sequelizer 0.1.6 → 0.2.0

data/Gemfile

@@ -4,7 +4,7 @@ source 'https://rubygems.org'
 gemspec
 
 group :development do
-  gem 'overcommit', '~> 0.60'
+  gem 'overcommit', '~> 0.68'
 end
 
 group :test do

data/Gemfile.lock

@@ -1,54 +1,61 @@
 GIT
   remote: https://github.com/outcomesinsights/sequel-hexspace.git
-  revision: d041282798332227bbdf0a48a07c0494b2b54931
+  revision: 91ff040fac46380e2b35406ab4c8a7041beacd25
   branch: master
   specs:
     sequel-hexspace (1.0.0)
-      hexspace
+      hexspace (>= 0.2.1)
       sequel (~> 5.0)
 
 PATH
   remote: .
   specs:
-    sequelizer (0.1.6)
-      activesupport (~> 7.0)
-      dotenv (~> 2.1)
-      hashie (~> 3.2)
+    sequelizer (0.2.0)
+      activesupport (>= 7, < 9)
+      dotenv (>= 2.1, < 4.0)
+      hashie (>= 3.2, < 6.0)
+      kvcsv (~> 0.1)
+      pp
       sequel (~> 5.93)
       thor (~> 1.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (7.2.2.1)
+    activesupport (8.1.2)
       base64
-      benchmark (>= 0.3)
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.3.1)
       connection_pool (>= 2.2.5)
       drb
       i18n (>= 1.6, < 2)
+      json
       logger (>= 1.4.2)
       minitest (>= 5.1)
       securerandom (>= 0.3)
       tzinfo (~> 2.0, >= 2.0.5)
+      uri (>= 0.13.1)
+    addressable (2.8.8)
+      public_suffix (>= 2.0.2, < 8.0)
     ast (2.4.3)
     base64 (0.3.0)
-    benchmark (0.4.1)
-    bigdecimal (3.2.2)
+    bigdecimal (4.0.1)
     childprocess (5.1.0)
       logger (~> 1.5)
     coderay (1.1.3)
-    concurrent-ruby (1.3.5)
-    connection_pool (2.5.3)
+    concurrent-ruby (1.3.6)
+    connection_pool (3.0.2)
+    csv (3.3.5)
     docile (1.4.1)
-    dotenv (2.7.5)
+    dotenv (3.2.0)
     drb (2.2.3)
-    ffi (1.16.3)
-    formatador (1.1.0)
-    guard (2.18.1)
+    ffi (1.17.3-x86_64-linux-gnu)
+    formatador (1.2.3)
+      reline
+    guard (2.20.1)
       formatador (>= 0.2.4)
       listen (>= 2.7, < 4.0)
+      logger (~> 1.6)
       lumberjack (>= 1.0.12, < 2.0)
       nenv (~> 0.1)
       notiffany (~> 0.0)
@@ -56,98 +63,122 @@ GEM
       shellany (~> 0.0)
       thor (>= 0.18.1)
     guard-compat (1.2.1)
-    guard-minitest (2.4.6)
+    guard-minitest (3.0.0)
       guard-compat (~> 1.2)
-      minitest (>= 3.0)
-    hashie (3.6.0)
-    hexspace (0.2.1)
+      minitest (>= 5.0.4, < 7.0)
+    hashie (5.1.0)
+      logger
+    hexspace (0.3.0)
+      bigdecimal
       thrift (>= 0.18)
-    i18n (1.14.7)
+    i18n (1.14.8)
       concurrent-ruby (~> 1.0)
     iniparse (1.5.0)
-    json (2.12.2)
+    io-console (0.8.2)
+    json (2.18.1)
+    json-schema (6.1.0)
+      addressable (~> 2.8)
+      bigdecimal (>= 3.1, < 5)
+    kvcsv (0.1.0)
+      csv (~> 3.0)
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)
-    listen (3.8.0)
+    listen (3.10.0)
+      logger
       rb-fsevent (~> 0.10, >= 0.10.3)
       rb-inotify (~> 0.9, >= 0.9.10)
     logger (1.7.0)
-    lumberjack (1.2.10)
-    method_source (1.0.0)
-    minitest (5.21.2)
+    lumberjack (1.4.2)
+    mcp (0.7.1)
+      json-schema (>= 4.1)
+    method_source (1.1.0)
+    minitest (6.0.2)
+      drb (~> 2.0)
+      prism (~> 1.5)
+    minitest-mock (5.27.0)
     nenv (0.3.0)
     notiffany (0.1.3)
       nenv (~> 0.1)
       shellany (~> 0.0)
-    overcommit (0.67.1)
+    overcommit (0.68.0)
       childprocess (>= 0.6.3, < 6)
       iniparse (~> 1.4)
       rexml (>= 3.3.9)
     parallel (1.27.0)
-    parser (3.3.8.0)
+    parser (3.3.10.2)
       ast (~> 2.4.1)
       racc
-    pg (1.6.2-x86_64-linux)
-    prism (1.4.0)
-    pry (0.14.2)
+    pg (1.6.3-x86_64-linux)
+    pp (0.6.3)
+      prettyprint
+    prettyprint (0.2.0)
+    prism (1.9.0)
+    pry (0.16.0)
       coderay (~> 1.1)
       method_source (~> 1.0)
+      reline (>= 0.6.0)
+    public_suffix (7.0.2)
     racc (1.8.1)
     rainbow (3.1.1)
-    rake (12.3.3)
+    rake (13.3.1)
     rb-fsevent (0.11.2)
-    rb-inotify (0.10.1)
+    rb-inotify (0.11.1)
       ffi (~> 1.0)
-    regexp_parser (2.10.0)
-    rexml (3.4.1)
-    rubocop (1.76.2)
+    regexp_parser (2.11.3)
+    reline (0.6.3)
+      io-console (~> 0.5)
+    rexml (3.4.4)
+    rubocop (1.85.0)
       json (~> 2.3)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.1.0)
+      mcp (~> 0.6)
       parallel (~> 1.10)
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 2.9.3, < 3.0)
-      rubocop-ast (>= 1.45.1, < 2.0)
+      rubocop-ast (>= 1.49.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 4.0)
-    rubocop-ast (1.45.1)
+    rubocop-ast (1.49.0)
       parser (>= 3.3.7.2)
-      prism (~> 1.4)
-    rubocop-minitest (0.38.1)
+      prism (~> 1.7)
+    rubocop-minitest (0.39.1)
       lint_roller (~> 1.1)
       rubocop (>= 1.75.0, < 2.0)
       rubocop-ast (>= 1.38.0, < 2.0)
     ruby-progressbar (1.13.0)
     securerandom (0.4.1)
-    sequel (5.93.0)
+    sequel (5.101.0)
       bigdecimal
     shellany (0.0.1)
     simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
       simplecov_json_formatter (~> 0.1)
-    simplecov-html (0.13.1)
+    simplecov-html (0.13.2)
     simplecov_json_formatter (0.1.4)
-    thor (1.3.0)
-    thrift (0.19.0)
+    thor (1.5.0)
+    thrift (0.22.0)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
-    unicode-display_width (3.1.4)
-      unicode-emoji (~> 4.0, >= 4.0.4)
-    unicode-emoji (4.0.4)
+    unicode-display_width (3.2.0)
+      unicode-emoji (~> 4.1)
+    unicode-emoji (4.2.0)
+    uri (1.1.1)
 
