From owner-svn-src-stable-10@FreeBSD.ORG Thu Aug 21 21:53:44 2014 Return-Path: Delivered-To: svn-src-stable-10@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id ACF84681; Thu, 21 Aug 2014 21:53:44 +0000 (UTC) Received: from svn.freebsd.org (svn.freebsd.org [IPv6:2001:1900:2254:2068::e6a:0]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8958E3B87; Thu, 21 Aug 2014 21:53:44 +0000 (UTC) Received: from svn.freebsd.org ([127.0.1.70]) by svn.freebsd.org (8.14.9/8.14.9) with ESMTP id s7LLriVr010523; Thu, 21 Aug 2014 21:53:44 GMT (envelope-from se@FreeBSD.org) Received: (from se@localhost) by svn.freebsd.org (8.14.9/8.14.9/Submit) id s7LLrhk0010520; Thu, 21 Aug 2014 21:53:43 GMT (envelope-from se@FreeBSD.org) Message-Id: <201408212153.s7LLrhk0010520@svn.freebsd.org> X-Authentication-Warning: svn.freebsd.org: se set sender to se@FreeBSD.org using -f From: Stefan Esser Date: Thu, 21 Aug 2014 21:53:43 +0000 (UTC) To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-stable@freebsd.org, svn-src-stable-10@freebsd.org Subject: svn commit: r270308 - stable/10/tools/tools/vt/keymaps X-SVN-Group: stable-10 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-BeenThere: svn-src-stable-10@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: SVN commit messages for only the 10-stable src tree List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 21 Aug 2014 21:53:44 -0000 Author: se Date: Thu Aug 21 21:53:43 2014 New Revision: 270308 URL: http://svnweb.freebsd.org/changeset/base/270308 Log: MFC 270131, 270152, 270199, 270232: Add converter from SYSCONS keymap format to NEWCONS and configuration files. The convert-keymap.pl script can be used to convert private SYSCONS keymaps ro NEWCONS format. Added: stable/10/tools/tools/vt/keymaps/ - copied from r270131, head/tools/tools/vt/keymaps/ Modified: stable/10/tools/tools/vt/keymaps/KBDFILES.map stable/10/tools/tools/vt/keymaps/convert-keymap.pl stable/10/tools/tools/vt/keymaps/convert-keymaps.pl Modified: stable/10/tools/tools/vt/keymaps/KBDFILES.map ============================================================================== --- head/tools/tools/vt/keymaps/KBDFILES.map Mon Aug 18 09:40:19 2014 (r270131) +++ stable/10/tools/tools/vt/keymaps/KBDFILES.map Thu Aug 21 21:53:43 2014 (r270308) @@ -1,28 +1,36 @@ # $FreeBSD$ - -ISO8859-15 be.iso.kbd be.kbd -ISO8859-15 be.iso.acc.kbd be.acc.kbd +# +# The Files are converted by "convert-keymaps.pl" from the given encoding to UCS. +# +# An additional "+EURO" causes the translation of the generic currency symbol to +# an Euro symbol, even if the source locale does not support an Euro symbol. +# This conversion is only performed for the "E" key (not e.g. on Shift-4, which +# still generates the currency symbol). +# +# Encoding syscons file name newcons (vt) file