국립국어원_HTTP적용 2020. 06 .24

package com.company;

import org.apache.hc.core5.http.ParseException;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import java.io.*;

import org.apache.hc.client5.http.classic.methods.HttpPost;
import org.apache.hc.client5.http.entity.mime.MultipartEntityBuilder;
import org.apache.hc.client5.http.entity.mime.StringBody;
import org.apache.hc.client5.http.impl.classic.CloseableHttpClient;
import org.apache.hc.client5.http.impl.classic.CloseableHttpResponse;
import org.apache.hc.client5.http.impl.classic.HttpClients;
import org.apache.hc.core5.http.ContentType;
import org.apache.hc.core5.http.HttpEntity;
import org.apache.hc.core5.http.io.entity.EntityUtils;
import org.xml.sax.SAXException;

public class ShinTest5 {
    public static void main(String[] args) throws IOException, SAXException, 
    		ParserConfigurationException {

        String input = "“당근”, ‘양파sdfgs’, 오4535이’s, 2345수dfgsv박!@#%@$^, /참$%^외^&*/";

        String[] modifdStr = getCSVArray(input);
        // comma 기준으로 배열 생성

        for (int j = 0; j < modifdStr.length; j++) {
            String content = getAPI(modifdStr, j);
            // 인덱스 순으로 API 참조한 String 결과
            String result = parseXML(content);
            // XML로 변환
            mkTxtFile(result, j);
            // 텍스트 파일로 만들기
        }

    }


    public static String[] getCSVArray(String input) {
    // Comma 분리
        String[] str = input.split(",");
        String[] modifdStr = new String[str.length];

        int i = 0;	
        // 특수문자와 공백 제거
        for (String e : str) {
            modifdStr[i] = StringReplace(e);
            modifdStr[i] = modifdStr[i].trim();
            i++;
        }

        for (String e : modifdStr) {
            System.out.println(e);
        }
        return modifdStr;
    }

    public static String StringReplace(String str) {
    // 한글이 아닌 값 삭제
        String match = "[^\uAC00-\uD7A3\\s]";
        str = str.replaceAll(match, "");
        return str;
    }

    public static String StringReplace2(String str) {
    // 한글, 점이 아닌 값 삭제
        String match = "[^\uAC00-\uD7A3.\\s]";
        str = str.replaceAll(match, "");
        return str;
    }

    private static String getAPI(String[] modifdStr, int j) throws IOException {
    // 국립 국어원 API 참조하여 XML결과 String형식 가져오기

        String content = "";
        CloseableHttpClient httpclient = HttpClients.createDefault();

        HttpPost httppost = new HttpPost("https://stdict.korean.go.kr/api/search.do");

        StringBody key = new StringBody("14F296AB6ADF1D06A38A8F1B1BF75207",
        		ContentType.TEXT_PLAIN);
        StringBody q = new StringBody(modifdStr[j], 
        		ContentType.TEXT_PLAIN.withCharset("UTF-8"));

        HttpEntity reqEntity = MultipartEntityBuilder.create()
                .addPart("key", key)
                .addPart("q", q)
                .build();

        httppost.setEntity(reqEntity);
        CloseableHttpResponse response = httpclient.execute(httppost);

        try {
            System.out.println("----------------------------------------");
            System.out.println("Response Code : " + response.getCode());
            HttpEntity resEntity = response.getEntity();
            if (resEntity != null) {
                String charset = "UTF-8";
                content = EntityUtils.toString(response.getEntity(), charset);
            }
            EntityUtils.consume(resEntity);
        } catch (ParseException parseException) {
            parseException.printStackTrace();
        } finally {
            response.close();
        }

        return content;
    }

    public static String parseXML(String content) throws ParserConfigurationException,
    		IOException, SAXException {
            // XML에서 word, pos, definition, type 순으로 CSV 형식 변환
        DocumentBuilderFactory dbFactoty = DocumentBuilderFactory.newInstance();
        DocumentBuilder dBuilder = dbFactoty.newDocumentBuilder();
        InputStream inptSrc = new ByteArrayInputStream(content.getBytes());
        Document doc = dBuilder.parse(inptSrc);

        String result = "word,pos,definition,type";
        NodeList nList = doc.getElementsByTagName("item");
        for (int temp = 0; temp < nList.getLength(); temp++) {
            Node nNode = nList.item(temp);
            if (nNode.getNodeType() == Node.ELEMENT_NODE) {

                Element eElement = (Element) nNode;
                result = result + "\n" + (getTagValue("word", eElement).trim() + "," + 
                		getTagValue("pos", eElement).trim() + "," + 
                        StringReplace2(getTagValue("definition", eElement).trim()) + "," + 
                        getTagValue("type", eElement).trim());
            }    // if end
        }    // for end

        return result;
    }

    private static String getTagValue(String tag, Element eElement) {
    // XML에서 해당하는 태그 값 가져오기
        NodeList nlList = eElement.getElementsByTagName(tag).item(0).getChildNodes();
        Node nValue = (Node) nlList.item(0);
        if (nValue == null)
            return null;
        return nValue.getNodeValue();
    }

    public static void mkTxtFile(String result, int j) throws IOException {
    // 지정 경로로 텍스트 파일 만들기
        BufferedOutputStream bs = null;
        try {
            bs = new BufferedOutputStream(new FileOutputStream("/home/ehdrud1129/다운로드/
            		20200624_국립국어원_결과" + (j + 1) + "_노동경.csv"));
            bs.write(result.getBytes());
        } catch (Exception e) {
            e.getStackTrace();
            // TODO: handle exception
        } finally {
            bs.close();
        }
    }
}