csv_orm 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9bb9dcf9aaa806b3e787579a8c0d3d058ef95ac4
-  data.tar.gz: 1ea60c99b878d4b63de6ec17666e0ac90f309759
+  metadata.gz: 40f766dd6da056cc5ab425d390c33a86783b1c1f
+  data.tar.gz: da13ec654fac0cfddb2375f274f6f0f11f099ed4
 SHA512:
-  metadata.gz: 7d63c9a5774ec628d26fd88b823dfdb136efa7d4a875fbe69538fa79c46654fe125ea05e153c2889cd3b118f786bb5d6c076b30d17caba3e869d0a2fdcb645b2
-  data.tar.gz: d1ae0d13d08b6ccfbc89bf262cbc16eabacbf4d8fb55e9784ff73c7e2a304cecd78566d3d2e343e0c77e435a12dd0b73e4776bd3f490c4a42e44ae4e0f30e13b
+  metadata.gz: aba4290e99c36ebd87b7cf0748cc25deb18c278e33346c6e71717bf6496501ca286f6ee2b733efbb05ae6e1c837320af21b92d96a806a6ed3fc7286933005aa0
+  data.tar.gz: 10d975ca6d8985ee36e044415ad1a95604ea6093cfbd973536beba0d9e98d10cabed1fa3b623aad709a9e6e632ec582d807996637b46bda686d5862fd14aa4ac

data/README.md

@@ -28,25 +28,42 @@ Or install it yourself as:
 Now you can do activerecord like queries on the dataset. Currently it supports 3 methods:
 
 ```ruby
-#where_any({key: 'value', other_key: 'other_value'})
-#where_all({key: 'value', other_key: 'other_value'})
-#aggregate(:field1, :field2)
+#where({key: 'value', other_key: 'other_value'}) (all conditions must be met)
+#where_any({key: 'value', other_key: 'other_value'}) (like an 'or' condition)
+#aggregate(:field1, :field2) (count unique values for each field)
 ```
 
 ```ruby
-  # show users who have have any admin access
-  my_data.where_any({admin: true, super_admin: true})
-
   # show users who are admin and named 'Mike'
-  my_data.where_all({admin: true, first_name: 'Mike'})
+  my_data.where({admin: true, first_name: 'Mike'})
+  
+  # show users who have admin access or have last name N-Z
+  my_data.where_any({admin: true, last_name: /^[n-zN-Z].*/})
 
   # give me a break down of orders by their delivery status for users named 'Mike'
-  my_data.where_all({first_name: 'Mike'}).aggregate(:delivery_status)
-  #=> {delivery_status: {placed: 10, processing: 22, shipped: 43, delivered: 8}}
+  my_data.where({first_name: 'Mike'}).aggregate(:delivery_status, :admin)
+  #=> {
+    delivery_status: {placed: 10, processing: 22, shipped: 43, delivered: 25},
+    admin: { true: 45, false: 55 }
+  }
 ```
 
 Maybe more will come...
 
+Ok a little more...
+
+Now supporting an option. `{smart: false}` - If you pass in a false flag, it will not try to convert time fields. Converting will happen internally on ingestion. So in other words, by default, it will take a string like `'2018-01-01'` and convert it to `1514764800`.
+
+Also supporting multiple data types as queryable criteria. You can now do...
+
+```ruby
+data.where({string_field: 'foo'})               # exact match
+data.where({string_field: /\d+/})               # pattern match
+data.where({array_field: ['a', 'b']})           # is one of
+data.where({range_field: (start_day..end_day)}) # is within range, supports numbers/dates
+```
+
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.

data/lib/csv_orm/ingestor.rb

@@ -2,12 +2,13 @@ module CsvOrm
   class Ingestor
     attr_accessor :file, :path, :headers, :headers_defined, :data_set
 
-    def initialize(file_path)
+    def initialize(file_path, options={})
       @path            = File.expand_path(file_path)
       @file            = File.open(path)
       @headers         = [] # will define in first iteration of loop
       @headers_defined = false
       @data_set        = []
+      @smart           = options[:smart] == false ? false : true
     end
 
     def parse
@@ -15,10 +16,21 @@ module CsvOrm
         unless @headers_defined
           @headers = row.map {|header| header.gsub(' ', '_').downcase.to_sym }
         end
-        @data_set << OpenStruct.new(Hash[headers.zip(row.map(&:to_s))]) if @headers_defined
+        parsed_row = row.map {|field| infer_data_type(field) }
+        @data_set << OpenStruct.new(Hash[headers.zip(parsed_row)]) if @headers_defined
         @headers_defined = true
       end
       @data_set
     end
+
+    def infer_data_type(field)
+      # currently supporting time to integer conversion
+      return field.to_s unless @smart
+      date = DateTime.parse(field) rescue nil
+      if date
+        return date.to_time.to_i
+      end
+      field.to_s
+    end
   end
 end

data/lib/csv_orm/query.rb

@@ -22,18 +22,70 @@ module CsvOrm
       agg
     end
 
+    def explain(method, args)
+      case
+      when method == :where 
+        build_expression('&&', args)
+      when method == :where_any
+        build_expression('||', args)
+      else
+        'not supported at this time'
+      end
+    end
+    
     def where_any(attrs)
       expression = build_expression('||', attrs)
       self.class.new(@data.select {|row| eval(expression)});
     end
 
-    def where_all(attrs)
+    def where(attrs)
       expression = build_expression('&&', attrs)
       self.class.new(@data.select {|row| eval(expression)});
     end
 
+    def not(attrs)
+      expression = build_expression('&&', attrs)
+      self.class.new(@data.reject {|row| eval(expression)});
+    end
+
+    def parse_range_values(range)
+      exclude = range.exclude_end?
+      first, last = DateTime.parse(range.begin), DateTime.parse(range.end) rescue nil
+  
+      if first && last
+        Range.new(first.to_time.to_i, last.to_time.to_i, exclude)
+      else
+        range
+      end
+    end
+
+    def build_expression_part(key, value)
+      case
+      when value.class == String
+        "row.send(:#{key}) == '#{value}'"
+      when value.class == Regexp
+        "row.send(:#{key}).match(/#{value.source}/)"
+      when value.class == Array
+        "#{value}.include?(row.send(:#{key}))"
+      when value.class == Range
+        parsed_range_value = parse_range_values(value)
+        "(#{parsed_range_value}).cover?(row.send(:#{key}))"
+      when [TrueClass, FalseClass].include?(value.class)
+        "row.send(:#{key}) == '#{value.to_s}'"
+      end
+    end
+
     def build_expression(conditional, attrs)
-      attrs.each_with_object([]) { |(k,v), array| array << "row.send(:#{k}) == '#{v}'" }.join(" #{conditional} ")
+      string   = ''
+      is_first = true
+
+      attrs.each do |k, v|
+        string << " #{conditional} " unless is_first
+        string << build_expression_part(k, v)
+        
+        is_first = false
+      end
+      string
     end
   end
 end

data/lib/csv_orm/version.rb

@@ -1,3 +1,3 @@
 module CsvOrm
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csv_orm
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Mike Lerner
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-02-24 00:00:00.000000000 Z
+date: 2019-02-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -112,6 +112,7 @@ files:
 - Rakefile
 - bin/console
 - bin/setup
+- csv_orm-0.1.0.gem
 - csv_orm.gemspec
 - lib/csv_orm.rb
 - lib/csv_orm/ingestor.rb