Preserve heading structure in zedai-to-html

Also has an effect on dtbook-to-html and dtbook-to-epub3 (which use zedai-to-html). Fixes daisy/pipeline#678 and daisy/pipeline#680.
daisy · Jun 15, 2023 · 21294fb · 21294fb
1 parent 3741d86
commit 21294fb
Show file tree

Hide file tree

Showing 12 changed files with 89 additions and 47 deletions.
diff --git a/bom/pom.xml b/bom/pom.xml
@@ -409,7 +409,7 @@
       <dependency>
         <groupId>org.daisy.pipeline.modules</groupId>
         <artifactId>zedai-to-html</artifactId>
-        <version>2.1.7-SNAPSHOT</version>
+        <version>2.2.0-SNAPSHOT</version>
       </dependency>
       <dependency>
         <groupId>org.daisy.pipeline.modules.braille</groupId>

diff --git a/scripts/daisy3-to-epub3/src/test/xprocspec/test_daisy3-to-epub3.xprocspec b/scripts/daisy3-to-epub3/src/test/xprocspec/test_daisy3-to-epub3.xprocspec
@@ -81,7 +81,7 @@
 		<x:expect label="the book-1.smil file" type="compare">
 			<x:document type="inline">
 				<smil xmlns="http://www.w3.org/ns/SMIL" version="3.0">
-					<body epub:type="frontmatter">
+					<body epub:textref="../book-1.xhtml#id_4" epub:type="frontmatter">
 						<seq epub:textref="../book-1.xhtml#id_1">
 							<seq epub:textref="../book-1.xhtml#forsmil-d1386e16" epub:type="title">
 								<par>
@@ -106,7 +106,7 @@
 		<x:expect label="the book-2.smil file" type="compare">
 			<x:document type="inline">
 				<smil xmlns="http://www.w3.org/ns/SMIL" version="3.0">
-					<body epub:type="bodymatter">
+					<body epub:textref="../book-2.xhtml#id_5" epub:type="bodymatter">
 						<seq epub:textref="../book-2.xhtml#id_2">
 							<par epub:type="pagebreak">
 								<text src="../book-2.xhtml#page_1"/>

diff --git a/scripts/dtbook-to-epub3/src/test/xprocspec/test_dtbook-to-epub3.script.xprocspec b/scripts/dtbook-to-epub3/src/test/xprocspec/test_dtbook-to-epub3.script.xprocspec
@@ -151,13 +151,13 @@
             </x:document>
         </x:expect>
         <x:context label="the content file">
-            <x:document type="file" base-uri="temp-dir" href="issue-94/output-dir/test_dtbook-to-epub3.script.epub!/EPUB/test_dtbook-to-epub3.script-2.xhtml" select="//html:h1[1]"/>
+            <x:document type="file" base-uri="temp-dir" href="issue-94/output-dir/test_dtbook-to-epub3.script.epub!/EPUB/test_dtbook-to-epub3.script-2.xhtml" select="//(html:h1|html:h2|html:h3|html:h4|html:h5|html:h6)[1]"/>
         </x:context>
         <x:expect label="the white space in between the 'em' elements should be preserved" type="compare" normalize-space="false">
             <x:document type="inline">
-                <h1 xmlns="http://www.w3.org/1999/xhtml" id="chapter_1">
+                <h3 xmlns="http://www.w3.org/1999/xhtml" id="chapter_1">
                                         <em>CHAPTER 1</em> <em>THE LAST JUDGEMENT (MICHAEL ANGELO)</em>
-                                    </h1>
+                                    </h3>
             </x:document>
         </x:expect>
     </x:scenario>
@@ -182,17 +182,16 @@
         <x:context label="the result HTML file">
             <x:document type="file" base-uri="temp-dir" href="dtbook110/output-dir/dtbook110.epub!/EPUB/dtbook110-1.xhtml"/>
         </x:context>
-        <x:expect label="the result HTML file"
-                  type="custom" href="http://www.daisy.org/xprocspec/custom-assertion-steps.xpl" step="x:compare-except-ids">
+        <x:expect label="the result HTML file" type="compare">
             <x:document type="inline">
                 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
                     <head>
                         <meta charset="UTF-8"/>
                         <title>Title</title>
                     </head>
-                    <body id="a" epub:type="frontmatter">
-                        <section id="b">
-                            <h1 id="c" epub:type="title">Title</h1>
+                    <body id="id_3" epub:type="frontmatter">
+                        <section id="id_4">
+                            <h3 id="id_5" epub:type="title">Title</h3>
                         </section>
                     </body>
                 </html>

