Examples with Utf8 org.apache.avro.util.Utf8 used on opensource projects

Example 91 with Utf8

use of org.apache.avro.util.Utf8 in project eiger by wlloyd.

the class CFMetaData method toAvro.

// converts CFM to avro CfDef
public org.apache.cassandra.db.migration.avro.CfDef toAvro() {
    org.apache.cassandra.db.migration.avro.CfDef cf = new org.apache.cassandra.db.migration.avro.CfDef();
    cf.id = cfId;
    cf.keyspace = new Utf8(ksName);
    cf.name = new Utf8(cfName);
    cf.column_type = new Utf8(cfType.name());
    cf.comparator_type = new Utf8(comparator.toString());
    if (subcolumnComparator != null) {
        assert cfType == ColumnFamilyType.Super : String.format("%s CF %s should not have subcomparator %s defined", cfType, cfName, subcolumnComparator);
        cf.subcomparator_type = new Utf8(subcolumnComparator.toString());
    }
    cf.comment = new Utf8(enforceCommentNotNull(comment));
    cf.read_repair_chance = readRepairChance;
    cf.replicate_on_write = replicateOnWrite;
    cf.gc_grace_seconds = gcGraceSeconds;
    cf.default_validation_class = defaultValidator == null ? null : new Utf8(defaultValidator.toString());
    cf.key_validation_class = new Utf8(keyValidator.toString());
    cf.min_compaction_threshold = minCompactionThreshold;
    cf.max_compaction_threshold = maxCompactionThreshold;
    cf.merge_shards_chance = mergeShardsChance;
    cf.key_alias = keyAlias;
    cf.column_metadata = new ArrayList<ColumnDef>(column_metadata.size());
    for (ColumnDefinition cd : column_metadata.values()) cf.column_metadata.add(cd.toAvro());
    cf.compaction_strategy = new Utf8(compactionStrategyClass.getName());
    if (compactionStrategyOptions != null) {
        cf.compaction_strategy_options = new HashMap<CharSequence, CharSequence>();
        for (Map.Entry<String, String> e : compactionStrategyOptions.entrySet()) cf.compaction_strategy_options.put(new Utf8(e.getKey()), new Utf8(e.getValue()));
    }
    cf.compression_options = compressionParameters.asAvroOptions();
    cf.bloom_filter_fp_chance = bloomFilterFpChance;
    cf.caching = new Utf8(caching.toString());
    return cf;
}

Example 92 with Utf8

use of org.apache.avro.util.Utf8 in project eiger by wlloyd.

the class ColumnDefinition method toAvro.

public org.apache.cassandra.db.migration.avro.ColumnDef toAvro() {
    org.apache.cassandra.db.migration.avro.ColumnDef cd = new org.apache.cassandra.db.migration.avro.ColumnDef();
    cd.name = ByteBufferUtil.clone(name);
    cd.validation_class = new Utf8(validator.toString());
    cd.index_type = index_type == null ? null : org.apache.cassandra.db.migration.avro.IndexType.valueOf(index_type.name());
    cd.index_name = index_name == null ? null : new Utf8(index_name);
    cd.index_options = getCharSequenceMap(index_options);
    return cd;
}

Example 93 with Utf8

use of org.apache.avro.util.Utf8 in project drill by apache.

the class AvroRecordReader method processPrimitive.

private void processPrimitive(final Object value, final Schema.Type type, final String fieldName, final MapOrListWriterImpl writer) {
    if (value == null) {
        return;
    }
    switch(type) {
        case STRING:
            byte[] binary = null;
            final int length;
            if (value instanceof Utf8) {
                binary = ((Utf8) value).getBytes();
                length = ((Utf8) value).getByteLength();
            } else {
                binary = value.toString().getBytes(Charsets.UTF_8);
                length = binary.length;
            }
            ensure(length);
            buffer.setBytes(0, binary);
            writer.varChar(fieldName).writeVarChar(0, length, buffer);
            break;
        case INT:
            writer.integer(fieldName).writeInt((Integer) value);
            break;
        case LONG:
            writer.bigInt(fieldName).writeBigInt((Long) value);
            break;
        case FLOAT:
            writer.float4(fieldName).writeFloat4((Float) value);
            break;
        case DOUBLE:
            writer.float8(fieldName).writeFloat8((Double) value);
            break;
        case BOOLEAN:
            writer.bit(fieldName).writeBit((Boolean) value ? 1 : 0);
            break;
        case BYTES:
            final ByteBuffer buf = (ByteBuffer) value;
            length = buf.remaining();
            ensure(length);
            buffer.setBytes(0, buf);
            writer.binary(fieldName).writeVarBinary(0, length, buffer);
            break;
        case NULL:
            // Nothing to do for null type
            break;
        case ENUM:
            final String symbol = value.toString();
            final byte[] b;
            try {
                b = symbol.getBytes("UTF-8");
            } catch (UnsupportedEncodingException e) {
                throw new DrillRuntimeException("Unable to read enum value for field: " + fieldName, e);
            }
            ensure(b.length);
            buffer.setBytes(0, b);
            writer.varChar(fieldName).writeVarChar(0, b.length, buffer);
            break;
        default:
            throw new DrillRuntimeException("Unhandled Avro type: " + type.toString());
    }
}

