duckdb 1.4.2.0 → 1.4.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.github/copilot-instructions.md +169 -0
- data/.github/workflows/linter.yml +30 -0
- data/.github/workflows/test_on_macos.yml +7 -2
- data/.github/workflows/test_on_ubuntu.yml +7 -2
- data/.github/workflows/test_on_windows.yml +8 -3
- data/.rubocop.yml +34 -0
- data/CHANGELOG.md +74 -0
- data/Dockerfile +2 -2
- data/Gemfile +12 -0
- data/Gemfile.lock +70 -7
- data/Rakefile +8 -6
- data/bin/console +4 -3
- data/duckdb.gemspec +2 -6
- data/ext/duckdb/bind_info.c +243 -0
- data/ext/duckdb/bind_info.h +13 -0
- data/ext/duckdb/connection.c +60 -2
- data/ext/duckdb/connection.h +1 -0
- data/ext/duckdb/data_chunk.c +137 -0
- data/ext/duckdb/data_chunk.h +13 -0
- data/ext/duckdb/duckdb.c +7 -0
- data/ext/duckdb/function_info.c +65 -0
- data/ext/duckdb/function_info.h +13 -0
- data/ext/duckdb/init_info.c +65 -0
- data/ext/duckdb/init_info.h +13 -0
- data/ext/duckdb/logical_type.c +42 -0
- data/ext/duckdb/memory_helper.c +339 -0
- data/ext/duckdb/memory_helper.h +8 -0
- data/ext/duckdb/result.c +8 -9
- data/ext/duckdb/result.h +1 -0
- data/ext/duckdb/ruby-duckdb.h +7 -0
- data/ext/duckdb/scalar_function.c +336 -1
- data/ext/duckdb/scalar_function.h +2 -0
- data/ext/duckdb/table_function.c +403 -0
- data/ext/duckdb/table_function.h +16 -0
- data/ext/duckdb/vector.c +201 -0
- data/ext/duckdb/vector.h +13 -0
- data/lib/duckdb/appender.rb +21 -11
- data/lib/duckdb/bind_info.rb +32 -0
- data/lib/duckdb/casting.rb +35 -0
- data/lib/duckdb/connection.rb +123 -2
- data/lib/duckdb/converter.rb +32 -47
- data/lib/duckdb/data_chunk.rb +114 -0
- data/lib/duckdb/extracted_statements.rb +1 -1
- data/lib/duckdb/function_info.rb +21 -0
- data/lib/duckdb/init_info.rb +22 -0
- data/lib/duckdb/instance_cache.rb +0 -4
- data/lib/duckdb/interval.rb +1 -1
- data/lib/duckdb/logical_type.rb +46 -5
- data/lib/duckdb/prepared_statement.rb +22 -8
- data/lib/duckdb/result.rb +1 -0
- data/lib/duckdb/scalar_function.rb +119 -0
- data/lib/duckdb/table_function.rb +191 -0
- data/lib/duckdb/vector.rb +20 -0
- data/lib/duckdb/version.rb +1 -1
- data/lib/duckdb.rb +8 -0
- data/sample/async_query.rb +2 -0
- data/sample/async_query_stream.rb +2 -0
- data/sample/issue922.rb +54 -0
- data/sample/issue922_benchmark.rb +169 -0
- data/sample/issue930.rb +49 -0
- data/sample/issue930_benchmark.rb +70 -0
- metadata +30 -57
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require 'duckdb'
|
|
4
|
+
require 'csv'
|
|
5
|
+
require 'stringio'
|
|
6
|
+
|
|
7
|
+
class CSVTableAdapter
|
|
8
|
