[CALCITE-6814] Support weekofyear fucntions for Hive

core/src/main/java/org/apache/calcite/adapter/enumerable/RexImpTable.java

@@ -337,6 +337,7 @@
 import static org.apache.calcite.sql.fun.SqlLibraryOperators.UNIX_SECONDS;
 import static org.apache.calcite.sql.fun.SqlLibraryOperators.URL_DECODE;
 import static org.apache.calcite.sql.fun.SqlLibraryOperators.URL_ENCODE;
+import static org.apache.calcite.sql.fun.SqlLibraryOperators.WEEKOFYEAR;
 import static org.apache.calcite.sql.fun.SqlLibraryOperators.XML_TRANSFORM;
 import static org.apache.calcite.sql.fun.SqlStdOperatorTable.ABS;
 import static org.apache.calcite.sql.fun.SqlStdOperatorTable.ACOS;
@@ -528,7 +529,7 @@
 import static org.apache.calcite.sql.fun.SqlStdOperatorTable.UNARY_PLUS;
 import static org.apache.calcite.sql.fun.SqlStdOperatorTable.UPPER;
 import static org.apache.calcite.sql.fun.SqlStdOperatorTable.USER;
-import static org.apache.calcite.sql.fun.SqlStdOperatorTable.VARIANTNULL;
+import static org.apache.calcite.sql.fun.SqlStdOperatorTable.VARIANTNULL;;
 import static org.apache.calcite.util.ReflectUtil.isStatic;
 
 import static java.util.Objects.requireNonNull;
@@ -960,6 +961,8 @@ void populate2() {
           BuiltInMethod.DATE_FROM_UNIX_DATE.method, NullPolicy.STRICT);
       defineMethod(UNIX_DATE, BuiltInMethod.UNIX_DATE.method,
           NullPolicy.STRICT);
+      defineMethod(WEEKOFYEAR, BuiltInMethod.WEEK_OF_YEAR.method,
+          NullPolicy.STRICT);
 
       // Datetime constructors
       defineMethod(DATE, BuiltInMethod.DATE.method, NullPolicy.STRICT);

core/src/main/java/org/apache/calcite/runtime/SqlFunctions.java

@@ -93,19 +93,10 @@
 import java.text.Normalizer;
 import java.text.ParsePosition;
 import java.text.SimpleDateFormat;
-import java.time.Instant;
-import java.time.LocalDate;
-import java.time.LocalDateTime;
-import java.time.LocalTime;
-import java.time.OffsetDateTime;
-import java.time.ZoneId;
-import java.time.ZoneOffset;
-import java.time.ZonedDateTime;
-import java.time.format.DateTimeFormatter;
-import java.time.format.DateTimeFormatterBuilder;
-import java.time.format.DateTimeParseException;
-import java.time.format.SignStyle;
+import java.time.*;
+import java.time.format.*;
 import java.time.temporal.ChronoField;
+import java.time.temporal.TemporalAccessor;
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Base64;
@@ -114,6 +105,7 @@
 import java.util.Collections;
 import java.util.Comparator;
 import java.util.Date;
+import java.util.GregorianCalendar;
 import java.util.HashMap;
 import java.util.HashSet;
 import java.util.LinkedHashMap;
@@ -134,6 +126,8 @@
 import java.util.regex.Pattern;
 import java.util.regex.PatternSyntaxException;
 
+import static java.time.temporal.ChronoField.*;
+
 import static org.apache.calcite.config.CalciteSystemProperty.FUNCTION_LEVEL_CACHE_MAX_SIZE;
 import static org.apache.calcite.linq4j.Nullness.castNonNull;
 import static org.apache.calcite.util.Static.RESOURCE;
@@ -5514,6 +5508,56 @@ public static String dayNameWithDate(int date, Locale locale) {
         .format(ROOT_DAY_FORMAT.withLocale(locale));
   }
 
