RubyGems - slaw - Versions diffs - 0.9.0 → 0.10.0 - Mend

slaw 0.9.0 → 0.10.0

Files changed (11) hide show

checksums.yaml CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 08d012c5c08856227cf9c203f5c932d076115522
-  data.tar.gz: 742fa6d2ff279945b3ed3cdff468c62a9567cd17
+  metadata.gz: 93a820ba2ec4e18e12c5a9935a954ad314dfc614
+  data.tar.gz: 6bed26afa25207e66575795a1f94b8504e040009
 SHA512:
-  metadata.gz: 7f831cd0db6d4d05a80634645b248cfb8555122e85f59af07cc848cdb32330d3f97eab5d59b883802209eb4d9ebe3079a7d29ad80df20a73b2ec340cd1568d2d
-  data.tar.gz: 21285db937fb61a1d81ef7a8a8359219e2b10c066e36e9d01ec6091d107bdd3f2d8ccb5e5fb06f1cb394ff4b8cf52b78c20cedcaab36ef19b8b271623ef946c0
+  metadata.gz: 7ff709e7d9931573ae661cad219350917bb352120aa7507d18589df6c47f2bd5e1e2066cc924393e1a98f2a40884363603b8e0e73ef82a125cb942af238e4860
+  data.tar.gz: 0d8f14587a3d706cdf32450dafc0a28e0a28b6bf9f6ca968a64f0c044f0072a21d36e62061457011a5b68ca42b14be6863bf1b05a7a1e6b48b01c1684acc3749

data/README.md CHANGED Viewed

@@ -157,6 +157,8 @@ in a document to indicate different levels of nesting.
 During post-processing it works out how to nest these appropriately.
+Special words, such as ``part`` and ``chapter`` are ignored if the line starts with a backslash ``\``.
 For more information see the South African by-law grammar at
 [lib/slaw/za/bylaw.treetop](lib/slaw/za/bylaw.treetop) and the list nesting
 at [lib/slaw/parse/blocklists.rb](lib/slaw/parse/blocklists.rb).
@@ -216,6 +218,11 @@ Akoma Ntoso `component` elements at the end of the XML document, with a name of
 ## Changelog
+### 0.10.0
+* New command `unparse FILE` which transforms an Akoma Ntoso XML document into plain text, suitable for re-parsing
+* Support escaping special words with a backslash
 ### 0.9.0
 * This release makes reasonably significant changes to generated XML, particularly

data/bin/slaw CHANGED Viewed

@@ -102,6 +102,14 @@ class SlawCLI < Thor
     puts builder.to_xml(doc)
   end
+  desc "unparse FILE", "Unparse FILE from Akoma Ntoso XML back into text suitable for re-parsing"
+  def unparse(name)
+    generator = Slaw::ActGenerator.new
+    doc = File.open(name, 'r') { |f| doc = generator.builder.parse_xml(f.read) }
+    puts generator.text_from_act(doc)
+  end
   map %w(--version) => :__print_version
   desc "--version", "Print slaw version info"
   def __print_version

data/lib/slaw/generator.rb CHANGED Viewed

@@ -62,5 +62,13 @@ module Slaw
       before > after * 1.25
     end
+    # Transform an Akoma Ntoso XML document back into a plain-text version
+    # suitable for re-parsing back into XML with no loss of structure.
+    def text_from_act(doc)
+      here = File.dirname(__FILE__)
+      xslt = Nokogiri::XSLT(File.read(File.join([here, 'za/act_text.xsl'])))
+      xslt.transform(doc).child.to_xml
+    end
   end
 end

data/lib/slaw/version.rb CHANGED Viewed

@@ -1,3 +1,3 @@
 module Slaw
-  VERSION = "0.9.0"
+  VERSION = "0.10.0"
 end

data/lib/slaw/za/act.treetop CHANGED Viewed

@@ -31,7 +31,7 @@ module Slaw
       end
       rule body
-        children:(chapter / part / section / subsection / block_paragraphs )+ <Body>
+        children:(chapter / part / section / subsection / block_paragraphs)+ <Body>
       end
       rule chapter
@@ -173,14 +173,17 @@ module Slaw
       ##########
       # 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? !(chapter_heading / part_heading / section_title / schedule_title / subsection_prefix) clauses eol
+        space? !(chapter_heading / part_heading / section_title / schedule_title / subsection_prefix) '\\'? clauses eol
         <NakedStatement>
       end
       rule pre_body_statement
-        space? !(chapter_heading / part_heading / section_title / schedule_title) clauses eol
+        space? !(chapter_heading / part_heading / section_title / schedule_title) '\\'? clauses eol
         <NakedStatement>
       end

