summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--ChangeLog10
-rw-r--r--enc/trans/cp850-tbl.rb130
-rw-r--r--enc/trans/cp852-tbl.rb130
-rw-r--r--enc/trans/cp855-tbl.rb130
-rw-r--r--enc/trans/koi8-r-tbl.rb130
-rw-r--r--enc/trans/koi8-u-tbl.rb130
-rw-r--r--enc/trans/single_byte.trans6
-rw-r--r--enc/trans/tis-620-tbl.rb89
-rw-r--r--test/ruby/test_transcode.rb192
9 files changed, 915 insertions, 32 deletions
diff --git a/ChangeLog b/ChangeLog
index 7bdd0c0bc9..56e29e0f15 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,13 @@
+Tue Dec 9 18:35:35 2008 Martin Duerst <duerst@it.aoyama.ac.jp>
+
+ * enc/trans/single_byte.trans, cp850-tbl.rb, cp852-tbl.rb,
+ cp855-tbl.rb, koi8-r-tbl.rb, koi8-u-tbl.rb, tis-620-tbl.rb:
+ new single-byte transcodings (from Yoshihiro Kambayashi)
+
+ * test/ruby/test_transcode.rb: added tests for the above
+ (from Yoshihiro Kambayashi), small cosmetic fixes
+
+
Tue Dec 9 13:33:53 2008 Nobuyoshi Nakada <nobu@ruby-lang.org>
* compile.c (iseq_compile_each), gc.c (assign_heap_slot),
diff --git a/enc/trans/cp850-tbl.rb b/enc/trans/cp850-tbl.rb
new file mode 100644
index 0000000000..615d3b2599
--- /dev/null
+++ b/enc/trans/cp850-tbl.rb
@@ -0,0 +1,130 @@
+CP850_TO_UCS_TBL = [
+ ["FF",0xA0],
+ ["AD",0xA1],
+ ["BD",0xA2],
+ ["9C",0xA3],
+ ["CF",0xA4],
+ ["BE",0xA5],
+ ["DD",0xA6],
+ ["F5",0xA7],
+ ["F9",0xA8],
+ ["B8",0xA9],
+ ["A6",0xAA],
+ ["AE",0xAB],
+ ["AA",0xAC],
+ ["F0",0xAD],
+ ["A9",0xAE],
+ ["EE",0xAF],
+ ["F8",0xB0],
+ ["F1",0xB1],
+ ["FD",0xB2],
+ ["FC",0xB3],
+ ["EF",0xB4],
+ ["E6",0xB5],
+ ["F4",0xB6],
+ ["FA",0xB7],
+ ["F7",0xB8],
+ ["FB",0xB9],
+ ["A7",0xBA],
+ ["AF",0xBB],
+ ["AC",0xBC],
+ ["AB",0xBD],
+ ["F3",0xBE],
+ ["A8",0xBF],
+ ["B7",0xC0],
+ ["B5",0xC1],
+ ["B6",0xC2],
+ ["C7",0xC3],
+ ["8E",0xC4],
+ ["8F",0xC5],
+ ["92",0xC6],
+ ["80",0xC7],
+ ["D4",0xC8],
+ ["90",0xC9],
+ ["D2",0xCA],
+ ["D3",0xCB],
+ ["DE",0xCC],
+ ["D6",0xCD],
+ ["D7",0xCE],
+ ["D8",0xCF],
+ ["D1",0xD0],
+ ["A5",0xD1],
+ ["E3",0xD2],
+ ["E0",0xD3],
+ ["E2",0xD4],
+ ["E5",0xD5],
+ ["99",0xD6],
+ ["9E",0xD7],
+ ["9D",0xD8],
+ ["EB",0xD9],
+ ["E9",0xDA],
+ ["EA",0xDB],
+ ["9A",0xDC],
+ ["ED",0xDD],
+ ["E8",0xDE],
+ ["E1",0xDF],
+ ["85",0xE0],
+ ["A0",0xE1],
+ ["83",0xE2],
+ ["C6",0xE3],
+ ["84",0xE4],
+ ["86",0xE5],
+ ["91",0xE6],
+ ["87",0xE7],
+ ["8A",0xE8],
+ ["82",0xE9],
+ ["88",0xEA],
+ ["89",0xEB],
+ ["8D",0xEC],
+ ["A1",0xED],
+ ["8C",0xEE],
+ ["8B",0xEF],
+ ["D0",0xF0],
+ ["A4",0xF1],
+ ["95",0xF2],
+ ["A2",0xF3],
+ ["93",0xF4],
+ ["E4",0xF5],
+ ["94",0xF6],
+ ["F6",0xF7],
+ ["9B",0xF8],
+ ["97",0xF9],
+ ["A3",0xFA],
+ ["96",0xFB],
+ ["81",0xFC],
+ ["EC",0xFD],
+ ["E7",0xFE],
+ ["98",0xFF],
+ ["D5",0x131],
+ ["9F",0x192],
+ ["F2",0x2017],
+ ["C4",0x2500],
+ ["B3",0x2502],
+ ["DA",0x250C],
+ ["BF",0x2510],
+ ["C0",0x2514],
+ ["D9",0x2518],
+ ["C3",0x251C],
+ ["B4",0x2524],
+ ["C2",0x252C],
+ ["C1",0x2534],
+ ["C5",0x253C],
+ ["CD",0x2550],
+ ["BA",0x2551],
+ ["C9",0x2554],
+ ["BB",0x2557],
+ ["C8",0x255A],
+ ["BC",0x255D],
+ ["CC",0x2560],
+ ["B9",0x2563],
+ ["CB",0x2566],
+ ["CA",0x2569],
+ ["CE",0x256C],
+ ["DF",0x2580],
+ ["DC",0x2584],
+ ["DB",0x2588],
+ ["B0",0x2591],
+ ["B1",0x2592],
+ ["B2",0x2593],
+ ["FE",0x25A0],
+] \ No newline at end of file
diff --git a/enc/trans/cp852-tbl.rb b/enc/trans/cp852-tbl.rb
new file mode 100644
index 0000000000..6763bfa6e9
--- /dev/null
+++ b/enc/trans/cp852-tbl.rb
@@ -0,0 +1,130 @@
+CP852_TO_UCS_TBL = [
+ ["FF",0xA0],
+ ["CF",0xA4],
+ ["F5",0xA7],
+ ["F9",0xA8],
+ ["AE",0xAB],
+ ["AA",0xAC],
+ ["F0",0xAD],
+ ["F8",0xB0],
+ ["EF",0xB4],
+ ["F7",0xB8],
+ ["AF",0xBB],
+ ["B5",0xC1],
+ ["B6",0xC2],
+ ["8E",0xC4],
+ ["80",0xC7],
+ ["90",0xC9],
+ ["D3",0xCB],
+ ["D6",0xCD],
+ ["D7",0xCE],
+ ["E0",0xD3],
+ ["E2",0xD4],
+ ["99",0xD6],
+ ["9E",0xD7],
+ ["E9",0xDA],
+ ["9A",0xDC],
+ ["ED",0xDD],
+ ["E1",0xDF],
+ ["A0",0xE1],
