(root)/android/import-contacts
» Revision
1
(compared to revision 62)
: src/org/waxworlds/importcontacts/VCFImporter.java
To get this branch, use:
bzr branch
http://bzr.ed.am/android/import-contacts
« back to all changes in this revision
Viewing changes to src/org/waxworlds/importcontacts/VCFImporter.java
- browse files at revision 1
- compare with another revision
- download diff
- download tarball
- view history from revision 1
- Committer: edam
- Date: 2009-01-10 16:14:11 UTC
- Revision ID: edam@waxworlds.org-20090110161411-4d17l9hs9d6j277q
Initial import
- files added:
- src/org
- src/org/waxworlds
- files removed:
- COPYING
- gen
- gen/am
- gen/am/ed
- gen/am/ed/importcontacts
- src/am
- src/am/ed
- files renamed:
- res/layout/configure_vcf.xml => res/layout/import_vcf.xml
- src/am/ed/importcontacts/ => src/org/waxworlds/importcontacts/
- src/am/ed/importcontacts/ConfigureVCF.java => src/org/waxworlds/importcontacts/ImportVCF.java
- src/am/ed/importcontacts/VcardImporter.java => src/org/waxworlds/importcontacts/VCFImporter.java
- files modified:
- .classpath
added
removed
src/org/waxworlds/importcontacts/VCFImporter.java
1
/*
2
* VCFImporter.java
3
*
4
* Copyright (C) 2009 to 2011 Tim Marston <tim@ed.am>
5
*
6
* This file is part of the Import Contacts program (hereafter referred
7
* to as "this program"). For more information, see
8
* http://ed.am/dev/android/import-contacts
9
*
10
* This program is free software: you can redistribute it and/or modify
11
* it under the terms of the GNU General Public License as published by
12
* the Free Software Foundation, either version 3 of the License, or
13
* (at your option) any later version.
14
*
15
* This program is distributed in the hope that it will be useful,
16
* but WITHOUT ANY WARRANTY; without even the implied warranty of
17
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18
* GNU General Public License for more details.
19
*
20
* You should have received a copy of the GNU General Public License
21
* along with this program. If not, see <http://www.gnu.org/licenses/>.
22
*/
23
24
package am.ed.importcontacts;
1
package org.waxworlds.importcontacts;
25
2
26
3
import java.io.BufferedReader;
27
4
import java.io.File;
28
import java.io.FileInputStream;
29
5
import java.io.FileNotFoundException;
30
6
import java.io.FileReader;
31
7
import java.io.FilenameFilter;
32
8
import java.io.IOException;
33
9
import java.io.UnsupportedEncodingException;
34
import java.nio.ByteBuffer;
35
import java.util.ArrayList;
36
10
import java.util.Arrays;
37
import java.util.HashMap;
38
11
import java.util.HashSet;
39
import java.util.Iterator;
40
12
import java.util.List;
41
import java.util.Locale;
42
import java.util.NoSuchElementException;
43
13
import java.util.Set;
44
14
import java.util.Vector;
45
15
import java.util.regex.Matcher;
46
16
import java.util.regex.Pattern;
47
17
48
import android.annotation.SuppressLint;
18
import org.waxworlds.importcontacts.Importer.AbortImportException;
19
49
20
import android.content.SharedPreferences;
21
import android.provider.Contacts;
22
import android.provider.Contacts.PhonesColumns;
50
23
51
public class VcardImporter extends Importer
24
public class VCFImporter extends Importer
52
25
{
53
private int _vcard_count = 0;
26
private int _vCardCount = 0;
54
27
private int _progress = 0;
55
28
56
public VcardImporter( Doit doit )
29
public VCFImporter( Doit doit )
57
30
{
58
31
super( doit );
59
32
}
60
33
61
@SuppressLint( "SdCardPath" )
62
34
@Override
63
35
protected void onImport() throws AbortImportException
64
36
{
72
44
try
73
45
{
74
46
// open directory
75
String path = "/sdcard" + prefs.getString( "location", "/" );
76
File file = new File( path );
77
if( !file.exists() )
47
String location = prefs.getString( "location", "" );
48
File dir = new File( location );
49
if( !dir.exists() || !dir.isDirectory() )
78
50
showError( R.string.error_locationnotfound );
79
51
80
// directory, or file?
81
if( file.isDirectory() )
82
{
83
// get files
84
class VCardFilter implements FilenameFilter {
85
public boolean accept( File dir, String name ) {
86
return name.toLowerCase( Locale.US ).endsWith( ".vcf" );
87
}
88
}
89
files = file.listFiles( new VCardFilter() );
90
}
91
else
92
{
93
// use just this file
94
files = new File[ 1 ];
95
files[ 0 ] = file;
96
}
52
// get files
53
class VCardFilter implements FilenameFilter {
54
public boolean accept( File dir, String name ) {
55
return name.toLowerCase().endsWith( ".vcf" );
56
}
57
}
58
files = dir.listFiles( new VCardFilter() );
97
59
}
98
60
catch( SecurityException e ) {
99
61
showError( R.string.error_locationpermissions );
111
73
countVCardFile( files[ i ] );
112
74
setTmpProgress( i );
113
75
}
114
setProgressMax( _vcard_count ); // will also update tmp progress
76
setProgressMax( _vCardCount ); // will also update tmp progress
115
77
116
78
// import them
117
79
setProgress( 0 );
118
80
for( int i = 0; i < files.length; i++ )
119
81
importVCardFile( files[ i ] );
120
setProgress( _vcard_count );
121
82
}
122
83
123
84
private void countVCardFile( File file ) throws AbortImportException
126
87
{
127
88
// open file
128
89
BufferedReader reader = new BufferedReader(
129
new FileReader( file ) );
90
new FileReader( file ) );
130
91
131
92
// read
132
93
String line;
133
boolean in_vcard = false;
94
boolean inVCard = false;
134
95
while( ( line = reader.readLine() ) != null )
135
96
{
136
if( !in_vcard ) {
97
if( !inVCard ) {
137
98
// look for vcard beginning
138
if( line.matches( "^BEGIN:VCARD" ) ) {
139
in_vcard = true;
140
_vcard_count++;
99
if( line.matches( "^BEGIN[ \\t]*:[ \\t]*VCARD" ) ) {
100
inVCard = true;
101
_vCardCount++;
141
102
}
142
103
}
143