+
def call(csv, name, columns: nil)
|
|
9
|
+
columns ||= infer_columns(csv)
|
|
10
|
+
DuckDB::TableFunction.create(name:, columns:) do |_func_info, output|
|
|
11
|
+
write_row(csv, output)
|
|
12
|
+
end
|
|
13
|
+
end
|
|
14
|
+
|
|
15
|
+
private
|
|
16
|
+
|
|
17
|
+
def write_row(csv, output)
|
|
18
|
+
line = csv.readline
|
|
19
|
+
if line
|
|
20
|
+
line.each_with_index { |cell, index| output.set_value(index, 0, cell[1]) }
|
|
21
|
+
1
|
|
22
|
+
else
|
|
23
|
+
csv.rewind
|
|
24
|
+
0
|
|
25
|
+
end
|
|
26
|
+
end
|
|
27
|
+
|
|
28
|
+
def infer_columns(csv)
|
|
29
|
+
headers = csv.first.headers
|
|
30
|
+
csv.rewind
|
|
31
|
+
headers.to_h { |header| [header, DuckDB::LogicalType::VARCHAR] }
|
|
32
|
+
end
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
def register_as_table_with_create_table(con, csv, name)
|
|
36
|
+
headers = csv.first.headers
|
|
37
|
+
csv.rewind
|
|
38
|
+
con.execute("CREATE OR REPLACE TABLE #{name} (#{headers.map { |h| "#{h} VARCHAR" }.join(', ')})")
|
|
39
|
+
csv.each do |row|
|
|
40
|
+
values = row.map { |cell| "'#{cell[1]}'" }.join(', ')
|
|
41
|
+
con.execute("INSERT INTO #{name} VALUES (#{values})")
|
|
42
|
+
end
|
|
43
|
+
end
|
|
44
|
+
|
|
45
|
+
DuckDB::TableFunction.add_table_adapter(CSV, CSVTableAdapter.new)
|
|
46
|
+
|
|
47
|
+
csv_data = 'id,name,age'
|
|
48
|
+
csv_data += 100_000.times.map { |i| "\n#{i + 1},Name#{i + 1},#{rand(0..100)}" }.join
|
|
49
|
+
|
|
50
|
+
db = DuckDB::Database.open
|
|
51
|
+
con = db.connect
|
|
52
|
+
con.query('SET threads=1')
|
|
53
|
+
|
|
54
|
+
csv = CSV.new(StringIO.new(csv_data), headers: true)
|
|
55
|
+
start_time = Process.clock_gettime(Process::CLOCK_MONOTONIC)
|
|
56
|
+
con.expose_as_table(csv, 'csv_tf')
|
|
57
|
+
con.query('SELECT * FROM csv_tf()').to_a
|
|
58
|
+
end_time = Process.clock_gettime(Process::CLOCK_MONOTONIC)
|
|
59
|
+
|
|
60
|
+
csv2 = CSV.new(StringIO.new(csv_data), headers: true)
|
|
61
|
+
start_time2 = Process.clock_gettime(Process::CLOCK_MONOTONIC)
|
|
62
|
+
register_as_table_with_create_table(con, csv2, 'csv_ct')
|
|
63
|
+
con.query('SELECT * FROM csv_ct').to_a
|
|
64
|
+
end_time2 = Process.clock_gettime(Process::CLOCK_MONOTONIC)
|
|
65
|
+
|
|
66
|
+
con.close
|
|
67
|
+
db.close
|
|
68
|
+
|
|
69
|
+
puts "Time taken for table function approach: #{end_time - start_time} seconds"
|
|
70
|
+
puts "Time taken for CREATE TABLE approach: #{end_time2 - start_time2} seconds"
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: duckdb
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.4.
