-/*\r
- * sample parser\r
- *\r
- * Copyright(c) 2009 olyutorskii\r
- * $Id: SampleParser.java 1000 2010-03-15 12:08:42Z olyutorskii $\r
- */\r
-\r
-package sample;\r
-\r
-import java.io.FileInputStream;\r
-import jp.sourceforge.jindolf.parser.*;\r
-import java.io.IOException;\r
-import java.io.InputStream;\r
-import java.nio.charset.Charset;\r
-import java.nio.charset.CharsetDecoder;\r
-import java.util.Collections;\r
-import java.util.Enumeration;\r
-import java.util.SortedMap;\r
-import java.util.TreeMap;\r
-import java.util.zip.ZipEntry;\r
-import java.util.zip.ZipFile;\r
-\r
-/**\r
- * サンプルのパーサ\r
- */\r
-public class SampleParser{\r
-\r
- private static final CharsetDecoder ud;\r
-\r
- static{\r
- ud = Charset.forName("UTF-8").newDecoder();\r
- }\r
-\r
- private SampleParser(){\r
- super();\r
- return;\r
- }\r
-\r
- public static SortedMap<String, ZipEntry> createEntryMap(ZipFile file){\r
- TreeMap<String, ZipEntry> result = new TreeMap<String, ZipEntry>();\r
-\r
- Enumeration<? extends ZipEntry> list = file.entries();\r
- while(list.hasMoreElements()){\r
- ZipEntry entry = list.nextElement();\r
- String name = entry.getName();\r
- result.put(name, entry);\r
- }\r
-\r
- return Collections.unmodifiableSortedMap(result);\r
- }\r
-\r
- public static DecodedContent contentFromStream(InputStream istream)\r
- throws IOException, DecodeException{\r
- StreamDecoder decoder = new StreamDecoder(ud);\r
- ContentBuilderUCS2 builder = new ContentBuilderUCS2();\r
-\r
- decoder.setDecodeHandler(builder);\r
-\r
- decoder.decode(istream);\r
-\r
- DecodedContent content = builder.getContent();\r
-\r
- return content;\r
- }\r
-\r
- public static void parseContent(DecodedContent content)\r
- throws HtmlParseException{\r
- HtmlParser parser = new HtmlParser();\r
- HtmlHandler handler = new SampleHandler();\r
-\r
- parser.setBasicHandler (handler);\r
- parser.setTalkHandler (handler);\r
- parser.setSysEventHandler(handler);\r
-\r
- parser.parseAutomatic(content);\r
-\r
- return;\r
- }\r
-\r
- public static void parseStream(InputStream istream)\r
- throws IOException,\r
- DecodeException,\r
- HtmlParseException{\r
- DecodedContent content = contentFromStream(istream);\r
-\r
- parseContent(content);\r
-\r
- return;\r
- }\r
-\r
- public static void main(String[] args)\r
- throws IOException,\r
- DecodeException,\r
- HtmlParseException {\r
- if(args.length == 0){\r
- System.out.println(\r
- "標準入力から人狼BBSのXHTML文書の読み取りを"\r
- +"開始します...");\r
-\r
- parseStream(System.in);\r
-\r
- System.exit(0);\r
-\r
- return;\r
- }else if(args[0].endsWith(".zip")){\r
- System.out.println(\r
- "ZIPアーカイブ内の*.htmlファイルから"\r
- +"人狼BBSのXHTML文書の読み取りを開始します...");\r
-\r
- ZipFile zipfile = new ZipFile(args[0]);\r
-\r
- SortedMap<String, ZipEntry> map = createEntryMap(zipfile);\r
-\r
- for(ZipEntry entry : map.values()){\r
- String name = entry.getName();\r
- if( ! name.endsWith(".html") ) continue;\r
-\r
- System.out.println(name + "のパースを開始...");\r
-\r
- InputStream istream = zipfile.getInputStream(entry);\r
- parseStream(istream);\r
-\r
- istream.close();\r
- }\r
-\r
- zipfile.close();\r
-\r
- System.exit(0);\r
-\r
- return;\r
- }else{\r
- System.out.println(args[0] + "のパースを開始...");\r
