gts

hutool-extra/src/main/java/cn/hutool/extra/compress/extractor/Extractor.java

@@ -1,9 +1,11 @@
 package cn.hutool.extra.compress.extractor;
 
+import cn.hutool.core.text.StrUtil;
 import org.apache.commons.compress.archivers.ArchiveEntry;
 
 import java.io.Closeable;
 import java.io.File;
+import java.io.InputStream;
 import java.util.function.Predicate;
 
 /**
@@ -31,6 +33,24 @@ public interface Extractor extends Closeable {
 	 */
 	void extract(File targetDir, Predicate<ArchiveEntry> predicate);
 
+	/**
+	 * 获取指定名称的文件流
+	 *
+	 * @param entryName entry名称
+	 * @return 文件流，无文件返回{@code null}
+	 */
+	default InputStream get(final String entryName) {
+		return getFirst((entry) -> StrUtil.equals(entryName, entry.getName()));
+	}
+
+	/**
+	 * 获取满足指定过滤要求的压缩包内的第一个文件流
+	 *
+	 * @param predicate 用于指定需要释放的文件，null表示不过滤。当{@link Predicate#test(Object)}为{@code true}返回对应流。
+	 * @return 满足过滤要求的第一个文件的流, 无满足条件的文件返回{@code null}
+	 */
+	InputStream getFirst(final Predicate<ArchiveEntry> predicate);
+
 	/**
 	 * 无异常关闭
 	 */

hutool-extra/src/main/java/cn/hutool/extra/compress/extractor/Seven7EntryInputStream.java

@@ -25,8 +25,18 @@ public class Seven7EntryInputStream extends InputStream {
 	 * @param entry      {@link SevenZArchiveEntry}
 	 */
 	public Seven7EntryInputStream(final SevenZFile sevenZFile, final SevenZArchiveEntry entry) {
+		this(sevenZFile, entry.getSize());
+	}
+
+	/**
+	 * 构造
+	 *
+	 * @param sevenZFile {@link SevenZFile}
+	 * @param size       读取长度
+	 */
+	public Seven7EntryInputStream(final SevenZFile sevenZFile, final long size) {
 		this.sevenZFile = sevenZFile;
-		this.size = entry.getSize();
+		this.size = size;
 	}
 
 	@Override

hutool-extra/src/main/java/cn/hutool/extra/compress/extractor/SevenZExtractor.java

@@ -1,10 +1,9 @@
 package cn.hutool.extra.compress.extractor;
 
-import cn.hutool.core.io.file.FileUtil;
 import cn.hutool.core.io.IORuntimeException;
 import cn.hutool.core.io.IoUtil;
+import cn.hutool.core.io.file.FileUtil;
 import cn.hutool.core.lang.Assert;
-import cn.hutool.core.text.StrUtil;
 import org.apache.commons.compress.archivers.ArchiveEntry;
 import org.apache.commons.compress.archivers.sevenz.SevenZArchiveEntry;
 import org.apache.commons.compress.archivers.sevenz.SevenZFile;
@@ -103,13 +102,7 @@ public class SevenZExtractor implements Extractor, RandomAccess {
 		}
 	}
 
-	/**
+	@Override
-	 * 获取满足指定过滤要求的压缩包内的第一个文件流
-	 *
-	 * @param predicate 用于指定需要释放的文件，null表示不过滤。当{@link Predicate#test(Object)}为{@code true}返回对应流。
-	 * @return 满足过滤要求的第一个文件的流, 无满足条件的文件返回{@code null}
-	 * @since 5.7.14
-	 */
 	public InputStream getFirst(final Predicate<ArchiveEntry> predicate) {
 		final SevenZFile sevenZFile = this.sevenZFile;
 		for (final SevenZArchiveEntry entry : sevenZFile.getEntries()) {
@@ -121,6 +114,7 @@ public class SevenZExtractor implements Extractor, RandomAccess {
 			}
 
 			try {
+				// 此处使用查找entry对应Stream方式，由于只调用一次，也只遍历一次
 				return sevenZFile.getInputStream(entry);
 			} catch (final IOException e) {
 				throw new IORuntimeException(e);
@@ -130,17 +124,6 @@ public class SevenZExtractor implements Extractor, RandomAccess {
 		return null;
 	}
 
-	/**
-	 * 获取指定名称的文件流
-	 *
-	 * @param entryName entry名称
-	 * @return 文件流，无文件返回{@code null}
-	 * @since 5.7.14
-	 */
-	public InputStream get(final String entryName) {
-		return getFirst((entry) -> StrUtil.equals(entryName, entry.getName()));
-	}
-
 	/**
 	 * 释放（解压）到指定目录
 	 *
@@ -153,7 +136,7 @@ public class SevenZExtractor implements Extractor, RandomAccess {
 		final SevenZFile sevenZFile = this.sevenZFile;
 		SevenZArchiveEntry entry;
 		File outItemFile;
-		while (null != (entry = this.sevenZFile.getNextEntry())) {
+		while (null != (entry = sevenZFile.getNextEntry())) {
 			if (null != predicate && false == predicate.test(entry)) {
 				continue;
 			}
@@ -164,6 +147,7 @@ public class SevenZExtractor implements Extractor, RandomAccess {
 				outItemFile.mkdirs();
 			} else if (entry.hasStream()) {
 				// 读取entry对应数据流
+				// 此处直接读取而非调用sevenZFile.getInputStream(entry)，因为此方法需要遍历查找entry对应位置，性能不好。
 				FileUtil.writeFromStream(new Seven7EntryInputStream(sevenZFile, entry), outItemFile);
 			} else {
 				// 无数据流的文件创建为空文件

hutool-extra/src/main/java/cn/hutool/extra/compress/extractor/StreamExtractor.java

@@ -68,7 +68,7 @@ public class StreamExtractor implements Extractor {
 	 * @param in           包流
 	 */
 	public StreamExtractor(final Charset charset, final String archiverName, InputStream in) {
-		if(in instanceof ArchiveInputStream){
+		if (in instanceof ArchiveInputStream) {
 			this.in = (ArchiveInputStream) in;
 			return;
 		}
@@ -78,7 +78,7 @@ public class StreamExtractor implements Extractor {
 			in = IoUtil.toBuffered(in);
 			if (StrUtil.isBlank(archiverName)) {
 				this.in = factory.createArchiveInputStream(in);
-			} else if("tgz".equalsIgnoreCase(archiverName) || "tar.gz".equalsIgnoreCase(archiverName)){
+			} else if ("tgz".equalsIgnoreCase(archiverName) || "tar.gz".equalsIgnoreCase(archiverName)) {
 				//issue#I5J33E，支持tgz格式解压
 				try {
 					this.in = new TarArchiveInputStream(new GzipCompressorInputStream(in));
@@ -95,6 +95,29 @@ public class StreamExtractor implements Extractor {
 		}
 	}
 
+	@Override
+	public InputStream getFirst(final Predicate<ArchiveEntry> predicate) {
+		final ArchiveInputStream in = this.in;
+		ArchiveEntry entry;
+		try {
+			while (null != (entry = in.getNextEntry())) {
+				if (null != predicate && false == predicate.test(entry)) {
+					continue;
+				}
+				if (entry.isDirectory() || false == in.canReadEntryData(entry)) {
+					// 目录或无法读取的文件直接跳过
+					continue;
+				}
+
+				return in;
+			}
+		} catch (final IOException e) {
+			throw new IORuntimeException(e);
+		}
+
+		return null;
+	}
+
 	/**
 	 * 释放（解压）到指定目录，结束后自动关闭流，此方法只能调用一次
 	 *