use of org.talend.dataprep.api.type.Type in project data-prep by Talend.
the class QualityAnalysisTest method TDP_1150_full.
/**
* This test ensures that data types have been rightly detected when performing a full analysis.
*
* See <a href="https://jira.talendforge.org/browse/TDP-224">https://jira.talendforge.org/browse/TDP-1150</a>.
*
* @throws Exception
*/
@Test
public void TDP_1150_full() {
// given
String[] expectedNames = { //
"string_boolean", //
"double_integer", //
"string_integer", //
"string_double", //
"string_date", //
"type_mix", //
"boolean", //
"integer", //
"double", //
"date", //
"string", //
"empty" };
Type[] expectedTypes = { //
Type.BOOLEAN, //
Type.DOUBLE, //
Type.INTEGER, //
Type.DOUBLE, //
Type.DATE, //
Type.STRING, //
Type.BOOLEAN, //
Type.INTEGER, //
Type.DOUBLE, //
Type.DATE, //
Type.STRING, //
Type.STRING };
// when
final DataSetMetadata actual = initializeDataSetMetadata(DataSetServiceTest.class.getResourceAsStream("../invalids_and_type_detection.csv"));
// then
assertThat(actual.getLifecycle().schemaAnalyzed(), is(true));
for (int i = 0; i < expectedTypes.length; i++) {
ColumnMetadata column = actual.getRowMetadata().getColumns().get(i);
assertThat(column.getName(), is(expectedNames[i]));
assertThat("column '" + column.getName() + "' is expected to be detected as '" + expectedTypes[i] + "' but was found as '" + column.getType() + //
"'", //
column.getType(), //
is(expectedTypes[i].getName()));
}
}
use of org.talend.dataprep.api.type.Type in project data-prep by Talend.
the class QualityAnalysisTest method TDP_1150_integer_must_be_detected_as_so_even_if_sampling_detects_text.
/**
* This test ensures that data types have been rightly detected when performing a full analysis.
*
* See <a href="https://jira.talendforge.org/browse/TDP-224">https://jira.talendforge.org/browse/TDP-1150</a>.
*
* @throws Exception
*/
@Test
public void TDP_1150_integer_must_be_detected_as_so_even_if_sampling_detects_text() {
final DataSetMetadata actual = initializeDataSetMetadata(DataSetServiceTest.class.getResourceAsStream("../valid_must_be_integer.csv"));
assertThat(actual.getLifecycle().schemaAnalyzed(), is(true));
String expectedName = "user_id";
Type expectedType = Type.INTEGER;
ColumnMetadata column = actual.getRowMetadata().getColumns().get(0);
assertThat(column.getName(), is(expectedName));
assertThat(column.getType(), is(expectedType.getName()));
}
use of org.talend.dataprep.api.type.Type in project data-prep by Talend.
the class SchemaAnalysisTest method testTDP_1674.
/**
* See <a href="https://jira.talendforge.org/browse/TDP-1674">TDP-1674_error_with_ipv6_addresses</a>.
*/
@Test
public void testTDP_1674() {
final DataSetMetadata actual = initializeDataSetMetadata(DataSetServiceTest.class.getResourceAsStream("../ipv6.csv"));
assertThat(actual.getLifecycle().schemaAnalyzed(), is(true));
String[] expectedNames = { "number", "description", "address" };
Type[] expectedTypes = { Type.INTEGER, Type.STRING, Type.STRING };
int i = 0;
for (ColumnMetadata column : actual.getRowMetadata().getColumns()) {
assertThat(column.getName(), is(expectedNames[i]));
assertThat(column.getType(), is(expectedTypes[i].getName()));
i++;
}
assertThat("IPv6 Address", is(actual.getRowMetadata().getColumns().get(2).getDomainLabel()));
}
use of org.talend.dataprep.api.type.Type in project data-prep by Talend.
the class SchemaAnalysisTest method testTDP_224.
/**
* See <a href="https://jira.talendforge.org/browse/TDP-224">https://jira.talendforge.org/browse/TDP-224</a>.
*
* @throws Exception
*/
@Test
public void testTDP_224() {
final DataSetMetadata actual = initializeDataSetMetadata(DataSetServiceTest.class.getResourceAsStream("../whatever.xls"));
assertThat(actual.getLifecycle().schemaAnalyzed(), is(true));
// Not a typo: this is what QA provided as column name.
String[] expectedNames = { "whaterver" };
Type[] expectedTypes = { Type.STRING };
int i = 0;
int j = 0;
for (ColumnMetadata column : actual.getRowMetadata().getColumns()) {
assertThat(column.getName(), is(expectedNames[i++]));
assertThat(column.getType(), is(expectedTypes[j++].getName()));
}
}
use of org.talend.dataprep.api.type.Type in project data-prep by Talend.
the class SchemaAnalysisTest method testTDP_226.
/**
* See <a href="https://jira.talendforge.org/browse/TDP-226">https://jira.talendforge.org/browse/TDP-226</a>.
*
* @throws Exception
*/
@Test
public void testTDP_226() {
final DataSetMetadata actual = initializeDataSetMetadata(DataSetServiceTest.class.getResourceAsStream("../empty_lines.csv"));
assertThat(actual.getLifecycle().schemaAnalyzed(), is(true));
String[] expectedNames = { "id", "firstname", "lastname", "age", "date-of-birth", "alive" };
Type[] expectedTypes = { Type.INTEGER, Type.STRING, Type.STRING, Type.INTEGER, Type.DATE, Type.BOOLEAN };
int i = 0;
for (ColumnMetadata column : actual.getRowMetadata().getColumns()) {
assertThat(column.getName(), is(expectedNames[i]));
assertThat(column.getType(), is(expectedTypes[i].getName()));
i++;
}
}
Aggregations