问题确认

确认JavaMail以及后续的Jakarta Mail均存在解码问题。主要存在于邮件标题的解码部分。涉及到一下几个主要情况

同一个中文文字在标题栏编码后进行了换行方案：先解码，最终合并再转换为正确的字符串
在编码前已经存在了部分文字方案：编码申明之前的数据需要保存下来，而不是直接将整个字符串认为是原始数据。可以使用正则匹配来识别需要保存的编码等。
还有一种就是标题本身没有额外编码，但是没有说明编码导致了问题
使用apache-mime4j来进行解码，但其可应对的情况优先，生需要自己额外处理
有些邮件编码没有使用mime编码，但是又不是UTF8编码，这时需要使用juniversalchardet识别编码

解决方案：

注意：以下代码可能存在资源泄漏，仅作为demo演示。

示例代码，关注其中的decodeString函数

package org.example;

import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.lang.reflect.Array;
import java.lang.reflect.Method;
import java.nio.charset.Charset;
import java.util.*;

import jakarta.mail.*;
import jakarta.mail.internet.MimeBodyPart;
import jakarta.mail.internet.MimeMessage;
import jakarta.mail.internet.MimeMultipart;
import jakarta.mail.internet.MimePart;
import javafx.util.Pair;
import org.apache.james.mime4j.codec.DecodeMonitor;
import org.apache.james.mime4j.codec.DecoderUtil;
import org.eclipse.angus.mail.util.BASE64DecoderStream;
import org.mozilla.universalchardet.UniversalDetector;


import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class GetRawEmail {
    static Method mReplaceUnderscores;
    static Method mDecodeQuotedPrintable;
    static Method mDecodeBase64;

    static Method mGetFileName;

    public static void initDecoder() throws  NoSuchMethodException{
        mReplaceUnderscores = DecoderUtil.class.getDeclaredMethod("replaceUnderscores", String.class);
        mReplaceUnderscores.setAccessible(true); //if security settings allow this

        mDecodeQuotedPrintable = DecoderUtil.class.getDeclaredMethod("decodeQuotedPrintable", String.class, DecodeMonitor.class);
        mDecodeQuotedPrintable.setAccessible(true); //if security settings allow this

        mDecodeBase64 = DecoderUtil.class.getDeclaredMethod("decodeBase64", String.class, DecodeMonitor.class);
        mDecodeBase64.setAccessible(true);

        mGetFileName = MimeBodyPart.class.getDeclaredMethod( "getFileName", MimePart.class);
        mGetFileName.setAccessible(true);
    }

    public static Pair<String, byte[]> decodeStringImp(String encoded){
        try{
            String patternStr = "=\\?(\\S+)\\?(\\S)\\?(\\S*)\\?=";
            Pattern pattern = Pattern.compile(patternStr);
            Matcher matcher = pattern.matcher(encoded);
            ArrayList<ArrayList<String> > matches = new ArrayList<>();
            while (matcher.find()){
                ArrayList<String> items = new ArrayList<>();
                for (int i = 1; i <= matcher.groupCount(); i++){
                    items.add( matcher.group(i) );
                }
                if( items.size() == 3) matches.add( items);
            }

            int len = 0;
            ArrayList<byte[]> bytesArray = new ArrayList<>();
            String encode = matches.get(0).get(0);
            for ( ArrayList<String> items: matches) {
                String type = items.get(1);
                String buf = items.get(2);

                String encodedText = (String)mReplaceUnderscores.invoke(null, buf);
                if( type.equals("B") || type.equals("b")){
                    byte[] decoded = (byte[])mDecodeBase64.invoke(null, encodedText, DecodeMonitor.SILENT);
                    len += decoded.length;
                    bytesArray.add(decoded);
                } else if( type.equals("Q") || type.equals("q")){
                    byte[] decoded = (byte[])mDecodeQuotedPrintable.invoke(null, encodedText, DecodeMonitor.SILENT);
                    len += decoded.length;
                    bytesArray.add(decoded);
                }
            }
            if( bytesArray.isEmpty()) return new Pair( "", encoded.getBytes());