else if( line.matches( "^END:VCARD" ) )
144
in_vcard = false;
104
else if( line.matches( "^END[ \\t]*:[ \\t]*VCARD" ) )
105
inVCard = false;
145
106
}
146
107
147
108
}
148
109
catch( FileNotFoundException e ) {
149
showError( getText( R.string.error_filenotfound ) +
150
file.getName() );
110
showError( getText( R.string.error_filenotfound ) + file.getName() );
151
111
}
152
112
catch( IOException e ) {
153
113
showError( getText( R.string.error_ioerror ) + file.getName() );
156
116
157
117
private void importVCardFile( File file ) throws AbortImportException
158
118
{
159
// check file is good
160
if( !file.exists() )
161
showError( getText( R.string.error_filenotfound ) +
162
file.getName() );
163
if( file.length() == 0 )
164
showError( getText( R.string.error_fileisempty ) +
165
file.getName() );
166
167
119
try
168
120
{
169
// open/read file
170
FileInputStream istream = new FileInputStream( file );
171
byte[] content = new byte[ (int)file.length() ];
172
istream.read( content );
173
istream = null;
174
175
// import
176
importVCardFileContent( content, file.getName() );
121
// open file
122
BufferedReader reader = new BufferedReader(
123
new FileReader( file ) );
124
125
// read
126
StringBuffer content = new StringBuffer();
127
String line;
128
while( ( line = reader.readLine() ) != null )
129
content.append( line ).append( "\n" );
130
131
importVCardFileContent( content.toString(), file.getName() );
177
132
}
178
133
catch( FileNotFoundException e ) {
179
showError( getText( R.string.error_filenotfound ) +
180
file.getName() );
134
showError( getText( R.string.error_filenotfound ) + file.getName() );
181
135
}
182
136
catch( IOException e ) {
183
137
showError( getText( R.string.error_ioerror ) + file.getName() );
184
138
}
185
139
}
186
140
187
private void importVCardFileContent( byte[] content, String fileName )
188
throws AbortImportException
141
private void importVCardFileContent( String content, String fileName )
142
throws AbortImportException
189
143
{
190
// go through lines
191
Vcard vcard = null;
192
int vcard_start_line = 0;
193
ContentLineIterator cli = new ContentLineIterator( content );
194
while( cli.hasNext() )
144
// unfold RFC2425 section 5.8.1 folded lines, except that we must also
145
// handle embedded Quoted-Printable encodings that have a trailing '='.
146
// So we remove these first before doing RFC2425 unfolding.
147
content = content.replaceAll( "=\n[ \\t]", "" )
148
.replaceAll( "\n[ \\t]", "" );
149
150
// get lines and parse them
151
String[] lines = content.split( "\n" );
152
VCard vCard = null;
153
for( int i = 0; i < lines.length; i++ )
195
154
{
196
ByteBuffer buffer = cli.next();
197
198
// get a US-ASCII version of the line for processing
199
String line;
200
try {
201
line = new String( buffer.array(), buffer.position(),
202
buffer.limit() - buffer.position(), "US-ASCII" );
203
}
204
catch( UnsupportedEncodingException e ) {
205
// we know US-ASCII is supported, so appease the compiler...
206
line = "";
207
}
208
209
if( vcard == null ) {
155
String line = lines[ i ];
156
157
if( vCard == null ) {
210
158
// look for vcard beginning
211
if( line.matches( "^BEGIN:VCARD" ) ) {
212
setProgress( _progress++ );
213
vcard = new Vcard();
214
vcard_start_line = cli.getLineNumber();
159
if( line.matches( "^BEGIN[ \\t]*:[ \\t]*VCARD" ) ) {
160
setProgress( ++_progress );
161
vCard = new VCard();
215
162
}
216
163
}
217
164
else {
218
165
// look for vcard content or ending
219
if( line.matches( "^END:VCARD" ) )
166
if( line.matches( "^END[ \\t]*:[ \\t]*VCARD" ) )
220
167
{
221
// finalise the vcard/contact
168
// store vcard and do away with it
222
169
try {
223
vcard.finaliseVcard();
224
225
// pass the finalised contact to the importer
226
importContact( vcard );
227
}
228
catch( Vcard.ParseException e ) {
229
if( !showContinue(
230
getText( R.string.error_vcf_parse ).toString()
231
+ fileName +
232
getText( R.string.error_vcf_parse_line ).toString()
233
+ cli.getLineNumber() + ":\n" + e.getMessage() ) )
234
{
235
finish( ACTION_ABORT );
236
}
237
else
238
skipContact();
239
}
240
catch( ContactData.ContactNotIdentifiableException e ) {
241
if( !showContinue(
242
getText( R.string.error_vcf_parse ).toString()
243
+ fileName +
244
getText( R.string.error_vcf_parse_line ).toString()
245
+ vcard_start_line + ":\n" + getText(
246
R.string.error_vcf_notenoughinfo ).toString()
247
) )
248
{
249
finish( ACTION_ABORT );
250
}
251
else
252
skipContact();
253
}
254
255
// discard this vcard
256
vcard = null;
170
vCard.finaliseParsing();
171
importContact( vCard );
172
}
173
catch( VCard.ParseException e ) {
174
skipContact();
175
if( !showContinue(
176
getText( R.string.error_vcf_parse ).toString()
177
+ fileName + "\n" + e.getMessage() ) )
178
abort();
179
}
180
catch( VCard.SkipContactException e ) {
181
skipContact();
182
// do nothing
183
}
184
vCard = null;
257
185
}
258
186
else
259
187
{
260
188
// try giving the line to the vcard
261
189
try {
262
vcard.parseLine( buffer, line,
263
cli.doesNextLineLookFolded() );
190
vCard.parseLine( line );
264
191
}
265
catch( Vcard.ParseException e ) {
192
catch( VCard.ParseException e ) {
266
193
skipContact();
267
194
if( !showContinue(
268
getText( R.string.error_vcf_parse ).toString()
269
+ fileName +
270
getText( R.string.error_vcf_parse_line ).toString()
271
+ cli.getLineNumber() + "\n" + e.getMessage() ) )
272
{
273
finish( ACTION_ABORT );
274
}
195
getText( R.string.error_vcf_parse ).toString()
196
+ fileName + "\n" + e.getMessage() ) )
197
abort();
275
198
276
199
// although we're continuing, we still need to abort
277
200
// this vCard. Further lines will be ignored until we
278
201
// get to another BEGIN:VCARD line.
