From c16bda7bbccbb9f6e10cae0269ca32c112cc53ec Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Thu, 19 Dec 2024 09:21:55 +0100
Subject: [PATCH 1/8] #730 Add code page CP1146.

---
 .../parser/encoding/codepage/CodePage.scala   |  1 +
 .../encoding/codepage/CodePage1145.scala      |  5 +-
 .../encoding/codepage/CodePage1146.scala      | 55 +++++++++++++++++++
 .../parser/decoders/StringDecodersSpec.scala  | 11 ++++
 .../codepage/CodePageSingleByteSpec.scala     |  5 ++
 5 files changed, 75 insertions(+), 2 deletions(-)
 create mode 100644 cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1146.scala

diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
index 2c0d9b8a2..6667f1ee9 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
@@ -63,6 +63,7 @@ object CodePage extends Logging {
       case "cp1140"          => new CodePage1140
       case "cp1141"          => new CodePage1141
       case "cp1145"          => new CodePage1145
+      case "cp1146"          => new CodePage1146
       case "cp1148"          => new CodePage1148
       case "cp1364"          => new CodePage1364
       case "cp1388"          => new CodePage1388
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1145.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1145.scala
index fcb86ed8e..36568bc36 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1145.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1145.scala
@@ -17,7 +17,8 @@
 package za.co.absa.cobrix.cobol.parser.encoding.codepage
 
 /**
-  * EBCDIC code page 284 is used to represent characters of Spain and Latin America.
+  * EBCDIC code page 1145 is used to represent characters of Spain and Latin America
+  * with € at the position of the international currency symbol ¤.
   */
 class CodePage1145 extends SingleByteCodePage(CodePage1145.ebcdicToAsciiMapping) {
   override def codePageShortName: String = "cp1145"
@@ -27,7 +28,7 @@ object CodePage1145 {
   val ebcdicToAsciiMapping: Array[Char] = {
     import EbcdicNonPrintable._
 
-    /* This is the EBCDIC Code Page 1145 which is the euro currency update of code  page CCSID 284
+    /* This is the EBCDIC Code Page 1145 which is the euro currency update of code page CCSID 284
        from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_284 */
     val ebcdic2ascii: Array[Char] = {
       // Non-printable characters map used: http://www.pacsys.com/asciitab.htm
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1146.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1146.scala
new file mode 100644
index 000000000..0dce6b10a
--- /dev/null
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1146.scala
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2018 ABSA Group Limited
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package za.co.absa.cobrix.cobol.parser.encoding.codepage
+
+/**
+  * EBCDIC code page 1146 is used to represent characters of the United Kingdom
+  * with € at the position of the international currency symbol ¤.
+  */
+class CodePage1146 extends SingleByteCodePage(CodePage1146.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp1146"
+}
+
+object CodePage1146 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 1146 which is the euro currency update of code page CCSID 285
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_285 */
+    val ebcdic2ascii: Array[Char] = {
+      // Non-printable characters map used: http://www.pacsys.com/asciitab.htm
+      Array[Char](
+        c00, c01, c02, c03, spc, c09, spc, del, spc, spc, spc, c0b, c0c, ccr, c0e, c0f, //   0 -  15
+        c10, c11, c12, c13, spc, nel, c08, spc, c18, c19, spc, spc, c1c, c1d, c1e, c1f, //  16 -  31
+        spc, spc, spc, spc, spc, clf, c17, c1b, spc, spc, spc, spc, spc, c05, c06, c07, //  32 -  47
+        spc, spc, c16, spc, spc, spc, spc, c04, spc, spc, spc, spc, c14, c15, spc, c1a, //  48 -  63
+        ' ', rsp, 'â', 'ä', 'à', 'á', 'ã', 'å', 'ç', 'ñ', '$', '.', '<', '(', '+', '|', //  64 -  79
+        '&', 'é', 'ê', 'ë', 'è', 'í', 'î', 'ï', 'ì', 'ß', '!', '£', '*', ')', ';', '¬', //  80 -  95
+        '-', '/', 'Â', 'Ä', 'À', 'Á', 'Ã', 'Å', 'Ç', 'Ñ', '¦', ',', '%', '_', '>', '?', //  96 - 111
+        'ø', 'É', 'Ê', 'Ë', 'È', 'Í', 'Î', 'Ï', 'Ì', '`', ':', '#', '@', qts, '=', qtd, // 112 - 127
+        'Ø', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', '«', '»', 'ð', 'ý', 'þ', '±', // 128 - 143
+        '°', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'ª', 'º', 'æ', '¸', 'Æ', '€', // 144 - 159
+        'µ', '¯', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '¡', '¿', 'Ð', 'Ý', 'Þ', '®', // 160 - 175
+        '¢', '[', '¥', '·', '©', '§', '¶', '¼', '½', '¾', '^', ']', '~', '¨', '´', '×', // 176 - 191
+        '{', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', shy, 'ô', 'ö', 'ò', 'ó', 'õ', // 192 - 207
+        '}', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', '¹', 'û', 'ü', 'ù', 'ú', 'ÿ', // 208 - 223
+        bsh, '÷', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '²', 'Ô', 'Ö', 'Ò', 'Ó', 'Õ', // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '³', 'Û', 'Ü', 'Ù', 'Ú', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
index 150658e0a..2c7917be6 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
@@ -285,6 +285,17 @@ class StringDecodersSpec extends AnyWordSpec {
         assert(actual == expected)
       }
 
+      "decode a CP1146 string special characters" in {
+        val expected = " $£¯¢[^~ä#|üܬ§¦!ߢ$Ö{}æö¯å@ÆØÅÄÉ€ "
+        val bytes = Array(0x40, 0x4A, 0x5B, 0xA1, 0xB0, 0xB1, 0xBA, 0xBC, 0x43, 0x7B, 0x4F, 0xDC, 0xFC, 0x5F, 0xB5, 0x6A, 0x5A, 0x59,
+          0xB0, 0x4A, 0xEC, 0xC0, 0xD0, 0x9C, 0xCC, 0xA1, 0x47, 0x7C, 0x9E, 0x80, 0x67, 0x63,
+          0x71, 0x9F, 0x40).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage1146, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
+
       "decode a CP1148 string special characters" in {
         val expected = "âäàáãåçñ[.<(+!&éêëèíîïìß]$*);^-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ€µ~stuvwxyz¡¿ÐÝÞ®¢£¥·©§¶¼½¾¬|¯¨´×{ABCDEFGHI\u00ADôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙÚ"
         val bytes = Array(
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
index 4d1d933df..4be8be0d7 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
@@ -132,6 +132,11 @@ class CodePageSingleByteSpec extends AnyFunSuite {
     assert(codePage.codePageShortName == "cp1145")
   }
 
+  test("Ensure codepage 'cp1146' gives the associated CodePage") {
+    val codePage = CodePage.getCodePageByName("cp1146")
+    assert(codePage.codePageShortName == "cp1146")
+  }
+
   test("Ensure codepage 'cp1148' gives the associated CodePage") {
     val codePage = CodePage.getCodePageByName("cp1148")
     assert(codePage.codePageShortName == "cp1148")

From bd4bb170611be2443ebb97738b71a680b2fc56c5 Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Thu, 19 Dec 2024 11:32:47 +0100
Subject: [PATCH 2/8] #730 Add CP274 (Belgium).

