add StrStripper

This commit is contained in:
Looly 2024-09-08 02:55:38 +08:00
parent 60e6ae7510
commit 91d4989c16
3 changed files with 288 additions and 61 deletions

View File

@ -1419,7 +1419,7 @@ public class CharSequenceUtil extends StrValidator {
* }
* </pre>
*
* @param str 被处理的字符串
* @param str 被处理的字符串{@code null}忽略
* @param prefixOrSuffix 前缀或后缀
* @return 处理后的字符串
* @since 3.1.2
@ -1449,8 +1449,8 @@ public class CharSequenceUtil extends StrValidator {
* </pre>
*
* @param str 被处理的字符串
* @param prefix 前缀
* @param suffix 后缀
* @param prefix 前缀{@code null}忽略
* @param suffix 后缀{@code null}忽略
* @return 处理后的字符串
* @since 3.1.2
*/
@ -1475,8 +1475,8 @@ public class CharSequenceUtil extends StrValidator {
* </pre>
*
* @param str 被处理的字符串
* @param prefix 前缀
* @param suffix 后缀
* @param prefix 前缀{@code null}忽略
* @param suffix 后缀{@code null}忽略
* @param ignoreCase 是否忽略大小写
* @return 处理后的字符串
* @since 3.1.2
@ -1486,29 +1486,8 @@ public class CharSequenceUtil extends StrValidator {
return toStringOrNull(str);
}
final String str2 = str.toString();
int from = 0;
int to = str2.length();
if (startWith(str2, prefix, ignoreCase)) {
from = prefix.length();
if (from == to) {
// "a", "a", "a" -> ""
return EMPTY;
}
}
if (endWith(str2, suffix, ignoreCase)) {
to -= suffix.length();
if (from == to) {
// "a", "a", "a" -> ""
return EMPTY;
} else if (to < from) {
// pre去除后和suffix有重叠 ("aba", "ab", "ba") -> "a"
to += suffix.length();
}
}
return str2.substring(from, to);
return new StrStripper(prefix, suffix, ignoreCase, false)
.apply(str);
}
/**
@ -1522,7 +1501,7 @@ public class CharSequenceUtil extends StrValidator {
* </pre>
*
* @param str 被处理的字符串
* @param prefixOrSuffix 前缀或后缀
* @param prefixOrSuffix 前缀或后缀{@code null}忽略
* @return 处理后的字符串
* @since 5.8.30
*/
@ -1558,44 +1537,47 @@ public class CharSequenceUtil extends StrValidator {
* @param prefix 前缀
* @param suffix 后缀
* @return 处理后的字符串
* @since 5.8.30
* @since 6.0.0
*/
public static String stripAll(final CharSequence str, final CharSequence prefix, final CharSequence suffix) {
return stripAll(str, prefix, suffix, false);
}
/**
* 去除两边<u><b>所有</b></u>的指定字符串
*
* <pre>{@code
* "aaa_STRIPPED_bbb", "a", "b" -> "_STRIPPED_"
* "aaa_STRIPPED_bbb", null, null -> "aaa_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "", "" -> "aaa_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "", "b" -> "aaa_STRIPPED_"
* "aaa_STRIPPED_bbb", null, "b" -> "aaa_STRIPPED_"
* "aaa_STRIPPED_bbb", "a", "" -> "_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "a", null -> "_STRIPPED_bbb"
*
* // special test
* "aaaaaabbb", "aaa", null -> "bbb"
* "aaaaaaabbb", "aa", null -> "abbb"
*
* "aaaaaaaaa", "aaa", "aa" -> ""
* "a", "a", "a" -> ""
* }
* </pre>
*
* @param str 被处理的字符串
* @param prefix 前缀
* @param suffix 后缀
* @param ignoreCase 是否忽略大小写
* @return 处理后的字符串
* @since 6.0.0
*/
public static String stripAll(final CharSequence str, final CharSequence prefix, final CharSequence suffix, final boolean ignoreCase) {
if (isEmpty(str)) {
return toStringOrNull(str);
}
final String prefixStr = toStringOrEmpty(prefix);
final String suffixStr = toStringOrEmpty(suffix);
final String str2 = str.toString();
int from = 0;
int to = str2.length();
if (!prefixStr.isEmpty()) {
while (str2.startsWith(prefixStr, from)) {
from += prefix.length();
if (from == to) {
// "a", "a", "a" -> ""
return EMPTY;
}
}
}
if (!suffixStr.isEmpty()) {
while (str2.startsWith(suffixStr, to - suffixStr.length())) {
to -= suffixStr.length();
if (from == to) {
// "a", "a", "a" -> ""
return EMPTY;
} else if (to < from) {
// pre去除后和suffix有重叠 ("aba", "ab", "ba") -> "a"
to += suffixStr.length();
break;
}
}
}
return str2.substring(from, to);
return new StrStripper(prefix, suffix, ignoreCase, true)
.apply(str);
}
// endregion

