From b40fe56dd9fb204e0f68d00fe1b9b74adde088cf Mon Sep 17 00:00:00 2001
From: Joris Van den Bossche <jorisvandenbossche@gmail.com>
Date: Mon, 24 Aug 2020 15:17:29 +0200
Subject: [PATCH 1/3] ARROW-9827: [C++][Dataset] Skip parsing RowGroup metadata
 statistics when there is no filter

---
 cpp/src/arrow/dataset/file_parquet.cc | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/cpp/src/arrow/dataset/file_parquet.cc b/cpp/src/arrow/dataset/file_parquet.cc
index 0f939d7da71..7c5a855b629 100644
--- a/cpp/src/arrow/dataset/file_parquet.cc
+++ b/cpp/src/arrow/dataset/file_parquet.cc
@@ -385,12 +385,14 @@ Result<ScanTaskIterator> ParquetFileFormat::ScanFile(std::shared_ptr<ScanOptions
                         GetReader(fragment->source(), options.get(), context.get()));
 
   if (!parquet_fragment->HasCompleteMetadata()) {
-    // row groups were not already filtered; do this now
-    RETURN_NOT_OK(parquet_fragment->EnsureCompleteMetadata(reader.get()));
-    ARROW_ASSIGN_OR_RAISE(row_groups,
-                          parquet_fragment->FilterRowGroups(*options->filter));
-    if (row_groups.empty()) {
-      return MakeEmptyIterator<std::shared_ptr<ScanTask>>();
+    // row groups were not already filtered; do this now (if there is a filter)
+    if (!options->filter->Equals(true)) {
+      RETURN_NOT_OK(parquet_fragment->EnsureCompleteMetadata(reader.get()));
+      ARROW_ASSIGN_OR_RAISE(row_groups,
+                            parquet_fragment->FilterRowGroups(*options->filter));
+      if (row_groups.empty()) {
+        return MakeEmptyIterator<std::shared_ptr<ScanTask>>();
+      }
     }
   }
 

From 105ddbe312cd5741df06befc946eba160999c943 Mon Sep 17 00:00:00 2001
From: Joris Van den Bossche <jorisvandenbossche@gmail.com>
Date: Tue, 25 Aug 2020 10:54:48 +0200
Subject: [PATCH 2/3] still need to get vector of row groups if no filter is
 specified

---
 cpp/src/arrow/dataset/file_parquet.cc | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/cpp/src/arrow/dataset/file_parquet.cc b/cpp/src/arrow/dataset/file_parquet.cc
index 7c5a855b629..f5168f2f742 100644
--- a/cpp/src/arrow/dataset/file_parquet.cc
+++ b/cpp/src/arrow/dataset/file_parquet.cc
@@ -393,6 +393,15 @@ Result<ScanTaskIterator> ParquetFileFormat::ScanFile(std::shared_ptr<ScanOptions
       if (row_groups.empty()) {
         return MakeEmptyIterator<std::shared_ptr<ScanTask>>();
       }
+    } else {
+      row_groups = parquet_fragment->row_groups();
+      if (row_groups.empty()) {
+        // empty vector represents all row groups
+        std::shared_ptr<parquet::FileMetaData> metadata =
+            reader->parquet_reader()->metadata();
+        int num_row_groups = metadata->num_row_groups();
+        row_groups = RowGroupInfo::FromCount(num_row_groups);
+      }
     }
   }
 

From 99d3aec6f2b6a51abe424701367e25dbcec7fe22 Mon Sep 17 00:00:00 2001
From: Joris Van den Bossche <jorisvandenbossche@gmail.com>
Date: Tue, 8 Sep 2020 14:19:27 +0200
Subject: [PATCH 3/3] add comment

---
 cpp/src/arrow/dataset/file_parquet.cc | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/cpp/src/arrow/dataset/file_parquet.cc b/cpp/src/arrow/dataset/file_parquet.cc
index f5168f2f742..d1969ed87af 100644
--- a/cpp/src/arrow/dataset/file_parquet.cc
+++ b/cpp/src/arrow/dataset/file_parquet.cc
@@ -394,6 +394,8 @@ Result<ScanTaskIterator> ParquetFileFormat::ScanFile(std::shared_ptr<ScanOptions
         return MakeEmptyIterator<std::shared_ptr<ScanTask>>();
       }
     } else {
+      // since we are not scanning this fragment with a filter, don't bother loading
+      // statistics
       row_groups = parquet_fragment->row_groups();
       if (row_groups.empty()) {
         // empty vector represents all row groups