purplelight 0.1.12 → 0.1.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 920b534dc9ac832d83600031277ddd35da2920cff494e0f96d0ca230652d4ba4
-  data.tar.gz: 2fd4476e73efc67d1f4a722dae8d7759ac8b51b5c21546dfb4b06d9fc1cd3934
+  metadata.gz: c500768ed34e247a92be3979f56c1036314b51003cb1ff7953562f1ca8278677
+  data.tar.gz: f12b305e35b201192e219aec23a0c66c13a7b9eb262c038dbac9d1e2a3c77bc5
 SHA512:
-  metadata.gz: 370660a815b47c4aa4a0725a6188d6e0455074232000a24c4f909a313c3b9c2d5d3219a17edb628df58f167115b317347c159cc93d5bd59e216d6de1ec7ecd77
-  data.tar.gz: efec787b1e355af50ec07e45b8c125d0f1054640734afbe7790a3a35181f999900d3c843104911eabcea644d2dc7f4604050571e17469f08fe97d9fa5aec92e9
+  metadata.gz: 0f6959b02fb695a4c28802ec555d7b6ce6e7020d348024d2df8381efbb022632916d2915c688131cf79aa042f05aa3e2ec8780ad866fdb774b45b51f53093d6b
+  data.tar.gz: aa2885e120f57bd492c1a98aee91f52b7c83bee15492ce34a0b6d3dae985e0355ea77489e69dfde2f27fb5b51974263b7f7358a51103697d8222a03cd98a4185

data/README.md

@@ -9,7 +9,7 @@ Purplelight is published on RubyGems: [purplelight on RubyGems](https://rubygems
 Add to your Gemfile:
 
 ```ruby
-gem 'purplelight', '~> 0.1.12'
+gem 'purplelight', '~> 0.1.13'
 ```
 
 Or install directly:
@@ -212,6 +212,7 @@ bundle exec bin/purplelight \
 - `--read-concern LEVEL`: `majority|local|linearizable|available|snapshot`.
 - `--no-cursor-timeout BOOL`: Toggle `noCursorTimeout` (default true).
 - `--parquet-row-group N`: Parquet row group size (rows).
+- `--parquet-max-rows N`: Parquet max rows per part (enables multi-part when not `--single-file`).
 - `--write-chunk-mb MB`: JSONL encode/write chunk size before enqueueing.
 - `--writer-threads N` (experimental): Number of writer threads (JSONL only).
 - `--telemetry on|off`: Force enable/disable telemetry output.
@@ -222,7 +223,7 @@ bundle exec bin/purplelight \
 Notes:
 - Compression backend selection order is: requested format → `zstd-ruby` → `zstds` → `gzip`.
 - `--single-file` and `--by-size` update only the sharding mode/params and preserve any provided `--prefix`.
-- Parquet multi-part sizing is programmatic via `parquet_max_rows`; there is no CLI flag for it.
+– Parquet multi-part sizing can be controlled via `parquet_max_rows` programmatically, or via CLI `--parquet-max-rows`.
 - To increase concurrent connections, set `maxPoolSize` on your Mongo URI (used by `--uri`), e.g., `mongodb://.../?maxPoolSize=32`. A good starting point is `maxPoolSize >= --partitions`.
 
 ### Architecture

data/bin/purplelight

@@ -25,6 +25,7 @@ options = {
   writer_threads: nil,
   write_chunk_bytes: nil,
   parquet_row_group: nil,
+  parquet_max_rows: nil,
   telemetry_flag: nil,
   read_concern: nil,
   no_cursor_timeout: nil,
@@ -61,6 +62,7 @@ parser = OptionParser.new do |opts|
   opts.on('--writer-threads N', Integer, 'Number of writer threads (experimental, JSONL only)') { |v| options[:writer_threads] = v }
   opts.on('--write-chunk-mb MB', Integer, 'JSONL encode/write chunk size in MB') { |v| options[:write_chunk_bytes] = v * 1024 * 1024 }
   opts.on('--parquet-row-group N', Integer, 'Parquet row group size (rows)') { |v| options[:parquet_row_group] = v }
+  opts.on('--parquet-max-rows N', Integer, 'Parquet max rows per part (multi-part only)') { |v| options[:parquet_max_rows] = v }
   opts.on('-q', '--query JSON', 'Filter query as JSON (Extended JSON supported)') do |v|
     # Prefer BSON Extended JSON to support $date, $oid, etc.
     options[:query] = BSON::ExtJSON.parse(v)
@@ -158,7 +160,8 @@ snapshot_args[:no_cursor_timeout] = options[:no_cursor_timeout] unless options[:
 snapshot_args[:compression_level] = options[:compression_level] if options[:compression_level]
 snapshot_args[:writer_threads] = options[:writer_threads] if options[:writer_threads]
 snapshot_args[:write_chunk_bytes] = options[:write_chunk_bytes] if options[:write_chunk_bytes]
-snapshot_args[:parquet_row_group] = options[:parquet_row_group] if options[:parquet_row_group]
+ snapshot_args[:parquet_row_group] = options[:parquet_row_group] if options[:parquet_row_group]
+ snapshot_args[:parquet_max_rows] = options[:parquet_max_rows] if options[:parquet_max_rows]
 
 # telemetry env override
 if options[:telemetry_flag]
@@ -169,6 +172,7 @@ end
 ENV['PL_ZSTD_LEVEL'] = options[:compression_level].to_s if options[:compression_level]
 ENV['PL_WRITE_CHUNK_BYTES'] = options[:write_chunk_bytes].to_s if options[:write_chunk_bytes]
 ENV['PL_PARQUET_ROW_GROUP'] = options[:parquet_row_group].to_s if options[:parquet_row_group]
+  # No env default for parquet_max_rows; it is snapshot-argument only
 ENV['PL_WRITER_THREADS'] = options[:writer_threads].to_s if options[:writer_threads]
 
 ok = Purplelight.snapshot(**snapshot_args)

data/lib/purplelight/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Purplelight
-  VERSION = '0.1.12'
+  VERSION = '0.1.13'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: purplelight
 version: !ruby/object:Gem::Version
-  version: 0.1.12
+  version: 0.1.13
 platform: ruby
 authors:
 - Alexander Nicholson