-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathEncodingTransform.java
More file actions
4792 lines (4707 loc) · 175 KB
/
EncodingTransform.java
File metadata and controls
4792 lines (4707 loc) · 175 KB
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
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
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import java.io.*;
import java.nio.file.*;
import java.util.*;
import java.net.URL;
public class EncodingTransform {
public static void main(String args[]) {
String inputDir;
String outputDir;
String inputEncode;
String outputEncode;
if(args == null || args.length < 3) {
System.out.println("输入参数错误");
System.out.println("使用方法:");
System.out.println(" javac EncodingTransform.java");
System.out.println(" java EncodingTransform 输入目录 输出文件编码 要转换编码的文件后缀\n 文件后缀为.all时转换全部文件的编码");
System.out.println("比如:");
System.out.println(" java EncodingTransform Test/ utf-8 .all");
System.out.println(" 转换Test目录下的所有文件编码为utf-8");
return;
}
//参数判断
String[] filters = new String[args.length - 2];
inputDir = new File(args[0]).getAbsolutePath();
outputDir = inputDir + ".编码转换";
if(inputDir.endsWith(File.pathSeparator)) {
inputDir = inputDir.substring(0, inputDir.length() - 1);
}
outputEncode = args[1];
for(int i = 2; i < args.length; i++) {
filters[i - 2] = args[i];
}
System.out.println("输入路径：" + inputDir);
System.out.println("输出路径：" + outputDir);
System.out.println("输出文件编码：" + outputEncode);
System.out.println("要过滤的文件：" + Arrays.asList(filters));
transfrom(inputDir, outputDir, outputEncode, filters);
}
/**
*
* 编码转换
* 输入文件， 输出文件，输入文件编码，输出文件编码
*/
public static void transfrom(String inputDir, String outputDir, String outputEncode, String[] filters) {
List<File> inputAllFiles = new ArrayList<>();
obtainFiles(new File(inputDir), inputAllFiles);
for(File inputFile : inputAllFiles) {
String outputFilePath = outputDir + inputFile.getPath().substring(inputDir.length());
File outputFile = new File(outputFilePath);
//如果是目录则直接创建
if(inputFile.isDirectory()) {
outputFile.mkdirs();
System.out.println("dir");
continue;
}
//使用EncodingDetect获取输入文件的编码
String inputEncode = EncodingDetect.getJavaEncode(inputFile.getAbsolutePath());
try {
if( filterFile( inputFile.getName(), filters ) ) {
copy(inputFile, outputFile, inputEncode, outputEncode);
} else {
//非目标文件直接拷贝
outputFile.getParentFile().mkdirs();
outputFile.createNewFile();
Files.copy(inputFile.toPath(), outputFile.toPath(), StandardCopyOption.REPLACE_EXISTING, StandardCopyOption.COPY_ATTRIBUTES);
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
/**
*
* 检查filename是否以filters数组的某一个字符串元素结尾, 确定该文件是否需要转换编码
*
*/
public static boolean filterFile(String filename, String filters[]) {
for(int i = 0; i < filters.length; i++) {
if(filename.endsWith(filters[i]) || filename.endsWith(".all")) {
return true;
}
}
return false;
}
/**
*
*获取输入目录的所有文件
*
*/
public static void obtainFiles(File inputFile, List<File> list) {
System.out.println(inputFile.getAbsolutePath());
if(inputFile.isFile()) {
list.add(inputFile);
return;
}
if(inputFile.isDirectory()) {
File[] childFiles = inputFile.listFiles();
if(childFiles == null || childFiles.length == 0) {
list.add(inputFile);
return;
}
for(File file : inputFile.listFiles()) {
obtainFiles(file, list);
}
}
}
/**
*
*转换inputFile的编码后保存到outputFile
*
*/
public static void copy(File inputFile, File outputFile, String inputEncode, String outputEncode) throws IOException, FileNotFoundException{
InputStreamReader isr = null;
OutputStreamWriter osr = null;
outputFile.getParentFile().mkdirs();
outputFile.createNewFile();
isr = new InputStreamReader(new FileInputStream(inputFile), inputEncode);
osr = new OutputStreamWriter(new FileOutputStream(outputFile), outputEncode);
//每次读取1024字节
int readedLen = 0;
char[] cache = new char[1024];
try {
while((readedLen = isr.read(cache)) != -1) {
osr.write(cache, 0, readedLen);