+ ["83",0xE2],
+ ["84",0xE4],
+ ["87",0xE7],
+ ["82",0xE9],
+ ["89",0xEB],
+ ["A1",0xED],
+ ["8C",0xEE],
+ ["A2",0xF3],
+ ["93",0xF4],
+ ["94",0xF6],
+ ["F6",0xF7],
+ ["A3",0xFA],
+ ["81",0xFC],
+ ["EC",0xFD],
+ ["C6",0x102],
+ ["C7",0x103],
+ ["A4",0x104],
+ ["A5",0x105],
+ ["8F",0x106],
+ ["86",0x107],
+ ["AC",0x10C],
+ ["9F",0x10D],
+ ["D2",0x10E],
+ ["D4",0x10F],
+ ["D1",0x110],
+ ["D0",0x111],
+ ["A8",0x118],
+ ["A9",0x119],
+ ["B7",0x11A],
+ ["D8",0x11B],
+ ["91",0x139],
+ ["92",0x13A],
+ ["95",0x13D],
+ ["96",0x13E],
+ ["9D",0x141],
+ ["88",0x142],
+ ["E3",0x143],
+ ["E4",0x144],
+ ["D5",0x147],
+ ["E5",0x148],
+ ["8A",0x150],
+ ["8B",0x151],
+ ["E8",0x154],
+ ["EA",0x155],
+ ["FC",0x158],
+ ["FD",0x159],
+ ["97",0x15A],
+ ["98",0x15B],
+ ["B8",0x15E],
+ ["AD",0x15F],
+ ["E6",0x160],
+ ["E7",0x161],
+ ["DD",0x162],
+ ["EE",0x163],
+ ["9B",0x164],
+ ["9C",0x165],
+ ["DE",0x16E],
+ ["85",0x16F],
+ ["EB",0x170],
+ ["FB",0x171],
+ ["8D",0x179],
+ ["AB",0x17A],
+ ["BD",0x17B],
+ ["BE",0x17C],
+ ["A6",0x17D],
+ ["A7",0x17E],
+ ["F3",0x2C7],
+ ["F4",0x2D8],
+ ["FA",0x2D9],
+ ["F2",0x2DB],
+ ["F1",0x2DD],
+ ["C4",0x2500],
+ ["B3",0x2502],
+ ["DA",0x250C],
+ ["BF",0x2510],
+ ["C0",0x2514],
+ ["D9",0x2518],
+ ["C3",0x251C],
+ ["B4",0x2524],
+ ["C2",0x252C],
+ ["C1",0x2534],
+ ["C5",0x253C],
+ ["CD",0x2550],
+ ["BA",0x2551],
+ ["C9",0x2554],
+ ["BB",0x2557],
+ ["C8",0x255A],
+ ["BC",0x255D],
+ ["CC",0x2560],
+ ["B9",0x2563],
+ ["CB",0x2566],
+ ["CA",0x2569],
+ ["CE",0x256C],
+ ["DF",0x2580],
+ ["DC",0x2584],
+ ["DB",0x2588],
+ ["B0",0x2591],
+ ["B1",0x2592],
+ ["B2",0x2593],
+ ["FE",0x25A0],
+] \ No newline at end of file
diff --git a/enc/trans/cp855-tbl.rb b/enc/trans/cp855-tbl.rb
new file mode 100644
index 0000000000..72e548b9cb
--- /dev/null
+++ b/enc/trans/cp855-tbl.rb
@@ -0,0 +1,130 @@
+CP855_TO_UCS_TBL = [
+ ["FF",0xA0],
+ ["CF",0xA4],
+ ["FD",0xA7],
+ ["AE",0xAB],
+ ["F0",0xAD],
+ ["AF",0xBB],
+ ["85",0x401],
+ ["81",0x402],
+ ["83",0x403],
+ ["87",0x404],
+ ["89",0x405],
+ ["8B",0x406],
+ ["8D",0x407],
+ ["8F",0x408],
+ ["91",0x409],
+ ["93",0x40A],
+ ["95",0x40B],
+ ["97",0x40C],
+ ["99",0x40E],
+ ["9B",0x40F],
+ ["A1",0x410],
+ ["A3",0x411],
+ ["EC",0x412],
+ ["AD",0x413],
+ ["A7",0x414],
+ ["A9",0x415],
+ ["EA",0x416],
+ ["F4",0x417],
+ ["B8",0x418],
+ ["BE",0x419],
+ ["C7",0x41A],
+ ["D1",0x41B],
+ ["D3",0x41C],
+ ["D5",0x41D],
+ ["D7",0x41E],
+ ["DD",0x41F],
+ ["E2",0x420],
+ ["E4",0x421],
+ ["E6",0x422],
+ ["E8",0x423],
+ ["AB",0x424],
+ ["B6",0x425],
+ ["A5",0x426],
+ ["FC",0x427],
+ ["F6",0x428],
+ ["FA",0x429],
+ ["9F",0x42A],
+ ["F2",0x42B],
+ ["EE",0x42C],
+ ["F8",0x42D],
+ ["9D",0x42E],
+ ["E0",0x42F],
+ ["A0",0x430],
+ ["A2",0x431],
+ ["EB",0x432],
+ ["AC",0x433],
+ ["A6",0x434],
+ ["A8",0x435],
+ ["E9",0x436],
+ ["F3",0x437],
+ ["B7",0x438],
+ ["BD",0x439],
+ ["C6",0x43A],
+ ["D0",0x43B],
+ ["D2",0x43C],
+ ["D4",0x43D],
+ ["D6",0x43E],
+ ["D8",0x43F],
+ ["E1",0x440],
+ ["E3",0x441],
+ ["E5",0x442],
+ ["E7",0x443],
+ ["AA",0x444],
+ ["B5",0x445],
+ ["A4",0x446],
+ ["FB",0x447],
+ ["F5",0x448],
+ ["F9",0x449],
+ ["9E",0x44A],
+ ["F1",0x44B],
+ ["ED",0x44C],
+ ["F7",0x44D],
+ ["9C",0x44E],
+ ["DE",0x44F],
+ ["84",0x451],
+ ["80",0x452],
+ ["82",0x453],
+ ["86",0x454],
+ ["88",0x455],
+ ["8A",0x456],
+ ["8C",0x457],
+ ["8E",0x458],
+ ["90",0x459],
+ ["92",0x45A],
+ ["94",0x45B],
+ ["96",0x45C],
+ ["98",0x45E],
+ ["9A",0x45F],
+ ["EF",0x2116],
+ ["C4",0x2500],
+ ["B3",0x2502],
+ ["DA",0x250C],
+ ["BF",0x2510],
+ ["C0",0x2514],
+ ["D9",0x2518],
+ ["C3",0x251C],
+ ["B4",0x2524],
+ ["C2",0x252C],
+ ["C1",0x2534],
+ ["C5",0x253C],
+ ["CD",0x2550],
+ ["BA",0x2551],
+ ["C9",0x2554],
+ ["BB",0x2557],
+ ["C8",0x255A],
+ ["BC",0x255D],
+ ["CC",0x2560],
+ ["B9",0x2563],
+ ["CB",0x2566],
+ ["CA",0x2569],
+ ["CE",0x256C],
+ ["DF",0x2580],
+ ["DC",0x2584],
+ ["DB",0x2588],
+ ["B0",0x2591],
