RubyGems - slaw - Versions diffs - 2.2.0 → 3.0.0 - Mend

slaw 2.2.0 → 3.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (23) hide show

checksums.yaml +4 -4
data/README.md +10 -0
data/bin/slaw +5 -0
data/lib/slaw/grammars/inlines.treetop +24 -6
data/lib/slaw/grammars/inlines_nodes.rb +36 -14
data/lib/slaw/grammars/schedules.treetop +2 -2
data/lib/slaw/grammars/schedules_nodes.rb +3 -3
data/lib/slaw/grammars/tables.treetop +1 -1
data/lib/slaw/grammars/tables_nodes.rb +2 -2
data/lib/slaw/grammars/za/act.treetop +39 -14
data/lib/slaw/grammars/za/act_nodes.rb +56 -3
data/lib/slaw/grammars/za/act_text.xsl +32 -5
data/lib/slaw/version.rb +1 -1
data/spec/generator_spec.rb +22 -0
data/spec/za/act_block_spec.rb +167 -50
data/spec/za/act_inline_spec.rb +171 -31
data/spec/za/act_schedules_spec.rb +16 -10
data/spec/za/act_table_spec.rb +12 -6
metadata +2 -7
data/lib/slaw/grammars/pl/act.treetop +0 -240
data/lib/slaw/grammars/pl/act_nodes.rb +0 -441
data/lib/slaw/grammars/pl/act_text.xsl +0 -271
data/spec/pl/act_block_spec.rb +0 -677

data/spec/za/act_table_spec.rb CHANGED

@@ -1,6 +1,7 @@
 # encoding: UTF-8
 require 'slaw'
+require 'slaw/grammars/za/act_nodes'
 describe Slaw::ActGenerator do
   subject { Slaw::ActGenerator.new('za') }
@@ -27,6 +28,11 @@ describe Slaw::ActGenerator do
     b.doc.root.to_xml(encoding: 'UTF-8')
   end
+  before(:each) do
+    Slaw::Grammars::ZA::Act::Crossheading.counters.clear
+    Slaw::Grammars::ZA::Act::BlockElements.counters.clear
+  end
   describe 'tables' do
     it 'should parse basic tables' do
       node = parse :table, <<EOS
@@ -177,10 +183,10 @@ EOS
       xml.should == '<section id="section-10">
   <num>10.</num>
   <heading>A section title</heading>
-  <paragraph id="section-10.paragraph-0">
+  <paragraph id="section-10.paragraph0">
     <content>
       <p>Heres a table:</p>
-      <table id="section-10.paragraph-0.table1">
+      <table id="section-10.paragraph0.table1">
         <tr>
           <td>
             <p>r1c1</p>
@@ -250,10 +256,10 @@ EOS
     <mainBody>
       <hcontainer id="schedule1" name="schedule">
         <heading>Schedule 1</heading>
-        <paragraph id="schedule1.paragraph-0">
+        <paragraph id="schedule1.paragraph0">
           <content>
             <p>Heres a table:</p>
-            <table id="schedule1.paragraph-0.table1">
+            <table id="schedule1.paragraph0.table1">
               <tr>
                 <td>
                   <p>r1c1</p>
@@ -280,14 +286,14 @@ EOS
     end
     it 'should ignore an escaped table' do
-      node = parse :block_paragraphs, <<EOS
+      node = parse :generic_container, <<EOS
 \\{|
 | r1c1
 | r1c2
 |}
 EOS
-      to_xml(node).should == '<paragraph id="paragraph-0">
+      to_xml(node).should == '<paragraph id="paragraph0">
   <content>
     <p>{|</p>
     <p>| r1c1</p>

metadata CHANGED

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 2.2.0
+  version: 3.0.0
 platform: ruby
 authors:
 - Greg Kempe
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2019-03-20 00:00:00.000000000 Z
+date: 2019-03-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -131,9 +131,6 @@ files:
 - lib/slaw/grammars/core_nodes.rb
 - lib/slaw/grammars/inlines.treetop
 - lib/slaw/grammars/inlines_nodes.rb
-- lib/slaw/grammars/pl/act.treetop
-- lib/slaw/grammars/pl/act_nodes.rb
-- lib/slaw/grammars/pl/act_text.xsl
 - lib/slaw/grammars/schedules.treetop
 - lib/slaw/grammars/schedules_nodes.rb
