我一直在使用Spring的多部分上传器控制器来上传和存储压缩文件中的条目，但我发现occaisional PNG文件已被破坏，而不是在其byte []中使用类似“PNG ...”的内容，它以“fþ»ÀÃgÞÉ”或类似的方式开头。这似乎发生在每次运行的相同文件中。我使用java.util.ZipEntry尝试了所有这些，然后我尝试了Apache Compress，发现Apache将损坏的不同文件压缩到Java 7实用程序，但在后续运行中始终使用相同的文件。
代码（首先是java.util.zip.ZipEntry）：
protected void processZipFile(String path, MultipartFile file, String signature) throws IOException {
DateFormat df = new SimpleDateFormat("yyyyMMddhhmmss");
File tempFile = new File(System.getProperty("user.dir") + "/" + file.getName() + df.format(new Date()));
file.transferTo(tempFile);
ZipFile zipFile = null;
try {
zipFile = new ZipFile(tempFile);
LOG.debug("Processing archive with name={}, size={}.", file.getName(), file.getSize());
final Enumeration<? extends ZipEntry> entries = zipFile.entries();
while ( entries.hasMoreElements() )
{
ZipEntry entry = entries.nextElement();
LOG.debug("Processing file={} is directory?={}.", entry.getName(), entry.isDirectory());
// we don't bother processing directories, and we don't process any resource fork info
// from Mac OS X (which does not seem to be transparent to ZipFile).
if (!(entry.isDirectory() || entry.getName().contains("__MACOSX") || entry.getName().contains(".DS_Store"))) {
// if the entry is a file, extract it
Content contentToSave = null;
if(entry.getName().contains("gif") || entry.getName().contains("png") || entry.getName().contains("jpeg")) {
byte[] bytes = readInputStream( zipFile.getInputStream( entry ), entry.getSize() );
LOG.debug("{} is of inflated-length={} from compressed-length={}",
entry.getName(), bytes.length, entry.getCompressedSize());
if(entry.getName().contains("gif")) {
contentToSave = Content.makeImage(path + entry.getName(), Content.GIF, signature, bytes);
} else if (entry.getName().contains("png")) {
contentToSave = Content.makeImage(path + entry.getName(), Content.PNG, signature, bytes);
} else if (entry.getName().contains("jpeg")) {
contentToSave = Content.makeImage(path + entry.getName(), Content.JPEG, signature, bytes);
}
} else {
InputStream is = zipFile.getInputStream(entry);
if (entry.getName().contains("json")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.JSON, signature, convertStreamToString(is));
} else if (entry.getName().contains("js")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.JS, signature, convertStreamToString(is));
} else if (entry.getName().contains("css")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.CSS, signature, convertStreamToString(is));
} else if (entry.getName().contains("xml")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.XML, signature, convertStreamToString(is));
} else if (entry.getName().contains("html")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.HTML, signature, convertStreamToString(is));
}
}
contentService.putOrReplace(contentToSave);
LOG.info("Persisted file: {} from uploaded version.", contentToSave.getName());
}
}
} catch (ZipException e) {
// If I can't create a ZipFile, then this is not a zip file at all and it cannot be processed
// by this method. Its pretty dumb that there's no way to determine whether the contents are zipped through
// the ZipFile API, but that's just one of its many problems.
e.printStackTrace();
LOG.error("{} is not a zipped file, or it is empty", file.getName());
} finally {
zipFile = null;
}
tempFile.delete();
}
现在org.apache.commons.compress.archivers.zip.ZipFile也是如此：
protected void processZipFile(String path, MultipartFile file, String signature) throws IOException {
DateFormat df = new SimpleDateFormat("yyyyMMddhhmmss");
File tempFile = new File(System.getProperty("user.dir") + "/" + file.getName() + df.format(new Date()));
file.transferTo(tempFile);
ZipFile zipFile = null;
try {
zipFile = new ZipFile(tempFile);
LOG.debug("Processing archive with name={}, size={}.", file.getName(), file.getSize());
final Enumeration<? extends ZipArchiveEntry> entries = zipFile.getEntries();
while ( entries.hasMoreElements() ) {
ZipArchiveEntry entry = entries.nextElement();
LOG.debug("Processing file={} is directory?={}.", entry.getName(), entry.isDirectory());
// we don't bother processing directories, and we don't process any resource fork info
// from Mac OS X (which does not seem to be transparent to ZipFile).
