(root)/android/import-contacts
» Revision
1
(compared to revision 46)
: 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/waxworlds/importcontacts/ImportContacts.java
- files removed:
- COPYING
- gen
- gen/org
- gen/org/waxworlds
- gen/org/waxworlds/edam
- gen/org/waxworlds/edam/importcontacts
- src/org/waxworlds/edam
- files renamed:
- res/layout/configure_vcf.xml => res/layout/import_vcf.xml
- src/org/waxworlds/edam/importcontacts/ => src/org/waxworlds/importcontacts/
- src/org/waxworlds/edam/importcontacts/ConfigureVCF.java => src/org/waxworlds/importcontacts/ImportVCF.java
- gen/org/waxworlds/edam/importcontacts/R.java => src/org/waxworlds/importcontacts/R.java
- src/org/waxworlds/edam/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 <edam@waxworlds.org>
5
*
6
* This file is part of the Import Contacts program (hereafter referred
7
* to as "this program"). For more information, see
8
* http://www.waxworlds.org/edam/software/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 org.waxworlds.edam.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.NoSuchElementException;
42
13
import java.util.Set;
43
14
import java.util.Vector;
44
15
import java.util.regex.Matcher;
45
16
import java.util.regex.Pattern;
46
17
18
import org.waxworlds.importcontacts.Importer.AbortImportException;
19
47
20
import android.content.SharedPreferences;
48
21
import android.provider.Contacts;
49
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
}
71
44
try
72
45
{
73
46
// open directory
74
String path = "/sdcard" + prefs.getString( "location", "/" );
75
File file = new File( path );
76
if( !file.exists() )
47
String location = prefs.getString( "location", "" );
48
File dir = new File( location );
49
if( !dir.exists() || !dir.isDirectory() )
77
50
showError( R.string.error_locationnotfound );
78
51
79
// directory, or file?
80
if( file.isDirectory() )
81
{
82
// get files
83
class VCardFilter implements FilenameFilter {
84
public boolean accept( File dir, String name ) {
85
return name.toLowerCase().endsWith( ".vcf" );
86
}
87
}
88
files = file.listFiles( new VCardFilter() );
89
}
90
else
91
{
92
// use just this file
93
files = new File[ 1 ];
94
files[ 0 ] = file;
95
}
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() );
96
59
}
97
60
catch( SecurityException e ) {
98
61
showError( R.string.error_locationpermissions );
110
73
countVCardFile( files[ i ] );
111
74
setTmpProgress( i );
112
75
}
113
setProgressMax( _vcard_count ); // will also update tmp progress
76
setProgressMax( _vCardCount ); // will also update tmp progress
114
77
115
78
// import them
116
79
setProgress( 0 );
117
80
for( int i = 0; i < files.length; i++ )
118
81
importVCardFile( files[ i ] );
119
setProgress( _vcard_count );
120
82
}
121
83
122
84
private void countVCardFile( File file ) throws AbortImportException
125
87
{
126
88
// open file
127
89
BufferedReader reader = new BufferedReader(
128
new FileReader( file ) );
90
new FileReader( file ) );
129
91
130
92
// read
131
93
String line;
132
boolean in_vcard = false;
94
boolean inVCard = false;
133
95
while( ( line = reader.readLine() ) != null )
134
96
{
135
if( !in_vcard ) {
97
if( !inVCard ) {
136
98
// look for vcard beginning
137
if( line.matches( "^BEGIN:VCARD" ) ) {
138
in_vcard = true;
139
_vcard_count++;
99
if( line.matches( "^BEGIN[ \\t]*:[ \\t]*VCARD" ) ) {
100
inVCard = true;
101
_vCardCount++;
140
102
}
141
103
}
142
else if( line.matches( "^END:VCARD" ) )
143
in_vcard = false;
104
else if( line.matches( "^END[ \\t]*:[ \\t]*VCARD" ) )
105
inVCard = false;
144
106
}
145
107
146
108
}
147
109
catch( FileNotFoundException e ) {
148
showError( getText( R.string.error_filenotfound ) +
149
file.getName() );
110
showError( getText( R.string.error_filenotfound ) + file.getName() );
150
111
}
151
112
catch( IOException e ) {
152
113
showError( getText( R.string.error_ioerror ) + file.getName() );
155
116
156
117
private void importVCardFile( File file ) throws AbortImportException
157
118
{
158
// check file is good
159
if( !file.exists() )
160
showError( getText( R.string.error_filenotfound ) +
161
file.getName() );
162
if( file.length() == 0 )
163
showError( getText( R.string.error_fileisempty ) +
164
file.getName() );
165
166
119
try
167
120
{
168
// open/read file
169
FileInputStream istream = new FileInputStream( file );
170
byte[] content = new byte[ (int)file.length() ];
171
istream.read( content );
172
istream = null;
173
174
// import
175
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() );
176
132
}
177
133
catch( FileNotFoundException e ) {
178
showError( getText( R.string.error_filenotfound ) +
179
file.getName() );
134
showError( getText( R.string.error_filenotfound ) + file.getName() );
180
135
}
181
136
catch( IOException e ) {
182
137
showError( getText( R.string.error_ioerror ) + file.getName() );
183
138
}
184
139
}
185
140
186
private void importVCardFileContent( byte[] content, String fileName )
187
throws AbortImportException
141
private void importVCardFileContent( String content, String fileName )
142
throws AbortImportException
188
143
{
189
// go through lines
190
Vcard vcard = null;
191
int vcard_start_line = 0;
192
ContentLineIterator cli = new ContentLineIterator( content );
193
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++ )
194
154
{
195
ByteBuffer buffer = cli.next();
196
197
// get a US-ASCII version of the line for processing
198
String line;
199
try {
200
line = new String( buffer.array(), buffer.position(),
201
buffer.limit() - buffer.position(), "US-ASCII" );
202
}
203
catch( UnsupportedEncodingException e ) {
204
// we know US-ASCII is supported, so appease the compiler...
