changed to RapidJson SAX ver

@@ -71,19 +71,23 @@
   <PropertyGroup Label="UserMacros" />
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
     <LinkIncremental>true</LinkIncremental>
-    <IncludePath>C:\boost\boost_1_62_0;C:\JsonCpp\jsoncpp-master\include;$(IncludePath)</IncludePath>
-    <LibraryPath>C:\boost\boost_1_62_0\stage\lib;C:\JsonCpp\jsoncpp-master\build\vs71\debug\lib_json;$(LibraryPath)</LibraryPath>
+    <IncludePath>C:\boost\boost_1_62_0;C:\rapidjson\include;$(IncludePath)</IncludePath>
+    <LibraryPath>C:\boost\boost_1_62_0\stage\lib;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
     <LinkIncremental>true</LinkIncremental>
-    <IncludePath>C:\boost\boost_1_62_0;C:\JsonCpp\jsoncpp-master\include;$(IncludePath)</IncludePath>
-    <LibraryPath>C:\boost\boost_1_62_0\stage\lib;C:\JsonCpp\jsoncpp-master\build\vs71\debug\lib_json;$(LibraryPath)</LibraryPath>
+    <IncludePath>C:\boost\boost_1_62_0;C:\rapidjson\include;$(IncludePath)</IncludePath>
+    <LibraryPath>C:\boost\boost_1_62_0\stage\lib;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
     <LinkIncremental>false</LinkIncremental>
+    <IncludePath>C:\rapidjson\include;C:\boost\boost_1_62_0;$(IncludePath)</IncludePath>
+    <LibraryPath>C:\boost\boost_1_62_0\stage\lib;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
     <LinkIncremental>false</LinkIncremental>
+    <IncludePath>C:\rapidjson\include;C:\boost\boost_1_62_0;$(IncludePath)</IncludePath>
+    <LibraryPath>C:\boost\boost_1_62_0\stage\lib;$(LibraryPath)</LibraryPath>
   </PropertyGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
     <ClCompile>
@@ -99,7 +103,7 @@
       <SubSystem>Console</SubSystem>
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalLibraryDirectories>%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>json_vc71_libmtd.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>%(AdditionalDependencies)</AdditionalDependencies>
     </Link>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
@@ -116,7 +120,7 @@
       <SubSystem>Console</SubSystem>
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalLibraryDirectories>%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
-      <AdditionalDependencies>json_vc71_libmtd.lib;%(AdditionalDependencies)</AdditionalDependencies>
+      <AdditionalDependencies>%(AdditionalDependencies)</AdditionalDependencies>
     </Link>
   </ItemDefinitionGroup>
   <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">

 #include <cstdio>
+#include <cinttypes>	//PRId64
 #include <exception>
 #include <fstream>
 #include <iostream>
@@ -7,7 +8,9 @@
 
 #include <boost/regex.hpp>
 
-#include <json/json.h>
+#include <rapidjson/document.h>
+#include <rapidjson/istreamwrapper.h>
+#include <rapidjson/reader.h>
 
 using namespace std;
 
@@ -15,105 +18,175 @@ const char* DBLP_FILENAME = "dblp.json";
 const char* DBLP_COAUTHOR_FILENAME = "tmp_dblp_coauthorship.json";
 const string COLUMN_DELIMITER = "||";
 const string AUTHOR_DELIMITER = "&&";
+boost::regex paper_reg{"(conf|journals).*"};
 
-int main() {
-	//init
-	Json::Value root;
-	Json::Reader reader;
-	ifstream dblp_paper, dblp_coauthor;
-	ofstream dblp_paper_out, dblp_coauthor_out;
-	boost::regex paper_reg{"(conf|journals).*"};
 
-	try {
-		//1. dblp paper dataset
-		dblp_paper.open(DBLP_FILENAME);
-		dblp_paper_out.open((string(DBLP_FILENAME)+string(".out")).c_str());
-		if (!dblp_paper || !dblp_paper_out) {
-			throw exception("dblp paper file error");
-		}
-		printf("* complete open\n");
+struct PaperRecord {
+	string paper_key;
+	vector<string> authors;
+	unsigned int year;
 
-		if (!reader.parse(dblp_paper, root)) {
-			throw exception("parse error");
+	void write(ofstream& fout) {
+		fout << paper_key << COLUMN_DELIMITER;
+		for (auto it=authors.begin(); it!=authors.end(); ++it) {
+			if (it != authors.begin()) {
+				fout << AUTHOR_DELIMITER;
+			}
+			fout << *it;
 		}
-		printf("* complete parse\n");
+		fout << COLUMN_DELIMITER << year << endl;
+	}
+	void clear() {
+		paper_key.clear();
+		authors.clear();
+		year = 1;
+	}
+	void add_author(string str) {
+		authors.push_back(str);
+	}
+};
 
+struct DblpPaperHandler {
+	bool whole_array = false;
+	bool is_record = false;
+	bool is_authors = false;
+	bool is_paper = false;
+	uint64_t record_count = 0;
 
-		Json::Value row;
-		Json::Value coauthors;
+	PaperRecord paper;
+	ofstream& ofs;
 
-		std::string paper_key;
-		std::vector<string> coauthor_list;
-		int year;
+	DblpPaperHandler(ofstream& fout)
+		: ofs(fout) {
+	}
 
