jacques-n commented on a change in pull request #2572:
URL: https://github.com/apache/calcite/pull/2572#discussion_r747009579
##########
File path: file/src/main/java/org/apache/calcite/adapter/file/CsvEnumerator.java
##########
@@ -130,30 +137,70 @@ public static RelDataType deduceRowType(JavaTypeFactory
typeFactory,
}
for (String string : strings) {
final String name;
- final CsvFieldType fieldType;
+ final RelDataType fieldType;
final int colon = string.indexOf(':');
if (colon >= 0) {
name = string.substring(0, colon);
String typeString = string.substring(colon + 1);
- fieldType = CsvFieldType.of(typeString);
- if (fieldType == null) {
- System.out.println("WARNING: Found unknown type: "
- + typeString + " in file: " + source.path()
- + " for column: " + name
- + ". Will assume the type of column is string");
+ Matcher decimalMatcher = DECIMAL_TYPE_PATTERN.matcher(typeString);
+ if (decimalMatcher.matches()) {
+ int precision = Integer.parseInt(decimalMatcher.group(1));
+ int scale = Integer.parseInt(decimalMatcher.group(2));
+ fieldType = parseDecimalSqlType(typeFactory, precision, scale);
+ } else {
+ switch (typeString) {
+ case "string":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.VARCHAR);
+ break;
+ case "boolean":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.BOOLEAN);
+ break;
+ case "byte":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.TINYINT);
+ break;
+ case "char":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.CHAR);
+ break;
+ case "short":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.SMALLINT);
+ break;
+ case "int":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.INTEGER);
+ break;
+ case "long":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.BIGINT);
+ break;
+ case "float":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.REAL);
+ break;
+ case "double":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.DOUBLE);
+ break;
+ case "date":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.DATE);
+ break;
+ case "timestamp":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.TIMESTAMP);
+ break;
+ case "time":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.TIME);
+ break;
+ default:
+ LOGGER.warn(
+ String.format(Locale.ROOT,
+ "Found unknown type: %s in file: %s for column: %s. Will
assume the type of "
Review comment:
when using a logger, you should use the loggers capability for value
replacement as opposed to string format.
##########
File path: file/src/main/java/org/apache/calcite/adapter/file/CsvEnumerator.java
##########
@@ -130,30 +137,70 @@ public static RelDataType deduceRowType(JavaTypeFactory
typeFactory,
}
for (String string : strings) {
final String name;
- final CsvFieldType fieldType;
+ final RelDataType fieldType;
final int colon = string.indexOf(':');
if (colon >= 0) {
name = string.substring(0, colon);
String typeString = string.substring(colon + 1);
- fieldType = CsvFieldType.of(typeString);
- if (fieldType == null) {
- System.out.println("WARNING: Found unknown type: "
- + typeString + " in file: " + source.path()
- + " for column: " + name
- + ". Will assume the type of column is string");
+ Matcher decimalMatcher = DECIMAL_TYPE_PATTERN.matcher(typeString);
+ if (decimalMatcher.matches()) {
+ int precision = Integer.parseInt(decimalMatcher.group(1));
+ int scale = Integer.parseInt(decimalMatcher.group(2));
+ fieldType = parseDecimalSqlType(typeFactory, precision, scale);
+ } else {
+ switch (typeString) {
+ case "string":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.VARCHAR);
+ break;
+ case "boolean":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.BOOLEAN);
+ break;
+ case "byte":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.TINYINT);
+ break;
+ case "char":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.CHAR);
+ break;
+ case "short":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.SMALLINT);
+ break;
+ case "int":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.INTEGER);
+ break;
+ case "long":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.BIGINT);
+ break;
+ case "float":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.REAL);
+ break;
+ case "double":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.DOUBLE);
+ break;
+ case "date":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.DATE);
+ break;
+ case "timestamp":
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.TIMESTAMP);
+ break;
+ case "time":
+ fieldType = toNullableRelDataType(typeFactory, SqlTypeName.TIME);
+ break;
+ default:
+ LOGGER.warn(
+ String.format(Locale.ROOT,
+ "Found unknown type: %s in file: %s for column: %s. Will
assume the type of "
+ + "column is string.",
+ typeString, source.path(), name));
+ fieldType = toNullableRelDataType(typeFactory,
SqlTypeName.VARCHAR);
Review comment:
Shouldn't you set a max length on this varchar? (same for the one below)
##########
File path: file/src/main/java/org/apache/calcite/adapter/file/CsvEnumerator.java
##########
@@ -314,22 +371,55 @@ static CSVReader openCsv(Source source) throws
IOException {
} catch (ParseException e) {
return null;
}
- case STRING:
+ case VARCHAR:
default:
return string;
}
}
}
+ private static RelDataType parseDecimalSqlType(JavaTypeFactory typeFactory,
int precision,
+ int scale) {
+ if (scale < 0) {
Review comment:
It seems like you should do some other checks here as well. For example,
can precision be negative? What are the requirements for a relationship between
precision and scale?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
