Java 如何读入RCF文件
我试图将一个小的RCFile（约200行数据）读入HashMap中，以进行映射端连接，但在将文件中的数据转换为可用状态时遇到了很多困难 以下是我目前掌握的信息，其中大部分来自： 如何正确读入这些数据，以便一次只能访问一行，例如Java 如何读入RCF文件,java,hadoop,mapreduce,Java,Hadoop,Mapreduce,我试图将一个小的RCFile（约200行数据）读入HashMap中，以进行映射端连接，但在将文件中的数据转换为可用状态时遇到了很多困难 以下是我目前掌握的信息，其中大部分来自： 如何正确读入这些数据，以便一次只能访问一行，例如 （191年，美国，美国，19）？经过进一步挖掘，我找到了一个解决方案。这里的关键是不要使用RCFile.Reader，而是使用RCFileRecordReader 以下是我最后得到的，也适用于打开多个文件： try
（191年，美国，美国，19）RCFile.ReaderRCFileRecordReadertry
{
FileSystem fs = FileSystem.get(job);
FileStatus [] fileStatuses = fs.listStatus(new Path("/path/to/dir/"));
LongWritable key = new LongWritable();
BytesRefArrayWritable value = new BytesRefArrayWritable();
int counter = 1;
for (int i = 0; i < fileStatuses.length; i++)
{
FileStatus fileStatus = fileStatuses[i];
if (!fileStatus.isDir())
{
System.out.println("File: " + fileStatus);
FileSplit split = new FileSplit(fileStatus.getPath(), 0, fileStatus.getLen(), job);
RCFileRecordReader reader = new RCFileRecordReader(job, split);
while (reader.next(key, value))
{
System.out.println("Getting row " + counter);
AllCountriesRow acr = AllCountriesRow.valueOf(value);
System.out.println("ROW: " + acr);
counter++;
}
}
}
}
catch (IOException e)
{
throw new Error(e);
}
这最终会得到一个AllCountriesRow对象，该对象中包含相关行的所有信息。由于RCFile的列性质，行读取路径与写入路径明显不同。我们仍然可以使用RCFile.Reader类按行读取RCFile（不需要RCFileRecordReader）。但除此之外，我们还需要使用ColumnarSerDe将列数据转换为行数据 下面是我们可以得到的最简单的代码，用于逐行读取RCF文件。有关更多详细信息，请参阅内联代码注释
private static void readRCFileByRow(String pathStr)
throws IOException, SerDeException {
final Configuration conf = new Configuration();
final Properties tbl = new Properties();
/*
* Set the column names and types using comma separated strings.
* The actual name of the columns are not important, as long as the count
* of column is correct.
*
* For types, this example uses strings. byte[] can be stored as string
* by encoding the bytes to ASCII (such as hexString or Base64)
*
* Numbers of columns and number of types must match exactly.
*/
tbl.setProperty("columns", "col1,col2,col3,col4,col5");
tbl.setProperty("columns.types", "string:string:string:string:string");
/*
* We need a ColumnarSerDe to de-serialize the columnar data to row-wise
* data
*/
ColumnarSerDe serDe = new ColumnarSerDe();
serDe.initialize(conf, tbl);
Path path = new Path(pathStr);
FileSystem fs = FileSystem.get(conf);
final RCFile.Reader reader = new RCFile.Reader(fs, path, conf);
final LongWritable key = new LongWritable();
final BytesRefArrayWritable cols = new BytesRefArrayWritable();
while (reader.next(key)) {
System.out.println("Getting next row.");
/*
* IMPORTANT: Pass the same cols object to the getCurrentRow API; do not
* create new BytesRefArrayWritable() each time. This is because one call
* to getCurrentRow(cols) can potentially read more than one column
* values which the serde below would take care to read one by one.