279
vcard = null;
202
vCard = null;
280
203
}
281
catch( Vcard.SkipImportException e ) {
204
catch( VCard.SkipContactException e ) {
282
205
skipContact();
283
206
// abort this vCard. Further lines will be ignored until
284
207
// we get to another BEGIN:VCARD line.
285
vcard = null;
208
vCard = null;
286
209
}
287
210
}
288
211
}
289
212
}
290
213
}
291
214
292
class ContentLineIterator implements Iterator< ByteBuffer >
293
{
294
protected byte[] _content = null;
295
protected int _pos = 0;
296
protected int _line = 0;
297
298
public ContentLineIterator( byte[] content )
299
{
300
_content = content;
301
}
302
303
@Override
304
public boolean hasNext()
305
{
306
return _pos < _content.length;
307
}
308
309
@Override
310
public ByteBuffer next()
311
{
312
int initial_pos = _pos;
313
314
// find newline
315
for( ; _pos < _content.length; _pos++ )
316
if( _content[ _pos ] == '\n' )
317
{
318
// adjust for a \r preceding the \n
319
int to = ( _pos > 0 && _content[ _pos - 1 ] == '\r' &&
320
_pos > initial_pos )? _pos - 1 : _pos;
321
_pos++;
322
_line++;
323
return ByteBuffer.wrap( _content, initial_pos,
324
to - initial_pos );
325
}
326
327
// we didn't find one, but were there bytes left?
328
if( _pos != initial_pos ) {
329
int to = _pos;
330
_pos++;
331
_line++;
332
return ByteBuffer.wrap( _content, initial_pos,
333
to - initial_pos );
334
}
335
336
// no bytes left
337
throw new NoSuchElementException();
338
}
339
340
@Override
341
public void remove()
342
{
343
throw new UnsupportedOperationException();
344
}
345
346
/**
347
* Does the next line, if there is one, look like it should be folded
348
* onto the end of this one?
349
* @return
350
*/
351
public boolean doesNextLineLookFolded()
352
{
353
return _pos > 0 && _pos < _content.length &&
354
_content[ _pos - 1 ] == '\n' && _content[ _pos ] == ' ';
355
}
356
357
public int getLineNumber()
358
{
359
return _line;
360
}
361
}
362
363
private class Vcard extends ContactData
215
private class VCard extends ContactData
364
216
{
365
217
private final static int NAMELEVEL_NONE = 0;
366
private final static int NAMELEVEL_N = 1;
218
private final static int NAMELEVEL_ORG = 1;
367
219
private final static int NAMELEVEL_FN = 2;
368
369
private final static int MULTILINE_NONE = 0;
370
private final static int MULTILINE_ENCODED = 1; // v2.1 quoted-printable
371
private final static int MULTILINE_ESCAPED = 2; // v2.1 \\CRLF
372
private final static int MULTILINE_FOLDED = 3; // v3.0 folding
220
private final static int NAMELEVEL_N = 3;
373
221
374
222
private String _version = null;
375
private Vector< ByteBuffer > _buffers = null;
376
private int _name_level = NAMELEVEL_NONE;
377
private int _parser_multiline_state = MULTILINE_NONE;
378
private String _parser_current_name_and_params = null;
379
private String _parser_buffered_value_so_far = "";
380
private String _cached_organisation = null;
381
private String _cached_title = null;
382
383
protected class UnencodeResult
384
{
385
private boolean _another_line_required;
386
private ByteBuffer _buffer;
387
388
public UnencodeResult( boolean another_line_required,
389
ByteBuffer buffer )
390
{
391
_another_line_required = another_line_required;
392
_buffer = buffer;
393
}
394
395
public boolean isAnotherLineRequired()
396
{
397
return _another_line_required;
398
}
399
400
public ByteBuffer getBuffer()
401
{
402
return _buffer;
403
}
404
}
405
406
@SuppressWarnings("serial")
223
private Vector< String > _lines = null;
224
private int _nameLevel = NAMELEVEL_NONE;
225
407
226
protected class ParseException extends Exception
408
227
{
409
@SuppressWarnings("unused")
410
228
public ParseException( String error )
411
229
{
412
230
super( error );
414
232
415
233
public ParseException( int res )
416
234
{
417
super( VcardImporter.this.getText( res ).toString() );
418
}
419
}
420
421
@SuppressWarnings("serial")
422
protected class SkipImportException extends Exception { }
423
424
private String extractCollonPartFromLine( ByteBuffer buffer,
425
String line, boolean former )
426
{
427
String ret = null;
428
429
// get a US-ASCII version of the line for processing, unless we were
430
// supplied with one
431
if( line == null ) {
432
try {
433
line = new String( buffer.array(), buffer.position(),
434
buffer.limit() - buffer.position(), "US-ASCII" );
435
}
436
catch( UnsupportedEncodingException e ) {
437
// we know US-ASCII is supported, so appease the compiler...
438
line = "";
439
}
440
}
441
442
// split line into name and value parts and check to make sure we
443
// only got 2 parts and that the first part is not zero in length
444
String[] parts = line.split( ":", 2 );
445
if( parts.length == 2 && parts[ 0 ].length() > 0 )
446
ret = parts[ former? 0 : 1 ];
447
448
return ret;
449
}
450
451
private String extractNameAndParamsFromLine( ByteBuffer buffer,
452
String line )
453
{
454
return extractCollonPartFromLine( buffer, line, true );
455
}
456
457
private String extractValueFromLine( ByteBuffer buffer, String line )
458
{
459
return extractCollonPartFromLine( buffer, line, false );
460
}
461
462
public void parseLine( ByteBuffer buffer, String line,
463
boolean next_line_looks_folded )
464
throws ParseException, SkipImportException,
465
AbortImportException
466
{
467
// do we have a version yet?