+ ["B1",0x2592],
+ ["B2",0x2593],
+ ["FE",0x25A0],
+] \ No newline at end of file
diff --git a/enc/trans/koi8-r-tbl.rb b/enc/trans/koi8-r-tbl.rb
new file mode 100644
index 0000000000..a1f55ff2e3
--- /dev/null
+++ b/enc/trans/koi8-r-tbl.rb
@@ -0,0 +1,130 @@
+KOI8_R_TO_UCS_TBL = [
+ ["9A",0xA0],
+ ["BF",0xA9],
+ ["9C",0xB0],
+ ["9D",0xB2],
+ ["9E",0xB7],
+ ["9F",0xF7],
+ ["B3",0x401],
+ ["E1",0x410],
+ ["E2",0x411],
+ ["F7",0x412],
+ ["E7",0x413],
+ ["E4",0x414],
+ ["E5",0x415],
+ ["F6",0x416],
+ ["FA",0x417],
+ ["E9",0x418],
+ ["EA",0x419],
+ ["EB",0x41A],
+ ["EC",0x41B],
+ ["ED",0x41C],
+ ["EE",0x41D],
+ ["EF",0x41E],
+ ["F0",0x41F],
+ ["F2",0x420],
+ ["F3",0x421],
+ ["F4",0x422],
+ ["F5",0x423],
+ ["E6",0x424],
+ ["E8",0x425],
+ ["E3",0x426],
+ ["FE",0x427],
+ ["FB",0x428],
+ ["FD",0x429],
+ ["FF",0x42A],
+ ["F9",0x42B],
+ ["F8",0x42C],
+ ["FC",0x42D],
+ ["E0",0x42E],
+ ["F1",0x42F],
+ ["C1",0x430],
+ ["C2",0x431],
+ ["D7",0x432],
+ ["C7",0x433],
+ ["C4",0x434],
+ ["C5",0x435],
+ ["D6",0x436],
+ ["DA",0x437],
+ ["C9",0x438],
+ ["CA",0x439],
+ ["CB",0x43A],
+ ["CC",0x43B],
+ ["CD",0x43C],
+ ["CE",0x43D],
+ ["CF",0x43E],
+ ["D0",0x43F],
+ ["D2",0x440],
+ ["D3",0x441],
+ ["D4",0x442],
+ ["D5",0x443],
+ ["C6",0x444],
+ ["C8",0x445],
+ ["C3",0x446],
+ ["DE",0x447],
+ ["DB",0x448],
+ ["DD",0x449],
+ ["DF",0x44A],
+ ["D9",0x44B],
+ ["D8",0x44C],
+ ["DC",0x44D],
+ ["C0",0x44E],
+ ["D1",0x44F],
+ ["A3",0x451],
+ ["95",0x2219],
+ ["96",0x221A],
+ ["97",0x2248],
+ ["98",0x2264],
+ ["99",0x2265],
+ ["93",0x2320],
+ ["9B",0x2321],
+ ["80",0x2500],
+ ["81",0x2502],
+ ["82",0x250C],
+ ["83",0x2510],
+ ["84",0x2514],
+ ["85",0x2518],
+ ["86",0x251C],
+ ["87",0x2524],
+ ["88",0x252C],
+ ["89",0x2534],
+ ["8A",0x253C],
+ ["A0",0x2550],
+ ["A1",0x2551],
+ ["A2",0x2552],
+ ["A4",0x2553],
+ ["A5",0x2554],
+ ["A6",0x2555],
+ ["A7",0x2556],
+ ["A8",0x2557],
+ ["A9",0x2558],
+ ["AA",0x2559],
+ ["AB",0x255A],
+ ["AC",0x255B],
+ ["AD",0x255C],
+ ["AE",0x255D],
+ ["AF",0x255E],
+ ["B0",0x255F],
+ ["B1",0x2560],
+ ["B2",0x2561],
+ ["B4",0x2562],
+ ["B5",0x2563],
+ ["B6",0x2564],
+ ["B7",0x2565],
+ ["B8",0x2566],
+ ["B9",0x2567],
+ ["BA",0x2568],
+ ["BB",0x2569],
+ ["BC",0x256A],
+ ["BD",0x256B],
+ ["BE",0x256C],
+ ["8B",0x2580],
+ ["8C",0x2584],
+ ["8D",0x2588],
+ ["8E",0x258C],
+ ["8F",0x2590],
+ ["90",0x2591],
+ ["91",0x2592],
+ ["92",0x2593],
+ ["94",0x25A0],
+] \ No newline at end of file
diff --git a/enc/trans/koi8-u-tbl.rb b/enc/trans/koi8-u-tbl.rb
new file mode 100644
index 0000000000..e87aa1aa3f
--- /dev/null
+++ b/enc/trans/koi8-u-tbl.rb
@@ -0,0 +1,130 @@
+KOI8_U_TO_UCS_TBL = [
+ ["9A",0xA0],
+ ["BF",0xA9],
+ ["9C",0xB0],
+ ["9D",0xB2],
+ ["9E",0xB7],
+ ["9F",0xF7],
+ ["B3",0x401],
+ ["B4",0x404],
+ ["B6",0x406],
+ ["B7",0x407],
+ ["E1",0x410],
+ ["E2",0x411],
+ ["F7",0x412],
+ ["E7",0x413],
+ ["E4",0x414],
+ ["E5",0x415],
+ ["F6",0x416],
+ ["FA",0x417],
+ ["E9",0x418],
+ ["EA",0x419],
+ ["EB",0x41A],
+ ["EC",0x41B],
+ ["ED",0x41C],
+ ["EE",0x41D],
+ ["EF",0x41E],
+ ["F0",0x41F],
+ ["F2",0x420],
+ ["F3",0x421],
+ ["F4",0x422],
+ ["F5",0x423],
+ ["E6",0x424],
+ ["E8",0x425],
+ ["E3",0x426],
+ ["FE",0x427],
+ ["FB",0x428],
+ ["FD",0x429],
+ ["FF",0x42A],
+ ["F9",0x42B],
+ ["F8",0x42C],
+ ["FC",0x42D],
+ ["E0",0x42E],
+ ["F1",0x42F],
+ ["C1",0x430],
+ ["C2",0x431],
+ ["D7",0x432],
+ ["C7",0x433],
+ ["C4",0x434],
+ ["C5",0x435],
+ ["D6",0x436],
+ ["DA",0x437],
+ ["C9",0x438],
+ ["CA",0x439],
+ ["CB",0x43A],
+ ["CC",0x43B],
+ ["CD",0x43C],
+ ["CE",0x43D],
+ ["CF",0x43E],
+ ["D0",0x43F],
+ ["D2",0x440],
+ ["D3",0x441],
+ ["D4",0x442],
+ ["D5",0x443],
+ ["C6",0x444],
+ ["C8",0x445],
+ ["C3",0x446],
+ ["DE",0x447],
+ ["DB",0x448],
+ ["DD",0x449],
+ ["DF",0x44A],
+ ["D9",0x44B],
+ ["D8",0x44C],
+ ["DC",0x44D],
+ ["C0",0x44E],
+ ["D1",0x44F],
+ ["A3",0x451],
+ ["A4",0x454],
+ ["A6",0x456],
+ ["A7",0x457],
