slaw 10.5.0 → 10.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ba413f53b9d24192d6ce5a168eed83ca55a317dcb3768009cfdf3bf902a23327
-  data.tar.gz: f664b13ce90bb21b65c0fffb2f780dc5937429c31ac2a9d6270259e0669f2f61
+  metadata.gz: 2feb9ea5e726f4300a0920de90b88f14b3a86ce4ae3dddd9a59b3bf8c855e575
+  data.tar.gz: 263ef515bc1a81b8cccc1788a3b107b573f3840492913cedf17ae729745d1c4b
 SHA512:
-  metadata.gz: 0f0929aa1fcce2c86f6340fec7731f5e865e0b58b793b4f7d64ba48ec2463299498b4b96fea3487a11ab57a2ae932273e27c593395cd2ca263347006fa36a88a
-  data.tar.gz: 72aceb516d091bd396deeb828873058a3cda366524c3e1819590ae77f021ab9a806baf0108f1239dceaaf0e7a64713e1c954ec385b5ed03563f1d702cd4b0984
+  metadata.gz: 573bab26b9e880856e74404058208e9fae5f400f0ee64413d771fea872e4b3b7c626ebefb5c020321dc4b4f35919b25b94801c6622e82d2f2a8dfe3507c35f61
+  data.tar.gz: 01d73bb0903dbee8213eae364316835361b4d34bbe0ed4a12f9dcaeb114bf1e5ec9ac46133e0570bea1998af0daaac610591da905463d64e63f1449ffd529db7

data/README.md

@@ -86,6 +86,10 @@ 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.

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/za/act_text.xsl

@@ -293,7 +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>
 

data/lib/slaw/version.rb

@@ -1,3 +1,3 @@
 module Slaw
-  VERSION = "10.5.0"
+  VERSION = "10.6.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: slaw
 version: !ruby/object:Gem::Version
-  version: 10.5.0
+  version: 10.6.0
 platform: ruby
 authors:
 - Greg Kempe
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-04-21 00:00:00.000000000 Z
+date: 2021-05-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake