Added ellipsis to truncated table cells in Markdown and HTML renderers.

Author: metasim

core/src/main/resources/reference.conf

@@ -3,6 +3,7 @@ rasterframes {
   prefer-gdal = true
   showable-tiles = true
   showable-max-cells = 20
+  max-truncate-row-element-length = 40
   raster-source-cache-timeout = 120 seconds
 }
 

core/src/main/scala/org/locationtech/rasterframes/util/package.scala

@@ -38,7 +38,7 @@ import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
 import org.apache.spark.sql.functions._
 import org.apache.spark.sql.rf._
-import org.apache.spark.sql.types.StringType
+import org.apache.spark.sql.types.{StringType, StructField}
 import org.apache.spark.sql._
 import org.slf4j.LoggerFactory
 import spire.syntax.cfor._
@@ -184,15 +184,25 @@ package object util {
     }
   }
 
+  private val truncateWidth = rfConfig.getInt("max-truncate-row-element-length")
+
   implicit class DFWithPrettyPrint(val df: Dataset[_]) extends AnyVal {
+
+    def stringifyRowElements(cols: Seq[StructField], truncate: Boolean) = {
+      cols
+        .map(c => s"`${c.name}`")
+        .map(c => df.col(c).cast(StringType))
+        .map(c => if (truncate) {
+          when(length(c) > lit(truncateWidth), concat(substring(c, 1, truncateWidth), lit("...")))
+            .otherwise(c)
+        } else c)
+    }
+
     def toMarkdown(numRows: Int = 5, truncate: Boolean = false): String = {
       import df.sqlContext.implicits._
-      val cols = df.columns
-      val header = cols.mkString("| ", " | ", " |") + "\n" + ("|---" * cols.length) + "|\n"
-      val stringifiers = cols
-        .map(c => s"`$c`")
-        .map(c => df.col(c).cast(StringType))
-        .map(c => if (truncate) substring(c, 1, 40) else c)
+      val cols = df.schema.fields
+      val header = cols.map(_.name).mkString("| ", " | ", " |") + "\n" + ("|---" * cols.length) + "|\n"
+      val stringifiers = stringifyRowElements(cols, truncate)
       val cat = concat_ws(" | ", stringifiers: _*)
       val body = df
         .select(cat).limit(numRows)
@@ -206,20 +216,16 @@ package object util {
 
     def toHTML(numRows: Int = 5, truncate: Boolean = false): String = {
       import df.sqlContext.implicits._
-      val cols = df.columns
-      val header = "<thead>\n" + cols.mkString("<tr><th>", "</th><th>", "</th></tr>\n") + "</thead>\n"
-      val stringifiers = cols
-        .map(c => s"`$c`")
-        .map(c => df.col(c).cast(StringType))
-        .map(c => if (truncate) substring(c, 1, 40) else c)
+      val cols = df.schema.fields
+      val header = "<thead>\n" + cols.map(_.name).mkString("<tr><th>", "</th><th>", "</th></tr>\n") + "</thead>\n"
+      val stringifiers = stringifyRowElements(cols, truncate)
       val cat = concat_ws("</td><td>", stringifiers: _*)
       val body = df
         .select(cat).limit(numRows)
         .as[String]
         .collect()
         .mkString("<tr><td>", "</td></tr>\n<tr><td>", "</td></tr>\n")
 
-
       "<table>\n" + header + "<tbody>\n" + body + "</tbody>\n" + "</table>"
     }
   }

core/src/test/scala/org/locationtech/rasterframes/ExtensionMethodSpec.scala

@@ -26,7 +26,7 @@ import geotrellis.raster.{ByteCellType, GridBounds, TileLayout}
 import geotrellis.spark.tiling.{CRSWorldExtent, LayoutDefinition}
 import geotrellis.spark.{KeyBounds, SpatialKey, TileLayerMetadata}
 import org.apache.spark.sql.Encoders
-import org.locationtech.rasterframes.util.SubdivideSupport
+import org.locationtech.rasterframes.util._
 
 import scala.xml.parsing.XhtmlParser
 
@@ -113,13 +113,15 @@ class ExtensionMethodSpec extends TestEnvironment with TestData with SubdivideSu
     }
 
     it("should render Markdown") {
-      import org.locationtech.rasterframes.util._
-      rf.toMarkdown().count(_ == '|') shouldBe >=(3 * 5)
+      val md = rf.toMarkdown()
+      md.count(_ == '|') shouldBe >=(3 * 5)
+      md.count(_ == '\n') should be (6)
+
+      val md2 = rf.toMarkdown(truncate=true)
+      md2 should include ("...")
     }
 
     it("should render HTML") {
-      import org.locationtech.rasterframes.util._
-
       noException shouldBe thrownBy {
         XhtmlParser(scala.io.Source.fromString(rf.toHTML()))
       }