+  /**
+   * SQL {@code WEEKOFYEAR} function, applied to a String argument.
+   *
+   * @param date string of date
+   * @return The week of the year of the given date
+   */
+  public static @Nullable Integer weekOfYear(String date) {
+    GregorianCalendar calendar = new GregorianCalendar(TimeZone.getTimeZone("UTC"));
+    calendar.setGregorianChange(new Date(Long.MIN_VALUE));
+    calendar.setFirstDayOfWeek(Calendar.MONDAY);
+    calendar.setMinimalDaysInFirstWeek(4);
+    try {
+      LocalDate localDate = valueOf(date.trim());
+      calendar.setTimeInMillis(localDate.atStartOfDay().toInstant(ZoneOffset.UTC).toEpochMilli());
+      return calendar.get(Calendar.WEEK_OF_YEAR);
+    } catch (DateTimeParseException | IllegalArgumentException e) {
+      return null;
+    }
+  }
+
+  /**
+   * Obtains an instance of Date from a text string such as 2021-02-22T09:39:27.
+   * Other supported formats are "2021-02-22T09:39:27Z", "2021-02-22 09:39:27",
+   * "2021-02-22T09:39:27+00:00", "2021-02-22". Any time information is simply
+   * dropped.
+   *
+   * @param text the text to parse, not null
+   * @return The {@code LocalDate} objects parsed from the text
+   * @throws IllegalArgumentException if the text cannot be parsed into a
+   *           {@code Date}
+   * @throws NullPointerException if {@code text} is null
+   */
+  public static LocalDate valueOf(final String text) {
+    String s = Objects.requireNonNull(text).trim();
+    ParsePosition pos = new ParsePosition(0);
+    try {
+      DateTimeFormatter PARSE_FORMATTER =
+          new DateTimeFormatterBuilder().appendValue(YEAR, 1, 10, SignStyle.NORMAL).appendLiteral('-')
+              .appendValue(MONTH_OF_YEAR, 1, 2, SignStyle.NORMAL).appendLiteral('-')
+              .appendValue(DAY_OF_MONTH, 1, 2, SignStyle.NORMAL).toFormatter().withResolverStyle(ResolverStyle.STRICT);
+      TemporalAccessor t = PARSE_FORMATTER.parseUnresolved(s, pos);
+      if (pos.getErrorIndex() >= 0) {
+        throw new DateTimeParseException("Text could not be parsed to date", s, pos.getErrorIndex());
+      }
+      return LocalDate.of(t.get(YEAR), t.get(MONTH_OF_YEAR), t.get(DAY_OF_MONTH));
+    } catch (DateTimeException e) {
+      throw new IllegalArgumentException("Cannot create date, parsing error");
+    }
+  }
+
   /**
    * SQL {@code MONTHNAME} function, applied to a TIMESTAMP argument.
    *

core/src/main/java/org/apache/calcite/sql/fun/SqlLibraryOperators.java

@@ -166,6 +166,14 @@ private SqlLibraryOperators() {
           OperandTypes.family(SqlTypeFamily.ANY, SqlTypeFamily.DATE,
               SqlTypeFamily.DATE));
 
+  /** The "WEEKOFYEAR(datetime)" function
+   * (HIVE) return the week of the year of the given date. */
+  @LibraryOperator(libraries = {HIVE})
+  public static final SqlFunction WEEKOFYEAR =
+      SqlBasicFunction.create("WEEKOFYEAR",
+          ReturnTypes.INTEGER_FORCE_NULLABLE,
+          OperandTypes.STRING, SqlFunctionCategory.TIMEDATE);
+
   /** The "CONVERT(type, expr [,style])" function (Microsoft SQL Server).
    *
    * <p>Syntax:

core/src/main/java/org/apache/calcite/sql/type/ReturnTypes.java

@@ -480,6 +480,13 @@ public static SqlCall stripSeparator(SqlCall call) {
   public static final SqlReturnTypeInference INTEGER_NULLABLE =
       INTEGER.andThen(SqlTypeTransforms.TO_NULLABLE);
 
+  /**
+   * Type-inference strategy whereby the result type of a call is a nullable
+   * INT.
+   */
+  public static final SqlReturnTypeInference INTEGER_FORCE_NULLABLE =
+      INTEGER.andThen(SqlTypeTransforms.FORCE_NULLABLE);
+
   /**
    * Type-inference strategy whereby the result type of a call is a BIGINT.
    */

core/src/main/java/org/apache/calcite/util/BuiltInMethod.java

@@ -443,6 +443,7 @@ public enum BuiltInMethod {
   SHA256(SqlFunctions.class, "sha256", String.class),
   SHA512(SqlFunctions.class, "sha512", String.class),
   THROW_UNLESS(SqlFunctions.class, "throwUnless", boolean.class, String.class),
+  WEEK_OF_YEAR(SqlFunctions.class, "weekOfYear", String.class),
   COMPRESS(CompressionFunctions.class, "compress", String.class),
   URL_DECODE(UrlFunctions.class, "urlDecode", String.class),
   URL_ENCODE(UrlFunctions.class, "urlEncode", String.class),

site/_docs/reference.md

@@ -1480,31 +1480,31 @@ Not implemented:
 
