traject 0.16.0 → 0.17.0

data/test/translation_map_test.rb

@@ -37,7 +37,15 @@ describe "TranslationMap" do
       map = Traject::TranslationMap.new("default_literal")
       map = Traject::TranslationMap.new("default_literal")
 
-      assert_equal "DEFAULT LITERAL", map["not in the map"] 
+      assert_equal "DEFAULT LITERAL", map["not in the map"]
+    end
+
+    it "does not trigger default on explicit nil result" do
+      map = Traject::TranslationMap.new({"alpha" => "one", "beta" => nil}, :default => "DEFAULT")
+
+      assert_equal "one", map["alpha"]
+      assert_nil map["beta"]
+      assert_equal "DEFAULT", map["not_found_in_map"]
     end
 
     it "finds .rb over .yaml" do
@@ -80,12 +88,12 @@ describe "TranslationMap" do
     assert_equal "value1", map["key1"]
   end
 
-  it "finds .properties defn" do 
+  it "finds .properties defn" do
     map =Traject::TranslationMap.new("properties_map")
 
     assert_equal "Value1", map["key1"]
     assert_equal "Value2", map["key2"]
-    assert_equal "Multi word value", map["key3"]   
+    assert_equal "Multi word value", map["key3"]
   end
 
   it "can use a hash instance too" do
@@ -117,6 +125,16 @@ describe "TranslationMap" do
     assert_equal ["hola", "first", "second", "last thing", "buenas noches", "hola", "everything else"], arr
   end
 
+  it "translate_array does not include nil values" do
+    # TranslationMap can explicitly map to nil, meaning,
+    # well, map to nothing. Make sure translate_array respects that.
+    map = Traject::TranslationMap.new("alpha" => "one", "beta" => nil)
+
+    values = map.translate_array(["alpha", "beta"])
+
+    assert_equal ["one"], values
+  end
+
   it "#to_hash" do
     map = Traject::TranslationMap.new("yaml_map")
 
@@ -129,4 +147,4 @@ describe "TranslationMap" do
     refute_same hash, map.to_hash, "each #to_hash result is a copy"
   end
 
-end
+end

data/test/translation_maps/bad_ruby.rb

@@ -1,8 +1,8 @@
-# this is not good ruby code at all. 
+# this is not good ruby code at all.
 
 x+y
 
 This is
   not valid ruby
   * if anything
-    * it's more like markdown
+    * it's more like markdown

data/test/translation_maps/both_map.rb

@@ -1 +1 @@
-{ "ruby" =>  "ruby" }
+{ "ruby" =>  "ruby" }

data/test/translation_maps/default_literal.rb

@@ -7,4 +7,4 @@ some_hash = {
 some_hash["__default__"] = "DEFAULT LITERAL"
 
 # can be other ruby here, last line needs to evaluate as a Hash
-some_hash
+some_hash

data/test/translation_maps/default_passthrough.rb

@@ -7,4 +7,4 @@ some_hash = {
 some_hash["__default__"] = "__passthrough__"
 
 # can be other ruby here, last line needs to evaluate as a Hash
-some_hash
+some_hash

data/test/translation_maps/ruby_map.rb

@@ -7,4 +7,4 @@ some_hash = {
 some_hash["also"] = "this"
 
 # can be other ruby here, last line needs to evaluate as a Hash
-some_hash
+some_hash

metadata

@@ -1,8 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: traject
 version: !ruby/object:Gem::Version
-  prerelease:
-  version: 0.16.0
+  version: 0.17.0
 platform: ruby
 authors:
 - Jonathan Rochkind
@@ -10,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-09-30 00:00:00.000000000 Z
+date: 2013-10-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: marc
@@ -19,13 +18,11 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: 0.7.1
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '>='
       - !ruby/object:Gem::Version
         version: 0.7.1
-    none: false
   prerelease: false
   type: :runtime
 - !ruby/object:Gem::Dependency
@@ -35,13 +32,11 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: 0.1.1
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '>='
       - !ruby/object:Gem::Version
         version: 0.1.1
-    none: false
   prerelease: false
   type: :runtime
 - !ruby/object:Gem::Dependency
@@ -54,7 +49,6 @@ dependencies:
     - - <
       - !ruby/object:Gem::Version
         version: '2.1'
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '>='
@@ -63,7 +57,6 @@ dependencies:
     - - <
       - !ruby/object:Gem::Version
         version: '2.1'
-    none: false
   prerelease: false
   type: :runtime
 - !ruby/object:Gem::Dependency
@@ -76,7 +69,6 @@ dependencies:
     - - <
       - !ruby/object:Gem::Version
         version: '4.0'
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '>='
@@ -85,7 +77,6 @@ dependencies:
     - - <
       - !ruby/object:Gem::Version
         version: '4.0'
-    none: false
   prerelease: false
   type: :runtime
 - !ruby/object:Gem::Dependency
@@ -95,13 +86,11 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-    none: false
   prerelease: false
   type: :runtime
 - !ruby/object:Gem::Dependency
@@ -111,13 +100,11 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
-    none: false
   prerelease: false
   type: :development
 - !ruby/object:Gem::Dependency
@@ -127,13 +114,11 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-    none: false
   prerelease: false
   type: :development
 - !ruby/object:Gem::Dependency
@@ -143,13 +128,11 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-    none: false
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-    none: false
   prerelease: false
   type: :development
 description:
@@ -161,7 +144,7 @@ extensions: []
 extra_rdoc_files:
 - doc/batch_execution.md
 - doc/extending.md
-- doc/macros.md
+- doc/indexing_rules.md
 - doc/other_commands.md
 - doc/settings.md
 files:
@@ -176,7 +159,7 @@ files:
 - bin/traject
 - doc/batch_execution.md
 - doc/extending.md
-- doc/macros.md
+- doc/indexing_rules.md
 - doc/other_commands.md
 - doc/settings.md
 - lib/tasks/load_maps.rake
@@ -285,6 +268,7 @@ files:
 homepage: http://github.com/jrochkind/traject
 licenses:
 - MIT
+metadata: {}
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -293,25 +277,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - '>='
     - !ruby/object:Gem::Version
-      segments:
-      - 0
-      hash: 2
       version: '0'
-  none: false
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - '>='
     - !ruby/object:Gem::Version
-      segments:
-      - 0
-      hash: 2
       version: '0'
-  none: false
 requirements: []
 rubyforge_project:
-rubygems_version: 1.8.24
+rubygems_version: 2.1.5
 signing_key:
-specification_version: 3
+specification_version: 4
 summary: Index MARC to Solr; or generally process source records to hash-like structures
 test_files:
 - test/debug_writer_test.rb

