forked from simdjson/simdjson-java
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathStringParsingTest.java
More file actions
167 lines (134 loc) · 5.96 KB
/
StringParsingTest.java
File metadata and controls
167 lines (134 loc) · 5.96 KB
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
package org.simdjson;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.params.ParameterizedTest;
import org.junit.jupiter.params.provider.ValueSource;
import java.util.Iterator;
import java.util.List;
import static java.lang.Character.MAX_CODE_POINT;
import static java.lang.Character.isBmpCodePoint;
import static java.lang.Character.lowSurrogate;
import static java.util.stream.IntStream.rangeClosed;
import static org.apache.commons.text.StringEscapeUtils.unescapeJava;
import static org.assertj.core.api.Assertions.assertThat;
import static org.junit.jupiter.api.Assertions.assertThrows;
import static org.simdjson.JsonValueAssert.assertThat;
import static org.simdjson.TestUtils.toUtf8;
public class StringParsingTest {
@Test
public void usableUnicodeCharacters() {
// given
SimdJsonParser parser = new SimdJsonParser();
List<String> unicodeCharacters = rangeClosed(0, MAX_CODE_POINT)
.filter(Character::isDefined)
.filter(codePoint -> !isReservedCodePoint(codePoint))
.mapToObj(StringParsingTest::toUnicodeEscape)
.toList();
for (String input : unicodeCharacters) {
byte[] json = toUtf8("\"" + input + "\"");
// when
JsonValue value = parser.parse(json, json.length);
// then
assertThat(value).isEqualTo(unescapeJava(input));
}
}
@Test
public void unicodeCharactersReservedForLowSurrogate() {
// given
SimdJsonParser parser = new SimdJsonParser();
List<String> unicodeCharacters = rangeClosed(0xDC00, 0xDFFF)
.mapToObj(StringParsingTest::toUnicodeEscape)
.toList();
for (String input : unicodeCharacters) {
byte[] json = toUtf8("\"" + input + "\"");
// when
JsonParsingException ex = assertThrows(JsonParsingException.class, () -> parser.parse(json, json.length));
// then
assertThat(ex.getMessage()).isEqualTo("Invalid code point. The range U+DC00–U+DFFF is reserved for low surrogate.");
}
}
@ParameterizedTest
@ValueSource(strings = {"\\uD8001", "\\uD800\\1", "\\uD800u", "\\uD800\\e", "\\uD800\\DC00"})
public void invalidLowSurrogateEscape(String input) {
// given
SimdJsonParser parser = new SimdJsonParser();
byte[] json = toUtf8("\"" + input + "\"");
// when
JsonParsingException ex = assertThrows(JsonParsingException.class, () -> parser.parse(json, json.length));
// then
assertThat(ex.getMessage()).isEqualTo("Low surrogate should start with '\\u'");
}
@ParameterizedTest
@ValueSource(strings = {"\\uD800\\u"})
public void missingLowSurrogate(String input) {
// given
SimdJsonParser parser = new SimdJsonParser();
byte[] json = toUtf8("\"" + input + "\"");
// when
JsonParsingException ex = assertThrows(JsonParsingException.class, () -> parser.parse(json, json.length));
// then
assertThat(ex.getMessage()).isEqualTo("Invalid code point. Low surrogate should be in the range U+DC00–U+DFFF.");
}
@Test
public void invalidLowSurrogateRange() {
// given
SimdJsonParser parser = new SimdJsonParser();
List<String> unicodeCharacters = rangeClosed(0x0000, 0xFFFF)
.filter(lowSurrogate -> lowSurrogate < 0xDC00 || lowSurrogate > 0xDFFF)
.mapToObj(lowSurrogate -> String.format("\\uD800\\u%04X", lowSurrogate))
.toList();
for (String input : unicodeCharacters) {
byte[] json = toUtf8("\"" + input + "\"");
// when
JsonParsingException ex = assertThrows(JsonParsingException.class, () -> parser.parse(json, json.length));
// then
assertThat(ex.getMessage()).isEqualTo("Invalid code point. Low surrogate should be in the range U+DC00–U+DFFF.");
}
}
@ParameterizedTest
@ValueSource(strings = {"\\u", "\\u1", "\\u12", "\\u123"})
public void invalidUnicode(String input) {
// given
SimdJsonParser parser = new SimdJsonParser();
byte[] json = toUtf8("\"" + input + "\"");
// when
JsonParsingException ex = assertThrows(JsonParsingException.class, () -> parser.parse(json, json.length));
// then
assertThat(ex.getMessage()).isEqualTo("Invalid unicode escape sequence.");
}
@ParameterizedTest
@ValueSource(strings = {"\\g", "\\ą"})
public void invalidEscape(String jsonStr) {
// given
SimdJsonParser parser = new SimdJsonParser();
byte[] json = toUtf8("[\"" + jsonStr + "\"]");
// when
JsonParsingException ex = assertThrows(JsonParsingException.class, () -> parser.parse(json, json.length));
// then
assertThat(ex.getMessage()).startsWith("Escaped unexpected character: ");
}
@Test
public void longString() {
// given
SimdJsonParser parser = new SimdJsonParser();
byte[] json = toUtf8("[\"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\"]");
// when
JsonValue jsonValue = parser.parse(json, json.length);
// then
assertThat(jsonValue.isArray()).isTrue();
Iterator<JsonValue> it = jsonValue.arrayIterator();
assertThat(it.hasNext()).isTrue();
assertThat(it.next()).isEqualTo("aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa");
assertThat(it.hasNext()).isFalse();
}
private static String toUnicodeEscape(int codePoint) {
if (isBmpCodePoint(codePoint)) {
return String.format("\\u%04X", codePoint);
} else {
return String.format("\\u%04X\\u%04X",
(int) Character.highSurrogate(codePoint), (int) lowSurrogate(codePoint));
}
}
private static boolean isReservedCodePoint(int codePoint) {
return codePoint >= 0xD800 && codePoint <= 0xDFFF;
}
}