slaw 10.4.1 → 11.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: aa5a1bf4a3098846a8f22ab9cff0c1a44f376407b9cc9c2f314ec69d9445c073
-  data.tar.gz: 918bc6711f33db010f38c80606a52c7f9ff446778230dcbeafa27d34abc5eceb
+  metadata.gz: 736f598c8a9924a22e2474b2380a229a49188b9fab567280a167cc187554fdb0
+  data.tar.gz: 01de6d73cd7352ff0d6dfbf201b25e7eeb219f6f213dbb8d4c7e05bca40e5b6b
 SHA512:
-  metadata.gz: 1231195c46118f5098b4b31deca137981d03dacdcdb57175c30779cd4abc0339a95d480d3d08962e8d8dfae8d6c67880c1f219867583fe3df15b531391b19086
-  data.tar.gz: 7bdbb9416a5c77eddab03eafef40b8aae830c2bcb71dc2cb4dc15f746be7404fd7122dbc242150e6ae90a9dca4f3a144f59013e3d36d5662de30f815aaf6ab00
+  metadata.gz: faab27a9d122bde77325b295e1d9f705edd314cb9a7abd2cdff8b5e08fd9cdc43333c879e8e7c7e7dd1c7ba9e702457ef683372c890726739f46fc002ee26f3e
+  data.tar.gz: 0c289d9a797771c43be62059cf0b08f4a0730ca637400c2e38aedd2285c193cf1c6ce44763b1a4c6c33335200c00351982ff46002fd60cd5c5e194444b8798b6

data/.github/workflows/test.yml

@@ -0,0 +1,22 @@
+name: Test
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        ruby-version: [2.7, 2.6]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Ruby ${{ matrix.ruby-version }}
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby-version }}
+      - name: Install dependencies
+        run: bundle install
+      - name: Run tests
+        run: bundle exec rake

data/README.md

@@ -86,6 +86,23 @@ You can create your own grammar by creating a gem that provides these files and
 
 ## Changelog
 
+### 11.0.0 (2021-10-29)
+
+* Prefix eId attributes in attachments with attachement's eId
+* Use crossHeading element for crossheadings
+
+### 10.7.0 (11 June 2021)
+
+* Support underlines with `__text__`
+
+### 10.6.0 (10 May 2021)
+
+* Handle sup and sub when extracting from HTML.
+
+### 10.5.0 (20 April 2021)
+
+* Handle escaping inlines when unparsing.
+
 ### 10.4.1 (14 April 2021)
 
 * Handle escaping in inlines, so that forward slashes in link text are unescaped correctly, eg `[https:\/\/example.com](https://example.com)`

data/lib/slaw/extract/html_to_akn_text.xsl

@@ -11,9 +11,10 @@
 
   <xsl:template match="head|style|script|link" />
 
-  <xsl:template match="ul|ol">
+  <!-- block containers that end with newlines -->
+  <xsl:template match="ul|ol|section|article|h1|h2|h3|h4|h5">
     <xsl:apply-templates />
-    <xsl:text>&#10;</xsl:text>
+    <xsl:text>&#10;&#10;</xsl:text>
   </xsl:template>
 
   <xsl:template match="ul/li">
@@ -23,20 +24,23 @@
     <xsl:text>&#10;</xsl:text>
   </xsl:template>
 
+  <!-- numbered lists should include a number -->
   <xsl:template match="ol/li">
-    <!-- 1. foo -->
+    <!-- \1. foo -->
     <xsl:text>\</xsl:text>
-    <xsl:value-of select="position()" />
+    <xsl:choose>
+      <xsl:when test="@value">
+        <xsl:value-of select="@value" />
+      </xsl:when>
+      <xsl:otherwise>
+        <xsl:value-of select="position()" />
+      </xsl:otherwise>
+    </xsl:choose>
     <xsl:text>. </xsl:text>
     <xsl:apply-templates />
     <xsl:text>&#10;</xsl:text>
   </xsl:template>
 
-  <xsl:template match="h1|h2|h3|h4|h5">
-    <xsl:apply-templates />
-    <xsl:text>&#10;&#10;</xsl:text>
-  </xsl:template>
-
   <xsl:template match="p|div">
     <xsl:choose>
       <xsl:when test="starts-with(., '[') and substring(., string-length(.)) = ']'">
@@ -51,32 +55,27 @@
     <xsl:text>&#10;&#10;</xsl:text>
   </xsl:template>
 
+  <!-- START tables -->
+
   <xsl:template match="table">
     <xsl:text>{| </xsl:text>
-    <xsl:text>
-|-</xsl:text>
+    <xsl:text>&#10;|-</xsl:text>
     <xsl:apply-templates />
-    <xsl:text>
-|}
-
-</xsl:text>
+    <xsl:text>&#10;|}&#10;&#10;</xsl:text>
   </xsl:template>
 
