over substrings of s split after each instance of sep.
- [FieldsSeq] returns an iterator over
  substrings of s split around runs of whitespace characters,
  as defined by unicode.IsSpace.
- [FieldsFuncSeq] returns an iterator

// Copyright 2024 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 bytes

import (
	"iter"
	"unicode"
	"unicode/utf8"
)

// Lines returns an iterator over the newline-terminated lines in the byte slice s.
// The lines yielded by the iterator include their terminating newlines.
// If s is empty, the iterator yields no lines at all.

// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package lex

import (
	"go/build/constraint"
	"io"
	"os"
	"strings"
	"text/scanner"
	"unicode"

	"cmd/asm/internal/flags"
	"cmd/internal/objabi"
	"cmd/internal/src"
)

// A Tokenizer is a simple wrapping of text/scanner.Scanner, configured

pkg unicode, var Linear_A *RangeTable
pkg unicode, var Mahajani *RangeTable
pkg unicode, var Manichaean *RangeTable
pkg unicode, var Mende_Kikakui *RangeTable
pkg unicode, var Modi *RangeTable
pkg unicode, var Mro *RangeTable
pkg unicode, var Nabataean *RangeTable
pkg unicode, var Old_North_Arabian *RangeTable
pkg unicode, var Old_Permic *RangeTable
pkg unicode, var Pahawh_Hmong *RangeTable
pkg unicode, var Palmyrene *RangeTable

 * character encoding. UTF-8 is defined in section D92 of <a
 * href="http://www.unicode.org/versions/Unicode6.2.0/ch03.pdf">The Unicode Standard Core
 * Specification, Chapter 3</a>.
 *
 * <p>The variant of UTF-8 implemented by this class is the restricted definition of UTF-8
 * introduced in Unicode 3.1. One implication of this is that it rejects <a
 * href="http://www.unicode.org/versions/corrigendum1.html">"non-shortest form"</a> byte sequences,

    /**
     * 
     * @param src
     * @param srcIndex
     * @param maxLen
     * @param unicode
     * @return read string
     */
    public String readString ( byte[] src, int srcIndex, int maxLen, boolean unicode ) {
        if ( unicode ) {
            // Unicode requires word alignment
            if ( ( ( srcIndex - this.headerStart ) % 2 ) != 0 ) {
                srcIndex++;

			return string(strconv.AppendInt(append([]byte(frame.File), ':'), int64(frame.Line), 10))
		}
	}

	return ""
}

func IsValidDBNameChar(c rune) bool {
	return !unicode.IsLetter(c) && !unicode.IsNumber(c) && c != '.' && c != '*' && c != '_' && c != '$' && c != '@'
}

// CheckTruth check string true or not
func CheckTruth(vals ...string) bool {
	for _, val := range vals {

    // The char values \uFFFE and \uFFFF are explicitly not allowed in XML
    // (Unicode code points above \uFFFF are represented via surrogate pairs
    // which means they are treated as pairs of safe characters).
    builder.setSafeRange(Character.MIN_VALUE, '\uFFFD');
    // Unsafe characters are replaced with the Unicode replacement character.
    builder.setUnsafeReplacement("\uFFFD");

    /*

            if( useUnicode ) {
                // should Unicode alignment be corrected for here?
                str = new String( src, srcIndex, len, UNI_ENCODING );
            } else {
    
                /* On NT without Unicode the fileNameLength
                 * includes the '\0' whereas on win98 it doesn't. I
                 * guess most clients only support non-unicode so
                 * they don't run into this.

	"io"
	"strings"
	"testing"
	"unicode"
	"unicode/utf8"
)

const smallMaxTokenSize = 256 // Much smaller for more efficient testing.

// Test white space table matches the Unicode definition.
func TestSpace(t *testing.T) {
	for r := rune(0); r <= utf8.MaxRune; r++ {
		if IsSpace(r) != unicode.IsSpace(r) {
			t.Fatalf("white space property disagrees: %#U should be %t", r, unicode.IsSpace(r))
		}
	}
}