205
line = "";
206
}
207
208
if( vcard == null ) {
155
String line = lines[ i ];
156
157
if( vCard == null ) {
209
158
// look for vcard beginning
210
if( line.matches( "^BEGIN:VCARD" ) ) {
211
setProgress( _progress++ );
212
vcard = new Vcard();
213
vcard_start_line = cli.getLineNumber();
159
if( line.matches( "^BEGIN[ \\t]*:[ \\t]*VCARD" ) ) {
160
setProgress( ++_progress );
161
vCard = new VCard();
214
162
}
215
163
}
216
164
else {
217
165
// look for vcard content or ending
218
if( line.matches( "^END:VCARD" ) )
166
if( line.matches( "^END[ \\t]*:[ \\t]*VCARD" ) )
219
167
{
220
// finalise the vcard/contact
168
// store vcard and do away with it
221
169
try {
222
vcard.finaliseVcard();
223
224
// pass the finalised contact to the importer
225
importContact( vcard );
226
}
227
catch( Vcard.ParseException e ) {
228
if( !showContinue(
229
getText( R.string.error_vcf_parse ).toString()
230
+ fileName +
231
getText( R.string.error_vcf_parse_line ).toString()
232
+ cli.getLineNumber() + ":\n" + e.getMessage() ) )
233
{
234
finish( ACTION_ABORT );
235
}
236
else
237
skipContact();
238
}
239
catch( ContactData.ContactNotIdentifiableException e ) {
240
if( !showContinue(
241
getText( R.string.error_vcf_parse ).toString()
242
+ fileName +
243
getText( R.string.error_vcf_parse_line ).toString()
244
+ vcard_start_line + ":\n" + getText(
245
R.string.error_vcf_notenoughinfo ).toString()
246
) )
247
{
248
finish( ACTION_ABORT );
249
}
250
else
251
skipContact();
252
}
253
254
// discard this vcard
255
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;
256
185
}
257
186
else
258
187
{
259
188
// try giving the line to the vcard
260
189
try {
261
vcard.parseLine( buffer, line,
262
cli.doesNextLineLookFolded() );
190
vCard.parseLine( line );
263
191
}
264
catch( Vcard.ParseException e ) {
192
catch( VCard.ParseException e ) {
265
193
skipContact();
266
194
if( !showContinue(
267
getText( R.string.error_vcf_parse ).toString()
268
+ fileName +
269
getText( R.string.error_vcf_parse_line ).toString()
270
+ cli.getLineNumber() + "\n" + e.getMessage() ) )
271
{
272
finish( ACTION_ABORT );
273
}
195
getText( R.string.error_vcf_parse ).toString()
196
+ fileName + "\n" + e.getMessage() ) )
197
abort();
274
198
275
199
// although we're continuing, we still need to abort
276
200
// this vCard. Further lines will be ignored until we
277
201
// get to another BEGIN:VCARD line.
278
vcard = null;
202
vCard = null;
279
203
}
280
catch( Vcard.SkipImportException e ) {
204
catch( VCard.SkipContactException e ) {
281
205
skipContact();
282
206
// abort this vCard. Further lines will be ignored until
283
207
// we get to another BEGIN:VCARD line.
