relaton-iso 1.18.4 → 1.19.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9d84323d65b954dcb15e73fb00917f6420494f11f1dfb5dbb5bf59e8fcae15ef
-  data.tar.gz: f9b9364c9804f46af7ad56d2b1c708a3e98760c9948142686f5ace87807a628c
+  metadata.gz: a66fbf3c95df32417a9bdaea666de8a154ec75d52ed1ef7a7db4a92925a57893
+  data.tar.gz: 05dbd444b033089d02f6334e82b54372c291b6d34cb7b3722b8bf0122abf62bb
 SHA512:
-  metadata.gz: b242baf862c63b243d6a4c41611cc9e6f900cc269e78ed80c36d8e44fabad7a2f2ae6abcf72b8661c65467e52193c4b922d7d15b6cf82c187f5620f5264135cc
-  data.tar.gz: fb95d361df7ed56a0c6b33cc2239a2445f44e7a41f8f217f41a7b337629a3021efe59a11a6686f951fbf79f8fec747dc741978308b1a800c94601f8d0061be36
+  metadata.gz: 70e8782fb0c925a56c329a9ff1a19de812f3055d072a113f1d0af390c7ef51904991bb615f37f912ca079f68ca5105542905f10102969c4aa5296e57b2fae8f7
+  data.tar.gz: 7e404e058db5336e2225428512da3e3d6e507baa6ae6c19a0ba5cde0aa39c5a5326c3dca63e20448c1baafa5beadf7e8193aaa11fdff6ccec6b9ed9789d0b69e

data/README.adoc

@@ -31,24 +31,13 @@ Or install it yourself as:
 
 == Usage
 
-=== Configuration
-
-Configuration is optional. The available option is `logger` which is a `Logger` instance. By default, the logger is `Logger.new($stderr)` with `Logger::WARN` level. To change the logger level, use `RelatonIso.configure` block.
+=== Search for standards using keywords
 
 [source,ruby]
 ----
 require 'relaton_iso'
 => true
 
-RelatonIso.configure do |config|
-  config.logger.level = Logger::DEBUG
-end
-----
-
-=== Search for standards using keywords
-
-[source,ruby]
-----
 hit_collection = RelatonIso::IsoBibliography.search("ISO 19115")
 => <RelatonIso::HitCollection:0x007fa5bc847038 @ref=19115 @fetched=false>
 
@@ -277,7 +266,7 @@ item.to_xml bibdata: true
       <fetched>2022-12-04</fetched>
       <title type="title-intro" format="text/plain" language="en" script="Latn">Geographic information</title>
       ...
-      <ext schema-version="v1.0.0">
+      <ext schema-version="v1.0.3">
         <doctype>international-standard</doctype>
         ...
       </ext>
@@ -360,6 +349,10 @@ item.link
   @type="rss">]
 ----
 
+=== Logging
+
+RelatonIso uses the relaton-logger gem for logging. By default, it logs to STDOUT. To change the log levels and add other loggers, read the https://github.com/relaton/relaton-logger#usage[relaton-logger] documentation.
+
 == 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/bin/{rdebug-ide → pubid-nist}

@@ -4,18 +4,16 @@
 #
 # This file was generated by Bundler.
 #
-# The application 'rdebug-ide' is installed as part of a gem, and
+# The application 'pubid-nist' is installed as part of a gem, and
 # this file is here to facilitate running it.
 #
 
-require "pathname"
-ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
-  Pathname.new(__FILE__).realpath)
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../Gemfile", __dir__)
 
-bundle_binstub = File.expand_path("../bundle", __FILE__)
+bundle_binstub = File.expand_path("bundle", __dir__)
 
 if File.file?(bundle_binstub)
-  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
+  if File.read(bundle_binstub, 300).include?("This file was generated by Bundler")
     load(bundle_binstub)
   else
     abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
@@ -26,4 +24,4 @@ end
 require "rubygems"
 require "bundler/setup"
 
-load Gem.bin_path("ruby-debug-ide", "rdebug-ide")
+load Gem.bin_path("pubid-nist", "pubid-nist")

data/lib/relaton_iso/data_fetcher.rb

@@ -95,12 +95,11 @@ module RelatonIso
       uri = URI(Scrapper::DOMAIN + path)
       begin
         get_response uri
-      rescue Net::OpenTimeout, Net::ReadTimeout => e
+      rescue Net::OpenTimeout, Net::ReadTimeout, Errno::ECONNREFUSED => e
         try += 1
         retry if check_try try, uri
 