diff --git a/scripts/dtbook-to-epub3/src/test/xprocspec/test_dtbook-to-epub3.xprocspec b/scripts/dtbook-to-epub3/src/test/xprocspec/test_dtbook-to-epub3.xprocspec
@@ -161,9 +161,9 @@
 			<x:document type="inline">
 				<smil xmlns="http://www.w3.org/ns/SMIL" version="3.0"
 				      xmlns:epub="http://www.idpf.org/2007/ops">
-					<body epub:textref="../minimal-1.xhtml#id_2" epub:type="frontmatter">
+					<body epub:textref="../minimal-1.xhtml#id_4" epub:type="frontmatter">
 						<seq epub:textref="../minimal-1.xhtml#id_1">
-							<seq epub:textref="../minimal-1.xhtml#id_3" epub:type="title">
+							<seq epub:textref="../minimal-1.xhtml#id_5" epub:type="title">
 								<par>
 									<text src="../minimal-1.xhtml#st1-1"/>
 									<audio src="../audio/part0000_00_000.wav" clipBegin="0:00:00.000" clipEnd="0:00:00.578"/>
@@ -185,9 +185,9 @@
 			<x:document type="inline">
 				<smil xmlns="http://www.w3.org/ns/SMIL" version="3.0"
 				      xmlns:epub="http://www.idpf.org/2007/ops">
-					<body epub:textref="../minimal-2.xhtml#id_1" epub:type="bodymatter">
+					<body epub:textref="../minimal-2.xhtml#id_6" epub:type="bodymatter">
 						<seq epub:textref="../minimal-2.xhtml#id_2">
-							<seq epub:textref="../minimal-2.xhtml#id_3">
+							<seq epub:textref="../minimal-2.xhtml#id_7">
 								<par>
 									<text src="../minimal-2.xhtml#st2-1"/>
 									<audio src="../audio/part0001_00_000.wav" clipBegin="0:00:00.000" clipEnd="0:00:00.565"/>

diff --git a/scripts/dtbook-to-html/src/test/xprocspec/test_dtbook-to-html.script.xprocspec b/scripts/dtbook-to-html/src/test/xprocspec/test_dtbook-to-html.script.xprocspec
@@ -23,17 +23,17 @@
 						<meta charset="UTF-8"/>
 						<title>Minimal DTBook</title>
 					</head>
-					<body>
-						<section xmlns:epub="http://www.idpf.org/2007/ops" epub:type="frontmatter">
-							<section id="a">
-								<h1 epub:type="title">Minimal DTBook</h1>
+					<body id="id_3">
+						<section id="id_4" xmlns:epub="http://www.idpf.org/2007/ops" epub:type="frontmatter">
+							<section id="id_1">
+								<h3 id="id_5" epub:type="title">Minimal DTBook</h3>
 								<p>Bert</p>
 							</section>
 						</section>
-						<section xmlns:epub="http://www.idpf.org/2007/ops" epub:type="bodymatter">
-							<section id="b">
+						<section id="id_6" xmlns:epub="http://www.idpf.org/2007/ops" epub:type="bodymatter">
+							<section id="id_2">
 								<span epub:type="pagebreak" title="1" id="page_1"/>
-								<h1>Chapter</h1>
+								<h3 id="id_7">Chapter</h3>
 								<p>Paragraph</p>
 								<span epub:type="pagebreak" title="2" id="page_2"/>
 								<p>Another paragraph</p>

diff --git a/scripts/dtbook-to-html/src/test/xprocspec/test_dtbook-to-html.xprocspec b/scripts/dtbook-to-html/src/test/xprocspec/test_dtbook-to-html.xprocspec
@@ -34,25 +34,24 @@
 		<x:context label="the result HTML">
 			<x:document type="port" port="result.in-memory" select="/*[base-uri()=resolve-uri('result/minimal.xhtml')]"/>
 		</x:context>
-		<x:expect label="the output HTML"
-		          type="custom" href="http://www.daisy.org/xprocspec/custom-assertion-steps.xpl" step="x:compare-except-ids">
+		<x:expect label="the output HTML" type="compare">
 			<x:document type="inline">
 				<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">
 					<head>
 						<meta charset="UTF-8"/>
 						<title>Minimal DTBook</title>
 					</head>
-					<body>
-						<section xmlns:epub="http://www.idpf.org/2007/ops" epub:type="frontmatter">
-							<section id="a">
-								<h1 epub:type="title">Minimal DTBook</h1>
+					<body id="id_3">
+						<section id="id_4" xmlns:epub="http://www.idpf.org/2007/ops" epub:type="frontmatter">
+							<section id="id_1">
+								<h3 id="id_5" epub:type="title">Minimal DTBook</h3>
 								<p>Bert</p>
 							</section>
 						</section>
-						<section xmlns:epub="http://www.idpf.org/2007/ops" epub:type="bodymatter">
-							<section id="b">
+						<section id="id_6" xmlns:epub="http://www.idpf.org/2007/ops" epub:type="bodymatter">
+							<section id="id_2">
 								<span epub:type="pagebreak" title="1" id="page_1"/>
-								<h1>Chapter</h1>
+								<h3 id="id_7">Chapter</h3>
 								<p>Paragraph</p>
 								<span epub:type="pagebreak" title="2" id="page_2"/>
 								<p>Another paragraph</p>