284
vcard = null;
208
vCard = null;
285
209
}
286
210
}
287
211
}
288
212
}
289
213
}
290
214
291
class ContentLineIterator implements Iterator< ByteBuffer >
292
{
293
protected byte[] _content = null;
294
protected int _pos = 0;
295
protected int _line = 0;
296
297
public ContentLineIterator( byte[] content )
298
{
299
_content = content;
300
}
301
302
@Override
303
public boolean hasNext()
304
{
305
return _pos < _content.length;
306
}
307
308
@Override
309
public ByteBuffer next()
310
{
311
int initial_pos = _pos;
312
313
// find newline
314
for( ; _pos < _content.length; _pos++ )
315
if( _content[ _pos ] == '\n' )
316
{
317
// adjust for a \r preceding the \n
318
int to = ( _pos > 0 && _content[ _pos - 1 ] == '\r' &&
319
_pos > initial_pos )? _pos - 1 : _pos;
320
_pos++;
321
_line++;
322
return ByteBuffer.wrap( _content, initial_pos,
323
to - initial_pos );
324
}
325
326
// we didn't find one, but were there bytes left?
327
if( _pos != initial_pos ) {
328
int to = _pos;
329
_pos++;
330
_line++;
331
return ByteBuffer.wrap( _content, initial_pos,
332
to - initial_pos );
333
}
334
335
// no bytes left
336
throw new NoSuchElementException();
337
}
338
339
@Override
340
public void remove()
341
{
342
throw new UnsupportedOperationException();
343
}
344
345
/**
346
* Does the next line, if there is one, look like it should be folded
347
* onto the end of this one?
348
* @return
349
*/
350
public boolean doesNextLineLookFolded()
351
{
352
return _pos > 0 && _pos < _content.length &&
353
_content[ _pos - 1 ] == '\n' && _content[ _pos ] == ' ';
354
}
355
356
public int getLineNumber()
357
{
358
return _line;
359
}
360
}
361
362
private class Vcard extends ContactData
215
private class VCard extends ContactData
363
216
{
364
217
private final static int NAMELEVEL_NONE = 0;
365
private final static int NAMELEVEL_N = 1;
218
private final static int NAMELEVEL_ORG = 1;
366
219
private final static int NAMELEVEL_FN = 2;
367
368
private final static int MULTILINE_NONE = 0;
369
private final static int MULTILINE_ENCODED = 1; // v2.1 quoted-printable
370
private final static int MULTILINE_ESCAPED = 2; // v2.1 \\CRLF
371
private final static int MULTILINE_FOLDED = 3; // v3.0 folding
220
private final static int NAMELEVEL_N = 3;
372
221
373
222
private String _version = null;
374
private Vector< ByteBuffer > _buffers = null;
375
private int _name_level = NAMELEVEL_NONE;
376
private int _parser_multiline_state = MULTILINE_NONE;
377
private String _parser_current_name_and_params = null;
378
private String _parser_buffered_value_so_far = "";
379
private String _cached_organisation = null;
380
private String _cached_title = null;
381
382
protected class UnencodeResult
383
{
384
private boolean _another_line_required;
385
private ByteBuffer _buffer;
386
387
public UnencodeResult( boolean another_line_required,
388
ByteBuffer buffer )
389
{
390
_another_line_required = another_line_required;
391
_buffer = buffer;
392
}
393
394
public boolean isAnotherLineRequired()
395
{
396
return _another_line_required;
397
}
398
399
public ByteBuffer getBuffer()
400
{
401
return _buffer;
402
}
403
}
404
405
@SuppressWarnings("serial")
223
private Vector< String > _lines = null;
224
private int _nameLevel = NAMELEVEL_NONE;
225
406
226
protected class ParseException extends Exception
407
227
{
408
@SuppressWarnings("unused")
409
228
public ParseException( String error )
410
229
{
411
230
super( error );
413
232
414
233
public ParseException( int res )
415
234
{
416
super( VcardImporter.this.getText( res ).toString() );
417
}
418
}
419
420
@SuppressWarnings("serial")
421
protected class SkipImportException extends Exception { }
422
423
private String extractCollonPartFromLine( ByteBuffer buffer,
424
String line, boolean former )
425
{
426
String ret = null;
427
428
// get a US-ASCII version of the line for processing, unless we were
429
// supplied with one
430
if( line == null ) {
431
try {
432
line = new String( buffer.array(), buffer.position(),
433
buffer.limit() - buffer.position(), "US-ASCII" );
434
}
435
catch( UnsupportedEncodingException e ) {
436
// we know US-ASCII is supported, so appease the compiler...