name +ISO8859-1+EURO be.iso.kbd be.kbd +ISO8859-1+EURO be.iso.acc.kbd be.acc.kbd ISO8859-5 bg.bds.ctrlcaps.kbd bg.bds.kbd -ISO8859-5 bg.phonetic.ctrlcaps.kbd bg.bds.ctrlcaps.kbd +ISO8859-5 bg.phonetic.ctrlcaps.kbd bg.phonetic.kbd -ISO8859-1 br275.iso.kbd br.kbd -ISO8859-1 br275.iso.acc.kbd br.acc.kbd -CP850 br275.cp850.kbd br.kbd.from-cp850 +#ISO8859-1 br275.iso.kbd br.kbd.from-iso1 (only AltGr-Shift-6 differs from CP850) +ISO8859-1 br275.iso.acc.kbd br.kbd +CP850 br275.cp850.kbd br.noacc.kbd -CP1131 by.cp1131.kbd by.kbd.from-cp1131 -CP1251 by.cp1251.kbd by.kbd.from-cp1251 -ISO8859-5 by.iso5.kbd by.kbd.from-iso5 +#CP1131 by.cp1131.kbd by.kbd.from-cp1131 (Shift-3 not OK) +#CP1251 by.cp1251.kbd by.kbd.from-cp1251 (result identical to CP1251) +ISO8859-5 by.iso5.kbd by.kbd -ISO8859-2 ce.iso2.kbd centraleuropean.kbd +ISO8859-2 ce.iso2.kbd centraleuropean.qwerty.kbd -ISO8859-1 colemak.iso15.acc.kbd colemak.kbd +ISO8859-1 colemak.iso15.acc.kbd colemak.acc.kbd ISO8859-2 cs.latin2.qwertz.kbd cz.kbd -ISO8859-2 cz.iso2.kbd cz.kbd.from-ce +ISO8859-2 cz.iso2.kbd cz.qwerty.kbd.from-ce -ISO8859-15 danish.iso.kbd dk.kbd -ISO8859-15 danish.iso.acc.kbd dk.acc.kbd +ISO8859-1+EURO danish.iso.kbd dk.kbd +ISO8859-1+EURO danish.iso.acc.kbd dk.acc.kbd CP865 danish.cp865.kbd dk.kbd.from-cp865 ISO8859-1 danish.iso.macbook.kbd dk.macbook.kbd @@ -36,19 +44,19 @@ ISO8859-1 estonian.iso.kbd ee.kbd.from- ISO8859-15 estonian.iso15.kbd ee.kbd CP850 estonian.cp850.kbd ee.kbd.from-cp850 -ISO8859-15 finnish.iso.kbd fi.kbd +ISO8859-1+EURO finnish.iso.kbd fi.kbd CP850 finnish.cp850.kbd fi.kbd.from-cp850 -ISO8859-15 fr.iso.kbd fr.kbd -ISO8859-15 fr.iso.acc.kbd fr.acc.kbd -ISO8859-15 fr.macbook.acc.kbd fr.macbook.kbd -ISO8859-1 fr.dvorak.kbd fr.dvorak.kbd -ISO8859-15 fr.dvorak.acc.kbd fr.dvorak.acc.kbd +ISO8859-1+EURO fr.iso.kbd fr.kbd +ISO8859-1+EURO fr.iso.acc.kbd fr.acc.kbd +ISO8859-1+EURO fr.macbook.acc.kbd fr.macbook.kbd +ISO8859-1+EURO fr.dvorak.kbd fr.dvorak.kbd +ISO8859-1 fr.dvorak.acc.kbd fr.dvorak.acc.kbd -ISO8859-15 fr_CA.iso.acc.kbd ca-fr.kbd +ISO8859-1+EURO fr_CA.iso.acc.kbd ca-fr.kbd -ISO8859-15 german.iso.kbd de.kbd -ISO8859-15 german.iso.acc.kbd de.acc.kbd +ISO8859-1+EURO german.iso.kbd de.noacc.kbd +ISO8859-1+EURO german.iso.acc.kbd de.acc.kbd CP850 german.cp850.kbd de.kbd.from-cp850 ISO8859-7 gr.elot.acc.kbd gr.elot.acc.kbd @@ -66,12 +74,12 @@ ARMSCII-8 hy.armscii-8.kbd am.kbd ISO8859-1 icelandic.iso.kbd is.kbd ISO8859-1 icelandic.iso.acc.kbd is.acc.kbd -ISO8859-15 it.iso.kbd it.kbd +ISO8859-1+EURO it.iso.kbd it.kbd -ISO8859-1 jp.106.kbd jp.kbd -ISO8859-1 jp.106x.kbd jp.capsctrl.kbd -ISO8859-1 jp.pc98.kbd jp.pc98.kbd -ISO8859-1 jp.pc98.iso.kbd jp.pc98.iso.kbd +ISO8859-1+YEN jp.106.kbd jp.kbd +ISO8859-1+YEN jp.106x.kbd jp.capsctrl.kbd +ISO8859-1+YEN jp.pc98.kbd