---
 README.md                                     |  1 +
 .../parser/encoding/codepage/CodePage.scala   |  1 +
 .../encoding/codepage/CodePage274.scala       | 54 +++++++++++++++++++
 .../parser/decoders/StringDecodersSpec.scala  | 11 ++++
 .../codepage/CodePageSingleByteSpec.scala     |  5 ++
 5 files changed, 72 insertions(+)
 create mode 100644 cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage274.scala

diff --git a/README.md b/README.md
index 53167d512..54cf5bc36 100644
--- a/README.md
+++ b/README.md
@@ -1625,6 +1625,7 @@ The output looks like this:
 | .option("ebcdic_code_page", "common") | Common      | (Default) Only characters common across EBCDIC code pages are decoded.                                      |
 | .option("ebcdic_code_page", "cp037")  | EBCDIC 037  | Australia, Brazil, Canada, New Zealand, Portugal, South Africa, USA.                                        |
 | .option("ebcdic_code_page", "cp273")  | EBCDIC 273  | Germany, Austria.                                                                                           |
+| .option("ebcdic_code_page", "cp274")  | EBCDIC 274  | Belgium.                                                                                                    |
 | .option("ebcdic_code_page", "cp275")  | EBCDIC 275  | Brazil.                                                                                                     |
 | .option("ebcdic_code_page", "cp277")  | EBCDIC 277  | Denmark and Norway.                                                                                         |
 | .option("ebcdic_code_page", "cp278")  | EBCDIC 278  | Finland and Sweden.                                                                                         |
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
index 6667f1ee9..35bbbe7c3 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
@@ -46,6 +46,7 @@ object CodePage extends Logging {
       case "cp037_extended"  => new CodePage037Ext
       case "cp00300"         => new CodePage300 // This is the same as cp300
       case "cp273"           => new CodePage273
+      case "cp274"           => new CodePage274
       case "cp275"           => new CodePage275
       case "cp277"           => new CodePage277
       case "cp278"           => new CodePage278
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage274.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage274.scala
new file mode 100644
index 000000000..8cfc9706c
--- /dev/null
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage274.scala
@@ -0,0 +1,54 @@
+/*
+ * Copyright 2018 ABSA Group Limited
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package za.co.absa.cobrix.cobol.parser.encoding.codepage
+
+/**
+  * EBCDIC code page 274. Belgium.
+  */
+class CodePage274 extends SingleByteCodePage(CodePage274.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp274"
+}
+
+object CodePage274 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 274 to ASCII conversion table
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_274 */
+    val ebcdic2ascii: Array[Char] = {
+      // Non-printable characters map used: http://www.pacsys.com/asciitab.htm
+      Array[Char](
+        c00, c01, c02, c03, spc, c09, spc, del, spc, spc, spc, c0b, c0c, ccr, c0e, c0f, //   0 -  15
+        c10, c11, c12, c13, spc, nel, c08, spc, c18, c19, spc, spc, c1c, c1d, c1e, c1f, //  16 -  31
+        spc, spc, spc, spc, spc, clf, c17, c1b, spc, spc, spc, spc, spc, c05, c06, c07, //  32 -  47
+        spc, spc, c16, spc, spc, spc, spc, c04, spc, spc, spc, spc, c14, c15, spc, c1a, //  48 -  63
+        ' ', rsp, 'â', 'ä', '@', 'á', 'ã', 'å', bsh, 'ñ', '[', '.', '<', '(', '+', '!', //  64 -  79
+        '&', '{', 'ê', 'ë', '}', 'í', 'î', 'ï', 'ì', 'ß', ']', '$', '*', ')', ';', '^', //  80 -  95
+        '-', '/', 'Â', 'Ä', 'À', 'Á', 'Ã', 'Å', 'Ç', 'Ñ', 'ù', ',', '%', '_', '>', '?', //  96 - 111
+        'ø', 'É', 'Ê', 'Ë', 'È', 'Í', 'Î', 'Ï', 'Ì', '`', ':', '#', 'à', qts, '=', qtd, // 112 - 127
+        'Ø', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', '«', '»', 'ð', 'ý', 'þ', '±', // 128 - 143
+        '°', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'ª', 'º', 'æ', '¸', 'Æ', '¤', // 144 - 159
+        'µ', '¨', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '¡', '¿', 'Ð', 'Ý', 'Þ', '®', // 160 - 175
+        '¢', '£', '¥', '·', '©', '§', '¶', '¼', '½', '¾', '¬', '|', '¯', '~', '´', '×', // 176 - 191
+        'é', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', shy, 'ô', 'ö', 'ò', 'ó', 'õ', // 192 - 207
+        'è', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', '¹', 'û', 'ü', '¦', 'ú', 'ÿ', // 208 - 223
+        'ç', '÷', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '²', 'Ô', 'Ö', 'Ò', 'Ó', 'Õ', // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '³', 'Û', 'Ü', 'Ù', 'Ú', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
index 2c7917be6..c47dc0c42 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
@@ -105,6 +105,17 @@ class StringDecodersSpec extends AnyWordSpec {
         assert(actual == expected)
       }
 
+      "decode a CP274 string special characters" in {
+        val expected = " æÄ!üÜ^Æö]ߢ§Øäèéø¨åÖ#àÅ[ç¤Ç "
+        val bytes = Array(0x40, 0x9C, 0x63, 0x4F, 0xDC, 0xFC, 0x5F, 0x9E, 0xCC, 0x5A, 0x59,
+          0xB0, 0xB5, 0x80, 0x43, 0xD0, 0xC0, 0x70, 0xA1, 0x47, 0xEC, 0x7B, 0x7C, 0x67, 0x4A,
+          0xE0, 0x9F, 0x68, 0x40).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage274, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
+
       "decode a CP275 string special characters" in {
         val expected = " æÄ!üÜ^Æö$ߢ§Øäéõø~åÖÕÃÅÉ\\¤] "
         val bytes = Array(0x40, 0x9C, 0x63, 0x4F, 0xDC, 0xFC, 0x5F, 0x9E, 0xCC, 0x5A, 0x59,
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
index 4be8be0d7..3fe3253c6 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
@@ -47,6 +47,11 @@ class CodePageSingleByteSpec extends AnyFunSuite {
     assert(codePage.codePageShortName == "cp273")
   }
 