235
super( VCFImporter.this.getText( res ).toString() );
236
}
237
}
238
239
protected class SkipContactException extends Exception { }
240
241
public void parseLine( String line )
242
throws ParseException, SkipContactException,
243
AbortImportException
244
{
245
// get property halves
246
String[] props = line.split( ":" );
247
for( int i = 0; i < props.length; i++ )
248
props[ i ] = props[ i ].trim();
249
if( props.length < 2 ||
250
props[ 0 ].length() < 1 || props[ 1 ].length() < 1 )
251
throw new ParseException( R.string.error_vcf_malformed );
252
468
253
if( _version == null )
469
254
{
470
// tentatively get name and params from line
471
String name_and_params =
472
extractNameAndParamsFromLine( buffer, line );
473
474
// is it a version line?
475
if( name_and_params != null &&
476
name_and_params.equals( "VERSION" ) )
255
if( props[ 0 ].equals( "VERSION" ) )
477
256
{
478
// yes, get it!
479
String value = extractValueFromLine( buffer, line );
480
if( !value.equals( "2.1" ) && !value.equals( "3.0" ) )
257
// get version
258
if( !props[ 1 ].equals( "2.1" ) &&
259
!props[ 1 ].equals( "3.0" ) )
481
260
throw new ParseException( R.string.error_vcf_version );
482
_version = value;
261
_version = props[ 1 ];
483
262
484
// parse any buffers we've been accumulating while we waited
485
// for a version
486
if( _buffers != null )
487
for( int i = 0; i < _buffers.size(); i++ )
488
parseLine( _buffers.get( i ), null,
489
i + 1 < _buffers.size() &&
490
_buffers.get( i + 1 ).hasRemaining() &&
491
_buffers.get( i + 1 ).get(
492
_buffers.get( i + 1 ).position() ) == ' ' );
493
_buffers = null;
263
// parse any other lines we've accumulated so far
264
if( _lines != null )
265
for( int i = 0; i < _lines.size(); i++ )
266
parseLine( _lines.get( i ) );
267
_lines = null;
494
268
}
495
269
else
496
270
{
497
// no, so stash this line till we get a version
498
if( _buffers == null )
499
_buffers = new Vector< ByteBuffer >();
500
_buffers.add( buffer );
271
// stash this line till we have a version
272
if( _lines == null )
273
_lines = new Vector< String >();
274
_lines.add( line );
501
275
}
502
276
}
503
277
else
504
278
{
505
// name and params and the position in the buffer where the
506
// "value" part of the line start
507
String name_and_params;
508
int pos;
509
510
if( _parser_multiline_state != MULTILINE_NONE )
511
{
512
// if we're currently in a multi-line value, use the stored
513
// property name and parameters
514
name_and_params = _parser_current_name_and_params;
515
516
// skip some initial line characters, depending on the type
517
// of multi-line we're handling
518
pos = buffer.position();
519
switch( _parser_multiline_state )
520
{
521
case MULTILINE_FOLDED:
522
pos++;
523
break;
524
case MULTILINE_ENCODED:
525
while( pos < buffer.limit() && (
526
buffer.get( pos ) == ' ' ||
527
buffer.get( pos ) == '\t' ) )
528
{
529
pos++;
530
}
531
break;
532
default:
533
// do nothing
534
}
535
536
// take us out of multi-line so that we can re-detect that
537
// this line is a multi-line or not
538
_parser_multiline_state = MULTILINE_NONE;
539
}
540
else
541
{
542
// get name and params from line, and since we're not
543
// parsing a subsequent line in a multi-line, this should
544
// not fail, or it's an error
545
name_and_params =
546
extractNameAndParamsFromLine( buffer, line );
547
if( name_and_params == null )
548
throw new ParseException(
549
R.string.error_vcf_malformed );
550
551
// calculate how many chars to skip from beginning of line
552
// so we skip the property "name:" part
553
pos = buffer.position() + name_and_params.length() + 1;
554
555
// reset the saved multi-line state
556
_parser_current_name_and_params = name_and_params;
557
_parser_buffered_value_so_far = "";
558
}
559
560
// get value from buffer, as raw bytes
561
ByteBuffer value;
562
value = ByteBuffer.wrap( buffer.array(), pos,
563
buffer.limit() - pos );
564
565
279
// get parameter parts
566
String[] name_param_parts = name_and_params.split( ";", -1 );
567
for( int i = 0; i < name_param_parts.length; i++ )
568
name_param_parts[ i ] = name_param_parts[ i ].trim();
569
570
// determine whether we care about this entry
571
final HashSet< String > interesting_fields =
572
new HashSet< String >( Arrays.asList( new String[] { "N",
573
"FN", "ORG", "TITLE", "TEL", "EMAIL", "ADR", "LABEL" }
574
) );
575
boolean is_interesting_field =
576
interesting_fields.contains( name_param_parts[ 0 ] );
577
578
// parse encoding parameter
579
String encoding = checkParam( name_param_parts, "ENCODING" );
580
if( encoding != null )
581
encoding = encoding.toUpperCase( Locale.US );
582
if( is_interesting_field && encoding != null &&
583
!encoding.equals( "8BIT" ) &&
584
!encoding.equals( "QUOTED-PRINTABLE" ) )
585
//&& !encoding.equals( "BASE64" ) )
586
{
587
throw new ParseException( R.string.error_vcf_encoding );
588
}