*/
reader.getCurrentRow(cols);
final ColumnarStruct row = (ColumnarStruct) serDe.deserialize(cols);
final ArrayList<Object> objects = row.getFieldsAsList();
for (final Object object : objects) {
// Lazy decompression happens here
final String payload =
((LazyString) object).getWritableObject().toString();
System.out.println("Value:" + payload);
}
}
}
private static void readRCFileByRow（字符串路径str）
抛出IOException，SerDeException{
最终配置conf=新配置（）；
最终属性tbl=新属性（）；
/*
*使用逗号分隔的字符串设置列名和类型。
*列的实际名称并不重要，只要计数
*列的名称是正确的。
*
*对于类型，此示例使用字符串。字节[]可以存储为字符串
*通过将字节编码为ASCII（如hexString或Base64）
*
*列数和类型数必须完全匹配。
*/
tbl.setProperty（“列”、“列1、列2、列3、列4、列5”）；
tbl.setProperty（“columns.types”、“string:string:string:string”）；
/*
*我们需要一个ColumnarSerDe将列数据反序列化为行数据
*资料
*/
ColumnarSerDe serDe=新ColumnarSerDe（）；
serDe.initialize（conf，tbl）；
路径路径=新路径（路径str）；
FileSystem fs=FileSystem.get（conf）；
final RCFile.Reader Reader=new RCFile.Reader（fs，path，conf）；
最终LongWritable键=新的LongWritable（）；
final BytesRefArrayWritable cols=新的BytesRefArrayWritable（）；
while（reader.next（键））{
System.out.println（“获取下一行”）；
/*
*要点：将相同的cols对象传递给getCurrentRow API；不要
*每次创建新的BytesRefArrayWritable（）。这是因为一个调用
*to getCurrentRow（cols）可能读取多个列
*下面的serde会注意逐个读取的值。
*/
reader.getCurrentRow（cols）；
final ColumnarStruct row=（ColumnarStruct）serDe.deserialize（cols）；
final ArrayList objects=row.getFieldsAsList（）；
用于（最终对象：对象）{
//惰性解压发生在这里
最终字符串有效负载=
（（LazyString）对象）.getWritableObject（）.toString（）；
System.out.println（“值：”+有效载荷）；
}
}
}
getCurrentRow（）coulmnarStruct.getFieldsAsList（）getWritableObject（）StructObjectInspectorcopyToStandardObjecttry
{
FileSystem fs = FileSystem.get(job);
FileStatus [] fileStatuses = fs.listStatus(new Path("/path/to/dir/"));
LongWritable key = new LongWritable();
BytesRefArrayWritable value = new BytesRefArrayWritable();
int counter = 1;
for (int i = 0; i < fileStatuses.length; i++)
{
FileStatus fileStatus = fileStatuses[i];
if (!fileStatus.isDir())
{
System.out.println("File: " + fileStatus);
FileSplit split = new FileSplit(fileStatus.getPath(), 0, fileStatus.getLen(), job);
RCFileRecordReader reader = new RCFileRecordReader(job, split);
while (reader.next(key, value))
{
System.out.println("Getting row " + counter);
AllCountriesRow acr = AllCountriesRow.valueOf(value);
System.out.println("ROW: " + acr);
counter++;
}
}
}
}
catch (IOException e)
{
throw new Error(e);
}
public static AllCountriesRow valueOf(BytesRefArrayWritable braw) throws IOException
{
try
{
StructObjectInspector soi = (StructObjectInspector) serDe.getObjectInspector();
Object row = serDe.deserialize(braw);
List<? extends StructField> fieldRefs = soi.getAllStructFieldRefs();
Object fieldData = soi.getStructFieldData(row, fieldRefs.get(Column.ID.ordinal()));
ObjectInspector oi = fieldRefs.get(Column.ID.ordinal()).getFieldObjectInspector();
int id = ((IntObjectInspector)oi).get(fieldData);
fieldData = soi.getStructFieldData(row, fieldRefs.get(Column.NAME.ordinal()));
oi = fieldRefs.get(Column.NAME.ordinal()).getFieldObjectInspector();
String name = ((StringObjectInspector)oi).getPrimitiveJavaObject(fieldData);
fieldData = soi.getStructFieldData(row, fieldRefs.get(Column.CODE.ordinal()));
oi = fieldRefs.get(Column.CODE.ordinal()).getFieldObjectInspector();
String code = ((StringObjectInspector)oi).getPrimitiveJavaObject(fieldData);
fieldData = soi.getStructFieldData(row, fieldRefs.get(Column.REGION_NAME.ordinal()));
oi = fieldRefs.get(Column.REGION_NAME.ordinal()).getFieldObjectInspector();
String regionName = ((StringObjectInspector)oi).getPrimitiveJavaObject(fieldData);
fieldData = soi.getStructFieldData(row, fieldRefs.get(Column.CONTINENT_ID.ordinal()));
oi = fieldRefs.get(Column.CONTINENT_ID.ordinal()).getFieldObjectInspector();
int continentId = ((IntObjectInspector)oi).get(fieldData);
return new AllCountriesRow(id, name, code, regionName, continentId);
}
catch (SerDeException e)
{
throw new IOException(e);
}
}
private static void readRCFileByRow(String pathStr)
throws IOException, SerDeException {
final Configuration conf = new Configuration();
final Properties tbl = new Properties();
/*
* Set the column names and types using comma separated strings.
* The actual name of the columns are not important, as long as the count
* of column is correct.
*
* For types, this example uses strings. byte[] can be stored as string
* by encoding the bytes to ASCII (such as hexString or Base64)
*
* Numbers of columns and number of types must match exactly.
*/
tbl.setProperty("columns", "col1,col2,col3,col4,col5");
tbl.setProperty("columns.types", "string:string:string:string:string");
/*
* We need a ColumnarSerDe to de-serialize the columnar data to row-wise
* data
*/
ColumnarSerDe serDe = new ColumnarSerDe();
serDe.initialize(conf, tbl);
Path path = new Path(pathStr);
FileSystem fs = FileSystem.get(conf);
final RCFile.Reader reader = new RCFile.Reader(fs, path, conf);
final LongWritable key = new LongWritable();
final BytesRefArrayWritable cols = new BytesRefArrayWritable();
while (reader.next(key)) {
System.out.println("Getting next row.");
/*
* IMPORTANT: Pass the same cols object to the getCurrentRow API; do not
* create new BytesRefArrayWritable() each time. This is because one call
* to getCurrentRow(cols) can potentially read more than one column
* values which the serde below would take care to read one by one.
*/
reader.getCurrentRow(cols);
final ColumnarStruct row = (ColumnarStruct) serDe.deserialize(cols);
final ArrayList<Object> objects = row.getFieldsAsList();
for (final Object object : objects) {
// Lazy decompression happens here
final String payload =
((LazyString) object).getWritableObject().toString();
System.out.println("Value:" + payload);
}
}
}