+  test("Ensure codepage 'cp274' gives the associated CodePage") {
+    val codePage = CodePage.getCodePageByName("cp274")
+    assert(codePage.codePageShortName == "cp274")
+  }
+
   test("Ensure codepage 'cp275' gives the associated CodePage") {
     val codePage = CodePage.getCodePageByName("cp275")
     assert(codePage.codePageShortName == "cp275")

From 0ff28fd2aac49c56c201ce447f3785e16bd07878 Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Tue, 7 Jan 2025 09:56:14 +0100
Subject: [PATCH 3/8] =?UTF-8?q?Add=20CP1142=20code=20page=20(Denmark=20and?=
 =?UTF-8?q?=20Norway)=20which=20is=20same=20as=20CP277=20with=205A=20is=20?=
 =?UTF-8?q?replaced=20with=20the=20"=E2=82=AC"=20(euro)=20character.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                                     |  1 +
 .../parser/encoding/codepage/CodePage.scala   |  1 +
 .../encoding/codepage/CodePage1142.scala      | 57 +++++++++++++++++++
 .../parser/decoders/StringDecodersSpec.scala  | 22 +++++++
 .../codepage/CodePageSingleByteSpec.scala     |  5 ++
 5 files changed, 86 insertions(+)
 create mode 100644 cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1142.scala

diff --git a/README.md b/README.md
index 54cf5bc36..399f79920 100644
--- a/README.md
+++ b/README.md
@@ -1642,6 +1642,7 @@ The output looks like this:
 | .option("ebcdic_code_page", "cp1047") | EBCDIC 1047 | A code page containing all of the Latin-1/Open System characters.                                           |
 | .option("ebcdic_code_page", "cp1140") | EBCDIC 1140 | Same as code page 037 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1141") | EBCDIC 1141 | Same as code page 273 with € at the position of the international currency symbol ¤.                        |
+| .option("ebcdic_code_page", "cp1142") | EBCDIC 1142 | Same as code page 277 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1145") | EBCDIC 1145 | Same as code page 284 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1148") | EBCDIC 1148 | Same as code page 500 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1364") | EBCDIC 1364 | Double-byte code page CCSID-1364, Korean.                                                                   |
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
index 35bbbe7c3..5ff82c26a 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
@@ -63,6 +63,7 @@ object CodePage extends Logging {
       case "cp1047"          => new CodePage1047
       case "cp1140"          => new CodePage1140
       case "cp1141"          => new CodePage1141
+      case "cp1142"          => new CodePage1142
       case "cp1145"          => new CodePage1145
       case "cp1146"          => new CodePage1146
       case "cp1148"          => new CodePage1148
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1142.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1142.scala
new file mode 100644
index 000000000..f3c449771
--- /dev/null
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1142.scala
@@ -0,0 +1,57 @@
+/*
+ * Copyright 2018 ABSA Group Limited
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package za.co.absa.cobrix.cobol.parser.encoding.codepage
+
+/**
+  * EBCDIC code page 1142. Denmark and Norway.
+  *
+  * It corresponds to code page 277 and only differs from it in position 5A, where the euro sign € is located instead
+  * of the international currency symbol ¤.
+  */
+class CodePage1142 extends SingleByteCodePage(CodePage1142.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp1142"
+}
+
+object CodePage1142 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 1142 to ASCII conversion table
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_277 */
+    val ebcdic2ascii: Array[Char] = {
+      // Non-printable characters map used: http://www.pacsys.com/asciitab.htm
+      Array[Char](
+        c00, c01, c02, c03, spc, c09, spc, del, spc, spc, spc, c0b, c0c, ccr, c0e, c0f, //   0 -  15
+        c10, c11, c12, c13, spc, nel, c08, spc, c18, c19, spc, spc, c1c, c1d, c1e, c1f, //  16 -  31
+        spc, spc, spc, spc, spc, clf, c17, c1b, spc, spc, spc, spc, spc, c05, c06, c07, //  32 -  47
+        spc, spc, c16, spc, spc, spc, spc, c04, spc, spc, spc, spc, c14, c15, spc, c1a, //  48 -  63
+        ' ', rsp, 'â', 'ä', 'à', 'á', 'ã', '}', 'ç', 'ñ', '#', '.', '<', '(', '+', '!', //  64 -  79
+        '&', 'é', 'ê', 'ë', 'è', 'í', 'î', 'ï', 'ì', 'ß', '€', 'Å', '*', ')', ';', '^', //  80 -  95
+        '-', '/', 'Â', 'Ä', 'À', 'Á', 'Ã', '$', 'Ç', 'Ñ', 'ø', ',', '%', '_', '>', '?', //  96 - 111
+        '¦', 'É', 'Ê', 'Ë', 'È', 'Í', 'Î', 'Ï', 'Ì', '`', ':', 'Æ', 'Ø', qts, '=', qtd, // 112 - 127
+        '@', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', '«', '»', 'ð', 'ý', 'þ', '±', // 128 - 143
+        '°', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'ª', 'º', '{', '¸', '[', ']', // 144 - 159
+        'µ', 'ü', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '¡', '¿', 'Ð', 'Ý', 'Þ', '®', // 160 - 175
+        '¢', '£', '¥', '·', '©', '§', '¶', '¼', '½', '¾', '¬', '|', '¯', '¨', '´', '×', // 176 - 191
+        'æ', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', shy, 'ô', 'ö', 'ò', 'ó', 'õ', // 192 - 207
+        'å', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', '¹', 'û', '~', 'ù', 'ú', 'ÿ', // 208 - 223
+        bsh, '÷', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '²', 'Ô', 'Ö', 'Ò', 'Ó', 'Õ', // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '³', 'Û', 'Ü', 'Ù', 'Ú', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
index c47dc0c42..c20a432f6 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
@@ -285,6 +285,28 @@ class StringDecodersSpec extends AnyWordSpec {
         assert(actual == expected)
       }
 
+      "decode a CP1142 string example" in {
+        val expected = "âäàáã}çñ#.<(+!&éêëèíîïì߀Å*);^-/ÂÄÀÁÃ$ÇÑø,%_>?¦ÉÊËÈÍÎÏÌ`:ÆØ'=\"@abcdefghi«»ðýþ±°jklmnopqrªº{¸[]µüstuvwxyz¡¿ÐÝÞ®¢£¥·©§¶¼½¾¬|¯¨´×æABCDEFGHI\u00ADôöòóõåJKLMNOPQR¹û~ùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙÚ"
+        val bytes = Array(
+          0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
+          0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
+          0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
+          0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
+          0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F,
+          0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9A, 0x9B, 0x9C, 0x9D, 0x9E, 0x9F,
+          0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF,
+          0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
+          0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
+          0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, 0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
+          0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
+          0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE
+        ).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage1142, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
+
       "decode a CP1145 string special characters" in {
         val expected = " äÑ|üܬ§ñ]ߢ[Ö{}æö¨å@ÆØÅÄÉ€ "
         val bytes = Array(0x40, 0x43, 0x7B, 0x4F, 0xDC, 0xFC, 0x5F, 0xB5, 0x6A, 0x5A, 0x59,
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
index 3fe3253c6..ae93375f7 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
@@ -132,6 +132,11 @@ class CodePageSingleByteSpec extends AnyFunSuite {
     assert(codePage.codePageShortName == "cp1141")
   }
 
