在线午夜精品自拍小视频_无码av无码专区线_亚洲无码精品人妻_人人澡欧美一区

<dependency>
  <groupId>org.ansj</groupId>
  <artifactId>ansj_seg</artifactId>
  <version>5.1.6</version>
  <scope>compile</scope>
</dependency>
<dependency>
  <groupId>com.janeluo</groupId>
  <artifactId>ikanalyzer</artifactId>
  <version>2012_u6</version>
</dependency>

@Test
public  void testAnsjSeg() {
    String str = "我叫李太白，我是一個詩人，我生活在唐朝" ;
    // 選擇使用哪種分詞器 BaseAnalysis ToAnalysis NlpAnalysis  IndexAnalysis
    Result result = ToAnalysis.parse(str);
    System.out.println(result);
    KeyWordComputer kwc = new KeyWordComputer(5);
    Collection<Keyword> keywords = kwc.computeArticleTfidf(str);
    System.out.println(keywords);
}

/**
 * Chinese words segmentation with user-dict in com.kingcall.dic
 * use Ansj(a java open source analyzer)
 */

// 這個信息就是你每次使用desc 進行獲取函數(shù)信息的時候返回的
@Description(name = "ansj_seg", value = "_FUNC_(str) - chinese words segment using ansj. Return list of words.",
        extended = "Example: select _FUNC_('我是測試字符串') from src limit 1;\n"
                + "[\"我\", \"是\", \"測試\", \"字符串\"]")

public class AnsjSeg extends GenericUDF {
    private transient ObjectInspectorConverters.Converter[] converters;
    private static final String userDic = "/app/stopwords/com.kingcall.dic";

    //load userDic in hdfs
    static {
        try {
            FileSystem fs = FileSystem.get(new Configuration());
            FSDataInputStream in = fs.open(new Path(userDic));
            BufferedReader br = new BufferedReader(new InputStreamReader(in));

            String line = null;
            String[] strs = null;
            while ((line = br.readLine()) != null) {
                line = line.trim();
                if (line.length() > 0) {
                    strs = line.split("\t");
                    strs[0] = strs[0].toLowerCase();
                    DicLibrary.insert(DicLibrary.DEFAULT, strs[0]); //ignore nature and freq
                }
            }
            MyStaticValue.isNameRecognition = Boolean.FALSE;
            MyStaticValue.isQuantifierRecognition = Boolean.TRUE;
        } catch (Exception e) {
            System.out.println("Error when load userDic" + e.getMessage());
        }
    }

    @Override
    public ObjectInspector initialize(ObjectInspector[] arguments) throws UDFArgumentException {
        if (arguments.length < 1 || arguments.length > 2) {
            throw new UDFArgumentLengthException(
                    "The function AnsjSeg(str) takes 1 or 2 arguments.");
        }

        converters = new ObjectInspectorConverters.Converter[arguments.length];
        converters[0] = ObjectInspectorConverters.getConverter(arguments[0], PrimitiveObjectInspectorFactory.writableStringObjectInspector);
        if (2 == arguments.length) {
            converters[1] = ObjectInspectorConverters.getConverter(arguments[1], PrimitiveObjectInspectorFactory.writableIntObjectInspector);
        }
        return ObjectInspectorFactory.getStandardListObjectInspector(PrimitiveObjectInspectorFactory.writableStringObjectInspector);
    }

    @Override
    public Object evaluate(DeferredObject[] arguments) throws HiveException {
        boolean filterStop = false;
        if (arguments[0].get() == null) {
            return null;
        }
        if (2 == arguments.length) {
            IntWritable filterParam = (IntWritable) converters[1].convert(arguments[1].get());
            if (1 == filterParam.get()) filterStop = true;
        }

        Text s = (Text) converters[0].convert(arguments[0].get());
        ArrayList<Text> result = new ArrayList<>();

        if (filterStop) {
            for (Term words : DicAnalysis.parse(s.toString()).recognition(StopLibrary.get())) {
                if (words.getName().trim().length() > 0) {
                    result.add(new Text(words.getName().trim()));
                }
            }
        } else {
            for (Term words : DicAnalysis.parse(s.toString())) {
                if (words.getName().trim().length() > 0) {
                    result.add(new Text(words.getName().trim()));
                }
            }
        }
        return result;
    }

    @Override
    public String getDisplayString(String[] children) {
        return getStandardDisplayString("ansj_seg", children);
    }
}