osr.flush();
}
} finally {
isr.close();
osr.close();
}
}
}
/**
* <Detect encoding .>
* Copyright (C) <2009> <Fluck,ACC http://androidos.cc/dev>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* EncodingDetect.java<br>
* 自动获取文件的编码
* @author Billows.Van
* @since Create on 2010-01-27 11:19:00
* @version 1.0
*/
class EncodingDetect {
public static void main(String[] args) {
if(args.length != 1) {
System.out.println("参数错误：");
System.out.println("使用方法：");
System.out.println("java EncodingDetect 要检测的文件");
}
String file = args[0];
String encode=getJavaEncode(file);
System.out.println(encode);
}
/**
* 得到文件的编码
* @param filePath 文件路径
* @return 文件的编码
*/
public static String getJavaEncode(String filePath){
BytesEncodingDetect s = new BytesEncodingDetect();
String fileCode = BytesEncodingDetect.javaname[s.detectEncoding(new File(filePath))];
return fileCode;
}
public static void readFile(String file, String code) {
BufferedReader fr;
try {
String myCode = code!=null&&!"".equals(code) ? code : "UTF8";
InputStreamReader read = new InputStreamReader(new FileInputStream(
file), myCode);
fr = new BufferedReader(read);
String line = null;
int flag=1;
// 读取每一行，如果结束了，line会为空
while ((line = fr.readLine()) != null && line.trim().length() > 0) {
if(flag==1) {
line=line.substring(1);//去掉文件头
flag++;
}
// 每一行创建一个Student对象，并存入数组中
System.out.println(line);
}
fr.close();
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
class BytesEncodingDetect extends Encoding {
// Frequency tables to hold the GB, Big5, and EUC-TW character
// frequencies
int GBFreq[][];
int GBKFreq[][];
int Big5Freq[][];
int Big5PFreq[][];
int EUC_TWFreq[][];
int KRFreq[][];
int JPFreq[][];
// int UnicodeFreq[94][128];
// public static String[] nicename;
// public static String[] codings;
public boolean debug;
public BytesEncodingDetect() {
super();
debug = false;
GBFreq = new int[94][94];
GBKFreq = new int[126][191];
Big5Freq = new int[94][158];
Big5PFreq = new int[126][191];
EUC_TWFreq = new int[94][94];
KRFreq = new int[94][94];
JPFreq = new int[94][94];
// Initialize the Frequency Table for GB, GBK, Big5, EUC-TW, KR, JP
initialize_frequencies();
}
public static void main(String argc[]) {
BytesEncodingDetect sinodetector;
int result = OTHER;
int i;
sinodetector = new BytesEncodingDetect();
for (i = 0; i < argc.length; i++) {
if (argc[i].startsWith("http://") == true) {
try {
result = sinodetector.detectEncoding(new URL(argc[i]));
} catch (Exception e) {
System.err.println("Bad URL " + e.toString());
}
} else if (argc[i].equals("-d")) {
sinodetector.debug = true;
continue;
} else {
result = sinodetector.detectEncoding(new File(argc[i]));
}
System.out.println(nicename[result]);
}
}
/**
* Function : detectEncoding Aruguments: URL Returns : One of the encodings from the Encoding enumeration (GB2312, HZ, BIG5,
* EUC_TW, ASCII, or OTHER) Description: This function looks at the URL contents and assigns it a probability score for each
* encoding type. The encoding type with the highest probability is returned.
*/
public int detectEncoding(URL testurl) {
byte[] rawtext = new byte[10000];
int bytesread = 0, byteoffset = 0;
int guess = OTHER;
InputStream chinesestream;
try {
chinesestream = testurl.openStream();
while ((bytesread = chinesestream.read(rawtext, byteoffset, rawtext.length - byteoffset)) > 0) {
byteoffset += bytesread;
}
;
chinesestream.close();
guess = detectEncoding(rawtext);
} catch (Exception e) {
System.err.println("Error loading or using URL " + e.toString());
guess = -1;
}
return guess;
}
/**
* Function : detectEncoding Aruguments: File Returns : One of the encodings from the Encoding enumeration (GB2312, HZ, BIG5,
* EUC_TW, ASCII, or OTHER) Description: This function looks at the file and assigns it a probability score for each encoding
* type. The encoding type with the highest probability is returned.
