Docs: add DataFile helper snippet

cbb330 · cbb330 · commit c294f5469015 · 2025-11-20T13:00:16.000-08:00
diff --git a/bug-bash-wap/QUICKSTART.md b/bug-bash-wap/QUICKSTART.md
@@ -131,6 +131,21 @@ import liopenhouse.relocated.org.apache.iceberg.types.Types
 ```
 Use `TableIdentifier.of("u_openhouse", tableName)` (instead of `Identifier.of`) whenever you load tables via the catalog.
 
+### Build a DataFile (Iceberg helper snippet)
+```scala
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
+```
+
 ### Commit Snapshot S1 to `main`
 Before branching, follow the same pattern that `apps/spark/src/test/java/com/linkedin/openhouse/catalog/e2e/WapIdJavaTest.java` uses to create the first committed snapshot on `main`:
 ```scala
diff --git a/bug-bash-wap/create-test-files.sh b/bug-bash-wap/create-test-files.sh
@@ -141,6 +141,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-08-rohit.md b/bug-bash-wap/results/java-08-rohit.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-09-selena.md b/bug-bash-wap/results/java-09-selena.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-1-abhishek.md b/bug-bash-wap/results/java-1-abhishek.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-10-shanthoosh.md b/bug-bash-wap/results/java-10-shanthoosh.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-11-simbarashe.md b/bug-bash-wap/results/java-11-simbarashe.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-12-aastha.md b/bug-bash-wap/results/java-12-aastha.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-13-jiefan.md b/bug-bash-wap/results/java-13-jiefan.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-14-zhe.md b/bug-bash-wap/results/java-14-zhe.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-15-kevin.md b/bug-bash-wap/results/java-15-kevin.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-16-junhao.md b/bug-bash-wap/results/java-16-junhao.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-17-ruolin.md b/bug-bash-wap/results/java-17-ruolin.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-2-daniel.md b/bug-bash-wap/results/java-2-daniel.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-3-vikram.md b/bug-bash-wap/results/java-3-vikram.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-4-william.md b/bug-bash-wap/results/java-4-william.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-5-christian.md b/bug-bash-wap/results/java-5-christian.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-6-stas.md b/bug-bash-wap/results/java-6-stas.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/results/java-7-levi.md b/bug-bash-wap/results/java-7-levi.md
@@ -15,6 +15,18 @@ import liopenhouse.relocated.org.apache.iceberg.SnapshotRef
 import liopenhouse.relocated.org.apache.iceberg.TableMetadata
 import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifier
 import liopenhouse.relocated.org.apache.iceberg.types.Types
+import org.apache.iceberg.DataFile
+import org.apache.iceberg.DataFiles
+import org.apache.iceberg.FileFormat
+
+// Build a DataFile for commits
+val dataFile: DataFile =
+  DataFiles.builder(table.spec())
+    .withPath("/fake/path/data.parquet")
+    .withFileSizeInBytes(1024)
+    .withRecordCount(100)
+    .withFormat(FileFormat.PARQUET)
+    .build()
 
 // Setup
 val timestamp = System.currentTimeMillis()
diff --git a/bug-bash-wap/start-testing.sh b/bug-bash-wap/start-testing.sh
@@ -74,6 +74,18 @@ echo -e "  import liopenhouse.relocated.org.apache.iceberg.catalog.TableIdentifi
 echo -e "  import liopenhouse.relocated.org.apache.iceberg.types.Types"
 echo ""
 
+echo -e "${YELLOW}DataFile helper imports & builder:${NC}"
+echo -e "  import org.apache.iceberg.DataFile"
+echo -e "  import org.apache.iceberg.DataFiles"
+echo -e "  import org.apache.iceberg.FileFormat"
+echo -e "  val dataFile: DataFile = DataFiles.builder(table.spec())"
+echo -e "    .withPath(\"/fake/path/data.parquet\")"
+echo -e "    .withFileSizeInBytes(1024)"
+echo -e "    .withRecordCount(100)"
+echo -e "    .withFormat(FileFormat.PARQUET)"
+echo -e "    .build()"
+echo ""
+
 echo -e "${YELLOW}Commit snapshot S1 on main (pattern from WapIdJavaTest):${NC}"
 echo -e "  val dataFile: org.apache.iceberg.DataFile = /* build via DataFiles */"
 echo -e "  table.newAppend().appendFile(dataFile).commit()"