View File

@ -0,0 +1,186 @@
/*
* Copyright (c) 2024 Hutool Team and hutool.cn
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.dromara.hutool.core.text;
import java.io.Serializable;
import java.util.function.UnaryOperator;
/**
* 字符串裁剪器用于裁剪字符串前后缀<br>
* 强调去除两边或某一边的<b>指定字符串</b>如果一边不存在另一边不影响去除
*
* @author Looly
* @since 5.8.0
*/
public class StrStripper implements UnaryOperator<CharSequence>, Serializable {
private static final long serialVersionUID = 1L;
private final CharSequence prefix;
private final CharSequence suffix;
private final boolean ignoreCase;
private final boolean stripAll;
/**
* 构造
*
* @param prefix 前缀{@code null}忽略
* @param suffix 后缀{@code null}忽略
* @param ignoreCase 是否忽略大小写
* @param stripAll 是否去除全部
*/
public StrStripper(final CharSequence prefix, final CharSequence suffix, final boolean ignoreCase, final boolean stripAll) {
this.prefix = prefix;
this.suffix = suffix;
this.ignoreCase = ignoreCase;
this.stripAll = stripAll;
}
@Override
public String apply(final CharSequence charSequence) {
return this.stripAll ? stripAll(charSequence) : stripOnce(charSequence);
}
/**
* 去除两边的指定字符串<br>
* 两边字符如果存在则去除不存在不做处理
* <pre>{@code
* "aaa_STRIPPED_bbb", "a", "b" -> "aa_STRIPPED_bb"
* "aaa_STRIPPED_bbb", null, null -> "aaa_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "", "" -> "aaa_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "", "b" -> "aaa_STRIPPED_bb"
* "aaa_STRIPPED_bbb", null, "b" -> "aaa_STRIPPED_bb"
* "aaa_STRIPPED_bbb", "a", "" -> "aa_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "a", null -> "aa_STRIPPED_bbb"
*
* "a", "a", "a" -> ""
* }</pre>
*
* @param charSequence 被处理的字符串
* @return 处理后的字符串
*/
private String stripOnce(final CharSequence charSequence) {
if (StrUtil.isEmpty(charSequence)) {
return StrUtil.toStringOrNull(charSequence);
}
final String str = charSequence.toString();
int from = 0;
int to = str.length();
if (StrUtil.isNotEmpty(this.prefix) && startWith(str, this.prefix, 0)) {
from = this.prefix.length();
if (from == to) {
// "a", "a", "a" -> ""
return StrUtil.EMPTY;
}
}
if (endWithSuffix(str)) {
to -= this.suffix.length();
if (from == to) {
// "a", "a", "a" -> ""
return StrUtil.EMPTY;
} else if (to < from) {
// pre去除后和suffix有重叠 ("aba", "ab", "ba") -> "a"
to += this.suffix.length();
}
}
return str.substring(from, to);
}
/**
* 去除两边<u><b>所有</b></u>的指定字符串
*
* <pre>{@code
* "aaa_STRIPPED_bbb", "a", "b" -> "_STRIPPED_"
* "aaa_STRIPPED_bbb", null, null -> "aaa_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "", "" -> "aaa_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "", "b" -> "aaa_STRIPPED_"
* "aaa_STRIPPED_bbb", null, "b" -> "aaa_STRIPPED_"
* "aaa_STRIPPED_bbb", "a", "" -> "_STRIPPED_bbb"
* "aaa_STRIPPED_bbb", "a", null -> "_STRIPPED_bbb"
*
* // special test
* "aaaaaabbb", "aaa", null -> "bbb"
* "aaaaaaabbb", "aa", null -> "abbb"
*
* "aaaaaaaaa", "aaa", "aa" -> ""
* "a", "a", "a" -> ""
* }</pre>
*
* @param charSequence 被处理的字符串
* @return 处理后的字符串
* @since 5.8.30
*/
private String stripAll(final CharSequence charSequence) {
if (StrUtil.isEmpty(charSequence)) {
return StrUtil.toStringOrNull(charSequence);
}
final String str = charSequence.toString();
int from = 0;
int to = str.length();
if (StrUtil.isNotEmpty(this.prefix)) {
while (startWith(str, this.prefix, from)) {
from += this.prefix.length();
if (from == to) {
// "a", "a", "a" -> ""
return StrUtil.EMPTY;
}
}
}
if (StrUtil.isNotEmpty(suffix)) {
final int suffixLength = this.suffix.length();
while (startWith(str, suffix, to - suffixLength)) {
to -= suffixLength;
if (from == to) {
// "a", "a", "a" -> ""
return StrUtil.EMPTY;
} else if (to < from) {
// pre去除后和suffix有重叠 ("aba", "ab", "ba") -> "a"
to += suffixLength;
break;
}
}
}
return str.substring(from, to);
}
/**
* 判断是否以指定前缀开头
*
* @param charSequence 被检查的字符串
* @param from 开始位置
* @return 是否以指定前缀开头
*/
private boolean startWith(final CharSequence charSequence, final CharSequence strToCheck, final int from) {
return new StrRegionMatcher(this.ignoreCase, false, from)
.test(charSequence, strToCheck);
}
/**
* 判断是否以指定后缀结尾
*
* @param charSequence 被检查的字符串
* @return 是否以指定后缀结尾
*/
private boolean endWithSuffix(final CharSequence charSequence) {
return StrUtil.isNotEmpty(suffix) && StrUtil.endWith(charSequence, suffix, ignoreCase);
}
}