jp.pc98.kbd +ISO8859-1+YEN jp.pc98.iso.kbd jp.pc98.iso.kbd PT154 kk.pt154.kst.kbd kz.kst.kbd PT154 kk.pt154.io.kbd kz.io.kbd @@ -87,8 +95,8 @@ ISO8859-1 norwegian.dvorak.kbd no.dvora ISO8859-2 pl_PL.ISO8859-2.kbd pl.kbd ISO8859-2 pl_PL.dvorak.kbd pl.dvorak.kbd -ISO8859-15 pt.iso.kbd pt.kbd -ISO8859-15 pt.iso.acc.kbd pt.acc.kbd +ISO8859-1+EURO pt.iso.kbd pt.kbd +ISO8859-1+EURO pt.iso.acc.kbd pt.acc.kbd CP866 ru.cp866.kbd ru.kbd.from-cp866 ISO8859-5 ru.iso5.kbd ru.kbd.from-iso5 @@ -96,34 +104,34 @@ KOI8-R ru.koi8-r.kbd ru.kbd KOI8-R ru.koi8-r.shift.kbd ru.shift.kbd KOI8-R ru.koi8-r.win.kbd ru.win.kbd -ISO8859-15 spanish.dvorak.kbd es.dvorak.kbd -ISO8859-1 spanish.iso.kbd es.kbd.from-iso1 -ISO8859-1 spanish.iso.acc.kbd es.acc.kbd -ISO8859-15 spanish.iso15.acc.kbd es.kbd +ISO8859-1+EURO spanish.dvorak.kbd es.dvorak.kbd +ISO8859-1+EURO spanish.iso.kbd es.kbd.from-iso1 +ISO8859-1+EURO spanish.iso.acc.kbd es.acc.kbd +ISO8859-1+EURO spanish.iso15.acc.kbd es.kbd ISO8859-2 si.iso.kbd si.kbd ISO8859-2 sk.iso2.kbd sk.kbd -ISO8859-1 swedish.iso.kbd se.kbd +ISO8859-1+EURO swedish.iso.kbd se.kbd CP850 swedish.cp850.kbd se.kbd.from-cp850 -ISO8859-1 swissfrench.iso.kbd ch-fr.kbd -ISO8859-1 swissfrench.iso.acc.kbd ch-fr.acc.kbd +ISO8859-1+EURO swissfrench.iso.kbd ch-fr.kbd +ISO8859-1+EURO swissfrench.iso.acc.kbd ch-fr.acc.kbd CP850 swissfrench.cp850.kbd ch-fr.kbd.from-cp850 -ISO8859-1 swissgerman.iso.kbd ch.kbd -ISO8859-1 swissgerman.iso.acc.kbd ch.acc.kbd +ISO8859-1+EURO swissgerman.iso.kbd ch.kbd +ISO8859-1+EURO swissgerman.iso.acc.kbd ch.acc.kbd CP850 swissgerman.cp850.kbd ch.kbd.from-cp850 -ISO8859-1 swissgerman.macbook.acc.kbd ch.macbook.acc.kbd +ISO8859-1+EURO swissgerman.macbook.acc.kbd ch.macbook.acc.kbd ISO8859-9 tr.iso9.q.kbd tr.kbd -ISO8859-1 uk.iso.kbd uk.kbd -ISO8859-1 uk.iso-ctrl.kbd uk.capsctrl.kbd -CP850 uk.cp850.kbd uk.kbd.from-cp850 -CP850 uk.cp850-ctrl.kbd uk.capsctrl.kbd.from-cp850 -ISO8859-1 uk.dvorak.kbd uk.dvorak.kbd +ISO8859-1+EURO uk.iso.kbd uk.kbd +ISO8859-1+EURO uk.iso-ctrl.kbd uk.capsctrl.kbd +#CP850 uk.cp850.kbd uk.kbd.from-cp850 (no ¤ and different Alt/Alt-Shift encodings) +#CP850 uk.cp850-ctrl.kbd uk.capsctrl.kbd.from-cp850 (no ¤ and different Alt/Alt-Shift encodings) +ISO8859-15 uk.dvorak.kbd uk.dvorak.kbd ISO8859-1 us.iso.kbd us.kbd ISO8859-1 us.iso.acc.kbd us.acc.kbd Modified: stable/10/tools/tools/vt/keymaps/convert-keymap.pl ============================================================================== --- head/tools/tools/vt/keymaps/convert-keymap.pl Mon Aug 18 09:40:19 2014 (r270131) +++ stable/10/tools/tools/vt/keymaps/convert-keymap.pl Thu Aug 21 21:53:43 2014 (r270308) @@ -6,9 +6,26 @@ use Encode; use strict; use utf8; -die "Usage: $0 filename.kbd CHARSET" unless ($ARGV[1]); -my $converter = Text::Iconv->new($ARGV[1], "UTF-8"); +# command