+ ["BD",0x490],
+ ["AD",0x491],
+ ["95",0x2219],
+ ["96",0x221A],
+ ["97",0x2248],
+ ["98",0x2264],
+ ["99",0x2265],
+ ["93",0x2320],
+ ["9B",0x2321],
+ ["80",0x2500],
+ ["81",0x2502],
+ ["82",0x250C],
+ ["83",0x2510],
+ ["84",0x2514],
+ ["85",0x2518],
+ ["86",0x251C],
+ ["87",0x2524],
+ ["88",0x252C],
+ ["89",0x2534],
+ ["8A",0x253C],
+ ["A0",0x2550],
+ ["A1",0x2551],
+ ["A2",0x2552],
+ ["A5",0x2554],
+ ["A8",0x2557],
+ ["A9",0x2558],
+ ["AA",0x2559],
+ ["AB",0x255A],
+ ["AC",0x255B],
+ ["AE",0x255D],
+ ["AF",0x255E],
+ ["B0",0x255F],
+ ["B1",0x2560],
+ ["B2",0x2561],
+ ["B5",0x2563],
+ ["B8",0x2566],
+ ["B9",0x2567],
+ ["BA",0x2568],
+ ["BB",0x2569],
+ ["BC",0x256A],
+ ["BE",0x256C],
+ ["8B",0x2580],
+ ["8C",0x2584],
+ ["8D",0x2588],
+ ["8E",0x258C],
+ ["8F",0x2590],
+ ["90",0x2591],
+ ["91",0x2592],
+ ["92",0x2593],
+ ["94",0x25A0],
+] \ No newline at end of file
diff --git a/enc/trans/single_byte.trans b/enc/trans/single_byte.trans
index 80bd3f9ae2..0d42740d30 100644
--- a/enc/trans/single_byte.trans
+++ b/enc/trans/single_byte.trans
@@ -73,6 +73,12 @@
transcode_tblgen_singlebyte "MACROMANIA"
transcode_tblgen_singlebyte "MACTURKISH"
transcode_tblgen_singlebyte "MACUKRAINE"
+ transcode_tblgen_singlebyte "KOI8-U"
+ transcode_tblgen_singlebyte "KOI8-R"
+ transcode_tblgen_singlebyte "TIS-620"
+ transcode_tblgen_singlebyte "CP850"
+ transcode_tblgen_singlebyte "CP852"
+ transcode_tblgen_singlebyte "CP855"
%>
<%= transcode_generated_code %>
diff --git a/enc/trans/tis-620-tbl.rb b/enc/trans/tis-620-tbl.rb
new file mode 100644
index 0000000000..a2f605730a
--- /dev/null
+++ b/enc/trans/tis-620-tbl.rb
@@ -0,0 +1,89 @@
+TIS_620_TO_UCS_TBL = [
+ ["A1",0xE01],
+ ["A2",0xE02],
+ ["A3",0xE03],
+ ["A4",0xE04],
+ ["A5",0xE05],
+ ["A6",0xE06],
+ ["A7",0xE07],
+ ["A8",0xE08],
+ ["A9",0xE09],
+ ["AA",0xE0A],
+ ["AB",0xE0B],
+ ["AC",0xE0C],
+ ["AD",0xE0D],
+ ["AE",0xE0E],
+ ["AF",0xE0F],
+ ["B0",0xE10],
+ ["B1",0xE11],
+ ["B2",0xE12],
+ ["B3",0xE13],
+ ["B4",0xE14],
+ ["B5",0xE15],
+ ["B6",0xE16],
+ ["B7",0xE17],
+ ["B8",0xE18],
+ ["B9",0xE19],
+ ["BA",0xE1A],
+ ["BB",0xE1B],
+ ["BC",0xE1C],
+ ["BD",0xE1D],
+ ["BE",0xE1E],
+ ["BF",0xE1F],
+ ["C0",0xE20],
+ ["C1",0xE21],
+ ["C2",0xE22],
+ ["C3",0xE23],
+ ["C4",0xE24],
+ ["C5",0xE25],
+ ["C6",0xE26],
+ ["C7",0xE27],
+ ["C8",0xE28],
+ ["C9",0xE29],
+ ["CA",0xE2A],
+ ["CB",0xE2B],
+ ["CC",0xE2C],
+ ["CD",0xE2D],
+ ["CE",0xE2E],
+ ["CF",0xE2F],
+ ["D0",0xE30],
+ ["D1",0xE31],
+ ["D2",0xE32],
+ ["D3",0xE33],
+ ["D4",0xE34],
+ ["D5",0xE35],
+ ["D6",0xE36],
+ ["D7",0xE37],
+ ["D8",0xE38],
+ ["D9",0xE39],
+ ["DA",0xE3A],
+ ["DF",0xE3F],
+ ["E0",0xE40],
+ ["E1",0xE41],
+ ["E2",0xE42],
+ ["E3",0xE43],
+ ["E4",0xE44],
+ ["E5",0xE45],
+ ["E6",0xE46],
+ ["E7",0xE47],
+ ["E8",0xE48],
+ ["E9",0xE49],
+ ["EA",0xE4A],
+ ["EB",0xE4B],
+ ["EC",0xE4C],
+ ["ED",0xE4D],
+ ["EE",0xE4E],
+ ["EF",0xE4F],
+ ["F0",0xE50],
+ ["F1",0xE51],
+ ["F2",0xE52],
+ ["F3",0xE53],
+ ["F4",0xE54],
+ ["F5",0xE55],
+ ["F6",0xE56],
+ ["F7",0xE57],
+ ["F8",0xE58],
+ ["F9",0xE59],
+ ["FA",0xE5A],
+ ["FB",0xE5B],
+]
diff --git a/test/ruby/test_transcode.rb b/test/ruby/test_transcode.rb
index 1d16d98422..0d1dfa2231 100644
--- a/test/ruby/test_transcode.rb
+++ b/test/ruby/test_transcode.rb
@@ -146,7 +146,7 @@ class TestTranscode < Test::Unit::TestCase
assert_raise(Encoding::UndefinedConversionError) { "\xFC".encode("utf-8", 'windows-874') }
assert_raise(Encoding::UndefinedConversionError) { "\xFF".encode("utf-8", 'windows-874') }
end
-
+
def test_windows_1250
check_both_ways("\u20AC", "\x80", 'windows-1250') # €
assert_raise(Encoding::UndefinedConversionError) { "\x81".encode("utf-8", 'windows-1250') }
@@ -175,7 +175,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u0111", "\xF0", 'windows-1250') # đ
check_both_ways("\u02D9", "\xFF", 'windows-1250') # ˙
end
-
+
def test_windows_1251
