traject 3.0.0.alpha.2 → 3.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8d8fb43f0b2c71754358c324beb828ab3fddd77b2bafeee7b7ff525ee85260ad
-  data.tar.gz: ba2556368b6b30559c110b752d99e837387f4f257d473b72518375b129eb9557
+  metadata.gz: cf92e5467d32d37b681a36ae1ffbd2995bbf3e0def938b13d74831a939b68632
+  data.tar.gz: 7c4693ded4a9a8b0e9c599e7489aaefdf9806dfffce6b20ae6054def9ba8c156
 SHA512:
-  metadata.gz: 60f7adf990eb03991b6fea938a729eeab076af76f5de4af54e7a1933d0ffb422925144180d4769c5b9af4a50cd12f60e19479c2d0ae31f26b7440512084f3a9a
-  data.tar.gz: 2e6c120bc9cd820cc708c9bd71dc5d0e91c681341dd29e8c169aaaa0e14cee2282b3362fb4b4d99f71b85a7e642b354e01f727f2c79d6cbcbd07913affd789b1
+  metadata.gz: 9e12113a6f53aa9c7629c072df80b1e347f432d069bd30dbb35d73373fccc3fa341682b281a65c778aa2a3eae9fb7b2d52c81c2f39aa17d348074ecb8b9c2512
+  data.tar.gz: 6f2294bce5deb181a20db0977f8ab7e73e8e1cda6e86d8ee562fabd7a8cce2c683011be8f3955ccafd0165787dbaf774e7c3571220f5d6e797eaf6fe8a02577d

data/.travis.yml

@@ -4,15 +4,14 @@ cache: bundler
 # at downloading jruby, and
 sudo: true
 rvm:
-  - 2.3.6
-  - 2.4.3
+  - 2.4.4
   - 2.5.1
   - "2.6.0-preview2"
 # avoid having travis install jdk on MRI builds where we don't need it.
 matrix:
   include:
     - jdk: openjdk8
-      rvm: jruby-9.0.5.0
+      rvm: jruby-9.1.17.0
     - jdk: openjdk8
       rvm: jruby-9.2.0.0
   allow_failures:

data/README.md

@@ -26,7 +26,7 @@ Initially by Jonathan Rochkind (Johns Hopkins Libraries) and Bill Dueber (Univer
 
 ## Installation
 
-Traject runs under jruby (9.0.x or higher), MRI ruby (2.3.x or higher), or probably any other ruby platform.
+Traject runs under jruby (9.1.x or higher), MRI ruby (2.3.x or higher), or probably any other ruby platform.
 
 Once you have ruby installed, just `$ gem install traject`.
 
@@ -135,12 +135,6 @@ For the syntax and complete possibilities of the specification string argument t
 
 To see all options for `extract_marc`, see the [extract_marc](http://rdoc.info/gems/traject/Traject/Macros/Marc21:extract_marc) method documentation.
 
-There is one special MARC-specific transformation macro, that strips punctuation from beginning and end of values using heuristics designed for AACR2 in MARC:
-
-```ruby
-    to_field "title", extract_marc("245abc"), trim_punctuation
-```
-
 ### XML mode, extract_xml
 
 See our [xml guide](./doc/xml.md) for more XML examples, but you will usually use extract_xpath.
@@ -190,15 +184,15 @@ Example:
 to_field "something", extract_xpath("//value"), strip, default("no value"), prepend("Extracted value: ")
 ```
 
-### Other built-in utility macros
+### Some more MARC-specific utility methods
 
-Other built-in methods that can be used with `to_field` include:
+Other built-in methods that can be used with `to_field` for MARC specifically include:
 
-a hard-coded literal string:
+Strip punctuation from beginning and end of values using heuristics designed for AACR2 in MARC:
 
-~~~ruby
-    to_field "source", literal("LIB_CATALOG")
-~~~
+```ruby
+    to_field "title", extract_marc("245abc"), trim_punctuation
+```
 
 the current record serialized back out as MARC, in binary, XML, or json:
 
@@ -218,7 +212,7 @@ text of all fields in a range:
 
 All of these methods are defined at [Traject::Macros::Marc21](./lib/traject/macros/marc21.rb) ([rdoc](http://rdoc.info/gems/traject/Traject/Macros/Marc21))
 
-## More complex canned MARC semantic logic
+### More complex canned MARC semantic logic
 
 Some more complex (and opinionated/subjective) algorithms for deriving semantics from Marc are also packaged with Traject, but not available by default. To make them available to your indexing, you just need to use ruby `require` and `extend`.
 
@@ -265,7 +259,7 @@ in a configuration file, using a ruby block, which looks like this:
 ~~~
 
 `do |record, accumulator| ... ` is the definition of a ruby block taking
-two arguments.  The first one passed in will be a MARC record. The
+two arguments.  The first one passed in will be a source record (eg MARC or XML). The
 second is an array, you add values to the array to send them to
 output.
 
@@ -296,6 +290,17 @@ use ruby methods like `map!` to modify it:
 If you find yourself repeating boilerplate code in your custom logic, you can
 even create your own 'macros' (like `extract_marc`). `extract_marc`, `translation_map`, `first_only` and other macros are nothing more than methods that return ruby lambda objects of the same format as the blocks you write for custom logic.
 
