slaw 9.2.0 → 10.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '0654597e1ede427474f5b9b4f703070c4d23fc34fdbf10700ae72485f8372a21'
-  data.tar.gz: d19cd4ebfe1e256f5366addde1723817547075e6468ab31b0d65c8d492f5c6d1
+  metadata.gz: e20546bab171b4b78f42ebd1d1a38bc246253a25423ff48067483f15d4806f71
+  data.tar.gz: 4f5899aa5565c5a70714c2edb78774468d79620d992deef7c66991c526f63a8a
 SHA512:
-  metadata.gz: a778d4798462049e8fbb123c30d72d2e43c4f7f8344e0bc31590d2c5873daa3675979cafdb3fc14be1327f3ed262c19e6220b2e2ed40e825cc68fe353bb57614
-  data.tar.gz: 585ea851576bca2c5059a3693067066f9f06a9b1ef67761534b707ddcd51f447cc8953f7f7b33842486cb77e442b3f7d60dd63e763306d269db14f1c1b17fcaa
+  metadata.gz: e3d8d3dd989a852d7950deb9bc3172788f475fdfa9b6342d0d92d1ba8f60ad973ed3efc7029086e80a915672e8098e99cbbd3ad654692a103e222e3f480f53bd
+  data.tar.gz: c605715d80d4704c619c19dd5578ed70189c302ad77d7adce70fee6b52c57b095570b041f43de24a9705fd80da924274dcb21217e2df8442b352ce082a1c4bf2

data/.travis.yml

@@ -2,6 +2,5 @@ language: ruby
 rvm:
   - 2.7.0
   - 2.6.2
-  - 2.5.4
 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.
 
@@ -86,6 +86,32 @@ You can create your own grammar by creating a gem that provides these files and
 
 ## Changelog
 
+### 10.4.0 (9 April 2021)
+
+* Remove dependency on mimemagic. Guess file type based on filename instead.
+
+### 10.3.1 (11 January 2021)
+
+* Strip ascii, unicode general and unicode supplemental punctuation from num elements when building eIds
+
+### 10.2.0 (4 September 2020)
+
+* support inline superscript `^^text^^`
+* support inline subscript `_^text^_`
+
+### 10.1.0 (18 June 2020)
+
+* hcontainer elements have name attributes, to be compliant with AKN 3.0
+
+### 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

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/extract/extractor.rb

@@ -1,5 +1,3 @@
-require 'mimemagic'
-
 module Slaw
   module Extract
 
@@ -13,15 +11,10 @@ module Slaw
       #
       # @return [String] extracted text
       def extract_from_file(filename)
-        mimetype = get_mimetype(filename)
-
-        case mimetype && mimetype.type
-        when 'text/html'
+        if filename.end_with? '.html' or filename.end_with? '.htm'
           extract_from_html(filename)
-        when 'text/plain', nil
-          extract_from_text(filename)
         else
-          raise ArgumentError.new("Unsupported file type #{mimetype || 'unknown'}")
+          extract_from_text(filename)
         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 +20,37 @@ 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."
+      #
+      # Our algorithm is:
+      # 1. strip all leading and trailing whitespace and punctuation (using the unicode punctuation blocks)
+      # 2. strip all whitespace
+      # 3. replace all remaining punctuation with a hyphen.
+      #
+      # The General Punctuation block is \u2000-\u206F, and the Supplemental Punctuation block is \u2E00-\u2E7F.
+      #
+      # (i) -> i
+      # 1.2. -> 1-2
+      # “2.3“ -> 2-3
+      # 3a bis -> 3abis
+      def self.clean(num)
+        # leading whitespace and punctuation
+        num = num.gsub(/^[\s\u{2000}-\u{206f}\u{2e00}-\u{2e7f}!"#$%&'()*+,\-.\/:;<=>?@\[\]^_`{|}~]+/, '')
+        # trailing whitespace and punctuation
+        num.gsub!(/[\s\u{2000}-\u{206f}\u{2e00}-\u{2e7f}!"#$%&'()*+,\-.\/:;<=>?@\[\]^_`{|}~]+$/, '')
+        # whitespace
+        num.gsub!(/\s/, '')
+        # remaining punctuation to a hyphen
+        num.gsub!(/[\u{2000}-\u{206f}\u{2e00}-\u{2e7f}!"#$%&'()*+,\-.\/:;<=>?@\[\]^_`{|}~]+/, '-')
+        num
+      end
     end
   end
 end

data/lib/slaw/grammars/inlines.treetop

@@ -20,7 +20,7 @@ module Slaw
       end
 
       rule inline_item
-        remark / image / ref / bold / italics / [^\n]
+        remark / image / ref / bold / italics / superscript / subscript / [^\n]
         <InlineItem>
       end
 
@@ -57,6 +57,18 @@ module Slaw
         <Ref>
       end
 
+      rule superscript
+        # ^^foo^^
+        '^^' content:(!'^^' inline_item)+ '^^'
+        <Superscript>
+      end
+
+      rule subscript
+        # _^foo^_
+        '_^' content:(!'^_' inline_item)+ '^_'
+        <Subscript>
+      end
+
     end
   end
 end

data/lib/slaw/grammars/inlines_nodes.rb

@@ -71,6 +71,26 @@ module Slaw
         end
       end
 
+      class Superscript < Treetop::Runtime::SyntaxNode
+        def to_xml(b, idprefix)
+          b.sup { |b|
+            for e in content.elements
+              e.inline_item.to_xml(b, idprefix)
+            end
+          }
+        end
+      end
+
+      class Subscript < Treetop::Runtime::SyntaxNode
+        def to_xml(b, idprefix)
+          b.sub { |b|
+            for e in content.elements
+              e.inline_item.to_xml(b, idprefix)
+            end
+          }
+        end
+      end
+
     end
   end
 end

data/lib/slaw/grammars/schedules_nodes.rb

@@ -10,7 +10,7 @@ module Slaw
 
       class ScheduleContainer < Treetop::Runtime::SyntaxNode
         def to_xml(b, idprefix="")
-          b.components { |b| 
+          b.attachments { |b|
             schedules.children.elements.each_with_index { |e, i|
               e.to_xml(b, idprefix, i+1)
             }
@@ -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/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
@@ -171,13 +171,15 @@ module Slaw
             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}"
+            id = id_prefix + "subpart_#{num}"
 
-            b.subpart(id: id) { |b|
+            b.subpart(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
@@ -203,11 +205,11 @@ module Slaw
           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
@@ -233,11 +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
@@ -308,11 +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, name: 'hcontainer') { |b|
               b.content { |b|
                 elements.each_with_index { |e, i| e.to_xml(b, idprefix, i) }
               }
@@ -326,10 +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)
             }
@@ -341,10 +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) }
@@ -358,7 +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
@@ -369,10 +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)
               }