*/
public int detectEncoding(File testfile) {
FileInputStream chinesefile;
byte[] rawtext;
rawtext = new byte[(int) testfile.length()];
try {
chinesefile = new FileInputStream(testfile);
chinesefile.read(rawtext);
chinesefile.close();
} catch (Exception e) {
System.err.println("Error: " + e);
}
return detectEncoding(rawtext);
}
/**
* Function : detectEncoding Aruguments: byte array Returns : One of the encodings from the Encoding enumeration (GB2312, HZ,
* BIG5, EUC_TW, ASCII, or OTHER) Description: This function looks at the byte array and assigns it a probability score for
* each encoding type. The encoding type with the highest probability is returned.
*/
public int detectEncoding(byte[] rawtext) {
int[] scores;
int index, maxscore = 0;
int encoding_guess = OTHER;
scores = new int[TOTALTYPES];
// Assign Scores
scores[GB2312] = gb2312_probability(rawtext);
scores[GBK] = gbk_probability(rawtext);
scores[GB18030] = gb18030_probability(rawtext);
scores[HZ] = hz_probability(rawtext);
scores[BIG5] = big5_probability(rawtext);
scores[CNS11643] = euc_tw_probability(rawtext);
scores[ISO2022CN] = iso_2022_cn_probability(rawtext);
scores[UTF8] = utf8_probability(rawtext);
scores[UNICODE] = utf16_probability(rawtext);
scores[EUC_KR] = euc_kr_probability(rawtext);
scores[CP949] = cp949_probability(rawtext);
scores[JOHAB] = 0;
scores[ISO2022KR] = iso_2022_kr_probability(rawtext);
scores[ASCII] = ascii_probability(rawtext);
scores[SJIS] = sjis_probability(rawtext);
scores[EUC_JP] = euc_jp_probability(rawtext);
scores[ISO2022JP] = iso_2022_jp_probability(rawtext);
scores[UNICODET] = 0;
scores[UNICODES] = 0;
scores[ISO2022CN_GB] = 0;
scores[ISO2022CN_CNS] = 0;
scores[OTHER] = 0;
// Tabulate Scores
for (index = 0; index < TOTALTYPES; index++) {
if (debug)
System.err.println("Encoding " + nicename[index] + " score " + scores[index]);
if (scores[index] > maxscore) {
encoding_guess = index;
maxscore = scores[index];
}
}
// Return OTHER if nothing scored above 50
if (maxscore <= 50) {
encoding_guess = OTHER;
}
return encoding_guess;
}
/*
* Function: gb2312_probability Argument: pointer to byte array Returns : number from 0 to 100 representing probability text
* in array uses GB-2312 encoding
*/
int gb2312_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, gbchars = 1;
long gbfreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Stage 1: Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
// System.err.println(rawtext[i]);
if (rawtext[i] >= 0) {
// asciichars++;
} else {
dbchars++;
if ((byte) 0xA1 <= rawtext[i] && rawtext[i] <= (byte) 0xF7 && (byte) 0xA1 <= rawtext[i + 1]
&& rawtext[i + 1] <= (byte) 0xFE) {
gbchars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0xA1;
column = rawtext[i + 1] + 256 - 0xA1;
if (GBFreq[row][column] != 0) {
gbfreq += GBFreq[row][column];
} else if (15 <= row && row < 55) {
// In GB high-freq character range
gbfreq += 200;
}
}
i++;
}
}
rangeval = 50 * ((float) gbchars / (float) dbchars);
freqval = 50 * ((float) gbfreq / (float) totalfreq);
return (int) (rangeval + freqval);
}
/*
* Function: gbk_probability Argument: pointer to byte array Returns : number from 0 to 100 representing probability text in
* array uses GBK encoding
*/
int gbk_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, gbchars = 1;
long gbfreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Stage 1: Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
// System.err.println(rawtext[i]);
if (rawtext[i] >= 0) {
// asciichars++;
} else {
dbchars++;
if ((byte) 0xA1 <= rawtext[i] && rawtext[i] <= (byte) 0xF7 && // Original GB range
