encodingxml.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 xml

import (
	"bytes"
	"strings"
)

var (
	begComment  = []byte("<!--")
	endComment  = []byte("-->")
	endProcInst = []byte("?>")
)

// isValidDirective reports whether dir is a valid directive text,
// meaning angle brackets are matched, ignoring comments and strings.
func isValidDirective(dir Directive) bool {
	var (
		depth     int
		inquote   uint8
		incomment bool
	)
	for i, c := range dir {
		switch {
		case incomment:
			if c == '>' {
				if n := 1 + i - len(endComment); n >= 0 && bytes.Equal(dir[n:i+1], endComment) {
					incomment = false
				}
			}
			// Just ignore anything in comment
		case inquote != 0:
			if c == inquote {
				inquote = 0
			}
			// Just ignore anything within quotes
		case c == '\'' || c == '"':
			inquote = c
		case c == '<':
			if i+len(begComment) < len(dir) && bytes.Equal(dir[i:i+len(begComment)], begComment) {
				incomment = true
			} else {
				depth++
			}
		case c == '>':
			if depth == 0 {
				return false
			}
			depth--
		}
	}
	return depth == 0 && inquote == 0 && !incomment
}

// Decide whether the given rune is in the XML Character Range, per
// the Char production of https://www.xml.com/axml/testaxml.htm,
// Section 2.2 Characters.
func isInCharacterRange(r rune) (inrange bool) {
	return r == 0x09 ||
		r == 0x0A ||
		r == 0x0D ||
		r >= 0x20 && r <= 0xD7FF ||
		r >= 0xE000 && r <= 0xFFFD ||
		r >= 0x10000 && r <= 0x10FFFF
}

// procInst parses the `param="..."` or `param='...'`
// value out of the provided string, returning "" if not found.
func procInst(param, s string) string {
	// TODO: this parsing is somewhat lame and not exact.
	// It works for all actual cases, though.
	param = param + "="
	_, v, _ := strings.Cut(s, param)
	if v == "" {
		return ""
	}
	if v[0] != '\'' && v[0] != '"' {
		return ""
	}
	unquote, _, ok := strings.Cut(v[1:], v[:1])
	if !ok {
		return ""
	}
	return unquote
}

func isNameByte(c byte) bool {
	return 'A' <= c && c <= 'Z' ||
		'a' <= c && c <= 'z' ||
		'0' <= c && c <= '9' ||
		c == '_' || c == ':' || c == '.' || c == '-'
}