diff --git a/scripts/zedai-to-epub3/src/test/xprocspec/test_zedai-to-epub3.script.xprocspec b/scripts/zedai-to-epub3/src/test/xprocspec/test_zedai-to-epub3.script.xprocspec
@@ -63,13 +63,13 @@
 			</x:document>
 		</x:expect>
 		<x:context label="the content file">
-			<x:document type="file" base-uri="temp-dir" href="issue-94/output-dir/test_zedai-to-epub3.script.epub!/EPUB/test_zedai-to-epub3.script.xhtml" select="//html:h1[1]"/>
+			<x:document type="file" base-uri="temp-dir" href="issue-94/output-dir/test_zedai-to-epub3.script.epub!/EPUB/test_zedai-to-epub3.script.xhtml" select="//(html:h1|html:h2|html:h3|html:h4|html:h5|html:h6)[1]"/>
 		</x:context>
 		<x:expect label="the white space in between the 'em' elements should be preserved" type="compare" normalize-space="false">
 			<x:document type="inline">
-				<h1 xmlns="http://www.w3.org/1999/xhtml" id="chapter_1">
+				<h3 xmlns="http://www.w3.org/1999/xhtml" id="chapter_1">
 										<em>CHAPTER 1</em> <em>THE LAST JUDGEMENT (MICHAEL ANGELO)</em>
-									</h1>
+									</h3>
 			</x:document>
 		</x:expect>
 	</x:scenario>

diff --git a/scripts/zedai-to-epub3/src/test/xprocspec/test_zedai-to-epub3.xprocspec b/scripts/zedai-to-epub3/src/test/xprocspec/test_zedai-to-epub3.xprocspec
@@ -94,8 +94,8 @@
 		</x:context>
 		<x:expect label="the toc in the alice-1.xhtml file" type="compare">
 			<x:document type="inline">
-				<nav xmlns="http://www.w3.org/1999/xhtml" epub:type="toc">
-					<h1>Contents</h1>
+				<nav xmlns="http://www.w3.org/1999/xhtml" id="id_17" epub:type="toc">
+					<h3 id="id_18">Contents</h3>
 					<ul>
 						<li>
 							I. Down the Rabbit-Hole <a href="alice-2.xhtml#p1">1</a>

diff --git a/scripts/zedai-to-html/pom.xml b/scripts/zedai-to-html/pom.xml
@@ -11,7 +11,7 @@
   </parent>
 
   <artifactId>zedai-to-html</artifactId>
-  <version>2.1.7-SNAPSHOT</version>
+  <version>2.2.0-SNAPSHOT</version>
   <packaging>bundle</packaging>
 
   <name>DAISY Pipeline 2 module :: ZedAI to HTML</name>

diff --git a/scripts/zedai-to-html/src/main/resources/xml/xproc/zedai-to-html.convert.xpl b/scripts/zedai-to-html/src/main/resources/xml/xproc/zedai-to-html.convert.xpl
@@ -57,6 +57,7 @@
     <p:import href="http://www.daisy.org/pipeline/modules/html-utils/library.xpl">
         <p:documentation>
             px:html-chunker
+            px:html-outline
         </p:documentation>
     </p:import>
 
@@ -116,6 +117,8 @@
                     <p:empty/>
                 </p:input>
             </p:xslt>
+            <!-- zedai-to-html.xsl only uses h1 -->
+            <px:html-outline fix-heading-ranks="outline-depth"/>
             <px:set-base-uri name="result">
                 <p:with-option name="base-uri" select="$result-basename"/>
             </px:set-base-uri>

diff --git a/scripts/zedai-to-html/src/test/xprocspec/test_zedai-to-html.script.xprocspec b/scripts/zedai-to-html/src/test/xprocspec/test_zedai-to-html.script.xprocspec
@@ -44,13 +44,14 @@
 			<x:option name="output-dir" select="resolve-uri('issue-94/output-dir/',$temp-dir)"/>
 		</x:call>
 		<x:context label="the html file">
-			<x:document type="file" base-uri="temp-dir" href="issue-94/output-dir/test_zedai-to-html.script.xhtml" select="//html:h1[1]"/>
+			<x:document type="file" base-uri="temp-dir" href="issue-94/output-dir/test_zedai-to-html.script.xhtml"
+			            select="//(html:h1|html:h2|html:h3|html:h4|html:h5|html:h6)[1]"/>
 		</x:context>
 		<x:expect label="the white space in between the 'em' elements should be preserved" type="compare" normalize-space="false">
 			<x:document type="inline">
-				<h1 xmlns="http://www.w3.org/1999/xhtml" id="chapter_1">
+				<h3 xmlns="http://www.w3.org/1999/xhtml" id="chapter_1">
 										<em>CHAPTER 1</em> <em>THE LAST JUDGEMENT (MICHAEL ANGELO)</em>
-									</h1>
+									</h3>
 			</x:document>
 		</x:expect>
 	</x:scenario>