 - lib/slaw/grammars/tables.treetop
@@ -159,7 +156,6 @@ files:
 - spec/generator_spec.rb
 - spec/parse/builder_spec.rb
 - spec/parse/cleanser_spec.rb
-- spec/pl/act_block_spec.rb
 - spec/spec_helper.rb
 - spec/xml_helpers.rb
 - spec/za/act_block_spec.rb
@@ -196,7 +192,6 @@ test_files:
 - spec/generator_spec.rb
 - spec/parse/builder_spec.rb
 - spec/parse/cleanser_spec.rb
-- spec/pl/act_block_spec.rb
 - spec/spec_helper.rb
 - spec/xml_helpers.rb
 - spec/za/act_block_spec.rb

data/lib/slaw/grammars/pl/act.treetop DELETED

@@ -1,240 +0,0 @@
-# encoding: UTF-8
-require 'slaw/parse/grammar_helpers'
-require 'slaw/grammars/pl/act_nodes'
-require 'slaw/grammars/terminals'
-require 'slaw/grammars/tables'
-require 'slaw/grammars/schedules'
-require 'slaw/grammars/inlines'
-module Slaw
-  module Grammars
-    module PL
-      grammar Act
-        include Slaw::Parse::GrammarHelpers
-        ########
-        # major containers
-        rule act
-          empty_line*
-          preface:preface?
-          preamble:preamble?
-          body
-          schedules:schedules_container? <Act>
-        end
-        rule preface
-          !'PREAMBLE'
-          ('PREFACE'i space? eol)?
-          statements:(!'PREAMBLE' pre_body_statement)* <Preface>
-        end
-        rule preamble
-          'PREAMBLE'i space? eol
-          statements:pre_body_statement* <Preamble>
-        end
-        rule body
-          children:(division / subdivision / chapter / article / section / paragraph / point / litera / indents / block_paragraphs)+ <Body>
-        end
-        rule division
-          heading:division_heading
-          children:(subdivision / chapter / article / section / paragraph / point / litera / indents / block_paragraphs)*
-          <Division>
-        end
-        rule subdivision
-          heading:subdivision_heading
-          children:(chapter / article / section / paragraph / point / litera / indents / block_paragraphs)*
-          <Subdivision>
-        end
-        rule chapter
-          heading:chapter_heading
-          children:(article / section / paragraph / point / litera / indents / block_paragraphs)*
-          <Chapter>
-        end
-        rule article
-          # Art. 55. some optional text
-          # 1. first paragraph etc.
-          article_prefix intro
-          children:(section / paragraph / point / litera / indents / block_paragraphs)* <Article>
-        end
-        rule section
-          # § 55. foo
-          section_prefix intro
-          children:(paragraph / point / litera / indents / block_paragraphs)* <Section>
-        end
-        rule paragraph
-          # ustęp:
-          #  34. ...
-          paragraph_prefix intro
-          children:(point / litera / indents / block_paragraphs)* <Paragraph>
-        end
-        rule point
-          # 12) aoeuaoeu
-          # 12a) aoeuaoeu
-          point_prefix intro
-          children:(litera / indents / block_paragraphs)* <Point>
-        end
-        rule litera
-          # a) aoeuaoeu
-          litera_prefix intro
-          children:(indents / block_paragraphs)* <Litera>
-        end
-        rule indents
-          # - foo
-          # - bar
-          children:indent_item+ <Indents>
-        end
-        rule indent_item
-          indent_prefix item_content:inline_block_element? eol? <IndentItem>
-        end
-        rule intro
-          (intro_inline:inline_block_element / (eol intro_block:block_element))? eol?
