slaw 8.0.0 → 10.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c0c018a71314291d2304ba458300e360da8555bfe6df1d4348fcba8bb4501700
-  data.tar.gz: 5c68a881a0d52f54b28998fe195d877a068361c3750a254e8f88e3479c24f056
+  metadata.gz: ada9248a6af947faeae4212b3d1cffe7b912d90712baf8c7273cc0fbb107c926
+  data.tar.gz: 01ea2d767da2b46bdbaea17566998c46b09e293e334a454e5022d63104981021
 SHA512:
-  metadata.gz: 5538b79f68d5db2289d713a0db9760147bb3baf4a986d63d0a9097fc86af95df6e6b3c8637eeaccd25834b4c79b8cadedf50c107c60833c8fb90382d7559f43f
-  data.tar.gz: d9bdcf5780887407f8ab397e765b6df83de5d54e1898a71792f0560a74044d1216e41b30e6166cc86974719fc4007513db82340c927117dec6087b974b176f1b
+  metadata.gz: 04a40af1f73282bdf912213451ca7e37e7538a77373c42ae294979bf91bf240b0a22e4b09e3816f303324f3e6e463cf2d16f81b240fd94d692e13c9fe0dc1d87
+  data.tar.gz: 49cb6f91a31977c3bc6808baee29da7e014a4743d677234b9da83d1ec9cfbdd539daee2b03d6b9878382d7b4bd0b63fe6227f8f083151d412bced1dbc40ef6a1

data/.travis.yml

@@ -1,7 +1,7 @@
 language: ruby
 rvm:
+  - 2.7.0
   - 2.6.2
   - 2.5.4
-  - 2.4.5
 before_install:
   - gem update bundler

data/README.md

@@ -1,6 +1,6 @@
 # Slaw [![Build Status](https://travis-ci.org/longhotsummer/slaw.svg)](http://travis-ci.org/longhotsummer/slaw) [![Gem Version](https://badge.fury.io/rb/slaw.svg)](https://badge.fury.io/rb/slaw)
 
-Slaw is a lightweight library for generating Akoma Ntoso 2.0 Act XML from plain text documents.
+Slaw is a lightweight library for generating Akoma Ntoso 3.0 Act XML from plain text documents.
 It is used to power [Indigo](https://github.com/laws-africa/indigo) and uses grammars developed for the legal
 tradition in South Africa, although others traditions are supported.
 
@@ -79,8 +79,38 @@ You can create your own grammar by creating a gem that provides these files and
 7. Push to the branch: `git push origin my-new-feature`
 8. Create a new Pull Request
 
+## Releasing
+
+1. Update `lib/slaw/version.rb`
+2. Run `rake release`
+
 ## Changelog
 
+### 10.0.0 (12 June 2020)
+
+* BREAKING: Create XML with AKN 3 namespace (http://docs.oasis-open.org/legaldocml/ns/akn/3.0), AKN2 is no longer supported
+* BREAKING: replace id attributes with eId attributes
+* BREAKING: serialize schedules as attachments to act, not as components as peers of the act
+* BREAKING: anonymous blocks are serialized as hcontainers, not paragraphs
+* BREAKING: crossheading hcontainer IDs correctly use hcontainer
+* Remove unnecessary schemaLocation header in root element
+
+### 9.2.0 (10 June 2020)
+
+* Subpart numbers are optional
+
+### 9.1.0 (15 April 2020)
+
+* Subsections can have numbers such as 1.1A and 1.1bis
+
+### 9.0.0 (17 Mar 2020)
+
+* Support SUBPART
+
+### 8.0.1 (26 Feb 2020)
+
+* Fix bug with id prefix on schedules container
+
 ### 8.0.0 (19 Feb 2020)
 
 * Obey --id-prefix for group nodes

data/bin/slaw

@@ -19,6 +19,7 @@ class SlawCLI < Thor
   option :section_number_position, enum: ['before-title', 'after-title', 'guess'], desc: "Where do section titles come in relation to the section number? Default: before-title"
   option :grammar, type: :string, desc: "Grammar name (usually a two-letter country code). Default is za."
   option :ascii, type: :boolean, default: false, desc: "Process text as ASCII using %-encoding. This can provide significant speed improvements if the grammar uses only ASCII literals. See https://github.com/cjheath/treetop/issues/31."
+  option :namespace, enum: ['akn3'], default: 'akn3', desc: 'AKN XML namespace to use.'
   def parse(name)
     logging
 
