Commit: 124 - testroom1 (svn)

作業部屋の使い方を試しています。

Commit MetaInfo

• Revision: 124 (tree)
• Time: 2015-03-09 11:56:22
• Author: tuna_p

Log Message

【仕様変更】XML読書き処理
旧:SearchDataRW.java → 新:ScrapingXml.java

Change Summary

• modified: branches/b3/WebScraping/src/WebScraping/utility/HtmlSearch.java
• added: branches/b3/WebScraping/src/WebScraping/utility/LibraryXml.java
• added: branches/b3/WebScraping/src/WebScraping/utility/ScrapingXml.java

Incremental Difference

--- branches/b3/WebScraping/src/WebScraping/utility/HtmlSearch.java	(revision 123)
+++ branches/b3/WebScraping/src/WebScraping/utility/HtmlSearch.java	(revision 124)
@@ -40,7 +40,7 @@
  * @author kgto
  */
 public class HtmlSearch extends javax.swing.JFrame {
-    private final SearchDataRW sio = new SearchDataRW();
+    private final ScrapingXml xmlwriter = new ScrapingXml();
 
     SearchDataTableModel sdatatblmodel;
     
@@ -332,8 +332,9 @@
         int selected = jFileChooser1.showOpenDialog(this);
         if (selected == JFileChooser.APPROVE_OPTION) {
             File file = jFileChooser1.getSelectedFile();
-            sio.load(file);
-            jTxtUrl.setText(sio.geturl());
+            xmlwriter.load(file);
+            jTxtUrl.setText(xmlwriter.getTestUrl());
+            xmlwriter.getSdata();
             sdatatblmodel.setRowCount(0);
             for(int i = 0; i < SearchData.size(); i++) {
                 SearchData sdata = SearchData.get(i);
@@ -347,7 +348,7 @@
         int selected = jFileChooser1.showSaveDialog(this);
         if (selected == JFileChooser.APPROVE_OPTION) {
             File file = jFileChooser1.getSelectedFile();
-            sio.seturl(jTxtUrl.getText());
+            xmlwriter.setTestUrl(jTxtUrl.getText());
             
             SearchData.clear();
             for(int row = 0; row < sdatatblmodel.getRowCount(); row++) {
@@ -354,7 +355,8 @@
                 SearchData sdata = sdatatblmodel.getSearchData(row);
                 SearchData.add(sdata);
             }
-            sio.save(file);
+            xmlwriter.setSdata();
+            xmlwriter.save(file);
         }
     }//GEN-LAST:event_jMenuSaveActionPerformed
 