line parsing +die "Usage: $0 filename.kbd CHARSET [EURO]" + unless ($ARGV[1]); + +my $inputfile = shift; # first command argument +my $converter = Text::Iconv->new(shift, "UTF-8"); # second argument +my $use_euro; +my $use_yen; +my $current_char; +my $current_scancode; + +while (my $arg = shift) { + $use_euro = 1, next + if $arg eq "EURO"; + $use_yen = 1, next + if $arg eq "YEN"; + die "Unknown encoding option '$arg'\n"; +} +# converter functions sub local_to_UCS_string { my ($string) = @_; @@ -18,47 +35,75 @@ sub local_to_UCS_string sub prettyprint_token { - my ($code) = @_; + my ($ucs_char) = @_; - return "'" . chr($code) . "'" - if 32 <= $code and $code <= 126; # print as ASCII if possible -# return sprintf "%d", $code; # <---- temporary decimal - return sprintf "0x%02x", $code - if $code <= 255; # print as hex number, else - return sprintf "0x%04x", $code; + return "'" . chr($ucs_char) . "'" + if 32 <= $ucs_char and $ucs_char <= 126; # print as ASCII if possible +# return sprintf "%d", $ucs_char; # <---- temporary decimal + return sprintf "0x%02x", $ucs_char + if $ucs_char <= 255; # print as hex number, else + return sprintf "0x%04x", $ucs_char; } sub local_to_UCS_code { my ($char) = @_; - return prettyprint_token(ord(Encode::decode("UTF-8", local_to_UCS_string($char)))); + my $ucs_char = ord(Encode::decode("UTF-8", local_to_UCS_string($char))); + + $current_char = lc(chr($ucs_char)), print("SETCUR: $ucs_char\n") + if $current_char eq ""; + + $ucs_char = 0x20ac # replace with Euro character + if $ucs_char == 0xa4 and $use_euro and $current_char eq "e"; + + $ucs_char = 0xa5 # replace with Jap. Yen character on PC kbd + if $ucs_char == ord('\\') and $use_yen and $current_scancode == 125; + + $ucs_char = 0xa5 # replace with Jap. Yen character on PC98x1 kbd + if $ucs_char == ord('\\') and $use_yen and $current_scancode == 13; + + return prettyprint_token($ucs_char); } +sub malformed_to_UCS_code +{ + my ($char) = @_; + + return prettyprint_token(ord(Encode::decode("UTF-8", $char))); +} sub convert_token { my ($C) = @_; return $1 - if $C =~ m/^([a-z][a-z0-9]*)$/; # key token + if $C =~ m/^([a-z][a-z0-9]*)$/; # key token return local_to_UCS_code(chr($1)) - if $C =~ m/^(\d+)$/; # decimal number + if $C =~ m/^(\d+)$/; # decimal number return local_to_UCS_code(chr(hex($1))) - if $C =~ m/^0x([0-9a-f]+)$/i; # hex number - return local_to_UCS_code($1) - if $C =~ m/^'(.)'$/; # character - return ""; # uncovered case + if $C =~ m/^0x([0-9a-f]+)$/i; # hex number + return local_to_UCS_code(chr(ord($1))) + if $C =~ m/^'(.)'$/; # character + return malformed_to_UCS_code($1) + if $C =~ m/^'(.