            byte[] decodedBytes = new byte[len];
            int index = 0;
            for ( byte[] bytes: bytesArray) {
                System.arraycopy( bytes, 0, decodedBytes, index, bytes.length);
                index += bytes.length;
            }
            return new Pair(encode, decodedBytes);
        }
        catch (Exception ex){
            System.out.println(ex.getMessage());
        }
        return new Pair( "", encoded.getBytes());
    }

    public static String decodeString_1(String encoded) {
        try{
            Pair<String, byte[]> p = decodeStringImp(encoded);
            String decodedString = new String( p.getValue(), p.getKey());
            return decodedString;
        } catch(Exception ex){
            System.out.println(ex.getMessage());
        }
        return encoded;
    }

    public static String decodeString(String encoded){
        String prefix = "=?";
        String seperator = "?";
        String suffix = "?=";


        try{
            // 分割字符串
            int from_index = 0;
            String prefix_string = "";
            ArrayList<String> lines = new ArrayList<>();
            while(true){
                // 查找示例 "=?GBK?Q?6057013719-=D6=D0=C8=DA-=C8=D5=BD=F8=B6=B7?="
                int line_from = encoded.indexOf(prefix, from_index);
                if( line_from == -1) break;
                if( lines.isEmpty()){
                    // 第一行
                    prefix_string = encoded.substring(from_index, line_from);
                }

                int seperator_index = encoded.indexOf(seperator, line_from+2);
                if( seperator_index == -1) return encoded;
                seperator_index = encoded.indexOf(seperator, seperator_index+1);
                if( seperator_index == -1) return encoded;

                int line_to = encoded.indexOf(suffix, seperator_index+1);
                if( line_to == -1) return encoded;

                from_index = line_to+2;
                lines.add( encoded.substring(line_from, line_to+2));
            }
            if( lines.isEmpty()) return encoded;
            ArrayList< byte[]> bytesArray = new ArrayList<>();
            ArrayList< String> encodings = new ArrayList<>();

            int len = 0;
            for ( String line: lines) {
                Pair<String, byte[]> p = decodeStringImp(line);
                len += p.getValue().length;
                bytesArray.add(p.getValue());
                encodings.add( p.getKey());
            }

            String rev = "";
            byte[] decodedBytes = new byte[len];
            int index = 0;
            int last_decode_from = 0;
            int last_decode_index = 0;

            for(int i = 0; i < bytesArray.size(); i++ ){
                byte[] bytes = bytesArray.get(i);
                System.arraycopy(bytes, 0, decodedBytes, index, bytes.length);
                index += bytes.length;
            }
            rev += prefix_string;
            String decodedString = new String( decodedBytes, encodings.get(0));
            rev += decodedString;

            return rev;
        }
        catch( Exception ex){
            System.out.println(ex.getMessage());
        }
        return encoded;
    }


    public static String DecodeBString(String bstring) {
        return decodeString(bstring);
    }

    public static String DecodeQString(String qstring) {
        return decodeString(qstring);
    }

    public static String GetStringByGuessEncoding(String subjectString){
        try {
            byte[] latin1 = subjectString.getBytes("Latin1");
            UniversalDetector ud = new UniversalDetector();
            ud.handleData(latin1);
            ud.dataEnd();
            String charset = ud.getDetectedCharset();
            return new String(latin1, charset);
        } catch (UnsupportedEncodingException e) {
            System.out.println(e.getMessage());
        }
        return subjectString;
    }

    public static void GetEmail(String[] args) throws Exception {
        //创建连接属性
        Properties props = new Properties();
        props.setProperty("mail.store.protocol", "imap");
        props.setProperty("mail.imap.host", "imap.263.net");
        props.setProperty("mail.imap.port", "993");
        props.setProperty("mail.imap.ssl.enable", "true");
        //props.setProperty("mail.imap.starttls.enable", "true");

        //创建Session
        Session session = Session.getInstance(props);

        //创建Store
        Store store = session.getStore("imap");
        store.connect("imap.263.net", 993,"xujinping@zritc.com", "123@zrt");