 ### Date/time functions
 
-| Operator syntax           | Description
-|:------------------------- |:-----------
-| LOCALTIME                 | Returns the current date and time in the session time zone in a value of datatype TIME
-| LOCALTIME(precision)      | Returns the current date and time in the session time zone in a value of datatype TIME, with *precision* digits of precision
-| LOCALTIMESTAMP            | Returns the current date and time in the session time zone in a value of datatype TIMESTAMP
-| LOCALTIMESTAMP(precision) | Returns the current date and time in the session time zone in a value of datatype TIMESTAMP, with *precision* digits of precision
-| CURRENT_TIME              | Returns the current time in the session time zone, in a value of datatype TIMESTAMP WITH TIME ZONE
-| CURRENT_DATE              | Returns the current date in the session time zone, in a value of datatype DATE
-| CURRENT_TIMESTAMP         | Returns the current date and time in the session time zone, in a value of datatype TIMESTAMP WITH TIME ZONE
-| EXTRACT(timeUnit FROM datetime) | Extracts and returns the value of a specified datetime field from a datetime value expression
-| FLOOR(datetime TO timeUnit) | Rounds *datetime* down to *timeUnit*
-| CEIL(datetime TO timeUnit) | Rounds *datetime* up to *timeUnit*
-| YEAR(date)                | Equivalent to `EXTRACT(YEAR FROM date)`. Returns an integer.
-| QUARTER(date)             | Equivalent to `EXTRACT(QUARTER FROM date)`. Returns an integer between 1 and 4.
-| MONTH(date)               | Equivalent to `EXTRACT(MONTH FROM date)`. Returns an integer between 1 and 12.
-| WEEK(date)                | Equivalent to `EXTRACT(WEEK FROM date)`. Returns an integer between 1 and 53.
-| DAYOFYEAR(date)           | Equivalent to `EXTRACT(DOY FROM date)`. Returns an integer between 1 and 366.
-| DAYOFMONTH(date)          | Equivalent to `EXTRACT(DAY FROM date)`. Returns an integer between 1 and 31.
-| DAYOFWEEK(date)           | Equivalent to `EXTRACT(DOW FROM date)`. Returns an integer between 1 and 7.
-| HOUR(date)                | Equivalent to `EXTRACT(HOUR FROM date)`. Returns an integer between 0 and 23.
-| MINUTE(date)              | Equivalent to `EXTRACT(MINUTE FROM date)`. Returns an integer between 0 and 59.
-| SECOND(date)              | Equivalent to `EXTRACT(SECOND FROM date)`. Returns an integer between 0 and 59.
-| TIMESTAMPADD(timeUnit, integer, datetime) | Returns *datetime* with an interval of (signed) *integer* *timeUnit*s added. Equivalent to `datetime + INTERVAL 'integer' timeUnit`
+| Operator syntax                              | Description
+|:---------------------------------------------|:-----------
+| LOCALTIME                                    | Returns the current date and time in the session time zone in a value of datatype TIME
+| LOCALTIME(precision)                         | Returns the current date and time in the session time zone in a value of datatype TIME, with *precision* digits of precision
+| LOCALTIMESTAMP                               | Returns the current date and time in the session time zone in a value of datatype TIMESTAMP
+| LOCALTIMESTAMP(precision)                    | Returns the current date and time in the session time zone in a value of datatype TIMESTAMP, with *precision* digits of precision
+| CURRENT_TIME                                 | Returns the current time in the session time zone, in a value of datatype TIMESTAMP WITH TIME ZONE
+| CURRENT_DATE                                 | Returns the current date in the session time zone, in a value of datatype DATE
+| CURRENT_TIMESTAMP                            | Returns the current date and time in the session time zone, in a value of datatype TIMESTAMP WITH TIME ZONE
+| EXTRACT(timeUnit FROM datetime)              | Extracts and returns the value of a specified datetime field from a datetime value expression
+| FLOOR(datetime TO timeUnit)                  | Rounds *datetime* down to *timeUnit*
+| CEIL(datetime TO timeUnit)                   | Rounds *datetime* up to *timeUnit*
+| YEAR(date)                                   | Equivalent to `EXTRACT(YEAR FROM date)`. Returns an integer.
+| QUARTER(date)                                | Equivalent to `EXTRACT(QUARTER FROM date)`. Returns an integer between 1 and 4.
+| MONTH(date)                                  | Equivalent to `EXTRACT(MONTH FROM date)`. Returns an integer between 1 and 12.
+| WEEK(date)                                   | Equivalent to `EXTRACT(WEEK FROM date)`. Returns an integer between 1 and 53.
+| DAYOFYEAR(date)                              | Equivalent to `EXTRACT(DOY FROM date)`. Returns an integer between 1 and 366.
+| DAYOFMONTH(date)                             | Equivalent to `EXTRACT(DAY FROM date)`. Returns an integer between 1 and 31.
+| DAYOFWEEK(date)                              | Equivalent to `EXTRACT(DOW FROM date)`. Returns an integer between 1 and 7.
+| HOUR(date)                                   | Equivalent to `EXTRACT(HOUR FROM date)`. Returns an integer between 0 and 23.
+| MINUTE(date)                                 | Equivalent to `EXTRACT(MINUTE FROM date)`. Returns an integer between 0 and 59.
+| SECOND(date)                                 | Equivalent to `EXTRACT(SECOND FROM date)`. Returns an integer between 0 and 59.
+| TIMESTAMPADD(timeUnit, integer, datetime)    | Returns *datetime* with an interval of (signed) *integer* *timeUnit*s added. Equivalent to `datetime + INTERVAL 'integer' timeUnit`
 | TIMESTAMPDIFF(timeUnit, datetime, datetime2) | Returns the (signed) number of *timeUnit* intervals between *datetime* and *datetime2*. Equivalent to `(datetime2 - datetime) timeUnit`
-| LAST_DAY(date)            | Returns the date of the last day of the month in a value of datatype DATE; For example, it returns DATE'2020-02-29' for both DATE'2020-02-10' and TIMESTAMP'2020-02-10 10:10:10'
+| LAST_DAY(date)                               | Returns the date of the last day of the month in a value of datatype DATE; For example, it returns DATE'2020-02-29' for both DATE'2020-02-10' and TIMESTAMP'2020-02-10 10:10:10'
 