(byte) 0xA1 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xFE) {
gbchars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0xA1;
column = rawtext[i + 1] + 256 - 0xA1;
// System.out.println("original row " + row + " column " + column);
if (GBFreq[row][column] != 0) {
gbfreq += GBFreq[row][column];
} else if (15 <= row && row < 55) {
gbfreq += 200;
}
} else if ((byte) 0x81 <= rawtext[i]
&& rawtext[i] <= (byte) 0xFE
&& // Extended GB range
(((byte) 0x80 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xFE) || ((byte) 0x40 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0x7E))) {
gbchars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0x81;
if (0x40 <= rawtext[i + 1] && rawtext[i + 1] <= 0x7E) {
column = rawtext[i + 1] - 0x40;
} else {
column = rawtext[i + 1] + 256 - 0x40;
}
// System.out.println("extended row " + row + " column " + column + " rawtext[i] " + rawtext[i]);
if (GBKFreq[row][column] != 0) {
gbfreq += GBKFreq[row][column];
}
}
i++;
}
}
rangeval = 50 * ((float) gbchars / (float) dbchars);
freqval = 50 * ((float) gbfreq / (float) totalfreq);
// For regular GB files, this would give the same score, so I handicap it slightly
return (int) (rangeval + freqval) - 1;
}
/*
* Function: gb18030_probability Argument: pointer to byte array Returns : number from 0 to 100 representing probability text
* in array uses GBK encoding
*/
int gb18030_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, gbchars = 1;
long gbfreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Stage 1: Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
// System.err.println(rawtext[i]);
if (rawtext[i] >= 0) {
// asciichars++;
} else {
dbchars++;
if ((byte) 0xA1 <= rawtext[i] && rawtext[i] <= (byte) 0xF7 && // Original GB range
i + 1 < rawtextlen && (byte) 0xA1 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xFE) {
gbchars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0xA1;
column = rawtext[i + 1] + 256 - 0xA1;
// System.out.println("original row " + row + " column " + column);
if (GBFreq[row][column] != 0) {
gbfreq += GBFreq[row][column];
} else if (15 <= row && row < 55) {
gbfreq += 200;
}
} else if ((byte) 0x81 <= rawtext[i] && rawtext[i] <= (byte) 0xFE
&& // Extended GB range
i + 1 < rawtextlen
&& (((byte) 0x80 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xFE) || ((byte) 0x40 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0x7E))) {
gbchars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0x81;
if (0x40 <= rawtext[i + 1] && rawtext[i + 1] <= 0x7E) {
column = rawtext[i + 1] - 0x40;
} else {
column = rawtext[i + 1] + 256 - 0x40;
}
// System.out.println("extended row " + row + " column " + column + " rawtext[i] " + rawtext[i]);
if (GBKFreq[row][column] != 0) {
gbfreq += GBKFreq[row][column];
}
} else if ((byte) 0x81 <= rawtext[i]
&& rawtext[i] <= (byte) 0xFE
&& // Extended GB range
i + 3 < rawtextlen && (byte) 0x30 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0x39
&& (byte) 0x81 <= rawtext[i + 2] && rawtext[i + 2] <= (byte) 0xFE && (byte) 0x30 <= rawtext[i + 3]
&& rawtext[i + 3] <= (byte) 0x39) {
gbchars++;
/*
* totalfreq += 500; row = rawtext[i] + 256 - 0x81; if (0x40 <= rawtext[i+1] && rawtext[i+1] <= 0x7E) { column =
* rawtext[i+1] - 0x40; } else { column = rawtext[i+1] + 256 - 0x40; } //System.out.println("extended row " + row + "
* column " + column + " rawtext[i] " + rawtext[i]); if (GBKFreq[row][column] != 0) { gbfreq += GBKFreq[row][column]; }
*/
}
i++;
}
}
rangeval = 50 * ((float) gbchars / (float) dbchars);
freqval = 50 * ((float) gbfreq / (float) totalfreq);