@@ -33,6 +34,11 @@ class SlawCLI < Thor
       text = extractor.extract_from_file(name)
     end
 
+    case options[:namespace]
+    when 'akn3'
+      Slaw.akn_namespace = Slaw::AKN3_NS
+    end
+
     generator = Slaw::ActGenerator.new(options[:grammar] || 'za')
 
     if options[:fragment]
@@ -49,7 +55,7 @@ class SlawCLI < Thor
 
       if options[:id_prefix]
         prefix = options[:id_prefix]
-        prefix += "." unless prefix.end_with?('.')
+        prefix += "__" unless prefix.end_with?('__')
         generator.builder.fragment_id_prefix = prefix
       end
     end

data/lib/slaw/grammars/counters.rb

@@ -4,16 +4,14 @@ module Slaw
       # Counters for generating element IDs. This is a hash from the element ID
       # prefix, to another hash that maps the element type name to a count.
       #
-      # For backwards compatibility, counters always start at -1, and must be
-      # incremented before being used. This ensures that element ids start at 0.
-      # This is NOT compatible with AKN 3.0 which requires that element numbers
-      # start at 1.
+      # Counters always start at 0, and must be incremented before being used.
+      # This ensures that element ids start at 1, as per AKN 3.0 spec.
       #
       # eg.
       #
       #   section-1 => paragraph => 2
       #
-      @@counters = Hash.new{ |h, k| h[k] = Hash.new(-1) }
+      @@counters = Hash.new{ |h, k| h[k] = Hash.new(0) }
 
       def self.counters
         @@counters
@@ -22,6 +20,25 @@ module Slaw
       def self.reset!
         @@counters.clear
       end
+
+      # Clean a <num> value for use in an eId
+      # See https://docs.oasis-open.org/legaldocml/akn-nc/v1.0/os/akn-nc-v1.0-os.html#_Toc531692306
+      #
+      # The number part of the identifiers of such elements corresponds to the
+      # stripping of all final punctuation, meaningless separations as well as
+      # redundant characters in the content of the <num> element. The
+      # representation is case-sensitive
+      #
+      # (i) -> i
+      # 1.2. -> 1-2
+      # 3a bis -> 3abis
+      def self.clean(num)
+        num
+          .gsub(/[ ()\[\]]/, '')
+          .gsub(/\.+$/, '')
+          .gsub(/^\.+/, '')
+          .gsub(/\.+/, '-')
+      end
     end
   end
 end

data/lib/slaw/grammars/schedules_nodes.rb

@@ -9,10 +9,10 @@ module Slaw
       MANIFESTATION_URI = EXPRESSION_URI
 
       class ScheduleContainer < Treetop::Runtime::SyntaxNode
-        def to_xml(b)
-          b.components { |b| 
+        def to_xml(b, idprefix="")
+          b.attachments { |b|
             schedules.children.elements.each_with_index { |e, i|
-              e.to_xml(b, "", i+1)
+              e.to_xml(b, idprefix, i+1)
             }
           }
         end
@@ -86,6 +86,9 @@ module Slaw
         end
 
         def to_xml(b, idprefix=nil, i=1)
+          # reset counters for this new schedule document
+          Slaw::Grammars::Counters.reset!
+
           heading_text = self.schedule_title.heading_text
           if not heading_text
             heading_text = "Schedule"
@@ -95,12 +98,13 @@ module Slaw
           # the schedule id is derived from the heading
           schedule_id = self.schedule_id(heading_text, i)
 
-          b.component(id: "component-#{schedule_id}") { |b|
-            b.doc_(name: schedule_id) { |b|
+          b.attachment(eId: "att_#{i}") { |b|
+            schedule_title.to_xml(b, '', heading_text)
+            b.doc_(name: "schedule") { |b|
               b.meta { |b|
                 b.identification(source: "#slaw") { |b|
                   b.FRBRWork { |b|
-                    b.FRBRthis(value: "#{WORK_URI}/#{schedule_id}")
+                    b.FRBRthis(value: "#{WORK_URI}/!#{schedule_id}")
                     b.FRBRuri(value: WORK_URI)
                     b.FRBRalias(value: heading_text)
                     b.FRBRdate(date: '1980-01-01', name: 'Generation')
@@ -108,14 +112,14 @@ module Slaw
                     b.FRBRcountry(value: 'za')
                   }
                   b.FRBRExpression { |b|
-                    b.FRBRthis(value: "#{EXPRESSION_URI}/#{schedule_id}")
+                    b.FRBRthis(value: "#{EXPRESSION_URI}/!#{schedule_id}")
                     b.FRBRuri(value: EXPRESSION_URI)
                     b.FRBRdate(date: '1980-01-01', name: 'Generation')
                     b.FRBRauthor(href: '#council')
                     b.FRBRlanguage(language: 'eng')
                   }
                   b.FRBRManifestation { |b|
-                    b.FRBRthis(value: "#{MANIFESTATION_URI}/#{schedule_id}")
+                    b.FRBRthis(value: "#{MANIFESTATION_URI}/!#{schedule_id}")
                     b.FRBRuri(value: MANIFESTATION_URI)
                     b.FRBRdate(date: Time.now.strftime('%Y-%m-%d'), name: 'Generation')
                     b.FRBRauthor(href: '#slaw')
@@ -124,14 +128,7 @@ module Slaw
               }
 
