/usr/share/gocode/src/gopkg.in/neurosnap/sentences.v1/sentences_test.go is in golang-gopkg-neurosnap-sentences.v1-dev 1.0.6-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 | package sentences
import (
"io/ioutil"
"strings"
"testing"
td "github.com/neurosnap/sentences/data"
)
func loadTokenizer(data string) *DefaultSentenceTokenizer {
b, err := td.Asset(data)
if err != nil {
panic(err)
}
training, err := LoadTraining(b)
if err != nil {
panic(err)
}
return NewSentenceTokenizer(training)
}
func readFile(fname string) string {
content, err := ioutil.ReadFile(fname)
if err != nil {
panic(err)
}
return string(content)
}
func getFileLocation(prefix, original, expected string) []string {
origText := strings.Join([]string{prefix, original}, "")
expectedText := strings.Join([]string{prefix, expected}, "")
return []string{origText, expectedText}
}
func TestEnglish(t *testing.T) {
t.Log("Starting test suite ...")
tokenizer := loadTokenizer("data/english.json")
prefix := "test_files/english/"
testFiles := [][]string{
getFileLocation(prefix, "carolyn.txt", "carolyn_s.txt"),
getFileLocation(prefix, "ecig.txt", "ecig_s.txt"),
getFileLocation(prefix, "foul_ball.txt", "foul_ball_s.txt"),
getFileLocation(prefix, "fbi.txt", "fbi_s.txt"),
getFileLocation(prefix, "dre.txt", "dre_s.txt"),
getFileLocation(prefix, "dr.txt", "dr_s.txt"),
getFileLocation(prefix, "quotes.txt", "quotes_s.txt"),
getFileLocation(prefix, "kiss.txt", "kiss_s.txt"),
getFileLocation(prefix, "kentucky.txt", "kentucky_s.txt"),
getFileLocation(prefix, "iphone6s.txt", "iphone6s_s.txt"),
getFileLocation(prefix, "lebanon.txt", "lebanon_s.txt"),
getFileLocation(prefix, "duma.txt", "duma_s.txt"),
getFileLocation(prefix, "demolitions.txt", "demolitions_s.txt"),
getFileLocation(prefix, "qa.txt", "qa_s.txt"),
getFileLocation(prefix, "anarchy.txt", "anarchy_s.txt"),
getFileLocation(prefix, "ethicist.txt", "ethicist_s.txt"),
getFileLocation(prefix, "self_reliance.txt", "self_reliance_s.txt"),
getFileLocation(prefix, "punct.txt", "punct_s.txt"),
getFileLocation(prefix, "clinton.txt", "clinton_s.txt"),
getFileLocation(prefix, "markets.txt", "markets_s.txt"),
getFileLocation(prefix, "nyfed.txt", "nyfed_s.txt"),
}
for _, f := range testFiles {
actualText := readFile(f[0])
expectedText := readFile(f[1])
expected := strings.Split(expectedText, "{{sentence_break}}")
t.Log(f[0])
sentences := tokenizer.Tokenize(actualText)
for index, s := range sentences {
sentence := strings.TrimSpace(s.Text)
if sentence != strings.TrimSpace(expected[index]) {
t.Logf("Actual : %q", sentence)
t.Log("--------")
t.Logf("Expected: %q", strings.TrimSpace(expected[index]))
t.Fatalf("%s line %d: Actual sentence does not match expected sentence", f[0], index)
}
}
}
}
func TestSemicolon(t *testing.T) {
t.Log("Tokenizer should parse sentences with semicolons")
tokenizer := loadTokenizer("data/english.json")
actualText := "I am here; you are over there. Will the tokenizer output two complete sentences?"
actual := tokenizer.Tokenize(actualText)
expected := []string{
"I am here; you are over there.",
" Will the tokenizer output two complete sentences?",
}
t.Logf("%v", actual)
if len(actual) != len(expected) {
t.Fatalf("Actual: %d, Expected: %d", len(actual), len(expected))
}
for index, sent := range actual {
if sent.Text != expected[index] {
t.Fatalf("Actual: %s\nExpected: %s", sent.Text, expected[index])
}
}
}
func TestEndOfTextNoPunct(t *testing.T) {
t.Log("Tokenizer should break up sentences even if text doesn't end in punctuation")
tokenizer := loadTokenizer("data/english.json")
actualText := "Hi does this work?\n\nIt seems to. This is great"
actual := tokenizer.Tokenize(actualText)
expected := []string{
"Hi does this work?",
"\n\nIt seems to.",
" This is great",
}
t.Logf("%v", actual)
if len(actual) != len(expected) {
t.Fatalf("Actual: %d, Expected: %d", len(actual), len(expected))
}
for index, sent := range actual {
if sent.Text != expected[index] {
t.Fatalf("Actual: %s\nExpected: %s", sent.Text, expected[index])
}
}
}
func TestWeirdEllipsis(t *testing.T) {
t.Log("Tokenizer should not break up ellipsis")
actualText := "Harry Potter . . . what an honor."
expected := []string{
"Harry Potter . . . what an honor.",
}
compareSentence(t, actualText, expected)
}
func TestNormalEllipsis(t *testing.T) {
t.Log("Tokenizer should not break up ellipsis")
actualText := "Harry Potter ... what an honor."
expected := []string{
"Harry Potter ... what an honor.",
}
compareSentence(t, actualText, expected)
}
func TestSpacedPeriod(t *testing.T) {
t.Log("Tokenizer should break up sentence with a barren period")
actualText := "Hi my name is steve . what is your name?"
expected := []string{
"Hi my name is steve .",
" what is your name?",
}
compareSentence(t, actualText, expected)
}
func compareSentence(t *testing.T, actualText string, expected []string) {
tokenizer := loadTokenizer("data/english.json")
actual := tokenizer.Tokenize(actualText)
t.Logf("Actual: %v", actual)
if len(actual) != len(expected) {
t.Fatalf("Actual: %d, Expected: %d", len(actual), len(expected))
}
for index, sent := range actual {
if sent.Text != expected[index] {
t.Fatalf("Actual: %s\nExpected: %s", sent.Text, expected[index])
}
}
}
|