   <xsl:template match="tr">
     <xsl:apply-templates />
-    <xsl:text>
-|-</xsl:text>
+    <xsl:text>&#10;|-</xsl:text>
   </xsl:template>
 
   <xsl:template match="th|td">
     <xsl:choose>
       <xsl:when test="local-name(.) = 'th'">
-        <xsl:text>
-! </xsl:text>
+        <xsl:text>&#10;! </xsl:text>
       </xsl:when>
       <xsl:when test="local-name(.) = 'td'">
-        <xsl:text>
-| </xsl:text>
+        <xsl:text>&#10;| </xsl:text>
       </xsl:when>
     </xsl:choose>
 
@@ -118,8 +117,15 @@
   </xsl:template>
 
   <xsl:template match="br">
-    <xsl:text>
-</xsl:text>
+    <xsl:text>&#10;</xsl:text>
+  </xsl:template>
+
+  <xsl:template match="sup">
+    <xsl:text>^^</xsl:text><xsl:apply-templates /><xsl:text>^^</xsl:text>
+  </xsl:template>
+
+  <xsl:template match="sub">
+    <xsl:text>_^</xsl:text><xsl:apply-templates /><xsl:text>^_</xsl:text>
   </xsl:template>
 
 

data/lib/slaw/grammars/inlines.treetop

@@ -20,7 +20,7 @@ module Slaw
       end
 
       rule inline_item
-        remark / image / ref / bold / italics / superscript / subscript / [^\n]
+        remark / image / ref / bold / italics / superscript / subscript / underline / '\\'? [^\n]
         <InlineItem>
       end
 
@@ -69,6 +69,12 @@ module Slaw
         <Subscript>
       end
 
+      rule underline
+        # __foo__
+        '__' content:(!'__' inline_item)+ '__'
+        <Underline>
+      end
+
     end
   end
 end

data/lib/slaw/grammars/inlines_nodes.rb

@@ -37,8 +37,12 @@ module Slaw
 
       class InlineItem < Treetop::Runtime::SyntaxNode
         def to_xml(b, idprefix)
-          # handle escaped characters foo\/bar -> foo/bar
-          b.text(text_value.gsub(/\\(.)?/, '\1'))
+          if text_value.start_with? '\\'
+            # handle escaped characters: \a -> a
+            b.text(text_value[1..])
+          else
+            b.text(text_value)
+          end
         end
       end
 
@@ -92,6 +96,15 @@ module Slaw
         end
       end
 
+      class Underline < Treetop::Runtime::SyntaxNode
+        def to_xml(b, idprefix)
+          b.u { |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

@@ -97,8 +97,9 @@ module Slaw
 
           # the schedule id is derived from the heading
           schedule_id = self.schedule_id(heading_text, i)
+          eId = "att_#{i}"
 
-          b.attachment(eId: "att_#{i}") { |b|
+          b.attachment(eId: eId) { |b|
             schedule_title.to_xml(b, '', heading_text)
             b.doc_(name: "schedule") { |b|
               b.meta { |b|
@@ -128,7 +129,7 @@ module Slaw
               }
 
               b.mainBody { |b| 
-                body.children.elements.each_with_index { |e| e.to_xml(b, '', i) } if body.is_a? Body
+                body.children.elements.each_with_index { |e| e.to_xml(b, eId + "__", i) } if body.is_a? Body
               }
             }
           }

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

@@ -234,8 +234,14 @@ module Slaw
             section_title.num
           end
 
-          def to_xml(b, *args)
+          def to_xml(b, idprefix='', *args)
             id = "sec_#{Slaw::Grammars::Counters.clean(num)}"
+            # For historical reasons, we normally ignore the idprefix for sections, assuming
+            # them to be unique. However, in an attachment (eg. a schedule), ensure they
+            # are correctly prefixed
+            # TODO: always include the idprefix
+            id = idprefix + id if idprefix.start_with? 'att_'
+
             b.section(eId: id) { |b|
               section_title.to_xml(b)
 
@@ -371,13 +377,11 @@ module Slaw
 
         class Crossheading < Treetop::Runtime::SyntaxNode
           def to_xml(b, idprefix, i=0)
-            cnt = Slaw::Grammars::Counters.counters[idprefix]['hcontainer'] += 1
-            id = "#{idprefix}hcontainer_#{cnt}"
+            cnt = Slaw::Grammars::Counters.counters[idprefix]['crossHeading'] += 1
+            id = "#{idprefix}crossHeading_#{cnt}"
 