-        warn "Error fetching #{uri}"
-        warn e.message
+        Util.error "Error fetching #{uri}, #{e.message}"
       end
     end
 
@@ -111,7 +110,7 @@ module RelatonIso
 
     def check_try(try, uri)
       if try < 3
-        warn "Timeout fetching #{uri}, retrying..."
+        Util.warn "Timeout fetching #{uri}, retrying..."
         sleep 1
         true
       end
@@ -137,9 +136,8 @@ module RelatonIso
       doc = Scrapper.parse_page docpath
       @mutex.synchronize { save_doc doc, docpath }
     rescue StandardError => e
-      warn "Error fetching document: #{Scrapper::DOMAIN}#{docpath}"
-      warn e.message
-      warn e.backtrace
+      Util.error "Error fetching document: #{Scrapper::DOMAIN}#{docpath}\n" \
+        "#{e.message}\n#{e.backtrace}"
     end
 
     # def compare_docids(id1, id2)
@@ -158,7 +156,7 @@ module RelatonIso
       file_name = docid.id.gsub(/[\s\/:]+/, "-").downcase
       file = File.join @output, "#{file_name}.#{@ext}"
       if @files.include? file
-        warn "Duplicate file #{file} for #{docid.id} from #{Scrapper::DOMAIN}#{docpath}"
+        Util.warn "Duplicate file #{file} for #{docid.id} from #{Scrapper::DOMAIN}#{docpath}"
       else
         @files << file
         index.add_or_update docid.to_h, file

data/lib/relaton_iso/document_identifier.rb

@@ -11,7 +11,7 @@ module RelatonIso
       end
       type == "URN" ? @id.urn.to_s : id_str
     rescue Pubid::Iso::Errors::NoEditionError => e
-      Util.warn "WARNING: #{type} identifier can't be generated for #{@id}: #{e.message}"
+      Util.warn "#{type} identifier can't be generated for `#{@id}`: #{e.message}"
     end
 
     def to_h

data/lib/relaton_iso/hit_collection.rb

@@ -47,8 +47,7 @@ module RelatonIso
     def create_pubid(id)
       Pubid::Iso::Identifier.create(**id)
     rescue StandardError => e
-      Util.warn "(#{ref_pubid}) WARNING: #{e.message}"
-      nil
+      Util.warn e.message, key: ref_pubid.to_s
     end
 
     def excludings

data/lib/relaton_iso/iso_bibliography.rb

@@ -38,7 +38,7 @@ module RelatonIso
 
       query_pubid = Pubid::Iso::Identifier.parse(code)
       query_pubid.root.year = year.to_i if year&.respond_to?(:to_i)
-      Util.warn "(#{query_pubid}) Fetching from Relaton repository ..."
+      Util.info "Fetching from Relaton repository ...", key: query_pubid.to_s
 
       hits, missed_year_ids = isobib_search_filter(query_pubid, opts)
       tip_ids = look_up_with_any_types_stages(hits, ref, opts)
@@ -46,13 +46,13 @@ module RelatonIso
       return fetch_ref_err(query_pubid, missed_year_ids, tip_ids) unless ret
 
       response_pubid = ret.docidentifier.first.id # .sub(" (all parts)", "")
-      Util.warn "(#{query_pubid}) Found: `#{response_pubid}`"
+      Util.info "Found: `#{response_pubid}`", key: query_pubid.to_s
       get_all = (query_pubid.root.year && opts[:keep_year].nil?) || opts[:keep_year] || opts[:all_parts]
       return ret if get_all
 
       ret.to_most_recent_reference
     rescue Pubid::Core::Errors::ParseError
-      Util.warn "(#{code}) Is not recognized as a standards identifier."
+      Util.info "Is not recognized as a standards identifier.", key: code
       nil
     end
 
