sparrow/vendor/github.com/Joker/jade/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   Pos      // The starting position, in bytes, of this item in the input string.
	val   string   // The value of this item.
	line  int      // The line number at the start of this item.
	depth int
}

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

const (
	eof        = -1
	spaceChars = " \t\r\n" // These are the space characters defined by Go itself.
)

// 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
	pos   Pos       // current position in the input
	start Pos       // start position of this item
	width Pos       // width of last rune read from input
	items chan item // channel of scanned items
	line  int       // 1+number of newlines seen

	depth         int  // current tag depth
	interpolation int  // interpolation depth
	longtext      bool // long text flag
}

// 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 = Pos(w)
	l.pos += l.width
	if r == '\n' {
		l.line++
	}
	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
	// Correct newline count.
	if l.width == 1 && l.input[l.pos] == '\n' {
		l.line--
	}
}

// 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.line, l.depth}
	// Some items contain text internally. If so, count their newlines.
	switch t {
	// case itemText, itemRawString, itemLeftDelim, itemRightDelim:
	case itemText:
		l.line += strings.Count(l.input[l.start:l.pos], "\n")
	}
	l.start = l.pos
}

// ignore skips over the pending input before this point.
func (l *lexer) ignore() {
	l.line += strings.Count(l.input[l.start:l.pos], "\n")
	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.ContainsRune(valid, l.next()) {
		return true
	}
	l.backup()
	return false
}

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

// 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...), l.line, l.depth}
	return nil
}

// nextItem returns the next item from the input.
// Called by the parser, not in the lexing goroutine.
func (l *lexer) nextItem() item {
	return <-l.items
}

// drain drains the output so the lexing goroutine will exit.
// Called by the parser, not in the lexing goroutine.
func (l *lexer) drain() {
	for range l.items {
	}
}

// lex creates a new scanner for the input string.
func lex(name, input string) *lexer {
	l := &lexer{
		name:  name,
		input: input,
		items: make(chan item),
		line:  1,
	}
	go l.run()
	return l
}

func (l *lexer) run() {
	for state := lexIndents; state != nil; {
		state = state(l)
	}
	close(l.items)
}

// atTerminator reports whether the input is at valid termination character to
// appear after an identifier. Breaks .X.Y into two pieces. Also catches cases
// like "$x+2" not being acceptable without a space, in case we decide one
// day to implement arithmetic.
func (l *lexer) atTerminator() bool {
	r := l.peek()
	if isSpace(r) || isEndOfLine(r) {
		return true
	}
	switch r {
	case eof, '.', ',', '|', ':', ')', '(':
		return true
	}

	return false
}

func (l *lexer) scanNumber() bool {
	// Optional leading sign.
	l.accept("+-")
	// Is it hex?
	digits := "0123456789"
	if l.accept("0") && l.accept("xX") {
		digits = "0123456789abcdefABCDEF"
	}
	l.acceptRun(digits)
	if l.accept(".") {
		l.acceptRun(digits)
	}
	if l.accept("eE") {
		l.accept("+-")
		l.acceptRun("0123456789")
	}
	// Is it imaginary?
	l.accept("i")
	// Next thing mustn't be alphanumeric.
	if isAlphaNumeric(l.peek()) {
		l.next()
		return false
	}
	return true
}

// 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)
}