2121#include < cstdio>
2222#include < memory>
2323#include < ostream>
24+ #include < sstream>
2425#include < string>
2526#include < vector>
2627
28+ #include " arrow/json/json_writer_internal.h"
2729#include " arrow/util/key_value_metadata.h"
2830#include " arrow/util/string.h"
2931
@@ -254,16 +256,18 @@ void ParquetFilePrinter::DebugPrint(std::ostream& stream, std::list<int> selecte
254256void ParquetFilePrinter::JSONPrint (std::ostream& stream, std::list<int > selected_columns,
255257 const char * filename) {
256258 const FileMetaData* file_metadata = fileReader->metadata ().get ();
257- stream << " {\n " ;
258- stream << " \" FileName\" : \" " << filename << " \" ,\n " ;
259- stream << " \" Version\" : \" " << ParquetVersionToString (file_metadata->version ())
260- << " \" ,\n " ;
261- stream << " \" CreatedBy\" : \" " << file_metadata->created_by () << " \" ,\n " ;
262- stream << " \" TotalRows\" : \" " << file_metadata->num_rows () << " \" ,\n " ;
263- stream << " \" NumberOfRowGroups\" : \" " << file_metadata->num_row_groups () << " \" ,\n " ;
264- stream << " \" NumberOfRealColumns\" : \" "
265- << file_metadata->schema ()->group_node ()->field_count () << " \" ,\n " ;
266- stream << " \" NumberOfColumns\" : \" " << file_metadata->num_columns () << " \" ,\n " ;
259+ ::arrow::json::JsonWriter writer;
260+ writer.StartObject ();
261+ writer.StringField (" FileName" , filename);
262+ writer.StringField (" Version" , ParquetVersionToString (file_metadata->version ()));
263+ writer.StringField (" CreatedBy" , file_metadata->created_by ());
264+ writer.StringField (" TotalRows" , std::to_string (file_metadata->num_rows ()));
265+ writer.StringField (" NumberOfRowGroups" ,
266+ std::to_string (file_metadata->num_row_groups ()));
267+ writer.StringField (
268+ " NumberOfRealColumns" ,
269+ std::to_string (file_metadata->schema ()->group_node ()->field_count ()));
270+ writer.StringField (" NumberOfColumns" , std::to_string (file_metadata->num_columns ()));
267271
268272 if (selected_columns.empty ()) {
269273 for (int i = 0 ; i < file_metadata->num_columns (); i++) {
@@ -277,161 +281,152 @@ void ParquetFilePrinter::JSONPrint(std::ostream& stream, std::list<int> selected
277281 }
278282 }
279283
280- stream << " \" Columns\" : [ \n " ;
281- int c = 0 ;
284+ writer. Key ( " Columns" ) ;
285+ writer. StartArray () ;
282286 for (auto i : selected_columns) {
283287 const ColumnDescriptor* descr = file_metadata->schema ()->Column (i);
284- stream << " { \" Id\" : \" " << i << " \" ,"
285- << " \" Name\" : \" " << descr->path ()->ToDotString () << " \" ,"
286- << " \" PhysicalType\" : \" "
287- << TypeToString (descr->physical_type (), descr->type_length ()) << " \" ,"
288- << " \" ConvertedType\" : \" " << ConvertedTypeToString (descr->converted_type ())
289- << " \" ,"
290- << " \" LogicalType\" : " << (descr->logical_type ())->ToJSON () << " }" ;
291- c++;
292- if (c != static_cast <int >(selected_columns.size ())) {
293- stream << " ,\n " ;
294- }
288+ writer.StartObject ();
289+ writer.StringField (" Id" , std::to_string (i));
290+ writer.StringField (" Name" , descr->path ()->ToDotString ());
291+ writer.StringField (" PhysicalType" ,
292+ TypeToString (descr->physical_type (), descr->type_length ()));
293+ writer.StringField (" ConvertedType" , ConvertedTypeToString (descr->converted_type ()));
294+ writer.Key (" LogicalType" );
295+ writer.RawValue (descr->logical_type ()->ToJSON ());
296+ writer.EndObject ();
295297 }
298+ writer.EndArray ();
296299
297- stream << " \n ],\n \" RowGroups\" : [\n " ;
300+ writer.Key (" RowGroups" );
301+ writer.StartArray ();
298302 for (int r = 0 ; r < file_metadata->num_row_groups (); ++r) {
299- stream << " {\n \" Id\" : \" " << r << " \" , " ;
303+ writer.StartObject ();
304+ writer.StringField (" Id" , std::to_string (r));
300305
301306 auto group_reader = fileReader->RowGroup (r);
302307 std::unique_ptr<RowGroupMetaData> group_metadata = file_metadata->RowGroup (r);
303308
304- stream << " \" TotalBytes\" : \" " << group_metadata->total_byte_size () << " \" , " ;
305- stream << " \" TotalCompressedBytes\" : \" " << group_metadata-> total_compressed_size ()
306- << " \" , " ;