check_both_ways("\u0402", "\x80", 'windows-1251') # Ђ
check_both_ways("\u20AC", "\x88", 'windows-1251') # €
@@ -196,7 +196,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u0440", "\xF0", 'windows-1251') # р
check_both_ways("\u044F", "\xFF", 'windows-1251') # я
end
-
+
def test_windows_1252
check_both_ways("\u20AC", "\x80", 'windows-1252') # €
assert_raise(Encoding::UndefinedConversionError) { "\x81".encode("utf-8", 'windows-1252') }
@@ -204,7 +204,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u0152", "\x8C", 'windows-1252') # >Œ
assert_raise(Encoding::UndefinedConversionError) { "\x8D".encode("utf-8", 'windows-1252') }
check_both_ways("\u017D", "\x8E", 'windows-1252') # Ž
- assert_raise(Encoding::UndefinedConversionError) { "\x8F".encode("utf-8", 'windows-1252') }
+ assert_raise(Encoding::UndefinedConversionError) { "\x8F".encode("utf-8", 'windows-1252') }
assert_raise(Encoding::UndefinedConversionError) { "\x90".encode("utf-8", 'windows-1252') }
check_both_ways("\u2018", "\x91", 'windows-1252') #‘
check_both_ways("\u0153", "\x9C", 'windows-1252') # œ
@@ -261,7 +261,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u03CE", "\xFE", 'windows-1253') # ώ
assert_raise(Encoding::UndefinedConversionError) { "\xFF".encode("utf-8", 'windows-1253') }
end
-
+
def test_windows_1254
check_both_ways("\u20AC", "\x80", 'windows-1254') # €
assert_raise(Encoding::UndefinedConversionError) { "\x81".encode("utf-8", 'windows-1254') }
@@ -288,12 +288,12 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u011F", "\xF0", 'windows-1254') # ğ
check_both_ways("\u00FF", "\xFF", 'windows-1254') # ÿ
end
-
+
def test_windows_1255
- check_both_ways("\u20AC", "\x80", 'windows-1255') # €
- assert_raise(Encoding::UndefinedConversionError) { "\x81".encode("utf-8", 'windows-1255') }
- check_both_ways("\u201A", "\x82", 'windows-1255') # ‚
- check_both_ways("\u2030", "\x89", 'windows-1255') # ‰
+ check_both_ways("\u20AC", "\x80", 'windows-1255') # €
+ assert_raise(Encoding::UndefinedConversionError) { "\x81".encode("utf-8", 'windows-1255') }
+ check_both_ways("\u201A", "\x82", 'windows-1255') # ‚
+ check_both_ways("\u2030", "\x89", 'windows-1255') # ‰
assert_raise(Encoding::UndefinedConversionError) { "\x8A".encode("utf-8", 'windows-1255') }
check_both_ways("\u2039", "\x8B", 'windows-1255') # ‹
assert_raise(Encoding::UndefinedConversionError) { "\x8C".encode("utf-8", 'windows-1255') }
@@ -333,7 +333,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u200F", "\xFE", 'windows-1255') # right-to-left mark
assert_raise(Encoding::UndefinedConversionError) { "\xFF".encode("utf-8", 'windows-1255') }
end
-
+
def test_windows_1256
check_both_ways("\u20AC", "\x80", 'windows-1256') # €
check_both_ways("\u0679", "\x8A", 'windows-1256') # ٹ
@@ -356,7 +356,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u064B", "\xF0", 'windows-1256') # ًً
check_both_ways("\u06D2", "\xFF", 'windows-1256') # ے
end
-
+
def test_windows_1257
check_both_ways("\u20AC", "\x80", 'windows-1257') # €
assert_raise(Encoding::UndefinedConversionError) { "\x81".encode("utf-8", 'windows-1257') }
@@ -420,7 +420,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u2261", "\xF0", 'IBM437') # ≡
check_both_ways("\u00A0", "\xFF", 'IBM437') # non-breaking space
end
-
+
def test_IBM775
check_both_ways("\u0106", "\x80", 'IBM775') # Ć
check_both_ways("\u00C5", "\x8F", 'IBM775') # Å
@@ -439,7 +439,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u00AD", "\xF0", 'IBM775') # osft hyphen
check_both_ways("\u00A0", "\xFF", 'IBM775') # non-breaking space
end
-
+
def test_IBM852
check_both_ways("\u00C7", "\x80", 'IBM852') # Ç
check_both_ways("\u0106", "\x8F", 'IBM852') # Ć
@@ -458,7 +458,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u00AD", "\xF0", 'IBM852') # osft hyphen
check_both_ways("\u00A0", "\xFF", 'IBM852') # non-breaking space
end
-
