normalize_vcard can now also compare two files automatically; it's also installed without .pl suffix

git-svn-id: https://zeitsenke.de/svn/SyncEvolution/trunk@43 15ad00c4-1369-45f4-8270-35d70d36bdcd

README

@@ -208,11 +208,16 @@ address book. Now one can either compare the address books in
 Evolution or do that automatically:
 - save the complete address books: mark all entries, save as vCard
 - normalize the files with the provided Perl script:
-     normalize_vcard.pl list1.vcf >list1.normal.vcf
-     normalize_vcard.pl list2.vcf >list2.normal.vcf
+     normalize_vcard list1.vcf >list1.normal.vcf
+     normalize_vcard list2.vcf >list2.normal.vcf
 - compare the normalized lists, e.g.:
      diff -c list1.normal.vcf list2.normal.vcf
 
+Alternatively, one can invoke normalize_vcard with two file names
+as arguments and it will normalize and compare them automatically
+with diff in the side-by-side mode:
+     normalize_vcard list1.vcf list2.vcf
+
 Normalizing is necessary because the order of cards and their
 properties as well as other minor formatting aspects may be
 different. The automatic unit testing (see HACKING) also contains

src/.cvsignore

@@ -10,3 +10,4 @@ test*.vcf
 synclog.txt
 client-api
 client-api.build
+normalize_vcard

src/Makefile.am

@@ -4,10 +4,13 @@ INCLUDES = @EPACKAGE_CFLAGS@ @SYNC4J_CFLAGS@
 AM_CFLAGS = -Wall -Werror -Wno-return-type
 
 bin_PROGRAMS = syncevolution
-bin_SCRIPTS = normalize_vcard.pl
-
+bin_SCRIPTS = normalize_vcard
 EXTRA_DIST = normalize_vcard.pl
 
+normalize_vcard : normalize_vcard.pl
+	cp $< $@
+	chmod u+x $@
+
 CORE_SOURCES  = \
         EvolutionContactSource.h \
         EvolutionSmartPtr.h \

src/normalize_vcard.pl

@@ -2,25 +2,85 @@
 
 use strict;
 
-$_ = join( "", grep( !/^(BEGIN:VCARD|VERSION|END:VCARD|UID:)/, <> ) );
-s/\r//g;
-
-my @cards = ();
-
-foreach $_ ( split( /\n\n/ ) ) {
-  # undo line continuation
-  s/\n\s//gs;
-  # ignore charset specifications, assume UTF-8
-  s/;CHARSET="UTF-8"//g;
-  # ignore extra email type
-  s/EMAIL;TYPE=INTERNET/EMAIL/g;
-  # ignore extra ADR type
-  s/ADR;TYPE=OTHER/ADR/g;
-  # the type of certain fields is ignore by Evolution
-  s/X-(AIM|GROUPWISE|ICQ|YAHOO);TYPE=HOME/X-$1/g;
-  # sort entries, putting "N:" first
-  my @lines = split( "\n" );
-  push @cards, join( "\n", grep( /^N:/, @lines ), sort( grep ( !/^N:/, @lines ) ) );
+sub Usage {
+  print "normalize_vcard <vcards.vcf\n";
+  print "                 vcards1.vcf vcards2.vcf\n\n";
+  print "Either normalizes one file (stdin or single argument)\n";
+  print "or compares the two files.\n";
 }
 
-print join( "\n\n", sort @cards ), "\n";
+sub Normalize {
+  my $in = shift;
+  my $out = shift;
+
+  $_ = join( "", grep( !/^(BEGIN:VCARD|VERSION|END:VCARD|UID:)/, <$in> ) );
+  s/\r//g;
+
+  my @cards = ();
+
+  foreach $_ ( split( /\n\n/ ) ) {
+    # undo line continuation
+    s/\n\s//gs;
+    # ignore charset specifications, assume UTF-8
+    s/;CHARSET="UTF-8"//g;
+    # ignore extra email type
+    s/EMAIL;TYPE=INTERNET/EMAIL/g;
+    # ignore extra ADR type
+    s/ADR;TYPE=OTHER/ADR/g;
+    # the type of certain fields is ignore by Evolution
+    s/X-(AIM|GROUPWISE|ICQ|YAHOO);TYPE=HOME/X-$1/g;
+    # TYPE=VOICE is the default in Evolution and may or may not appear in the vcard
+    s/^TEL([^:]*);TYPE=VOICE([^:]*):/TEL$1$2:/mg;
+    # replace parameters with a sorted parameter list
+    s!^([^;:]*);(.*?):!$1 . ";" . join(';',sort(split(/;/, $2))) . ":"!meg;
+
+
+    # sort entries, putting "N:" first
+    my @lines = split( "\n" );
+    push @cards, join( "\n", grep( /^N:/, @lines ), sort( grep ( !/^N:/, @lines ) ) );
+  }
+
+  print $out join( "\n\n", sort @cards ), "\n";
+}
+
+if($#ARGV > 1) {
+  # error
+  Usage();
+  exit 1;
+} elsif($#ARGV == 1) {
+  # comparison
+
+  my ($file1, $file2) = ($ARGV[0], $ARGV[1]);
+  my $normal1 = `mktemp`;
+  my $normal2 = `mktemp`;
+  chomp($normal1);
+  chomp($normal2);
+
+  open(IN1, "<$file1") || die "$file1: $!";
+  open(IN2, "<$file2") || die "$file2: $!";
+  open(OUT1, ">$normal1") || die "$normal1: $!";
+  open(OUT2, ">$normal2") || die "$normal2: $!";
+  Normalize(*IN1{IO}, *OUT1{IO});
+  Normalize(*IN2{IO}, *OUT2{IO});
+  close(IN1);
+  close(IN2);
+  close(OUT1);
+  close(OUT2);
+
+  my $res = system( "diff", "--suppress-common-lines", "-y", $normal1, $normal2 );
+  
+  unlink($normal1);
+  unlink($normal2);
+  exit($res ? 1 : 0);
+} else {
+  # normalize
+  my $in;
+  if( $#ARGV >= 0 ) {
+    open(IN, "<$ARGV[0]") || die "$ARGV[0]: $!";
+    $in = *IN{IO};
+  } else {
+    $in = *STDIN{IO};
+  }
+
+  Normalize($in, *STDOUT{IO});
+}