
	OpLiteral                      // matches Runes sequence
	OpCharClass                    // matches Runes interpreted as range pair list
	OpAnyCharNotNL                 // matches any character except newline
	OpAnyChar                      // matches any character
	OpBeginLine                    // matches empty string at beginning of line
	OpEndLine                      // matches empty string at end of line
	OpBeginText                    // matches empty string at beginning of text
	OpEndText                      // matches empty string at end of text
	OpWordBoundary                 // matches word boundary `\b`
	OpNoWordBoundary               // matches word non-boundary `\B`
	OpCapture                      // capturing subexpression with index Cap, optional name Name
	OpStar                         // matches Sub[0] zero or more times
	OpPlus                         // matches Sub[0] one or more times
	OpQuest                        // matches Sub[0] zero or one times
	OpRepeat                       // matches Sub[0] at least Min times, at most Max (Max == -1 is no limit)
	OpConcat                       // matches concatenation of Subs
	OpAlternate                    // matches alternation of Subs
)

const opPseudo Op = 128 // where pseudo-ops start

// Equal reports whether x and y have identical structure.
func ( *Regexp) ( *Regexp) bool {
	if  == nil ||  == nil {
		return  == 
	}
	if .Op != .Op {
		return false
	}
	switch .Op {
	case OpEndText:
		// The parse flags remember whether this is \z or \Z.
		if .Flags&WasDollar != .Flags&WasDollar {
			return false
		}

	case OpLiteral, OpCharClass:
		if len(.Rune) != len(.Rune) {
			return false
		}
		for ,  := range .Rune {
			if  != .Rune[] {
				return false
			}
		}

	case OpAlternate, OpConcat:
		if len(.Sub) != len(.Sub) {
			return false
		}
		for ,  := range .Sub {
			if !.(.Sub[]) {
				return false
			}
		}

	case OpStar, OpPlus, OpQuest:
		if .Flags&NonGreedy != .Flags&NonGreedy || !.Sub[0].(.Sub[0]) {
			return false
		}

	case OpRepeat:
		if .Flags&NonGreedy != .Flags&NonGreedy || .Min != .Min || .Max != .Max || !.Sub[0].(.Sub[0]) {
			return false
		}

	case OpCapture:
		if .Cap != .Cap || .Name != .Name || !.Sub[0].(.Sub[0]) {
			return false
		}
	}
	return true
}