-            b.hcontainer(eId: id, name: 'crossheading') { |b|
-              b.heading { |b|
+            b.crossHeading(eId: id) { |b|
                 inline_items.to_xml(b, idprefix)
-              }
             }
           end
         end

data/lib/slaw/grammars/za/act_text.xsl

@@ -9,31 +9,147 @@
   <xsl:strip-space elements="*"/>
   <xsl:preserve-space elements="a:a a:affectedDocument a:b a:block a:caption a:change a:concept a:courtType a:date a:def a:del a:docCommittee a:docDate a:docIntroducer a:docJurisdiction a:docNumber a:docProponent a:docPurpose a:docStage a:docStatus a:docTitle a:docType a:docketNumber a:entity a:event a:extractText a:fillIn a:from a:heading a:i a:inline a:ins a:judge a:lawyer a:legislature a:li a:listConclusion a:listIntroduction a:location a:mmod a:mod a:mref a:narrative a:neutralCitation a:num a:object a:omissis a:opinion a:organization a:outcome a:p a:party a:person a:placeholder a:process a:quantity a:quotedText a:recordedTime a:ref a:relatedDocument a:remark a:rmod a:role a:rref a:scene a:session a:shortTitle a:signature a:span a:sub a:subheading a:summary a:sup a:term a:tocItem a:u a:vote"/>
 
+  <!-- replaces "value" in "text" with "replacement" -->
+  <xsl:template name="string-replace-all">
+    <xsl:param name="text" />
+    <xsl:param name="value" />
+    <xsl:param name="replacement" />
+
+    <xsl:choose>
+      <xsl:when test="$text = '' or $value = '' or not($value)">
+        <xsl:value-of select="$text" />
+      </xsl:when>
+      <xsl:when test="contains($text, $value)">
+        <xsl:value-of select="substring-before($text, $value)"/>
+        <xsl:value-of select="$replacement" />
+        <xsl:call-template name="string-replace-all">
+          <xsl:with-param name="text" select="substring-after($text, $value)" />
+          <xsl:with-param name="value" select="$value" />
+          <xsl:with-param name="replacement" select="$replacement" />
+        </xsl:call-template>
+      </xsl:when>
+      <xsl:otherwise>
+        <xsl:value-of select="$text" />
+      </xsl:otherwise>
+    </xsl:choose>
+  </xsl:template>
+
+  <!-- Escape inline markers with a backslash -->
+  <xsl:template name="escape-inlines">
+    <xsl:param name="text" />
+
+    <!-- This works from the inside out, first escaping backslash chars themselves, then escaping
+          the different types of inline markers -->
+    <xsl:call-template name="string-replace-all">
+      <xsl:with-param name="text">
+        <xsl:call-template name="string-replace-all">
+          <xsl:with-param name="text">
+            <xsl:call-template name="string-replace-all">
+              <xsl:with-param name="text">
+                <xsl:call-template name="string-replace-all">
+                  <xsl:with-param name="text">
+                    <xsl:call-template name="string-replace-all">
+                      <xsl:with-param name="text">
+                        <xsl:call-template name="string-replace-all">
+                          <xsl:with-param name="text">
+                            <xsl:call-template name="string-replace-all">
+                              <xsl:with-param name="text">
+                                <xsl:call-template name="string-replace-all">
+                                  <xsl:with-param name="text">
+                                    <xsl:call-template name="string-replace-all">
+                                      <xsl:with-param name="text">
+                                        <xsl:call-template name="string-replace-all">
+                                          <xsl:with-param name="text">
+                                            <xsl:call-template name="string-replace-all">
+                                              <xsl:with-param name="text" select="$text" />
+                                              <xsl:with-param name="value"><xsl:value-of select="'\'" /></xsl:with-param>
+                                              <xsl:with-param name="replacement"><xsl:value-of select="'\\'" /></xsl:with-param>
+                                            </xsl:call-template>
+                                          </xsl:with-param>
+                                          <xsl:with-param name="value"><xsl:value-of select="'**'" /></xsl:with-param>
+                                          <xsl:with-param name="replacement"><xsl:value-of select="'\*\*'" /></xsl:with-param>
+                                        </xsl:call-template>
+                                      </xsl:with-param>
+                                      <xsl:with-param name="value"><xsl:value-of select="'__'" /></xsl:with-param>
+                                      <xsl:with-param name="replacement"><xsl:value-of select="'\_\_'" /></xsl:with-param>
+                                    </xsl:call-template>
+                                  </xsl:with-param>
+                                  <xsl:with-param name="value"><xsl:value-of select="'//'" /></xsl:with-param>
+                                  <xsl:with-param name="replacement"><xsl:value-of select="'\/\/'" /></xsl:with-param>
+                                </xsl:call-template>
+                              </xsl:with-param>
+                              <xsl:with-param name="value"><xsl:value-of select="'_^'" /></xsl:with-param>
+                              <xsl:with-param name="replacement"><xsl:value-of select="'\_^'" /></xsl:with-param>
+                            </xsl:call-template>
+                          </xsl:with-param>
+                          <xsl:with-param name="value"><xsl:value-of select="'^_'" /></xsl:with-param>
+                          <xsl:with-param name="replacement"><xsl:value-of select="'\^_'" /></xsl:with-param>
+                        </xsl:call-template>
+                      </xsl:with-param>
+                      <xsl:with-param name="value"><xsl:value-of select="'^^'" /></xsl:with-param>
+                      <xsl:with-param name="replacement"><xsl:value-of select="'\^\^'" /></xsl:with-param>
+                  </xsl:call-template>
+                </xsl:with-param>
+                <xsl:with-param name="value"><xsl:value-of select="'!['" /></xsl:with-param>
+                <xsl:with-param name="replacement"><xsl:value-of select="'\!['" /></xsl:with-param>
+              </xsl:call-template>
+              </xsl:with-param>
+              <xsl:with-param name="value"><xsl:value-of select="']('" /></xsl:with-param>
+              <xsl:with-param name="replacement"><xsl:value-of select="'\]('" /></xsl:with-param>
+            </xsl:call-template>
+          </xsl:with-param>
+          <xsl:with-param name="value"><xsl:value-of select="'[['" /></xsl:with-param>
+          <xsl:with-param name="replacement"><xsl:value-of select="'\[\['" /></xsl:with-param>
+        </xsl:call-template>
+      </xsl:with-param>
+      <xsl:with-param name="value"><xsl:value-of select="']]'" /></xsl:with-param>
+      <xsl:with-param name="replacement"><xsl:value-of select="'\]\]'" /></xsl:with-param>
+    </xsl:call-template>
+  </xsl:template>
+
   <!-- adds a backslash to the start of the value param, if necessary -->
-  <xsl:template name="escape">
+  <xsl:template name="escape-prefixes">
     <xsl:param name="value"/>
 