+  test("Ensure codepage 'cp1142' gives the associated CodePage") {
+    val codePage = CodePage.getCodePageByName("cp1142")
+    assert(codePage.codePageShortName == "cp1142")
+  }
+
   test("Ensure codepage 'cp1145' gives the associated CodePage") {
     val codePage = CodePage.getCodePageByName("cp1145")
     assert(codePage.codePageShortName == "cp1145")

From c4a32291f7011fe1392a6ade68114da6e4be7851 Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Wed, 8 Jan 2025 09:05:53 +0100
Subject: [PATCH 4/8] =?UTF-8?q?Add=20CP1143=20code=20page=20(Finland=20and?=
 =?UTF-8?q?=20Sweden)=20which=20is=20same=20as=20CP278=20with=205A=20is=20?=
 =?UTF-8?q?replaced=20with=20the=20"=E2=82=AC"=20(euro)=20character.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                                     |  1 +
 .../parser/encoding/codepage/CodePage.scala   |  1 +
 .../encoding/codepage/CodePage1143.scala      | 57 +++++++++++++++++++
 .../parser/decoders/StringDecodersSpec.scala  | 22 +++++++
 .../codepage/CodePageSingleByteSpec.scala     |  5 ++
 5 files changed, 86 insertions(+)
 create mode 100644 cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1143.scala

diff --git a/README.md b/README.md
index 399f79920..3b02246fa 100644
--- a/README.md
+++ b/README.md
@@ -1643,6 +1643,7 @@ The output looks like this:
 | .option("ebcdic_code_page", "cp1140") | EBCDIC 1140 | Same as code page 037 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1141") | EBCDIC 1141 | Same as code page 273 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1142") | EBCDIC 1142 | Same as code page 277 with € at the position of the international currency symbol ¤.                        |
+| .option("ebcdic_code_page", "cp1143") | EBCDIC 1143 | Same as code page 278 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1145") | EBCDIC 1145 | Same as code page 284 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1148") | EBCDIC 1148 | Same as code page 500 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1364") | EBCDIC 1364 | Double-byte code page CCSID-1364, Korean.                                                                   |
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
index 5ff82c26a..3432da412 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
@@ -64,6 +64,7 @@ object CodePage extends Logging {
       case "cp1140"          => new CodePage1140
       case "cp1141"          => new CodePage1141
       case "cp1142"          => new CodePage1142
+      case "cp1143"          => new CodePage1143
       case "cp1145"          => new CodePage1145
       case "cp1146"          => new CodePage1146
       case "cp1148"          => new CodePage1148
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1143.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1143.scala
new file mode 100644
index 000000000..27b92ee29
--- /dev/null
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1143.scala
@@ -0,0 +1,57 @@
+/*
+ * Copyright 2018 ABSA Group Limited
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package za.co.absa.cobrix.cobol.parser.encoding.codepage
+
+/**
+  * EBCDIC code page 1143. Finland and Sweden.
+  *
+  * It corresponds to code page 278 and only differs from it in position 5A, where the euro sign € is located instead
+  * of the international currency symbol ¤.
+  */
+class CodePage1143 extends SingleByteCodePage(CodePage1143.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp1143"
+}
+
+object CodePage1143 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 1143 to ASCII conversion table
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_278 */
+    val ebcdic2ascii: Array[Char] = {
+      // Non-printable characters map used: http://www.pacsys.com/asciitab.htm
+      Array[Char](
+        c00, c01, c02, c03, spc, c09, spc, del, spc, spc, spc, c0b, c0c, ccr, c0e, c0f, //   0 -  15
+        c10, c11, c12, c13, spc, nel, c08, spc, c18, c19, spc, spc, c1c, c1d, c1e, c1f, //  16 -  31
+        spc, spc, spc, spc, spc, clf, c17, c1b, spc, spc, spc, spc, spc, c05, c06, c07, //  32 -  47
+        spc, spc, c16, spc, spc, spc, spc, c04, spc, spc, spc, spc, c14, c15, spc, c1a, //  48 -  63
+        ' ', rsp, 'â', '{', 'à', 'á', 'ã', '}', 'ç', 'ñ', '§', '.', '<', '(', '+', '!', //  64 -  79
+        '&', '`', 'ê', 'ë', 'è', 'í', 'î', 'ï', 'ì', 'ß', '€', 'Å', '*', ')', ';', '^', //  80 -  95
+        '-', '/', 'Â', '#', 'À', 'Á', 'Ã', '$', 'Ç', 'Ñ', 'ö', ',', '%', '_', '>', '?', //  96 - 111
+        'ø', bsh, 'Ê', 'Ë', 'È', 'Í', 'Î', 'Ï', 'Ì', 'é', ':', 'Ä', 'Ö', qts, '=', qtd, // 112 - 127
+        'Ø', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', '«', '»', 'ð', 'ý', 'þ', '±', // 128 - 143
+        '°', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'ª', 'º', 'æ', '¸', 'Æ', ']', // 144 - 159
+        'µ', 'ü', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '¡', '¿', 'Ð', 'Ý', 'Þ', '®', // 160 - 175
+        '¢', '£', '¥', '·', '©', '[', '¶', '¼', '½', '¾', '¬', '|', '¯', '¨', '´', '×', // 176 - 191
+        'ä', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', shy, 'ô', '¦', 'ò', 'ó', 'õ', // 192 - 207
+        'å', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', '¹', 'û', '~', 'ù', 'ú', 'ÿ', // 208 - 223
+        'É', '÷', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '²', 'Ô', '@', 'Ò', 'Ó', 'Õ', // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '³', 'Û', 'Ü', 'Ù', 'Ú', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
index c20a432f6..78023ba0f 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
@@ -307,6 +307,28 @@ class StringDecodersSpec extends AnyWordSpec {
         assert(actual == expected)
       }
 
+      "decode a CP1143 string example" in {
+        val expected = "â{àáã}çñ§.<(+!&`êëèíîïì߀Å*);^-/Â#ÀÁÃ$ÇÑö,%_>?ø\\ÊËÈÍÎÏÌé:ÄÖ'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ]µüstuvwxyz¡¿ÐÝÞ®¢£¥·©[¶¼½¾¬|¯¨´×äABCDEFGHI\u00ADô¦òóõåJKLMNOPQR¹û~ùúÿÉ÷STUVWXYZ²Ô@ÒÓÕ0123456789³ÛÜÙÚ"
+        val bytes = Array(
+          0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
+          0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
+          0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
+          0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
+          0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F,
+          0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9A, 0x9B, 0x9C, 0x9D, 0x9E, 0x9F,
+          0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF,
+          0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
+          0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
+          0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, 0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
+          0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
+          0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE
+        ).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage1143, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
+
       "decode a CP1145 string special characters" in {
         val expected = " äÑ|üܬ§ñ]ߢ[Ö{}æö¨å@ÆØÅÄÉ€ "
         val bytes = Array(0x40, 0x43, 0x7B, 0x4F, 0xDC, 0xFC, 0x5F, 0xB5, 0x6A, 0x5A, 0x59,
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
index ae93375f7..4b2aac2bb 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
@@ -137,6 +137,11 @@ class CodePageSingleByteSpec extends AnyFunSuite {
     assert(codePage.codePageShortName == "cp1142")
   }
 