// For regular GB files, this would give the same score, so I handicap it slightly
return (int) (rangeval + freqval) - 1;
}
/*
* Function: hz_probability Argument: byte array Returns : number from 0 to 100 representing probability text in array uses HZ
* encoding
*/
int hz_probability(byte[] rawtext) {
int i, rawtextlen;
int hzchars = 0, dbchars = 1;
long hzfreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int hzstart = 0, hzend = 0;
int row, column;
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen; i++) {
if (rawtext[i] == '~') {
if (rawtext[i + 1] == '{') {
hzstart++;
i += 2;
while (i < rawtextlen - 1) {
if (rawtext[i] == 0x0A || rawtext[i] == 0x0D) {
break;
} else if (rawtext[i] == '~' && rawtext[i + 1] == '}') {
hzend++;
i++;
break;
} else if ((0x21 <= rawtext[i] && rawtext[i] <= 0x77) && (0x21 <= rawtext[i + 1] && rawtext[i + 1] <= 0x77)) {
hzchars += 2;
row = rawtext[i] - 0x21;
column = rawtext[i + 1] - 0x21;
totalfreq += 500;
if (GBFreq[row][column] != 0) {
hzfreq += GBFreq[row][column];
} else if (15 <= row && row < 55) {
hzfreq += 200;
}
} else if ((0xA1 <= rawtext[i] && rawtext[i] <= 0xF7) && (0xA1 <= rawtext[i + 1] && rawtext[i + 1] <= 0xF7)) {
hzchars += 2;
row = rawtext[i] + 256 - 0xA1;
column = rawtext[i + 1] + 256 - 0xA1;
totalfreq += 500;
if (GBFreq[row][column] != 0) {
hzfreq += GBFreq[row][column];
} else if (15 <= row && row < 55) {
hzfreq += 200;
}
}
dbchars += 2;
i += 2;
}
} else if (rawtext[i + 1] == '}') {
hzend++;
i++;
} else if (rawtext[i + 1] == '~') {
i++;
}
}
}
if (hzstart > 4) {
rangeval = 50;
} else if (hzstart > 1) {
rangeval = 41;
} else if (hzstart > 0) { // Only 39 in case the sequence happened to occur
rangeval = 39; // in otherwise non-Hz text
} else {
rangeval = 0;
}
freqval = 50 * ((float) hzfreq / (float) totalfreq);
return (int) (rangeval + freqval);
}
/**
* Function: big5_probability Argument: byte array Returns : number from 0 to 100 representing probability text in array uses
* Big5 encoding
*/
int big5_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, bfchars = 1;
float rangeval = 0, freqval = 0;
long bffreq = 0, totalfreq = 1;
int row, column;
// Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
if (rawtext[i] >= 0) {
// asciichars++;
} else {
dbchars++;
if ((byte) 0xA1 <= rawtext[i]
&& rawtext[i] <= (byte) 0xF9
&& (((byte) 0x40 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0x7E) || ((byte) 0xA1 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xFE))) {
bfchars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0xA1;
if (0x40 <= rawtext[i + 1] && rawtext[i + 1] <= 0x7E) {
column = rawtext[i + 1] - 0x40;
} else {
column = rawtext[i + 1] + 256 - 0x61;
}
if (Big5Freq[row][column] != 0) {
bffreq += Big5Freq[row][column];
} else if (3 <= row && row <= 37) {
bffreq += 200;
}
}
i++;
}
}
rangeval = 50 * ((float) bfchars / (float) dbchars);
freqval = 50 * ((float) bffreq / (float) totalfreq);
return (int) (rangeval + freqval);
}
/*
* Function: big5plus_probability Argument: pointer to unsigned char array Returns : number from 0 to 100 representing
* probability text in array uses Big5+ encoding
*/
int big5plus_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, bfchars = 1;
long bffreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Stage 1: Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
// System.err.println(rawtext[i]);
if (rawtext[i] >= 128) {
// asciichars++;
} else {
dbchars++;
if (0xA1 <= rawtext[i] && rawtext[i] <= 0xF9 && // Original Big5 range
((0x40 <= rawtext[i + 1] && rawtext[i + 1] <= 0x7E) || (0xA1 <= rawtext[i + 1] && rawtext[i + 1] <= 0xFE))) {
