deltalake-rb 0.1.0 → 0.1.2
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/CHANGELOG.md +16 -0
- data/Cargo.lock +506 -337
- data/README.md +33 -3
- data/ext/deltalake/Cargo.toml +7 -4
- data/ext/deltalake/src/error.rs +62 -15
- data/ext/deltalake/src/features.rs +67 -0
- data/ext/deltalake/src/lib.rs +1114 -48
- data/ext/deltalake/src/merge.rs +205 -0
- data/lib/deltalake/table.rb +170 -10
- data/lib/deltalake/table_alterer.rb +58 -0
- data/lib/deltalake/table_merger.rb +38 -0
- data/lib/deltalake/table_optimizer.rb +67 -0
- data/lib/deltalake/utils.rb +59 -0
- data/lib/deltalake/version.rb +1 -1
- data/lib/deltalake.rb +50 -12
- metadata +8 -2
data/lib/deltalake.rb
CHANGED
@@ -7,12 +7,17 @@ end
|
|
7
7
|
|
8
8
|
# stdlib
|
9
9
|
require "json"
|
10
|
+
require "time"
|
10
11
|
|
11
12
|
# modules
|
12
13
|
require_relative "deltalake/field"
|
13
14
|
require_relative "deltalake/metadata"
|
14
15
|
require_relative "deltalake/schema"
|
15
16
|
require_relative "deltalake/table"
|
17
|
+
require_relative "deltalake/table_alterer"
|
18
|
+
require_relative "deltalake/table_merger"
|
19
|
+
require_relative "deltalake/table_optimizer"
|
20
|
+
require_relative "deltalake/utils"
|
16
21
|
require_relative "deltalake/version"
|
17
22
|
|
18
23
|
module DeltaLake
|
@@ -22,8 +27,43 @@ module DeltaLake
|
|
22
27
|
class CommitFailedError < Error; end
|
23
28
|
class SchemaMismatchError < Error; end
|
24
29
|
|
25
|
-
class
|
30
|
+
class Todo < Error
|
31
|
+
def message
|
32
|
+
"not implemented yet"
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
ProtocolVersions =
|
37
|
+
Struct.new(
|
38
|
+
:min_reader_version,
|
39
|
+
:min_writer_version,
|
40
|
+
:writer_features,
|
41
|
+
:reader_features
|
42
|
+
)
|
43
|
+
|
44
|
+
CommitProperties =
|
45
|
+
Struct.new(
|
46
|
+
:custom_metadata,
|
47
|
+
:max_commit_retries,
|
48
|
+
# TODO
|
49
|
+
# :app_transactions,
|
50
|
+
keyword_init: true
|
51
|
+
)
|
52
|
+
|
53
|
+
PostCommitHookProperties =
|
54
|
+
Struct.new(
|
55
|
+
:create_checkpoint,
|
56
|
+
:cleanup_expired_logs,
|
57
|
+
keyword_init: true
|
58
|
+
)
|
26
59
|
|
60
|
+
class ArrowArrayStream
|
61
|
+
def arrow_c_stream
|
62
|
+
self
|
63
|
+
end
|
64
|
+
end
|
65
|
+
|
66
|
+
class << self
|
27
67
|
def write(
|
28
68
|
table_or_uri,
|
29
69
|
data,
|
@@ -35,7 +75,10 @@ module DeltaLake
|
|
35
75
|
schema_mode: nil,
|
36
76
|
storage_options: nil,
|
37
77
|
predicate: nil,
|
38
|
-
target_file_size: nil
|
78
|
+
target_file_size: nil,
|
79
|
+
writer_properties: nil,
|
80
|
+
commit_properties: nil,
|
81
|
+
post_commithook_properties: nil
|
39
82
|
)
|
40
83
|
table, table_uri = try_get_table_and_table_uri(table_or_uri, storage_options)
|
41
84
|
|
@@ -47,7 +90,7 @@ module DeltaLake
|
|
47
90
|
return
|
48
91
|
end
|
49
92
|
|
50
|
-
data = convert_data(data)
|
93
|
+
data = Utils.convert_data(data)
|
51
94
|
|
52
95
|
write_deltalake_rust(
|
53
96
|
table_uri,
|
@@ -61,7 +104,10 @@ module DeltaLake
|
|
61
104
|
name,
|
62
105
|
description,
|
63
106
|
configuration,
|
64
|
-
storage_options
|
107
|
+
storage_options,
|
108
|
+
writer_properties,
|
109
|
+
commit_properties,
|
110
|
+
post_commithook_properties
|
65
111
|
)
|
66
112
|
|
67
113
|
if table
|
@@ -92,13 +138,5 @@ module DeltaLake
|
|
92
138
|
rescue TableNotFoundError
|
93
139
|
nil
|
94
140
|
end
|
95
|
-
|
96
|
-
def convert_data(data)
|
97
|
-
if data.respond_to?(:arrow_c_stream)
|
98
|
-
data.arrow_c_stream
|
99
|
-
else
|
100
|
-
raise TypeError, "Only objects implementing the Arrow C stream interface are valid inputs for source."
|
101
|
-
end
|
102
|
-
end
|
103
141
|
end
|
104
142
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: deltalake-rb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Andrew Kane
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-
|
11
|
+
date: 2024-12-03 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rb_sys
|
@@ -39,7 +39,9 @@ files:
|
|
39
39
|
- ext/deltalake/Cargo.toml
|
40
40
|
- ext/deltalake/extconf.rb
|
41
41
|
- ext/deltalake/src/error.rs
|
42
|
+
- ext/deltalake/src/features.rs
|
42
43
|
- ext/deltalake/src/lib.rs
|
44
|
+
- ext/deltalake/src/merge.rs
|
43
45
|
- ext/deltalake/src/schema.rs
|
44
46
|
- ext/deltalake/src/utils.rs
|
45
47
|
- lib/deltalake-rb.rb
|
@@ -48,6 +50,10 @@ files:
|
|
48
50
|
- lib/deltalake/metadata.rb
|
49
51
|
- lib/deltalake/schema.rb
|
50
52
|
- lib/deltalake/table.rb
|
53
|
+
- lib/deltalake/table_alterer.rb
|
54
|
+
- lib/deltalake/table_merger.rb
|
55
|
+
- lib/deltalake/table_optimizer.rb
|
56
|
+
- lib/deltalake/utils.rb
|
51
57
|
- lib/deltalake/version.rb
|
52
58
|
homepage: https://github.com/ankane/delta-ruby
|
53
59
|
licenses:
|