# HG changeset patch
# User Igor Chubin <igor@chub.in>
# Date 1274023218 -10800
# Node ID 46e987f4636db8be64d8cd0c250897d2960d7dea
# Parent  190d4ac6b07cf63208fed4e79c054cde3cb331cf
part.pl script + german normalization support

diff -r 190d4ac6b07c -r 46e987f4636d en.sh
--- a/en.sh	Thu May 06 21:05:20 2010 +0300
+++ b/en.sh	Sun May 16 18:20:18 2010 +0300
@@ -1,7 +1,19 @@
 #!/bin/sh
 
+DICTD_SERVER="dictd.xdsl.by"
+DICTD_SERVER_ARGS="-h $DICTD_SERVER"
+DICT_NAME=mueller24
+
+
+myname="`echo $0 | sed s@.*/@@`"
+case $myname in
+  "de") DICT_NAME=deu-eng ; DICTD_SERVER_ARGS='' ;;
+  "pl") DICT_NAME=slovnyk_pl-ru ;;
+  "ru") DICT_NAME=ozhshv ;;
+esac
+
 (
-    dict -h dictd.xdsl.by -d mueller24 "$@"
+    dict $DICTD_SERVER_ARGS -d "$DICT_NAME" "$@"
     if [ -e "$ORIGINAL_TEXT" ]
     then
         echo . . . . . . . . . . . . . . . . . . . . . . . . . ; echo
diff -r 190d4ac6b07c -r 46e987f4636d new-words.sh
--- a/new-words.sh	Thu May 06 21:05:20 2010 +0300
+++ b/new-words.sh	Sun May 16 18:20:18 2010 +0300
@@ -44,10 +44,13 @@
 
 LANGUAGE=en
 my_name="`echo $0 | sed s@.*/@@ | sed s/-.*// `"
-if echo "$1" | grep -q http://...wikipedia.org/wiki/
-then
-LANGUAGE="`echo $1 | sed s@http://@@ | sed s@.wikipedia.*@@`"
-fi
+for arg
+do
+    if echo "$arg" | grep -q http://...wikipedia.org/wiki/
+    then
+    LANGUAGE="`echo $arg | sed s@http://@@ | sed s@.wikipedia.*@@`"
+    fi
+done
 [ "${my_name}" = "new" ] || LANGUAGE="$my_name"
 if [ "$1" = "-l" ]
 then
@@ -179,11 +182,11 @@
 
 group_words()
 {
-    if [ "$LANGUAGE" != "en" ]
-    then
-        cat 
-        return
-    fi
+    #if [ "$LANGUAGE" != "en" ]
+    #then
+    #    cat 
+    #    return
+    #fi
     PERL_SCRIPT_TEMP_NAME=`mktemp /tmp/perl-group-words-XXXXXXXX`
     cat <<'PERL_SCRIPT' > $PERL_SCRIPT_TEMP_NAME
 #!/usr/bin/perl
@@ -211,9 +214,43 @@
 
 sub normalize($)
 {
+    if   ( $ENV{LANGUAGE} eq "en" ) { return normalize_english(shift); }
+    elsif ( $ENV{LANGUAGE} eq "de" ) { return normalize_german(shift); }
+    else { return shift ; }
+}
+
+sub normalize_german($)
+{
+    $_=lc(shift);
+
+    s/heit$//;  s/keit$//; s/tum$//; s/ung$//; s/nis$//;s/schaft$//; s/ist$//; 
+    s/en$//; s/er$//;
+
+    s/lich$//; s/ig$//;
+    s/al$//; s/isch$//;
+    s/ell$//; s/haft$//;
+
+    s/bar$//; s/sam$//; s/lich$//;
+
+    @prefixes=qw(
+        ab an auf aus bei dazwischen ein fest heraus her hinaus hin los mit nach voraus vorbei vor weg weiter zurück zusammen zu
+        be emp ent er ge miss ver zer durch über um unter wieder);
+    for $pref (@prefixes) {
+        s/^$pref//;
+    }
+
+
+    return $_;
+}
+
+sub normalize_english($)
+{
     $_=lc(shift);
 
     s/s$//;
+
+    s/ation$//;  s/ness$//; s/ship$//; s/ally$//; s/ance$//;s/ity$//; s/ment$//; 
+
     s/ed$//;
     s/en$//;
     s/er$//;
@@ -221,8 +258,7 @@
     s/ing$//;
 
     s/ism$//; s/ist$//; s/ful$//; s/able$//; s/ably$//;
-    s/ation$//;  s/ness$//; s/ship$//; s/ally$//;
-    s/ment$//; s/ify$//; s/ity$//; s/fy$//; s/ly$//;
+    s/ify$//; s/fy$//; s/ly$//;
     s/ise$//; s/ize$//;
 
     s/e$//;
@@ -286,6 +322,7 @@
 PERL_SCRIPT
     export VOCABULARY
     export NEED_TO_USE_VOCABULARY_WHEN_SORT
+    export LANGUAGE
     perl $PERL_SCRIPT_TEMP_NAME
     rm $PERL_SCRIPT_TEMP_NAME
 }
diff -r 190d4ac6b07c -r 46e987f4636d part.pl
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/part.pl	Sun May 16 18:20:18 2010 +0300
@@ -0,0 +1,39 @@
+#!/usr/bin/perl
+
+my @lines=<STDIN>;
+my $lines=$#lines;
+my $interval=$ARGV[0];
+my ($start,$stop,$total);
+if ($interval =~ m@(.*)/(.*)@) {
+    $start = $1;
+    $total = $2;
+}
+else {
+    $start=$interval;
+    $total=0;
+}
+if ($start =~ m@(.*)-(.*)@) {
+    $start = $1;
+    $stop = $2;
+}
+if ($start =~ m@(.*)\+(.*)@) {
+    $start = $1;
+    #if ($2 =~ /%$/) {
+    #}
+    #else {
+    $stop = $start+$2;
+    #}
+}
+#print "start = $start\n";
+#print "stop = $stop\n";
+#print "total = $total\n";
+
+$start=int($lines/$total*$start);
+$stop=int($lines/$total*$stop);
+
+#print "start = $start\n";
+#print "stop = $stop\n";
+#print "total = $total\n";
+for($i=$start;$i<$stop;$i++){
+    print $lines[$i];
+}