        //打开收件箱
        Folder inbox = store.getFolder("INBOX");
        inbox.open(Folder.READ_ONLY);

        //获取最新的邮件
        int count = inbox.getMessageCount();
        //Message message = messages[messages.length - 1];
        //for(int i = count -1; i >=0; i--)
        for(int i = 34795; i >=0; i--)
        {
            if( i % 100 == 0) System.out.println( "processing " + String.valueOf(i));
            Message message = inbox.getMessage(i);

            MimeMessage mimeMessage = (MimeMessage) message;

            String subjects[] = mimeMessage.getHeader("Subject");
            if( true || subjects[0].contains("?GBK?B?") ) {
                System.out.println( "message index:" + String.valueOf(i) );
                String subject = GetStringByGuessEncoding( subjects[0]);
                Enumeration<String> rrr = mimeMessage.getAllHeaderLines();
                subject = decodeString(subject);
                System.out.println("Origin: " + subjects[0]);
                System.out.println("Subject: " + subject);
                String mimeFilename = (String)mGetFileName.invoke(null, mimeMessage);
            }

            MimeMultipart content = (MimeMultipart)mimeMessage.getContent();
            for(int bpi = 0; bpi != content.getCount(); bpi++){
                BodyPart bp = content.getBodyPart(bpi);
                String filename = bp.getFileName();
                if( filename != null && !filename.isEmpty()){
                    FileOutputStream bpf = new FileOutputStream(filename);
                    InputStream base64S = (InputStream)bp.getContent();
                    byte[] buff = new byte[1024*1024];
                    for(int rlen = 0; rlen != -1; ){
                        rlen = base64S.read(buff);
                        if( rlen != -1) bpf.write(buff, 0, rlen);
                     }
                    System.out.println( "BodyPart[" + String.valueOf(bpi) + "]: " + filename);
                }
            }
         }

        //关闭连接
        inbox.close(false);
        store.close();
    }

    public static void main(String[] args) throws Exception {
        initDecoder();
        GetEmail(args);
    }

    }

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

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

package org.example;

import java.io.FileOutputStream;

import java.io.InputStream;

import java.io.UnsupportedEncodingException;

import java.lang.reflect.Array;

import java.lang.reflect.Method;

import java.nio.charset.Charset;

import java.util.*;

import jakarta.mail.*;

import jakarta.mail.internet.MimeBodyPart;

import jakarta.mail.internet.MimeMessage;

import jakarta.mail.internet.MimeMultipart;

import jakarta.mail.internet.MimePart;

import javafx.util.Pair;

import org.apache.james.mime4j.codec.DecodeMonitor;

import org.apache.james.mime4j.codec.DecoderUtil;

import org.eclipse.angus.mail.util.BASE64DecoderStream;

import org.mozilla.universalchardet.UniversalDetector;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

public class GetRawEmail {

static Method mReplaceUnderscores;

static Method mDecodeQuotedPrintable;

static Method mDecodeBase64;

static Method mGetFileName;

public static void initDecoder() throws NoSuchMethodException{

mReplaceUnderscores = DecoderUtil.class.getDeclaredMethod("replaceUnderscores", String.class);

mReplaceUnderscores.setAccessible(true); //if security settings allow this

mDecodeQuotedPrintable = DecoderUtil.class.getDeclaredMethod("decodeQuotedPrintable", String.class, DecodeMonitor.class);

mDecodeQuotedPrintable.setAccessible(true); //if security settings allow this

mDecodeBase64 = DecoderUtil.class.getDeclaredMethod("decodeBase64", String.class, DecodeMonitor.class);

mDecodeBase64.setAccessible(true);

mGetFileName = MimeBodyPart.class.getDeclaredMethod( "getFileName", MimePart.class);

mGetFileName.setAccessible(true);

}

public static Pair<String, byte[]> decodeStringImp(String encoded){

try{

String patternStr = "=\\?(\\S+)\\?(\\S)\\?(\\S*)\\?=";

Pattern pattern = Pattern.compile(patternStr);

Matcher matcher = pattern.matcher(encoded);

