Skip to content

implement CESU-8 #44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
headius merged 1 commit into from
Feb 1, 2022
Merged

implement CESU-8 #44

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added resources/tables/Transcoder_Cesu8_ByteArray.bin
View file
Open in desktop
Binary file not shown.
Binary file added resources/tables/Transcoder_Cesu8_WordArray.bin
View file
Open in desktop
Binary file not shown.
Binary file modified resources/tables/Transcoder_Escape_ByteArray.bin
View file
Open in desktop
Binary file not shown.
Binary file modified resources/tables/Transcoder_Escape_WordArray.bin
View file
Open in desktop
Binary file not shown.
Binary file modified resources/tables/Transcoder_SingleByte_ByteArray.bin
View file
Open in desktop
Binary file not shown.
Binary file modified resources/tables/Transcoder_SingleByte_WordArray.bin
View file
Open in desktop
Binary file not shown.
5 changes: 3 additions & 2 deletions scripts/generate.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,7 @@ def generate_encoding_list
"KOI8-R" => "KOI8R",
"KOI8-U" => "KOI8U",
"Shift_JIS" => "SJIS",
"CESU-8" => "CESU8",
"UTF-16BE" => "UTF16BE",
"UTF-16LE" => "UTF16LE",
"UTF-32BE" => "UTF32BE",
Expand All @@ -78,7 +79,7 @@ def generate_encoding_list
"Windows-1257" => "Windows_1257"
}

defines, other = open("#{REPO_PATH}/encdb.h").read.tr('()', '').scan(/ENC_([A-Z_]+)(.*?);/m).reject{|a, b| b =~ /CESU/}.partition { |a, b| a =~ /DEFINE/ }
defines, other = open("#{REPO_PATH}/encdb.h").read.tr('()', '').scan(/ENC_([A-Z_]+)(.*?);/m).partition { |a, b| a =~ /DEFINE/ }
other << ["ALIAS", "\"MS932\", \"Windows-31J\""]
other << ["ALIAS", "\"UTF8\", \"UTF-8\""]

Expand All @@ -93,7 +94,7 @@ def generate_transcoder_list
generic_list = []
transcoder_list = []

Dir["#{REPO_PATH}/enc/trans/*.c"].reject{|f| f =~ /transdb/ || f =~ /cesu/}.sort.each do |trans_file|
Dir["#{REPO_PATH}/enc/trans/*.c"].reject{|f| f =~ /transdb/}.sort.each do |trans_file|
name = trans_file[/(\w+)\.c/, 1].split('_').map{|e| e.capitalize}.join("")
trans_src = open(trans_file){|f|f.read}

Expand Down
4 changes: 4 additions & 0 deletions src/org/jcodings/EncodingList.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ static final void load() {
EncodingDB.declare("Big5", "BIG5");
EncodingDB.declare("Big5-HKSCS", "Big5HKSCS");
EncodingDB.declare("Big5-UAO", "Big5UAO");
EncodingDB.declare("CESU-8", "CESU8");
EncodingDB.declare("CP949", "CP949");
EncodingDB.declare("Emacs-Mule", "EmacsMule");
EncodingDB.declare("EUC-JP", "EUCJP");
Expand Down Expand Up @@ -68,6 +69,8 @@ static final void load() {
EncodingDB.alias("BINARY", "ASCII-8BIT");
EncodingDB.replicate("IBM437", "ASCII-8BIT");
EncodingDB.alias("CP437", "IBM437");
EncodingDB.replicate("IBM720", "ASCII-8BIT");
EncodingDB.alias("CP720", "IBM720");
EncodingDB.replicate("IBM737", "ASCII-8BIT");
EncodingDB.alias("CP737", "IBM737");
EncodingDB.replicate("IBM775", "ASCII-8BIT");
Expand Down Expand Up @@ -205,6 +208,7 @@ public static Encoding getInstance(String name) {
case "BIG5": return BIG5Encoding.INSTANCE;
case "Big5HKSCS": return Big5HKSCSEncoding.INSTANCE;
case "Big5UAO": return Big5UAOEncoding.INSTANCE;
case "CESU8": return CESU8Encoding.INSTANCE;
case "CP949": return CP949Encoding.INSTANCE;
case "EmacsMule": return EmacsMuleEncoding.INSTANCE;
case "EUCJP": return EUCJPEncoding.INSTANCE;
Expand Down
Loading