|
|
4
|
+
version: 1.4.4.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Masaki Suketa
|
|
@@ -23,62 +23,6 @@ dependencies:
|
|
|
23
23
|
- - ">="
|
|
24
24
|
- !ruby/object:Gem::Version
|
|
25
25
|
version: 3.1.4
|
|
26
|
-
- !ruby/object:Gem::Dependency
|
|
27
|
-
name: bundler
|
|
28
|
-
requirement: !ruby/object:Gem::Requirement
|
|
29
|
-
requirements:
|
|
30
|
-
- - "~>"
|
|
31
|
-
- !ruby/object:Gem::Version
|
|
32
|
-
version: '2.3'
|
|
33
|
-
type: :development
|
|
34
|
-
prerelease: false
|
|
35
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
36
|
-
requirements:
|
|
37
|
-
- - "~>"
|
|
38
|
-
- !ruby/object:Gem::Version
|
|
39
|
-
version: '2.3'
|
|
40
|
-
- !ruby/object:Gem::Dependency
|
|
41
|
-
name: minitest
|
|
42
|
-
requirement: !ruby/object:Gem::Requirement
|
|
43
|
-
requirements:
|
|
44
|
-
- - "~>"
|
|
45
|
-
- !ruby/object:Gem::Version
|
|
46
|
-
version: '5.0'
|
|
47
|
-
type: :development
|
|
48
|
-
prerelease: false
|
|
49
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
50
|
-
requirements:
|
|
51
|
-
- - "~>"
|
|
52
|
-
- !ruby/object:Gem::Version
|
|
53
|
-
version: '5.0'
|
|
54
|
-
- !ruby/object:Gem::Dependency
|
|
55
|
-
name: rake
|
|
56
|
-
requirement: !ruby/object:Gem::Requirement
|
|
57
|
-
requirements:
|
|
58
|
-
- - "~>"
|
|
59
|
-
- !ruby/object:Gem::Version
|
|
60
|
-
version: '13.0'
|
|
61
|
-
type: :development
|
|
62
|
-
prerelease: false
|
|
63
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
64
|
-
requirements:
|
|
65
|
-
- - "~>"
|
|
66
|
-
- !ruby/object:Gem::Version
|
|
67
|
-
version: '13.0'
|
|
68
|
-
- !ruby/object:Gem::Dependency
|
|
69
|
-
name: rake-compiler
|
|
70
|
-
requirement: !ruby/object:Gem::Requirement
|
|
71
|
-
requirements:
|
|
72
|
-
- - ">="
|
|
73
|
-
- !ruby/object:Gem::Version
|
|
74
|
-
version: '0'
|
|
75
|
-
type: :development
|
|
76
|
-
prerelease: false
|
|
77
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
78
|
-
requirements:
|
|
79
|
-
- - ">="
|
|
80
|
-
- !ruby/object:Gem::Version
|
|
81
|
-
version: '0'
|
|
82
26
|
description: This module is Ruby binding for DuckDB database engine. You must have
|
|
83
27
|
the DuckDB engine installed to build/use this module.
|
|
84
28
|
email:
|
|
@@ -90,12 +34,15 @@ extra_rdoc_files: []
|
|
|
90
34
|
files:
|
|
91
35
|
- ".gitattributes"
|
|
92
36
|
- ".github/FUNDING.yml"
|
|
37
|
+
- ".github/copilot-instructions.md"
|
|
38
|
+
- ".github/workflows/linter.yml"
|
|
93
39
|
- ".github/workflows/make_documents.yml"
|
|
94
40
|
- ".github/workflows/test_on_macos.yml"
|
|
95
41
|
- ".github/workflows/test_on_ubuntu.yml"
|
|
96
42
|
- ".github/workflows/test_on_windows.yml"
|
|
97
43
|
- ".gitignore"
|
|
98
44
|
- ".rdoc_options"
|
|
45
|
+
- ".rubocop.yml"
|
|
99
46
|
- CHANGELOG.md
|
|
100
47
|
- CONTRIBUTION.md
|
|
101
48
|
- Dockerfile
|
|
@@ -114,6 +61,8 @@ files:
|
|
|
114
61
|
- duckdb.gemspec
|
|
115
62
|
- ext/duckdb/appender.c
|
|
116
63
|
- ext/duckdb/appender.h
|
|
64
|
+
- ext/duckdb/bind_info.c
|
|
65
|
+
- ext/duckdb/bind_info.h