+  test("Ensure codepage 'cp1143' gives the associated CodePage") {
+    val codePage = CodePage.getCodePageByName("cp1143")
+    assert(codePage.codePageShortName == "cp1143")
+  }
+
   test("Ensure codepage 'cp1145' gives the associated CodePage") {
     val codePage = CodePage.getCodePageByName("cp1145")
     assert(codePage.codePageShortName == "cp1145")

From e6907086e450e8e68a02f43f885d9e0b066f2ee5 Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Wed, 8 Jan 2025 09:45:10 +0100
Subject: [PATCH 5/8] Update scodec dependencies to latest versions.

---
 project/Dependencies.scala | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/project/Dependencies.scala b/project/Dependencies.scala
index cb7449204..17b4e8299 100644
--- a/project/Dependencies.scala
+++ b/project/Dependencies.scala
@@ -18,8 +18,7 @@ import sbt._
 
 object Dependencies {
   private val guavaVersion = "15.0"
-  private val scodecBitsVersion = "1.1.4"
-  private val scodecCoreVersion = "1.11.4"
+  private val scodecCoreVersion = "1.11.10"
   private val antlrValue = "4.8"
   private val slf4jVersion = "1.7.25"
   private val jacksonVersion = "2.13.0"

From 2f9309af59c7366a7408801d79da9778f7d2cc33 Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Tue, 14 Jan 2025 11:09:55 +0100
Subject: [PATCH 6/8] =?UTF-8?q?Add=20CP1144=20code=20page=20(Italy)=20whic?=
 =?UTF-8?q?h=20is=20same=20as=20CP280=20with=205A=20is=20replaced=20with?=
 =?UTF-8?q?=20the=20"=E2=82=AC"=20(euro)=20character.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                                     |  1 +
 .../parser/encoding/codepage/CodePage.scala   |  1 +
 .../encoding/codepage/CodePage1144.scala      | 57 +++++++++++++++++++
 .../parser/decoders/StringDecodersSpec.scala  | 22 +++++++
 .../codepage/CodePageSingleByteSpec.scala     |  5 ++
 .../cobol/source/index/IndexBuilder.scala     |  1 -
 6 files changed, 86 insertions(+), 1 deletion(-)
 create mode 100644 cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1144.scala

diff --git a/README.md b/README.md
index 3b02246fa..191132864 100644
--- a/README.md
+++ b/README.md
@@ -1644,6 +1644,7 @@ The output looks like this:
 | .option("ebcdic_code_page", "cp1141") | EBCDIC 1141 | Same as code page 273 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1142") | EBCDIC 1142 | Same as code page 277 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1143") | EBCDIC 1143 | Same as code page 278 with € at the position of the international currency symbol ¤.                        |
+| .option("ebcdic_code_page", "cp1144") | EBCDIC 1144 | Same as code page 280 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1145") | EBCDIC 1145 | Same as code page 284 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1148") | EBCDIC 1148 | Same as code page 500 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1364") | EBCDIC 1364 | Double-byte code page CCSID-1364, Korean.                                                                   |
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
index 3432da412..fbb0622c9 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
@@ -65,6 +65,7 @@ object CodePage extends Logging {
       case "cp1141"          => new CodePage1141
       case "cp1142"          => new CodePage1142
       case "cp1143"          => new CodePage1143
+      case "cp1144"          => new CodePage1144
       case "cp1145"          => new CodePage1145
       case "cp1146"          => new CodePage1146
       case "cp1148"          => new CodePage1148
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1144.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1144.scala
new file mode 100644
index 000000000..31de8e161
--- /dev/null
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1144.scala
@@ -0,0 +1,57 @@
+/*
+ * Copyright 2018 ABSA Group Limited
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package za.co.absa.cobrix.cobol.parser.encoding.codepage
+
+/**
+  * EBCDIC code page 1144. Italy.
+  *
+  * It corresponds to code page 280 and only differs from it in position 9F, where the euro sign € is located instead
+  * of the international currency symbol ¤.
+  */
+class CodePage1144 extends SingleByteCodePage(CodePage1144.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp1144"
+}
+
+object CodePage1144 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 1144 to ASCII conversion table
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_280 */
+    val ebcdic2ascii: Array[Char] = {
+      // Non-printable characters map used: http://www.pacsys.com/asciitab.htm
+      Array[Char](
+        c00, c01, c02, c03, spc, c09, spc, del, spc, spc, spc, c0b, c0c, ccr, c0e, c0f, //   0 -  15
+        c10, c11, c12, c13, spc, nel, c08, spc, c18, c19, spc, spc, c1c, c1d, c1e, c1f, //  16 -  31
+        spc, spc, spc, spc, spc, clf, c17, c1b, spc, spc, spc, spc, spc, c05, c06, c07, //  32 -  47
+        spc, spc, c16, spc, spc, spc, spc, c04, spc, spc, spc, spc, c14, c15, spc, c1a, //  48 -  63
+        ' ', rsp, 'â', 'ä', '{', 'á', 'ã', 'å', bsh, 'ñ', '°', '.', '<', '(', '+', '!', //  64 -  79
+        '&', ']', 'ê', 'ë', '}', 'í', 'î', 'ï', '~', 'ß', 'é', '$', '*', ')', ';', '^', //  80 -  95
+        '-', '/', 'Â', 'Ä', 'À', 'Á', 'Ã', 'Å', 'Ç', 'Ñ', 'ò', ',', '%', '_', '>', '?', //  96 - 111
+        'ø', 'É', 'Ê', 'Ë', 'È', 'Í', 'Î', 'Ï', 'Ì', 'ù', ':', '£', '§', qts, '=', qtd, // 112 - 127
+        'Ø', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', '«', '»', 'ð', 'ý', 'þ', '±', // 128 - 143
+        '[', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'ª', 'º', 'æ', '¸', 'Æ', '€', // 144 - 159
+        'µ', 'ì', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '¡', '¿', 'Ð', 'Ý', 'Þ', '®', // 160 - 175
+        '¢', '#', '¥', '·', '©', '@', '¶', '¼', '½', '¾', '¬', '|', '¯', '¨', '´', '×', // 176 - 191
+        'à', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', shy, 'ô', 'ö', '¦', 'ó', 'õ', // 192 - 207
+        'è', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', '¹', 'û', 'ü', '`', 'ú', 'ÿ', // 208 - 223
+        'ç', '÷', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '²', 'Ô', 'Ö', 'Ò', 'Ó', 'Õ', // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '³', 'Û', 'Ü', 'Ù', 'Ú', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
index 78023ba0f..449f52540 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
@@ -329,6 +329,28 @@ class StringDecodersSpec extends AnyWordSpec {
         assert(actual == expected)
       }
 
