Merge pull request #23 from openmainframeproject/release-5.0.1

Release 5.0.1

Author: alexgubanow

.gitignore

@@ -109,4 +109,11 @@ buildNumber.properties
 .mvn/wrapper/maven-wrapper.jar
 .flattened-pom.xml
 
-# End of https://www.gitignore.io/api/java,maven,eclipse
+# End of https://www.gitignore.io/api/java,maven,eclipse
+
+.vscode
+
+cpp/obj
+cpp/bin
+.vs
+/cpp/packages

README.md

@@ -15,6 +15,13 @@ IBM Mainframe files on any workstation or laptop etc. that supports Java.
 
 ## Updates ##
 
+**Version 5.0.1: July 2023 -- September 2025**
+
+- Updated pom.xml to have Maven compile using Java 21
+- Allow user to specify only <input file> for text files. Resulting <output file> will be <input file>.txt
+- Added C++ port
+- Added commit id to the version
+
 **Version 5: March 2021**
 
 - Support for variable length binary records. Variable length records processed in binary mode will be prefixed with a 4 byte field in the same format as the IBM RDW i.e. 2 byte record length field (including RDW length, big-endian) followed by 2 bytes of zeros.
@@ -25,7 +32,7 @@ For execution, TerseDecompress needs a JVM runtime environment.
 
 Usage:
 
-```java -jar tersedecompress-5.0.0.jar [-b] tersed-file output-file```
+```java -jar tersedecompress.jar [-b] tersed-file output-file```
 
 Default mode is text mode, which will attempt EBCDIC -> ASCII conversion.
 

cpp/.clang-format

@@ -0,0 +1,22 @@
+---
+BasedOnStyle: Microsoft
+AlignEscapedNewlines: Left
+AllowShortFunctionsOnASingleLine: All
+AlwaysBreakAfterReturnType: None
+AlwaysBreakTemplateDeclarations: 'Yes'
+ColumnLimit: '125'
+IndentCaseLabels: 'true'
+IndentPPDirectives: BeforeHash
+IndentWidth: '2'
+Language: Cpp
+MaxEmptyLinesToKeep: '1'
+NamespaceIndentation: All
+PenaltyBreakAssignment: '50'
+SortUsingDeclarations: 'true'
+SpaceBeforeCtorInitializerColon: 'false'
+SpaceBeforeInheritanceColon: 'false'
+SpacesInAngles: 'true'
+TabWidth: '2'
+UseTab: Never
+
+...

cpp/Makefile

@@ -0,0 +1,24 @@
+.SECONDARY:
+.SUFIXES:
+.PHONY: all src tests clean
+
+UNAME:=$(shell uname)
+
+ifneq ($(filter $(UNAME),Linux Darwin),)
+MAKE_FLAGS := -j8
+endif
+
+default: all
+
+src:
+	$(MAKE) $(MAKE_FLAGS) -C src
+tests: src
+	$(MAKE) $(MAKE_FLAGS) -C tests
+check: tests
+	$(MAKE) $(MAKE_FLAGS) -C tests check
+
+all: src
+
+clean:
+	$(MAKE) $(MAKE_FLAGS) -C src clean
+	$(MAKE) $(MAKE_FLAGS) -C tests clean

cpp/envdef.mak

@@ -0,0 +1,28 @@
+ROOT_DIR:=$(dir $(abspath $(lastword $(MAKEFILE_LIST))))
+OBJ_DIR:=$(ROOT_DIR)obj
+BIN_DIR:=$(ROOT_DIR)bin
+
+UNAME:=$(shell uname)
+PREFIX?=$(HOME)/local
+CXXFLAGS = -std=c++17 -O2
+CCFLAGS_DLL += -fPIC -fvisibility=default
+AR=ar
+
+ifneq ($(filter $(UNAME),Linux Darwin),)
+INSTALL_CMD:=install -m 644
+INSTALL_CMD_BIN:=install -m 755
+CC:=clang
+CXX:=clang++
+LD:=clang++
+else
+INSTALL_CMD:=cp
+INSTALL_CMD_BIN:=cp
+CC:=ibm-clang
+CXX:=ibm-clang++
+LD:=ibm-clang++
+CXXFLAGS +=-m64 -mzos-float-kind=ieee -D_UNIX03_SOURCE -D_UNIX03_THREADS -D_POSIX_SOURCE -D_POSIX_THREADS \
+	-D_OPEN_SYS_SOCK_IPV6=1 -D_XOPEN_SOURCE_EXTENDED=1 -DOE_SOCKETS -D_OPEN_SYS_IF_EXT=1
+LDFLAGS +=-m64
+endif
+
+GIT_TAG := $(shell git rev-parse --short HEAD)

