Escape literals

CHANGES.md

@@ -1,5 +1,14 @@
 # Change Log
 
+## 0.7.0
+
+- escape double quotes, LF and CR and backslash in literals as
+  required by the [N-Triples specs, sec. 2.3 RDF
+  Literals](https://www.w3.org/TR/n-triples/#sec-literals). Escaping
+  must already be done by the XTriples processor, i.e. in the XSLT
+  stylesheet. This fixes issue #6.
+- reverts escaping done in 0.6.4 from the recipes 
+
 ## 0.6.3
 
 escape double quotes in extracted literals

recipes/tei/crm-entities.xml

@@ -62,14 +62,14 @@ target/bin/xslt.sh -xsl:xsl/extract-param-doc.xsl -s:recipes/tei/crm-entity-name
                 <condition>/$repeatIndex eq 1</condition>
                 <subject prefix="ent">/concat(local-name(.), '#', @xml:id)</subject>
                 <predicate prefix="crm">P48_has_preferred_identifier</predicate>
-                <object type="bnode">/concat('entityIdentifier_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)=>replace('&quot;', '&amp;quot;')</object>
+                <object type="bnode">/concat('entityIdentifier_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)</object>
             </statement>
 
             <!-- identifiers from all names -->
             <statement repeat="{/count(*[self::tei:name or self::tei:persName or self::tei:placeName or self::tei:orgName or self::tei:eventName]) }">
                 <subject prefix="ent">/concat(local-name(.), '#', @xml:id)</subject>
                 <predicate prefix="crm">P1_is_identified_by</predicate>
-                <object type="bnode">/concat('entityIdentifier_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)=>replace('&quot;', '&amp;quot;')</object>
+                <object type="bnode">/concat('entityIdentifier_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)</object>
             </statement>
             <statement repeat="{/count(*[self::tei:name or self::tei:persName or self::tei:placeName or self::tei:orgName or self::tei:eventName]) }">
                 <subject type="bnode">/concat('entityIdentifier_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)</subject>
@@ -80,7 +80,7 @@ target/bin/xslt.sh -xsl:xsl/extract-param-doc.xsl -s:recipes/tei/crm-entity-name
                 <subject type="bnode">/concat('entityIdentifier_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)</subject>
                 <!-- sdh:P21 = sdh:P100_has_value see https://ontome.net/property/1843/namespace/3#identification -->
                 <predicate prefix="sdh">P21</predicate>
-                <object type="literal">/*[$repeatIndex]=>normalize-space()=>replace('&quot;', '&amp;quot;')</object>
+                <object type="literal">/*[$repeatIndex]=>normalize-space()</object>
             </statement>
             <statement repeat="{/count(*[self::tei:name or self::tei:persName or self::tei:placeName or self::tei:orgName or self::tei:eventName]) }">
                 <subject type="bnode">/concat('entityIdentifier_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)</subject>

recipes/tei/lincs-entities.xml

@@ -111,7 +111,7 @@ target/bin/xslt.sh -xsl:xsl/extract-param-doc.xsl -s:recipes/tei/lincs-entities.
             <statement>
                 <subject type="bnode">/concat('attributeAssignment', $resourceIndex)</subject>
                 <predicate prefix="crm">P3_has_note</predicate>
-                <object type="literal">/normalize-space(.)=>replace('&quot;', '&amp;quot;')</object>
+                <object type="literal">/normalize-space(.)</object>
             </statement>
             <statement>
                 <subject type="bnode">/concat('attributeAssignment', $resourceIndex)</subject>
@@ -223,7 +223,7 @@ target/bin/xslt.sh -xsl:xsl/extract-param-doc.xsl -s:recipes/tei/lincs-entities.
             <statement>
                 <subject type="bnode">/concat('quote', $resourceIndex)</subject>
                 <predicate prefix="oa">exact</predicate>
-                <object type="literal">/normalize-space(.)=>replace('&quot;', '&amp;quot;')</object>
+                <object type="literal">/normalize-space(.)</object>
             </statement>
             <statement>
                 <condition>/exists(function-lookup(xs:QName('utils:prefix'), 1))</condition>

recipes/tei/tei-entities.xml

@@ -67,7 +67,7 @@ target/bin/xslt.sh -xsl:xsl/extract-param-doc.xsl -s:recipes/tei/crm-entity-name
             <statement repeat="{/count(*[self::tei:desc or self::tei:note]) }">
                 <subject type="bnode">/concat('description_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)</subject>
                 <predicate prefix="sdh">P21</predicate>
-                <object type="literal">/*[self::tei:desc or self::tei:note][$repeatIndex]=>normalize-space()=>replace('&quot;', '&amp;quot;')</object>
+                <object type="literal">/*[self::tei:desc or self::tei:note][$repeatIndex]=>normalize-space()</object>
             </statement>
             <statement repeat="{/count(*[self::tei:desc or self::tei:note]) }">
                 <subject type="bnode">/concat('description_', local-name(.), '_', $resourceIndex, '_', $repeatIndex)</subject>