               b.mainBody { |b| 
-                idprefix = "#{schedule_id}."
-
-                # there is no good AKN hierarchy container for schedules, so we
-                # use hcontainer instead
-                b.hcontainer(id: schedule_id, name: "schedule") { |b|
-                  schedule_title.to_xml(b, idprefix, heading_text)
-                  body.children.elements.each_with_index { |e| e.to_xml(b, idprefix, i) } if body.is_a? Body
-                }
+                body.children.elements.each_with_index { |e| e.to_xml(b, '', i) } if body.is_a? Body
               }
             }
           }

data/lib/slaw/grammars/tables_nodes.rb

@@ -3,7 +3,9 @@ module Slaw
     module Tables
       class Table < Treetop::Runtime::SyntaxNode
         def to_xml(b, idprefix, i=0)
-          b.table(id: "#{idprefix}table#{i}") { |b|
+          cnt = Slaw::Grammars::Counters.counters[idprefix]['table'] += 1
+
+          b.table(eId: "#{idprefix}table_#{cnt}") { |b|
             # we'll gather cells into this row list
             rows = []
             cells = []

data/lib/slaw/grammars/terminals.treetop

@@ -20,7 +20,11 @@ module Slaw
       end
 
       rule dotted_number_2
-        number '.' number
+        # 9.1
+        # 9.1A
+        # 9.1A1
+        # NOT: 9.A
+        number '.' number alphanums?
       end
 
       rule number

data/lib/slaw/grammars/za/act.treetop

@@ -44,37 +44,43 @@ module Slaw
 
         rule body
           ('BODY' space? eol)?
-          children:(chapter / part / section / subsection / generic_container)* <Body>
+          children:(chapter / part / subpart / section / subsection / generic_container)* <Body>
         end
 
         # chapter (parts allowed)
         rule chapter
           heading:chapter_heading
-          children:(part_no_chapter / section / subsection / generic_container)*
+          children:(part_no_chapter / subpart / section / subsection / generic_container)*
           <Chapter>
         end
 
         # part (chapters allowed)
         rule part
           heading:part_heading
-          children:(chapter_no_part / section / subsection / generic_container)*
+          children:(chapter_no_part / subpart / section / subsection / generic_container)*
           <Part>
         end
 
         # part (no chapters)
         rule part_no_chapter
           heading:part_heading
-          children:(section / subsection / generic_container)*
+          children:(subpart / section / subsection / generic_container)*
           <Part>
         end
 
         # chapter (no parts)
         rule chapter_no_part
           heading:chapter_heading
-          children:(section / subsection / generic_container)*
+          children:(subpart / section / subsection / generic_container)*
           <Chapter>
         end
 
+        rule subpart
+          heading:subpart_heading
+          children:(section / subsection / generic_container)*
+          <Subpart>
+        end
+
         rule section
           section_title
           children:(subsection / generic_container)* <Section>
@@ -134,6 +140,10 @@ module Slaw
           children:part_no_chapter+ <GroupNode>
         end
 
+        rule subparts
+          children:subpart+ <GroupNode>
+        end
+
         rule sections
           children:section+ <GroupNode>
         end
@@ -151,6 +161,11 @@ module Slaw
           <PartHeading>
         end
 
+        rule subpart_heading
+          space? subpart_heading_prefix heading:(newline? space? inline_items)? eol
+          <SubpartHeading>
+        end
+
         rule section_title
           section_title_1 / section_1_title
         end
@@ -241,6 +256,10 @@ module Slaw
           'part'i space alphanums [ :-]*
         end
 
