From c0aa72210ae18e16f77ed71006d7c0176868a3c0 Mon Sep 17 00:00:00 2001 From: Tom Tromey Date: Tue, 26 Jun 2001 04:36:47 +0000 Subject: [PATCH] encodings.pl: Generate lower-case names. * scripts/encodings.pl: Generate lower-case names. Updated URL for `character-sets' file. * gnu/gcj/convert/IOConverter.java (canonicalize): Convert name to lower case. Rebuilt list of aliases. From-SVN: r43566 --- libjava/ChangeLog | 8 ++++ libjava/gnu/gcj/convert/IOConverter.java | 47 ++++++++++++------------ libjava/scripts/encodings.pl | 9 +++-- 3 files changed, 38 insertions(+), 26 deletions(-) diff --git a/libjava/ChangeLog b/libjava/ChangeLog index 2ec86c53264..bc2792976bb 100644 --- a/libjava/ChangeLog +++ b/libjava/ChangeLog @@ -1,3 +1,11 @@ +2001-06-25 Tom Tromey + + * scripts/encodings.pl: Generate lower-case names. Updated URL + for `character-sets' file. + * gnu/gcj/convert/IOConverter.java (canonicalize): Convert name to + lower case. + Rebuilt list of aliases. + 2001-06-25 Tom Tromey * java/io/natFileDescriptorPosix.cc (open): Change error message diff --git a/libjava/gnu/gcj/convert/IOConverter.java b/libjava/gnu/gcj/convert/IOConverter.java index 9b5fbad00f4..2c1d526b4cd 100644 --- a/libjava/gnu/gcj/convert/IOConverter.java +++ b/libjava/gnu/gcj/convert/IOConverter.java @@ -1,4 +1,4 @@ -/* Copyright (C) 2000 Free Software Foundation +/* Copyright (C) 2000, 2001 Free Software Foundation This file is part of libgcj. @@ -29,33 +29,34 @@ public abstract class IOConverter hash.put ("ISO-Latin-1", "8859_1"); // All aliases after this point are automatically generated by the // `encodings.pl' script. Run it to make any corrections. - hash.put ("ANSI_X3.4-1968", "ASCII"); + hash.put ("ansi_x3.4-1968", "ASCII"); hash.put ("iso-ir-6", "ASCII"); - hash.put ("ANSI_X3.4-1986", "ASCII"); - hash.put ("ISO_646.irv:1991", "ASCII"); - hash.put ("ASCII", "ASCII"); - hash.put ("ISO646-US", "ASCII"); - hash.put ("US-ASCII", "ASCII"); + hash.put ("ansi_x3.4-1986", "ASCII"); + hash.put ("iso_646.irv:1991", "ASCII"); + hash.put ("ascii", "ASCII"); + hash.put ("iso646-us", "ASCII"); + hash.put ("us-ascii", "ASCII"); hash.put ("us", "ASCII"); - hash.put ("IBM367", "ASCII"); + hash.put ("ibm367", "ASCII"); hash.put ("cp367", "ASCII"); - hash.put ("csASCII", "ASCII"); - hash.put ("ISO_8859-1:1987", "8859_1"); + hash.put ("csascii", "ASCII"); + hash.put ("iso_8859-1:1987", "8859_1"); hash.put ("iso-ir-100", "8859_1"); - hash.put ("ISO_8859-1", "8859_1"); - hash.put ("ISO-8859-1", "8859_1"); + hash.put ("iso_8859-1", "8859_1"); + hash.put ("iso-8859-1", "8859_1"); hash.put ("latin1", "8859_1"); hash.put ("l1", "8859_1"); - hash.put ("IBM819", "8859_1"); - hash.put ("CP819", "8859_1"); - hash.put ("csISOLatin1", "8859_1"); - hash.put ("UTF-8", "UTF8"); - hash.put ("Shift_JIS", "SJIS"); - hash.put ("MS_Kanji", "SJIS"); - hash.put ("csShiftJIS", "SJIS"); - hash.put ("Extended_UNIX_Code_Packed_Format_for_Japanese", "EUCJIS"); - hash.put ("csEUCPkdFmtJapanese", "EUCJIS"); - hash.put ("EUC-JP", "EUCJIS"); + hash.put ("ibm819", "8859_1"); + hash.put ("cp819", "8859_1"); + hash.put ("csisolatin1", "8859_1"); + hash.put ("utf-8", "UTF8"); + hash.put ("none", "UTF8"); + hash.put ("shift_jis", "SJIS"); + hash.put ("ms_kanji", "SJIS"); + hash.put ("csshiftjis", "SJIS"); + hash.put ("extended_unix_code_packed_format_for_japanese", "EUCJIS"); + hash.put ("cseucpkdfmtjapanese", "EUCJIS"); + hash.put ("euc-jp", "EUCJIS"); iconv_byte_swap = iconv_init (); } @@ -65,7 +66,7 @@ public abstract class IOConverter // Turn an alias into the canonical form. protected static final String canonicalize (String name) { - String c = (String) hash.get (name); + String c = (String) hash.get (name.toLowerCase ()); return c == null ? name : c; } } diff --git a/libjava/scripts/encodings.pl b/libjava/scripts/encodings.pl index 4c7f0579534..5e802c1f5fc 100644 --- a/libjava/scripts/encodings.pl +++ b/libjava/scripts/encodings.pl @@ -17,7 +17,7 @@ if ($ARGV[0] eq '') if (! -f $file) { # Too painful to figure out how to get Perl to do it. - system 'wget -o .wget-log http://www.isi.edu/in-notes/iana/assignments/character-sets'; + system 'wget -o .wget-log http://www.iana.org/assignments/character-sets'; } } else @@ -42,12 +42,15 @@ while () } ($type, $name) = split (/\s+/); + # Encoding names are case-insensitive. We do all processing on + # the lower-case form. + my $lower = lc ($name); if ($type eq 'Name:') { $current = $map{$name}; if ($current) { - print " hash.put (\"$name\", \"$current\");\n"; + print " hash.put (\"$lower\", \"$current\");\n"; } } elsif ($type eq 'Alias:') @@ -55,7 +58,7 @@ while () # The IANA list has some ugliness. if ($name ne '' && $name ne 'NONE' && $current) { - print " hash.put (\"$name\", \"$current\");\n"; + print " hash.put (\"$lower\", \"$current\");\n"; } } } -- 2.30.2