[ruby/prism] Add cp855 encoding

https://github.com/ruby/prism/commit/8069d143f5

prism/enc/pm_encoding.h

@@ -158,9 +158,10 @@ extern const uint8_t pm_encoding_unicode_table[256];
 extern pm_encoding_t pm_encoding_ascii;
 extern pm_encoding_t pm_encoding_ascii_8bit;
 extern pm_encoding_t pm_encoding_big5;
+extern pm_encoding_t pm_encoding_cp51932;
 extern pm_encoding_t pm_encoding_cp850;
 extern pm_encoding_t pm_encoding_cp852;
-extern pm_encoding_t pm_encoding_cp51932;
+extern pm_encoding_t pm_encoding_cp855;
 extern pm_encoding_t pm_encoding_euc_jp;
 extern pm_encoding_t pm_encoding_gbk;
 extern pm_encoding_t pm_encoding_iso_8859_1;

prism/enc/pm_tables.c

@@ -72,6 +72,30 @@ static uint8_t pm_encoding_cp852_table[256] = {
     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // Fx
 };
 
+/**
+ * Each element of the following table contains a bitfield that indicates a
+ * piece of information about the corresponding CP855 character.
+ */
+static uint8_t pm_encoding_cp855_table[256] = {
+//  0  1  2  3  4  5  6  7  8  9  A  B  C  D  E  F
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 1x
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 2x
+    2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 0, 0, 0, 0, // 3x
+    0, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, // 4x
+    7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 0, 0, 0, 0, 0, // 5x
+    0, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // 6x
+    3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 0, 0, 0, 0, 0, // 7x
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 8x
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 9x
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // Ax
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // Bx
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // Cx
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // Dx
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // Ex
+    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // Fx
+};
+
 /**
  * Each element of the following table contains a bitfield that indicates a
  * piece of information about the corresponding ISO-8859-1 character.
@@ -739,6 +763,7 @@ pm_encoding_koi8_r_char_width(const uint8_t *b, PRISM_ATTRIBUTE_UNUSED ptrdiff_t
 
 PRISM_ENCODING_TABLE(cp850)
 PRISM_ENCODING_TABLE(cp852)
+PRISM_ENCODING_TABLE(cp855)
 PRISM_ENCODING_TABLE(iso_8859_1)
 PRISM_ENCODING_TABLE(iso_8859_2)
 PRISM_ENCODING_TABLE(iso_8859_3)
@@ -807,6 +832,16 @@ pm_encoding_t pm_encoding_cp852 = {
     .multibyte = false
 };
 
+/** CP855 */
+pm_encoding_t pm_encoding_cp855 = {
+    .name = "CP855",
+    .char_width = pm_encoding_single_char_width,
+    .alnum_char = pm_encoding_cp855_alnum_char,
+    .alpha_char = pm_encoding_cp855_alpha_char,
+    .isupper_char = pm_encoding_cp855_isupper_char,
+    .multibyte = false
+};
+
 /** ISO-8859-1 */
 pm_encoding_t pm_encoding_iso_8859_1 = {
     .name = "ISO-8859-1",

prism/prism.c

@@ -6070,6 +6070,7 @@ parser_lex_magic_comment_encoding_value(pm_parser_t *parser, const uint8_t *star
     ENCODING1("Big5", pm_encoding_big5);
     ENCODING2("CP850", "IBM850", pm_encoding_cp850);
     ENCODING1("CP852", pm_encoding_cp852);
+    ENCODING1("CP855", pm_encoding_cp855);
     ENCODING2("GBK", "CP936", pm_encoding_gbk);
     ENCODING2("ISO-8859-1", "ISO8859-1", pm_encoding_iso_8859_1);
     ENCODING2("ISO-8859-2", "ISO8859-2", pm_encoding_iso_8859_2);

test/prism/encoding_test.rb

@@ -5,46 +5,45 @@ require_relative "test_helper"
 module Prism
   class EncodingTest < TestCase
     [
-      "US-ASCII",
+      Encoding::ASCII,
-      "ASCII-8BIT",
+      Encoding::ASCII_8BIT,
-      "Big5",
+      Encoding::Big5,
-      "CP850",
+      Encoding::CP51932,
-      "CP852",
+      Encoding::CP850,
-      "CP51932",
+      Encoding::CP852,
-      "EUC-JP",
+      Encoding::CP855,
-      "GBK",
+      Encoding::EUC_JP,
-      "ISO-8859-1",
+      Encoding::GBK,
-      "ISO-8859-2",
+      Encoding::ISO_8859_1,
-      "ISO-8859-3",
+      Encoding::ISO_8859_2,
-      "ISO-8859-4",
+      Encoding::ISO_8859_3,
-      "ISO-8859-5",
+      Encoding::ISO_8859_4,
-      "ISO-8859-6",
+      Encoding::ISO_8859_5,
-      "ISO-8859-7",
+      Encoding::ISO_8859_6,
-      "ISO-8859-8",
+      Encoding::ISO_8859_7,
-      "ISO-8859-9",
+      Encoding::ISO_8859_8,
-      "ISO-8859-10",
+      Encoding::ISO_8859_9,
-      "ISO-8859-11",
+      Encoding::ISO_8859_10,
-      "ISO-8859-13",
+      Encoding::ISO_8859_11,
-      "ISO-8859-14",
+      Encoding::ISO_8859_13,
-      "ISO-8859-15",
+      Encoding::ISO_8859_14,
-      "ISO-8859-16",
+      Encoding::ISO_8859_15,
-      "KOI8-R",
+      Encoding::ISO_8859_16,
-      "Shift_JIS",
+      Encoding::KOI8_R,
-      "UTF-8",
+      Encoding::Shift_JIS,
-      "UTF8-MAC",
+      Encoding::UTF_8,
-      "Windows-1250",
+      Encoding::UTF8_MAC,
-      "Windows-1251",
+      Encoding::Windows_1250,
-      "Windows-1252",
+      Encoding::Windows_1251,
-      "Windows-1253",
+      Encoding::Windows_1252,
-      "Windows-1254",
+      Encoding::Windows_1253,
-      "Windows-1255",
+      Encoding::Windows_1254,
-      "Windows-1256",
+      Encoding::Windows_1255,
-      "Windows-1257",
+      Encoding::Windows_1256,
-      "Windows-1258",
+      Encoding::Windows_1257,
-      "Windows-31J"
+      Encoding::Windows_1258,
-    ].each do |canonical_name|
+      Encoding::Windows_31J
-      encoding = Encoding.find(canonical_name)
+    ].each do |encoding|
-
       encoding.names.each do |name|
         # Even though UTF-8-MAC is an alias for UTF8-MAC, CRuby treats it as
         # UTF-8. So we'll skip this test.

test/prism/newline_test.rb

@@ -7,7 +7,7 @@ return unless defined?(RubyVM::InstructionSequence)
 module Prism
   class NewlineTest < TestCase
     base = File.expand_path("../", __FILE__)
-    filepaths = Dir["*.rb", base: base] - %w[unescape_test.rb]
+    filepaths = Dir["*.rb", base: base] - %w[encoding_test.rb unescape_test.rb]
 
     filepaths.each do |relative|
       define_method("test_newline_flags_#{relative}") do