test/backslash.tei.xml

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<?xml-model href="http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng" type="application/xml"
+	schematypens="http://purl.oclc.org/dsdl/schematron"?>
+<TEI xmlns="http://www.tei-c.org/ns/1.0">
+  <teiHeader>
+      <fileDesc>
+         <titleStmt>
+            <title>\Title\</title>
+         </titleStmt>
+         <publicationStmt>
+            <p>Publication Information</p>
+         </publicationStmt>
+         <sourceDesc>
+            <p>Information about the source</p>
+         </sourceDesc>
+      </fileDesc>
+  </teiHeader>
+  <text>
+      <body>
+         <p>Some text here.</p>
+      </body>
+  </text>
+</TEI>

test/cr-lf.tei.xml

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<?xml-model href="http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng" type="application/xml"
+	schematypens="http://purl.oclc.org/dsdl/schematron"?>
+<TEI xmlns="http://www.tei-c.org/ns/1.0">
+   <teiHeader>
+      <fileDesc>
+         <titleStmt>
+            <title xml:space="preserve">Title
+with&#xd;&#xa;new lines</title>
+         </titleStmt>
+         <publicationStmt>
+            <p>Publication Information</p>
+         </publicationStmt>
+         <sourceDesc>
+            <p>Information about the source</p>
+         </sourceDesc>
+      </fileDesc>
+   </teiHeader>
+   <text>
+      <body>
+         <p>Some text here.</p>
+      </body>
+   </text>
+</TEI>

test/quote.tei.xml

@@ -0,0 +1,24 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?xml-model href="http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?>
+<?xml-model href="http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng" type="application/xml"
+	schematypens="http://purl.oclc.org/dsdl/schematron"?>
+<TEI xmlns="http://www.tei-c.org/ns/1.0">
+  <teiHeader>
+      <fileDesc>
+         <titleStmt>
+            <title>"Title"</title>
+         </titleStmt>
+         <publicationStmt>
+            <p>Publication Information</p>
+         </publicationStmt>
+         <sourceDesc>
+            <p>Information about the source</p>
+         </sourceDesc>
+      </fileDesc>
+  </teiHeader>
+  <text>
+      <body>
+         <p>Some text here.</p>
+      </body>
+  </text>
+</TEI>

xsl/xtriples.xsl

@@ -256,7 +256,13 @@ This is only a module and should be imported by some calling stylesheet.
                 <xsl:when test="$part/@type eq 'literal' or $part/self::object[not(@type)]">
                     <xsl:value-of>
                         <xsl:text>"</xsl:text>
-                        <xsl:value-of select="$x"/>
+                        <!-- try to escape, however, some types cannot be escaped -->
+                        <xsl:try>
+                            <xsl:value-of select="$x => xtriples:escape-literal()"/>
+                            <xsl:catch>
+                                <xsl:value-of select="$x"/>
+                            </xsl:catch>
+                        </xsl:try>
                         <xsl:text>"</xsl:text>
                         <xsl:choose>
                             <!--
@@ -304,6 +310,13 @@ This is only a module and should be imported by some calling stylesheet.
         </xsl:for-each>
     </xsl:function>
 
+    <xsl:function name="xtriples:escape-literal" as="xs:string">
+        <xsl:param name="unescaped" as="xs:string"/>
+        <xsl:value-of
+            select="$unescaped => replace('\\', '\\\\') => replace('&#xa;', '\\n') => replace('&#xd;', '\\r') => replace('&quot;', '\\&quot;')"
+        />
+    </xsl:function>
+
     <xsl:function name="xtriples:serialize">
         <xsl:param name="sentence-parts" as="item()*"/>
         <xsl:for-each select="$sentence-parts">

xsl/xtriples.xspec

@@ -320,4 +320,34 @@
             select="'"Es ist alles eitel 2.0"'"/>
     </x:scenario>
 
+    <x:scenario label="double quotes in literals are escaped">
+        <x:call template="xtriples:extract">
+            <x:param name="config" href="../test/config-01.xml"/>
+            <x:param name="resource" href="../test/quote.tei.xml"/>
+            <x:param name="resource-index" select="1"/>
+        </x:call>
+        <x:expect label="quote escaped in literal" as="xs:string" test="$x:result[3]"
+            select="'&quot;\&quot;Title\&quot;&quot;'"/>
+    </x:scenario>
+
+    <x:scenario label="backslashed in literals are escaped">
+        <x:call template="xtriples:extract">
+            <x:param name="config" href="../test/config-01.xml"/>
+            <x:param name="resource" href="../test/backslash.tei.xml"/>
+            <x:param name="resource-index" select="1"/>
+        </x:call>
+        <x:expect label="backslash escaped in literal" as="xs:string" test="$x:result[3]"
+            select="'&quot;\\Title\\&quot;'"/>
+    </x:scenario>
+
+    <x:scenario label="CR and LF in literals are escaped">
+        <x:call template="xtriples:extract">
+            <x:param name="config" href="../test/config-01.xml"/>
+            <x:param name="resource" href="../test/cr-lf.tei.xml"/>
+            <x:param name="resource-index" select="1"/>
+        </x:call>
+        <x:expect label="CR and LF escaped in literal" as="xs:string" test="$x:result[3]"
+            select="'&quot;Title\nwith\r\nnew lines&quot;'"/>
+    </x:scenario>
+
 </x:description>