309+ writer. StringField ( " TotalBytes" , std::to_string ( group_metadata->total_byte_size ())) ;
310+ writer. StringField ( " TotalCompressedBytes" ,
311+ std::to_string (group_metadata-> total_compressed_size ())) ;
307312 auto row_group_sorting_columns = group_metadata->sorting_columns ();
308313 if (!row_group_sorting_columns.empty ()) {
309- stream << " \" SortColumns\" : [\n " ;
310- for (size_t i = 0 ; i < row_group_sorting_columns.size (); i++) {
311- stream << " {\" column_idx\" : " << row_group_sorting_columns[i].column_idx
312- << " , \" descending\" : " << row_group_sorting_columns[i].descending
313- << " , \" nulls_first\" : " << row_group_sorting_columns[i].nulls_first
314- << " }" ;
315- if (i + 1 != row_group_sorting_columns.size ()) {
316- stream << " ," ;
317- }
318- stream << ' \n ' ;
314+ writer.Key (" SortColumns" );
315+ writer.StartArray ();
316+ for (const auto & sorting_column : row_group_sorting_columns) {
317+ writer.StartObject ();
318+ writer.IntField (" column_idx" , sorting_column.column_idx );
319+ writer.IntField (" descending" , sorting_column.descending );
320+ writer.IntField (" nulls_first" , sorting_column.nulls_first );
321+ writer.EndObject ();
319322 }
320- stream << " ], " ;
323+ writer. EndArray () ;
321324 }
322- stream << " \" Rows\" : \" " << group_metadata->num_rows () << " \" , \n " ;
325+ writer. StringField ( " Rows" , std::to_string ( group_metadata->num_rows ())) ;
323326
324- // Print column metadata
325- stream << " \" ColumnChunks\" : [\n " ;
326- int c1 = 0 ;
327+ writer.Key (" ColumnChunks" );
328+ writer.StartArray ();
327329 for (auto i : selected_columns) {
328330 auto column_chunk = group_metadata->ColumnChunk (i);
329331 std::shared_ptr<Statistics> stats = column_chunk->statistics ();
330-
331332 const ColumnDescriptor* descr = file_metadata->schema ()->Column (i);
332- stream << " {\" Id\" : \" " << i << " \" , \" Values\" : \" "
333- << column_chunk->num_values () << " \" , "
334- << " \" StatsSet\" : " ;
333+
334+ writer.StartObject ();
335+ writer.StringField (" Id" , std::to_string (i));
336+ writer.StringField (" Values" , std::to_string (column_chunk->num_values ()));
335337 if (column_chunk->is_stats_set ()) {
336- stream << R"( "True", "Stats": {)" ;
338+ writer.StringField (" StatsSet" , " True" );
339+ writer.Key (" Stats" );
340+ writer.StartObject ();
337341 if (stats->HasNullCount ()) {
338- stream << R" ( "NumNulls": " )" << stats->null_count () << " \" " ;
342+ writer. StringField (" NumNulls" , std::to_string ( stats->null_count ())) ;
339343 }
340344 if (stats->HasDistinctCount ()) {
341- stream << " , "
342- << R"( "DistinctValues": ")" << stats->distinct_count () << " \" " ;
345+ writer.StringField (" DistinctValues" , std::to_string (stats->distinct_count ()));
343346 }
344347 if (stats->HasMinMax ()) {
345348 std::string min = stats->EncodeMin (), max = stats->EncodeMax ();
346- stream << " , "
347- << R"( "Max": ")"
348- << FormatStatValue (descr->physical_type (), max, descr->logical_type ())
349- << " \" , "
350- << R"( "Min": ")"
351- << FormatStatValue (descr->physical_type (), min, descr->logical_type ())
352- << " \" " ;
349+ writer.StringField (
350+ " Max" , FormatStatValue (descr->physical_type (), max, descr->logical_type ()));
351+ writer.StringField (
352+ " Min" , FormatStatValue (descr->physical_type (), min, descr->logical_type ()));
353353 if (stats->is_max_value_exact ().has_value ()) {
354- stream << " , "
355- << R"( "IsMaxValueExact": ")"
356- << (stats->is_max_value_exact ().value () ? " True" : " False" ) << " \" " ;
354+ writer.StringField (" IsMaxValueExact" ,
355+ stats->is_max_value_exact ().value () ? " True" : " False" );
357356 } else {
358- stream << " , "
359- << R"( "IsMaxValueExact": "unknown")" ;
357+ writer.StringField (" IsMaxValueExact" , " unknown" );
360358 }
361359 if (stats->is_min_value_exact ().has_value ()) {
362- stream << " , "
363- << R"( "IsMinValueExact": ")"
364- << (stats->is_min_value_exact ().value () ? " True" : " False" ) << " \" " ;
360+ writer.StringField (" IsMinValueExact" ,
361+ stats->is_min_value_exact ().value () ? " True" : " False" );
365362 } else {
366- stream << " , "
367- << R"( "IsMinValueExact": "unknown")" ;