if (!(entry.isDirectory() || entry.getName().contains("__MACOSX") || entry.getName().contains(".DS_Store"))) {
// if the entry is a file, extract it
Content contentToSave = null;
if(entry.getName().contains("gif") || entry.getName().contains("png") || entry.getName().contains("jpeg")) {
byte[] bytes = readInputStream( zipFile.getInputStream( entry ), entry.getSize() );
LOG.debug("{} is of inflated-length={} from compressed-length={}",
entry.getName(), bytes.length, entry.getCompressedSize());
if(entry.getName().contains("gif")) {
contentToSave = Content.makeImage(path + entry.getName(), Content.GIF, signature, bytes);
} else if (entry.getName().contains("png")) {
contentToSave = Content.makeImage(path + entry.getName(), Content.PNG, signature, bytes);
} else if (entry.getName().contains("jpeg")) {
contentToSave = Content.makeImage(path + entry.getName(), Content.JPEG, signature, bytes);
}
} else {
InputStream is = zipFile.getInputStream(entry);
if (entry.getName().contains("json")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.JSON, signature, convertStreamToString(is));
} else if (entry.getName().contains("js")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.JS, signature, convertStreamToString(is));
} else if (entry.getName().contains("css")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.CSS, signature, convertStreamToString(is));
} else if (entry.getName().contains("xml")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.XML, signature, convertStreamToString(is));
} else if (entry.getName().contains("html")) {
contentToSave = Content.makeFile(path + entry.getName(), Content.HTML, signature, convertStreamToString(is));
}
}
contentService.putOrReplace(contentToSave);
LOG.info("Persisted file: {} from uploaded version.", contentToSave.getName());
}
}
} catch (ZipException e) {
e.printStackTrace();
LOG.error("{} is not a zipped file, or it is empty", file.getName());
} catch (IOException e) {
e.printStackTrace();
LOG.error("{} is not a file, or it is empty", file.getName());
} finally {
zipFile = null;
}
tempFile.delete();
}
这两种被称为方法的方法是：
private static byte[] readInputStream( final InputStream is, final long length ) throws IOException {
final byte[] buf = new byte[ (int) length ];
int read = 0;
int cntRead;
while ( ( cntRead = is.read( buf, 0, buf.length ) ) >=0 )
{
read += cntRead;
}
return buf;
}
和
public String convertStreamToString(InputStream is) throws IOException {
StringBuilder sb = new StringBuilder(2048);
char[] read = new char[128];
try (InputStreamReader ir = new InputStreamReader(is, StandardCharsets.UTF_8)) {
for (int i; -1 != (i = ir.read(read)); sb.append(read, 0, i));
}
// need to remove the ? at teh beginning of some files. This comes from the UTF8 BOM
// that is added to some files saved as UTF8
String out = sb.toString();
String utf8Bom = new String(new char[]{'\ufeff'});
if(out.contains(utf8Bom)) {
out = out.replace(utf8Bom,"");
}
return out;
}
第二个当然不太可能是问题的一部分。
我已经搜索过了，看起来已经发现了与此类似的问题，但它一直是一些外部问题。有谁知道为什么会这样？
我重新编辑了一些图像，发现如果我将图像更改为黑白，或者更改整个图像的色调，问题就会消失，但如果我添加边框或更改单一颜色问题遗迹。看起来某些文件中特定的字节排列会勾勒出Java自己和Apache压缩文件读取器使用的任何底层API中的错误，但这只是推测。
编辑：其他用法表明损坏发生在大小超过10K的gif中，所以这可能与bug有关吗？我试图在ReadInputStream（）调用中任意加倍缓冲区的大小，但除了在特殊大图像中溢出MySQL中的blob大小（49K变为98K，这太大了）之外什么也没做。
com.mysql.jdbc.MysqlDataTruncation: Data truncation: Data too long for column 'encoded_content' at row 1
答案 0 :(得分：0)
我的发现是，这个问题出现在“打包大小”的情况下。比实际大小大，这可能发生在png文件中，例如已经压缩过的＆＃39;他们自己。