From daabc0fc189b26d827709978bbe118b85f01a88b Mon Sep 17 00:00:00 2001
From: MiserableLife <kdw6485@gmail.com>
Date: Sat, 24 Mar 2018 12:18:22 +0900
Subject: [PATCH] [feature] divide into modules

* divide into modules.
* refactoring into C++ form
* add sequence analyze
---
 SequenceAnalyzer.cpp      |  79 +++++++++++++++++++++
 SequenceAnalyzer.h        |  52 ++++++++++++++
 SetAnalyzer.cpp           |  94 +++++++++++++++++++++++++
 SetAnalyzer.h             |  31 +++++++++
 main.cpp                  | 140 --------------------------------------
 sequence_analyze_test.cpp |  48 +++++++++++++
 set_analyze_test.cpp      |  32 +++++++++
 7 files changed, 336 insertions(+), 140 deletions(-)
 create mode 100644 SequenceAnalyzer.cpp
 create mode 100644 SequenceAnalyzer.h
 create mode 100644 SetAnalyzer.cpp
 create mode 100644 SetAnalyzer.h
 delete mode 100644 main.cpp
 create mode 100644 sequence_analyze_test.cpp
 create mode 100644 set_analyze_test.cpp

diff --git a/SequenceAnalyzer.cpp b/SequenceAnalyzer.cpp
new file mode 100644
index 0000000..7f91420
--- /dev/null
+++ b/SequenceAnalyzer.cpp
@@ -0,0 +1,79 @@
+#include "SequenceAnalyzer.h"
+#include <fstream>
+#include <iostream>
+
+
+sequence_table* SequenceAnalyzer::divide_by_thread(const char* filename)
+{
+	std::ifstream in;
+	char buffer[MAXBUFFER];
+	struct contents tmp;
+	std::string str;
+	int num_line=0;
+	sequence_table* table = new sequence_table;
+	in.open(filename);
+	while(!in.eof())
+	{
+		in.getline(buffer, MAXBUFFER);
+		str = buffer;
+	//delimeter process
+	//std::cout<<str2<<std::endl;
+		num_line++;
+		size_t pos = str.find_first_of(del.c_str());
+		int num_thread = atoi(str.substr(0,pos).c_str() );
+		str = str.substr(pos+1 ); 
+		pos = str.find("(");
+		str = str.substr(0, pos);
+	
+		tmp.pos = num_line;
+		tmp.body = str;
+		(*table)[num_thread].push_back(tmp);
+
+	}
+
+	in.close();
+	return table;
+}	
+void SequenceAnalyzer::print_sequence_table_into_file(sequence_table& table, const char* prefix_filename )
+{
+	std::ofstream out;
+	std::string filename;
+	for(sequence_table::iterator it = table.begin();  it!= table.end(); it++)
+	{
+		filename = prefix_filename;
+	   	filename += std::to_string(it->first);
+		out.open(filename.c_str());
+		std::vector<struct contents >& c = it->second;
+		for(std::vector<struct contents>::iterator it_v = c.begin(); it_v!= c.end(); it_v++)
+			out<< it_v->body <<std::endl;
+		out.close();
+	}
+}
+
+void SequenceAnalyzer::compare(const sequence& s1, const sequence& s2)
+{
+	int i=0;
+	int comp_size = s1.size() < s2.size(); 
+	int size = comp_size ? s1.size(): s2.size();
+	
+	for(int i=0; i< size ; i++)
+	{
+		if( s1[i].body != s2[i].body)
+		{
+			std::cout<<s1[i].pos <<" : <<< "<< s1[i].body<< std::endl;
+			std::cout<<s2[i].pos <<" : >>> "<< s2[i].body<< std::endl;
+			return ;
+		}
+	}
+
+	if(comp_size < 0 ) 
+		std::cout<< "left sequence is subset of right sequence"<<std::endl;
+	else if(comp_size >0)
+		std::cout<<"right sequence is subset of left sequence"<<std::endl;
+	else
+		std::cout<<"exactly equal sequence"<<std::endl;
+
+
+}
+
+
diff --git a/SequenceAnalyzer.h b/SequenceAnalyzer.h
new file mode 100644
index 0000000..3530844
--- /dev/null
+++ b/SequenceAnalyzer.h
@@ -0,0 +1,52 @@
+#ifndef SEQUENCE_ANALYZER_H_
+#define SEQUENCE_ANALYZER_H_
+
+#include <vector>
+#include <map>
+#include <string>
+
+enum {
+	MAXBUFFER= 8192
+}	;
+
+struct contents
+{