+)'$/; # character + return ""; # uncovered case } sub tokenize { # split on white space and parentheses (but not within token) my ($line) = @_; - $line =~ s/' '/ _spc_ /g; # prevent splitting of ' ' $line =~ s/'\('/ _lpar_ /g; # prevent splitting of '(' $line =~ s/'\)'/ _rpar_ /g; # prevent splitting of ')' + $line =~ s/'''/'_squote_'/g; # remove quoted single quotes from matches below $line =~ s/([()])/ $1 /g; # insert blanks around remaining parentheses + my $matches; + do { + $matches = ($line =~ s/^([^']*)'([^']+)'/$1_squoteL_$2_squoteR_/g); + } while $matches; + $line =~ s/_squoteL_ _squoteR_/ _spc_ /g; # prevent splitting of ' ' my @KEYTOKEN = split (" ", $line); + grep(s/_squote[LR]?_/'/g, @KEYTOKEN); grep(s/_spc_/' '/, @KEYTOKEN); grep(s/_lpar_/'('/, @KEYTOKEN); grep(s/_rpar_/')'/, @KEYTOKEN); @@ -66,7 +111,7 @@ sub tokenize { # split on white space an } # main program -open FH, "<$ARGV[0]"; +open FH, "<$inputfile"; while () { if (m/^#/) { print local_to_UCS_string($_); @@ -78,20 +123,24 @@ while () { my $C; foreach $C (@KEYTOKEN) { if ($at_bol) { + $current_char = ""; + $current_scancode = -1; if ($C =~ m/^\s*\d/) { # line begins with key code number + $current_scancode = $C; printf " %03d ", $C; } elsif ($C =~ m/^[a-z]/) { # line begins with accent name or paren printf " %-4s ", $C; # accent name starts accent definition } elsif ($C eq "(") { printf "%17s", "( "; # paren continues accent definition } else { - print "UNKNOWN DEFINITION: $_"; + print "Unknown input line format: $_"; } $at_bol = 0; } else { if ($C =~ m/^([BCNO])$/) { print " $1"; # special case: effect of Caps Lock/Num Lock } elsif ($C eq "(") { + $current_char = ""; print " ( "; } elsif ($C eq ")") { print " )"; Modified: stable/10/tools/tools/vt/keymaps/convert-keymaps.pl ============================================================================== --- head/tools/tools/vt/keymaps/convert-keymaps.pl Mon Aug 18 09:40:19 2014 (r270131) +++ stable/10/tools/tools/vt/keymaps/convert-keymaps.pl Thu Aug 21 21:53:43 2014 (r270308) @@ -83,17 +83,18 @@ my $kbdfile; foreach $kbdfile (glob("$dir_keymaps_syscons/*.kbd")) { my $basename; ($basename = $kbdfile) =~ s:.*/::; - my $encoding = $ENCODING{$basename}; + my ($encoding) = $ENCODING{$basename}; + $encoding =~ s/\+/ /g; # e.g. "ISO8859-1+EURO" -> "ISO8859-1 EURO" my $outfile = $FILE_NEW{$basename}; if ($encoding and $outfile) { if (-r $kbdfile) { - print "converting from '$basename' ($encoding) to '$outfile' (Unicode)\n"; - my $cmdline = "$dir_convtool/convert-keymap.pl $kbdfile $ENCODING{$basename} > $dir_keymaps_output/$outfile"; + print "converting from '$basename' ($encoding) to '$outfile' (UCS)\n"; + my $cmdline = "$dir_convtool/convert-keymap.pl $kbdfile $encoding > $dir_keymaps_output/$outfile"; system "$cmdline"; } else { print "$kbdfile not found\n"; } } else { - print "Unknown input file: $basename\n"; + print "Ignore '$basename': No encoding defined in KBDFILES.map\n"; } }