Merge pull request #1 from RyogaMasaki/rewrite

Rewrite

.clang-format

@@ -0,0 +1,12 @@
+Language: Cpp
+Standard: Cpp11
+BasedOnStyle: LLVM
+BreakBeforeBraces: Linux
+SpaceBeforeParens: Never
+TabWidth: 2
+UseTab: Always
+AlignTrailingComments: true
+AllowShortIfStatementsOnASingleLine: false
+IndentCaseLabels: true
+
+Cpp11BracedListStyle: true

.gitignore

@@ -2,4 +2,4 @@
 *.code-workspace
 bin
 build
-
+etc

CMakeLists.txt

@@ -0,0 +1,27 @@
+INCLUDE (CheckIncludeFiles)
+
+# define project
+cmake_minimum_required (VERSION 3.5)
+project (jstrings VERSION 1.1 LANGUAGES CXX)
+
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_CXX_COMPILER_NAMES clang++ g++ icpc c++ cxx)
+# set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${PROJECT_SOURCE_DIR}/bin)
+set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DDEBUG")
+
+if (NOT EXISTS ${CMAKE_BINARY_DIR}/CMakeCache.txt)
+  if (NOT CMAKE_BUILD_TYPE)
+    set(CMAKE_BUILD_TYPE "Release" CACHE STRING "" FORCE)
+  endif()
+endif()
+
+# define target
+aux_source_directory(${PROJECT_SOURCE_DIR}/src CPPFILES)
+add_executable(jstrings ${CPPFILES}) 
+
+target_include_directories(jstrings PUBLIC "${PROJECT_SOURCE_DIR}/inc")
+target_compile_features(jstrings PUBLIC cxx_std_11)
+target_link_libraries(jstrings png)
+
+install(TARGETS jstrings
+        RUNTIME DESTINATION bin)

README.md

@@ -1,35 +1,47 @@
 # jstrings
-A tool for finding JIS-based Japanese characters in binary data.
+A tool for finding JIS-based Japanese text in binary data.
 
 ## Usage
-	jstrings [options] [input]
+	jstrings [options] [input_file]
 
-Input can be a filename or data from stdin.
+Input can be a filename or data from stdin. Output is sent to stdout.
 
 ### Options
-	-m number
+	-e encoding
+	--encoding encoding
 
-Set minimum number of characters to match as a valid string. Default: 10.
+Specify the encoding to use. Use one of the strings listed in parantheses below for that encoding:
 
-	-e encoding
+* Shift-JIS (shift-jis, shiftjis, sjis)
+* EUC-JP (euc, euc-jp, eucjp)
+* Microsoft CP932 (cp932, windows932, windows31j)
 
-Specify the encoding to use. Currently, the only valid value is "shift-jis". Default: shift-jis
+Optional; default is Shift-JIS.
 
-	-l
+	-m number
+	--match-length number
 
-Use little-endian order for multibyte characters
+Set minimum number of characters to match as a valid string. Optional; default is 10.
 
-	-jisx0213
+	-c number
+	--cutoff number
 
-Use JIS X 0213 character set instead of JIS X 0208 for double byte characters
+Limit the output to the specified number of characters for a string. This is useful for "previewing" a file which may have large blocks of junk data that happen to fall within the range of valid encoding values. Optional; default is no cutoff.
 
-## Notes
+## Output
 Data is output in its original encoding without any conversion. Other tools, such as iconv, can do conversion to something more useful (such as UTF8). For example:
 
-	jstrings file.bin | iconv -f SHIFT-JIS -t UTF-8 -c
+	# for Shift-JIS
+	jstrings file.bin | iconv -f SHIFT-JIS -t UTF-8 -c | less
+	# for CP932
+	jstrings file.bin | iconv -f CP932 -t UTF-8 -c | less
+	# for EUC-JP
+	jstrings file.bin | iconv -f EUC-JP -t UTF-8 -c | less
 
-### To Do
-- Add support for other JIS encodings: CP932, EUC
-- Add support for JIS X 0212 for non-SJIS encodings (only EUC?)
-- Add option to only return strings with double-byte characters present
+## Building
+CMake is used for the build system. From the root directory:
 