+In fact, in addition to a literal block on the end, you can pass as many `proc` objects as you want to transform data.
+
+```ruby
+to_field( "something", extract_xpath("//title"),
+          ->(record, acc) { acc << "extra value" },
+          method_that_returns_a_proc
+        ) do |rec, acc|
+     whatever_to(acc)
+end
+```
+
 For tips, gotchas, and a more complete explanation of how this works, see
 additional documentation page on [Indexing Rules: Macros and Custom Logic](./doc/indexing_rules.md)
 

data/doc/xml.md

@@ -58,6 +58,14 @@ to_field "title", extract_xpath("/oai:record/oai:metadata/oai:dc/dc:title", ns:
 })
 ```
 
+If you are accessing a nokogiri method directly, like in `some_record.xpath`, the registered default namespaces aren't known by nokogiri -- but they are available in the indexer as `default_namespaces`, so can be referenced and passed into the nokogiri method:
+
+```ruby
+each_record do |record|
+   log( record.xpath("//dc:title"), default_namespaces )
+end
+```
+
 You can use all the standard transforation macros in Traject::Macros::Transformation:
 
 ```ruby

data/lib/traject/marc_reader.rb

@@ -9,12 +9,12 @@ require 'traject/ndj_reader'
 # the gem traject-marc4j_reader.
 #
 # By default assumes binary MARC encoding, please set marc_source.type setting
-# for XML or json. If binary, please set marc_source.encoding with char encoding. 
+# for XML or json. If binary, please set marc_source.encoding with char encoding.
 #
 # ## Settings
 
 # * "marc_source.type":  serialization type. default 'binary'
-#       * "binary". standard ISO 2709 "binary" MARC format, 
+#       * "binary". standard ISO 2709 "binary" MARC format,
 #           will use ruby-marc MARC::Reader (Note, if you are using
 #          type 'binary', you probably want to also set 'marc_source.encoding')
 #       * "xml", MarcXML, will use ruby-marc MARC::XMLReader
@@ -23,15 +23,16 @@ require 'traject/ndj_reader'
 #         allowed, and no unescpaed internal newlines allowed in the json
 #         objects -- we just read line by line, and assume each line is a
 #         marc-in-json. http://dilettantes.code4lib.org/blog/2010/09/a-proposal-to-serialize-marc-in-json/
-#         will use Traject::NDJReader which uses MARC::Record.new_from_hash. 
+#         will use Traject::NDJReader which uses MARC::Record.new_from_hash.
 # * "marc_source.encoding": Only used for marc_source.type 'binary', character encoding
 #         of the source marc records. Can be any
 #         encoding recognized by ruby, OR 'MARC-8'.  For 'MARC-8', content will
-#         be transcoded (by ruby-marc) to UTF-8 in internal MARC::Record Strings. 
+#         be transcoded (by ruby-marc) to UTF-8 in internal MARC::Record Strings.
 #         Default nil, meaning let MARC::Reader use it's default, which will
-#         probably be Encoding.default_internal, which will probably be UTF-8. 
+#         be your system's Encoding.default_external, which will probably be UTF-8.
+#         (but may be something unexpected/undesired on Windows, where you may want to set this explicitly.)
 #         Right now Traject::MarcReader is hard-coded to transcode to UTF-8 as
-#         an internal encoding. 
+#         an internal encoding.
 # * "marc_reader.xml_parser": For XML type, which XML parser to tell Marc::Reader
 #         to use. Anything recognized by [Marc::Reader :parser
 #         argument](http://rdoc.info/github/ruby-marc/ruby-marc/MARC/XMLReader).
@@ -75,7 +76,7 @@ class Traject::MarcReader
           Traject::NDJReader.new(self.input_stream, settings)
         else
           args = { :invalid => :replace }
-          args[:external_encoding] = settings["marc_source.encoding"]          
+          args[:external_encoding] = settings["marc_source.encoding"]
           MARC::Reader.new(self.input_stream, args)
         end
     end

data/lib/traject/version.rb

@@ -1,3 +1,3 @@
 module Traject
-  VERSION = "3.0.0.alpha.2"
+  VERSION = "3.0.0"
 end

data/test/indexer/nokogiri_indexer_test.rb

@@ -56,6 +56,17 @@ describe "Traject::NokogiriIndexer" do
     refute_empty results.last["rights"]
   end
 
+  it "exposes nokogiri.namespaces setting in default_namespaces" do
+    namespaces = @namespaces
+    @indexer.configure do
+      settings do
+        provide "nokogiri.namespaces", namespaces
+      end
+    end
+    @indexer.settings.fill_in_defaults!
+    assert_equal namespaces, @indexer.default_namespaces
+  end
+
   describe "xpath to non-terminal element" do
     before do
       @xml = <<-EOS

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: traject
 version: !ruby/object:Gem::Version
-  version: 3.0.0.alpha.2
+  version: 3.0.0
 platform: ruby
 authors:
 - Jonathan Rochkind
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-08-30 00:00:00.000000000 Z
+date: 2018-10-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: concurrent-ruby
@@ -381,9 +381,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
 rubygems_version: 2.7.7