ArrayList<ArrayList<String> > matches = new ArrayList<>();

while (matcher.find()){

ArrayList<String> items = new ArrayList<>();

for (int i = 1; i <= matcher.groupCount(); i++){

items.add( matcher.group(i) );

}

if( items.size() == 3) matches.add( items);

}

int len = 0;

ArrayList<byte[]> bytesArray = new ArrayList<>();

String encode = matches.get(0).get(0);

for ( ArrayList<String> items: matches) {

String type = items.get(1);

String buf = items.get(2);

String encodedText = (String)mReplaceUnderscores.invoke(null, buf);

if( type.equals("B") || type.equals("b")){

byte[] decoded = (byte[])mDecodeBase64.invoke(null, encodedText, DecodeMonitor.SILENT);

len += decoded.length;

bytesArray.add(decoded);

} else if( type.equals("Q") || type.equals("q")){

byte[] decoded = (byte[])mDecodeQuotedPrintable.invoke(null, encodedText, DecodeMonitor.SILENT);

len += decoded.length;

bytesArray.add(decoded);

}

if( bytesArray.isEmpty()) return new Pair( "", encoded.getBytes());

byte[] decodedBytes = new byte[len];

int index = 0;

for ( byte[] bytes: bytesArray) {

System.arraycopy( bytes, 0, decodedBytes, index, bytes.length);

index += bytes.length;

}

return new Pair(encode, decodedBytes);

}

catch (Exception ex){

System.out.println(ex.getMessage());

}

return new Pair( "", encoded.getBytes());

}

public static String decodeString_1(String encoded) {

try{

Pair<String, byte[]> p = decodeStringImp(encoded);

String decodedString = new String( p.getValue(), p.getKey());

return decodedString;

} catch(Exception ex){

System.out.println(ex.getMessage());

}

return encoded;

}

public static String decodeString(String encoded){

String prefix = "=?";

String seperator = "?";

String suffix = "?=";

try{

// 分割字符串

int from_index = 0;

String prefix_string = "";

ArrayList<String> lines = new ArrayList<>();

while(true){

// 查找示例 "=?GBK?Q?6057013719-=D6=D0=C8=DA-=C8=D5=BD=F8=B6=B7?="

int line_from = encoded.indexOf(prefix, from_index);

if( line_from == -1) break;

if( lines.isEmpty()){

// 第一行

prefix_string = encoded.substring(from_index, line_from);

}

int seperator_index = encoded.indexOf(seperator, line_from+2);

if( seperator_index == -1) return encoded;

seperator_index = encoded.indexOf(seperator, seperator_index+1);

if( seperator_index == -1) return encoded;

int line_to = encoded.indexOf(suffix, seperator_index+1);

if( line_to == -1) return encoded;

from_index = line_to+2;

lines.add( encoded.substring(line_from, line_to+2));

}

if( lines.isEmpty()) return encoded;

ArrayList< byte[]> bytesArray = new ArrayList<>();

ArrayList< String> encodings = new ArrayList<>();

int len = 0;

for ( String line: lines) {

Pair<String, byte[]> p = decodeStringImp(line);

len += p.getValue().length;

bytesArray.add(p.getValue());

encodings.add( p.getKey());

}

String rev = "";

byte[] decodedBytes = new byte[len];

int index = 0;

int last_decode_from = 0;

int last_decode_index = 0;

for(int i = 0; i < bytesArray.size(); i++ ){

byte[] bytes = bytesArray.get(i);

System.arraycopy(bytes, 0, decodedBytes, index, bytes.length);

index += bytes.length;

}

rev += prefix_string;

String decodedString = new String( decodedBytes, encodings.get(0));

rev += decodedString;

return rev;

}

catch( Exception ex){

System.out.println(ex.getMessage());

}

return encoded;

}

public static String DecodeBString(String bstring) {

return decodeString(bstring);

}

public static String DecodeQString(String qstring) {

return decodeString(qstring);

}

public static String GetStringByGuessEncoding(String subjectString){

try {

byte[] latin1 = subjectString.getBytes("Latin1");

UniversalDetector ud = new UniversalDetector();

ud.handleData(latin1);

ud.dataEnd();

