PARQUET-760: Store correct encoding in fallback data pages

Author: Uwe L. Korn <[email protected]> Closes apache#182 from xhochy/PARQUET-760 and squashes the following commits: 1791506 [Uwe L. Korn] PARQUET-760: Store correct encoding in fallback data pages Change-Id: Id8f2308a3c8a9ebacb251476f532b82bba9f2787
wesm · Nov 1, 2016 · e3658a6 · e3658a6
1 parent 3159841
commit e3658a6
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 4 deletions.
diff --git a/cpp/src/parquet/column/column-writer-test.cc b/cpp/src/parquet/column/column-writer-test.cc
@@ -381,10 +381,11 @@ TYPED_TEST(TestPrimitiveWriter, RequiredVeryLargeChunk) {
   writer->WriteBatch(this->values_.size(), nullptr, nullptr, this->values_ptr_);
   writer->Close();
 
-  // Just read the first SMALL_SIZE rows to ensure we could read it back in
-  this->ReadColumn();
-  ASSERT_EQ(SMALL_SIZE, this->values_read_);
-  this->values_.resize(SMALL_SIZE);
+  // Read all rows so we are sure that also the non-dictionary pages are read correctly
+  this->SetupValuesOut(VERY_LARGE_SIZE);
+  this->ReadColumnFully();
+  ASSERT_EQ(VERY_LARGE_SIZE, this->values_read_);
+  this->values_.resize(VERY_LARGE_SIZE);
   ASSERT_EQ(this->values_, this->values_out_);
   std::vector<Encoding::type> encodings = this->metadata_encodings();
   // There are 3 encodings (RLE, PLAIN_DICTIONARY, PLAIN) in a fallback case

diff --git a/cpp/src/parquet/column/writer.cc b/cpp/src/parquet/column/writer.cc
@@ -216,6 +216,7 @@ void TypedColumnWriter<Type>::CheckDictionarySizeLimit() {
     fallback_ = true;
     // Only PLAIN encoding is supported for fallback in V1
     current_encoder_.reset(new PlainEncoder<Type>(descr_, properties_->allocator()));
+    encoding_ = Encoding::PLAIN;
   }
 }