+	mkdir build && cd build
+	cmake ..
+	make
+	sudo make install

inc/enc_cp932.h

@@ -0,0 +1,24 @@
+/*!
+ * \author Damian Rogers ([email protected])
+ * \version 1.1
+ * \date 2019.12.01
+ * \copyright MIT License
+ */
+
+#ifndef ENC_CP932_H
+#define ENC_CP932_H
+
+#include "enc_shiftjis.h"
+
+namespace encodings
+{
+
+class cp932 : public shift_jis
+{
+public:
+	u8 is_valid(u8 const *data);
+};
+
+} // namespace encodings
+
+#endif

inc/enc_eucjp.h

@@ -0,0 +1,22 @@
+/*!
+ * \author Damian Rogers ([email protected])
+ * \version 1.1
+ * \date 2019.12.01
+ * \copyright MIT License
+ */
+#ifndef ENC_EUCJP_H
+#define ENC_EUCJP_H
+#include "encoding.h"
+
+namespace encodings
+{
+
+class euc : public encoding
+{
+public:
+	euc() : encoding(3){};
+	u8 is_valid(u8 const *data);
+};
+
+} // namespace encodings
+#endif // ENC_EUC_H

inc/enc_shiftjis.h

@@ -0,0 +1,23 @@
+/*!
+ * \author Damian Rogers ([email protected])
+ * \version 1.1
+ * \date 2019.12.01
+ * \copyright MIT License
+ */
+
+#ifndef ENC_SHIFTJIS_H
+#define ENC_SHIFTJIS_H
+#include "encoding.h"
+
+namespace encodings
+{
+
+class shift_jis : public encoding
+{
+public:
+	shift_jis() : encoding(2){};
+	u8 is_valid(u8 const *data);
+};
+
+} // namespace encodings
+#endif // ENC_SHIFTJIS_H

inc/encoding.h

@@ -0,0 +1,32 @@
+/*!
+ * \author Damian Rogers ([email protected])
+ * \version 1.1
+ * \date 2019.12.01
+ * \copyright MIT License
+ */
+
+#ifndef ENCODING_H
+#define ENCODING_H
+#include "types.h"
+
+/*!
+ * \brief Abstract for encoding classes
+ */
+class encoding
+{
+public:
+	encoding(u8 max_seq_len) { this->max_seq_len = max_seq_len; }
+
+	/*!
+	 * \brief Determines if the given bytes are a valid byte sequence for the
+	 * encoding. Returns the number of valid bytes if true.
+	 */
+	virtual u8 is_valid(u8 const *data) = 0;
+
+	const u8 get_max_seq_len() { return this->max_seq_len; }
+
+protected:
+	u8 max_seq_len;
+};
+
+#endif // ENCODING_H

inc/main.h

@@ -0,0 +1,31 @@
+/*!
+ * \author Damian Rogers ([email protected])
+ * \version 1.1
+ * \date 2019.12.01
+ * \copyright MIT License
+ */
+
+#include <getopt.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <fstream>
+#include <iomanip>
+#include <iostream>
+
+#include "enc_cp932.h"
+#include "enc_eucjp.h"
+#include "enc_shiftjis.h"
+#include "encoding.h"
+#include "types.h"
+
+/*!
+ * \enum encodings
+ * \brief List of supported encodings
+ */
+enum enctypes { shift_jis, cp932, eucjp };
+
+void process_args(int argc, char **argv);
+
+void print_help();

inc/types.h

@@ -0,0 +1,48 @@
+/*!
+ * \author Damian Rogers ([email protected])
+ * \version 1.1
+ * \date 2019.12.01
+ * \copyright MIT License
+ */
+
+#ifndef TYPES_H
+#define TYPES_H
+
+#include <map>
+#include <memory>
+#include <stdint.h>
+#include <vector>
+
+typedef uint8_t u8;
+typedef uint16_t u16;
+typedef uint32_t u32;
+typedef uint64_t u64;
+
+typedef int8_t s8;
+typedef int16_t s16;
+typedef int32_t s32;
+typedef int64_t s64;
+
+template <typename T> using uptr = std::unique_ptr<T>;
+template <typename T> using sptr = std::shared_ptr<T>;
+
+typedef std::map<std::string const, std::string> kvmap;
+
+/*!
+ * \brief POD structure for containing a found string
+ */
+class found_string
+{
+public:
+	/*!
+	 * \brief The offset of the beginning of the found string relative to the
+	 * start of the stream
+	 */
+	off_t address;
+	/*!
+	 * \brief The extracted string data
+	 */
+	std::vector<uint8_t> data;
+};
+
+#endif