+	int pos;//line number where the contents exist
+	std::string body;
+};
+
+typedef std::vector<struct contents> sequence;
+typedef std::map<int, sequence > sequence_table;
+/*
+ * Analyzing format 
+ * thread_number	key(some parameters) any other things
+ * ex)
+ *	1				fopen("myfile.txt","rt") somebodyhelpme
+ *
+ *
+ **
+ */
+class SequenceAnalyzer
+{
+private:
+	std::string del;
+
+
+public:
+	SequenceAnalyzer() : del(" \t") {}
+	inline void setdelimeter(const char* delimeter)
+	{
+		del  = delimeter;
+	}
+	sequence_table* divide_by_thread(const char* filename);
+	void print_sequence_table_into_file(sequence_table& table, const char* prefix_filename );
+	void compare(const sequence& s1, const sequence& s2);
+
+
+
+};
+
+
+
+
+#endif
diff --git a/SetAnalyzer.cpp b/SetAnalyzer.cpp
new file mode 100644
index 0000000..0eefeaf
--- /dev/null
+++ b/SetAnalyzer.cpp
@@ -0,0 +1,94 @@
+#include "SetAnalyzer.h"
+#include <vector>
+#include <map>
+#include <fstream>
+
+
+int SetAnalyzer::read_with_delimeter(std::set<std::string>& filtered_set, const char* filename, bool append)
+{
+	std::ifstream in; 
+	char buffer[255];
+
+	if(!append)
+		filtered_set.clear();
+	in.open(filename);
+	while(!in.eof())
+	{
+		std::vector<std::string> temp_storage;
+		in.getline(buffer, 255);
+		//delimeter process
+		std::string str = buffer;
+		std::size_t prepos=0, pos = str.find_first_of(del.c_str());
+		while(pos != std::string::npos)
+		{
+			temp_storage.push_back(str.substr(prepos, pos-prepos));
+			prepos = pos+1;
+			while( ( pos = str.find_first_of(del.c_str(),pos+1)) != std::string::npos )
+				if( pos != prepos) 
+					break;
+				else
+					prepos = pos+1;
+		}
+		temp_storage.push_back(str.substr(prepos, pos-prepos));
+		str="";
+		for(std::vector<std::string>::iterator it= temp_storage.begin(); it!= temp_storage.end(); it++)
+			str += *it + " ";
+		//delimeter process end
+
+		filtered_set.insert(str);
+	}
+	in.close();
+	return 0;
+}
+std::set<std::string>* SetAnalyzer::get_diffset(const std::set<std::string>& set1, const std::set<std::string>& set2)
+{
+	std::set<std::string>* diff1_2 = new std::set<std::string>;
+	//set1 - set2 
+	*diff1_2 = set1;
+	for(std::set<std::string>::iterator it = set2.begin(); it!= set2.end(); it++)
+		diff1_2->erase(*it);
+	return diff1_2;
+}
+
+void analyze_with_key(const std::set<std::string>& diff1_2, const std::set<std::string>& diff2_1)// developing.... 
+{
+	std::map<std::string, std::string > orghash;
+	for(std::set<std::string>::iterator it = diff1_2.begin(); it!= diff1_2.end(); it++)
+	{
+		std::string str = *it;
+		std::size_t pos = str.find_first_of(" ");
+		orghash[str.substr(0,pos)] = str.substr(pos+1);
+	}
+	for(std::set<std::string>::iterator it = diff2_1.begin(); it!= diff2_1.end(); it++)
+	{
+		std::string str = *it;
+		std::size_t pos = str.find_first_of(" ");
+		if(!orghash[str.substr(0,pos)].empty())
+		{
+			std::string outputstr="";
+			std::cout<< str.substr(0,pos)<< " " <<orghash[str.substr(0,pos)]<<std::endl;
+			for(int i=0; i<pos+1; i++)
+				outputstr += " ";
+	
+			str = orghash[str.substr(0,pos)];
+			std::size_t prepos=0, pos = str.find_first_of(" ");
+			while(pos != std::string::npos)
+			{
+			
+			str.substr(prepos, pos-prepos);
+			prepos = pos+1;
+//		pos = str.find_first_of(" \t",pos+1);
+			while( ( pos = str.find_first_of(" \t",pos+1)) != std::string::npos )
+				if( pos != prepos) 
+					break;
+				else
+					prepos = pos+1;
+			}
+	
+		}
+	}
+
+
+}