--- branches/b3/WebScraping/src/WebScraping/utility/LibraryXml.java	(nonexistent)
+++ branches/b3/WebScraping/src/WebScraping/utility/LibraryXml.java	(revision 124)
@@ -0,0 +1,138 @@
+/*
+ * Copyright (C) 2014-2015 kgto.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301  USA
+ */
+/*
+ * $Id:$
+ */
+
+package webScraping.utility;
+
+import java.io.File;
+import java.io.FileNotFoundException;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.util.logging.Level;
+import java.util.logging.Logger;
+
+import javax.xml.parsers.DocumentBuilder;
+import javax.xml.parsers.DocumentBuilderFactory;
+import javax.xml.parsers.ParserConfigurationException;
+import javax.xml.transform.Transformer;
+import javax.xml.transform.TransformerConfigurationException;
+import javax.xml.transform.TransformerException;
+import javax.xml.transform.TransformerFactory;
+import javax.xml.transform.dom.DOMSource;
+import javax.xml.transform.stream.StreamResult;
+
+import org.w3c.dom.DOMImplementation;
+import org.w3c.dom.Document;
+import org.w3c.dom.Element;
+import org.w3c.dom.Node;
+import org.w3c.dom.NodeList;
+import org.xml.sax.SAXException;
+
+public class LibraryXml {
+
+    String xmlrootname = "xmlcontainer";
+
+    DocumentBuilder builder;
+    public Document readdoc, writedoc;
+    Element xmlroot;
+
+    /* ---------------------------------------------------------------------- *
+     *   コンストラクタ
+     * ---------------------------------------------------------------------- */
+    public LibraryXml() {
+        try {
+            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
+            builder = factory.newDocumentBuilder();
+
+        } catch (ParserConfigurationException ex) {
+            Logger.getLogger(LibraryXml.class.getName()).log(Level.SEVERE, null, ex);
+        }
+    }
+
+    /* ---------------------------------------------------------------------- *
+     *   メソッド
+     * ---------------------------------------------------------------------- */
+    /* 読込み処理 */
+    public Element getwriteRoot(String elementName) {
+        mainElement();
+        Element element = writedoc.createElement(elementName);
+        xmlroot.appendChild(element);
+        return element;
+    }
+
+    private void mainElement() {
+        if(writedoc == null) {
+            DOMImplementation domImpl = builder.getDOMImplementation();
+            writedoc = domImpl.createDocument("", xmlrootname, null);
+            xmlroot = writedoc.getDocumentElement();
+        }
+    }
+
+    /**
+     * XML書込み.
+     * @param file
+     */
+    public void write(File file) {
+        try {
+            TransformerFactory transFactory = TransformerFactory.newInstance();
+            Transformer transformer = transFactory.newTransformer();
+
+            transformer.setOutputProperty("indent", "yes");  // 改行指定
+            transformer.setOutputProperty("method", "xml");
+
+            FileOutputStream os = new FileOutputStream(file);
+            DOMSource source = new DOMSource(writedoc);
+            StreamResult result = new StreamResult(os);
+            transformer.transform(source, result);
+
+        } catch (TransformerConfigurationException ex) {
+            Logger.getLogger(LibraryXml.class.getName()).log(Level.SEVERE, null, ex);
+        } catch (FileNotFoundException | TransformerException ex) {
+            Logger.getLogger(LibraryXml.class.getName()).log(Level.SEVERE, null, ex);
+        }
+    }
+
+    /* ---------------------------------------------------------------------- */
+    /* 書込み処理 */
+
+    Element getreadRoot(String elementName) {
+        NodeList nodelist = xmlroot.getElementsByTagName(elementName);
+        Node node = nodelist.item(0);
+        return (node.getNodeType() == Node.ELEMENT_NODE ? (Element)node : null);
+    }
+
+    /**
+     * XML読込み.
+     * @param file
+     */
+    public void read(File file) {
+        try {
+            readdoc = builder.parse(file);
+            xmlroot = readdoc.getDocumentElement();
+
+        } catch (SAXException | IOException ex) {
+            Logger.getLogger(LibraryXml.class.getName()).log(Level.SEVERE, null, ex);
+        }
+    }
+
+    /* ---------------------------------------------------------------------- */
+    
+}