data/lib/slaw/za/act_text.xsl ADDED Viewed

@@ -0,0 +1,225 @@
+<?xml version="1.0"?>
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0"
+  xmlns:a="http://www.akomantoso.org/2.0"
+  exclude-result-prefixes="a">
+  <xsl:output method="text" indent="no" omit-xml-declaration="yes" />
+  <xsl:strip-space elements="*"/>
+  <xsl:template match="a:act">
+    <xsl:apply-templates select="a:coverPage" />
+    <xsl:apply-templates select="a:preface" />
+    <xsl:apply-templates select="a:preamble" />
+    <xsl:apply-templates select="a:body" />
+    <xsl:apply-templates select="a:conclusions" />
+  </xsl:template>
+  <xsl:template match="a:preface">
+    <xsl:text>PREFACE</xsl:text>
+    <xsl:text>
+</xsl:text>
+    <xsl:apply-templates />
+  </xsl:template>
+  <xsl:template match="a:preamble">
+    <xsl:text>PREAMBLE</xsl:text>
+    <xsl:text>
+</xsl:text>
+    <xsl:apply-templates />
+  </xsl:template>
+  <xsl:template match="a:part">
+    <xsl:text>Part </xsl:text>
+    <xsl:value-of select="./a:num" />
+    <xsl:text> - </xsl:text>
+    <xsl:value-of select="./a:heading" />
+    <xsl:text>
+</xsl:text>
+    <xsl:apply-templates select="./*[not(self::a:num) and not(self::a:heading)]" />
+  </xsl:template>
+  <xsl:template match="a:chapter">
+    <xsl:text>Chapter </xsl:text>
+    <xsl:value-of select="./a:num" />
+    <xsl:text> - </xsl:text>
+    <xsl:value-of select="./a:heading" />
+    <xsl:text>
+</xsl:text>
+    <xsl:apply-templates select="./*[not(self::a:num) and not(self::a:heading)]" />
+  </xsl:template>
+  <xsl:template match="a:section">
+    <xsl:value-of select="a:num" />
+    <xsl:text> </xsl:text>
+    <xsl:if test="a:heading != ''">
+      <xsl:value-of select="a:heading" />
+    </xsl:if>
+    <xsl:text>
+</xsl:text>
+    <xsl:apply-templates select="./*[not(self::a:num) and not(self::a:heading)]" />
+  </xsl:template>
+  <xsl:template match="a:subsection">
+    <xsl:if test="a:num != ''">
+      <xsl:value-of select="a:num" />
+      <xsl:text> </xsl:text>
+    </xsl:if>
+    <xsl:apply-templates select="./*[not(self::a:num) and not(self::a:heading)]" />
+  </xsl:template>
+  <!-- these are block elements and have a newline at the end -->
+  <xsl:template match="a:heading">
+    <xsl:apply-templates />
+    <xsl:text>
+</xsl:text>
+  </xsl:template>
+  <xsl:template match="a:p">
+    <xsl:variable name="prefix" select="translate(substring(., 1, 10), 'abcdefghijklmnopqrstuvwxyz', 'ABCDEFGHIJKLMNOPQRSTUVWXYZ')" />
+    <xsl:variable name="numprefix" select="translate(substring(., 1, 3), '1234567890', 'NNNNNNNNNN')" />
+    <!-- p tags must escape initial content that looks like a block element marker -->
+    <xsl:if test="starts-with($prefix, 'BODY') or
+                  starts-with($prefix, 'CHAPTER') or
+                  starts-with($prefix, 'PART') or
+                  starts-with($prefix, 'PREAMBLE') or
+                  starts-with($prefix, 'PREFACE') or
+                  starts-with($prefix, 'SCHEDULE') or
+                  starts-with($prefix, '{|') or
+                  starts-with($numprefix, '(') or
+                  starts-with($numprefix, 'N.')">
+      <xsl:text>\</xsl:text>
+    </xsl:if>
+    <xsl:value-of select="."/>
+    <!-- p tags must end with a newline -->
+    <xsl:text>
+</xsl:text>
+  </xsl:template>
+  <xsl:template match="a:blockList">
+    <xsl:if test="a:listIntroduction != ''">
+      <xsl:apply-templates select="a:listIntroduction" />
+      <xsl:text>
+</xsl:text>
+    </xsl:if>
+    <xsl:apply-templates select="./*[not(self::a:listIntroduction)]" />
+  </xsl:template>
+  <xsl:template match="a:item">
+    <xsl:value-of select="./a:num" />
+    <xsl:text> </xsl:text>
+    <xsl:apply-templates select="./*[not(self::a:num)]" />
+  </xsl:template>
+  <xsl:template match="a:list">
+    <xsl:if test="a:intro != ''">
+      <xsl:value-of select="a:intro" />
+      <xsl:text>
+</xsl:text>
+    </xsl:if>
+    <xsl:apply-templates select="./*[not(self::a:intro)]" />
+  </xsl:template>
+  <!-- components/schedules -->
+  <xsl:template match="a:doc">
+    <xsl:text>Schedule - </xsl:text>
+    <xsl:value-of select="a:meta/a:identification/a:FRBRWork/a:FRBRalias/@value" />
+    <xsl:if test="a:mainBody/a:article/a:heading">
+      <xsl:text>
+</xsl:text>
+      <xsl:value-of select="a:mainBody/a:article/a:heading" />
+    </xsl:if>
+    <xsl:text>
+</xsl:text>
+    <xsl:apply-templates select="a:mainBody" />
+  </xsl:template>
+  <xsl:template match="a:mainBody/a:article/a:heading">
+    <!-- no-op, this is handled by the schedules template above -->
+  </xsl:template>
+  <!-- tables -->
+  <xsl:template match="a:table">
+    <xsl:text>{| </xsl:text>
+    <!-- attributes -->
+    <xsl:for-each select="@*[local-name()!='id']">
+      <xsl:value-of select="local-name(.)" />
+      <xsl:text>="</xsl:text>
+      <xsl:value-of select="." />
+      <xsl:text>" </xsl:text>
+    </xsl:for-each>
+    <xsl:text>
+|-</xsl:text>
+    <xsl:apply-templates />
+    <xsl:text>
+|}
+</xsl:text>
+  </xsl:template>
+  <xsl:template match="a:tr">
+    <xsl:apply-templates />
+    <xsl:text>
+|-</xsl:text>
+  </xsl:template>
+  <xsl:template match="a:th|a:td">
+    <xsl:choose>
+      <xsl:when test="local-name(.) = 'th'">
+        <xsl:text>
+! </xsl:text>
+      </xsl:when>
+      <xsl:when test="local-name(.) = 'td'">
+        <xsl:text>
+| </xsl:text>
+      </xsl:when>
+    </xsl:choose>
+    <!-- attributes -->
+    <xsl:if test="@*">
+      <xsl:for-each select="@*">
+        <xsl:value-of select="local-name(.)" />
+        <xsl:text>="</xsl:text>
+        <xsl:value-of select="." />
+        <xsl:text>" </xsl:text>
+      </xsl:for-each>
+      <xsl:text>| </xsl:text>
+    </xsl:if>
+    <xsl:apply-templates />
+  </xsl:template>
+  <!-- don't end p tags with newlines in tables -->
+  <xsl:template match="a:table//a:p">
+    <xsl:apply-templates />
+  </xsl:template>
+  <!-- END tables -->
+  <xsl:template match="a:remark">
+    <xsl:text>[</xsl:text>
+    <xsl:apply-templates />
+    <xsl:text>]</xsl:text>
+  </xsl:template>
+  <!-- for most nodes, just dump their text content -->
+  <xsl:template match="*">
+    <xsl:text/><xsl:apply-templates /><xsl:text/>
+  </xsl:template>
+</xsl:stylesheet>

