[jira] [Commented] (PARQUET-1256) [C++] Add --print-key-value-metadata option to parquet_reader tool

["ASF GitHub Bot (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/PARQUET-1256?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16584429#comment-16584429 ] 

ASF GitHub Bot commented on PARQUET-1256:
-----------------------------------------

wesm closed pull request #450: PARQUET-1256: Add --print-key-value-metadata option to parquet_reader tool
URL: https://github.com/apache/parquet-cpp/pull/450
 
 
   

This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:

As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):

diff --git a/src/parquet/printer.cc b/src/parquet/printer.cc
index 3f18a5c8..9f26a418 100644
--- a/src/parquet/printer.cc
+++ b/src/parquet/printer.cc
@@ -33,13 +33,25 @@ namespace parquet {
 #define COL_WIDTH "30"
 
 void ParquetFilePrinter::DebugPrint(std::ostream& stream, std::list<int> selected_columns,
-                                    bool print_values, const char* filename) {
+                                    bool print_values, bool print_key_value_metadata,
+                                    const char* filename) {
   const FileMetaData* file_metadata = fileReader->metadata().get();
 
   stream << "File Name: " << filename << "\n";
   stream << "Version: " << file_metadata->version() << "\n";
   stream << "Created By: " << file_metadata->created_by() << "\n";
   stream << "Total rows: " << file_metadata->num_rows() << "\n";
+
+  if (print_key_value_metadata) {
+    auto key_value_metadata = file_metadata->key_value_metadata();
+    int64_t size_of_key_value_metadata = key_value_metadata->size();
+    stream << "Key Value File Metadata: " << size_of_key_value_metadata << " entries\n";
+    for (int64_t i = 0; i < size_of_key_value_metadata; i++) {
+      stream << " Key nr " << i << " " << key_value_metadata->key(i) << ": "
+             << key_value_metadata->value(i) << "\n";
+    }
+  }
+
   stream << "Number of RowGroups: " << file_metadata->num_row_groups() << "\n";
   stream << "Number of Real Columns: "
          << file_metadata->schema()->group_node()->field_count() << "\n";
diff --git a/src/parquet/printer.h b/src/parquet/printer.h
index 3b828829..1113c3fe 100644
--- a/src/parquet/printer.h
+++ b/src/parquet/printer.h
@@ -38,7 +38,8 @@ class PARQUET_EXPORT ParquetFilePrinter {
   ~ParquetFilePrinter() {}
 
   void DebugPrint(std::ostream& stream, std::list<int> selected_columns,
-                  bool print_values = true, const char* fileame = "No Name");
+                  bool print_values = true, bool print_key_value_metadata = false,
+                  const char* filename = "No Name");
 
   void JSONPrint(std::ostream& stream, std::list<int> selected_columns,
                  const char* filename = "No Name");
diff --git a/tools/parquet_reader.cc b/tools/parquet_reader.cc
index 7ef59dc1..34bdfc10 100644
--- a/tools/parquet_reader.cc
+++ b/tools/parquet_reader.cc
@@ -24,13 +24,14 @@
 int main(int argc, char** argv) {
   if (argc > 5 || argc < 2) {
     std::cerr << "Usage: parquet_reader [--only-metadata] [--no-memory-map] [--json]"
-                 "[--columns=...] <file>"
+                 "[--print-key-value-metadata] [--columns=...] <file>"
               << std::endl;
     return -1;
   }
 
   std::string filename;
   bool print_values = true;
+  bool print_key_value_metadata = false;
   bool memory_map = true;
   bool format_json = false;
 
@@ -42,6 +43,8 @@ int main(int argc, char** argv) {
   for (int i = 1; i < argc; i++) {
     if ((param = std::strstr(argv[i], "--only-metadata"))) {
       print_values = false;
+    } else if ((param = std::strstr(argv[i], "--print-key-value-metadata"))) {
+      print_key_value_metadata = true;
     } else if ((param = std::strstr(argv[i], "--no-memory-map"))) {
       memory_map = false;
     } else if ((param = std::strstr(argv[i], "--json"))) {
@@ -64,7 +67,8 @@ int main(int argc, char** argv) {
     if (format_json) {
       printer.JSONPrint(std::cout, columns, filename.c_str());
     } else {
-      printer.DebugPrint(std::cout, columns, print_values, filename.c_str());
+      printer.DebugPrint(std::cout, columns, print_values,
+        print_key_value_metadata, filename.c_str());
     }
   } catch (const std::exception& e) {
     std::cerr << "Parquet error: " << e.what() << std::endl;


 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


> [C++] Add --print-key-value-metadata option to parquet_reader tool
> ------------------------------------------------------------------
>
>                 Key: PARQUET-1256
>                 URL: https://issues.apache.org/jira/browse/PARQUET-1256
>             Project: Parquet
>          Issue Type: Improvement
>          Components: parquet-cpp
>            Reporter: Jacek Pliszka
>            Priority: Trivial
>              Labels: patch, pull-request-available
>             Fix For: cpp-1.5.0
>
>   Original Estimate: 0.25h
>  Remaining Estimate: 0.25h
>
> Added --print-key-value-metadata option to parquet_reader tool
> https://github.com/apache/parquet-cpp/pull/450
>  



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)