363+ writer.StringField (" IsMinValueExact" , " unknown" );
368364 }
369365 }
370- stream << " }, " ;
366+ writer. EndObject () ;
371367 } else {
372- stream << " \" False \" , " ;
368+ writer. StringField ( " StatsSet " , " False " ) ;
373369 }
374- stream << " \n \" Compression\" : \" "
375- << ::arrow::internal::AsciiToUpper (
376- Codec::GetCodecAsString (column_chunk->compression ()))
377- << R"( ", "Encodings": )" ;
378- stream << " \" " ;
370+
371+ writer.StringField (" Compression" ,
372+ ::arrow::internal::AsciiToUpper (
373+ Codec::GetCodecAsString (column_chunk->compression ())));
374+
375+ std::ostringstream encodings_stream;
379376 if (column_chunk->encoding_stats ().empty()) {
380377 for (auto encoding : column_chunk->encodings ()) {
381- stream << EncodingToString (encoding) << " " ;
378+ encodings_stream << EncodingToString (encoding) << " " ;
382379 }
383380 } else {
384- PrintPageEncodingStats (stream , column_chunk->encoding_stats ());
381+ PrintPageEncodingStats (encodings_stream , column_chunk->encoding_stats ());
385382 }
386- stream << " \" " ;
387- stream << " , "
388- << R"( "UncompressedSize": ")" << column_chunk->total_uncompressed_size ()
389- << R"( ", "CompressedSize": ")" << column_chunk->total_compressed_size ()
390- << " \" " ;
383+ writer.StringField(" Encodings" , encodings_stream.str());
384+
385+ writer.StringField(" UncompressedSize" ,
386+ std::to_string (column_chunk->total_uncompressed_size ()));
387+ writer.StringField(" CompressedSize" ,
388+ std::to_string (column_chunk->total_compressed_size ()));
391389
392390 if (column_chunk->bloom_filter_offset ()) {
393- // Output BloomFilter {offset, length}
394- stream << " , \" BloomFilter\" : {"
395- << R"( "offset": ")" << column_chunk->bloom_filter_offset ().value () << " \" " ;
391+ writer.Key (" BloomFilter" );
392+ writer.StartObject ();
393+ writer.StringField (" offset" ,
394+ std::to_string (column_chunk->bloom_filter_offset ().value ()));
396395 if (column_chunk->bloom_filter_length ()) {
397- stream << R"( , "length": " )" << column_chunk-> bloom_filter_length (). value ()
398- << " \" " ;
396+ writer. StringField ( " length" ,
397+ std::to_string (column_chunk-> bloom_filter_length (). value ())) ;
399398 }
400- stream << " } " ;
399+ writer. EndObject () ;
401400 }
402401
403402 if (column_chunk->GetColumnIndexLocation ()) {
404403 auto location = column_chunk->GetColumnIndexLocation ().value ();
405- // Output ColumnIndex {offset, length}
406- stream << " , \" ColumnIndex \" : { "
407- << R" ( "offset": " )" << location.offset ;
408- stream << R"( ", " length": " )" << location.length ;
409- stream << " \" } " ;
404+ writer. Key ( " ColumnIndex" );
405+ writer. StartObject ();
406+ writer. StringField (" offset" , std::to_string ( location.offset )) ;
407+ writer. StringField ( " length" , std::to_string ( location.length )) ;
408+ writer. EndObject () ;
410409 }
411410
412411 if (column_chunk->GetOffsetIndexLocation ()) {
413412 auto location = column_chunk->GetOffsetIndexLocation ().value ();
414- // Output OffsetIndex {offset, length}
415- stream << " , \" OffsetIndex \" : { "
416- << R" ( "offset": " )" << location.offset << " \" " ;
417- stream << R"( , "length": " )" << location.length << " \" " ;
418- stream << " } " ;
413+ writer. Key ( " OffsetIndex" );
414+ writer. StartObject ();
415+ writer. StringField (" offset" , std::to_string ( location.offset )) ;
416+ writer. StringField ( " length" , std::to_string ( location.length )) ;
417+ writer. EndObject () ;
419418 }
420419
421- // end of a ColumnChunk
422- stream << " }" ;
423- c1++;
424- if (c1 != static_cast <int >(selected_columns.size ())) {
425- stream << " ,\n " ;
426- }
427- }
428-
429- stream << " \n ]\n }" ;
430- if ((r + 1 ) != static_cast <int >(file_metadata->num_row_groups ())) {
431- stream << " ,\n " ;
420+ writer.EndObject();
432421 }
422+ writer.EndArray();
423+ writer.EndObject();
433424 }
434- stream << " \n ]\n }\n " ;
425+ writer.EndArray ();
426+ writer.EndObject ();
427+
428+ PARQUET_ASSIGN_OR_THROW (std::string pretty_json, writer.GetPrettyString ());
429+ stream << pretty_json << " \n " ;
435430}
436431
437432} // namespace parquet
0 commit comments