data/slaw.gemspec CHANGED Viewed

@@ -19,7 +19,7 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
   spec.add_development_dependency "bundler", "~> 1.5"
-  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rake", "~> 10.3.1"
   spec.add_development_dependency "rspec", "~> 2.14.1"
   spec.add_runtime_dependency "nokogiri", "~> 1.6.0"

data/spec/generator_spec.rb CHANGED Viewed

@@ -38,4 +38,59 @@ Some content.
       end
     end
   end
+  describe 'unparse' do
+    it 'should escape keywards when unparsing' do
+      doc = xml2doc(section(<<XML
+        <num>1.</num>
+        <heading>Section</heading>
+        <paragraph id="section-1.paragraph-0">
+          <content>
+            <p>Chapter 2 ignored</p>
+            <p>Part 2 ignored</p>
+            <p>Schedule 2 ignored</p>
+            <p>BODY ignored</p>
+            <p>PREAMBLE ignored</p>
+            <p>PREFACE ignored</p>
+            <p>2. ignored</p>
+            <p>2.1 ignored</p>
+            <p>(2) ignored</p>
+            <p>(a) ignored</p>
+            <p>(2a) ignored</p>
+            <p>{| ignored</p>
+          </content>
+        </paragraph>
+XML
+      ))
+      text = subject.text_from_act(doc)
+      text.should == '1. Section
+\Chapter 2 ignored
+\Part 2 ignored
+\Schedule 2 ignored
+\BODY ignored
+\PREAMBLE ignored
+\PREFACE ignored
+\2. ignored
+\2.1 ignored
+\(2) ignored
+\(a) ignored
+\(2a) ignored
+\{| ignored
+'
+    end
+  end
 end