+        rule subpart_heading_prefix
+          'subpart'i num:(space alphanums)? [ :-]*
+        end
+
         rule chapter_heading_prefix
           'chapter'i space alphanums [ :-]*
         end
@@ -275,12 +294,12 @@ module Slaw
 
         rule body_hierarchy_prefix
           # Text that indicates the start of a hierarchy element, in the body
-          chapter_heading / part_heading / section_title / schedule_title / subsection_prefix / crossheading
+          chapter_heading / part_heading / subpart_heading / section_title / schedule_title / subsection_prefix / crossheading
         end
 
         rule non_body_hierarchy_prefix
           # Text that indicates the start of a hierarchy element, in the preamble or preface
-          chapter_heading / part_heading / section_title / schedule_title / crossheading
+          chapter_heading / part_heading / subpart_heading / section_title / schedule_title / crossheading
         end
 
         include Slaw::Grammars::Inlines

data/lib/slaw/grammars/za/act_nodes.rb

@@ -12,13 +12,13 @@ module Slaw
           MANIFESTATION_URI = EXPRESSION_URI
 
           def to_xml(b, idprefix=nil, i=0)
-            b.act(contains: "originalVersion") { |b|
+            b.act(contains: 'originalVersion', name: 'act') { |b|
               write_meta(b)
               write_preface(b)
               write_preamble(b)
               write_body(b)
+              write_schedules(b)
             }
-            write_schedules(b)
           end
 
           def write_meta(b)
@@ -26,8 +26,8 @@ module Slaw
               write_identification(b)
 
               b.references(source: "#this") {
-                b.TLCOrganization(id: 'slaw', href: 'https://github.com/longhotsummer/slaw', showAs: "Slaw")
-                b.TLCOrganization(id: 'council', href: '/ontology/organization/za/council', showAs: "Council")
+                b.TLCOrganization(eId: 'slaw', href: 'https://github.com/longhotsummer/slaw', showAs: "Slaw")
+                b.TLCOrganization(eId: 'council', href: '/ontology/organization/za/council', showAs: "Council")
               }
             }
           end
@@ -38,7 +38,7 @@ module Slaw
               b.FRBRWork { |b|
                 b.FRBRthis(value: "#{WORK_URI}/main")
                 b.FRBRuri(value: WORK_URI)
-                b.FRBRalias(value: 'Short Title')
+                b.FRBRalias(value: 'Short Title', name: 'title')
                 b.FRBRdate(date: '1980-01-01', name: 'Generation')
                 b.FRBRauthor(href: '#council')
                 b.FRBRcountry(value: 'za')
@@ -125,7 +125,7 @@ module Slaw
             if !stmts.empty?
               b.preamble { |b|
                 stmts.each { |e|
-                  e.preamble_statement.to_xml(b, "")
+                  e.preamble_statement.to_xml(b, "preamble__")
                 }
               }
             end
@@ -138,11 +138,11 @@ module Slaw
           end
 
           def to_xml(b, id_prefix='', *args)
-            id = id_prefix + "part-#{num}"
+            id = id_prefix + "part_#{Slaw::Grammars::Counters.clean(num)}"
 
-            b.part(id: id) { |b|
+            b.part(eId: id) { |b|
               heading.to_xml(b)
-              children.elements.each_with_index { |e, i| e.to_xml(b, id + '.', i) }
+              children.elements.each_with_index { |e, i| e.to_xml(b, id + '__', i) }
             }
           end
         end
@@ -162,17 +162,54 @@ module Slaw
           end
         end
 
+        class Subpart < Treetop::Runtime::SyntaxNode
+          def num
+            heading.num
+          end
+
+          def to_xml(b, id_prefix='', *args)
+            num = self.num
+            if num.empty?
+              num = Slaw::Grammars::Counters.counters[id_prefix]['subpart'] += 1
+            else
+              num = Slaw::Grammars::Counters.clean(num)
+            end
+
+            id = id_prefix + "subpart_#{num}"
+
+            b.subpart(eId: id) { |b|
+              heading.to_xml(b)
+              children.elements.each_with_index { |e, i| e.to_xml(b, id + '__', i) }
+            }
+          end
+        end
+
+        class SubpartHeading < Treetop::Runtime::SyntaxNode
+          def num
+            subpart_heading_prefix.num.text_value.strip()
+          end
+
+          def to_xml(b)
+            b.num(num) unless self.num.empty?
+            if heading.respond_to? :inline_items
+              b.heading { |b|
+                heading.inline_items.to_xml(b)
+              }
+            end
+          end
+        end
+
         class Chapter < Treetop::Runtime::SyntaxNode
           def num
             heading.num
           end
 
           def to_xml(b, id_prefix='', *args)
-            id = id_prefix + "chapter-#{num}"
+            id = id_prefix + "chp_#{Slaw::Grammars::Counters.clean(num)}"
 
