/**
* @param ordinal
* @param data
*/
private void findExtractedFields(int ordinal, String data) {
List<FieldExtractor> extractors = schema.getEntity().getExtractorsForField(ordinal);
for (FieldExtractor extractor : extractors) {
String extField = extrtactedFields.get(extractor.getOrdinal());
if (null == extField || extField.isEmpty()) {
String match = extractor.findMatch(data);
if (null == match) {
match = "";
}
extrtactedFields.put(extractor.getOrdinal(), match);
}
}
}
/* (non-Javadoc)
* @see org.apache.hadoop.mapreduce.Mapper#map(KEYIN, VALUEIN, org.apache.hadoop.mapreduce.Mapper.Context)
*/
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String[] items = value.toString().split(fieldDelimRegex);
itemList.clear();
for (int i = 0; i < items.length; ++i) {
String item = items[i];
Field field = schema.getEntity().getFieldByOrdinal(i);
if (null != field && field.getDataType().equals(Field.DATA_TYPE_TEXT)) {
String format = field.getTextDataSubTypeFormat();
if (field.getDataSubType().equals(Field.TEXT_TYPE_PERSON_NAME)) {
item = countryFormat.personNameFormat(item);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_STREET_ADDRESS)) {
item = countryFormat.caseFormat(item, format);
item = countryFormat.streetAddressFormat(item);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_STREET_ADDRESS_ONE)) {
item = countryFormat.caseFormat(item, format);
item = countryFormat.streetAddressOneFormat(item);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_STREET_ADDRESS_TWO)) {
item = countryFormat.caseFormat(item, format);
item = countryFormat.streetAddressTwoFormat(item);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_CITY)) {
item = countryFormat.caseFormat(item, format);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_STATE)) {
item = countryFormat.stateFormat(item);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_ZIP)) {
item = countryFormat.caseFormat(item, format);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_COUNTRY)) {
item = countryFormat.caseFormat(item, format);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_EMAIL_ADDR)) {
item = countryFormat.emailFormat(item, format);
} else if (field.getDataSubType().equals(Field.TEXT_TYPE_PHONE_NUM)) {
item = countryFormat.phoneNumFormat(item, format);
} else {
// if text field analyze
item = tokenize(item);
}
}
itemList.add(item);
}
// build value string
valueHolder.set(org.chombo.util.Utility.join(itemList, fieldDelim));
context.write(NullWritable.get(), valueHolder);
}
/* (non-Javadoc)
* @see org.apache.hadoop.mapreduce.Mapper#setup(org.apache.hadoop.mapreduce.Mapper.Context)
*/
protected void setup(Context context) throws IOException, InterruptedException {
fieldDelim = context.getConfiguration().get("field.delim", "[]");
fieldDelimRegex = context.getConfiguration().get("field.delim.regex", "\\[\\]");
consolidateFields = context.getConfiguration().getBoolean("consolidate.field", false);
String textFields = context.getConfiguration().get("text.field.ordinals", "");
String[] items = textFields.toString().split(",");
for (int i = 0; i < items.length; ++i) {
textFieldOrdinals.add(Integer.parseInt(items[i]));
}
analyzer = new StandardAnalyzer(Version.LUCENE_35);
Configuration conf = context.getConfiguration();
String filePath = conf.get("raw.schema.file.path");
FileSystem dfs = FileSystem.get(conf);
Path src = new Path(filePath);
FSDataInputStream fs = dfs.open(src);
ObjectMapper mapper = new ObjectMapper();
schema = mapper.readValue(fs, SingleTypeSchema.class);
for (Field field : schema.getEntity().getFields()) {
retainedFieldOrdinals.add(field.getOrdinal());
}
}