589
590
// parse charset parameter
591
String charset = checkParam( name_param_parts, "CHARSET" );
592
if( charset != null )
593
charset = charset.toUpperCase( Locale.US );
594
if( charset != null &&
595
!charset.equals( "US-ASCII" ) &&
596
!charset.equals( "ASCII" ) &&
597
!charset.equals( "UTF-8" ) )
598
{
599
throw new ParseException( R.string.error_vcf_charset );
600
}
601
602
// do unencoding (or default to a fake unencoding result with
603
// the raw string)
604
UnencodeResult unencoding_result = null;
605
if( encoding != null && encoding.equals( "QUOTED-PRINTABLE" ) )
606
unencoding_result = unencodeQuotedPrintable( value );
607
// else if( encoding != null && encoding.equals( "BASE64" ) )
608
// unencoding_result = unencodeBase64( props[ 1 ], charset );
609
if( unencoding_result != null ) {
610
value = unencoding_result.getBuffer();
611
if( unencoding_result.isAnotherLineRequired() )
612
_parser_multiline_state = MULTILINE_ENCODED;
613
}
614
615
// convert 8-bit US-ASCII charset to UTF-8 (where no charset is
616
// specified for a v2.1 vcard entry, we assume it's US-ASCII)
617
if( ( charset == null && _version.equals( "2.1" ) ) ||
618
( charset != null && (
619
charset.equals( "ASCII" ) ||
620
charset.equals( "US-ASCII" ) ) ) )
621
{
622
value = transcodeAsciiToUtf8( value );
623
}
624
625
// process charset (value is now in UTF-8)
626
String string_value;
627
try {
628
string_value = new String( value.array(), value.position(),
629
value.limit() - value.position(), "UTF-8" );
630
} catch( UnsupportedEncodingException e ) {
631
throw new ParseException( R.string.error_vcf_charset );
632
}
633
634
// for some entries that have semicolon-separated value parts,
635
// check to see if the value ends in an escape character, which
636
// indicates that we have a multi-line value
637
if( ( name_param_parts[ 0 ].equals( "N" ) ||
638
name_param_parts[ 0 ].equals( "ORG" ) ||
639
name_param_parts[ 0 ].equals( "ADR" ) ) &&
640
doesStringEndInAnEscapeChar( string_value ) )
641
{
642
_parser_multiline_state = MULTILINE_ESCAPED;
643
string_value = string_value.substring( 0,
644
string_value.length() - 1 );
645
}
646
647
// now we know whether we're in an encoding multi-line,
648
// determine if we're in a v3 folded multi-line or not
649
if( _parser_multiline_state == MULTILINE_NONE &&
650
_version.equals( "3.0" ) && next_line_looks_folded )
651
{
652
_parser_multiline_state = MULTILINE_FOLDED;
653
}
654
655
// handle multi-lines by buffering them and parsing them when we
656
// are processing the last line in a multi-line sequence
657
if( _parser_multiline_state != MULTILINE_NONE ) {
658
_parser_buffered_value_so_far += string_value;
659
return;
660
}
661
String complete_value =
662
( _parser_buffered_value_so_far + string_value ).trim();
663
664
// ignore empty values
665
if( complete_value.length() < 1 ) return;
280
String[] params = props[ 0 ].split( ";" );
281
for( int i = 0; i < params.length; i++ )
282
params[ i ] = params[ i ].trim();
666
283
667
284
// parse some properties
668
if( name_param_parts[ 0 ].equals( "N" ) )
669
parseN( name_param_parts, complete_value );
670
else if( name_param_parts[ 0 ].equals( "FN" ) )
671
parseFN( name_param_parts, complete_value );
672
else if( name_param_parts[ 0 ].equals( "ORG" ) )
673
parseORG( name_param_parts, complete_value );
674
else if( name_param_parts[ 0 ].equals( "TITLE" ) )
675
parseTITLE( name_param_parts, complete_value );
676
else if( name_param_parts[ 0 ].equals( "TEL" ) )
677
parseTEL( name_param_parts, complete_value );
678
else if( name_param_parts[ 0 ].equals( "EMAIL" ) )
679
parseEMAIL( name_param_parts, complete_value );
680
else if( name_param_parts[ 0 ].equals( "ADR" ) )
681
parseADR( name_param_parts, complete_value );
682
else if( name_param_parts[ 0 ].equals( "LABEL" ) )
683
parseLABEL( name_param_parts, complete_value );
684
}
685
}
686
687
private boolean doesStringEndInAnEscapeChar( String string )
688
{
689
// count the number of backslashes at the end of the string
690
int count = 0;
691
for( int a = string.length() - 1; a >= 0; a-- )
692
if( string.charAt( a ) == '\\' )
693
count++;
694
else
695
break;
696
697
// if there are an even number of backslashes then the final one
698
// doesn't count
699
return ( count & 1 ) == 1;
700
}
701
702
private String[] splitValueByCharacter( String value, char character )
703
{
704
// split string in to parts by specified character
705
ArrayList< String > parts = new ArrayList< String >(
706
Arrays.asList( value.split( "" + character ) ) );
707
708
// go through parts
709
for( int a = 0; a < parts.size(); a++ )
710
{
711
String str = parts.get( a );
712
713
// look for parts that end in an escape character, but ignore
714
// the final part. We've already detected escape chars at the
715
// end of the final part in parseLine() and handled multi-lines
716
// accordingly.
