Prepend underscore for parquet fields starting with number

snowplow · Sep 9, 2024 · 6c989fd · 6c989fd
1 parent 879ccc5
commit 6c989fd
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 5 deletions.
diff --git a/modules/core/src/main/scala/com.snowplowanalytics/iglu.schemaddl/parquet/Field.scala b/modules/core/src/main/scala/com.snowplowanalytics/iglu.schemaddl/parquet/Field.scala
@@ -68,9 +68,13 @@ object Field {
       .map(endMap(_))
   }
 
-  private[parquet] def normalizeName(field: Field): String =
-    StringUtils.snakeCase
-      .andThen(replaceDisallowedCharacters)(field.name)
+  // Normalize field name and prepend underscore if name starts with a number
+  private[parquet] def normalizeName(field: Field): String = {
+    val normalized = StringUtils.snakeCase.andThen(replaceDisallowedCharacters)(field.name)
+    if (normalized.nonEmpty && normalized.charAt(0).isDigit) s"_$normalized"
+    else normalized
+  }
+
 
   /**
    * Replaces disallowed parquet column characters with underscore

diff --git a/modules/core/src/test/scala/com/snowplowanalytics/iglu/schemaddl/parquet/FieldSpec.scala b/modules/core/src/test/scala/com/snowplowanalytics/iglu/schemaddl/parquet/FieldSpec.scala
@@ -375,11 +375,11 @@ class FieldSpec extends org.specs2.Specification { def is = s2"""
       (fieldNormalName("test1Test2Test3") must beEqualTo("test1_test2_test3")) and
       (fieldNormalName("Test1Test2TEST3") must beEqualTo("test1_test2_test3")) and
       (fieldNormalName("test1,test2.test3;test4") must beEqualTo("test1_test2_test3_test4")) and
-      (fieldNormalName("1test1,test2.test3;test4") must beEqualTo("1test1_test2_test3_test4")) and
+      (fieldNormalName("1test1,test2.test3;test4") must beEqualTo("_1test1_test2_test3_test4")) and
       (fieldNormalName("_50test1,test2.test3;test4") must beEqualTo("_50test1_test2_test3_test4")) and
       (fieldNormalName("_.test1,test2.test3;test4") must beEqualTo("__test1_test2_test3_test4")) and
       (fieldNormalName(",.;:") must beEqualTo("____")) and
-      (fieldNormalName("1test1,Test2Test3Test4.test5;test6") must beEqualTo("1test1_test2_test3_test4_test5_test6"))
+      (fieldNormalName("1test1,Test2Test3Test4.test5;test6") must beEqualTo("_1test1_test2_test3_test4_test5_test6"))
   }
 
   def e14 = {