-		int count = 1;
-		for (auto it=root.begin();
-			it!=root.end();
-			++it) {
+	//
+	bool Null() {
+		return true;
+	}
+	bool Bool(bool b) {
+		//cout << "Bool(" << boolalpha << b << ")" << endl;
+		return true;
+	}
+	bool Int(int i) {
+		//cout << "Int(" << i << ")" << endl;
+		return true;
+	}
+	bool Uint(unsigned u) {
+		//cout << "Uint(" << u << ")" << endl;
+		if (is_paper) {
+			paper.year = u;
+		}
 
-			//Àüó¸®
-			row.clear();
-			coauthors.clear();
-			coauthor_list.clear();
+		return true;
+	}
+	bool Int64(int64_t i) {
+		//cout << "Int64(" << i << ")" << endl;
+		return true;
+	}
+	bool Uint64(uint64_t u) {
+		//cout << "Uint64(" << u << ")" << endl;
+		return true;
+	}
+	bool Double(double d) {
+		//cout << "Double(" << d << ")" << endl;
+		return true;
+	}
+	bool RawNumber(const char* str, rapidjson::SizeType length, bool copy) {
+		//cout << "Number(" << str << ", " << length << ", " << boolalpha << copy << ")" << endl;
+		return true;
+	}
+	bool String(const char* str, rapidjson::SizeType length, bool copy) {
+		if (is_record) {
+			if (is_authors) {
+				if (!is_paper)
+					return true;
 
-			//print
-			if (count%1000000 == 0) {
-				printf("* [%d]\n", count);
+				paper.add_author(string(str));
+			} else {
+				if (boost::regex_match(str, paper_reg)) {
+					is_paper = true;
+					paper.paper_key = string(str);
+				}
 			}
-
-			//row ´ÜÀ§·Î read
-			row = *it;
-			paper_key = row[0].asString();
-
-			//check whether it is paper
-			if (boost::regex_match(paper_key, paper_reg)) {
-				coauthors = row[1];
-				for (auto coit=coauthors.begin(); coit!=coauthors.end(); ++coit) {
-					coauthor_list.push_back(coit->asString());
+		}
+		return true;
+	}
+	bool StartObject() {
+		//cout << "StartObject()" << endl;
+		return true;
+	}
+	bool Key(const char* str, rapidjson::SizeType length, bool copy) {
+		//cout << "Key(" << str << ", " << length << ", " << boolalpha << copy << ")" << endl;
+		return true;
+	}
+	bool EndObject(rapidjson::SizeType memberCount) {
+		//cout << "EndObject(" << memberCount << ")" << endl;
+		return true;
+	}
+	bool StartArray() {
+		if (!whole_array) {
+			whole_array = true;
+		} else if (!is_record) {
+			is_record = true;
+		} else if (!is_authors) {
+			is_authors = true;
+		}
+		return true;
+	}
+	bool EndArray(rapidjson::SizeType elementCount) {
+		if (is_record) {
+			if (is_authors) {
+				is_authors = false;
+			} else {
+				if (is_paper) {
+					paper.write(ofs);
+					paper.clear();
 				}
-				year = ((row[2].isNull())?-1:row[2].asInt());
-
-				//write
-				dblp_paper_out << paper_key << COLUMN_DELIMITER;
-				if (coauthor_list.size() > 0) {
-					for (auto auit=coauthor_list.begin(); auit!=coauthor_list.end();) {
-						dblp_paper_out << (*auit);
-						++auit;
-						if (auit != coauthor_list.end()) {
-							dblp_paper_out << AUTHOR_DELIMITER;
-						}
-					}
-				} else {
-					//empty
-					throw exception("paper without author");
+
+				is_record = false;
+				is_paper = false;
+				++record_count;
+				if (record_count % 100000 == 0) {
+					printf("* [%" PRIu64 "] \n", record_count);
 				}
-				dblp_paper_out << COLUMN_DELIMITER
-					<< year
-					<< endl;
-			} else {
-				//not paper
 			}
+		} else {
+			whole_array = false;
+			printf("* total paper record: [%" PRIu64 "]\n", record_count);
+		}
+		return true;
+	}
+};
+
 
-			//ÈÄó¸®
-			++count;
+int main() {
+	try {
+		ifstream dblp_paper_in, dblp_coauthor_in;
+		ofstream dblp_paper_out, dblp_coauthor_out;
+		dblp_paper_in.open(DBLP_FILENAME);
+		dblp_paper_out.open((string(DBLP_FILENAME)+string(".out")).c_str());
+		if (!dblp_paper_in || !dblp_paper_out) {
+			throw exception("dblp paper file");
 		}
-		printf("* complete convert dblp paper\n");
-	
+		
+		DblpPaperHandler paper_handler(dblp_paper_out);
 
-		//2. dblp coauthorship dataset
-		//dblp_coauthor.open(DBLP_COAUTHOR_FILENAME);
+		rapidjson::IStreamWrapper dblp_paper_isw(dblp_paper_in);
+		rapidjson::Reader reader;
 
+		reader.Parse(dblp_paper_isw, paper_handler);
+
+		//release
+		if (dblp_paper_in) dblp_paper_in.close();
+		if (dblp_paper_out) dblp_paper_out.close();
+		if (dblp_coauthor_in) dblp_coauthor_in.close();
+		if (dblp_coauthor_out) dblp_coauthor_out.close();
 	}
 	catch (const exception& e) {
 		cerr << "Error: " << e.what() << endl;
 		return -1;
 	}
 
-
-	//release
-	if (dblp_paper) dblp_paper.close();
-	if (dblp_coauthor) dblp_coauthor.close();
-	if (dblp_paper_out) dblp_paper_out.close();
-	if (dblp_coauthor_out) dblp_coauthor_out.close();
 	return 0;
 }
\ No newline at end of file