/usr/share/gocode/src/golang.org/x/text/unicode/rangetable/merge_test.go is in golang-golang-x-text-dev 0.0~git20170627.0.6353ef0-1ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 | // Copyright 2015 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 rangetable
import (
"testing"
"unicode"
)
var (
maxRuneTable = &unicode.RangeTable{
R32: []unicode.Range32{
{unicode.MaxRune, unicode.MaxRune, 1},
},
}
overlap1 = &unicode.RangeTable{
R16: []unicode.Range16{
{0x100, 0xfffc, 4},
},
R32: []unicode.Range32{
{0x100000, 0x10fffc, 4},
},
}
overlap2 = &unicode.RangeTable{
R16: []unicode.Range16{
{0x101, 0xfffd, 4},
},
R32: []unicode.Range32{
{0x100001, 0x10fffd, 3},
},
}
// The following table should be compacted into two entries for R16 and R32.
optimize = &unicode.RangeTable{
R16: []unicode.Range16{
{0x1, 0x1, 1},
{0x2, 0x2, 1},
{0x3, 0x3, 1},
{0x5, 0x5, 1},
{0x7, 0x7, 1},
{0x9, 0x9, 1},
{0xb, 0xf, 2},
},
R32: []unicode.Range32{
{0x10001, 0x10001, 1},
{0x10002, 0x10002, 1},
{0x10003, 0x10003, 1},
{0x10005, 0x10005, 1},
{0x10007, 0x10007, 1},
{0x10009, 0x10009, 1},
{0x1000b, 0x1000f, 2},
},
}
)
func TestMerge(t *testing.T) {
for i, tt := range [][]*unicode.RangeTable{
{unicode.Cc, unicode.Cf},
{unicode.L, unicode.Ll},
{unicode.L, unicode.Ll, unicode.Lu},
{unicode.Ll, unicode.Lu},
{unicode.M},
unicode.GraphicRanges,
cased,
// Merge R16 only and R32 only and vice versa.
{unicode.Khmer, unicode.Khudawadi},
{unicode.Imperial_Aramaic, unicode.Radical},
// Merge with empty.
{&unicode.RangeTable{}},
{&unicode.RangeTable{}, &unicode.RangeTable{}},
{&unicode.RangeTable{}, &unicode.RangeTable{}, &unicode.RangeTable{}},
{&unicode.RangeTable{}, unicode.Hiragana},
{unicode.Inherited, &unicode.RangeTable{}},
{&unicode.RangeTable{}, unicode.Hanunoo, &unicode.RangeTable{}},
// Hypothetical tables.
{maxRuneTable},
{overlap1, overlap2},
// Optimization
{optimize},
} {
rt := Merge(tt...)
for r := rune(0); r <= unicode.MaxRune; r++ {
if got, want := unicode.Is(rt, r), unicode.In(r, tt...); got != want {
t.Fatalf("%d:%U: got %v; want %v", i, r, got, want)
}
}
// Test optimization and correctness for R16.
for k := 0; k < len(rt.R16)-1; k++ {
if lo, hi := rt.R16[k].Lo, rt.R16[k].Hi; lo > hi {
t.Errorf("%d: Lo (%x) > Hi (%x)", i, lo, hi)
}
if hi, lo := rt.R16[k].Hi, rt.R16[k+1].Lo; hi >= lo {
t.Errorf("%d: Hi (%x) >= next Lo (%x)", i, hi, lo)
}
if rt.R16[k].Hi+rt.R16[k].Stride == rt.R16[k+1].Lo {
t.Errorf("%d: missed optimization for R16 at %d between %X and %x",
i, k, rt.R16[k], rt.R16[k+1])
}
}
// Test optimization and correctness for R32.
for k := 0; k < len(rt.R32)-1; k++ {
if lo, hi := rt.R32[k].Lo, rt.R32[k].Hi; lo > hi {
t.Errorf("%d: Lo (%x) > Hi (%x)", i, lo, hi)
}
if hi, lo := rt.R32[k].Hi, rt.R32[k+1].Lo; hi >= lo {
t.Errorf("%d: Hi (%x) >= next Lo (%x)", i, hi, lo)
}
if rt.R32[k].Hi+rt.R32[k].Stride == rt.R32[k+1].Lo {
t.Errorf("%d: missed optimization for R32 at %d between %X and %X",
i, k, rt.R32[k], rt.R32[k+1])
}
}
}
}
const runes = "Hello World in 2015!,\U0010fffd"
func BenchmarkNotMerged(t *testing.B) {
for i := 0; i < t.N; i++ {
for _, r := range runes {
unicode.In(r, unicode.GraphicRanges...)
}
}
}
func BenchmarkMerged(t *testing.B) {
rt := Merge(unicode.GraphicRanges...)
for i := 0; i < t.N; i++ {
for _, r := range runes {
unicode.Is(rt, r)
}
}
}
var cased = []*unicode.RangeTable{
unicode.Lower,
unicode.Upper,
unicode.Title,
unicode.Other_Lowercase,
unicode.Other_Uppercase,
}
func BenchmarkNotMergedCased(t *testing.B) {
for i := 0; i < t.N; i++ {
for _, r := range runes {
unicode.In(r, cased...)
}
}
}
func BenchmarkMergedCased(t *testing.B) {
// This reduces len(R16) from 243 to 82 and len(R32) from 65 to 35 for
// Unicode 7.0.0.
rt := Merge(cased...)
for i := 0; i < t.N; i++ {
for _, r := range runes {
unicode.Is(rt, r)
}
}
}
func BenchmarkInit(t *testing.B) {
for i := 0; i < t.N; i++ {
Merge(cased...)
Merge(unicode.GraphicRanges...)
}
}
func BenchmarkInit2(t *testing.B) {
// Hypothetical near-worst-case performance.
for i := 0; i < t.N; i++ {
Merge(overlap1, overlap2)
}
}
|