doc: links for some functions

Some functions scaladoc issue --> hablapps#135
eruizalo · Jan 10, 2022 · 7d59780 · 7d59780
1 parent 9b57a58
commit 7d59780
Show file tree

Hide file tree

Showing 4 changed files with 37 additions and 45 deletions.
diff --git a/core/src/main/scala/doric/syntax/BooleanColumns.scala b/core/src/main/scala/doric/syntax/BooleanColumns.scala
@@ -67,7 +67,7 @@ private[syntax] trait BooleanColumns {
       *
       * @throws java.lang.RuntimeException if the condition is false
       * @group Boolean Type
-      * @see [[org.apache.spark.sql.functions.assert_true]]
+      * @see [[org.apache.spark.sql.functions.assert_true(c:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.assert_true]]
       */
     def assertTrue: NullColumn = column.elem.map(f.assert_true).toDC
 
@@ -76,7 +76,7 @@ private[syntax] trait BooleanColumns {
       *
       * @throws java.lang.RuntimeException if the condition is false
       * @group Boolean Type
-      * @see [[org.apache.spark.sql.functions.assert_true]]
+      * @see [[org.apache.spark.sql.functions.assert_true(c:org\.apache\.spark\.sql\.Column,e:* org.apache.spark.sql.functions.assert_true]]
       */
     def assertTrue(msg: StringColumn): NullColumn =
       (column.elem, msg.elem).mapN(f.assert_true).toDC

diff --git a/core/src/main/scala/doric/syntax/DateColumns.scala b/core/src/main/scala/doric/syntax/DateColumns.scala
@@ -33,7 +33,7 @@ private[syntax] trait DateColumns {
       *   Date column after adding months
       * @note
       *   Timestamp columns will be truncated to Date column
-      * @see [[org.apache.spark.sql.functions.add_months]]
+      * @see [[org.apache.spark.sql.functions.add_months(startDate:org\.apache\.spark\.sql\.Column,numMonths:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.add_months]]
       */
     def addMonths(nMonths: IntegerColumn): DateColumn =
       (column.elem, nMonths.elem).mapN(f.add_months).toDC
@@ -46,7 +46,7 @@ private[syntax] trait DateColumns {
       * @note
       *   Timestamp columns will be truncated to Date column
       * @group Date & Timestamp Type
-      * @see [[org.apache.spark.sql.functions.date_add]]
+      * @see [[org.apache.spark.sql.functions.date_add(start:org\.apache\.spark\.sql\.Column,days:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.date_add]]
       */
     def addDays(days: IntegerColumn): DateColumn =
       (column.elem, days.elem).mapN(f.date_add).toDC
@@ -79,7 +79,7 @@ private[syntax] trait DateColumns {
       * @note
       *   Timestamp columns will be truncated to Date column
       * @group Date & Timestamp Type
-      * @see [[org.apache.spark.sql.functions.date_sub]]
+      * @see [[org.apache.spark.sql.functions.date_sub(start:org\.apache\.spark\.sql\.Column,days:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.date_sub]]
       */
     def subDays(days: IntegerColumn): DateColumn =
       (column.elem, days.elem).mapN(f.date_sub).toDC
@@ -164,7 +164,7 @@ private[syntax] trait DateColumns {
       * @param dateCol
       *   Date or Timestamp column
       * @group Date & Timestamp Type
-      * @see [[org.apache.spark.sql.functions.months_between]]
+      * @see [[org.apache.spark.sql.functions.months_between(end:org\.apache\.spark\.sql\.Column,start:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.months_between]]
       */
     def monthsBetween(dateCol: DoricColumn[T]): DoubleColumn =
       (column.elem, dateCol.elem).mapN(f.months_between).toDC
@@ -178,7 +178,7 @@ private[syntax] trait DateColumns {
       *   If `roundOff` is set to true, the result is rounded off to 8 digits;
       *   it is not rounded otherwise.
       * @group Date & Timestamp Type
-      * @see [[org.apache.spark.sql.functions.months_between]]
+      * @see [[org.apache.spark.sql.functions.months_between(end:org\.apache\.spark\.sql\.Column,start:org\.apache\.spark\.sql\.Column,roundOff:* org.apache.spark.sql.functions.months_between]]
       */
     def monthsBetween(
         dateCol: DoricColumn[T],
@@ -260,7 +260,7 @@ private[syntax] trait DateColumns {
       *   A long
       *
       * @group Date & Timestamp Type
-      * @see [[org.apache.spark.sql.functions.unix_timestamp]]
+      * @see [[org.apache.spark.sql.functions.unix_timestamp(s:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.unix_timestamp]]
       */
     def unixTimestamp: LongColumn = column.elem.map(f.unix_timestamp).toDC
 