+      "decode a CP1144 string example" in {
+        val expected = "âä{áãå\\ñ°.<(+!&]êë}íîï~ßé$*);^-/ÂÄÀÁÃÅÇÑò,%_>?øÉÊËÈÍÎÏÌù:£§'=\"Øabcdefghi«»ðýþ±[jklmnopqrªºæ¸Æ€µìstuvwxyz¡¿ÐÝÞ®¢#¥·©@¶¼½¾¬|¯¨´×àABCDEFGHI\u00ADôö¦óõèJKLMNOPQR¹ûü`úÿç÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙÚ"
+        val bytes = Array(
+          0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
+          0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
+          0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
+          0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
+          0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F,
+          0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9A, 0x9B, 0x9C, 0x9D, 0x9E, 0x9F,
+          0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF,
+          0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
+          0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
+          0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7, 0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
+          0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7, 0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
+          0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE
+        ).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage1144, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
+
       "decode a CP1145 string special characters" in {
         val expected = " äÑ|üܬ§ñ]ߢ[Ö{}æö¨å@ÆØÅÄÉ€ "
         val bytes = Array(0x40, 0x43, 0x7B, 0x4F, 0xDC, 0xFC, 0x5F, 0xB5, 0x6A, 0x5A, 0x59,
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
index 4b2aac2bb..485b1a5c9 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
@@ -142,6 +142,11 @@ class CodePageSingleByteSpec extends AnyFunSuite {
     assert(codePage.codePageShortName == "cp1143")
   }
 
+  test("Ensure codepage 'cp1144' gives the associated CodePage") {
+    val codePage = CodePage.getCodePageByName("cp1144")
+    assert(codePage.codePageShortName == "cp1144")
+  }
+
   test("Ensure codepage 'cp1145' gives the associated CodePage") {
     val codePage = CodePage.getCodePageByName("cp1145")
     assert(codePage.codePageShortName == "cp1145")
diff --git a/spark-cobol/src/main/scala/za/co/absa/cobrix/spark/cobol/source/index/IndexBuilder.scala b/spark-cobol/src/main/scala/za/co/absa/cobrix/spark/cobol/source/index/IndexBuilder.scala
index 45667a7a5..413a0f359 100644
--- a/spark-cobol/src/main/scala/za/co/absa/cobrix/spark/cobol/source/index/IndexBuilder.scala
+++ b/spark-cobol/src/main/scala/za/co/absa/cobrix/spark/cobol/source/index/IndexBuilder.scala
@@ -56,7 +56,6 @@ private[source] object IndexBuilder extends Logging {
         buildIndexForVarLenReader(filesList, reader, sqlContext)
       case _                                                                                                                       =>
         buildIndexForFullFiles(filesList, sqlContext)
-      case _                                                                                                                       => null
     }
   }
 

From 42cdebb309b7837c9ca5ccb10fb9440544f6e672 Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Wed, 15 Jan 2025 16:03:46 +0100
Subject: [PATCH 7/8] =?UTF-8?q?Add=20CP1147=20code=20page=20(France)=20whi?=
 =?UTF-8?q?ch=20is=20same=20as=20CP297=20with=209F=20is=20replaced=20with?=
 =?UTF-8?q?=20the=20"=E2=82=AC"=20(euro)=20character.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                                     |  1 +
 .../parser/encoding/codepage/CodePage.scala   |  1 +
 .../encoding/codepage/CodePage1147.scala      | 55 +++++++++++++++++++
 .../parser/decoders/StringDecodersSpec.scala  | 11 ++++
 .../codepage/CodePageSingleByteSpec.scala     |  5 ++
 project/Dependencies.scala                    |  2 +-
 6 files changed, 74 insertions(+), 1 deletion(-)
 create mode 100644 cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1147.scala

diff --git a/README.md b/README.md
index 191132864..dc6da74ba 100644
--- a/README.md
+++ b/README.md
@@ -1646,6 +1646,7 @@ The output looks like this:
 | .option("ebcdic_code_page", "cp1143") | EBCDIC 1143 | Same as code page 278 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1144") | EBCDIC 1144 | Same as code page 280 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1145") | EBCDIC 1145 | Same as code page 284 with € at the position of the international currency symbol ¤.                        |
+| .option("ebcdic_code_page", "cp1147") | EBCDIC 1147 | Same as code page 297 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1148") | EBCDIC 1148 | Same as code page 500 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1364") | EBCDIC 1364 | Double-byte code page CCSID-1364, Korean.                                                                   |
 | .option("ebcdic_code_page", "cp1388") | EBCDIC 1388 | Double-byte code page CCSID-1388, Simplified Chinese.                                                       |
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
index fbb0622c9..043c61acf 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
@@ -68,6 +68,7 @@ object CodePage extends Logging {
       case "cp1144"          => new CodePage1144
       case "cp1145"          => new CodePage1145
       case "cp1146"          => new CodePage1146
+      case "cp1147"          => new CodePage1147
       case "cp1148"          => new CodePage1148
       case "cp1364"          => new CodePage1364
       case "cp1388"          => new CodePage1388
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1147.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1147.scala
new file mode 100644
index 000000000..3e3d33c0c
--- /dev/null
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1147.scala
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2018 ABSA Group Limited
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package za.co.absa.cobrix.cobol.parser.encoding.codepage
+
+/**
+  * EBCDIC code page 1147 of France is the same as 297.
+  * with € at the position of the international currency symbol ¤.
+  */
+class CodePage1147 extends SingleByteCodePage(CodePage1147.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp1147"
+}
+
+object CodePage1147 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 1147 to ASCII conversion table
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_297 */
+    val ebcdic2ascii: Array[Char] = {
+      // Non-printable characters map used: http://www.pacsys.com/asciitab.htm
+      Array[Char](
+        c00, c01, c02, c03, spc, c09, spc, del, spc, spc, spc, c0b, c0c, ccr, c0e, c0f, //   0 -  15
+        c10, c11, c12, c13, spc, nel, c08, spc, c18, c19, spc, spc, c1c, c1d, c1e, c1f, //  16 -  31
+        spc, spc, spc, spc, spc, clf, c17, c1b, spc, spc, spc, spc, spc, c05, c06, c07, //  32 -  47
+        spc, spc, c16, spc, spc, spc, spc, c04, spc, spc, spc, spc, c14, c15, spc, c1a, //  48 -  63
+        ' ', rsp, 'â', 'ä', '@', 'á', 'ã', 'å', bsh, 'ñ', '°', '.', '<', '(', '+', '!', //  64 -  79
+        '&', '{', 'ê', 'ë', '}', 'í', 'î', 'ï', 'ì', 'ß', '§', '$', '*', ')', ';', '^', //  80 -  95
+        '-', '/', 'Â', 'Ä', 'À', 'Á', 'Ã', 'Å', 'Ç', 'Ñ', 'ù', ',', '%', '_', '>', '?', //  96 - 111
+        'ø', 'É', 'Ê', 'Ë', 'È', 'Í', 'Î', 'Ï', 'Ì', 'µ', ':', '£', 'à', qts, '=', qtd, // 112 - 127
+        'Ø', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', '«', '»', 'ð', 'ý', 'þ', '±', // 128 - 143
+        '[', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'ª', 'º', 'æ', '¸', 'Æ', '€', // 144 - 159
+        '`', '¨', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '¡', '¿', 'Ð', 'Ý', 'Þ', '®', // 160 - 175
+        '¢', '#', '¥', '·', '©', ']', '¶', '¼', '½', '¾', '¬', '|', '¯', '~', '´', '×', // 176 - 191
+        'é', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', shy, 'ô', 'ö', 'ò', 'ó', 'õ', // 192 - 207
+        'è', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', '¹', 'û', 'ü', '¦', 'ú', 'ÿ', // 208 - 223
+        'ç', '÷', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '²', 'Ô', 'Ö', 'Ò', 'Ó', 'Õ', // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '³', 'Û', 'Ü', 'Ù', 'Ú', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
index 449f52540..87ef58abf 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
@@ -373,6 +373,17 @@ class StringDecodersSpec extends AnyWordSpec {
         assert(actual == expected)
       }
 