@@ -115,23 +115,23 @@ module RelatonIso
 
     # @param pubid [Pubid::Iso::Identifier] PubID with no results
     def fetch_ref_err(pubid, missed_year_ids, tip_ids) # rubocop:disable Metrics/MethodLength,Metrics/AbcSize
-      Util.warn "(#{pubid}) Not found."
+      Util.info "Not found.", key: pubid.to_s
 
       if missed_year_ids.any?
         ids = missed_year_ids.map { |i| "`#{i}`" }.join(", ")
-        Util.warn "(#{pubid}) TIP: No match for edition year #{pubid.year}, but matches exist for #{ids}."
+        Util.info "TIP: No match for edition year #{pubid.year}, but matches exist for #{ids}.", key: pubid.to_s
       end
 
       if tip_ids.any?
         ids = tip_ids.map { |i| "`#{i}`" }.join(", ")
-        Util.warn "(#{pubid}) TIP: Matches exist for #{ids}."
+        Util.info "TIP: Matches exist for #{ids}.", key: pubid.to_s
       end
 
       if pubid.part
-        Util.warn "(#{pubid}) TIP: If it cannot be found, the document may no longer be published in parts."
+        Util.info "TIP: If it cannot be found, the document may no longer be published in parts.", key: pubid.to_s
       else
-        Util.warn "(#{pubid}) TIP: If you wish to cite all document parts for the reference, " \
-                  "use `#{pubid.to_s(format: :ref_undated)} (all parts)`."
+        Util.info "TIP: If you wish to cite all document parts for the reference, " \
+                  "use `#{pubid.to_s(format: :ref_undated)} (all parts)`.", key: pubid.to_s
       end
 
       nil

data/lib/relaton_iso/scrapper.rb

@@ -218,8 +218,9 @@ module RelatonIso
       case resp.code
       when "200" then [resp, uri]
       when "301" then get_redirection(resp["location"])
+      when "404" then raise RelatonBib::RequestError, "#{uri} not found."
       else
-        sleep 1
+        sleep (2**try)
         get_response uri, try + 1
       end
     end
@@ -279,7 +280,7 @@ module RelatonIso
     # @return [String, nil] ID
     #
     def item_ref(doc)
-      doc.at("//main//section/div/div/div//h1/span[1]")&.text
+      doc.at("//main//section/div/div/div//h1/span[1]")&.text&.strip
     end
 
     # Fetch status.

data/lib/relaton_iso/util.rb

@@ -1,9 +1,6 @@
 module RelatonIso
   module Util
     extend RelatonBib::Util
-
-    def self.logger
-      RelatonIso.configuration.logger
-    end
+    PROGNAME = "relaton-iso".freeze
   end
 end

data/lib/relaton_iso/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RelatonIso
-  VERSION = "1.18.4"
+  VERSION = "1.19.0"
 end

data/lib/relaton_iso.rb

@@ -7,7 +7,6 @@ require "pubid-iso"
 require "relaton/index"
 require "relaton_iso_bib"
 require "relaton_iso/version"
-require "relaton_iso/config"
 require "relaton_iso/util"
 require "relaton_iso/hash_converter"
 require "relaton_iso/hit"

data/relaton_iso.gemspec

@@ -28,5 +28,5 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency "pubid", "~> 0.1.1"
   spec.add_dependency "relaton-index", "~> 0.2.12"
-  spec.add_dependency "relaton-iso-bib", "~> 1.18.0"
+  spec.add_dependency "relaton-iso-bib", "~> 1.19.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: relaton-iso
 version: !ruby/object:Gem::Version
-  version: 1.18.4
+  version: 1.19.0
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-05-30 00:00:00.000000000 Z
+date: 2024-07-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pubid
@@ -44,14 +44,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.18.0
+        version: 1.19.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.18.0
+        version: 1.19.0
 description: 'RelatonIso: retrieve ISO Standards for bibliographic use using the IsoBibliographicItem
   model'
 email:
@@ -81,10 +81,10 @@ files:
 - bin/ldiff
 - bin/nokogiri
 - bin/pry
+- bin/pubid-nist
 - bin/racc
 - bin/rackup
 - bin/rake
-- bin/rdebug-ide
 - bin/rspec
 - bin/rubocop
 - bin/ruby-parse
@@ -93,13 +93,11 @@ files:
 - bin/setup
 - bin/thor
 - lib/relaton_iso.rb
-- lib/relaton_iso/config.rb
 - lib/relaton_iso/data_fetcher.rb
 - lib/relaton_iso/document_identifier.rb
 - lib/relaton_iso/hash_converter.rb
 - lib/relaton_iso/hit.rb
 - lib/relaton_iso/hit_collection.rb
-- lib/relaton_iso/index.rb
 - lib/relaton_iso/iso_bibliography.rb
 - lib/relaton_iso/processor.rb
 - lib/relaton_iso/queue.rb

