slaw 10.2.0 → 10.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f76b66445a595e5130d1a3af8b153498d41007416bcd7c5ced418d4339030303
-  data.tar.gz: cd28f4839c8ecd4b430a6111a3c5ec3df764af84674b1e6205d54ac27b3c734f
+  metadata.gz: 2feb9ea5e726f4300a0920de90b88f14b3a86ce4ae3dddd9a59b3bf8c855e575
+  data.tar.gz: 263ef515bc1a81b8cccc1788a3b107b573f3840492913cedf17ae729745d1c4b
 SHA512:
-  metadata.gz: f04d34041c3dc21f552b81af8d331d4440cd7c36d94e38007d15be8b467cca15b2bedbc1b5d1fb7d652ebd2b263f695a02afd337ce20df5c0e5eca7b1ec02050
-  data.tar.gz: dae3ef8b12f13761543a90b1711b301af9a3368cbde2387c8c00adf717c6a297ddfcfe108b9ef53073b370178574877a978fb8968d63317ed736ca1c49417232
+  metadata.gz: 573bab26b9e880856e74404058208e9fae5f400f0ee64413d771fea872e4b3b7c626ebefb5c020321dc4b4f35919b25b94801c6622e82d2f2a8dfe3507c35f61
+  data.tar.gz: 01d73bb0903dbee8213eae364316835361b4d34bbe0ed4a12f9dcaeb114bf1e5ec9ac46133e0570bea1998af0daaac610591da905463d64e63f1449ffd529db7

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

@@ -86,6 +86,26 @@ You can create your own grammar by creating a gem that provides these files and
 
 ## Changelog
 
+### 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)`
+
+### 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^^`

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/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/counters.rb

@@ -24,20 +24,32 @@ module Slaw
       # 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
+      # "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
+      # 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
-          .gsub(/[ ()\[\]]/, '')
-          .gsub(/\.+$/, '')
-          .gsub(/^\.+/, '')
-          .gsub(/\.+/, '-')
       end
     end
   end

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 / '\\'? [^\n]
         <InlineItem>
       end
 

data/lib/slaw/grammars/inlines_nodes.rb

@@ -37,7 +37,12 @@ module Slaw
 
       class InlineItem < Treetop::Runtime::SyntaxNode
         def to_xml(b, idprefix)
-          b.text(text_value)
+          if text_value.start_with? '\\'
+            # handle escaped characters: \a -> a
+            b.text(text_value[1..])
+          else
+            b.text(text_value)
+          end
         end
       end
 

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

@@ -9,31 +9,141 @@
   <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" 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: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">
@@ -157,12 +267,19 @@
   </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 +293,7 @@
       <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 +309,24 @@
       <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>
 

data/lib/slaw/version.rb

@@ -1,3 +1,3 @@
 module Slaw
-  VERSION = "10.2.0"
+  VERSION = "10.6.0"
 end

data/slaw.gemspec

@@ -25,5 +25,4 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency "treetop", "~> 1.5"
   spec.add_runtime_dependency "log4r", "~> 1.1"
   spec.add_runtime_dependency "thor", "~> 0.20"
-  spec.add_runtime_dependency "mimemagic", "~> 0.2"
 end

data/spec/counters_spec.rb

@@ -0,0 +1,38 @@
+# encoding: UTF-8
+
+require 'spec_helper'
+
+require 'slaw'
+
+describe Slaw::Grammars::Counters do
+  describe '#clean' do
+    it 'should remove leading and trailing punctuation' do
+      described_class.clean("").should == ""
+      described_class.clean(" ").should == ""
+      described_class.clean("( )").should == ""
+      described_class.clean("(123.4-5)").should == "123-4-5"
+      described_class.clean("(312.32.7)").should == "312-32-7"
+      described_class.clean("(312_32_7)").should == "312-32-7"
+      described_class.clean("(6)").should == "6"
+      described_class.clean("[16]").should == "16"
+      described_class.clean("(i)").should == "i"
+      described_class.clean("[i]").should == "i"
+      described_class.clean("(2bis)").should == "2bis"
+      described_class.clean('"1.2.').should == "1-2"
+      described_class.clean("1.2.").should == "1-2"
+      described_class.clean("“2.3").should == "2-3"
+      described_class.clean("2,3").should == "2-3"
+      described_class.clean("2,3, 4,").should == "2-3-4"
+      described_class.clean("3a bis").should == "3abis"
+      described_class.clean("3é").should == "3é"
+      described_class.clean(" -3a--4,9").should == "3a-4-9"
+    end
+
+    it 'should handle non-arabic numerals' do
+      # hebrew aleph
+      described_class.clean("(א)").should == "א"
+      # chinese 3
+      described_class.clean("(三)").should == "三"
+    end
+  end
+end

data/spec/fixtures/roundtrip-escapes.txt

@@ -0,0 +1,20 @@
+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 \^_^_
+

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
 
@@ -269,4 +305,13 @@ 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

@@ -117,16 +117,19 @@ EOS
     it 'should handle escaped content' do
       node = parse :body, <<EOS
 \\1. ignored
+foo \\\\bar
 
-\\CROSSHEADING crossheading
+\\CROSSHEADING cross\\heading
 
-1. Section
+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 +139,7 @@ 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>

data/spec/za/act_inline_spec.rb

@@ -325,6 +325,17 @@ EOS
     <p>This statement has <remark status="editorial">[<ref href="/foo/bar">a link in</ref> a remark]</remark></p>
     <p>This statement has <remark status="editorial">[a <ref href="/foo/bar">link in a remark</ref>]</remark></p>
   </content>
+</hcontainer>'
+    end
+
+    it 'should handle escapes in links' do
+      node = parse :generic_container, <<EOS
+      Visit the site [https:\\/\\/example.com](https://example.com) for more.
+EOS
+      to_xml(node, "").should == '<hcontainer eId="hcontainer_1" name="hcontainer">
+  <content>
+    <p>Visit the site <ref href="https://example.com">https://example.com</ref> for more.</p>
+  </content>
 </hcontainer>'
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 10.2.0
+  version: 10.6.0
 platform: ruby
 authors:
 - Greg Kempe
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-09-04 00:00:00.000000000 Z
+date: 2021-05-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -94,20 +94,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.20'
-- !ruby/object:Gem::Dependency
-  name: mimemagic
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.2'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.2'
 description: Slaw is a lightweight library for rendering and generating Akoma Ntoso
   acts from plain text and PDF documents.
 email:
@@ -155,8 +141,10 @@ files:
 - lib/slaw/version.rb
 - lib/slaw/xml_support.rb
 - slaw.gemspec
+- 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
@@ -172,7 +160,7 @@ homepage: https://github.com/longhotsummer/slaw
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -188,12 +176,14 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubygems_version: 3.0.3
-signing_key: 
+signing_key:
 specification_version: 4
 summary: A lightweight library for using Akoma Ntoso acts in Ruby.
 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