+
def test_IBM855
check_both_ways("\u0452", "\x80", 'IBM855') # ђ
check_both_ways("\u0408", "\x8F", 'IBM855') # Ј
@@ -505,7 +505,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u00BE", "\xF3", 'IBM857') # ¾
check_both_ways("\u00A0", "\xFF", 'IBM857') # non-breaking space
end
-
+
def test_IBM860
check_both_ways("\u00C7", "\x80", 'IBM860') # Ç
check_both_ways("\u00C2", "\x8F", 'IBM860') # Â
@@ -524,7 +524,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u2261", "\xF0", 'IBM860') # ≡
check_both_ways("\u00A0", "\xFF", 'IBM860') # non-breaking space
end
-
+
def test_IBM861
check_both_ways("\u00C7", "\x80", 'IBM861') # Ç
check_both_ways("\u00C5", "\x8F", 'IBM861') # Å
@@ -543,7 +543,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u2261", "\xF0", 'IBM861') # ≡
check_both_ways("\u00A0", "\xFF", 'IBM861') # non-breaking space
end
-
+
def test_IBM862
check_both_ways("\u05D0", "\x80", 'IBM862') # א
check_both_ways("\u05DF", "\x8F", 'IBM862') # ן
@@ -562,7 +562,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u2261", "\xF0", 'IBM862') # ≡
check_both_ways("\u00A0", "\xFF", 'IBM862') # non-breaking space
end
-
+
def test_IBM863
check_both_ways("\u00C7", "\x80", 'IBM863') # Ç
check_both_ways("\u00A7", "\x8F", 'IBM863') # §
@@ -581,7 +581,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u2261", "\xF0", 'IBM863') # ≡
check_both_ways("\u00A0", "\xFF", 'IBM863') # non-breaking space
end
-
+
def test_IBM865
check_both_ways("\u00C7", "\x80", 'IBM865') # Ç
check_both_ways("\u00C5", "\x8F", 'IBM865') # Å
@@ -600,7 +600,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u2261", "\xF0", 'IBM865') # ≡
check_both_ways("\u00A0", "\xFF", 'IBM865') # non-breaking space
end
-
+
def test_IBM866
check_both_ways("\u0410", "\x80", 'IBM866') # А
check_both_ways("\u041F", "\x8F", 'IBM866') # П
@@ -619,7 +619,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u0401", "\xF0", 'IBM866') # Ё
check_both_ways("\u00A0", "\xFF", 'IBM866') # non-breaking space
end
-
+
def test_IBM869
assert_raise(Encoding::UndefinedConversionError) { "\x80".encode("utf-8", 'IBM869') }
assert_raise(Encoding::UndefinedConversionError) { "\x85".encode("utf-8", 'IBM869') }
@@ -646,7 +646,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u00AD", "\xF0", 'IBM869') # soft hyphen
check_both_ways("\u00A0", "\xFF", 'IBM869') # non-breaking space
end
-
+
def test_macCroatian
check_both_ways("\u00C4", "\x80", 'macCroatian') # Ä
check_both_ways("\u00E8", "\x8F", 'macCroatian') # è
@@ -681,7 +681,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u00E6", "\xFE", 'macCroatian') # æ
check_both_ways("\u02C7", "\xFF", 'macCroatian') # ˇ
end
-
+
def test_macCyrillic
check_both_ways("\u0410", "\x80", 'macCyrillic') # А
check_both_ways("\u041F", "\x8F", 'macCyrillic') # П
@@ -700,7 +700,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u0440", "\xF0", 'macCyrillic') # р
check_both_ways("\u00A4", "\xFF", 'macCyrillic') # ¤
end
-
+
def test_macGreek
check_both_ways("\u00C4", "\x80", 'macGreek') # Ä
check_both_ways("\u00E8", "\x8F", 'macGreek') # è
@@ -721,7 +721,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u03B0", "\xFE", 'macGreek') # ΰ
assert_raise(Encoding::UndefinedConversionError) { "\xFF".encode("utf-8", 'macGreek') }
end
-
+
def test_macIceland
check_both_ways("\u00C4", "\x80", 'macIceland') # Ä
check_both_ways("\u00E8", "\x8F", 'macIceland') # è
@@ -760,7 +760,7 @@ class TestTranscode < Test::Unit::TestCase
#check_both_ways("\uF8FF", "\xF0", 'macRoman') # Apple logo
check_both_ways("\u02C7", "\xFF", 'macRoman') # ˇ
end
-
+
def test_macRomania
check_both_ways("\u00C4", "\x80", 'macRomania') # Ä
check_both_ways("\u00E8", "\x8F", 'macRomania') # è
@@ -780,7 +780,7 @@ class TestTranscode < Test::Unit::TestCase
#check_both_ways("\uF8FF", "\xF0", 'macRomania') # Apple logo
check_both_ways("\u02C7", "\xFF", 'macRomania') # ˇ