     <xsl:variable name="prefix" select="translate(substring($value, 1, 13), 'abcdefghijklmnopqrstuvwxyz', 'ABCDEFGHIJKLMNOPQRSTUVWXYZ')" />
     <!-- '(' is considered special, so translate numbers into '(' so we can find and escape them -->
     <xsl:variable name="numprefix" select="translate(substring($value, 1, 3), '1234567890', '((((((((((')" />
 
-    <!-- p tags must escape initial content that looks like a block element marker -->
-    <xsl:if test="$prefix = 'BODY' or
-                  $prefix = 'PREAMBLE' or
-                  $prefix = 'PREFACE' or
-                  starts-with($prefix, 'CHAPTER ') or
-                  starts-with($prefix, 'PART ') or
-                  starts-with($prefix, 'SUBPART ') or
-                  starts-with($prefix, 'SCHEDULE ') or
-                  starts-with($prefix, 'HEADING ') or
-                  starts-with($prefix, 'SUBHEADING ') or
-                  starts-with($prefix, 'LONGTITLE ') or
-                  starts-with($prefix, 'CROSSHEADING ') or
-                  starts-with($prefix, '{|') or
-                  starts-with($numprefix, '(')">
-      <xsl:text>\</xsl:text>
-    </xsl:if>
-    <xsl:value-of select="$value"/>
+    <xsl:variable name="slash">
+      <!-- p tags must escape initial content that looks like a block element marker -->
+      <xsl:if test="$prefix = 'BODY' or
+                    $prefix = 'PREAMBLE' or
+                    $prefix = 'PREFACE' or
+                    starts-with($prefix, 'CHAPTER ') or
+                    starts-with($prefix, 'PART ') or
+                    starts-with($prefix, 'SUBPART ') or
+                    starts-with($prefix, 'SCHEDULE ') or
+                    starts-with($prefix, 'HEADING ') or
+                    starts-with($prefix, 'SUBHEADING ') or
+                    starts-with($prefix, 'LONGTITLE ') or
+                    starts-with($prefix, 'CROSSHEADING ') or
+                    starts-with($prefix, '{|') or
+                    starts-with($numprefix, '(')">
+        <xsl:value-of select="'\'" />
+      </xsl:if>
+    </xsl:variable>
+
+    <xsl:value-of select="concat($slash, $value)" />
+  </xsl:template>
+
+  <!-- adds a backslash to the start of the text param, if necessary -->
+  <xsl:template name="escape">
+    <xsl:param name="value"/>
+
+    <xsl:variable name="escaped">
+      <xsl:call-template name="escape-inlines">
+        <xsl:with-param name="text" select="$value" />
+      </xsl:call-template>
+    </xsl:variable>
+
+    <xsl:call-template name="escape-prefixes">
+      <xsl:with-param name="value" select="$escaped" />
+    </xsl:call-template>
   </xsl:template>
 