437
line = "";
438
}
439
}
440
441
// split line into name and value parts and check to make sure we
442
// only got 2 parts and that the first part is not zero in length
443
String[] parts = line.split( ":", 2 );
444
if( parts.length == 2 && parts[ 0 ].length() > 0 )
445
ret = parts[ former? 0 : 1 ];
446
447
return ret;
448
}
449
450
private String extractNameAndParamsFromLine( ByteBuffer buffer,
451
String line )
452
{
453
return extractCollonPartFromLine( buffer, line, true );
454
}
455
456
private String extractValueFromLine( ByteBuffer buffer, String line )
457
{
458
return extractCollonPartFromLine( buffer, line, false );
459
}
460
461
public void parseLine( ByteBuffer buffer, String line,
462
boolean next_line_looks_folded )
463
throws ParseException, SkipImportException,
464
AbortImportException
465
{
466
// 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
467
253
if( _version == null )
468
254
{
469
// tentatively get name and params from line
470
String name_and_params =
471
extractNameAndParamsFromLine( buffer, line );
472
473
// is it a version line?
474
if( name_and_params != null &&
475
name_and_params.equals( "VERSION" ) )
255
if( props[ 0 ].equals( "VERSION" ) )
476
256
{
477
// yes, get it!
478
String value = extractValueFromLine( buffer, line );
479
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" ) )
480
260
throw new ParseException( R.string.error_vcf_version );
481
_version = value;
261
_version = props[ 1 ];
482
262
483
// parse any buffers we've been accumulating while we waited
484
// for a version
485
if( _buffers != null )
486
for( int i = 0; i < _buffers.size(); i++ )
487
parseLine( _buffers.get( i ), null,
488
i + 1 < _buffers.size() &&
489
_buffers.get( i + 1 ).hasRemaining() &&
490
_buffers.get( i + 1 ).get(
491
_buffers.get( i + 1 ).position() ) == ' ' );
492
_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;
493
268
}
494
269
else
495
270
{
496
// no, so stash this line till we get a version
497
if( _buffers == null )
498
_buffers = new Vector< ByteBuffer >();
499
_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 );
500
275
}
501
276
}
502
277
else
503
278
{
504
// name and params and the position in the buffer where the
505
// "value" part of the line start
506
String name_and_params;
507
int pos;
508
509
if( _parser_multiline_state != MULTILINE_NONE )
510
{
511
// if we're currently in a multi-line value, use the stored
512
// property name and parameters
513
name_and_params = _parser_current_name_and_params;
514
515
// skip some initial line characters, depending on the type
516
// of multi-line we're handling
517
pos = buffer.position();
518
switch( _parser_multiline_state )
519
{
520
case MULTILINE_FOLDED:
521
pos++;
522
break;
523
case MULTILINE_ENCODED:
524
while( pos < buffer.limit() && (
525
buffer.get( pos ) == ' ' ||
526
buffer.get( pos ) == '\t' ) )
527
{
528
pos++;
529
}
530
break;
531
default:
532
// do nothing
533
}
534
535
// take us out of multi-line so that we can re-detect that
536
// this line is a multi-line or not
537
_parser_multiline_state = MULTILINE_NONE;
538
}
539
else
540
{
541
// get name and params from line, and since we're not
542
// parsing a subsequent line in a multi-line, this should
543
// not fail, or it's an error
544
name_and_params =
545
extractNameAndParamsFromLine( buffer, line );
546
if( name_and_params == null )
547
throw new ParseException(
548
R.string.error_vcf_malformed );
549
550
// calculate how many chars to skip from beginning of line
551
// so we skip the property "name:" part
552
pos = buffer.position() + name_and_params.length() + 1;
553
554
// reset the saved multi-line state
555
_parser_current_name_and_params = name_and_params;
556
_parser_buffered_value_so_far = "";
557
}
558
559
// get value from buffer, as raw bytes
560
ByteBuffer value;
561
value = ByteBuffer.wrap( buffer.array(), pos,
562
buffer.limit() - pos );
563
564
279
// get parameter parts
565
String[] name_param_parts = name_and_params.split( ";", -1 );
566
for( int i = 0; i < name_param_parts.length; i++ )
567
name_param_parts[ i ] = name_param_parts[ i ].trim();
568
569
// determine whether we care about this entry
570
final HashSet< String > interesting_fields =
571
new HashSet< String >( Arrays.asList( new String[]
572
{ "N", "FN", "ORG", "TITLE", "TEL", "EMAIL", "ADR" }
573
) );
574
boolean is_interesting_field =
575
interesting_fields.contains( name_param_parts[ 0 ] );
576
577
// parse encoding parameter
578
String encoding = checkParam( name_param_parts, "ENCODING" );
579
if( encoding != null ) encoding = encoding.toUpperCase();
580
if( is_interesting_field && encoding != null &&
581
!encoding.equals( "8BIT" ) &&
582
!encoding.equals( "QUOTED-PRINTABLE" ) )
583
