Add more EBCDIC code pages (mostly European)

README.md

@@ -1626,8 +1626,13 @@ 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", "cp275")  | EBCDIC 275  | Brazil.                                                                                                     |
 | .option("ebcdic_code_page", "cp277")  | EBCDIC 277  | Denmark and Norway.                                                                                         |
 | .option("ebcdic_code_page", "cp278")  | EBCDIC 278  | Finland and Sweden.                                                                                         |
+| .option("ebcdic_code_page", "cp280")  | EBCDIC 280  | Italy.                                                                                                      |
+| .option("ebcdic_code_page", "cp284")  | EBCDIC 284  | Spain and Latin America.                                                                                    |
+| .option("ebcdic_code_page", "cp285")  | EBCDIC 285  | United Kingdom.                                                                                             |
+| .option("ebcdic_code_page", "cp297")  | EBCDIC 297  | France.                                                                                                     |
 | .option("ebcdic_code_page", "cp300")  | EBCDIC 300  | Double-byte code page with Japanese and Latin characters.                                                   |
 | .option("ebcdic_code_page", "cp500")  | EBCDIC 500  | Belgium, Canada, Switzerland, International.                                                                |
 | .option("ebcdic_code_page", "cp838")  | EBCDIC 838  | Double-byte code page with Thai and Latin characters.                                                       |

cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage.scala

@@ -46,8 +46,13 @@ object CodePage extends Logging {
       case "cp037_extended"  => new CodePage037Ext
       case "cp00300"         => new CodePage300 // This is the same as cp300
       case "cp273"           => new CodePage273
+      case "cp275"           => new CodePage275
       case "cp277"           => new CodePage277
       case "cp278"           => new CodePage278
+      case "cp280"           => new CodePage280
+      case "cp284"           => new CodePage284
+      case "cp285"           => new CodePage285
+      case "cp297"           => new CodePage297
       case "cp300"           => new CodePage300
       case "cp500"           => new CodePage500
       case "cp838"           => new CodePage838

cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage275.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 277 is used to represent characters of Brazil.
+  */
+class CodePage275 extends SingleByteCodePage(CodePage275.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp275"
+}
+
+object CodePage275 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 275 to ASCII conversion table
+       from https://en.wikibooks.org/wiki/Character_Encodings/Code_Tables/EBCDIC/EBCDIC_275 */
+    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', '`', 'å', '¦', 'ñ', 'É', '.', '<', '(', '+', '!', //  64 -  79
+        '&', '}', 'ê', 'ë', 'è', 'í', 'î', 'ï', 'ì', 'ß', '$', 'Ç', '*', ')', ';', '^', //  80 -  95
+        '-', '/', 'Â', 'Ä', 'À', 'Á', '@', 'Å', ']', 'Ñ', 'ç', ',', '%', '_', '>', '?', //  96 - 111
+        'ø', '[', 'Ê', 'Ë', 'È', 'Í', 'Î', 'Ï', 'Ì', 'ã', ':', 'Õ', 'Ã', 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
+        'õ', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', shy, 'ô', 'ö', 'ò', 'ó', '{', // 192 - 207
+        'é', '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', '#', // 224 - 239
+        '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '³', 'Û', 'Ü', 'Ù', 'Ú', spc) // 240 - 255
+    }
+    ebcdic2ascii
+  }
+}

cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage280.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 280 is used to represent characters of Italy.
+  */
+class CodePage280 extends SingleByteCodePage(CodePage280.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp280"
+}
+
+object CodePage280 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 280 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
+  }
+}

cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage284.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 284 is used to represent characters of Spain and Latin America.
+  */
+class CodePage284 extends SingleByteCodePage(CodePage284.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp284"
+}
+
+object CodePage284 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 284 to ASCII conversion table
+       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
+      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', '¦', '[', '.', '<', '(', '+', '|', //  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', '`', ':', 'Ñ', '@', 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
+  }
+}

cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage285.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 285 is used to represent characters of the United Kingdom.
+  */
+class CodePage285 extends SingleByteCodePage(CodePage285.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp285"
+}
+
+object CodePage285 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 285 to ASCII conversion table
+       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
+  }
+}

cobol-parser/src/main/scala/za/co/absa/cobrix/cobol/parser/encoding/codepage/CodePage297.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 285 is used to represent characters of France.
+  */
+class CodePage297 extends SingleByteCodePage(CodePage297.ebcdicToAsciiMapping) {
+  override def codePageShortName: String = "cp297"
+}
+
+object CodePage297 {
+  val ebcdicToAsciiMapping: Array[Char] = {
+    import EbcdicNonPrintable._
+
+    /* This is the EBCDIC Code Page 297 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
+  }
+}