bfchars++;
totalfreq += 500;
row = rawtext[i] - 0xA1;
if (0x40 <= rawtext[i + 1] && rawtext[i + 1] <= 0x7E) {
column = rawtext[i + 1] - 0x40;
} else {
column = rawtext[i + 1] - 0x61;
}
// System.out.println("original row " + row + " column " + column);
if (Big5Freq[row][column] != 0) {
bffreq += Big5Freq[row][column];
} else if (3 <= row && row < 37) {
bffreq += 200;
}
} else if (0x81 <= rawtext[i] && rawtext[i] <= 0xFE && // Extended Big5 range
((0x40 <= rawtext[i + 1] && rawtext[i + 1] <= 0x7E) || (0x80 <= rawtext[i + 1] && rawtext[i + 1] <= 0xFE))) {
bfchars++;
totalfreq += 500;
row = rawtext[i] - 0x81;
if (0x40 <= rawtext[i + 1] && rawtext[i + 1] <= 0x7E) {
column = rawtext[i + 1] - 0x40;
} else {
column = rawtext[i + 1] - 0x40;
}
// System.out.println("extended row " + row + " column " + column + " rawtext[i] " + rawtext[i]);
if (Big5PFreq[row][column] != 0) {
bffreq += Big5PFreq[row][column];
}
}
i++;
}
}
rangeval = 50 * ((float) bfchars / (float) dbchars);
freqval = 50 * ((float) bffreq / (float) totalfreq);
// For regular Big5 files, this would give the same score, so I handicap it slightly
return (int) (rangeval + freqval) - 1;
}
/*
* Function: euc_tw_probability Argument: byte array Returns : number from 0 to 100 representing probability text in array
* uses EUC-TW (CNS 11643) encoding
*/
int euc_tw_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, cnschars = 1;
long cnsfreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Check to see if characters fit into acceptable ranges
// and have expected frequency of use
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
if (rawtext[i] >= 0) { // in ASCII range
// asciichars++;
} else { // high bit set
dbchars++;
if (i + 3 < rawtextlen && (byte) 0x8E == rawtext[i] && (byte) 0xA1 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xB0
&& (byte) 0xA1 <= rawtext[i + 2] && rawtext[i + 2] <= (byte) 0xFE && (byte) 0xA1 <= rawtext[i + 3]
&& rawtext[i + 3] <= (byte) 0xFE) { // Planes 1 - 16
cnschars++;
// System.out.println("plane 2 or above CNS char");
// These are all less frequent chars so just ignore freq
i += 3;
} else if ((byte) 0xA1 <= rawtext[i] && rawtext[i] <= (byte) 0xFE && // Plane 1
(byte) 0xA1 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xFE) {
cnschars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0xA1;
column = rawtext[i + 1] + 256 - 0xA1;
if (EUC_TWFreq[row][column] != 0) {
cnsfreq += EUC_TWFreq[row][column];
} else if (35 <= row && row <= 92) {
cnsfreq += 150;
}
i++;
}
}
}
rangeval = 50 * ((float) cnschars / (float) dbchars);
freqval = 50 * ((float) cnsfreq / (float) totalfreq);
return (int) (rangeval + freqval);
}
/*
* Function: iso_2022_cn_probability Argument: byte array Returns : number from 0 to 100 representing probability text in
* array uses ISO 2022-CN encoding WORKS FOR BASIC CASES, BUT STILL NEEDS MORE WORK
*/
int iso_2022_cn_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, isochars = 1;
long isofreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Check to see if characters fit into acceptable ranges
// and have expected frequency of use
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
if (rawtext[i] == (byte) 0x1B && i + 3 < rawtextlen) { // Escape char ESC
if (rawtext[i + 1] == (byte) 0x24 && rawtext[i + 2] == 0x29 && rawtext[i + 3] == (byte) 0x41) { // GB Escape $ ) A
i += 4;
while (rawtext[i] != (byte) 0x1B) {
dbchars++;
if ((0x21 <= rawtext[i] && rawtext[i] <= 0x77) && (0x21 <= rawtext[i + 1] && rawtext[i + 1] <= 0x77)) {
isochars++;
row = rawtext[i] - 0x21;