   <xsl:template match="a:act">
@@ -115,9 +231,9 @@
   </xsl:template>
 
   <!-- crossheadings -->
-  <xsl:template match="a:hcontainer[@name='crossheading']">
+  <xsl:template match="a:crossHeading">
     <xsl:text>CROSSHEADING </xsl:text>
-    <xsl:apply-templates select="a:heading" />
+    <xsl:apply-templates />
     <xsl:text>&#10;&#10;</xsl:text>
   </xsl:template>
 
@@ -157,12 +273,19 @@
   </xsl:template>
 
   <!-- first text nodes of these elems must be escaped if they have special chars -->
-  <xsl:template match="a:p[not(ancestor::a:table)]/text()[1] | a:listIntroduction/text()[1] | a:intro/text()[1]">
+  <xsl:template match="a:p[not(ancestor::a:table)]/text()[not(preceding-sibling::*)] | a:listIntroduction/text()[not(preceding-sibling::*)] | a:intro/text()[not(preceding-sibling::*)]">
     <xsl:call-template name="escape">
       <xsl:with-param name="value" select="." />
     </xsl:call-template>
   </xsl:template>
 
+  <!-- escape inlines in text nodes -->
+  <xsl:template match="text()">
+    <xsl:call-template name="escape-inlines">
+      <xsl:with-param name="text" select="." />
+    </xsl:call-template>
+  </xsl:template>
+
 
   <!-- attachments/schedules -->
   <xsl:template match="a:attachment">
@@ -176,7 +299,7 @@
       <xsl:text>&#10;</xsl:text>
     </xsl:if>
 
-    <xsl:text>&#10;&#10;</xsl:text>
+    <xsl:text>&#10;</xsl:text>
     <xsl:apply-templates select="a:doc/a:mainBody" />
   </xsl:template>
 
@@ -192,31 +315,24 @@
       <xsl:value-of select="." />
       <xsl:text>" </xsl:text>
     </xsl:for-each>
-    <xsl:text>
-|-</xsl:text>
+    <xsl:text>&#10;|-</xsl:text>
 
     <xsl:apply-templates />
-    <xsl:text>
-|}
-
-</xsl:text>
+    <xsl:text>&#10;|}&#10;&#10;</xsl:text>
   </xsl:template>
 
   <xsl:template match="a:tr">
     <xsl:apply-templates />
-    <xsl:text>
-|-</xsl:text>
+    <xsl:text>&#10;|-</xsl:text>
   </xsl:template>
 
   <xsl:template match="a:th|a:td">
     <xsl:choose>
       <xsl:when test="local-name(.) = 'th'">
-        <xsl:text>
-! </xsl:text>
+        <xsl:text>&#10;! </xsl:text>
       </xsl:when>
       <xsl:when test="local-name(.) = 'td'">
-        <xsl:text>
-| </xsl:text>
+        <xsl:text>&#10;| </xsl:text>
       </xsl:when>
     </xsl:choose>
 
@@ -287,6 +403,12 @@
     <xsl:text>^_</xsl:text>
   </xsl:template>
 
+  <xsl:template match="a:u">
+    <xsl:text>__</xsl:text>
+    <xsl:apply-templates />
+    <xsl:text>__</xsl:text>
+  </xsl:template>
+
   <xsl:template match="a:eol">
     <xsl:text>&#10;</xsl:text>
   </xsl:template>

data/lib/slaw/version.rb

@@ -1,3 +1,3 @@
 module Slaw
-  VERSION = "10.4.1"
+  VERSION = "11.0.0"
 end

data/spec/fixtures/roundtrip-escapes.txt

@@ -0,0 +1,24 @@
+BODY
+
+1. Section that tests escapes
+
+text \\ with a single slash
+
+some **inlines \/\/ [with \/\/ slashes](#foo)**
+
+inlines that \*\* should \/\/ be \[\[ escaped \![ and \]\]
+
+refs [https:\/\/example.com with ] and and \]( and **nested \*\* stars \*\***](#foo)
+
+nested ** stars \*\* in bold \*\***
+
+nested // slashes \/\/ in italics \/\///
+
+nested ** stars in // italics \*\* // and bold **
+
+super ^^with \^\^ hats \^\^^^ and sub _^\_^ with \^_ end tokens \^_^_
+
+underlines __underline with _ underscores__ and \_\_escaped underlines \_\_
+
+mixed __underline **and \_\_ bold**__
+