-        end
-        ##########
-        # group elements
-        #
-        # these are used externally and provide support when parsing just
-        # a particular portion of a document
-        rule articles
-          children:article+ <GroupNode>
-        end
-        rule chapters
-          children:chapter+ <GroupNode>
-        end
-        rule divisions
-          children:division+ <GroupNode>
-        end
-        rule paragraphs
-          children:paragraph+ <GroupNode>
-        end
-        rule sections
-          children:section+ <GroupNode>
-        end
-        rule subdivisions
-          children:subdivision+ <GroupNode>
-        end
-        ##########
-        # headings
-        rule division_heading
-          space? prefix:division_heading_prefix heading:(newline? content)? eol
-          <GenericHeading>
-        end
-        rule subdivision_heading
-          space? prefix:subdivision_heading_prefix heading:(newline? content)? eol
-          <GenericHeading>
-        end
-        rule chapter_heading
-          space? prefix:chapter_heading_prefix heading:(newline? content)? eol
-          <GenericHeading>
-        end
-        ##########
-        # blocks of content inside containers
-        rule block_paragraphs
-          block_element+ <BlockParagraph>
-        end
-        rule block_element
-          table / naked_statement
-        end
-        # Block elements that don't have to appear at the start of a line.
-        # ie. we don't need to guard against the start of a chapter, section, etc.
-        rule inline_block_element
-          table / inline_statement
-        end
-        ##########
-        # statements - single lines of content
-        #
-        # If a statement starts with a backslash, it's considered to have escaped the subsequent word,
-        # and is ignored. This allows escaping of section headings, etc.
-        rule naked_statement
-          space? !(division_heading / subdivision_heading / chapter_heading / article_prefix / section_prefix / schedule_title / paragraph_prefix / point_prefix / litera_prefix / indent_prefix) '\\'? clauses eol
-          <NakedStatement>
-        end
-        rule pre_body_statement
-          space? !(division_heading / subdivision_heading / chapter_heading / article_prefix / section_prefix / schedule_title) '\\'? clauses eol
-          <NakedStatement>
-        end
-        ##########
-        # prefixes
-        rule division_heading_prefix
-          'dzia'i ('ł'/'Ł') space alphanums [ :-]*
-        end
-        rule subdivision_heading_prefix
-          'oddzia'i ('ł'/'Ł') space alphanums [ :.-]*
-        end
-        rule chapter_heading_prefix
-          'rozdzia'i ('ł'/'Ł') space alphanums [ :.-]*
-        end
-        rule article_prefix
-          ('Art.'i / ('Artyku'i 'ł'/'Ł')) space number_letter '.'?
-        end
-        rule section_prefix
-          '§' space alphanums '.'?
-        end
-        rule paragraph_prefix
-          number_letter '.'