717
if( a < parts.size() - 1 &&
718
doesStringEndInAnEscapeChar( str ) )
719
{
720
// append the escaped character, join the next part to this
721
// part and remove the next part
722
parts.set( a, str.substring( 0, str.length() - 1 ) +
723
character + parts.get( a + 1 ) );
724
parts.remove( a + 1 );
725
726
// re-visit this part
727
a--;
728
continue;
729
}
730
731
// trim and replace string
732
str = str.trim();
733
parts.set( a, str );
734
}
735
736
String[] ret = new String[ parts.size() ];
737
return parts.toArray( ret );
738
}
739
740
private String unescapeValue( String value )
741
{
742
StringBuilder ret = new StringBuilder( value.length() );
743
boolean in_escape = false;
744
for( int a = 0; a < value.length(); a++ )
745
{
746
int c = value.codePointAt( a );
747
748
// process a normal character
749
if( !in_escape ) {
750
if( c == '\\' )
751
in_escape = true;
752
else
753
ret.append( Character.toChars( c ) );
754
continue;
755
}
756
757
// process an escape sequence
758
in_escape = false;
759
switch( c )
760
{
761
case 'N':
762
case 'n':
763
// add newline
764
ret.append( '\n' );
765
break;
766
case '\\':
767
case ',':
768
case ';':
769
// add escaped character
770
ret.append( Character.toChars( c ) );
771
break;
772
default:
773
// unknown escape sequence, so add it unescaped
774
ret.append( "\\" );
775
ret.append( Character.toChars( c ) );
776
break;
777
}
778
}
779
780
return ret.toString();
285
if( params[ 0 ].equals( "N" ) )
286
parseN( params, props[ 1 ] );
287
else if( params[ 0 ].equals( "FN" ) )
288
parseFN( params, props[ 1 ] );
289
else if( params[ 0 ].equals( "ORG" ) )
290
parseORG( params, props[ 1 ] );
291
else if( params[ 0 ].equals( "TEL" ) )
292
parseTEL( params, props[ 1 ] );
293
else if( params[ 0 ].equals( "EMAIL" ) )
294
parseEMAIL( params, props[ 1 ] );
295
}
781
296
}
782
297
783
298
private void parseN( String[] params, String value )
299
throws ParseException, SkipContactException,
300
AbortImportException
784
301
{
785
302
// already got a better name?
786
if( _name_level >= NAMELEVEL_N ) return;
303
if( _nameLevel >= NAMELEVEL_N ) return;
787
304
788
305
// get name parts
789
String[] name_parts = splitValueByCharacter( value, ';' );
306
String[] nameparts = value.split( ";" );
307
for( int i = 0; i < nameparts.length; i++ )
308
nameparts[ i ] = nameparts[ i ].trim();
790
309
791
310
// build name
792
311
value = "";
793
final int[] part_order = { 3, 1, 2, 0, 4 };
794
for( int a = 0; a < part_order.length; a++ )
795
if( name_parts.length > part_order[ a ] &&
796
name_parts[ part_order[ a ] ].length() > 0 )
797
{
798
// split this part in to it's comma-separated bits
799
String[] name_part_parts = splitValueByCharacter(
800
name_parts[ part_order[ a ] ], ',' );
801
for( int b = 0; b < name_part_parts.length; b++ )
802
if( name_part_parts[ b ].length() > 0 )
803
{
804
if( value.length() == 0 ) value += " ";
805
value += name_part_parts[ b ];
806
}
807
}
312
if( nameparts.length > 1 && nameparts[ 1 ].length() > 0 )
313
value += nameparts[ 1 ];
314
if( nameparts[ 0 ].length() > 0 )
315
value += ( value.length() == 0? "" : " " ) + nameparts[ 0 ];
808
316
809
317
// set name
810
setName( unescapeValue( value ) );
811
_name_level = NAMELEVEL_N;
318
setName( undoCharsetAndEncoding( params, value ) );
319
_nameLevel = NAMELEVEL_N;
320
321
// check now to see if we need to import this contact (to avoid
322
// parsing the rest of the vCard unnecessarily)
323
if( !isImportRequired( getName() ) )
324
throw new SkipContactException();
812
325
}
813
326
814
327
private void parseFN( String[] params, String value )
328
throws ParseException, SkipContactException
815
329
{
816
330
// already got a better name?
817
if( _name_level >= NAMELEVEL_FN ) return;
331
if( _nameLevel >= NAMELEVEL_FN ) return;
818
332
819
333
// set name
820
setName( unescapeValue( value ) );
821
_name_level = NAMELEVEL_FN;
334
setName( undoCharsetAndEncoding( params, value ) );
335
_nameLevel = NAMELEVEL_FN;
822
336
}
823
337
824
338
private void parseORG( String[] params, String value )
339
throws ParseException, SkipContactException
825
340
{
341
// already got a better name?
342
if( _nameLevel >= NAMELEVEL_ORG ) return;
343
826
344
// get org parts
827
String[] org_parts = splitValueByCharacter( value, ';' );
828
if( org_parts == null || org_parts.length < 1 ) return;
829
830
// build organisation name
831
StringBuilder builder = new StringBuilder(
832
String.valueOf( org_parts[ 0 ] ) );
833
for( int a = 1; a < org_parts.length; a++ )
834
builder.append( ", " ).append( org_parts[ a ] );
835
String organisation = unescapeValue( builder.toString() );
836
837
// set organisation name (using a title we've previously found)
838
addOrganisation( organisation, _cached_title, true );
839
840
// if we've not previously found a title, store this organisation
841
// name (we'll need it when we find a title to update the
842
// organisation, by name), else if we *have* previously found a
843
// title, clear it (since we just used it)
844
if( _cached_title == null )
845
_cached_organisation = organisation;
846
else
847
_cached_title = null;
848
}
849
850
private void parseTITLE( String[] params, String value )
851
{
852
value = unescapeValue( value );
853
854
// if we previously had an organisation, look it up and append this
855
// title to it
856
if( _cached_organisation != null && hasOrganisations() ) {
857
HashMap< String, ExtraDetail > datas = getOrganisations();
858
ExtraDetail detail = datas.get( _cached_organisation );
859
if( detail != null )
860
detail.setExtra( value );
861
}
862
863
// same as when handling organisation, if we've not previously found
864
// an organisation we store this title, else we clear it (since we
865
// just appended this title to it)
866
if( _cached_organisation == null )
867
_cached_title = value;
868
else
869
_cached_organisation = null;
345
String[] orgparts = value.split( ";" );
346
for( int i = 0; i < orgparts.length; i++ )
347
orgparts[ i ] = orgparts[ i ].trim();
348
349
// build name
350
if( orgparts[ 0 ].length() == 0 && orgparts.length > 1 )
351
value = orgparts[ 1 ];
352
else
353
value = orgparts[ 0 ];
354
355
// set name
356
setName( undoCharsetAndEncoding( params, value ) );
357
_nameLevel = NAMELEVEL_ORG;
870
358
}
871
359
872
360
private void parseTEL( String[] params, String value )
361
throws ParseException
873
362
{
874
363
if( value.length() == 0 ) return;
875
364
876
365
Set< String > types = extractTypes( params, Arrays.asList(
877
"PREF", "HOME", "WORK", "VOICE", "FAX", "MSG", "CELL",
878
"PAGER", "BBS", "MODEM", "CAR", "ISDN", "VIDEO" ) );
366
"PREF", "HOME", "WORK", "VOICE", "FAX", "MSG", "CELL",
367
"PAGER", "BBS", "MODEM", "CAR", "ISDN", "VIDEO" ) );
879
368
880
369
// here's the logic...