-            b.chapter(id: id) { |b|
+            b.chapter(eId: id) { |b|
               heading.to_xml(b)
-              children.elements.each_with_index { |e, i| e.to_xml(b, id + '.', i) }
+              children.elements.each_with_index { |e, i| e.to_xml(b, id + '__', i) }
             }
           end
         end
@@ -198,11 +235,11 @@ module Slaw
           end
 
           def to_xml(b, *args)
-            id = "section-#{num}"
-            b.section(id: id) { |b|
+            id = "sec_#{Slaw::Grammars::Counters.clean(num)}"
+            b.section(eId: id) { |b|
               section_title.to_xml(b)
 
-              idprefix = "#{id}."
+              idprefix = "#{id}__"
               children.elements.each_with_index { |e, i| e.to_xml(b, idprefix, i) }
             }
           end
@@ -273,11 +310,11 @@ module Slaw
 
         class BlockElements < Treetop::Runtime::SyntaxNode
           def to_xml(b, idprefix='', i=0)
-            cnt = Slaw::Grammars::Counters.counters[idprefix]['paragraph'] += 1
-            id = "#{idprefix}paragraph#{cnt}"
-            idprefix = "#{id}."
+            cnt = Slaw::Grammars::Counters.counters[idprefix]['hcontainer'] += 1
+            id = "#{idprefix}hcontainer_#{cnt}"
+            idprefix = "#{id}__"
 
-            b.paragraph(id: id) { |b|
+            b.hcontainer(eId: id) { |b|
               b.content { |b|
                 elements.each_with_index { |e, i| e.to_xml(b, idprefix, i) }
               }
@@ -291,10 +328,10 @@ module Slaw
           end
 
           def to_xml(b, idprefix, i)
-            id = idprefix + num.gsub(/[()]/, '')
-            idprefix = id + "."
+            id = idprefix + "subsec_" + Slaw::Grammars::Counters.clean(num)
+            idprefix = id + "__"
 
-            b.subsection(id: id) { |b|
+            b.subsection(eId: id) { |b|
               b.num(num)
               block_elements_with_inline.to_xml(b, idprefix)
             }
@@ -306,10 +343,10 @@ module Slaw
           # yield to it a builder to insert a listIntroduction node
           def to_xml(b, idprefix, i=0, &block)
             cnt = Slaw::Grammars::Counters.counters[idprefix]['list'] += 1
-            id = idprefix + "list#{cnt}"
-            idprefix = id + '.'
+            id = idprefix + "list_#{cnt}"
+            idprefix = id + '__'
 
-            b.blockList(id: id, renest: true) { |b|
+            b.blockList(eId: id, renest: true) { |b|
               b.listIntroduction { |b| yield b } if block_given?
 
               elements.each { |e| e.to_xml(b, idprefix) }
@@ -323,7 +360,7 @@ module Slaw
           end
 
           def to_xml(b, idprefix)
-            b.item(id: idprefix + num.gsub(/[()]/, '')) { |b|
+            b.item(eId: idprefix + "item_" + Slaw::Grammars::Counters.clean(num)) { |b|
               b.num(num)
               b.p { |b|
                 item_content.inline_items.to_xml(b, idprefix) if respond_to? :item_content and item_content.respond_to? :inline_items
@@ -334,10 +371,10 @@ module Slaw
 
         class Crossheading < Treetop::Runtime::SyntaxNode
           def to_xml(b, idprefix, i=0)
-            cnt = Slaw::Grammars::Counters.counters[idprefix]['crossheading'] += 1
-            id = "#{idprefix}crossheading-#{cnt}"
+            cnt = Slaw::Grammars::Counters.counters[idprefix]['hcontainer'] += 1
+            id = "#{idprefix}hcontainer_#{cnt}"
 
-            b.hcontainer(id: id, name: 'crossheading') { |b|
+            b.hcontainer(eId: id, name: 'crossheading') { |b|
               b.heading { |b|
                 inline_items.to_xml(b, idprefix)
               }