data/doc/macros.md

@@ -1,103 +0,0 @@
-# Traject Indexing 'Macros'
-
-Traject macros are a way of providing re-usable index mapping rules. Before we discuss how they work, we need to remind ourselves of the basic/direct Traject `to_field` indexing method.
-
-## Review and details of direct indexing logic
-
-Here's the simplest possible direct Traject mapping logic, duplicating the effects of the `literal` function:
-
-~~~ruby
-to_field("title") do |record, accumulator, context|
-  accumulator << "FIXED LITERAL"
-end
-~~~
-
-That `do` is just ruby `block` syntax, whereby we can pass a block of ruby code as an argument to to a ruby method. We pass a block taking three arguments, labelled `record`, `accumulator`, and `context`, to the `to_field` method.
-
-The block is then stored by the Traject::Indexer, and called for each record indexed. When it's called, it's passed the particular record at hand for the first argument, an Array used as an 'accumulator' as the second argument, and a Traject::Indexer::Context as the third argument.
-
-The code in the block can add values to the accumulator array, which the Traject::Indexer then adds to the field specified by `to_field`.
-
-It's also worth pointing out that ruby blocks are `closures`, so they can "capture" and use values from outside the block. So this would work too:
-
-~~~ruby
-my_var = "FIXED LITERAL"
-to_field("title") do |record, accumulator, context|
-  accumulator << my_var
-end
-~~~
-
-So that's the way to provide direct logic for mapping rules.
-
-## Macros
-
-A Traject macro is a way to automatically create indexing rules via re-usable "templates".
-
-Traject macros are simply methods that return ruby lambda/proc objects. A ruby lambda is just another syntax for creating blocks of ruby logic that can be passed around as data.
-
-So, for instance, we could capture that fixed literal block in a lambda like this:
-
-~~~ruby
-always_add_black = lambda do |record, accumulator, context|
-   accumulator << "BLACK"
-end
-~~~
-
-Then, knowing that the `to_field` ruby method takes a block, we can use the ruby `&` operator
-to convert our lambda to a block argument. This would in fact work:
-
-~~~ruby
-to_field "color", &always_add_black
-~~~
-
-However, for convenience, the `to_field` method can take a lambda directly (without having to use '&' to convert it to a block argument) as a second argument too. So this would work too:
-
-~~~ruby
-to_field "color", always_add_black
-~~~
-
-A macro is jus more step, using a method to create lambdas dynamically:  A Traject macro is just a ruby method that **returns** a lambda, a three-arg lambda like `to_field` wants.
-
-Here is in fact how the `literal` function is implemented:
-
-~~~ruby
-def literal(value)
-  return lambda do |record, accumulator, context|
-     # because a lambda is a closure, we can define it in terms
-     # of the 'value' from the scope it's defined in!
-     accumulator << value
-  end
-end
-to_field("something"), literal("something")
-~~~
-
-It's really as simple as that, that's all a Traject macro is. A function that takes parameters, and based on those parameters returns a lambda; the lambda is then passed to the `to_field` indexing method, or similar methods.
-
-How do you make these methods available to the indexer?
-
-Define it in a module:
-
-~~~ruby
-# in a file literal_macro.rb
-module LiteralMacro
-  def literal(value)
-    return lambda do |record, accumulator, context|
-       # because a lambda is a closure, we can define it in terms
-       # of the 'value' from the scope it's defined in!
-       accumulator << value
-    end
-  end
-end
-~~~
-
-And then use ordinary ruby `require` and `extend` to add it to the current Indexer file, by simply including this
-in one of your config files:
-
-~~~
-require `literal_macro.rb`
-extend LiteralMacro
-
-to_field ...
-~~~
-
-That's it.  You can use the traject command line `-I` option to set the ruby load path, so your file will be findable via `require`.  Or you can distribute it in a gem, and use straight rubygems and the `gem` command in your configuration file, or Bundler with traject command-line `-g` option.