881
boolean is_preferred = types.contains( "PREF" );
882
int type;
370
boolean preferred = types.contains( "PREF" );
371
if( types.contains( "VOICE" ) )
372
if( types.contains( "WORK" ) )
373
addPhone( value, PhonesColumns.TYPE_WORK, preferred );
374
else
375
addPhone( value, PhonesColumns.TYPE_HOME, preferred );
376
else if( types.contains( "CELL" ) || types.contains( "VIDEO" ) )
377
addPhone( value, PhonesColumns.TYPE_MOBILE, preferred );
883
378
if( types.contains( "FAX" ) )
884
379
if( types.contains( "HOME" ) )
885
type = TYPE_FAX_HOME;
380
addPhone( value, PhonesColumns.TYPE_FAX_HOME, preferred );
886
381
else
887
type = TYPE_FAX_WORK;
888
else if( types.contains( "CELL" ) || types.contains( "VIDEO" ) )
889
type = TYPE_MOBILE;
890
else if( types.contains( "PAGER" ) )
891
type = TYPE_PAGER;
892
else if( types.contains( "WORK" ) )
893
type = TYPE_WORK;
894
else
895
type = TYPE_HOME;
896
897
// add phone number
898
addNumber( value, type, is_preferred );
382
addPhone( value, PhonesColumns.TYPE_FAX_WORK, preferred );
383
if( types.contains( "PAGER" ) )
384
addPhone( value, PhonesColumns.TYPE_PAGER, preferred );
899
385
}
900
386
901
387
public void parseEMAIL( String[] params, String value )
903
389
if( value.length() == 0 ) return;
904
390
905
391
Set< String > types = extractTypes( params, Arrays.asList(
906
"PREF", "WORK", "HOME", "INTERNET" ) );
907
908
// add email address
909
boolean is_preferred = types.contains( "PREF" );
910
int type;
911
if( types.contains( "WORK" ) )
912
type = TYPE_WORK;
913
else
914
type = TYPE_HOME;
915
916
addEmail( unescapeValue( value ), type, is_preferred );
917
}
918
919
private void parseADR( String[] params, String value )
920
{
921
// get address parts
922
String[] adr_parts = splitValueByCharacter( value, ';' );
923
924
// build address
925
value = "";
926
for( int a = 0; a < adr_parts.length; a++ )
927
if( adr_parts[ a ].length() > 0 )
928
{
929
// split this part in to it's comma-separated bits
930
String[] adr_part_parts =
931
splitValueByCharacter( adr_parts[ a ], ',' );
932
for( int b = 0; b < adr_part_parts.length; b++ )
933
if( adr_part_parts[ b ].length() > 0 )
934
{
935
if( value.length() > 0 ) value += "\n";
936
value += adr_part_parts[ b ];
937
}
938
}
939
940
Set< String > types = extractTypes( params, Arrays.asList(
941
"PREF", "WORK", "HOME" ) );
942
943
// add address
944
int type;
945
if( types.contains( "WORK" ) )
946
type = TYPE_WORK;
947
else
948
type = TYPE_HOME;
949
950
addAddress( unescapeValue( value ), type );
951
}
952
953
private void parseLABEL( String[] params, String value )
954
{
955
Set< String > types = extractTypes( params, Arrays.asList(
956
"PREF", "WORK", "HOME" ) );
957
958
// add address
959
int type;
960
if( types.contains( "WORK" ) )
961
type = TYPE_WORK;
962
else
963
type = TYPE_HOME;
964
965
addAddress( unescapeValue( value ), type );
966
}
967
968
public void finaliseVcard()
969
throws ParseException, ContactNotIdentifiableException
392
"PREF", "WORK", "HOME", "INTERNET" ) );
393
394
// here's the logic...
395
boolean preferred = types.contains( "PREF" );
396
if( types.contains( "WORK" ) )
397
addEmail( value, Contacts.ContactMethods.TYPE_WORK, preferred );
398
else
399
addEmail( value, Contacts.ContactMethods.TYPE_HOME, preferred );
400
}
401
402
public void finaliseParsing()
403
throws ParseException, SkipContactException,
404
AbortImportException
970
405
{
971
406
// missing version (and data is present)
972
if( _version == null && _buffers != null )
407
if( _version == null && _lines != null )
973
408
throw new ParseException( R.string.error_vcf_malformed );
974
409
975
// finalise the parent class
976
finalise();
977
}
978
979
/**
980
* Amongst the params, find the value of the first, only, of any with
981
* the specified name
982
* @param params
983
* @param name
984
* @return a value, or null
985
*/
410
// missing name properties?
411
if( _nameLevel == NAMELEVEL_NONE )
412
throw new ParseException( R.string.error_vcf_noname );
413
414
// check if we should import this one? If we've already got an 'N'-
415
// type name, this will already have been done by parseN() so we
416
// mustn't do this here (or it could prompt twice!)
417
if( _nameLevel < NAMELEVEL_N && !isImportRequired( getName() ) )
418
throw new SkipContactException();
419
}
420
421
private String undoCharsetAndEncoding( String[] params, String value )
422
throws ParseException
423
{
424
// check encoding/charset
425
String charset, encoding;
426
if( ( charset = checkParam( params, "CHARSET" ) ) != null &&
427
!charset.equals( "UTF-8" ) && !charset.equals( "UTF-16" ) )
428
throw new ParseException( R.string.error_vcf_charset );
429
if( ( encoding = checkParam( params, "ENCODING" ) ) != null &&
430
!encoding.equals( "QUOTED-PRINTABLE" ) )
431
throw new ParseException( R.string.error_vcf_encoding );
432
433
// do decoding?