//&& !encoding.equals( "BASE64" ) )
584
{
585
throw new ParseException( R.string.error_vcf_encoding );
586
}
587
588
// parse charset parameter
589
String charset = checkParam( name_param_parts, "CHARSET" );
590
if( charset != null ) charset = charset.toUpperCase();
591
if( charset != null &&
592
!charset.equals( "US-ASCII" ) &&
593
!charset.equals( "ASCII" ) &&
594
!charset.equals( "UTF-8" ) )
595
{
596
throw new ParseException( R.string.error_vcf_charset );
597
}
598
599
// do unencoding (or default to a fake unencoding result with
600
// the raw string)
601
UnencodeResult unencoding_result = null;
602
if( encoding != null && encoding.equals( "QUOTED-PRINTABLE" ) )
603
unencoding_result = unencodeQuotedPrintable( value );
604
// else if( encoding != null && encoding.equals( "BASE64" ) )
605
// unencoding_result = unencodeBase64( props[ 1 ], charset );
606
if( unencoding_result != null ) {
607
value = unencoding_result.getBuffer();
608
if( unencoding_result.isAnotherLineRequired() )
609
_parser_multiline_state = MULTILINE_ENCODED;
610
}
611
612
// convert 8-bit US-ASCII charset to UTF-8 (where no charset is
613
// specified for a v2.1 vcard entry, we assume it's US-ASCII)
614
if( ( charset == null && _version.equals( "2.1" ) ) ||
615
( charset != null && (
616
charset.equals( "ASCII" ) ||
617
charset.equals( "US-ASCII" ) ) ) )
618
{
619
value = transcodeAsciiToUtf8( value );
620
}
621
622
// process charset (value is now in UTF-8)
623
String string_value;
624
try {
625
string_value = new String( value.array(), value.position(),
626
value.limit() - value.position(), "UTF-8" );
627
} catch( UnsupportedEncodingException e ) {
628
throw new ParseException( R.string.error_vcf_charset );
629
}
630
631
// for some entries that have semicolon-separated value parts,
632
// check to see if the value ends in an escape character, which
633
// indicates that we have a multi-line value
634
if( ( name_param_parts[ 0 ].equals( "N" ) ||
635
name_param_parts[ 0 ].equals( "ORG" ) ||
636
name_param_parts[ 0 ].equals( "ADR" ) ) &&
637
doesStringEndInAnEscapeChar( string_value ) )
638
{
639
_parser_multiline_state = MULTILINE_ESCAPED;
640
string_value = string_value.substring( 0,
641
string_value.length() - 1 );
642
}
643
644
// now we know whether we're in an encoding multi-line,
645
// determine if we're in a v3 folded multi-line or not
646
if( _parser_multiline_state == MULTILINE_NONE &&
647
_version.equals( "3.0" ) && next_line_looks_folded )
648
{
649
_parser_multiline_state = MULTILINE_FOLDED;
650
}
651
652
// handle multi-lines by buffering them and parsing them when we
653
// are processing the last line in a multi-line sequence
654
if( _parser_multiline_state != MULTILINE_NONE ) {
655
_parser_buffered_value_so_far += string_value;
656
return;
657
}
658
String complete_value =
659
( _parser_buffered_value_so_far + string_value ).trim();
660
661
// ignore empty values
662
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();
663
283
664
284
// parse some properties
665
if( name_param_parts[ 0 ].equals( "N" ) )
666
parseN( name_param_parts, complete_value );
667
else if( name_param_parts[ 0 ].equals( "FN" ) )
668
parseFN( name_param_parts, complete_value );
669
else if( name_param_parts[ 0 ].equals( "ORG" ) )
670
parseORG( name_param_parts, complete_value );
671
else if( name_param_parts[ 0 ].equals( "TITLE" ) )
672
parseTITLE( name_param_parts, complete_value );
673
else if( name_param_parts[ 0 ].equals( "TEL" ) )
674
parseTEL( name_param_parts, complete_value );
675
else if( name_param_parts[ 0 ].equals( "EMAIL" ) )
676
parseEMAIL( name_param_parts, complete_value );
677
else if( name_param_parts[ 0 ].equals( "ADR" ) )
678
parseADR( name_param_parts, complete_value );
679
}
680
}
681
682
private boolean doesStringEndInAnEscapeChar( String string )
683
{
684
// count the number of backslashes at the end of the string
685
int count = 0;
686
for( int a = string.length() - 1; a >= 0; a-- )
687
if( string.charAt( a ) == '\\' )
688
count++;
689
else
690
break;
691
692
// if there are an even number of backslashes then the final one
693
// doesn't count
694
return ( count & 1 ) == 1;
695
}
696
697
private String[] splitValueByCharacter( String value, char character )
698
{
699
// split string in to parts by specified character
700
ArrayList< String > parts = new ArrayList< String >(
701
Arrays.asList( value.split( "" + character ) ) );
702
703
// go through parts
704
for( int a = 0; a < parts.size(); a++ )
705
{
706
String str = parts.get( a );
707
708
// look for parts that end in an escape character, but ignore
709
// the final part. We've already detected escape chars at the
710
// end of the final part in parseLine() and handled multi-lines
711
// accordingly.