data/spec/generator_spec.rb

@@ -78,45 +78,81 @@ XML
 
 1. Section
 
-\Chapter 2 ignored
+\\Chapter 2 ignored
 
 Chapters
 
-\Part 2 ignored
+\\Part 2 ignored
 
 participation
 
-\Schedule 2 ignored
+\\Schedule 2 ignored
 
 Schedules
 
-\HEADING x
+\\HEADING x
 
-\SUBHEADING x
+\\SUBHEADING x
 
 BODY not escaped
 
-\BODY
+\\BODY
 
 PREAMBLE not escaped
 
-\PREAMBLE
+\\PREAMBLE
 
 PREFACE not escaped
 
-\PREFACE
+\\PREFACE
 
-\2. ignored
+\\2. ignored
 
-\2.1 ignored
+\\2.1 ignored
 
-\(2) ignored
+\\(2) ignored
 
-\(a) ignored
+\\(a) ignored
 
-\(2a) ignored
+\\(2a) ignored
 
-\{| ignored
+\\{| ignored
+
+'
+    end
+
+    it 'should escape inlines when unparsing' do
+      doc = xml2doc(section(<<'XML'
+        <num>1.</num>
+        <heading>Section</heading>
+        <paragraph id="section-1.paragraph-0">
+          <content>
+            <p>text \ with a single slash</p>
+            <p>some <b>inlines // <ref href="#foo">with // slashes</ref></b></p>
+            <p>inlines that ** should // be [[ escaped ![ and ]]</p>
+            <p>refs <ref href="#foo">https://example.com with ] and ]( and <b>nested **</b></ref></p>
+            <p>super <sup>with ^^</sup> and sub <sub>_^ with ^_</sub></p>
+          </content>
+        </paragraph>
+XML
+      ))
+
+      text = subject.text_from_act(doc)
+      # NOTE: in single quoted strings, backslash sequences aren't considered special, EXCEPT a double backslash
+      # which is actually a single backslash. So \\ needs to be \\\\ while \* is just \*. The mind boggles.
+      text.should == 'BODY
+
+1. Section
+
+text \\\\ with a single slash
+
+some **inlines \/\/ [with \/\/ slashes](#foo)**
+
+inlines that \*\* should \/\/ be \[\[ escaped \![ and \]\]
+
+refs [https:\/\/example.com with ] and \]( and **nested \*\***](#foo)
+
+super ^^with \^\^^^ and sub _^\_^ with \^_^_
 
 '
     end
@@ -148,7 +184,7 @@ XML
 
 1. Section
 
-\(2) A special meeting [[ foo ]]:
+\\(2) A special meeting [[ foo ]]:
 
 (a) the chairperson so directs; or
 
@@ -201,6 +237,27 @@ XML
 
 Hello [there](/za/act/123) friend.
 
+'
+    end
+
+    it 'should unparse underlines correctly' do
+      doc = xml2doc(section(<<XML
+        <num>1.</num>
+        <paragraph id="section-19.paragraph-0">
+          <content>
+            <p>Hello <u>underlined</u>.</p>
+          </content>
+        </paragraph>
+XML
+      ))
+
+      text = subject.text_from_act(doc)
+      text.should == 'BODY
+
+1. 
+
+Hello __underlined__.
+
 '
     end
 
@@ -269,4 +326,13 @@ Subject to approval in terms of this By-Law.
 '
     end
   end
+
+  describe 'round trip' do
+    it 'should be idempotent for escapes' do
+      text = File.open('spec/fixtures/roundtrip-escapes.txt', 'r').read()
+      act = subject.generate_from_text(text)
+      xml = act.to_xml(encoding: 'utf-8')
+      subject.text_from_act(act).should == text
+    end
+  end
 end

data/spec/za/act_block_spec.rb

@@ -59,9 +59,7 @@ EOS
         <p>Hello there</p>
       </content>
     </hcontainer>
-    <hcontainer eId="sec_1__hcontainer_2" name="crossheading">
-      <heading>crossheading</heading>
-    </hcontainer>
+    <crossHeading eId="sec_1__crossHeading_1">crossheading</crossHeading>
   </section>
 </body>'
     end
@@ -96,9 +94,7 @@ EOS
       </blockList>
     </content>
   </hcontainer>
-  <hcontainer eId="hcontainer_2" name="crossheading">
-    <heading>crossheading</heading>
-  </hcontainer>
+  <crossHeading eId="crossHeading_1">crossheading</crossHeading>
   <section eId="sec_1">
     <num>1.</num>
     <heading>Section</heading>
@@ -107,9 +103,7 @@ EOS
         <p>Hello there</p>
       </content>
     </hcontainer>
-    <hcontainer eId="sec_1__hcontainer_2" name="crossheading">
-      <heading>crossheading</heading>
-    </hcontainer>
+    <crossHeading eId="sec_1__crossHeading_1">crossheading</crossHeading>
   </section>
 </body>'
     end
@@ -117,16 +111,19 @@ EOS
     it 'should handle escaped content' do
       node = parse :body, <<EOS
 \\1. ignored
+foo \\\\bar
 