column = rawtext[i + 1] - 0x21;
totalfreq += 500;
if (GBFreq[row][column] != 0) {
isofreq += GBFreq[row][column];
} else if (15 <= row && row < 55) {
isofreq += 200;
}
i++;
}
i++;
}
} else if (i + 3 < rawtextlen && rawtext[i + 1] == (byte) 0x24 && rawtext[i + 2] == (byte) 0x29
&& rawtext[i + 3] == (byte) 0x47) {
// CNS Escape $ ) G
i += 4;
while (rawtext[i] != (byte) 0x1B) {
dbchars++;
if ((byte) 0x21 <= rawtext[i] && rawtext[i] <= (byte) 0x7E && (byte) 0x21 <= rawtext[i + 1]
&& rawtext[i + 1] <= (byte) 0x7E) {
isochars++;
totalfreq += 500;
row = rawtext[i] - 0x21;
column = rawtext[i + 1] - 0x21;
if (EUC_TWFreq[row][column] != 0) {
isofreq += EUC_TWFreq[row][column];
} else if (35 <= row && row <= 92) {
isofreq += 150;
}
i++;
}
i++;
}
}
if (rawtext[i] == (byte) 0x1B && i + 2 < rawtextlen && rawtext[i + 1] == (byte) 0x28 && rawtext[i + 2] == (byte) 0x42) { // ASCII:
// ESC
// ( B
i += 2;
}
}
}
rangeval = 50 * ((float) isochars / (float) dbchars);
freqval = 50 * ((float) isofreq / (float) totalfreq);
// System.out.println("isochars dbchars isofreq totalfreq " + isochars + " " + dbchars + " " + isofreq + " " + totalfreq + "
// " + rangeval + " " + freqval);
return (int) (rangeval + freqval);
// return 0;
}
/*
* Function: utf8_probability Argument: byte array Returns : number from 0 to 100 representing probability text in array uses
* UTF-8 encoding of Unicode
*/
int utf8_probability(byte[] rawtext) {
int score = 0;
int i, rawtextlen = 0;
int goodbytes = 0, asciibytes = 0;
// Maybe also use UTF8 Byte Order Mark: EF BB BF
// Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen; i++) {
if ((rawtext[i] & (byte) 0x7F) == rawtext[i]) { // One byte
asciibytes++;
// Ignore ASCII, can throw off count
} else if (-64 <= rawtext[i] && rawtext[i] <= -33 && // Two bytes
i + 1 < rawtextlen && -128 <= rawtext[i + 1] && rawtext[i + 1] <= -65) {
goodbytes += 2;
i++;
} else if (-32 <= rawtext[i] && rawtext[i] <= -17
&& // Three bytes
i + 2 < rawtextlen && -128 <= rawtext[i + 1] && rawtext[i + 1] <= -65 && -128 <= rawtext[i + 2]
&& rawtext[i + 2] <= -65) {
goodbytes += 3;
i += 2;
}
}
if (asciibytes == rawtextlen) {
return 0;
}
score = (int) (100 * ((float) goodbytes / (float) (rawtextlen - asciibytes)));
// System.out.println("rawtextlen " + rawtextlen + " goodbytes " + goodbytes + " asciibytes " + asciibytes + " score " +
// score);
// If not above 98, reduce to zero to prevent coincidental matches
// Allows for some (few) bad formed sequences
if (score > 98) {
return score;
} else if (score > 95 && goodbytes > 30) {
return score;
} else {
return 0;
}
}
/*
* Function: utf16_probability Argument: byte array Returns : number from 0 to 100 representing probability text in array uses
* UTF-16 encoding of Unicode, guess based on BOM // NOT VERY GENERAL, NEEDS MUCH MORE WORK
*/
int utf16_probability(byte[] rawtext) {
// int score = 0;
// int i, rawtextlen = 0;
// int goodbytes = 0, asciibytes = 0;
if (rawtext.length > 1 && ((byte) 0xFE == rawtext[0] && (byte) 0xFF == rawtext[1]) || // Big-endian
((byte) 0xFF == rawtext[0] && (byte) 0xFE == rawtext[1])) { // Little-endian
return 100;
}
return 0;
/*
* // Check to see if characters fit into acceptable ranges rawtextlen = rawtext.length; for (i = 0; i < rawtextlen; i++) {
* if ((rawtext[i] & (byte)0x7F) == rawtext[i]) { // One byte goodbytes += 1; asciibytes++; } else if ((rawtext[i] &
* (byte)0xDF) == rawtext[i]) { // Two bytes if (i+1 < rawtextlen && (rawtext[i+1] & (byte)0xBF) == rawtext[i+1]) {
* goodbytes += 2; i++; } } else if ((rawtext[i] & (byte)0xEF) == rawtext[i]) { // Three bytes if (i+2 < rawtextlen &&
* (rawtext[i+1] & (byte)0xBF) == rawtext[i+1] && (rawtext[i+2] & (byte)0xBF) == rawtext[i+2]) { goodbytes += 3; i+=2; } } }
*
* score = (int)(100 * ((float)goodbytes/(float)rawtext.length)); // An all ASCII file is also a good UTF8 file, but I'd
* rather it // get identified as ASCII. Can delete following 3 lines otherwise if (goodbytes == asciibytes) { score = 0; } //
* If not above 90, reduce to zero to prevent coincidental matches if (score > 90) { return score; } else { return 0; }
*/
}
/*
* Function: ascii_probability Argument: byte array Returns : number from 0 to 100 representing probability text in array uses
* all ASCII Description: Sees if array has any characters not in ASCII range, if so, score is reduced
*/
int ascii_probability(byte[] rawtext) {
int score = 75;
int i, rawtextlen;
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen; i++) {
if (rawtext[i] < 0) {
score = score - 5;
} else if (rawtext[i] == (byte) 0x1B) { // ESC (used by ISO 2022)
score = score - 5;
}
if (score <= 0) {
return 0;
}
}
return score;
}
/*
* Function: euc_kr__probability Argument: pointer to byte array Returns : number from 0 to 100 representing probability text
* in array uses EUC-KR encoding
*/
int euc_kr_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, krchars = 1;
long krfreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Stage 1: Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
// System.err.println(rawtext[i]);
if (rawtext[i] >= 0) {
// asciichars++;
} else {
dbchars++;
if ((byte) 0xA1 <= rawtext[i] && rawtext[i] <= (byte) 0xFE && (byte) 0xA1 <= rawtext[i + 1]
&& rawtext[i + 1] <= (byte) 0xFE) {
krchars++;
totalfreq += 500;
row = rawtext[i] + 256 - 0xA1;
column = rawtext[i + 1] + 256 - 0xA1;
if (KRFreq[row][column] != 0) {
krfreq += KRFreq[row][column];
} else if (15 <= row && row < 55) {
krfreq += 0;
}
}
i++;
}
}
rangeval = 50 * ((float) krchars / (float) dbchars);
freqval = 50 * ((float) krfreq / (float) totalfreq);
return (int) (rangeval + freqval);
}
/*
* Function: cp949__probability Argument: pointer to byte array Returns : number from 0 to 100 representing probability text
* in array uses Cp949 encoding
*/
int cp949_probability(byte[] rawtext) {
int i, rawtextlen = 0;
int dbchars = 1, krchars = 1;
long krfreq = 0, totalfreq = 1;
float rangeval = 0, freqval = 0;
int row, column;
// Stage 1: Check to see if characters fit into acceptable ranges
rawtextlen = rawtext.length;
for (i = 0; i < rawtextlen - 1; i++) {
// System.err.println(rawtext[i]);
if (rawtext[i] >= 0) {
// asciichars++;
} else {
dbchars++;
if ((byte) 0x81 <= rawtext[i]
&& rawtext[i] <= (byte) 0xFE
&& ((byte) 0x41 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0x5A || (byte) 0x61 <= rawtext[i + 1]
&& rawtext[i + 1] <= (byte) 0x7A || (byte) 0x81 <= rawtext[i + 1] && rawtext[i + 1] <= (byte) 0xFE)) {
krchars++;
totalfreq += 500;
if ((byte) 0xA1 <= rawtext[i] && rawtext[i] <= (byte) 0xFE && (byte) 0xA1 <= rawtext[i + 1]
&& rawtext[i + 1] <= (byte) 0xFE) {
row = rawtext[i] + 256 - 0xA1;
column = rawtext[i + 1] + 256 - 0xA1;
if (KRFreq[row][column] != 0) {
krfreq += KRFreq[row][column];
}
}
}
i++;
}
}
rangeval = 50 * ((float) krchars / (float) dbchars);
freqval = 50 * ((float) krfreq / (float) totalfreq);
return (int) (rangeval + freqval);
}
int iso_2022_kr_probability(byte[] rawtext) {
int i;
for (i = 0; i < rawtext.length; i++) {
if (i + 3 < rawtext.length && rawtext[i] == 0x1b && (char) rawtext[i + 1] == '$' && (char) rawtext[i + 2] == ')'
&& (char) rawtext[i + 3] == 'C') {
return 100;
}