end
-
+
def test_macTurkish
check_both_ways("\u00C4", "\x80", 'macTurkish') # Ä
check_both_ways("\u00E8", "\x8F", 'macTurkish') # è
@@ -802,7 +802,7 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u02C6", "\xF6", 'macTurkish') # ˆ
check_both_ways("\u02C7", "\xFF", 'macTurkish') # ˇ
end
-
+
def test_macUkraine
check_both_ways("\u0410", "\x80", 'macUkraine') # А
check_both_ways("\u041F", "\x8F", 'macUkraine') # П
@@ -821,7 +821,135 @@ class TestTranscode < Test::Unit::TestCase
check_both_ways("\u0440", "\xF0", 'macUkraine') # р
check_both_ways("\u00A4", "\xFF", 'macUkraine') # ¤
end
+
+ def test_koi8_u
+ check_both_ways("\u2500", "\x80", 'KOI8-U') # ─
+ check_both_ways("\u2590", "\x8F", 'KOI8-U') # ▐
+ check_both_ways("\u2591", "\x90", 'KOI8-U') # ░
+ check_both_ways("\u00F7", "\x9F", 'KOI8-U') # ÷
+ check_both_ways("\u2550", "\xA0", 'KOI8-U') # ═
+ check_both_ways("\u0454", "\xA4", 'KOI8-U') # є
+ check_both_ways("\u0456", "\xA6", 'KOI8-U') # і
+ check_both_ways("\u0457", "\xA7", 'KOI8-U') # ї
+ check_both_ways("\u0491", "\xAD", 'KOI8-U') # ґ
+ check_both_ways("\u255E", "\xAF", 'KOI8-U') # ╞
+ check_both_ways("\u255F", "\xB0", 'KOI8-U') # ╟
+ check_both_ways("\u0404", "\xB4", 'KOI8-U') # Є
+ check_both_ways("\u0406", "\xB6", 'KOI8-U') # І
+ check_both_ways("\u0407", "\xB7", 'KOI8-U') # Ї
+ check_both_ways("\u0490", "\xBD", 'KOI8-U') # Ґ
+ check_both_ways("\u00A9", "\xBF", 'KOI8-U') # ©
+ check_both_ways("\u044E", "\xC0", 'KOI8-U') # ю
+ check_both_ways("\u043E", "\xCF", 'KOI8-U') # о
+ check_both_ways("\u043F", "\xD0", 'KOI8-U') # п
+ check_both_ways("\u044A", "\xDF", 'KOI8-U') # ъ
+ check_both_ways("\u042E", "\xE0", 'KOI8-U') # Ю
+ check_both_ways("\u041E", "\xEF", 'KOI8-U') # О
+ check_both_ways("\u041F", "\xF0", 'KOI8-U') # П
+ check_both_ways("\u042A", "\xFF", 'KOI8-U') # Ъ
+ end
+
+ def test_koi8_r
+ check_both_ways("\u2500", "\x80", 'KOI8-R') # ─
+ check_both_ways("\u2590", "\x8F", 'KOI8-R') # ▐
+ check_both_ways("\u2591", "\x90", 'KOI8-R') # ░
+ check_both_ways("\u00F7", "\x9F", 'KOI8-R') # ÷
+ check_both_ways("\u2550", "\xA0", 'KOI8-R') # ═
+ check_both_ways("\u255E", "\xAF", 'KOI8-R') # ╞
+ check_both_ways("\u255F", "\xB0", 'KOI8-R') # ╟
+ check_both_ways("\u00A9", "\xBF", 'KOI8-R') # ©
+ check_both_ways("\u044E", "\xC0", 'KOI8-R') # ю
+ check_both_ways("\u043E", "\xCF", 'KOI8-R') # о
+ check_both_ways("\u043F", "\xD0", 'KOI8-R') # п
+ check_both_ways("\u044A", "\xDF", 'KOI8-R') # ъ
+ check_both_ways("\u042E", "\xE0", 'KOI8-R') # Ю
+ check_both_ways("\u041E", "\xEF", 'KOI8-R') # О
+ check_both_ways("\u041F", "\xF0", 'KOI8-R') # П
+ check_both_ways("\u042A", "\xFF", 'KOI8-R') # Ъ
+ end
+
+ def test_TIS_620
+ assert_raise(Encoding::UndefinedConversionError) { "\x80".encode("utf-8", 'TIS-620') }
+ assert_raise(Encoding::UndefinedConversionError) { "\x8F".encode("utf-8", 'TIS-620') }
+ assert_raise(Encoding::UndefinedConversionError) { "\x90".encode("utf-8", 'TIS-620') }
+ assert_raise(Encoding::UndefinedConversionError) { "\x9F".encode("utf-8", 'TIS-620') }
+ assert_raise(Encoding::UndefinedConversionError) { "\xA0".encode("utf-8", 'TIS-620') }
+ check_both_ways("\u0E01", "\xA1", 'TIS-620') # ก
+ check_both_ways("\u0E0F", "\xAF", 'TIS-620') # ฏ
+ check_both_ways("\u0E10", "\xB0", 'TIS-620') # ฐ
+ check_both_ways("\u0E1F", "\xBF", 'TIS-620') # ฟ
+ check_both_ways("\u0E20", "\xC0", 'TIS-620') # ภ
+ check_both_ways("\u0E2F", "\xCF", 'TIS-620') # ฯ
+ check_both_ways("\u0E30", "\xD0", 'TIS-620') # ะ
+ check_both_ways("\u0E3A", "\xDA", 'TIS-620') # ฺ
+ assert_raise(Encoding::UndefinedConversionError) { "\xDB".encode("utf-8", 'TIS-620') }
+ assert_raise(Encoding::UndefinedConversionError) { "\xDE".encode("utf-8", 'TIS-620') }
+ check_both_ways("\u0E3F", "\xDF", 'TIS-620') # ฿
+ check_both_ways("\u0E40", "\xE0", 'TIS-620') # เ
+ check_both_ways("\u0E4F", "\xEF", 'TIS-620') # ๏