@Description(name = "ansj_seg", value = "_FUNC_(str) - chinese words segment using Iknalyzer. Return list of words.",
        extended = "Example: select _FUNC_('我是測試字符串') from src limit 1;\n"
                + "[\"我\", \"是\", \"測試\", \"字符串\"]")
public class IknalyzerSeg extends GenericUDF {
    private transient ObjectInspectorConverters.Converter[] converters;
    //用來存放停用詞的集合
    Set<String> stopWordSet = new HashSet<String>();

    @Override
    public ObjectInspector initialize(ObjectInspector[] arguments) throws UDFArgumentException {
        if (arguments.length < 1 || arguments.length > 2) {
            throw new UDFArgumentLengthException(
                    "The function AnsjSeg(str) takes 1 or 2 arguments.");
        }
        //讀入停用詞文件
        BufferedReader StopWordFileBr = null;
        try {
            StopWordFileBr = new BufferedReader(new InputStreamReader(new FileInputStream(new File("stopwords/baidu_stopwords.txt"))));
            //初如化停用詞集
            String stopWord = null;
            for(; (stopWord = StopWordFileBr.readLine()) != null;){
                stopWordSet.add(stopWord);
            }
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }

        converters = new ObjectInspectorConverters.Converter[arguments.length];
        converters[0] = ObjectInspectorConverters.getConverter(arguments[0], PrimitiveObjectInspectorFactory.writableStringObjectInspector);
        if (2 == arguments.length) {
            converters[1] = ObjectInspectorConverters.getConverter(arguments[1], PrimitiveObjectInspectorFactory.writableIntObjectInspector);
        }
        return ObjectInspectorFactory.getStandardListObjectInspector(PrimitiveObjectInspectorFactory.writableStringObjectInspector);

    }

    @Override
    public Object evaluate(DeferredObject[] arguments) throws HiveException {
        boolean filterStop = false;
        if (arguments[0].get() == null) {
            return null;
        }
        if (2 == arguments.length) {
            IntWritable filterParam = (IntWritable) converters[1].convert(arguments[1].get());
            if (1 == filterParam.get()) filterStop = true;
        }
        Text s = (Text) converters[0].convert(arguments[0].get());
        StringReader reader = new StringReader(s.toString());
        IKSegmenter iks = new IKSegmenter(reader, true);
        List<Text> list = new ArrayList<>();
        if (filterStop) {
            try {
                Lexeme lexeme;
                while ((lexeme = iks.next()) != null) {
                    if (!stopWordSet.contains(lexeme.getLexemeText())) {
                        list.add(new Text(lexeme.getLexemeText()));
                    }
                }
            } catch (IOException e) {
            }
        } else {
            try {
                Lexeme lexeme;
                while ((lexeme = iks.next()) != null) {
                    list.add(new Text(lexeme.getLexemeText()));
                }
            } catch (IOException e) {
            }
        }
        return list;
    }

    @Override
    public String getDisplayString(String[] children) {
        return "Usage: evaluate(String str)";
    }
}

@Test
public void testAnsjSegFunc() throws HiveException {
    AnsjSeg udf = new AnsjSeg();
    ObjectInspector valueOI0 = PrimitiveObjectInspectorFactory.javaStringObjectInspector;
    ObjectInspector valueOI1 = PrimitiveObjectInspectorFactory.javaIntObjectInspector;
    ObjectInspector[] init_args = {valueOI0, valueOI1};
    udf.initialize(init_args);

    Text str = new Text("我是測試字符串");

    GenericUDF.DeferredObject valueObj0 = new GenericUDF.DeferredJavaObject(str);
    GenericUDF.DeferredObject valueObj1 = new GenericUDF.DeferredJavaObject(0);
    GenericUDF.DeferredObject[] args = {valueObj0, valueObj1};
    ArrayList<Object> res = (ArrayList<Object>) udf.evaluate(args);
    System.out.println(res);
}

@Test
public void testIkSegFunc() throws HiveException {
    IknalyzerSeg udf = new IknalyzerSeg();
    ObjectInspector valueOI0 = PrimitiveObjectInspectorFactory.javaStringObjectInspector;
    ObjectInspector valueOI1 = PrimitiveObjectInspectorFactory.javaIntObjectInspector;
    ObjectInspector[] init_args = {valueOI0, valueOI1};
    udf.initialize(init_args);

    Text str = new Text("我是測試字符串");

    GenericUDF.DeferredObject valueObj0 = new GenericUDF.DeferredJavaObject(str);
    GenericUDF.DeferredObject valueObj1 = new GenericUDF.DeferredJavaObject(0);
    GenericUDF.DeferredObject[] args = {valueObj0, valueObj1};
    ArrayList<Object> res = (ArrayList<Object>) udf.evaluate(args);
    System.out.println(res);
}