-        end
-        rule point_prefix
-          # 1) foo
-          # 2A) foo
-          number_letter ')'
-        end
-        rule litera_prefix
-          # a) foo
-          # bb) foo
-          letters:letter+ ')'
-        end
-        rule indent_prefix
-          # these are two different dash characters
-          '–' / '-' space
-        end
-        include Slaw::Grammars::Inlines
-        include Slaw::Grammars::Tables
-        include Slaw::Grammars::Schedules
-        include Slaw::Grammars::Terminals
-      end
-    end
-  end
-end

data/lib/slaw/grammars/pl/act_nodes.rb DELETED

@@ -1,441 +0,0 @@
-require 'slaw/grammars/core_nodes'
-module Slaw
-  module Grammars
-    module PL
-      module Act
-        class Act < Treetop::Runtime::SyntaxNode
-          FRBR_URI = '/pl/act/1980/01'
-          WORK_URI = FRBR_URI
-          EXPRESSION_URI = "#{FRBR_URI}/pol@"
-          MANIFESTATION_URI = EXPRESSION_URI
-          def to_xml(b, idprefix=nil, i=0)
-            b.act(contains: "originalVersion") { |b|
-              write_meta(b)
-              write_preface(b)
-              write_preamble(b)
-              write_body(b)
-            }
-            write_schedules(b)
-          end
-          def write_meta(b)
-            b.meta { |b|
-              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")
-              }
-            }
-          end
-          def write_identification(b)
-            b.identification(source: "#slaw") { |b|
-              # use stub values so that we can generate a validating document
-              b.FRBRWork { |b|
-                b.FRBRthis(value: "#{WORK_URI}/main")
-                b.FRBRuri(value: WORK_URI)
-                b.FRBRalias(value: 'Short Title')
-                b.FRBRdate(date: '1980-01-01', name: 'Generation')
-                b.FRBRauthor(href: '#council')
-                b.FRBRcountry(value: 'za')
-              }
-              b.FRBRExpression { |b|
-                b.FRBRthis(value: "#{EXPRESSION_URI}/main")
-                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}/main")
-                b.FRBRuri(value: MANIFESTATION_URI)
-                b.FRBRdate(date: Time.now.strftime('%Y-%m-%d'), name: 'Generation')
-                b.FRBRauthor(href: '#slaw')
-              }
-            }
-          end
-          def write_preface(b)
-            preface.to_xml(b) if preface.respond_to? :to_xml
-          end
-          def write_preamble(b)
-            preamble.to_xml(b) if preamble.respond_to? :to_xml
-          end
-          def write_body(b)
-            body.to_xml(b)
-          end
-          def write_schedules(b)
-            if schedules.text_value != ""
-              schedules.to_xml(b)
-            end
-          end
-        end
-        class Preface < Treetop::Runtime::SyntaxNode
-          def to_xml(b, *args)
-            if text_value != ""
-              b.preface { |b|
-                statements.elements.each { |element|
-                  for e in element.elements
-                    e.to_xml(b, "") if e.is_a? Slaw::Grammars::Inlines::NakedStatement
-                  end
-                }
-              }
-            end
-          end
-        end
-        class Preamble < Treetop::Runtime::SyntaxNode
-          def to_xml(b, *args)
-            if text_value != ""
-              b.preamble { |b|
-                statements.elements.each { |e|
-                  e.to_xml(b, "")
-                }
-              }
-            end
-          end
-        end
-        class Part < Treetop::Runtime::SyntaxNode
-          def num
-            heading.num
-          end
-          def to_xml(b, *args)
-            id = "part-#{num}"
-            # include a chapter number in the id if our parent has one
-            if parent and parent.parent.is_a?(Chapter) and parent.parent.num
-              id = "chapter-#{parent.parent.num}.#{id}"
-            end
-            b.part(id: id) { |b|
-              heading.to_xml(b)
-              children.elements.each_with_index { |e, i| e.to_xml(b, id + '.', i) }
-            }
-          end
-        end
-        class GenericHeading < Treetop::Runtime::SyntaxNode
-          def num
-            prefix.alphanums.text_value
-          end
-          def title
-            if heading.text_value and heading.respond_to? :content
-              heading.content.text_value.strip
-            end
-          end
-          def to_xml(b)
-            b.num(num)
-            b.heading(title) if title
-          end
-        end
-        class Division < Treetop::Runtime::SyntaxNode
-          def num
-            heading.num
-          end
-          def to_xml(b, *args)
-            id = "division-#{num}"
-            b.division(id: id) { |b|
-              heading.to_xml(b)
-              children.elements.each_with_index { |e, i| e.to_xml(b, id + '.', i) }
-            }
-          end
-        end
-        class Subdivision < Treetop::Runtime::SyntaxNode
-          def num
-            heading.num
-          end
-          def to_xml(b, *args)
-            id = "subdivision-#{num}"
-            b.subdivision(id: id) { |b|
-              heading.to_xml(b)
-              children.elements.each_with_index { |e, i| e.to_xml(b, id + '.', i) }
-            }
-          end
-        end
-        class Chapter < Treetop::Runtime::SyntaxNode
-          def num
-            heading.num
-          end
-          def to_xml(b, *args)
-            id = "chapter-#{num}"
-            # TODO: do this for the oddzial and zial
-            # include a part number in the id if our parent has one
-            if parent and parent.parent.is_a?(Part) and parent.parent.num
-              id = "part-#{parent.parent.num}.#{id}"
-            end
-            b.chapter(id: id) { |b|
-              heading.to_xml(b)
-              children.elements.each_with_index { |e, i| e.to_xml(b, id + '.', i) }
-            }
-          end
-        end
-        class BlockWithIntroAndChildren < Treetop::Runtime::SyntaxNode
-          def intro_node
-            if intro.elements.length >= 1
-              el = intro.elements[0]
-              if el.respond_to? :intro_inline
-                el.intro_inline
-              elsif el.respond_to? :intro_block
-                el.intro_block
-              end
-            end
-          end
-          def intro_and_children_xml(b, idprefix)
-            if intro_node and !intro_node.empty?