+
+
diff --git a/SetAnalyzer.h b/SetAnalyzer.h
new file mode 100644
index 0000000..458474f
--- /dev/null
+++ b/SetAnalyzer.h
@@ -0,0 +1,31 @@
+#ifndef SETANALYZER_H_
+#define SETANALYZER_H_
+
+#include <string>
+#include <set>
+
+
+
+class SetAnalyzer
+{
+private:
+//	std::map<std::string, std::string> orghash;
+	std::string del; 
+public:
+	SetAnalyzer() : del("\t")
+	{
+	};
+	inline void setdelimeter(const char* delimeter)
+	{
+		del = delimeter;
+	}
+	int read_with_delimeter(std::set<std::string>& filtered_set, const char* filename, bool append=false);
+	std::set<std::string>* SetAnalyzer::get_diffset(const std::set<std::string>& set1, const std::set<std::string>& set2);
+	
+
+};
+
+
+
+#endif
+
diff --git a/main.cpp b/main.cpp
deleted file mode 100644
index 398359b..0000000
--- a/main.cpp
+++ /dev/null
@@ -1,140 +0,0 @@
-#include <iostream>
-#include <fstream>
-#include <set>
-#include <string>
-#include <vector>
-#include <sstream>
-#include <map>
-
-
-int main(int argc, char** argv)
-{
-	std::ifstream in; 
-	if(argc <3 )
-		return 1;
-	char* file1 = argv[1];
-	char* file2 = argv[2];
-	char buffer[255];
-	std::set<std::string> set1;
-	std::set<std::string> set2;
-	std::set<std::string> diff1_2;
-	std::set<std::string> diff2_1;
-	std::map<std::string, std::string> orghash;
-	in.open(file1);
-	while(!in.eof())
-	{
-		std::vector<std::string> temp_storage;
-		in.getline(buffer, 255);
-		//delimeter process
-		std::string str = buffer;
-		std::size_t prepos=0, pos = str.find_first_of(" \t");
-		while(pos != std::string::npos)
-		{
-			temp_storage.push_back(str.substr(prepos, pos-prepos));
-			prepos = pos+1;
-			while( ( pos = str.find_first_of(" \t",pos+1)) != std::string::npos )
-				if( pos != prepos) 
-					break;
-				else
-					prepos = pos+1;
-		}
-		temp_storage.push_back(str.substr(prepos, pos-prepos));
-		str="";
-		for(std::vector<std::string>::iterator it= temp_storage.begin(); it!= temp_storage.end(); it++)
-			str += *it + " ";
-		//delimeter process end
-		
-		set1.insert(str);
-	}
-	in.close();
-	in.open(file2);
-	while(!in.eof())
-	{
-		std::vector<std::string> temp_storage;
-		in.getline(buffer,255);
-	//delimeter process
-		std::string str = buffer;
-		std::size_t prepos=0, pos = str.find_first_of(" \t");
-		while(pos != std::string::npos)
-		{
-			
-			temp_storage.push_back(str.substr(prepos, pos-prepos));
-			prepos = pos+1;
-//			pos = str.find_first_of(" \t",pos+1);
-			while( ( pos = str.find_first_of(" \t",pos+1)) != std::string::npos )
-				if( pos != prepos) 
-					break;
-				else
-					prepos = pos+1;
-		}
-		temp_storage.push_back(str.substr(prepos, pos-prepos));
-		str="";
-		for(std::vector<std::string>::iterator it= temp_storage.begin(); it!= temp_storage.end(); it++)
-			str += *it + " ";
-		//delimeter process end
-		
-		set2.insert(str);
-	}
-	in.close();
-
-	diff1_2 = set1;
-	diff2_1 = set2;
-
-	for(std::set<std::string>::iterator it = set1.begin(); it!= set1.end(); it++)
-		diff2_1.erase(*it);
-	for(std::set<std::string>::iterator it = set2.begin(); it!= set2.end(); it++)
-		diff1_2.erase(*it);
-
-
-	for(std::set<std::string>::iterator it = diff1_2.begin(); it!= diff1_2.end(); it++)
-	{
-		std::string str = *it;
-		std::size_t pos = str.find_first_of(" ");
-		orghash[str.substr(0,pos)] = str.substr(pos+1);
-	}
-	for(std::set<std::string>::iterator it = diff2_1.begin(); it!= diff2_1.end(); it++)
-	{
-		std::string str = *it;