cpp/src/Constants.h

@@ -0,0 +1,34 @@
+#ifndef TERSE_CONSTANTS_H
+#define TERSE_CONSTANTS_H
+
+#include <array>
+#include <cstdint>
+
+namespace Tersedecompress
+{
+  static constexpr int BUFFERSIZE = 0x07FF; // 2047 (not directly used in our code)
+  static constexpr int HASHSIZE = 0x0FFF;   // 4095 (not directly used in decode)
+  static constexpr int TREESIZE = 0x1000;   // 4096
+  static constexpr int RECORDMARK = 257;    // used in putChar logic
+  static constexpr char ENDOFFILE = 0;      // used to indicate EOF in blockReader
+  static constexpr int BASE = 0;
+  static constexpr int CODESIZE = 257; // 256 codepoints + EOF/recordmark
+
+  static constexpr std::array< int, 256 > EbcToAsc = {
+      0x00, 0x01, 0x02, 0x03, 0xCF, 0x09, 0xD3, 0x7F, 0xD4, 0xD5, 0xC3, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13,
+      0xC7, 0xB4, 0x08, 0xC9, 0x18, 0x19, 0xCC, 0xCD, 0x83, 0x1D, 0xD2, 0x1F, 0x81, 0x82, 0x1C, 0x84, 0x86, 0x0A, 0x17, 0x1B,
+      0x89, 0x91, 0x92, 0x95, 0xA2, 0x05, 0x06, 0x07, 0xE0, 0xEE, 0x16, 0xE5, 0xD0, 0x1E, 0xEA, 0x04, 0x8A, 0xF6, 0xC6, 0xC2,
+      0x14, 0x15, 0xC1, 0x1A, 0x20, 0xA6, 0xE1, 0x80, 0xEB, 0x90, 0x9F, 0xE2, 0xAB, 0x8B, 0x9B, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
+      0x26, 0xA9, 0xAA, 0x9C, 0xDB, 0xA5, 0x99, 0xE3, 0xA8, 0x9E, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E, 0x2D, 0x2F, 0xDF, 0xDC,
+      0x9A, 0xDD, 0xDE, 0x98, 0x9D, 0xAC, 0xBA, 0x2C, 0x25, 0x5F, 0x3E, 0x3F, 0xD7, 0x88, 0x94, 0xB0, 0xB1, 0xB2, 0xFC, 0xD6,
+      0xFB, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22, 0xF8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x96, 0xA4,
+      0xF3, 0xAF, 0xAE, 0xC5, 0x8C, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71, 0x72, 0x97, 0x87, 0xCE, 0x93, 0xF1, 0xFE,
+      0xC8, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0xEF, 0xC0, 0xDA, 0x5B, 0xF2, 0xF9, 0xB5, 0xB6, 0xFD, 0xB7,
+      0xB8, 0xB9, 0xE6, 0xBB, 0xBC, 0xBD, 0x8D, 0xD9, 0xBF, 0x5D, 0xD8, 0xC4, 0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+      0x48, 0x49, 0xCB, 0xCA, 0xBE, 0xE8, 0xEC, 0xED, 0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51, 0x52, 0xA1, 0xAD,
+      0xF5, 0xF4, 0xA3, 0x8F, 0x5C, 0xE7, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0xA0, 0x85, 0x8E, 0xE9, 0xE4, 0xD1,
+      0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0xB3, 0xF7, 0xF0, 0xFA, 0xA7, 0xFF};
+
+} // namespace Tersedecompress
+
+#endif // TERSE_CONSTANTS_H

cpp/src/Makefile

@@ -0,0 +1,45 @@
+.SECONDARY:
+.SUFIXES:
+.PHONY: all clean
+default: all
+
+include ../envdef.mak
+
+OBJ_LIB_DIR=$(OBJ_DIR)/lib
+LIBTERSEDECOMPRESS = $(BIN_DIR)/libtersedecompress.a
+TERSEDECOMPRESS = $(BIN_DIR)/tersedecompress++
+SRC_LIB=\
+NonSpackDecompresser.cpp \
+SpackDecompresser.cpp \
+TerseBlockReader.cpp \
+TerseDecompresser.cpp \
+TerseHeader.cpp
+SRC_APP=\
+main.cpp \
+argumentParser.cpp
+
+OBJS_LIB += $(addprefix $(OBJ_LIB_DIR)/, $(addsuffix .o, $(basename $(SRC_LIB))))
+OBJS += $(addprefix $(OBJ_DIR)/, $(addsuffix .o, $(basename $(SRC_APP))))
+DEPS += $(addsuffix .d, $(basename $(OBJS)))
+
+$(OBJ_DIR)/%.o: %.cpp | $(OBJ_DIR)
+	$(CXX) $(CXXFLAGS) -DGIT_TAG=\"$(GIT_TAG)\" -MMD -MF $(OBJ_DIR)/$*.d -MP -c $< -o $@
+
+$(OBJ_LIB_DIR)/%.o: %.cpp | $(OBJ_DIR) $(OBJ_LIB_DIR)
+	$(CXX) $(CXXFLAGS) $(CCFLAGS_DLL) -MMD -MF $(OBJ_LIB_DIR)/$*.d -MP -c $< -o $@
+
+$(LIBTERSEDECOMPRESS): $(OBJS_LIB) | $(BIN_DIR)
+	$(AR) rcs $(LIBTERSEDECOMPRESS) $(OBJS_LIB)
+
+$(TERSEDECOMPRESS): $(OBJS) $(LIBTERSEDECOMPRESS) | $(BIN_DIR)
+	$(LD) $(LDFLAGS) -L$(BIN_DIR) -o $(TERSEDECOMPRESS) $(OBJS) -ltersedecompress
+
+$(OBJ_DIR) $(OBJ_LIB_DIR) $(BIN_DIR):
+	-mkdir -p $@
+
+all: $(TERSEDECOMPRESS)
+
+clean:
+	rm -rf $(OBJ_DIR) $(OBJS_LIB) $(BIN_DIR) $(OBJS) $(DEPS) $(LIBTERSEDECOMPRESS) $(TERSEDECOMPRESS)
+
+-include $(OBJS:%.o=%.d)