-              if not children.empty?
-                b.intro { |b| intro_node.to_xml(b, idprefix) }
-              else
-                b.content { |b| intro_node.to_xml(b, idprefix) }
-              end
-            elsif children.empty?
-              b.content { |b| b.p }
-            end
-            children.elements.each_with_index { |e, i| e.to_xml(b, idprefix, i) }
-          end
-        end
-        class Article < BlockWithIntroAndChildren
-          def num
-            article_prefix.number_letter.text_value
-          end
-          def to_xml(b, *args)
-            id = "article-#{num}"
-            idprefix = "#{id}."
-            b.article(id: id) { |b|
-              b.num("#{num}.")
-              intro_and_children_xml(b, idprefix)
-            }
-          end
-        end
-        class Section < BlockWithIntroAndChildren
-          def num
-            section_prefix.alphanums.text_value
-          end
-          def to_xml(b, *args)
-            id = "section-#{num}"
-            idprefix = "#{id}."
-            b.section(id: id) { |b|
-              b.num("#{num}.")
-              intro_and_children_xml(b, idprefix)
-            }
-          end
-        end
-        class Paragraph < BlockWithIntroAndChildren
-          def num
-            paragraph_prefix.number_letter.text_value
-          end
-          def to_xml(b, idprefix='', *args)
-            id = "#{idprefix}paragraph-#{num}"
-            idprefix = id + "."
-            b.paragraph(id: id) { |b|
-              b.num(paragraph_prefix.text_value)
-              intro_and_children_xml(b, idprefix)
-            }
-          end
-        end
-        class Point < BlockWithIntroAndChildren
-          def num
-            point_prefix.number_letter.text_value
-          end
-          def to_xml(b, idprefix='', i)
-            id = "#{idprefix}point-#{num}"
-            idprefix = id + "."
-            b.point(id: id) { |b|
-              b.num(point_prefix.text_value)
-              intro_and_children_xml(b, idprefix)
-            }
-          end
-        end
-        class Litera < BlockWithIntroAndChildren
-          def num
-            litera_prefix.letters.text_value
-          end
-          def to_xml(b, idprefix='', i)
-            id = "#{idprefix}alinea-#{num}"
-            idprefix = id + "."
-            b.alinea(id: id) { |b|
-              b.num(litera_prefix.text_value)
-              intro_and_children_xml(b, idprefix)
-            }
-          end
-        end
-        class BlockParagraph < Treetop::Runtime::SyntaxNode
-          def to_xml(b, idprefix='', i=0)
-            id = "#{idprefix}subparagraph-0"
-            idprefix = id + "."
-            b.subparagraph(id: id) { |b|
-              b.content { |b|
-                elements.each_with_index { |e, i| e.to_xml(b, idprefix, i) }
-              }
-            }
-          end
-        end
-        class Indents < Treetop::Runtime::SyntaxNode
-          # Render a list of indent items.