+ check_both_ways("\u0E50", "\xF0", 'TIS-620') # ๐
+ check_both_ways("\u0E5B", "\xFB", 'TIS-620') # ๛
+ assert_raise(Encoding::UndefinedConversionError) { "\xFC".encode("utf-8", 'TIS-620') }
+ assert_raise(Encoding::UndefinedConversionError) { "\xFF".encode("utf-8", 'TIS-620') }
+ end
+ def test_CP850
+ check_both_ways("\u00C7", "\x80", 'CP850') # Ç
+ check_both_ways("\u00C5", "\x8F", 'CP850') # Å
+ check_both_ways("\u00C9", "\x90", 'CP850') # É
+ check_both_ways("\u0192", "\x9F", 'CP850') # ƒ
+ check_both_ways("\u00E1", "\xA0", 'CP850') # á
+ check_both_ways("\u00BB", "\xAF", 'CP850') # »
+ check_both_ways("\u2591", "\xB0", 'CP850') # ░
+ check_both_ways("\u2510", "\xBF", 'CP850') # ┐
+ check_both_ways("\u2514", "\xC0", 'CP850') # └
+ check_both_ways("\u00A4", "\xCF", 'CP850') # ¤
+ check_both_ways("\u00F0", "\xD0", 'CP850') # ð
+ check_both_ways("\u2580", "\xDF", 'CP850') # ▀
+ check_both_ways("\u00D3", "\xE0", 'CP850') # Ó
+ check_both_ways("\u00B4", "\xEF", 'CP850') # ´
+ check_both_ways("\u00AD", "\xF0", 'CP850') # soft hyphen
+ check_both_ways("\u00A0", "\xFF", 'CP850') # non-breaking space
+ end
+
+ def test_CP852
+ check_both_ways("\u00C7", "\x80", 'CP852') # Ç
+ check_both_ways("\u0106", "\x8F", 'CP852') # Ć
+ check_both_ways("\u00C9", "\x90", 'CP852') # É
+ check_both_ways("\u010D", "\x9F", 'CP852') # č
+ check_both_ways("\u00E1", "\xA0", 'CP852') # á
+ check_both_ways("\u00BB", "\xAF", 'CP852') # »
+ check_both_ways("\u2591", "\xB0", 'CP852') # ░
+ check_both_ways("\u2510", "\xBF", 'CP852') # ┐
+ check_both_ways("\u2514", "\xC0", 'CP852') # └
+ check_both_ways("\u00A4", "\xCF", 'CP852') # ¤
+ check_both_ways("\u0111", "\xD0", 'CP852') # đ
+ check_both_ways("\u2580", "\xDF", 'CP852') # ▀
+ check_both_ways("\u00D3", "\xE0", 'CP852') # Ó
+ check_both_ways("\u00B4", "\xEF", 'CP852') # ´
+ check_both_ways("\u00AD", "\xF0", 'CP852') # soft hyphen
+ check_both_ways("\u00A0", "\xFF", 'CP852') # non-breaking space
+ end
+
+ def test_CP855
+ check_both_ways("\u0452", "\x80", 'CP855') # ђ
+ check_both_ways("\u0408", "\x8F", 'CP855') # Ј
+ check_both_ways("\u0459", "\x90", 'CP855') # љ
+ check_both_ways("\u042A", "\x9F", 'CP855') # Ъ
+ check_both_ways("\u0430", "\xA0", 'CP855') # а
+ check_both_ways("\u00BB", "\xAF", 'CP855') # »
+ check_both_ways("\u2591", "\xB0", 'CP855') # ░
+ check_both_ways("\u2510", "\xBF", 'CP855') # ┐
+ check_both_ways("\u2514", "\xC0", 'CP855') # └
+ check_both_ways("\u00A4", "\xCF", 'CP855') # ¤
+ check_both_ways("\u043B", "\xD0", 'CP855') # л
+ check_both_ways("\u2580", "\xDF", 'CP855') # ▀
+ check_both_ways("\u042F", "\xE0", 'CP855') # Я
+ check_both_ways("\u2116", "\xEF", 'CP855') # №
+ check_both_ways("\u00AD", "\xF0", 'CP855') # soft hyphen
+ check_both_ways("\u00A0", "\xFF", 'CP855') # non-breaking space
+ end
+
def check_utf_16_both_ways(utf8, raw)
copy = raw.dup
0.step(copy.length-1, 2) { |i| copy[i+1], copy[i] = copy[i], copy[i+1] }
@@ -933,7 +1061,7 @@ class TestTranscode < Test::Unit::TestCase
check_utf_32_both_ways("\u{8FF00}", "\x00\x08\xFF\x00")
check_utf_32_both_ways("\u{F00FF}", "\x00\x0F\x00\xFF")
end
-
+
def test_invalid_ignore
# arguments only
assert_nothing_raised { 'abc'.encode('utf-8', invalid: :replace, replace: "") }
@@ -1212,11 +1340,11 @@ class TestTranscode < Test::Unit::TestCase
assert_equal("\e$B!!\e(B".force_encoding("ISO-2022-JP"),
"\xA1\xA1".encode("ISO-2022-JP", "EUC-JP"))
end
-
+
def test_iso_2022_jp_1
# check_both_ways("\u9299", "\x1b$(Dd!\x1b(B", "iso-2022-jp-1") # JIS X 0212 区68 点01 銙
end
-
+
def test_unicode_public_review_issue_121 # see http://www.unicode.org/review/pr-121.html
# assert_equal("\x00\x61\xFF\xFD\x00\x62".force_encoding('UTF-16BE'),
# "\x61\xF1\x80\x80\xE1\x80\xC2\x62".encode('UTF-16BE', 'UTF-8', invalid: :replace)) # option 1
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-09 18:58:14 +0000