712
if( a < parts.size() - 1 &&
713
doesStringEndInAnEscapeChar( str ) )
714
{
715
// append the escaped character, join the next part to this
716
// part and remove the next part
717
parts.set( a, str.substring( 0, str.length() - 1 ) +
718
character + parts.get( a + 1 ) );
719
parts.remove( a + 1 );
720
721
// re-visit this part
722
a--;
723
continue;
724
}
725
726
// trim and replace string
727
str = str.trim();
728
parts.set( a, str );
729
}
730
731
String[] ret = new String[ parts.size() ];
732
return parts.toArray( ret );
733
}
734
735
private String unescapeValue( String value )
736
{
737
StringBuilder ret = new StringBuilder( value.length() );
738
boolean in_escape = false;
739
for( int a = 0; a < value.length(); a++ )
740
{
741
int c = value.codePointAt( a );
742
743
// process a normal character
744
if( !in_escape ) {
745
if( c == '\\' )
746
in_escape = true;
747
else
748
ret.append( Character.toChars( c ) );
749
continue;
750
}
751
752
// process an escape sequence
753
in_escape = false;
754
switch( c )
755
{
756
case 'N':
757
case 'n':
758
// add newline
759
ret.append( '\n' );
760
break;
761
case '\\':
762
case ',':
763
case ';':
764
// add escaped character
765
ret.append( Character.toChars( c ) );
766
break;
767
default:
768
// unknown escape sequence, so add it unescaped
769
ret.append( "\\" );
770
ret.append( Character.toChars( c ) );
771
break;
772
}
773
}
774
775
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
}
776
296
}
777
297
778
298
private void parseN( String[] params, String value )
299
throws ParseException, SkipContactException,
300
AbortImportException
779
301
{
780
302
// already got a better name?
781
if( _name_level >= NAMELEVEL_N ) return;
303
if( _nameLevel >= NAMELEVEL_N ) return;
782
304
783
305
// get name parts
784
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();
785
309
786
310
// build name
787
311
value = "";
788
final int[] part_order = { 3, 1, 2, 0, 4 };
789
for( int a = 0; a < part_order.length; a++ )
790
if( name_parts.length > part_order[ a ] &&
791
name_parts[ part_order[ a ] ].length() > 0 )
792
{
793
// split this part in to it's comma-separated bits
794
String[] name_part_parts = splitValueByCharacter(
795
name_parts[ part_order[ a ] ], ',' );
796
for( int b = 0; b < name_part_parts.length; b++ )
797
if( name_part_parts[ b ].length() > 0 )
798
{
799
if( value.length() == 0 ) value += " ";
800
value += name_part_parts[ b ];
801
}
802
}
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 ];
803
316
804
317
// set name
805
setName( unescapeValue( value ) );
806
_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();
807
325
}
808
326
809
327
private void parseFN( String[] params, String value )
328
throws ParseException, SkipContactException
810
329
{
811
330
// already got a better name?
812
if( _name_level >= NAMELEVEL_FN ) return;
331
if( _nameLevel >= NAMELEVEL_FN ) return;
813
332
814
333
// set name
815
setName( unescapeValue( value ) );
816
_name_level = NAMELEVEL_FN;
334
setName( undoCharsetAndEncoding( params, value ) );
335
_nameLevel = NAMELEVEL_FN;
817
336
}
818
337
819
338
private void parseORG( String[] params, String value )
339
throws ParseException, SkipContactException
820
340
{
341
// already got a better name?