data/spec/za/act_spec.rb CHANGED Viewed

@@ -91,6 +91,31 @@ EOS
       </content>
     </paragraph>
   </section>
+</body>'
+    end
+    it 'should handle escaped content' do
+      node = parse :body, <<EOS
+\\1. ignored
+1. Section
+\\Chapter 2 ignored
+EOS
+      to_xml(node).should == '<body>
+  <paragraph id="paragraph-0">
+    <content>
+      <p>1. ignored</p>
+    </content>
+  </paragraph>
+  <section id="section-1">
+    <num>1.</num>
+    <heading>Section</heading>
+    <paragraph id="section-1.paragraph-0">
+      <content>
+        <p>Chapter 2 ignored</p>
+      </content>
+    </paragraph>
+  </section>
 </body>'
     end
   end
@@ -255,6 +280,29 @@ EOS
       </table>
     </content>
   </paragraph>
+</chapter>'
+    end
+    it 'should ignore escaped chapter headers' do
+      node = parse :chapter, <<EOS
+Chapter 1 The Chapter
+Stuff
+\\Chapter 2 - Ignored
+More stuff
+EOS
+      to_xml(node).should == '<chapter id="chapter-1">
+  <num>1</num>
+  <heading>The Chapter</heading>
+  <paragraph id="chapter-1.paragraph-0">
+    <content>
+      <p>Stuff</p>
+      <p>Chapter 2 - Ignored</p>
+      <p>More stuff</p>
+    </content>
+  </paragraph>
 </chapter>'
     end
   end
@@ -439,6 +487,24 @@ EOS
     <num>3</num>
     <heading>The Other Heading</heading>
   </part>
+</body>'
+    end
+    it 'should handle escaped parts' do
+      node = parse :body, <<EOS
+Part 2 The Part Heading
+\\Part 3 ignored
+EOS
+      to_xml(node).should == '<body>
+  <part id="part-2">
+    <num>2</num>
+    <heading>The Part Heading</heading>
+    <paragraph id="part-2.paragraph-0">
+      <content>
+        <p>Part 3 ignored</p>
+      </content>
+    </paragraph>
+  </part>
 </body>'
     end
   end
@@ -629,6 +695,30 @@ EOS
       </item>
     </blockList>
   </content>
+</subsection>'
+    end
+    it 'should ignore escaped items' do
+      node = parse(:subsection, <<EOS
+        (1) a subsection
+        \\(1) ignored
+        \\9.9.2 item2
+        \\some text
+        \\(d) item 4
+        \\(b) (i) single
+EOS
+      )
+      to_xml(node, '', 1).should == '<subsection id="1">
+  <num>(1)</num>
+  <content>
+    <p>a subsection</p>
+    <p>(1) ignored</p>
+    <p>9.9.2 item2</p>
+    <p>some text</p>
+    <p>(d) item 4</p>
+    <p>(b) (i) single</p>
+  </content>
 </subsection>'
     end
   end
@@ -867,6 +957,18 @@ EOS
 </preface>'
     end
+    it 'should ignore escaped preface' do
+      node = parse :act, <<EOS
+\\PREFACE
+1. Section
+(1) hello
+EOS
+      to_xml(node.preface).should == '<preface>
+  <p>PREFACE</p>
+</preface>'
+    end
     it 'should support remarks in the preface' do
       node = parse :act, <<EOS
 PREFACE
@@ -993,10 +1095,29 @@ EOS
       node.elements.first.text_value.should == ""
     end
+    it 'should ignore escaped preamble' do
+      node = parse :act, <<EOS
+PREFACE
+this is the preface
+PREAMBLE
+\\PREAMBLE
+1. Section
+(1) hello
+EOS
+      to_xml(node.preamble).should == '<preamble>
+  <p>PREAMBLE</p>
+</preamble>'
+    end
   end
   #-------------------------------------------------------------------------------
-  # Section
+  # Sections
   context 'section' do
     it 'should handle section numbers after title' do
@@ -1160,6 +1281,29 @@ EOS
       </blockList>
     </content>
   </paragraph>
+</section>'
+    end
+    it 'should ignore escaped section headings' do
+      node = parse :section, <<EOS
+1. Section
+\\1. ignored
+\\2. another line