+      "decode a CP1147 string special characters" in {
+        val expected = " °$¨¢#¬¯ä£!üÜ^]ù§ß¢°Öéèæö¨åàÆØÅÄÉ€ "
+        val bytes = Array(0x40, 0x4A, 0x5B, 0xA1, 0xB0, 0xB1, 0xBA, 0xBC, 0x43, 0x7B, 0x4F, 0xDC, 0xFC, 0x5F, 0xB5, 0x6A, 0x5A, 0x59,
+          0xB0, 0x4A, 0xEC, 0xC0, 0xD0, 0x9C, 0xCC, 0xA1, 0x47, 0x7C, 0x9E, 0x80, 0x67, 0x63,
+          0x71, 0x9F, 0x40).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage1147, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
+
       "decode a CP1148 string special characters" in {
         val expected = "âäàáãåçñ[.<(+!&éêëèíîïìß]$*);^-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ€µ~stuvwxyz¡¿ÐÝÞ®¢£¥·©§¶¼½¾¬|¯¨´×{ABCDEFGHI\u00ADôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙÚ"
         val bytes = Array(
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
index 485b1a5c9..6368b075c 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
@@ -157,6 +157,11 @@ class CodePageSingleByteSpec extends AnyFunSuite {
     assert(codePage.codePageShortName == "cp1146")
   }
 
+  test("Ensure codepage 'cp1147' gives the associated CodePage") {
+    val codePage = CodePage.getCodePageByName("cp1147")
+    assert(codePage.codePageShortName == "cp1147")
+  }
+
   test("Ensure codepage 'cp1148' gives the associated CodePage") {
     val codePage = CodePage.getCodePageByName("cp1148")
     assert(codePage.codePageShortName == "cp1148")
diff --git a/project/Dependencies.scala b/project/Dependencies.scala
index 17b4e8299..85c18ffa1 100644
--- a/project/Dependencies.scala
+++ b/project/Dependencies.scala
@@ -18,7 +18,7 @@ import sbt._
 
 object Dependencies {
   private val guavaVersion = "15.0"
-  private val scodecCoreVersion = "1.11.10"
+  private val scodecCoreVersion = "1.11.4"
   private val antlrValue = "4.8"
   private val slf4jVersion = "1.7.25"
   private val jacksonVersion = "2.13.0"

From bee7dfbe5b680dc3f0fa09ab9202c3c95bb0785a Mon Sep 17 00:00:00 2001
From: Ruslan Iushchenko <yruslan@gmail.com>
Date: Thu, 16 Jan 2025 14:11:47 +0100
Subject: [PATCH 8/8] =?UTF-8?q?Add=20CP1160=20code=20page=20(Thai)=20which?=
 =?UTF-8?q?=20is=20same=20as=20CP838=20with=20FE=20is=20replaced=20with=20?=
 =?UTF-8?q?the=20"=E2=82=AC"=20(euro)=20character.?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 README.md                                     |  1 +
 .../parser/encoding/codepage/CodePage.scala   |  1 +
 .../encoding/codepage/CodePage1160.scala      | 72 +++++++++++++++++++
 .../encoding/codepage/CodePage838.scala       |  8 +--
 .../parser/decoders/StringDecodersSpec.scala  | 20 ++++++
 .../codepage/CodePageSingleByteSpec.scala     |  5 ++
 6 files changed, 101 insertions(+), 6 deletions(-)
 create mode 100644 cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1160.scala

diff --git a/README.md b/README.md
index dc6da74ba..5294ca2a4 100644
--- a/README.md
+++ b/README.md
@@ -1648,6 +1648,7 @@ The output looks like this:
 | .option("ebcdic_code_page", "cp1145") | EBCDIC 1145 | Same as code page 284 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1147") | EBCDIC 1147 | Same as code page 297 with € at the position of the international currency symbol ¤.                        |
 | .option("ebcdic_code_page", "cp1148") | EBCDIC 1148 | Same as code page 500 with € at the position of the international currency symbol ¤.                        |
+| .option("ebcdic_code_page", "cp1160") | EBCDIC 1160 | Same as code page 838 with € at the position 0xFE.                                                          |
 | .option("ebcdic_code_page", "cp1364") | EBCDIC 1364 | Double-byte code page CCSID-1364, Korean.                                                                   |
 | .option("ebcdic_code_page", "cp1388") | EBCDIC 1388 | Double-byte code page CCSID-1388, Simplified Chinese.                                                       |
 