342
if( _nameLevel >= NAMELEVEL_ORG ) return;
343
821
344
// get org parts
822
String[] org_parts = splitValueByCharacter( value, ';' );
823
if( org_parts == null || org_parts.length < 1 ) return;
824
825
// build organisation name
826
StringBuilder builder = new StringBuilder(
827
String.valueOf( org_parts[ 0 ] ) );
828
for( int a = 1; a < org_parts.length; a++ )
829
builder.append( ", " ).append( org_parts[ a ] );
830
String organisation = unescapeValue( builder.toString() );
831
832
// set organisation name (using a title we've previously found)
833
addOrganisation( organisation, _cached_title, true );
834
835
// if we've not previously found a title, store this organisation
836
// name (we'll need it when we find a title to update the
837
// organisation, by name), else if we *have* previously found a
838
// title, clear it (since we just used it)
839
if( _cached_title == null )
840
_cached_organisation = organisation;
841
else
842
_cached_title = null;
843
}
844
845
private void parseTITLE( String[] params, String value )
846
{
847
value = unescapeValue( value );
848
849
// if we previously had an organisation, look it up and append this
850
// title to it
851
if( _cached_organisation != null && hasOrganisations() ) {
852
HashMap< String, ExtraDetail > datas = getOrganisations();
853
ExtraDetail detail = datas.get( _cached_organisation );
854
if( detail != null )
855
detail.setExtra( value );
856
}
857
858
// same as when handling organisation, if we've not previously found
859
// an organisation we store this title, else we clear it (since we
860
// just appended this title to it)
861
if( _cached_organisation == null )
862
_cached_title = value;
863
else
864
_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;
865
358
}
866
359
867
360
private void parseTEL( String[] params, String value )
361
throws ParseException
868
362
{
869
363
if( value.length() == 0 ) return;
870
364
871
365
Set< String > types = extractTypes( params, Arrays.asList(
872
"PREF", "HOME", "WORK", "VOICE", "FAX", "MSG", "CELL",
873
"PAGER", "BBS", "MODEM", "CAR", "ISDN", "VIDEO" ) );
366
"PREF", "HOME", "WORK", "VOICE", "FAX", "MSG", "CELL",
367
"PAGER", "BBS", "MODEM", "CAR", "ISDN", "VIDEO" ) );
874
368
875
369
// here's the logic...
876
boolean is_preferred = types.contains( "PREF" );
877
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 );
878
378
if( types.contains( "FAX" ) )
879
379
if( types.contains( "HOME" ) )
880
type = PhonesColumns.TYPE_FAX_HOME;
380
addPhone( value, PhonesColumns.TYPE_FAX_HOME, preferred );
881
381
else
882
type = PhonesColumns.TYPE_FAX_WORK;
883
else if( types.contains( "CELL" ) || types.contains( "VIDEO" ) )
884
type = PhonesColumns.TYPE_MOBILE;
885
else if( types.contains( "PAGER" ) )
886
type = PhonesColumns.TYPE_PAGER;
887
else if( types.contains( "WORK" ) )
888
type = PhonesColumns.TYPE_WORK;
889
else
890
type = PhonesColumns.TYPE_HOME;
891
892
// add phone number
893
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 );
894
385
}
895
386
896
387
public void parseEMAIL( String[] params, String value )
898
389
if( value.length() == 0 ) return;
899
390
900
391
Set< String > types = extractTypes( params, Arrays.asList(
901
"PREF", "WORK", "HOME", "INTERNET" ) );
902
903
// add email address
904
boolean is_preferred = types.contains( "PREF" );
905
int type;
906
if( types.contains( "WORK" ) )
907
type = Contacts.ContactMethods.TYPE_WORK;
908
else
909
type = Contacts.ContactMethods.TYPE_HOME;
910
911
addEmail( unescapeValue( value ), type, is_preferred );
912
}
913
914
private void parseADR( String[] params, String value )
915
{
916
// get address parts
917
String[] adr_parts = splitValueByCharacter( value, ';' );
918
919
// build address
920
value = "";
921
for( int a = 0; a < adr_parts.length; a++ )
922
if( adr_parts[ a ].length() > 0 )
923
{
924
// split this part in to it's comma-separated bits
925
String[] adr_part_parts =
926
splitValueByCharacter( adr_parts[ a ], ',' );
927
for( int b = 0; b < adr_part_parts.length; b++ )
928
if( adr_part_parts[ b ].length() > 0 )
929
{
930
if( value.length() > 0 ) value += "\n";
931
value += adr_part_parts[ b ];
932
}
933
}
934
935
Set< String > types = extractTypes( params, Arrays.asList(
936
"PREF", "WORK", "HOME", "INTERNET" ) );
937
938
// add address
939
int type;
940
if( types.contains( "WORK" ) )
941
type = Contacts.ContactMethods.TYPE_WORK;
942
else
943
type = Contacts.ContactMethods.TYPE_HOME;
944
945
addAddress( unescapeValue( value ), type );
946
}
947
948
public void finaliseVcard()
949
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
950
405
{
951
406
// missing version (and data is present)
952
if( _version == null && _buffers != null )
407
if( _version == null && _lines != null )
953
408
throw new ParseException( R.string.error_vcf_malformed );
954
409
955
// finalise the parent class
956
finalise();
957
}
958
959
/**
960
* Amongst the params, find the value of the first, only, of any with
961
* the specified name
962
* @param params
963
* @param name
964
* @return a value, or null
965
*/
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
966
441
private String checkParam( String[] params, String name )
967
442
{
968
String[] res = checkParams( params, name );
969
return res.length > 0? res[ 0 ] : null;
970
}
971
972
/**
973
* Amongst the params, find the values of any with the specified name
974
* @param params
975
* @param name
976
* @return an array of values, or null
977
*/
978
private String[] checkParams( String[] params, String name )
979
{
980
HashSet< String > ret = new HashSet< String >();
981
982
Pattern p = Pattern.compile(
983
"^" + name + "[ \\t]*=[ \\t]*(\"?)(.*)\\1$" );
443
Pattern p = Pattern.compile( "^" + name + "[ \\t]*=[ \\t]*(.*)$" );
984
444
for( int i = 0; i < params.length; i++ ) {
985
445
Matcher m = p.matcher( params[ i ] );
986
446
if( m.matches() )
987
ret.add( m.group( 2 ) );
447
return m.group( 1 );
988
448
}
989
990
return (String[]) ret.toArray( new String[ ret.size() ] );
449
return null;
991
450
}
992
451
993
/**
994
* Amongst the params, return any type values present. For v2.1 vCards,
995
* those types are just parameters. For v3.0, they are prefixed with
996
* "TYPE=". There may also be multiple type parameters.