View File

@ -0,0 +1,59 @@
/*
* Copyright (c) 2024 Hutool Team and hutool.cn
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.dromara.hutool.core.text;
import org.junit.jupiter.api.Test;
import static org.junit.jupiter.api.Assertions.assertEquals;
public class StrStripperTest {
@Test
void stripAllPrefixTest() {
final StrStripper prefixStripper = new StrStripper("a", null, false, true);
assertEquals("_STRIPPED_bbb", prefixStripper.apply("aaa_STRIPPED_bbb"));
// 不忽略大小写则不替换
assertEquals("AAA_STRIPPED_bbb", prefixStripper.apply("AAA_STRIPPED_bbb"));
}
@Test
void stripAllSuffixTest() {
final StrStripper suffixStripper = new StrStripper(null, "b", false, true);
assertEquals("aaa_STRIPPED_", suffixStripper.apply("aaa_STRIPPED_bbb"));
// 不忽略大小写则不替换
assertEquals("aaa_STRIPPED_BBB", suffixStripper.apply("aaa_STRIPPED_BBB"));
}
@Test
void stripAllPrefixIgnoreCaseTest() {
final StrStripper prefixStripper = new StrStripper("A", null, true, true);
assertEquals("_STRIPPED_bbb", prefixStripper.apply("aaa_STRIPPED_bbb"));
assertEquals("_STRIPPED_bbb", prefixStripper.apply("Aaa_STRIPPED_bbb"));
assertEquals("_STRIPPED_bbb", prefixStripper.apply("AAA_STRIPPED_bbb"));
assertEquals("_STRIPPED_bbb", prefixStripper.apply("aaA_STRIPPED_bbb"));
}
@Test
void stripAllSuffixIgnoreCaseTest() {
final StrStripper prefixStripper = new StrStripper(null, "B", true, true);
assertEquals("aaa_STRIPPED_", prefixStripper.apply("aaa_STRIPPED_bbb"));
assertEquals("aaa_STRIPPED_", prefixStripper.apply("aaa_STRIPPED_Bbb"));
assertEquals("aaa_STRIPPED_", prefixStripper.apply("aaa_STRIPPED_BBB"));
assertEquals("aaa_STRIPPED_", prefixStripper.apply("aaa_STRIPPED_bbB"));
}
}