// writeRegexp writes the Perl syntax for the regular expression re to b.
func ( *strings.Builder,  *Regexp) {
	switch .Op {
	default:
		.WriteString("<invalid op" + strconv.Itoa(int(.Op)) + ">")
	case OpNoMatch:
		.WriteString(`[^\x00-\x{10FFFF}]`)
	case OpEmptyMatch:
		.WriteString(`(?:)`)
	case OpLiteral:
		if .Flags&FoldCase != 0 {
			.WriteString(`(?i:`)
		}
		for ,  := range .Rune {
			escape(, , false)
		}
		if .Flags&FoldCase != 0 {
			.WriteString(`)`)
		}
	case OpCharClass:
		if len(.Rune)%2 != 0 {
			.WriteString(`[invalid char class]`)
			break
		}
		.WriteRune('[')
		if len(.Rune) == 0 {
			.WriteString(`^\x00-\x{10FFFF}`)
		} else if .Rune[0] == 0 && .Rune[len(.Rune)-1] == unicode.MaxRune && len(.Rune) > 2 {
			// Contains 0 and MaxRune. Probably a negated class.
			// Print the gaps.
			.WriteRune('^')
			for  := 1;  < len(.Rune)-1;  += 2 {
				,  := .Rune[]+1, .Rune[+1]-1
				escape(, ,  == '-')
				if  !=  {
					.WriteRune('-')
					escape(, ,  == '-')
				}
			}
		} else {
			for  := 0;  < len(.Rune);  += 2 {
				,  := .Rune[], .Rune[+1]
				escape(, ,  == '-')
				if  !=  {
					.WriteRune('-')
					escape(, ,  == '-')
				}
			}
		}
		.WriteRune(']')
	case OpAnyCharNotNL:
		.WriteString(`(?-s:.)`)
	case OpAnyChar:
		.WriteString(`(?s:.)`)
	case OpBeginLine:
		.WriteString(`(?m:^)`)
	case OpEndLine:
		.WriteString(`(?m:$)`)
	case OpBeginText:
		.WriteString(`\A`)
	case OpEndText:
		if .Flags&WasDollar != 0 {
			.WriteString(`(?-m:$)`)
		} else {
			.WriteString(`\z`)
		}
	case OpWordBoundary:
		.WriteString(`\b`)
	case OpNoWordBoundary:
		.WriteString(`\B`)
	case OpCapture:
		if .Name != "" {
			.WriteString(`(?P<`)
			.WriteString(.Name)
			.WriteRune('>')
		} else {
			.WriteRune('(')
		}
		if .Sub[0].Op != OpEmptyMatch {
			(, .Sub[0])
		}
		.WriteRune(')')
	case OpStar, OpPlus, OpQuest, OpRepeat:
		if  := .Sub[0]; .Op > OpCapture || .Op == OpLiteral && len(.Rune) > 1 {
			.WriteString(`(?:`)
			(, )
			.WriteString(`)`)
		} else {
			(, )
		}
		switch .Op {
		case OpStar:
			.WriteRune('*')
		case OpPlus:
			.WriteRune('+')
		case OpQuest:
			.WriteRune('?')
		case OpRepeat:
			.WriteRune('{')
			.WriteString(strconv.Itoa(.Min))
			if .Max != .Min {
				.WriteRune(',')
				if .Max >= 0 {
					.WriteString(strconv.Itoa(.Max))
				}
			}
			.WriteRune('}')
		}
		if .Flags&NonGreedy != 0 {
			.WriteRune('?')
		}
	case OpConcat:
		for ,  := range .Sub {
			if .Op == OpAlternate {
				.WriteString(`(?:`)
				(, )
				.WriteString(`)`)
			} else {
				(, )
			}
		}
	case OpAlternate:
		for ,  := range .Sub {
			if  > 0 {
				.WriteRune('|')
			}
			(, )
		}
	}
}

func ( *Regexp) () string {
	var  strings.Builder
	writeRegexp(&, )
	return .String()
}

const meta = `\.+*?()|[]{}^$`

func ( *strings.Builder,  rune,  bool) {
	if unicode.IsPrint() {
		if strings.ContainsRune(meta, ) ||  {
			.WriteRune('\\')
		}
		.WriteRune()
		return
	}

	switch  {
	case '\a':
		.WriteString(`\a`)
	case '\f':
		.WriteString(`\f`)
	case '\n':
		.WriteString(`\n`)
	case '\r':
		.WriteString(`\r`)
	case '\t':
		.WriteString(`\t`)
	case '\v':
		.WriteString(`\v`)
	default:
		if  < 0x100 {
			.WriteString(`\x`)
			 := strconv.FormatInt(int64(), 16)
			if len() == 1 {
				.WriteRune('0')
			}
			.WriteString()
			break
		}
		.WriteString(`\x{`)
		.WriteString(strconv.FormatInt(int64(), 16))
		.WriteString(`}`)
	}
}

// MaxCap walks the regexp to find the maximum capture index.
func ( *Regexp) () int {
	 := 0
	if .Op == OpCapture {
		 = .Cap
	}
	for ,  := range .Sub {
		if  := .();  <  {
			 = 
		}
	}
	return 
}

// CapNames walks the regexp to find the names of capturing groups.
func ( *Regexp) () []string {
	 := make([]string, .MaxCap()+1)
	.capNames()
	return 
}

func ( *Regexp) ( []string) {
	if .Op == OpCapture {
		[.Cap] = .Name
	}
	for ,  := range .Sub {
		.()
	}
}