metanorma-plugin-datastruct 0.2.3 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fe622d105e9790da8f5d61265addc954c5718827464c6b7069bfcf4f28b854e2
-  data.tar.gz: aa6fd9ec16c14b9d558631ce6dd3f87a4a5547d7cd917a8651489018ca7b9bdc
+  metadata.gz: 506a0c248f1bcd37ddc11b9927517a0e64244a56e19f482fd2b49e7cf753d1f9
+  data.tar.gz: 933f231c3e43cce3f0d7058a036c4f3d80c028c5a463bc7823d5ff8b938fa417
 SHA512:
-  metadata.gz: 57afedfbda26e055e3b09cc7ea5fd84978c95862039ce7894438ad6acead8dff3551fc9c7980fa006ad98eadfc6d3ed5d1c76dbe465c89df487aaa69be44c642
-  data.tar.gz: 23171c33074450db80cd6c6ab310cfdab19153428bf147beb9a7478edc3d7a61c55a89e29274debece82663ffc9d98d9d886a3193cce259b37e78a1bc40fe046
+  metadata.gz: 49014c580c342ceab3e6a86b2ab9e056ba78f03b76e7e260c5ce44f7de3e139e668670ce99266db3aa2f6fd39a8d71749dcaa8863f60a566890153db81fffebe
+  data.tar.gz: 92c523b5a89060a8754073c5f5fd776a167f160bb2219254325c4ecb1d0f79e180da9cdbf1a75a35169068d55294f1675d2db409a2a9be2e1e0c5d2f607e5859

data/.gitignore

@@ -9,4 +9,8 @@
 
 # rspec failure tracking
 .rspec_status
-Gemfile.lock
+Gemfile.lock
+
+.byebug_history
+*.err
+.rubocop*

data/lib/metanorma/plugin/datastruct/base_structured_text_preprocessor.rb

@@ -8,6 +8,7 @@ require "liquid/custom_blocks/with_yaml_nested_context"
 require "liquid/custom_blocks/with_json_nested_context"
 require "liquid/custom_filters/values"
 require "liquid/custom_filters/replace_regex"
+require "metanorma/plugin/datastruct/source_extractor"
 
 Liquid::Template.register_tag("keyiterator", Liquid::CustomBlocks::KeyIterator)
 Liquid::Template
@@ -28,8 +29,15 @@ module Metanorma
         BLOCK_END_REGEXP = /\A\{[A-Z]+\}\z/.freeze
 
         def process(document, reader)
-          input_lines = reader.readlines.to_enum
-          Asciidoctor::Reader.new(processed_lines(document, input_lines))
+          input_lines = reader.readlines
+          Metanorma::Plugin::Datastruct::SourceExtractor.extract(
+            document,
+            input_lines,
+          )
+
+          Asciidoctor::Reader.new(
+            processed_lines(document, input_lines.to_enum),
+          )
         end
 
         protected
@@ -38,6 +46,10 @@ module Metanorma
           raise ArgumentError, "Implement `content_from_file` in your class"
         end
 
+        def content_from_anchor(_document, _file_path)
+          raise ArgumentError, "Implement `content_from_anchor` in your class"
+        end
+
         private
 
         def processed_lines(document, input_lines)
@@ -109,7 +121,13 @@ module Metanorma
         def parse_template(document, current_block, block_match)
           transformed_liquid_lines = current_block
             .map(&method(:transform_line_liquid))
-          context_items = content_from_file(document, block_match[1])
+
+          context_items = if block_match[1].start_with?("#")
+                            content_from_anchor(document, block_match[1][1..-1])
+                          else
+                            content_from_file(document, block_match[1])
+                          end
+
           parse_context_block(document: document,
                               context_lines: transformed_liquid_lines,
                               context_items: context_items,

data/lib/metanorma/plugin/datastruct/json2_text_preprocessor.rb

@@ -41,6 +41,10 @@ module Metanorma
           JSON.parse(File.read(relative_file_path(document, file_path),
                                encoding: "UTF-8"))
         end
+
+        def content_from_anchor(document, anchor)
+          JSON.parse(document.attributes["source_blocks"][anchor])
+        end
       end
     end
   end