+stuff
+\\3. a third
+EOS
+      to_xml(node, "").should == '<section id="section-1">
+  <num>1.</num>
+  <heading>Section</heading>
+  <paragraph id="section-1.paragraph-0">
+    <content>
+      <p>1. ignored</p>
+      <p>2. another line</p>
+      <p>stuff</p>
+      <p>3. a third</p>
+    </content>
+  </paragraph>
 </section>'
     end
   end
@@ -1653,6 +1797,61 @@ Schedule 3. Matters which shall continue to be regulated by Swazi Law and Custom
 Schedule 4. Specially entrenched provisions and entrenched provisions.
 EOS
     end
+    it 'should handle escaped schedules' do
+      node = parse :schedules, <<EOS
+Schedule
+Subject to approval in terms of this By-Law.
+\\Schedule another
+More stuff
+EOS
+      s = to_xml(node)
+      today = Time.now.strftime('%Y-%m-%d')
+      s.should == '<component id="component-schedule">
+  <doc name="schedule">
+    <meta>
+      <identification source="#slaw">
+        <FRBRWork>
+          <FRBRthis value="/za/act/1980/01/schedule"/>
+          <FRBRuri value="/za/act/1980/01"/>
+          <FRBRalias value="Schedule"/>
+          <FRBRdate date="1980-01-01" name="Generation"/>
+          <FRBRauthor href="#council"/>
+          <FRBRcountry value="za"/>
+        </FRBRWork>
+        <FRBRExpression>
+          <FRBRthis value="/za/act/1980/01/eng@/schedule"/>
+          <FRBRuri value="/za/act/1980/01/eng@"/>
+          <FRBRdate date="1980-01-01" name="Generation"/>
+          <FRBRauthor href="#council"/>
+          <FRBRlanguage language="eng"/>
+        </FRBRExpression>
+        <FRBRManifestation>
+          <FRBRthis value="/za/act/1980/01/eng@/schedule"/>
+          <FRBRuri value="/za/act/1980/01/eng@"/>
+          <FRBRdate date="' + today + '" name="Generation"/>
+          <FRBRauthor href="#slaw"/>
+        </FRBRManifestation>
+      </identification>
+    </meta>
+    <mainBody>
+      <article id="schedule">
+        <paragraph id="schedule.paragraph-0">
+          <content>
+            <p>Subject to approval in terms of this By-Law.</p>
+            <p>Schedule another</p>
+            <p>More stuff</p>
+          </content>
+        </paragraph>
+      </article>
+    </mainBody>
+  </doc>
+</component>'
+    end
   end
   #-------------------------------------------------------------------------------
@@ -1768,6 +1967,24 @@ EOS
   </doc>
 </component>'
     end
+    it 'should ignore an escaped table' do
+      node = parse :block_paragraphs, <<EOS
+\\{|
+| r1c1
+| r1c2
+|}
+EOS
+      to_xml(node).should == '<paragraph id="paragraph-0">
+  <content>
+    <p>{|</p>
+    <p>| r1c1</p>
+    <p>| r1c2</p>
+    <p>|}</p>
+  </content>
+</paragraph>'
+    end
   end
   #-------------------------------------------------------------------------------

metadata CHANGED Viewed

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.10.0
 platform: ruby
 authors:
 - Greg Kempe
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2016-03-05 00:00:00.000000000 Z
+date: 2016-12-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -28,16 +28,16 @@ dependencies:
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 10.3.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 10.3.1
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -191,6 +191,7 @@ files:
 - lib/slaw/xml_support.rb
 - lib/slaw/za/act.treetop
 - lib/slaw/za/act_nodes.rb
+- lib/slaw/za/act_text.xsl
 - slaw.gemspec
 - spec/act_spec.rb
 - spec/bylaw_spec.rb