 PLATFORMS
   x86_64-linux
 
 DEPENDENCIES
-  bundler (~> 2.0)
+  bundler (>= 2.0)
   guard (~> 2.0)
-  guard-minitest (~> 2.3)
-  minitest (~> 5.3)
-  overcommit (~> 0.60)
+  guard-minitest (~> 3.0)
+  minitest (~> 6.0)
+  minitest-mock (~> 5.27)
+  overcommit (~> 0.68)
   pg (~> 1.0)
-  rake (~> 12.0)
+  rake (~> 13.3)
   rubocop (~> 1.0)
   rubocop-minitest (~> 0.25)
   sequel-hexspace!
@@ -155,4 +186,4 @@ DEPENDENCIES
   simplecov (~> 0.22)
 
 BUNDLED WITH
-   2.4.7
+   2.6.9

data/config/platforms/base.csv

@@ -0,0 +1,5 @@
+key,value
+supports_cte,true
+supports_cte_recursive,true
+supports_temp_tables,true
+drop_table_needs_unquoted,false

data/config/platforms/rdbms/athena.csv

@@ -0,0 +1,4 @@
+key,value
+supports_temp_tables,false
+supports_cte_recursive,false
+drop_table_needs_unquoted,true

data/config/platforms/rdbms/postgres.csv

@@ -0,0 +1,3 @@
+key,value
+prefers_cte,true
+schema_switching_method,search_path

data/config/platforms/rdbms/snowflake.csv

@@ -0,0 +1 @@
+key,value

data/config/platforms/rdbms/spark.csv

@@ -0,0 +1,3 @@
+key,value
+prefers_cte,false
+prefers_parquet,true

data/lib/sequel/extensions/cold_col.rb

@@ -292,7 +292,7 @@ module Sequel
     # @param opts_chain [Hash] the dataset's query options
     # @return [Array<Symbol>] array of column names from table.* expressions
     def extract_table_star_columns(cols, opts_chain)
-      cols.select { |c| c.is_a?(Sequel::SQL::ColumnAll) }
+      cols.grep(Sequel::SQL::ColumnAll)
           .flat_map { |c| from_named_sources(c.table, opts_chain) }
     end
 