data/lib/metanorma/plugin/datastruct/source_extractor.rb

@@ -0,0 +1,99 @@
+module Metanorma
+  module Plugin
+    module Datastruct
+      class SourceExtractor
+        # example:
+        #   - [[abc]]
+        ANCHOR_REGEX_1 = /^\[\[(?<id>[^\]]*)\]\]\s*$/.freeze
+
+        # examples:
+        #   - [#abc]
+        #   - [source#abc,ruby]
+        ANCHOR_REGEX_2 = /^\[[^#,]*#(?<id>[^,\]]*)[,\]]/.freeze
+
+        # examples:
+        #   - [id=abc]
+        #   - [source,id="abc"]
+        ANCHOR_REGEX_3 = /^\[(?:.+,)?id=['"]?(?<id>[^,\]'"]*)['"]?[,\]]/.freeze
+
+        def initialize(document, input_lines)
+          @document = document
+          @input_lines = input_lines
+
+          @document.attributes["source_blocks"] ||= {}
+        end
+
+        def self.extract(document, input_lines)
+          new(document, input_lines).extract
+        end
+
+        def extract
+          lines = @input_lines.to_enum
+
+          loop do
+            line = lines.next
+
+            if /^embed::|^include::/.match?(line.strip)
+              file_lines = read(filename(@document, line))
+              SourceExtractor.extract(@document, file_lines)
+            elsif m = match_anchor(line)
+              @document.attributes["source_blocks"][m[:id]] = read_section lines
+            end
+          end
+        end
+
+        private
+
+        def match_anchor(line)
+          line.match(ANCHOR_REGEX_1) ||
+            line.match(ANCHOR_REGEX_2) ||
+            line.match(ANCHOR_REGEX_3)
+        end
+
+        def readlines_safe(file)
+          return [] if file.eof?
+
+          file.readlines
+        end
+
+        def read(inc_path)
+          ::File.open inc_path, "r" do |fd|
+            readlines_safe(fd).map(&:chomp)
+          end
+        end
+
+        def filename(document, line)
+          m = /(^include::|^embed::)([^\[]+)\[/.match(line)
+          return nil unless m
+
+          file_path = relative_file_path(document, m[2])
+
+          File.exist?(file_path) ? file_path : nil
+        end
+
+        def relative_file_path(document, file_path)
+          docfile_directory = File.dirname(
+            document.attributes["docfile"] || ".",
+          )
+          document
+            .path_resolver
+            .system_path(file_path, docfile_directory)
+        end
+
+        def read_section(lines)
+          m = lines.next.match(/^--+/)
+          return "" unless m
+
+          end_mark = m[0]
+          current_section = []
+
+          while (line = lines.next) != end_mark
+            current_section << line
+          end
+
+          current_section.join("\n")
+        end
+      end
+    end
+  end
+end

data/lib/metanorma/plugin/datastruct/version.rb

@@ -1,7 +1,7 @@
 module Metanorma
   module Plugin
     module Datastruct
-      VERSION = "0.2.3".freeze
+      VERSION = "0.2.4".freeze
     end
   end
 end

data/lib/metanorma/plugin/datastruct/yaml2_text_preprocessor.rb

@@ -43,7 +43,16 @@ module Metanorma
             File.read(relative_file_path(document, file_path), encoding: "UTF-8"),
             permitted_classes: [Date, Time],
             permitted_symbols: [],
-            aliases: true
+            aliases: true,
+          )
+        end
+
+        def content_from_anchor(document, anchor)
+          YAML.safe_load(
+            document.attributes["source_blocks"][anchor],
+            permitted_classes: [Date, Time],
+            permitted_symbols: [],
+            aliases: true,
           )
         end
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metanorma-plugin-datastruct
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.2.4
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-04-09 00:00:00.000000000 Z
+date: 2023-07-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: asciidoctor
@@ -234,6 +234,7 @@ files:
 - lib/metanorma-plugin-datastruct.rb
 - lib/metanorma/plugin/datastruct/base_structured_text_preprocessor.rb
 - lib/metanorma/plugin/datastruct/json2_text_preprocessor.rb
+- lib/metanorma/plugin/datastruct/source_extractor.rb
 - lib/metanorma/plugin/datastruct/version.rb
 - lib/metanorma/plugin/datastruct/yaml2_text_preprocessor.rb
 - metanorma-plugin-datastruct.gemspec