lex.go

// 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 jade

import (
	"fmt"
	"strings"
	"unicode"
	"unicode/utf8"
)

// item represents a token or text string returned from the scanner.
type item struct {
	typ itemType // The type of this item.
	pos psn      // The starting position, in bytes, of this item in the input string.
	val string   // The value of this item.
}

func (i item) String() string {
	switch {
	case i.typ == itemEOF:
		return "EOF"
	case i.typ == itemError:
		return i.val
	case len(i.val) > 10:
		return fmt.Sprintf("%.10q...", i.val)
	}
	return fmt.Sprintf("%q", i.val)
}

const eof = -1

// stateFn represents the state of the scanner as a function that returns the next state.
type stateFn func(*lexer) stateFn

// lexer holds the state of the scanner.
type lexer struct {
	name       string    // the name of the input; used only for error reports
	input      string    // the string being scanned
	leftDelim  string    // start of action
	rightDelim string    // end of action
	state      stateFn   // the next lexing function to enter
	pos        psn       // current position in the input
	start      psn       // start position of this item
	width      psn       // width of last rune read from input
	lastPos    psn       // position of most recent item returned by nextItem
	items      chan item // channel of scanned items
	previous   int       // previous depth
	parenDepth int       // nesting depth
	env        map[mode]int
}

// next returns the next rune in the input.
func (l *lexer) next() rune {
	if int(l.pos) >= len(l.input) {
		l.width = 0
		return eof
	}
	r, w := utf8.DecodeRuneInString(l.input[l.pos:])
	l.width = psn(w)
	l.pos += l.width
	return r
}

// peek returns but does not consume the next rune in the input.
func (l *lexer) peek() rune {
	r := l.next()
	l.backup()
	return r
}

// backup steps back one rune. Can only be called once per call of next.
func (l *lexer) backup() {
	l.pos -= l.width
}

// emit passes an item back to the client.
func (l *lexer) emit(t itemType) {
	l.items <- item{t, l.start, l.input[l.start:l.pos]}
	l.start = l.pos
}

// ignore skips over the pending input before this point.
func (l *lexer) ignore() {
	l.start = l.pos
}

// accept consumes the next rune if it's from the valid set.
func (l *lexer) accept(valid string) bool {
	if strings.IndexRune(valid, l.next()) >= 0 {
		return true
	}
	l.backup()
	return false
}

// acceptRun consumes a run of runes from the valid set.
func (l *lexer) acceptRun(valid string) {
	for strings.IndexRune(valid, l.next()) >= 0 {
	}
	l.backup()
}

// lineNumber reports which line we're on, based on the position of
// the previous item returned by nextItem. Doing it this way
// means we don't have to worry about peek double counting.
func (l *lexer) lineNumber() int {
	return 1 + strings.Count(l.input[:l.lastPos], "\n")
}

// errorf returns an error token and terminates the scan by passing
// back a nil pointer that will be the next state, terminating l.nextItem.
func (l *lexer) errorf(format string, args ...interface{}) stateFn {
	l.items <- item{itemError, l.start, fmt.Sprintf(format, args...)}
	return nil
}

// nextItem returns the next item from the input.
func (l *lexer) nextItem() item {
	item := <-l.items
	l.lastPos = item.pos
	return item
}

// lex creates a new scanner for the input string.
func lex(name, input, left, right string) *lexer {
	if left == "" {
		left = LeftDelim
	}
	if right == "" {
		right = RightDelim
	}
	l := &lexer{
		name:       name,
		input:      input,
		leftDelim:  left,
		rightDelim: right,
		items:      make(chan item),
		env:        make(map[mode]int),
	}
	go l.run()
	return l
}

// isSpace reports whether r is a space character.
func isSpace(r rune) bool {
	return r == ' ' || r == '\t'
}

// isEndOfLine reports whether r is an end-of-line character.
func isEndOfLine(r rune) bool {
	return r == '\r' || r == '\n'
}

// isAlphaNumeric reports whether r is an alphabetic, digit, or underscore.
func isAlphaNumeric(r rune) bool {
	return r == '_' || r == '-' || unicode.IsLetter(r) || unicode.IsDigit(r)
}