 \\CROSSHEADING cross\\heading
 
 1. Sec\\tion
 \\Chapter 2 ignored
+Some text with a \\\\real backslash
 EOS
       to_xml(node).should == '<body>
   <hcontainer eId="hcontainer_1" name="hcontainer">
     <content>
       <p>1. ignored</p>
+      <p>foo \\bar</p>
       <p>CROSSHEADING crossheading</p>
     </content>
   </hcontainer>
@@ -136,6 +133,7 @@ EOS
     <hcontainer eId="sec_1__hcontainer_1" name="hcontainer">
       <content>
         <p>Chapter 2 ignored</p>
+        <p>Some text with a \\real backslash</p>
       </content>
     </hcontainer>
   </section>
@@ -256,10 +254,8 @@ EOS
       to_xml(node).should == '<chapter eId="chp_2">
   <num>2</num>
   <heading>The Chapter Heading</heading>
-  <hcontainer eId="chp_2__hcontainer_1" name="crossheading">
-    <heading>crossheading</heading>
-  </hcontainer>
-  <hcontainer eId="chp_2__hcontainer_2" name="hcontainer">
+  <crossHeading eId="chp_2__crossHeading_1">crossheading</crossHeading>
+  <hcontainer eId="chp_2__hcontainer_1" name="hcontainer">
     <content>
       <p>Some lines at the start of the chapter.</p>
     </content>
@@ -485,9 +481,7 @@ EOS
       to_xml(node).should == '<part eId="part_2">
   <num>2</num>
   <heading>The Part Heading</heading>
-  <hcontainer eId="part_2__hcontainer_1" name="crossheading">
-    <heading>crossheading</heading>
-  </hcontainer>
+  <crossHeading eId="part_2__crossHeading_1">crossheading</crossHeading>
   <section eId="sec_1">
     <num>1.</num>
     <heading>Section</heading>
@@ -1868,9 +1862,7 @@ EOS
   context 'crossheadings' do
     it 'should handle a inline_items in crossheadings' do
       node = parse :crossheading, "CROSSHEADING something [[remark]] [link](/foo/bar)\n"
-      to_xml(node, '').should == '<hcontainer eId="hcontainer_1" name="crossheading">
-  <heading>something <remark status="editorial">[remark]</remark> <ref href="/foo/bar">link</ref></heading>
-</hcontainer>'
+      to_xml(node, '').should == '<crossHeading eId="crossHeading_1">something <remark status="editorial">[remark]</remark> <ref href="/foo/bar">link</ref></crossHeading>'
     end
 
     it 'should not be allowed in preface' do
@@ -1920,9 +1912,7 @@ Text
     <p>Some text</p>
   </preface>
   <body>
-    <hcontainer eId="hcontainer_1" name="crossheading">
-      <heading>In the body</heading>
-    </hcontainer>
+    <crossHeading eId="crossHeading_1">In the body</crossHeading>
     <section eId="sec_1">
       <num>1.</num>
       <heading>Section 1</heading>
@@ -1983,9 +1973,7 @@ Text
     <p>Some text</p>
   </preamble>
   <body>
-    <hcontainer eId="hcontainer_1" name="crossheading">
-      <heading>In the body</heading>
-    </hcontainer>
+    <crossHeading eId="crossHeading_1">In the body</crossHeading>
     <section eId="sec_1">
       <num>1.</num>
       <heading>Section 1</heading>

data/spec/za/act_inline_spec.rb

@@ -197,7 +197,7 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>
             <remark status="editorial">[Schedule 1 added by Act 23 of 2004]</remark>
@@ -535,4 +535,17 @@ EOS
     end
   end
 
+  describe 'underline' do
+    it 'should handle underline' do
+      node = parse :generic_container, <<EOS
+      Text __with underline__ and _ under__scores__.
+EOS
+      to_xml(node, "").should == '<hcontainer eId="hcontainer_1" name="hcontainer">
+  <content>
+    <p>Text <u>with underline</u> and _ under<u>scores</u>.</p>
+  </content>
+</hcontainer>'
+    end
+  end
+
 end