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
index 043c61acf..0e4a65892 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala
@@ -70,6 +70,7 @@ object CodePage extends Logging {
       case "cp1146"          => new CodePage1146
       case "cp1147"          => new CodePage1147
       case "cp1148"          => new CodePage1148
+      case "cp1160"          => new CodePage1160
       case "cp1364"          => new CodePage1364
       case "cp1388"          => new CodePage1388
       case codePage          => throw new IllegalArgumentException(s"The code page '$codePage' is not one of the builtin EBCDIC code pages.")
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1160.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1160.scala
new file mode 100644
index 000000000..19e38cd14
--- /dev/null
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage1160.scala
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2018 ABSA Group Limited
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package za.co.absa.cobrix.cobol.parser.encoding.codepage
+
+/**
+  * EBCDIC code page 1160 with support for Thai script used in IBM mainframes which is same as 838
+  * with € at the position 0xFE.
+  */
+class CodePage1160 extends SingleByteCodePage(CodePage1160.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp1160"
+}
+
+object CodePage1160 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 1160 to ASCII conversion table
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_838 */
+    val ebcdic2ascii: Array[Char] = {
+      val c01 = '\u0E48'
+      val c02 = '\u0E4E'
+      val c03 = '\u0E31'
+      val c04 = '\u0E34'
+      val c05 = '\u0E49'
+      val c06 = '\u0E35'
+      val c07 = '\u0E36'
+      val c08 = '\u0E37'
+      val c09 = '\u0E38'
+      val c10 = '\u0E39'
+      val c11 = '\u0E3A'
+      val c12 = '\u0E47'
+      val c13 = '\u0E48'
+      val c14 = '\u0E49'
+      val c15 = '\u0E4A'
+      val c16 = '\u0E4B'
+      val c18 = '\u0E4D'
+
+      Array[Char](
+        spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, ccr, spc, spc, //   0 -  15
+        spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, //  16 -  31
+        spc, spc, spc, spc, spc, clf, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, //  32 -  47
+        spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, spc, //  48 -  63
+        spc, spc, 'ก', 'ข', 'ฃ', 'ค', 'ฅ', 'ฆ', 'ง', '[', '¢', '.', '<', '(', '+', '|', //  64 -  79
+        '&', c01, 'จ', 'ฉ', 'ช', 'ซ', 'ฌ', 'ญ', 'ฎ', ']', '!', '$', '*', ')', ';', '¬', //  80 -  95
+        '-', '/', 'ฏ', 'ฐ', 'ฑ', 'ฒ', 'ณ', 'ด', 'ต', '^', '¦', ',', '%', '_', '>', '?', //  96 - 111
+        '฿', c02, 'ถ', 'ท', 'ธ', 'น', 'บ', 'ป', 'ผ', '`', ':', '#', '@', qts, '=', qtd, // 112 - 127
+        '๏', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'ฝ', 'พ', 'ฟ', 'ภ', 'ม', 'ย', // 128 - 143
+        '๚', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 'ร', 'ฤ', 'ล', 'ฦ', 'ว', 'ศ', // 144 - 159
+        '๛', '~', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', 'ษ', 'ส', 'ห', 'ฬ', 'อ', 'ฮ', // 160 - 175
+        '๐', '๑', '๒', '๓', '๔', '๕', '๖', '๗', '๘', '๙', 'ฯ', 'ะ', c03, 'า', 'ำ', c04, // 176 - 191
+        '{', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', c05, c06, c07, c08, c09, c10, // 192 - 207
+        '}', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', c11, 'เ', 'แ', 'โ', 'ใ', 'ไ', // 208 - 223
+        bsh, c15, 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'ๅ', 'ๆ', c12, c13, c14, c15, // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', c16, c17, c18, c16, '€', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}
diff --git a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage838.scala b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage838.scala
index e06524325..9bfd5cfb3 100644
--- a/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage838.scala
+++ b/cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage838.scala
@@ -25,15 +25,11 @@ class CodePage838 extends SingleByteCodePage(CodePage838.ebcdicToAsciiMapping) {
 
 object CodePage838 {
   val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
     /* This is the EBCDIC Code Page 838 to ASCII conversion table with non-printable characters mapping
        from https://en.everybodywiki.com/EBCDIC_838 */
     val ebcdic2ascii: Array[Char] = {
-      val clf = '\r'
-      val ccr = '\n'
-      val spc = ' '
-      val qts = '\''
-      val qtd = '\"'
-      val bsh = '\\'
       val c01 = '\u0E48'
       val c02 = '\u0E4E'
       val c03 = '\u0E31'
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
index 87ef58abf..613b12de4 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/decoders/StringDecodersSpec.scala
@@ -241,6 +241,16 @@ class StringDecodersSpec extends AnyWordSpec {
         assert(actual == expected)
       }
 
+      "decode a CP838 string special characters" in {
+        val expected = " ¢$~๐๑ฯัข#|แํ¬๕¦!]๐¢็{}ลึ~ฆ@ว๏ดฐ "
+        val bytes = Array(0x40, 0x4A, 0x5B, 0xA1, 0xB0, 0xB1, 0xBA, 0xBC, 0x43, 0x7B, 0x4F, 0xDC, 0xFC, 0x5F, 0xB5, 0x6A, 0x5A, 0x59,
+          0xB0, 0x4A, 0xEC, 0xC0, 0xD0, 0x9C, 0xCC, 0xA1, 0x47, 0x7C, 0x9E, 0x80, 0x67, 0x63, 0x40).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage838, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
+
       "decode a CP1140 string special characters" in {
         val expected = "âäàáãåçñ¢.<(+|&éêëèíîïìß!$*);¬-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ€µ~stuvwxyz¡¿ÐÝÞ®^£¥·©§¶¼½¾[]¯¨´×{ABCDEFGHI\u00ADôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙÚ"
         val bytes = Array(
@@ -405,6 +415,16 @@ class StringDecodersSpec extends AnyWordSpec {
 
         assert(actual == expected)
       }
+
+      "decode a CP1160 string special characters" in {
+        val expected = " ¢$~๐๑ฯัข#|แํ¬๕¦!]๐¢็{}ลึ~ฆ@ว๏ดฐ€ "
+        val bytes = Array(0x40, 0x4A, 0x5B, 0xA1, 0xB0, 0xB1, 0xBA, 0xBC, 0x43, 0x7B, 0x4F, 0xDC, 0xFC, 0x5F, 0xB5, 0x6A, 0x5A, 0x59,
+          0xB0, 0x4A, 0xEC, 0xC0, 0xD0, 0x9C, 0xCC, 0xA1, 0x47, 0x7C, 0x9E, 0x80, 0x67, 0x63, 0xFE, 0x40).map(_.toByte)
+
+        val actual = decodeEbcdicString(bytes, KeepAll, new CodePage1160, improvedNullDetection = false)
+
+        assert(actual == expected)
+      }
     }
   }
 
diff --git a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
index 6368b075c..b637ee4f2 100644
--- a/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
+++ b/cobol-parser/src/test/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePageSingleByteSpec.scala
@@ -167,6 +167,11 @@ class CodePageSingleByteSpec extends AnyFunSuite {
     assert(codePage.codePageShortName == "cp1148")
   }
 
+  test("Ensure codepage 'cp1160' gives the associated CodePage") {
+    val codePage = CodePage.getCodePageByName("cp1160")
+    assert(codePage.codePageShortName == "cp1160")
+  }
+
   test("Ensure codepage 'cp1364' gives the associated CodePage") {
     val codePage = CodePage.getCodePageByName("cp1364")
     assert(codePage.codePageShortName == "cp1364")