-          def to_xml(b, idprefix, i=0)
-            id = idprefix + "list-#{i}"
-            idprefix = id + '.'
-            b.list(id: id) { |b|
-              children.elements.each_with_index { |e, i| e.to_xml(b, idprefix, i) }
-            }
-          end
-        end
-        class IndentItem < Treetop::Runtime::SyntaxNode
-          def to_xml(b, idprefix, i)
-            id = idprefix + "indent-#{i}"
-            idprefix = id + '.'
-            b.indent(id: id) { |b|
-              b.content { |b|
-                if not item_content.empty?
-                  item_content.to_xml(b, idprefix)
-                else
-                  b.p
-                end
-              }
-            }
-          end
-        end
-        class ScheduleContainer < Treetop::Runtime::SyntaxNode
-          def to_xml(b)
-            b.components { |b|
-              schedules.children.elements.each_with_index { |e, i|
-                e.to_xml(b, "", i+1)
-              }
-            }
-          end
-        end
-        class Schedule < Treetop::Runtime::SyntaxNode
-          def num
-            n = schedule_title.num.text_value
-            return (n && !n.empty?) ? n : nil
-          end
-          def alias
-            if not schedule_title.title.text_value.blank?
-              schedule_title.title.text_value
-            elsif num
-              "Schedule #{num}"
-            else
-              "Schedule"
-            end
-          end
-          def heading
-            if schedule_title.heading.respond_to? :content
-              schedule_title.heading.content.text_value
-            else
-              nil
-            end
-          end
-          def to_xml(b, idprefix=nil, i=1)
-            if num
-              n = num
-              component = "schedule#{n}"
-            else
-              n = i
-              # make a component name from the schedule title
-              component = self.alias.downcase().strip().gsub(/[^a-z0-9]/i, '').gsub(/ +/, '')
-            end
-            id = "#{idprefix}#{component}"
-            b.component(id: "component-#{id}") { |b|
-              b.doc_(name: component) { |b|
-                b.meta { |b|
-                  b.identification(source: "#slaw") { |b|
-                    b.FRBRWork { |b|
-                      b.FRBRthis(value: "#{Act::WORK_URI}/#{component}")
-                      b.FRBRuri(value: Act::WORK_URI)
-                      b.FRBRalias(value: self.alias)
-                      b.FRBRdate(date: '1980-01-01', name: 'Generation')
-                      b.FRBRauthor(href: '#council')
-                      b.FRBRcountry(value: 'za')
-                    }
-                    b.FRBRExpression { |b|
-                      b.FRBRthis(value: "#{Act::EXPRESSION_URI}/#{component}")
-                      b.FRBRuri(value: Act::EXPRESSION_URI)
-                      b.FRBRdate(date: '1980-01-01', name: 'Generation')
-                      b.FRBRauthor(href: '#council')
-                      b.FRBRlanguage(language: 'eng')
-                    }
-                    b.FRBRManifestation { |b|
-                      b.FRBRthis(value: "#{Act::MANIFESTATION_URI}/#{component}")
-                      b.FRBRuri(value: Act::MANIFESTATION_URI)
-                      b.FRBRdate(date: Time.now.strftime('%Y-%m-%d'), name: 'Generation')
-                      b.FRBRauthor(href: '#slaw')
-                    }
-                  }
-                }
-                b.mainBody { |b|
-                  idprefix = "#{id}."
-                  # there is no good AKN hierarchy container for schedules, so we
-                  # just use article because we don't use it anywhere else.
-                  b.article(id: id) { |b|
-                    b.heading(heading) if heading
-                    body.children.elements.each_with_index { |e| e.to_xml(b, idprefix, i) } if body.is_a? Body
-                  }
-                }
-              }
-            }
-          end
-        end
-        class ScheduleStatement < Treetop::Runtime::SyntaxNode
-          def to_xml(b, idprefix)
-            b.p { |b| clauses.to_xml(b, idprefix) } if clauses
-          end
-        end
-      end
-    end
-  end
-end