@@ -359,7 +359,7 @@ module Sequel
     # @return [Array<Symbol>, nil] column names if found, nil otherwise
     def find_from_alias(name, opts_chain)
       from = (opts_chain[:from] || [])
-             .select { |f| f.is_a?(Sequel::SQL::AliasedExpression) }
+             .grep(Sequel::SQL::AliasedExpression)
              .detect { |f| literal(f.alias) == literal(name) }
 
       from&.expression&.columns_search(opts_chain)

data/lib/sequel/extensions/funky.rb

@@ -0,0 +1,136 @@
+module Sequel
+
+  module Funky
+
+    class FunkyBase
+
+      def initialize(db)
+        @db = db
+      end
+
+      def to_strptime(format)
+        return format if format =~ /%/
+
+        format.gsub('yyyy', '%Y').gsub('MM', '%m').gsub('dd', '%d')
+      end
+
+      def from_strptime(format)
+        return format unless format =~ /%/
+
+        format.gsub('%Y', 'yyyy').gsub('%m', 'MM').gsub('%d', 'dd')
+      end
+
+    end
+
+    class FunkySpark < FunkyBase
+
+      def str_to_date(value, format, try: false) # rubocop:disable Lint/UnusedMethodArgument
+        Sequel.function(:to_date, Sequel.cast_string(value), format)
+      end
+
+      def hash(*)
+        Sequel.function(:xxhash64, *)
+      end
+
+      def make_json_column(ds, key_column, value_column)
+        json_object_col = Sequel.function(
+          :named_struct,
+          'key',
+          key_column,
+          'value',
+          value_column,
+        ).then do |json_object_col|
+          Sequel.function(
+            :collect_list,
+            json_object_col,
+          )
+        end.then do |list_col|
+          Sequel.function(
+            :map_from_entries,
+            list_col,
+          )
+        end.then do |map_from_entries_col|
+          Sequel.function(
+            :to_json,
+            map_from_entries_col,
+          )
+        end
+        ds.from_self
+          .select(json_object_col)
+          .limit(1)
+      end
+
+      def collect_list(column)
+        Sequel.function(:collect_list, column)
+      end
+
+    end
+
+    class FunkyDuckDB < FunkyBase
+
+      def str_to_date(value, format, try: false)
+        strptime_func = try ? :try_strptime : :strptime
+        Sequel.function(strptime_func, Sequel.cast_string(value), to_strptime(format))
+      end
+
+      def hash(*)
+        Sequel.function(:hash, concat(*)).then do |hash_val|
+          Sequel.case(
+            { hash_val <= 9_223_372_036_854_775_807 => hash_val },
+            hash_val - 18_446_744_073_709_551_616,
+          ).cast(:bigint)
+        end
+      end
+
+      def concat(*)
+        Sequel.function(:concat, *)
+      end
+
+      def make_json_column(ds, key_column, value_column)
+        json_object_col = Sequel.function(
+          :json_object,
+          key_column,
+          value_column,
+        ).then do |json_object_col|
+          Sequel.function(
+            :list,
+            json_object_col,
+          )
+        end
+        ds.from_self
+          .select(json_object_col)
+          .limit(1)
+      end
+
+      def collect_list(column)
+        Sequel.function(:list, column)
+      end
+
+    end
+
+    def self.extended(db)
+      db.instance_exec do
+        @funky = get_funky(db.database_type)
+      end
+    end
+
+    def funky
+      @funky
+    end
+
+    def get_funky(database_type)
+      case database_type
+      when :spark
+        FunkySpark.new(self)
+      when :duckdb
+        FunkyDuckDB.new(self)
+      else
+        raise "No known functions for #{database_type}"
+      end
+    end
+
+  end
+
+  Database.register_extension(:funky, Funky)
+
+end

data/lib/sequel/extensions/make_readyable.rb

@@ -1,5 +1,3 @@
-require 'pathname'
-
 module Sequel
 
   # = MakeReadyable