@@ -287,15 +287,15 @@ private[syntax] trait DateColumns {
       * Transform date to timestamp
       *
       * @group Date Type
-      * @see [[org.apache.spark.sql.functions.to_timestamp]]
+      * @see [[org.apache.spark.sql.functions.to_timestamp(s:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.to_timestamp]]
       */
     def toTimestamp: TimestampColumn = column.elem.map(f.to_timestamp).toDC
 
     /**
       * Transform date to Instant
       *
       * @group Date Type
-      * @see [[org.apache.spark.sql.functions.to_timestamp]]
+      * @see [[org.apache.spark.sql.functions.to_timestamp(s:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.to_timestamp]]
       */
     def toInstant: InstantColumn = column.elem.map(f.to_timestamp).toDC
   }

diff --git a/core/src/main/scala/doric/syntax/StringColumns.scala b/core/src/main/scala/doric/syntax/StringColumns.scala
@@ -170,7 +170,8 @@ private[syntax] trait StringColumns {
       * @note
       *   The position is not zero based, but 1 based index. returns 0 if substr
       *   could not be found in str.
-      * @see [[org.apache.spark.sql.functions.locate]]
+      * @see org.apache.spark.sql.functions.locate
+      * @todo scaladoc link (issue #135)
       */
     def locate(
         substr: StringColumn,
@@ -209,7 +210,7 @@ private[syntax] trait StringColumns {
       * Trim the spaces from left end for the specified string value.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.ltrim]]
+      * @see [[org.apache.spark.sql.functions.ltrim(e:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.ltrim]]
       */
     def ltrim: StringColumn = s.elem.map(f.ltrim).toDC
 
@@ -218,7 +219,7 @@ private[syntax] trait StringColumns {
       * string column.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.ltrim]]
+      * @see [[org.apache.spark.sql.functions.ltrim(e:org\.apache\.spark\.sql\.Column,trimString:* org.apache.spark.sql.functions.ltrim]]
       */
     def ltrim(trimString: StringColumn): StringColumn =
       (s.elem, trimString.elem)
@@ -232,7 +233,7 @@ private[syntax] trait StringColumns {
       * byte position `pos` of `src` and proceeding for `len` bytes.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.overlay]]
+      * @see [[org.apache.spark.sql.functions.overlay(src:org\.apache\.spark\.sql\.Column,replace:org\.apache\.spark\.sql\.Column,pos:org\.apache\.spark\.sql\.Column,len:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.overlay]]
       */
     def overlay(
         replace: StringColumn,
@@ -267,7 +268,7 @@ private[syntax] trait StringColumns {
       * with replacement.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.regexp_replace]]
+      * @see [[org.apache.spark.sql.functions.regexp_replace(e:org\.apache\.spark\.sql\.Column,pattern:org\.apache\.spark\.sql\.Column,* org.apache.spark.sql.functions.regexp_replace]]
       */
     def regexpReplace(
         pattern: StringColumn,
@@ -302,7 +303,7 @@ private[syntax] trait StringColumns {
       * Trim the spaces from right end for the specified string value.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.rtrim]]
+      * @see [[org.apache.spark.sql.functions.rtrim(e:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.rtrim]]
       */
     def rtrim: StringColumn = s.elem.map(f.rtrim).toDC
 