 Calls to niladic functions such as `CURRENT_DATE` do not accept parentheses in
 standard SQL. Calls with parentheses, such as `CURRENT_DATE()` are accepted in certain
@@ -3032,6 +3032,7 @@ In the following:
 | b s | UNIX_DATE(date)                              | Returns the number of days since 1970-01-01
 | s | URL_DECODE(string)                             | Decodes a *string* in 'application/x-www-form-urlencoded' format using a specific encoding scheme, returns original *string* when decoded error
 | s | URL_ENCODE(string)                             | Translates a *string* into 'application/x-www-form-urlencoded' format using a specific encoding scheme
+| h | WEEKOFYEAR(string)                             | Returns the week of the year of the given date, from 1 to 54
 | o | XMLTRANSFORM(xml, xslt)                        | Applies XSLT transform *xslt* to XML string *xml* and returns the result
 
 Note:

testkit/src/main/java/org/apache/calcite/test/SqlOperatorTest.java

@@ -5559,6 +5559,28 @@ void testBitGetFunc(SqlOperatorFixture f, String functionName) {
     f0.forEachLibrary(libraries, consumer);
   }
 
+  /** Test case for
+   * <a href="https://issues.apache.org/jira/browse/CALCITE-6814">[CALCITE-6814]
+   * Add base64 function (enabled in Hive library)</a>. */
+  @Test void testWeekOfYear() {
+    final SqlOperatorFixture f0 = fixture().setFor(SqlLibraryOperators.WEEKOFYEAR);
+    final Consumer<SqlOperatorFixture> consumer = f -> {
+      f.checkString("weekofyear('2022-02-01')",
+          "5",
+          "INTEGER");
+      f.checkString("weekofyear('2022-02-01 22:21:23')",
+          "5",
+          "INTEGER");
+      f.checkNull("weekofyear(NULL)");
+      f.checkNull("weekofyear('2022-22-01')");
+      f.checkNull("weekofyear('aawwss')");
+      f.checkNull("weekofyear('2022')");
+    };
+    final List<SqlLibrary> libraries =
+        list(SqlLibrary.HIVE);
+    f0.forEachLibrary(libraries, consumer);
+  }
+
   @Test void testToDatePg() {
     final SqlOperatorFixture f = fixture().withLibrary(SqlLibrary.POSTGRESQL)
         .setFor(SqlLibraryOperators.TO_DATE_PG);