-\r
- InputStream istream = new FileInputStream(args[0]);\r
- parseStream(istream);\r
- istream.close();\r
-\r
- System.exit(0);\r
- }\r
-\r
- return;\r
- }\r
-\r
-}\r
+/*
+ * sample parser
+ *
+ * License : The MIT License
+ * Copyright(c) 2009 olyutorskii
+ */
+
+package sample;
+
+import java.io.FileInputStream;
+import jp.sourceforge.jindolf.parser.*;
+import java.io.IOException;
+import java.io.InputStream;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.util.Collections;
+import java.util.Enumeration;
+import java.util.SortedMap;
+import java.util.TreeMap;
+import java.util.zip.ZipEntry;
+import java.util.zip.ZipFile;
+
+/**
+ * サンプルのパーサ
+ */
+public class SampleParser{
+
+ private static final CharsetDecoder ud;
+
+ static{
+ ud = Charset.forName("UTF-8").newDecoder();
+ }
+
+ private SampleParser(){
+ super();
+ return;
+ }
+
+ public static SortedMap<String, ZipEntry> createEntryMap(ZipFile file){
+ TreeMap<String, ZipEntry> result = new TreeMap<String, ZipEntry>();
+
+ Enumeration<? extends ZipEntry> list = file.entries();
+ while(list.hasMoreElements()){
+ ZipEntry entry = list.nextElement();
+ String name = entry.getName();
+ result.put(name, entry);
+ }
+
+ return Collections.unmodifiableSortedMap(result);
+ }
+
+ public static DecodedContent contentFromStream(InputStream istream)
+ throws IOException, DecodeException{
+ StreamDecoder decoder = new StreamDecoder(ud);
+ ContentBuilderUCS2 builder = new ContentBuilderUCS2();
+
+ decoder.setDecodeHandler(builder);
+
+ decoder.decode(istream);
+
+ DecodedContent content = builder.getContent();
+
+ return content;
+ }
+
+ public static void parseContent(DecodedContent content)
+ throws HtmlParseException{
+ HtmlParser parser = new HtmlParser();
+ HtmlHandler handler = new SampleHandler();
+
+ parser.setBasicHandler (handler);
+ parser.setTalkHandler (handler);
+ parser.setSysEventHandler(handler);
+
+ parser.parseAutomatic(content);
+
+ return;
+ }
+
+ public static void parseStream(InputStream istream)
+ throws IOException,
+ DecodeException,
+ HtmlParseException{
+ DecodedContent content = contentFromStream(istream);
+
+ parseContent(content);
+
+ return;
+ }
+
+ public static void main(String[] args)
+ throws IOException,
+ DecodeException,
+ HtmlParseException {
+ if(args.length == 0){
+ System.out.println(
+ "標準入力から人狼BBSのXHTML文書の読み取りを"
+ +"開始します...");
+
+ parseStream(System.in);
+
+ System.exit(0);
+
+ return;
+ }else if(args[0].endsWith(".zip")){
+ System.out.println(
+ "ZIPアーカイブ内の*.htmlファイルから"
+ +"人狼BBSのXHTML文書の読み取りを開始します...");
+
+ ZipFile zipfile = new ZipFile(args[0]);
+
+ SortedMap<String, ZipEntry> map = createEntryMap(zipfile);
+
+ for(ZipEntry entry : map.values()){
+ String name = entry.getName();
+ if( ! name.endsWith(".html") ) continue;
+
+ System.out.println(name + "のパースを開始...");
+
+ InputStream istream = zipfile.getInputStream(entry);
+ parseStream(istream);
+
+ istream.close();
+ }
+
+ zipfile.close();
+
+ System.exit(0);
+
+ return;
+ }else{
+ System.out.println(args[0] + "のパースを開始...");
+
+ InputStream istream = new FileInputStream(args[0]);
+ parseStream(istream);
+ istream.close();
+
+ System.exit(0);
+ }
+
+ return;
+ }
+
+}
OSDN Git Service