data/lib/relaton_iso/config.rb

@@ -1,10 +0,0 @@
-module RelatonIso
-  module Config
-    include RelatonBib::Config
-  end
-  extend Config
-
-  class Configuration < RelatonBib::Configuration
-    PROGNAME = "relaton-iso".freeze
-  end
-end

data/lib/relaton_iso/index.rb

@@ -1,132 +0,0 @@
-module RelatonIso
-  # Index.
-  class Index
-    #
-    # Initialise index. If file path is given, read index from file. If file is not
-    # given, look for it in a `/home/USER/.relaton/iso` directory. If file
-    # doesn't exist, or is outdated then fetch index from GitHub.
-    #
-    # @param [String, nil] file path to index file.
-    #
-    def initialize(file = nil)
-      @file = file
-    end
-
-    #
-    # Create index.
-    #
-    # @return [Array<Hash>] index
-    #
-    def index
-      @index ||= read_index || read_from_user_dir || fetch_index
-    end
-
-    #
-    # Add or update index entry.
-    #
-    # @param [RelatonIsoBib::IsoBibliographicItem] item document
-    #
-    # @return [void]
-    #
-    def <<(item)
-      id = item.docidentifier.detect(&:primary).id
-      row = self[id] || begin
-        r = { id: id }
-        index << r
-        r
-      end
-      row[:title] = item.title.first.title.content
-    end
-
-    #
-    # Fetch document from index by ID.
-    #
-    # @param [String] id document ID
-    #
-    # @return [Hash] index entry
-    #
-    def [](id)
-      index.detect { |i| i[:id] == id }
-    end
-
-    #
-    # Save index to file.
-    #
-    # @return [void]
-    #
-    def save
-      serialize_and_save index
-    end
-
-    private
-
-    #
-    # Serialize index and save to file.
-    #
-    # @param [Array<Hash>] idx index
-    #
-    # @return [void]
-    #
-    def serialize_and_save(idx)
-      File.open(@file, "w:UTF-8") do |f|
-        f.puts "---"
-        idx.each do |i|
-          f.puts i.transform_keys(&:to_s).to_yaml.sub("---\n", "")
-        end
-      end
-    end
-
-    #
-    # Read index from file. If file doesn't exist, create empty index.
-    #
-    # @return [Array<Hash>, nil] index
-    #
-    def read_index
-      if @file && File.exist?(@file) then read_file
-      elsif @file then []
-      end
-    end
-
-    #
-    # Read index from `/home/USER/.relaton/iso` or fetch it from GitHub,
-    # if file doesn't exist, or is outdated.
-    #
-    # @return [Array<Hash>] index
-    #
-    def read_from_user_dir
-      @file = File.join(Dir.home, "index.yml")
-      read_file if File.exist?(@file) && !outdated?
-    end
-
-    def read_file
-      yaml = File.read @file, encoding: "UTF-8"
-      RelatonBib.parse_yaml yaml, [], symbolize_names: true
-    end
-
-    #
-    # Check if index file is outdated.
-    #
-    # @return [Boolean] true if older than 24 hours
-    #
-    def outdated?
-      (Time.now - File.mtime(@file)) / 3600 > 24
-    end
-
-    #
-    # Fetch index from GitHub.
-    #
-    # @return [Array<Hash>] index
-    #
-    def fetch_index
-      url = "https://raw.githubusercontent.com/relaton/relaton-data-iso/master/iso/index.zip"
-      zip = Zip::InputStream.new URI(url).open
-      yaml = zip.get_next_entry.get_input_stream.read
-      idx = RelatonBib.parse_yaml yaml, [], symbolize_names: true
-      serialize_and_save idx
-      idx
-    rescue OpenURI::HTTPError => e
-      warn "[relaton-iso] WARNING: failed to fetch index: #{e.message}"
-      []
-    end
-  end
-end