diff --git a/scripts/zedai-to-html/src/test/xprocspec/test_zedai-to-html.xprocspec b/scripts/zedai-to-html/src/test/xprocspec/test_zedai-to-html.xprocspec
@@ -81,21 +81,49 @@
 				<x:document type="inline">
 					<d:fileset xmlns:d="http://www.daisy.org/ns/pipeline/data">
 						<d:file href="output-dir/alice-1.xhtml" original-href="../resources/resources/alice.xml">
+							<d:anchor id="id_5"/>
+							<d:anchor id="id_4"/>
+							<d:anchor id="id_7"/>
+							<d:anchor id="id_6"/>
+							<d:anchor id="id_9"/>
+							<d:anchor id="id_8"/>
+							<d:anchor id="id_13"/>
+							<d:anchor id="id_14"/>
+							<d:anchor id="id_11"/>
+							<d:anchor id="id_12"/>
+							<d:anchor id="id_10"/>
+							<d:anchor id="id_17"/>
+							<d:anchor id="id_18"/>
+							<d:anchor id="id_3"/>
+							<d:anchor id="id_15"/>
+							<d:anchor id="id_2"/>
+							<d:anchor id="id_16"/>
 							<d:anchor id="img_1"/>
 						</d:file>
 						<d:file href="output-dir/alice-2.xhtml" original-href="../resources/resources/alice.xml">
+							<d:anchor id="id_24"/>
+							<d:anchor id="id_25"/>
+							<d:anchor id="id_22"/>
+							<d:anchor id="p14"/>
+							<d:anchor id="id_23"/>
+							<d:anchor id="p13"/>
+							<d:anchor id="id_20"/>
+							<d:anchor id="id_21"/>
+							<d:anchor id="id_28"/>
+							<d:anchor id="id_29"/>
+							<d:anchor id="id_26"/>
+							<d:anchor id="id_27"/>
 							<d:anchor id="p1"/>
 							<d:anchor id="img_4"/>
 							<d:anchor id="img_2"/>
 							<d:anchor id="img_3"/>
-							<d:anchor id="p14"/>
-							<d:anchor id="p13"/>
+							<d:anchor id="id_33"/>
+							<d:anchor id="id_34"/>
+							<d:anchor id="id_31"/>
+							<d:anchor id="id_32"/>
+							<d:anchor id="id_30"/>
 						</d:file>
 						<d:file href="output-dir/alice-3.xhtml" original-href="../resources/resources/alice.xml">
-							<d:anchor id="img_6"/>
-							<d:anchor id="img_7"/>
-							<d:anchor id="img_5"/>
-							<d:anchor id="img_8"/>
 							<d:anchor id="p16"/>
 							<d:anchor id="p15"/>
 							<d:anchor id="p18"/>
@@ -109,8 +137,18 @@
 							<d:anchor id="p24"/>
 							<d:anchor id="p27"/>
 							<d:anchor id="p26"/>
+							<d:anchor id="img_6"/>
+							<d:anchor id="img_7"/>
+							<d:anchor id="img_5"/>
+							<d:anchor id="img_8"/>
+							<d:anchor id="id_35"/>
+							<d:anchor id="id_36"/>
+							<d:anchor id="id_37"/>
 						</d:file>
 						<d:file href="output-dir/alice-4.xhtml" original-href="../resources/resources/alice.xml">
+							<d:anchor id="p29"/>
+							<d:anchor id="id_19"/>
+							<d:anchor id="id_1"/>
 							<d:anchor id="img_10"/>
 							<d:anchor id="img_9"/>
 							<d:anchor id="p32"/>
@@ -121,9 +159,11 @@
 							<d:anchor id="p35"/>
 							<d:anchor id="p38"/>
 							<d:anchor id="p37"/>
+							<d:anchor id="id_40"/>
 							<d:anchor id="p39"/>
 							<d:anchor id="p40"/>
-							<d:anchor id="p29"/>
+							<d:anchor id="id_39"/>
+							<d:anchor id="id_38"/>
 						</d:file>
 					</d:fileset>
 				</x:document>