PARQUET-2211: [C++] Print ColumnMetaData.encoding_stats field (#14556)

Authored-by: Gang Wu <ustcwg@gmail.com> Signed-off-by: Antoine Pitrou <antoine@python.org>
apache · Nov 6, 2022 · 7f067f9 · 7f067f9
1 parent 2cac16b
commit 7f067f9
Show file tree

Hide file tree

Showing 2 changed files with 34 additions and 7 deletions.
diff --git a/cpp/src/parquet/printer.cc b/cpp/src/parquet/printer.cc
@@ -39,6 +39,25 @@ namespace parquet {
 
 class ColumnReader;
 
+namespace {
+
+void PrintPageEncodingStats(std::ostream& stream,
+                            const std::vector<PageEncodingStats>& encoding_stats) {
+  for (size_t i = 0; i < encoding_stats.size(); ++i) {
+    const auto& encoding = encoding_stats.at(i);
+    stream << EncodingToString(encoding.encoding);
+    if (encoding.page_type == parquet::PageType::DICTIONARY_PAGE) {
+      // Explicitly tell if this encoding comes from a dictionary page
+      stream << "(DICT_PAGE)";
+    }
+    if (i + 1 != encoding_stats.size()) {
+      stream << " ";
+    }
+  }
+}
+
+}  // namespace
+
 // ----------------------------------------------------------------------
 // ParquetFilePrinter::DebugPrint
 
@@ -131,9 +150,13 @@ void ParquetFilePrinter::DebugPrint(std::ostream& stream, std::list<int> selecte
              << "  Compression: "
              << ::arrow::internal::AsciiToUpper(
                     Codec::GetCodecAsString(column_chunk->compression()))
-             << ", Encodings:";
-      for (auto encoding : column_chunk->encodings()) {
-        stream << " " << EncodingToString(encoding);
+             << ", Encodings: ";
+      if (column_chunk->encoding_stats().empty()) {
+        for (auto encoding : column_chunk->encodings()) {
+          stream << EncodingToString(encoding) << " ";
+        }
+      } else {
+        PrintPageEncodingStats(stream, column_chunk->encoding_stats());
       }
       stream << std::endl
              << "  Uncompressed Size: " << column_chunk->total_uncompressed_size()
@@ -271,8 +294,12 @@ void ParquetFilePrinter::JSONPrint(std::ostream& stream, std::list<int> selected
              << ::arrow::internal::AsciiToUpper(
                     Codec::GetCodecAsString(column_chunk->compression()))
              << "\", \"Encodings\": \"";
-      for (auto encoding : column_chunk->encodings()) {
-        stream << EncodingToString(encoding) << " ";
+      if (column_chunk->encoding_stats().empty()) {
+        for (auto encoding : column_chunk->encodings()) {
+          stream << EncodingToString(encoding) << " ";
+        }
+      } else {
+        PrintPageEncodingStats(stream, column_chunk->encoding_stats());
       }
       stream << "\", "
              << "\"UncompressedSize\": \"" << column_chunk->total_uncompressed_size()

diff --git a/cpp/src/parquet/reader_test.cc b/cpp/src/parquet/reader_test.cc
@@ -547,12 +547,12 @@ Column 1: b (INT32)
 --- Rows: 3 ---
 Column 0
   Values: 18  Statistics Not Set
-  Compression: SNAPPY, Encodings: RLE PLAIN_DICTIONARY
+  Compression: SNAPPY, Encodings: PLAIN_DICTIONARY(DICT_PAGE) PLAIN_DICTIONARY
   Uncompressed Size: 103, Compressed Size: 104
 Column 1
   Values: 3, Null Values: 0, Distinct Values: 0
   Max: 1, Min: 1
-  Compression: SNAPPY, Encodings: BIT_PACKED PLAIN_DICTIONARY
+  Compression: SNAPPY, Encodings: PLAIN_DICTIONARY(DICT_PAGE) PLAIN_DICTIONARY
   Uncompressed Size: 52, Compressed Size: 56
 )###";
   std::string values_output = R"###(--- Values ---