(root)/android/import-contacts
» Revision
45
: src/org/waxworlds/edam/importcontacts/VcardImporter.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/edam/importcontacts/VcardImporter.java
- browse files at revision 45
- compare with another revision
- compare with revision 57
- download diff
- download tarball
- view history from revision 45
- Committer: edam
- Date: 2011-06-04 13:16:20 UTC
- Revision ID: edam@waxworlds.org-20110604131620-hean9j66r3f5i72h
- fix UTF-8 unencoding by default on v3.0 vCards
- proper unescaping of strings in v3.0 vCards (also works for v2.1, although the 2.1 specs don't mention it)
- proper unescaping of strings in v3.0 vCards (also works for v2.1, although the 2.1 specs don't mention it)
- files modified:
- TODO
added
removed
src/org/waxworlds/edam/importcontacts/VcardImporter.java
362
362
private class Vcard extends ContactData
363
363
{
364
364
private final static int NAMELEVEL_NONE = 0;
365
private final static int NAMELEVEL_FN = 1;
366
private final static int NAMELEVEL_N = 2;
365
private final static int NAMELEVEL_N = 1;
366
private final static int NAMELEVEL_FN = 2;
367
367
368
368
private final static int MULTILINE_NONE = 0;
369
369
private final static int MULTILINE_ENCODED = 1; // v2.1 quoted-printable
609
609
_parser_multiline_state = MULTILINE_ENCODED;
610
610
}
611
611
612
// convert 8-bit ASCII charset to US-ASCII
613
if( charset == null || charset.equals( "ASCII" ) ) {
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
{
614
619
value = transcodeAsciiToUtf8( value );
615
charset = "UTF-8";
616
620
}
617
621
618
// process charset
622
// process charset (value is now in UTF-8)
619
623
String string_value;
620
624
try {
621
625
string_value = new String( value.array(), value.position(),
622
value.limit() - value.position(), charset );
626
value.limit() - value.position(), "UTF-8" );
623
627
} catch( UnsupportedEncodingException e ) {
624
628
throw new ParseException( R.string.error_vcf_charset );
625
629
}
690
694
return ( count & 1 ) == 1;
691
695
}
692
696
693
private String[] splitValueBySemicolon( String value )
697
private String[] splitValueByCharacter( String value, char character )
694
698
{
695
// split string in to parts by semicolon
699
// split string in to parts by specified character
696
700
ArrayList< String > parts = new ArrayList< String >(
697
Arrays.asList( value.split( ";" ) ) );
701
Arrays.asList( value.split( "" + character ) ) );
698
702
699
703
// go through parts
700
704
for( int a = 0; a < parts.size(); a++ )
708
712
if( a < parts.size() - 1 &&
709
713
doesStringEndInAnEscapeChar( str ) )
710
714
{
711
// join the next part to this part and remove the next part
715
// append the escaped character, join the next part to this
716
// part and remove the next part
712
717
parts.set( a, str.substring( 0, str.length() - 1 ) +
713
';' + parts.get( a + 1 ) );
718
character + parts.get( a + 1 ) );
714
719
parts.remove( a + 1 );
715
720
716
721
// re-visit this part
727
732
return parts.toArray( ret );
728
733
}
729
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();
776
}
777
730
778
private void parseN( String[] params, String value )
731
779
{
732
780
// already got a better name?
733
781
if( _name_level >= NAMELEVEL_N ) return;
734
782
735
783
// get name parts
736
String[] name_parts = splitValueBySemicolon( value );
784
String[] name_parts = splitValueByCharacter( value, ';' );
737
785
738
786
// build name
739
787
value = "";
740
if( name_parts.length > 1 && name_parts[ 1 ].length() > 0 )
741
value += name_parts[ 1 ];
742
if( name_parts.length > 0 && name_parts[ 0 ].length() > 0 )
743
value += ( value.length() == 0? "" : " " ) + name_parts[ 0 ];
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
}
744
803
745
804
// set name
746
setName( value );
805
setName( unescapeValue( value ) );
747
806
_name_level = NAMELEVEL_N;
748
807
}
749
808
753
812
if( _name_level >= NAMELEVEL_FN ) return;
754
813
755
814
// set name
756
setName( value );
815
setName( unescapeValue( value ) );
757
816
_name_level = NAMELEVEL_FN;
758
817
}
759
818
760
819
private void parseORG( String[] params, String value )
761
820
{
762
821
// get org parts
763
String[] org_parts = splitValueBySemicolon( value );
822
String[] org_parts = splitValueByCharacter( value, ';' );
764
823
if( org_parts == null || org_parts.length < 1 ) return;
765
824
766
825
// build organisation name
768
827
String.valueOf( org_parts[ 0 ] ) );
769
828
for( int a = 1; a < org_parts.length; a++ )
770
829
builder.append( ", " ).append( org_parts[ a ] );
771
String organisation = builder.toString();
830
String organisation = unescapeValue( builder.toString() );
772
831
773
832
// set organisation name (using a title we've previously found)
774
833
addOrganisation( organisation, _cached_title, true );
785
844
786
845
private void parseTITLE( String[] params, String value )
787
846
{
847
value = unescapeValue( value );
848
788
849
// if we previously had an organisation, look it up and append this
789
850
// title to it
790
851
if( _cached_organisation != null && hasOrganisations() ) {
847
908
else
848
909
type = Contacts.ContactMethods.TYPE_HOME;
849
910
850
addEmail( value, type, is_preferred );
911
addEmail( unescapeValue( value ), type, is_preferred );
851
912
}
852
913
853
914
private void parseADR( String[] params, String value )
854
915
{
855
916
// get address parts
856
String[] adr_parts = splitValueBySemicolon( value );
917
String[] adr_parts = splitValueByCharacter( value, ';' );
857
918
858
919
// build address
859
920
value = "";
860
for( int a = 0; a < adr_parts.length; a++ ) {
861
if( value.length() > 0 ) value += "\n";
862
value += adr_parts[ a ].trim();
863
}
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
}
864
934
865
935
Set< String > types = extractTypes( params, Arrays.asList(
866
936
"PREF", "WORK", "HOME", "INTERNET" ) );
872
942
else
873
943
type = Contacts.ContactMethods.TYPE_HOME;
874
944
875
addAddress( value, type );
945
addAddress( unescapeValue( value ), type );
876
946
}
877
947
878
948
public void finaliseVcard()
Loggerhead is a web-based interface for Bazaar branches
Version: 1.18.2, Revision: 480