String charset = ud.getDetectedCharset();

return new String(latin1, charset);

} catch (UnsupportedEncodingException e) {

System.out.println(e.getMessage());

}

return subjectString;

}

public static void GetEmail(String[] args) throws Exception {

//创建连接属性

Properties props = new Properties();

props.setProperty("mail.store.protocol", "imap");

props.setProperty("mail.imap.host", "imap.263.net");

props.setProperty("mail.imap.port", "993");

props.setProperty("mail.imap.ssl.enable", "true");

//props.setProperty("mail.imap.starttls.enable", "true");

//创建Session

Session session = Session.getInstance(props);

//创建Store

Store store = session.getStore("imap");

store.connect("imap.263.net", 993,"xujinping@zritc.com", "123@zrt");

//打开收件箱

Folder inbox = store.getFolder("INBOX");

inbox.open(Folder.READ_ONLY);

//获取最新的邮件

int count = inbox.getMessageCount();

//Message message = messages[messages.length - 1];

//for(int i = count -1; i >=0; i--)

for(int i = 34795; i >=0; i--)

{

if( i % 100 == 0) System.out.println( "processing " + String.valueOf(i));

Message message = inbox.getMessage(i);

MimeMessage mimeMessage = (MimeMessage) message;

String subjects[] = mimeMessage.getHeader("Subject");

if( true || subjects[0].contains("?GBK?B?") ) {

System.out.println( "message index:" + String.valueOf(i) );

String subject = GetStringByGuessEncoding( subjects[0]);

Enumeration<String> rrr = mimeMessage.getAllHeaderLines();

subject = decodeString(subject);

System.out.println("Origin: " + subjects[0]);

System.out.println("Subject: " + subject);

String mimeFilename = (String)mGetFileName.invoke(null, mimeMessage);

}

MimeMultipart content = (MimeMultipart)mimeMessage.getContent();

for(int bpi = 0; bpi != content.getCount(); bpi++){

BodyPart bp = content.getBodyPart(bpi);

String filename = bp.getFileName();

if( filename != null && !filename.isEmpty()){

FileOutputStream bpf = new FileOutputStream(filename);

InputStream base64S = (InputStream)bp.getContent();

byte[] buff = new byte[1024*1024];

for(int rlen = 0; rlen != -1; ){

rlen = base64S.read(buff);

if( rlen != -1) bpf.write(buff, 0, rlen);

}

System.out.println( "BodyPart[" + String.valueOf(bpi) + "]: " + filename);

}

//关闭连接

inbox.close(false);

store.close();

}

public static void main(String[] args) throws Exception {

initDecoder();

GetEmail(args);

}

其中使用到的packages

<dependencies>
        <dependency>
            <groupId>jakarta.mail</groupId>
            <artifactId>jakarta.mail-api</artifactId>
            <version>2.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.eclipse.angus</groupId>
            <artifactId>angus-mail</artifactId>
            <version>2.0.1</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.13.2</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.james</groupId>
            <artifactId>apache-mime4j-james-utils</artifactId>
            <version>0.8.9</version>
        </dependency>
        <dependency>
            <groupId>com.github.albfernandez</groupId>
            <artifactId>juniversalchardet</artifactId>
            <version>2.4.0</version>
        </dependency>
</dependencies>

<groupId>jakarta.mail</groupId>

<artifactId>jakarta.mail-api</artifactId>

</dependency>

<groupId>org.eclipse.angus</groupId>

<artifactId>angus-mail</artifactId>

</dependency>

<groupId>junit</groupId>

<artifactId>junit</artifactId>

</dependency>

<groupId>org.apache.james</groupId>

<artifactId>apache-mime4j-james-utils</artifactId>

</dependency>

<groupId>com.github.albfernandez</groupId>

<artifactId>juniversalchardet</artifactId>

</dependency>

</dependencies>

解决Java Mail邮件标题乱码

问题确认

解决方案：

发表回复取消回复

解决Java Mail邮件标题乱码

问题确认

解决方案：

发表回复 取消回复

发表回复取消回复