-		std::size_t pos = str.find_first_of(" ");
-		if(!orghash[str.substr(0,pos)].empty())
-		{
-			std::string outputstr="";
-			std::cout<< str.substr(0,pos)<< " " <<orghash[str.substr(0,pos)]<<std::endl;
-			for(int i=0; i<pos+1; i++)
-				outputstr += " ";
-
-			str = orghash[str.substr(0,pos)];
-			std::size_t prepos=0, pos = str.find_first_of(" ");
-			while(pos != std::string::npos)
-			{
-			
-			str.substr(prepos, pos-prepos);
-			prepos = pos+1;
-//			pos = str.find_first_of(" \t",pos+1);
-			while( ( pos = str.find_first_of(" \t",pos+1)) != std::string::npos )
-				if( pos != prepos) 
-					break;
-				else
-					prepos = pos+1;
-		}
-		temp_storage.push_back(str.substr(prepos, pos-prepos));
-		
-			
-
-			std::cout<< 
-		}
-	}
-
-	std::cout<<"only on "<<file1<<"  contents"<<std::endl;
-	for(std::set<std::string>::iterator it = diff1_2.begin(); it!= diff1_2.end(); it++) 
-		std::cout<<*it<<std::endl;
-
-	std::cout<<std::endl<<std::endl;
-	std::cout<<"only on "<<file2<<"  contents"<<std::endl;
-	for(std::set<std::string>::iterator it = diff2_1.begin(); it!= diff2_1.end(); it++) 
-		std::cout<<*it<<std::endl;
-
-
-
-	return 0;	
-}
diff --git a/sequence_analyze_test.cpp b/sequence_analyze_test.cpp
new file mode 100644
index 0000000..47dd2f1
--- /dev/null
+++ b/sequence_analyze_test.cpp
@@ -0,0 +1,48 @@
+#include <iostream>
+#include "SequenceAnalyzer.h"
+
+int main(int argc, char** argv)
+{
+	if(argc <3 )
+		return 1;
+	char* file1 = argv[1];
+	char* file2 = argv[2];
+	sequence_table* table1;//thread , contents
+	sequence_table* table2;//thread , contents
+
+	SequenceAnalyzer sa;
+
+	table1 = sa.divide_by_thread(file1);
+	table2 = sa.divide_by_thread(file2);
+
+	int cmd;
+	while(true)
+	{
+		std::cout<<"1. print out to files by thread number"<<std::endl;
+		std::cout<<"2. find out where the difference between two contents occurs "<<std::endl;
+		std::cout<<"Enter cmd :  ";
+		scanf("%d",&cmd);
+		switch(cmd)
+		{
+			case 1:
+				sa.print_sequence_table_into_file(*table1, argv[1]);
+				sa.print_sequence_table_into_file(*table2, argv[2]);
+				break;
+			case 2:
+				int thr1, thr2;
+				std::cout<<"type thread number from "<<argv[1];
+				scanf("%d",&thr1);
+				std::cout<<"type thread number from "<<argv[2];
+				scanf("%d",&thr2);
+				sa.compare((*table1)[thr1],(*table2)[thr2]);
+				break;
+			default:
+				std::cout<<"invalid command "<<std::endl;
+				
+		}
+	}
+
+
+	return 0;
+}
+
diff --git a/set_analyze_test.cpp b/set_analyze_test.cpp
new file mode 100644
index 0000000..225cb99
--- /dev/null
+++ b/set_analyze_test.cpp
@@ -0,0 +1,32 @@
+#include <iostream>
+#include "SetAnalyzer.h"
+
+
+
+int main(int argc, char** argv)
+{
+	if(argc <3 )
+		return 1;
+	char* file1 = argv[1];
+	char* file2 = argv[2];
+	SetAnalyzer sa;
+	std::set<std::string> set1, set2;
+	sa.read_with_delimeter(set1, file1);
+	sa.read_with_delimeter(set2, file2);
+
+	std::set<std::string>* diff1_2 = sa.get_diffset(set1, set2);
+	std::set<std::string>* diff2_1 = sa.get_diffset(set2, set1);
+	std::cout<<"only on "<<file1<<"  contents"<<std::endl;
+	for(std::set<std::string>::iterator it = diff1_2->begin(); it!= diff1_2->end(); it++) 
+		std::cout<<*it<<std::endl;
+
+	std::cout<<std::endl<<std::endl;
+	std::cout<<"only on "<<file2<<"  contents"<<std::endl;
+	for(std::set<std::string>::iterator it = diff2_1->begin(); it!= diff2_1->end(); it++) 
+		std::cout<<*it<<std::endl;
+
+	delete diff1_2;
+	delete diff2_1;
+
+	return 0;	
+}