--- branches/b3/WebScraping/src/WebScraping/utility/ScrapingXml.java	(nonexistent)
+++ branches/b3/WebScraping/src/WebScraping/utility/ScrapingXml.java	(revision 124)
@@ -0,0 +1,198 @@
+/*
+ * Copyright (C) 2014-2015 kgto.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301  USA
+ */
+/*
+ * $Id:$
+ */
+
+package webScraping.utility;
+
+import webScraping.core.SearchData;
+import java.io.File;
+import java.util.ArrayList;
+import org.w3c.dom.Element;
+import org.w3c.dom.Node;
+import org.w3c.dom.NodeList;
+
+public class ScrapingXml {
+    /* ---------------------------------------------------------------------- *
+     *   フィールド
+     * ---------------------------------------------------------------------- */
+    String rootnameScraping = "webscraping";
+
+    private String testUrl;
+    private SearchData[] sdata;
+
+    LibraryXml xlib = new LibraryXml();
+    Element root;
+
+    /* ---------------------------------------------------------------------- *
+     *   コンストラクタ
+     * ---------------------------------------------------------------------- */
+    ScrapingXml() {
+    }
+
+    /* ---------------------------------------------------------------------- *
+     *   Setter
+     * ---------------------------------------------------------------------- */
+    void setTestUrl(String testUrl) {
+        this.testUrl = testUrl;
+    }
+
+    void setSdata() {
+        this.sdata = new SearchData[SearchData.size()];
+        for(int i = 0; i < SearchData.size(); i++) {
+            this.sdata[i] = SearchData.get(i);
+        }
+    }
+
+    /* ---------------------------------------------------------------------- *
+     *   Getter
+     * ---------------------------------------------------------------------- */
+    String getTestUrl() {
+        return testUrl;
+    }
+
+    void getSdata() {
+        SearchData.clear();
+        for(SearchData sdata1 : sdata) {
+            SearchData.add(sdata1);
+        }
+    }
+
+    /* ---------------------------------------------------------------------- *
+     *   メソッド
+     * ---------------------------------------------------------------------- */
+    void save(File file) {
+
+        elementset();
+
+        xlib.write(file);
+    }
+
+    public void elementset() {
+        root = xlib.getwriteRoot(rootnameScraping);
+        elementsetUrl();
+        elementsetSearchdata();
+        System.out.println("elementset XmlScraping");
+    }
+
+    private void elementsetUrl() {
+        Element url = xlib.writedoc.createElement("url");
+        url.appendChild(xlib.writedoc.createTextNode(testUrl));
+        root.appendChild(url);
+    }
+
+    private void elementsetSearchdata() {
+        int count = 0;
+        for(SearchData sdat : sdata) {
+            Element cslist    = xlib.writedoc.createElement("searchlist");
+            cslist.setAttribute("listNo", String.valueOf(++count));
+
+            addChild(cslist, "item"     , sdat.getitem());
+            addChild(cslist, "htmltag"  , sdat.getHtmltag());
+            addChild(cslist, "htmlid"   , sdat.getHtmlid());
+            addChild(cslist, "htmlclass", sdat.getHtmlclass());
+            addChild(cslist, "around"   , sdat.getaround());
+            addChild(cslist, "regexp"   , sdat.getregexp());
+
+            root.appendChild(cslist);
+        }
+    }
+
+    private void addChild(Element cslist, String keyword, String data) {
+        if(!data.isEmpty()) {
+            Element element = xlib.writedoc.createElement(keyword);
+            element.appendChild(xlib.writedoc.createTextNode(data));
+            cslist.appendChild(element);
+        }
+    }
+
+    /* ---------------------------------------------------------------------- */
+
+    void load(File file) {
+        xlib.read(file);
+        elementget();
+    }
+
+    public void elementget() {
+        root = xlib.getreadRoot(rootnameScraping);
+        elementgetUrl();
+        elementgetSearchdata();
+    }
+
+    private void elementgetUrl() {
+        NodeList nodelist = root.getElementsByTagName("url");
+        Node node = nodelist.item(0);
+        testUrl = node.getFirstChild().getNodeValue();
+    }
+
+    private void elementgetSearchdata() {
+        ArrayList<SearchData> slist = new ArrayList<>();
+
+        NodeList nodelist = root.getElementsByTagName("searchlist");
+        for(int i = 0; i < nodelist.getLength(); i++) {
+            Node childnode = nodelist.item(i);
+
+            boolean sdatflg = false;
+            SearchData sdat = new SearchData();
+            for (Node child = childnode.getFirstChild(); child != null; child = child.getNextSibling()) {
+                if(child.getNodeType() == Node.ELEMENT_NODE) {
+                    String tag = child.getNodeName();
+                    String rtn = "";
+                    if(child.getFirstChild() != null) {
+                        rtn = child.getFirstChild().getNodeValue();
+                    }
+                    switch (tag) {
+                        case "item" :
+                            sdat.setitem(rtn);
+                            sdatflg = true;
+                            break;
+                        case "htmltag" :
+                            sdat.setHtmltag(rtn);
+                            sdatflg = true;
+                            break;
+                        case "htmlid" :
+                            sdat.setHtmlid(rtn);
+                            sdatflg = true;
+                            break;
+                        case "htmlclass" :
+                            sdat.setHtmlclass(rtn);
+                            sdatflg = true;
+                            break;
+                        case "around" :
+                            sdat.setaround(rtn);
+                            sdatflg = true;
+                            break;
+                        case "regexp" :
+                            sdat.setregexp(rtn);
+                            sdatflg = true;
+                            break;
+                    }
+                }
+            }
+            if(sdatflg) slist.add(sdat);
+        }
+        // 配列化
+        sdata = new SearchData[slist.size()];
+        for(int i = 0; i < slist.size(); i++) {
+            sdata[i] = slist.get(i);
+        }
+    }
+
+}