|
|
117
66
|
- ext/duckdb/blob.c
|
|
118
67
|
- ext/duckdb/blob.h
|
|
119
68
|
- ext/duckdb/column.c
|
|
@@ -124,6 +73,8 @@ files:
|
|
|
124
73
|
- ext/duckdb/connection.h
|
|
125
74
|
- ext/duckdb/converter.h
|
|
126
75
|
- ext/duckdb/conveter.c
|
|
76
|
+
- ext/duckdb/data_chunk.c
|
|
77
|
+
- ext/duckdb/data_chunk.h
|
|
127
78
|
- ext/duckdb/database.c
|
|
128
79
|
- ext/duckdb/database.h
|
|
129
80
|
- ext/duckdb/duckdb.c
|
|
@@ -132,10 +83,16 @@ files:
|
|
|
132
83
|
- ext/duckdb/extconf.rb
|
|
133
84
|
- ext/duckdb/extracted_statements.c
|
|
134
85
|
- ext/duckdb/extracted_statements.h
|
|
86
|
+
- ext/duckdb/function_info.c
|
|
87
|
+
- ext/duckdb/function_info.h
|
|
88
|
+
- ext/duckdb/init_info.c
|
|
89
|
+
- ext/duckdb/init_info.h
|
|
135
90
|
- ext/duckdb/instance_cache.c
|
|
136
91
|
- ext/duckdb/instance_cache.h
|
|
137
92
|
- ext/duckdb/logical_type.c
|
|
138
93
|
- ext/duckdb/logical_type.h
|
|
94
|
+
- ext/duckdb/memory_helper.c
|
|
95
|
+
- ext/duckdb/memory_helper.h
|
|
139
96
|
- ext/duckdb/pending_result.c
|
|
140
97
|
- ext/duckdb/pending_result.h
|
|
141
98
|
- ext/duckdb/prepared_statement.c
|
|
@@ -145,21 +102,30 @@ files:
|
|
|
145
102
|
- ext/duckdb/ruby-duckdb.h
|
|
146
103
|
- ext/duckdb/scalar_function.c
|
|
147
104
|
- ext/duckdb/scalar_function.h
|
|
105
|
+
- ext/duckdb/table_function.c
|
|
106
|
+
- ext/duckdb/table_function.h
|
|
148
107
|
- ext/duckdb/util.c
|
|
149
108
|
- ext/duckdb/util.h
|
|
150
109
|
- ext/duckdb/value_impl.c
|
|
151
110
|
- ext/duckdb/value_impl.h
|
|
111
|
+
- ext/duckdb/vector.c
|
|
112
|
+
- ext/duckdb/vector.h
|
|
152
113
|
- getduckdb.sh
|
|
153
114
|
- lib/duckdb.rb
|
|
154
115
|
- lib/duckdb/appender.rb
|
|
116
|
+
- lib/duckdb/bind_info.rb
|
|
117
|
+
- lib/duckdb/casting.rb
|
|
155
118
|
- lib/duckdb/column.rb
|
|
156
119
|
- lib/duckdb/config.rb
|
|
157
120
|
- lib/duckdb/connection.rb
|
|
158
121
|
- lib/duckdb/converter.rb
|
|
159
122
|
- lib/duckdb/converter/int_to_sym.rb
|
|
123
|
+
- lib/duckdb/data_chunk.rb
|
|
160
124
|
- lib/duckdb/database.rb
|
|
161
125
|
- lib/duckdb/extracted_statements.rb
|
|
126
|
+
- lib/duckdb/function_info.rb
|
|
162
127
|
- lib/duckdb/infinity.rb
|
|
128
|
+
- lib/duckdb/init_info.rb
|
|
163
129
|
- lib/duckdb/instance_cache.rb
|
|
164
130
|
- lib/duckdb/interval.rb
|
|
165
131
|
- lib/duckdb/library_version.rb
|
|
@@ -167,9 +133,16 @@ files:
|
|
|
167
133
|
- lib/duckdb/pending_result.rb
|
|
168
134
|
- lib/duckdb/prepared_statement.rb
|
|
169
135
|
- lib/duckdb/result.rb
|
|
136
|
+
- lib/duckdb/scalar_function.rb
|
|
137
|
+
- lib/duckdb/table_function.rb
|
|
138
|
+
- lib/duckdb/vector.rb
|
|
170
139
|
- lib/duckdb/version.rb
|
|
171
140
|
- sample/async_query.rb
|
|
172
141
|
- sample/async_query_stream.rb
|
|
142
|
+
- sample/issue922.rb
|
|
143
|
+
- sample/issue922_benchmark.rb
|
|
144
|
+
- sample/issue930.rb
|
|
145
|
+
- sample/issue930_benchmark.rb
|
|
173
146
|
homepage: https://github.com/suketa/ruby-duckdb
|
|
174
147
|
licenses:
|
|
175
148
|
- MIT
|