From 392c2f68fbf09d1e5a174a758d337c2fe498ba53 Mon Sep 17 00:00:00 2001
From: MURATA Makoto <eb2m-mrt@asahi-net.or.jp>
Date: Mon, 10 Jul 2017 18:33:45 +0900
Subject: [PATCH] Allow xml:lang="" by replacing datatype.languagecode by
 datatype.languagecode | string "". (#778)

* Allow xml:lang="" by replacing datatype.languagecode by datatype.languagecode | string "".

* Add test for schema changes for empty lang attribute

fixes #777
---
 .../com/adobe/epubcheck/schema/30/mod/datatypes.rnc   |  2 +-
 .../epubcheck/schema/30/mod/html5/html5-attrib-30.rnc |  6 +++---
 .../epubcheck/schema/30/mod/html5/html5-embed-30.rnc  |  2 +-
 .../java/com/adobe/epubcheck/ops/OPSCheckerTest.java  |  7 +++++++
 .../30/single/xhtml/valid/issue777-empty-lang.xhtml   | 11 +++++++++++
 5 files changed, 23 insertions(+), 5 deletions(-)
 create mode 100644 src/test/resources/30/single/xhtml/valid/issue777-empty-lang.xhtml

diff --git a/src/main/resources/com/adobe/epubcheck/schema/30/mod/datatypes.rnc b/src/main/resources/com/adobe/epubcheck/schema/30/mod/datatypes.rnc
index f90a81cc4..eacaa4c09 100644
--- a/src/main/resources/com/adobe/epubcheck/schema/30/mod/datatypes.rnc
+++ b/src/main/resources/com/adobe/epubcheck/schema/30/mod/datatypes.rnc
@@ -6,7 +6,7 @@ div {
     
   datatype.languagecode = datatype.BCP47
   # http://www.w3.org/TR/xmlschema11-2/#language
-  datatype.BCP47 = xsd:language { pattern = "[a-zA-Z]{1,8}(-[a-zA-Z0-9]{1,8})*" }
+  datatype.BCP47 = xsd:language
   # http://www.w3.org/TR/xmlschema11-2/#ID  
   datatype.ID.xsd = xsd:ID
   # http://www.w3.org/TR/xmlschema11-2/#NCName
diff --git a/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-attrib-30.rnc b/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-attrib-30.rnc
index e18a99a2a..b6c566334 100644
--- a/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-attrib-30.rnc
+++ b/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-attrib-30.rnc
@@ -9,8 +9,8 @@
    
    
    
-   html5.lang.attr = attribute lang { datatype.languagecode }
-   html5.xml.lang.attr = attribute xml:lang { datatype.languagecode }       
+   html5.lang.attr = attribute lang { datatype.languagecode | string "" }
+   html5.xml.lang.attr = attribute xml:lang { datatype.languagecode | string "" }       
    html5.dir.attr = attribute dir { 'ltr' | 'rtl' | 'auto' }  
    html5.id.attr = attribute id { datatype.html5.token }   
    html5.title.attr = attribute title { string }   
@@ -19,7 +19,7 @@
    html5.xml.space.attr = attribute xml:space { 'preserve' | 'default' }
    
    html5.href.attr = attribute href { datatype.html5.URL.spaces }
-   html5.hreflang.attr = attribute hreflang { datatype.languagecode }      
+   html5.hreflang.attr = attribute hreflang { datatype.languagecode | string ""}      
    html5.target.attr = attribute target { datatype.html5.browsing.context.name.or.keyword } 
    html5.rel.attr = attribute rel { datatype.html5.space.separated.tokens }  
    html5.media.attr = attribute media { datatype.html5.media.query }   
diff --git a/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-embed-30.rnc b/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-embed-30.rnc
index 53d793c69..9bbe68a78 100644
--- a/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-embed-30.rnc
+++ b/src/main/resources/com/adobe/epubcheck/schema/30/mod/html5/html5-embed-30.rnc
@@ -37,7 +37,7 @@
       & html5.track.srclang.attr? & html5.track.label.attr?
 
    html5.track.kind.attr = attribute kind { 'subtitles' | 'captions' | 'descriptions' | 'chapters' | 'metadata' }   
-   html5.track.srclang.attr = attribute srclang { datatype.languagecode }
+   html5.track.srclang.attr = attribute srclang { datatype.languagecode | string "" }
    html5.track.label.attr = attribute label { datatype.string  }
    html5.track.default.attr = attribute default { 'default' | '' }
 
diff --git a/src/test/java/com/adobe/epubcheck/ops/OPSCheckerTest.java b/src/test/java/com/adobe/epubcheck/ops/OPSCheckerTest.java
index b9addd56e..42d58830a 100644
--- a/src/test/java/com/adobe/epubcheck/ops/OPSCheckerTest.java
+++ b/src/test/java/com/adobe/epubcheck/ops/OPSCheckerTest.java
@@ -928,4 +928,11 @@ public void testValidateXHTMLEmptyClass_EPUB2_Valid()
         EPUBVersion.VERSION_2);
   }
 
+  @Test
+  public void testValidateEmptyLangAttribute_EPUB3_Valid()
+  {
+    testValidateDocument("xhtml/valid/issue777-empty-lang.xhtml", "application/xhtml+xml",
+        EPUBVersion.VERSION_3);
+  }
+
 }
diff --git a/src/test/resources/30/single/xhtml/valid/issue777-empty-lang.xhtml b/src/test/resources/30/single/xhtml/valid/issue777-empty-lang.xhtml
new file mode 100644
index 000000000..6228b9a7e
--- /dev/null
+++ b/src/test/resources/30/single/xhtml/valid/issue777-empty-lang.xhtml
@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+	<head>
+		<title>Allow empty lang attribute</title>
+	</head>
+	<body>
+		<p lang="" xml:lang="">This para has an empty lang attribute which was invalid prior to v4.1</p>
+		<p>Details: https://github.com/IDPF/epubcheck/issues/777</p>
+	</body>
+</html>
\ No newline at end of file