data/spec/za/act_schedules_spec.rb

@@ -88,11 +88,11 @@ EOS
         </identification>
       </meta>
       <mainBody>
-        <section eId="sec_1">
+        <section eId="att_1__sec_1">
           <num>1.</num>
           <heading>Foo</heading>
         </section>
-        <section eId="sec_2">
+        <section eId="att_1__sec_2">
           <num>2.</num>
           <heading>Bar</heading>
         </section>
@@ -129,7 +129,7 @@ EOS
         </identification>
       </meta>
       <mainBody>
-        <hcontainer eId="hcontainer_1" name="hcontainer">
+        <hcontainer eId="att_2__hcontainer_1" name="hcontainer">
           <content>
             <p>Baz</p>
             <p>Boom</p>
@@ -186,16 +186,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -246,16 +246,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -304,16 +304,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -372,19 +372,19 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <part eId="part_I">
+      <part eId="att_1__part_I">
         <num>I</num>
         <heading>Form of authentication statement</heading>
-        <hcontainer eId="part_I__hcontainer_1" name="hcontainer">
+        <hcontainer eId="att_1__part_I__hcontainer_1" name="hcontainer">
           <content>
             <p>This printed impression has been carefully compared by me with the bill which was passed by Parliament and found by me to be a true copy of the bill.</p>
           </content>
         </hcontainer>
       </part>
-      <part eId="part_II">
+      <part eId="att_1__part_II">
         <num>II</num>
         <heading>Form of statement of the President’s assent.</heading>
-        <hcontainer eId="part_II__hcontainer_1" name="hcontainer">
+        <hcontainer eId="att_1__part_II__hcontainer_1" name="hcontainer">
           <content>
             <p>I signify my assent to the bill and a whole bunch of other stuff.</p>
           </content>
@@ -447,7 +447,7 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law.</p>
           <p>Schedule another</p>
@@ -499,7 +499,7 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law.</p>
         </content>
@@ -550,16 +550,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -608,12 +608,12 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
@@ -665,16 +665,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -729,11 +729,11 @@ EOS
         </identification>
       </meta>
       <mainBody>
-        <section eId="sec_1">
+        <section eId="att_1__sec_1">
           <num>1.</num>
           <heading>Foo</heading>
         </section>
-        <section eId="sec_2">
+        <section eId="att_1__sec_2">
           <num>2.</num>
           <heading>Bar</heading>
         </section>
@@ -770,7 +770,7 @@ EOS
         </identification>
       </meta>
       <mainBody>
-        <hcontainer eId="hcontainer_1" name="hcontainer">
+        <hcontainer eId="att_2__hcontainer_1" name="hcontainer">
           <content>
             <p>Baz</p>
             <p>Boom</p>
@@ -826,16 +826,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -885,16 +885,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -942,16 +942,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law, the erection:</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -1001,16 +1001,16 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Other than as is set out hereinbelow, no signs other than locality bound signs, temporary signs including loose portable sign, estate agents signs, newspaper headline posters and posters (the erection of which must comply with the appropriate schedules pertinent thereto) shall be erected on Municipal owned land.</p>
         </content>
       </hcontainer>
-      <section eId="sec_1">
+      <section eId="att_1__sec_1">
         <num>1.</num>
         <heading>Foo</heading>
       </section>
-      <section eId="sec_2">
+      <section eId="att_1__sec_2">
         <num>2.</num>
         <heading>Bar</heading>
       </section>
@@ -1060,7 +1060,7 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Subject to approval in terms of this By-Law.</p>
         </content>

data/spec/za/act_table_spec.rb

@@ -298,10 +298,10 @@ EOS
       </identification>
     </meta>
     <mainBody>
-      <hcontainer eId="hcontainer_1" name="hcontainer">
+      <hcontainer eId="att_1__hcontainer_1" name="hcontainer">
         <content>
           <p>Heres a table:</p>
-          <table eId="hcontainer_1__table_1">
+          <table eId="att_1__hcontainer_1__table_1">
             <tr>
               <td>
                 <p>r1c1</p>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 10.4.1
+  version: 11.0.0
 platform: ruby
 authors:
 - Greg Kempe
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-04-14 00:00:00.000000000 Z
+date: 2021-11-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -103,9 +103,9 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/test.yml"
 - ".gitignore"
 - ".rspec"
-- ".travis.yml"
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -144,6 +144,7 @@ files:
 - spec/counters_spec.rb
 - spec/extract/extractor_spec.rb
 - spec/fixtures/community-fire-safety.xml
+- spec/fixtures/roundtrip-escapes.txt
 - spec/generator_spec.rb
 - spec/parse/blocklists_spec.rb
 - spec/parse/builder_spec.rb
@@ -174,7 +175,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.1.4
 signing_key:
 specification_version: 4
 summary: A lightweight library for using Akoma Ntoso acts in Ruby.
@@ -182,6 +183,7 @@ test_files:
 - spec/counters_spec.rb
 - spec/extract/extractor_spec.rb
 - spec/fixtures/community-fire-safety.xml
+- spec/fixtures/roundtrip-escapes.txt
 - spec/generator_spec.rb
 - spec/parse/blocklists_spec.rb
 - spec/parse/builder_spec.rb

data/.travis.yml

@@ -1,6 +0,0 @@
-language: ruby
-rvm:
-  - 2.7.0
-  - 2.6.2
-before_install:
-  - gem update bundler