@@ -311,7 +312,7 @@ private[syntax] trait StringColumns {
       * string column.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.rtrim]]
+      * @see [[org.apache.spark.sql.functions.rtrim(e:org\.apache\.spark\.sql\.Column,trimString:* org.apache.spark.sql.functions.rtrim]]
       */
     def rtrim(trimString: StringColumn): StringColumn =
       (s.elem, trimString.elem)
@@ -326,19 +327,6 @@ private[syntax] trait StringColumns {
       */
     def soundex: StringColumn = s.elem.map(f.soundex).toDC
 
-    /**
-      * Splits str around matches of the given pattern.
-      *
-      * @param pattern
-      *   a string representing a regular expression. The regex string should be
-      *   a Java regular expression.
-      *
-      * @group String Type
-      * @see [[org.apache.spark.sql.functions.split]]
-      */
-    def split(pattern: StringColumn): ArrayColumn[String] =
-      split(pattern, (-1).lit)
-
     /**
       * Splits str around matches of the given pattern.
       *
@@ -353,10 +341,12 @@ private[syntax] trait StringColumns {
       *       contain all input beyond the last matched regex.
       *     - __limit less than or equal to 0__: `regex` will be applied as many times as possible,
       *       and the resulting array can be of any size.
+      * @see org.apache.spark.sql.functions.split
+      * @todo scaladoc link (issue #135)
       */
     def split(
         pattern: StringColumn,
-        limit: IntegerColumn
+        limit: IntegerColumn = (-1).lit
     ): ArrayColumn[String] =
       (s.elem, pattern.elem, limit.elem)
         .mapN((str, p, l) => new Column(StringSplit(str.expr, p.expr, l.expr)))
@@ -421,7 +411,7 @@ private[syntax] trait StringColumns {
       * Trim the spaces from both ends for the specified string column.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.trim]]
+      * @see [[org.apache.spark.sql.functions.trim(e:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.trim]]
       */
     def trim: StringColumn = s.elem.map(f.trim).toDC
 
@@ -430,7 +420,7 @@ private[syntax] trait StringColumns {
       * column (literal).
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.trim]]
+      * @see [[org.apache.spark.sql.functions.trim(e:org\.apache\.spark\.sql\.Column,trimString:* org.apache.spark.sql.functions.trim]]
       */
     def trim(trimString: StringColumn): StringColumn =
       (s.elem, trimString.elem)
@@ -467,7 +457,7 @@ private[syntax] trait StringColumns {
       * String ends with. Returns a boolean column based on a string match.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.Column.endsWith]]
+      * @see [[org.apache.spark.sql.Column.endsWith(other:* org.apache.spark.sql.Column.endsWith]]
       */
     def endsWith(dc: StringColumn): BooleanColumn =
       (s.elem, dc.elem).mapN(_.endsWith(_)).toDC
@@ -499,7 +489,7 @@ private[syntax] trait StringColumns {
       * String starts with. Returns a boolean column based on a string match.
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.Column.startsWith]]
+      * @see [[org.apache.spark.sql.Column.startsWith(other:* org.apache.spark.sql.Column.startsWith]]
       */
     def startsWith(dc: StringColumn): BooleanColumn =
       (s.elem, dc.elem).mapN(_.startsWith(_)).toDC
@@ -547,7 +537,7 @@ private[syntax] trait StringColumns {
       *   A long
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.unix_timestamp]]
+      * @see [[org.apache.spark.sql.functions.unix_timestamp(s:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.unix_timestamp]]
       */
     def unixTimestamp: LongColumn = s.elem.map(f.unix_timestamp).toDC
 