997
* @param params
998
* @param a list of type values to look for
999
* @return a set of present type values
1000
*/
1001
452
private Set< String > extractTypes( String[] params,
1002
List< String > valid_types )
453
List< String > validTypes )
1003
454
{
1004
455
HashSet< String > types = new HashSet< String >();
1005
456
1006
457
// get 3.0-style TYPE= param
1007
String type_params[] = checkParams( params, "TYPE" );
1008
for( int a = 0; a < type_params.length; a++ )
1009
{
1010
// check for a comma-separated list of types (why? this isn't in
1011
// the specs!)
1012
String[] parts = type_params[ a ].split( "," );
1013
for( int i = 0; i < parts.length; i++ )
1014
if( valid_types.contains( parts[ i ] ) )
1015
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 ] );
1016
464
}
1017
465
1018
466
// get 2.1-style type param
1019
467
if( _version.equals( "2.1" ) ) {
1020
468
for( int i = 1; i < params.length; i++ )
1021
if( valid_types.contains( params[ i ] ) )
469
if( validTypes.contains( params[ i ] ) )
1022
470
types.add( params[ i ] );
1023
471
}
1024
472
1025
473
return types;
1026
474
}
1027
475
1028
private UnencodeResult unencodeQuotedPrintable( ByteBuffer in )
476
private String unencodeQuotedPrintable( String str, String charset )
1029
477
{
1030
boolean another = false;
478
// default encoding scheme
479
if( charset == null ) charset = "UTF-8";
1031
480
1032
// unencode quoted-printable encoding, as per RFC1521 section 5.1
1033
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() ];
1034
483
int j = 0;
1035
for( int i = in.position(); i < in.limit(); i++ )
1036
{
1037
// get next char and process...
1038
byte ch = in.array()[ i ];
1039
if( ch == '=' && i < in.limit() - 2 )
1040
{
1041
// we found a =XX format byte, add it
1042
out[ j ] = (byte)(
1043
Character.digit( in.array()[ i + 1 ], 16 ) * 16 +
1044
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 ) );
1045
490
i += 2;
1046
491
}
1047
else if( ch == '=' && i == in.limit() - 1 )
1048
{
1049
// we found a '=' at the end of a line signifying a multi-
1050
// line string, so we don't add it.
1051
another = true;
1052
continue;
1053
}
1054
492
else
1055
// just a normal char...
1056
out[ j ] = (byte)ch;
1057
j++;
1058
}
1059
1060
return new UnencodeResult( another, ByteBuffer.wrap( out, 0, j ) );
1061
}
1062
1063
private ByteBuffer transcodeAsciiToUtf8( ByteBuffer in )
1064
{
1065
// transcode
1066
byte[] out = new byte[ ( in.limit() - in.position() ) * 2 ];
1067
int j = 0;
1068
for( int a = in.position(); a < in.limit(); a++ )
1069
{
1070
// if char is < 127, keep it as-is
1071
if( in.array()[ a ] >= 0 )
1072
out[ j++ ] = in.array()[ a ];
1073
1074
// else, convert it to UTF-8
1075
else {
1076
int b = 0xff & (int)in.array()[ a ];
1077
out[ j++ ] = (byte)( 0xc0 | ( b >> 6 ) );
1078
out[ j++ ] = (byte)( 0x80 | ( b & 0x3f ) );
1079
}
1080
}
1081
1082
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;
1083
499
}
1084
500
}
1085
501
}
Loggerhead is a web-based interface for Bazaar branches
Version: 1.18.2, Revision: 480