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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
|
// Copyright Yahoo. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
package com.yahoo.text;
import java.util.Locale;
import java.util.OptionalInt;
/**
* Text utility functions.
*
* @author bratseth
*/
public final class Text {
private static final boolean[] allowedAsciiChars = new boolean[0x80];
static {
allowedAsciiChars[0x0] = false;
allowedAsciiChars[0x1] = false;
allowedAsciiChars[0x2] = false;
allowedAsciiChars[0x3] = false;
allowedAsciiChars[0x4] = false;
allowedAsciiChars[0x5] = false;
allowedAsciiChars[0x6] = false;
allowedAsciiChars[0x7] = false;
allowedAsciiChars[0x8] = false;
allowedAsciiChars[0x9] = true; //tab
allowedAsciiChars[0xA] = true; //nl
allowedAsciiChars[0xB] = false;
allowedAsciiChars[0xC] = false;
allowedAsciiChars[0xD] = true; //cr
for (int i = 0xE; i < 0x20; i++) {
allowedAsciiChars[i] = false;
}
for (int i = 0x20; i < 0x7F; i++) {
allowedAsciiChars[i] = true; //printable ascii chars
}
allowedAsciiChars[0x7F] = true; //del - discouraged, but allowed
}
/** No instantiation */
private Text() {}
/**
* Returns whether the given codepoint is a valid text character, potentially suitable for
* purposes such as indexing and display, see http://www.w3.org/TR/2006/REC-xml11-20060816/#charsets
*/
public static boolean isTextCharacter(int codepoint) {
// The link above notes that 0x7F-0x84 and 0x86-0x9F are discouraged, but they are still allowed -
// see http://www.w3.org/International/questions/qa-controls
return (codepoint < 0x80)
? allowedAsciiChars[codepoint]
: (codepoint < Character.MIN_SURROGATE) || isTextCharAboveMinSurrogate(codepoint);
}
private static boolean isTextCharAboveMinSurrogate(int codepoint) {
if (codepoint <= Character.MAX_HIGH_SURROGATE) return false;
if (codepoint < 0xFDD0) return true;
if (codepoint <= 0xFDDF) return false;
if (codepoint < 0x10000) return true;
if (codepoint >= 0x10FFFE) return false;
return (codepoint & 0xffff) < 0xFFFE;
}
/**
* Validates that the given string value only contains text characters and
* returns the first illegal code point if one is found.
*/
public static OptionalInt validateTextString(String string) {
for (int i = 0; i < string.length(); ) {
int codePoint = string.codePointAt(i);
if ( ! Text.isTextCharacter(codePoint))
return OptionalInt.of(codePoint);
int charCount = Character.charCount(codePoint);
if (Character.isHighSurrogate(string.charAt(i))) {
if ( charCount == 1) {
return OptionalInt.of(string.codePointAt(i));
} else if ( !Character.isLowSurrogate(string.charAt(i+1))) {
return OptionalInt.of(string.codePointAt(i+1));
}
}
i += charCount;
}
return OptionalInt.empty();
}
/**
* Validates that the given string value only contains text characters.
*/
public static boolean isValidTextString(String string) {
int length = string.length();
for (int i = 0; i < length; ) {
int codePoint = string.codePointAt(i);
if (codePoint < 0x80) {
if ( ! allowedAsciiChars[codePoint]) return false;
} else if (codePoint >= Character.MIN_SURROGATE) {
if ( ! isTextCharAboveMinSurrogate(codePoint)) return false;
if ( ! Character.isBmpCodePoint(codePoint)) {
i++;
}
}
i++;
}
return true;
}
/** Returns whether the given code point is displayable. */
public static boolean isDisplayable(int codePoint) {
switch (Character.getType(codePoint)) {
case Character.CONNECTOR_PUNCTUATION :
case Character.DASH_PUNCTUATION :
case Character.START_PUNCTUATION :
case Character.END_PUNCTUATION :
case Character.INITIAL_QUOTE_PUNCTUATION :
case Character.FINAL_QUOTE_PUNCTUATION:
case Character.OTHER_PUNCTUATION :
case Character.LETTER_NUMBER :
case Character.OTHER_LETTER :
case Character.LOWERCASE_LETTER :
case Character.TITLECASE_LETTER :
case Character.MODIFIER_LETTER :
case Character.UPPERCASE_LETTER :
case Character.DECIMAL_DIGIT_NUMBER :
case Character.OTHER_NUMBER :
case Character.CURRENCY_SYMBOL :
case Character.OTHER_SYMBOL :
case Character.MATH_SYMBOL :
return true;
default :
return false;
}
}
private static StringBuilder lazy(StringBuilder sb, String s, int i) {
if (sb == null) {
sb = new StringBuilder(s.substring(0, i));
}
sb.append(' ');
return sb;
}
/** Returns a string where any invalid characters in the input string is replaced by spaces */
public static String stripInvalidCharacters(String string) {
StringBuilder stripped = null; // lazy, as most string will not need stripping
for (int i = 0; i < string.length();) {
int codePoint = string.codePointAt(i);
int charCount = Character.charCount(codePoint);
if ( ! Text.isTextCharacter(codePoint)) {
stripped = lazy(stripped, string, i);
} else {
if (Character.isHighSurrogate(string.charAt(i))) {
if (charCount == 1) {
stripped = lazy(stripped, string, i);
} else if (!Character.isLowSurrogate(string.charAt(i+1))) {
stripped = lazy(stripped, string, i);
} else {
if (stripped != null) {
stripped.appendCodePoint(codePoint);
}
}
} else {
if (stripped != null) {
stripped.appendCodePoint(codePoint);
}
}
}
i += charCount;
}
return stripped != null ? stripped.toString() : string;
}
/**
* Returns a string which is never larger than the given number of characters.
* If the string is longer than the given length it will be truncated.
* If length is 4 or less the string will be truncated to length.
* If length is longer than 4, it will be truncated at length-4 with " ..." added at the end.
*/
public static String truncate(String s, int length) {
if (s.length() <= length) return s;
if (length <= 4) return s.substring(0, length);
return s.substring(0, length - 4) + " ...";
}
public static String substringByCodepoints(String s, int fromCP, int toCP) {
int len = s.length();
if ((fromCP >= len) || (fromCP >= toCP)) return "";
int from;
try {
from = s.offsetByCodePoints(0, fromCP);
} catch (IndexOutOfBoundsException e) {
return "";
}
if (from >= len) return "";
int lenCP = toCP - fromCP;
if (from + lenCP >= len) return s.substring(from);
try {
int to = s.offsetByCodePoints(from, toCP - fromCP);
return (to >= len)
? s.substring(from)
: s.substring(from, to);
} catch (IndexOutOfBoundsException e) {
return s.substring(from);
}
}
public static String format(String format, Object... args) {
return String.format(Locale.US, format, args);
}
}
|