Example 94 with Utf8

use of org.apache.avro.util.Utf8 in project gora by apache.

the class SolrStore method deserializeFieldValue.

@SuppressWarnings("unchecked")
private Object deserializeFieldValue(Field field, Schema fieldSchema, Object solrValue, T persistent) throws IOException {
    Object fieldValue = null;
    switch(fieldSchema.getType()) {
        case MAP:
        case ARRAY:
        case RECORD:
            @SuppressWarnings("rawtypes") SpecificDatumReader reader = getDatumReader(fieldSchema);
            fieldValue = IOUtils.deserialize((byte[]) solrValue, reader, persistent.get(field.pos()));
            break;
        case ENUM:
            fieldValue = AvroUtils.getEnumValue(fieldSchema, (String) solrValue);
            break;
        case FIXED:
            throw new IOException("???");
        // break;
        case BYTES:
            fieldValue = ByteBuffer.wrap((byte[]) solrValue);
            break;
        case STRING:
            fieldValue = new Utf8(solrValue.toString());
            break;
        case UNION:
            if (fieldSchema.getTypes().size() == 2 && isNullable(fieldSchema)) {
                // schema [type0, type1]
                Type type0 = fieldSchema.getTypes().get(0).getType();
                Type type1 = fieldSchema.getTypes().get(1).getType();
                // ["null","type"] or ["type","null"]
                if (!type0.equals(type1)) {
                    if (type0.equals(Schema.Type.NULL))
                        fieldSchema = fieldSchema.getTypes().get(1);
                    else
                        fieldSchema = fieldSchema.getTypes().get(0);
                } else {
                    fieldSchema = fieldSchema.getTypes().get(0);
                }
                fieldValue = deserializeFieldValue(field, fieldSchema, solrValue, persistent);
            } else {
                @SuppressWarnings("rawtypes") SpecificDatumReader unionReader = getDatumReader(fieldSchema);
                fieldValue = IOUtils.deserialize((byte[]) solrValue, unionReader, persistent.get(field.pos()));
                break;
            }
            break;
        default:
            fieldValue = solrValue;
    }
    return fieldValue;
}

Example 95 with Utf8

use of org.apache.avro.util.Utf8 in project gora by apache.

the class DistributedLogManager method parseLine.

/**
   * Parses a single log line in combined log format using StringTokenizers
   */
private Pageview parseLine(String line) throws ParseException {
    StringTokenizer matcher = new StringTokenizer(line);
    //parse the log line
    String ip = matcher.nextToken();
    //discard
    matcher.nextToken();
    matcher.nextToken();
    long timestamp = dateFormat.parse(matcher.nextToken("]").substring(2)).getTime();
    matcher.nextToken("\"");
    String request = matcher.nextToken("\"");
    String[] requestParts = request.split(" ");
    String httpMethod = requestParts[0];
    String url = requestParts[1];
    matcher.nextToken(" ");
    int httpStatusCode = Integer.parseInt(matcher.nextToken());
    int responseSize = Integer.parseInt(matcher.nextToken());
    matcher.nextToken("\"");
    String referrer = matcher.nextToken("\"");
    matcher.nextToken("\"");
    String userAgent = matcher.nextToken("\"");
    //construct and return pageview object
    Pageview pageview = new Pageview();
    pageview.setIp(new Utf8(ip));
    pageview.setTimestamp(timestamp);
    pageview.setHttpMethod(new Utf8(httpMethod));
    pageview.setUrl(new Utf8(url));
    pageview.setHttpStatusCode(httpStatusCode);
    pageview.setResponseSize(responseSize);
    pageview.setReferrer(new Utf8(referrer));
    pageview.setUserAgent(new Utf8(userAgent));
    return pageview;
}