@@ -559,7 +549,7 @@ private[syntax] trait StringColumns {
       * @throws java.lang.IllegalArgumentException if invalid pattern
       *
       * @group String Type
-      * @see [[org.apache.spark.sql.functions.unix_timestamp]]
+      * @see [[org.apache.spark.sql.functions.unix_timestamp(s:org\.apache\.spark\.sql\.Column,p:* org.apache.spark.sql.functions.unix_timestamp]]
       */
     def unixTimestamp(pattern: StringColumn): LongColumn =
       (s.elem, pattern.elem)
@@ -595,7 +585,7 @@ private[syntax] trait StringColumns {
       * @return
       *   A date, or null if `e` was a string that could not be cast to a date
       *   or `format` was an invalid format
-      * @see [[org.apache.spark.sql.functions.to_date]]
+      * @see [[org.apache.spark.sql.functions.to_date(e:org\.apache\.spark\.sql\.Column,fmt:* org.apache.spark.sql.functions.to_date]]
       */
     def toDate(format: StringColumn): LocalDateColumn =
       (s.elem, format.elem)
@@ -617,7 +607,7 @@ private[syntax] trait StringColumns {
       * @return
       *   A timestamp, or null if `s` was a string that could not be cast to a
       *   timestamp or `format` was an invalid format
-      * @see [[org.apache.spark.sql.functions.to_timestamp]]
+      * @see [[org.apache.spark.sql.functions.to_timestamp(s:org\.apache\.spark\.sql\.Column,fmt:* org.apache.spark.sql.functions.to_timestamp]]
       */
     def toTimestamp(format: StringColumn): InstantColumn =
       (s.elem, format.elem)

diff --git a/core/src/main/scala/doric/syntax/TimestampColumns.scala b/core/src/main/scala/doric/syntax/TimestampColumns.scala
@@ -33,7 +33,8 @@ private[syntax] trait TimestampColumns {
       *
       * @throws java.time.DateTimeException if invalid timeZone
       * @group Timestamp Type
-      * @see [[org.apache.spark.sql.functions.from_utc_timestamp]]
+      * @see org.apache.spark.sql.functions.from_utc_timestamp
+      * @todo scaladoc link (issue #135)
       */
     def fromUtc(timeZone: StringColumn): TimestampColumn =
       (column.elem, timeZone.elem)
@@ -49,7 +50,8 @@ private[syntax] trait TimestampColumns {
       *
       * @throws java.time.DateTimeException if invalid timeZone
       * @group Timestamp Type
-      * @see [[org.apache.spark.sql.functions.to_utc_timestamp]]
+      * @see org.apache.spark.sql.functions.to_utc_timestamp
+      * @todo scaladoc link (issue #135)
       */
     def toUtc(timeZone: StringColumn): TimestampColumn =
       (column.elem, timeZone.elem)
@@ -74,7 +76,7 @@ private[syntax] trait TimestampColumns {
       *                       `1 second`. Check `org.apache.spark.unsafe.types.CalendarInterval` for
       *                       valid duration identifiers.
       * @group Timestamp Type
-      * @see [[org.apache.spark.sql.functions.window]]
+      * @see [[org.apache.spark.sql.functions.window(timeColumn:org\.apache\.spark\.sql\.Column,windowDuration:String):* org.apache.spark.sql.functions.window]]
       */
     def window(windowDuration: String): RowColumn =
       column.elem.map(x => f.window(x, windowDuration)).toDC
@@ -102,7 +104,7 @@ private[syntax] trait TimestampColumns {
       *   start 15 minutes past the hour, e.g. 12:15-13:15, 13:15-14:15... provide
       *   `startTime` as `15 minutes`.
       * @group Timestamp Type
-      * @see [[org.apache.spark.sql.functions.window]]
+      * @see [[org.apache.spark.sql.functions.window(timeColumn:org\.apache\.spark\.sql\.Column,windowDuration:String,slideDuration:String,startTime:* org.apache.spark.sql.functions.window]]
       */
     def window(
         windowDuration: String,
@@ -119,7 +121,7 @@ private[syntax] trait TimestampColumns {
       * @group Timestamp Type
       * @return
       *   a Date Column without the hour
-      * @see [[org.apache.spark.sql.functions.to_date]]
+      * @see [[org.apache.spark.sql.functions.to_date(e:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.to_date]]
       */
     def toDate: DateColumn = column.elem.map(f.to_date).toDC
 
@@ -129,7 +131,7 @@ private[syntax] trait TimestampColumns {
       * @group Timestamp Type
       * @return
       *   a LocalDate Column without the hour
-      * @see [[org.apache.spark.sql.functions.to_date]]
+      * @see [[org.apache.spark.sql.functions.to_date(e:org\.apache\.spark\.sql\.Column):* org.apache.spark.sql.functions.to_date]]
       */
     def toLocalDate: LocalDateColumn = column.elem.map(f.to_date).toDC
   }