cpp/src/NonSpackDecompresser.cpp

@@ -0,0 +1,100 @@
+#include "NonSpackDecompresser.h"
+#include "Constants.h"
+
+#include <stdexcept>
+#include <vector>
+
+NonSpackDecompresser::NonSpackDecompresser(std::istream &in, std::ostream &out, std::unique_ptr< TerseBlockReader > reader,
+                                           const TerseHeader &header)
+    : TerseDecompresser(in, out)
+{
+  blockReader_ = std::move(reader);
+  hostFlag_ = header.hostFlag;
+  variableFlag_ = header.recfmV;
+  recordLength_ = header.recordLength;
+}
+
+void NonSpackDecompresser::decode()
+{
+  std::vector< int > Father(Tersedecompress::TREESIZE, 0);
+  std::vector< int > CharExt(Tersedecompress::TREESIZE, 0);
+  std::vector< int > Backward(Tersedecompress::TREESIZE, 0);
+  std::vector< int > Forward(Tersedecompress::TREESIZE, 0);
+
+  int H1 = 0, H2 = 0;
+  int x = 0, d = 0, y = 0;
+  int q = 0, r = 0, e = 0, p = 0, h = 0;
+
+  H2 = 65;
+
+  for (H1 = 258; H1 < Tersedecompress::TREESIZE; ++H1)
+  {
+    Father[H1] = H2;
+    CharExt[H1] = 65;
+    H2 = H1;
+  }
+
+  for (H1 = 258; H1 < (Tersedecompress::TREESIZE - 1); ++H1)
+  {
+    Backward[H1 + 1] = H1;
+    Forward[H1] = H1 + 1;
+  }
+
+  Backward[0] = Tersedecompress::TREESIZE - 1;
+  Forward[0] = 258;
+  Backward[258] = 0;
+  Forward[Tersedecompress::TREESIZE - 1] = 0;
+
+  x = 0;
+  d = blockReader_->getBlok();
+
+  while (d != Tersedecompress::ENDOFFILE)
+  {
+    h = 0;
+    y = Backward[0];
+    q = Backward[y];
+    Backward[0] = q;
+    Forward[q] = 0;
+    h = y;
+    p = 0;
+
+    while (d > 257)
+    {
+      q = Forward[d];
+      r = Backward[d];
+      Forward[r] = q;
+      Backward[q] = r;
+      Forward[d] = h;
+      Backward[h] = d;
+      h = d;
+      e = Father[d];
+      Father[d] = p;
+      p = d;
+      d = e;
+    }
+
+    q = Forward[0];
+    Forward[y] = q;
+    Backward[q] = y;
+    Forward[0] = h;
+    Backward[h] = 0;
+
+    CharExt[x] = d;
+    putChar(d);
+
+    x = y;
+
+    while (p != 0)
+    {
+      e = Father[p];
+      putChar(CharExt[p]);
+      Father[p] = d;
+      d = p;
+      p = e;
+    }
+
+    Father[y] = d;
+    d = blockReader_->getBlok();
+  }
+  close();
+}

cpp/src/NonSpackDecompresser.h

@@ -0,0 +1,17 @@
+#ifndef NONSPACKDECOMPRESSER_H
+#define NONSPACKDECOMPRESSER_H
+
+#include "TerseBlockReader.h"
+#include "TerseDecompresser.h"
+#include "TerseHeader.h"
+#include <memory>
+
+class NonSpackDecompresser: public TerseDecompresser
+{
+public:
+  NonSpackDecompresser(std::istream &in, std::ostream &out, std::unique_ptr< TerseBlockReader > reader,
+                       const TerseHeader &header);
+  void decode() override;
+};
+
+#endif // NONSPACKDECOMPRESSER_H