434
if( encoding != null && encoding.equals( "QUOTED-PRINTABLE" ) )
435
return unencodeQuotedPrintable( value, charset );
436
437
// nothing to do!
438
return value;
439
}
440
986
441
private String checkParam( String[] params, String name )
987
442
{
988
String[] res = checkParams( params, name );
989
return res.length > 0? res[ 0 ] : null;
990
}
991
992
/**
993
* Amongst the params, find the values of any with the specified name
994
* @param params
995
* @param name
996
* @return an array of values, or null
997
*/
998
private String[] checkParams( String[] params, String name )
999
{
1000
HashSet< String > ret = new HashSet< String >();
1001
1002
Pattern p = Pattern.compile(
1003
"^" + name + "[ \\t]*=[ \\t]*(\"?)(.*)\\1$" );
443
Pattern p = Pattern.compile( "^" + name + "[ \\t]*=[ \\t]*(.*)$" );
1004
444
for( int i = 0; i < params.length; i++ ) {
1005
445
Matcher m = p.matcher( params[ i ] );
1006
446
if( m.matches() )
1007
ret.add( m.group( 2 ) );
447
return m.group( 1 );
1008
448
}
1009
1010
return (String[]) ret.toArray( new String[ ret.size() ] );
449
return null;
1011
450
}
1012
451
1013
/**
1014
* Amongst the params, return any type values present. For v2.1 vCards,
1015
* those types are just parameters. For v3.0, they are prefixed with
1016
* "TYPE=". There may also be multiple type parameters.
1017
* @param params
1018
* @param a list of type values to look for
1019
* @return a set of present type values
1020
*/
1021
452
private Set< String > extractTypes( String[] params,
1022
List< String > valid_types )
453
List< String > validTypes )
1023
454
{
1024
455
HashSet< String > types = new HashSet< String >();
1025
456
1026
457
// get 3.0-style TYPE= param
1027
String type_params[] = checkParams( params, "TYPE" );
1028
for( int a = 0; a < type_params.length; a++ )
1029
{
1030
// check for a comma-separated list of types (why? this isn't in
1031
// the specs!)
1032
String[] parts = type_params[ a ].split( "," );
1033
for( int i = 0; i < parts.length; i++ )
1034
if( valid_types.contains( parts[ i ] ) )
1035
types.add( parts[ i ] );
458
String typeParam;
459
if( ( typeParam = checkParam( params, "TYPE" ) ) != null ) {
460
String[] bits = typeParam.split( "," );
461
for( int i = 0; i < bits.length; i++ )
462
if( validTypes.contains( bits[ i ] ) )
463
types.add( bits[ i ] );
1036
464
}
1037
465
1038
466
// get 2.1-style type param
1039
467
if( _version.equals( "2.1" ) ) {
1040
468
for( int i = 1; i < params.length; i++ )
1041
if( valid_types.contains( params[ i ] ) )
469
if( validTypes.contains( params[ i ] ) )
1042
470
types.add( params[ i ] );
1043
471
}
1044
472
1045
473
return types;
1046
474
}
1047
475
1048
private UnencodeResult unencodeQuotedPrintable( ByteBuffer in )
476
private String unencodeQuotedPrintable( String str, String charset )
1049
477
{
1050
boolean another = false;
478
// default encoding scheme
479
if( charset == null ) charset = "UTF-8";
1051
480
1052
// unencode quoted-printable encoding, as per RFC1521 section 5.1
1053
byte[] out = new byte[ in.limit() - in.position() ];
481
// unencode quoted-pritable encoding, as per RFC1521 section 5.1
482
byte[] bytes = new byte[ str.length() ];
1054
483
int j = 0;
1055
for( int i = in.position(); i < in.limit(); i++ )
1056
{
1057
// get next char and process...
1058
byte ch = in.array()[ i ];
1059
if( ch == '=' && i < in.limit() - 2 )
1060
{
1061
// we found a =XX format byte, add it
1062
out[ j ] = (byte)(
1063
Character.digit( in.array()[ i + 1 ], 16 ) * 16 +
1064
Character.digit( in.array()[ i + 2 ], 16 ) );
484
for( int i = 0; i < str.length(); i++, j++ ) {
485
char ch = str.charAt( i );
486
if( ch == '=' && i < str.length() - 2 ) {
487
bytes[ j ] = (byte)(
488
Character.digit( str.charAt( i + 1 ), 16 ) * 16 +
489
Character.digit( str.charAt( i + 2 ), 16 ) );
1065
490
i += 2;
1066
491
}
1067
else if( ch == '=' && i == in.limit() - 1 )
1068
{
1069
// we found a '=' at the end of a line signifying a multi-
1070
// line string, so we don't add it.
1071
another = true;
1072
continue;
1073
}
1074
492
else
1075
// just a normal char...
1076
out[ j ] = (byte)ch;
1077
j++;
1078
}
1079
1080
return new UnencodeResult( another, ByteBuffer.wrap( out, 0, j ) );
1081
}
1082
1083
private ByteBuffer transcodeAsciiToUtf8( ByteBuffer in )
1084
{
1085
// transcode
1086
byte[] out = new byte[ ( in.limit() - in.position() ) * 2 ];
1087
int j = 0;
1088
for( int a = in.position(); a < in.limit(); a++ )
1089
{
1090
// if char is < 127, keep it as-is
1091
if( in.array()[ a ] >= 0 )
1092
out[ j++ ] = in.array()[ a ];
1093
1094
// else, convert it to UTF-8
1095
else {
1096
int b = 0xff & (int)in.array()[ a ];
1097
out[ j++ ] = (byte)( 0xc0 | ( b >> 6 ) );
1098
out[ j++ ] = (byte)( 0x80 | ( b & 0x3f ) );
1099
}
1100
}
1101
1102
return ByteBuffer.wrap( out, 0, j );
493
bytes[ j ] = (byte)ch;
494
}
495
try {
496
return new String( bytes, 0, j, charset );
497
} catch( UnsupportedEncodingException e ) { }
498
return null;
1103
499
}
1104
500
}
1105
501
}
Loggerhead is a web-based interface for Bazaar branches
Version: 1.18.2, Revision: 480