Merge pull request #360 from clarin-eric/formats

a quick update of the master

SIS/clarin/data/domains.xml

@@ -1,31 +1,31 @@
 <domains xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:noNamespaceSchemaLocation="../schemas/domains.xsd">
 <!-- sync the state of this taxonomy with the schema for recommendations, i.e. recommendation.xsd   -->
-    <domain id="1" orderBy="Source Data">
+    <domain id="1" orderBy="Source Language Data">
         <name>Audiovisual Source Language Data</name>
         <desc>Audio or video recordings providing spoken/multimodal or signed language data for
             research purposes.</desc>
     </domain>
-    <domain id="2" orderBy="Source Data">
+    <domain id="2" orderBy="Source Language Data">
         <name>Image Source Language Data</name>
         <desc>Digitized images of analogue sources of written language data for research purposes
             (e.g. facsimiles, scans of handwriting, photos of inscriptions).</desc>
     </domain>
-    <domain id="3" orderBy="Source Data">
+    <domain id="3" orderBy="Source Language Data">
         <name>Textual Source Language Data</name>
-        <desc>Written unstructured/plain text or originally structured text (e.g. HTML) without linguistic or other mark-up added for research purposes.</desc>
+        <desc>Written unstructured/plain text or originally structured text (e.g. HTML), without linguistic or other mark-up added for research purposes.</desc>
     </domain>
-    <domain id="4" orderBy="Source Data">
+    <domain id="4">
         <name>Contextual Data</name>
-        <desc>Images (photos or drawings) or documents relevant to the communicative event or text but not part of the source language data.</desc>
+        <desc>Images (photos or drawings) or documents relevant to the communicative event or text, but not part of the source language data.</desc>
     </domain>
     <domain id="5" orderBy="Annotation">
         <name>Text Annotation</name>
         <desc>Annotations of textual sources/written text, with the original text included or as stand-off.</desc>
     </domain>
     <domain id="6" orderBy="Annotation">
         <name>Audiovisual Annotation</name>
-        <desc>Annotations of audiovisual sources, usually including a basic rendering of the spoken content (transcription) and sometimes further annotation.</desc>
+        <desc>Annotations of audiovisual sources, usually including a basic rendering of the spoken content (transcription) and, sometimes, further annotation.</desc>
     </domain>
     <domain id="7" orderBy="Annotation">
         <name>Image Annotation</name>
@@ -47,31 +47,31 @@
         <name>Documentation</name>
         <desc>Unstructured documentation of the resource and its parts such as corpus or annotation guidelines.</desc>
     </domain>
-    <domain id="12" orderBy="Databases">
+    <domain id="12">
         <name>Lexical Resource</name>
-        <desc>Structured (item-based) resources for lexical and/or conceptual information on units of language (e.g. wordlists, lexicons, WordNets etc.)</desc>
+        <desc>Structured (item-based) resources for lexical and/or conceptual information on units of language (e.g., wordlists, lexicons, WordNets, etc.)</desc>
     </domain>
-    <domain id="13" orderBy="Uncategorized">
+    <domain id="13">
         <name>Tool Support</name>
-        <desc>Tool-related formats required for specific functionality of the tool or reliable reuse of resources (e.g. tagsets, annotation schemes, vocabularies, language models, parameter files, and other specifications or settings)</desc>
+        <desc>Tool-related formats required for specific functionality of the tool or reliable reuse of resources (e.g., tagsets, annotation schemes, vocabularies, language models, parameter files, and other specifications or settings).</desc>
     </domain>
-    <domain id="14" orderBy="Databases">
+    <domain id="14">
         <name>Geodata</name>
         <desc>Information on geographic locations.</desc>
     </domain>
-    <domain id="15" orderBy="Databases">
+    <domain id="15">
         <name>Statistical Data</name>
         <desc>Data from surveys and tests in numeric formats.</desc>
     </domain>
-    <domain id="16" orderBy="Databases">
+    <domain id="16">
         <name>Language Description</name>
-        <desc>Structured or unstructured descriptions of linguistic varieties or phenomena, typological databases etc.</desc>
+        <desc>Structured or unstructured descriptions of linguistic varieties or phenomena, typological databases, etc.</desc>
     </domain>
-    <domain id="17" orderBy="Uncategorized">
+    <domain id="17">
         <name>Packaging</name>
         <desc>Packaging formats of various nature (archiving, compression, library) if no more specific domain is suitable.</desc>
     </domain>
-    <domain id="18" orderBy="Uncategorized">
+    <domain id="18">
         <name>Other</name>
         <desc>Any other function that cannot be included in an existing domain. The content of this domain will be periodically examined for potential patterns that may give rise to new domains.</desc>
     </domain>

SIS/clarin/model/domain.xqm

@@ -1,4 +1,4 @@
-xquery version "3.0";
+xquery version "3.1";
 
 module namespace domain="http://clarin.ids-mannheim.de/standards/domain";
 
@@ -31,7 +31,22 @@ declare function domain:get-metadomain($nameOrId as xs:string){
 };
 
 (: return a sequence of full domain nodes by passing the name of a metadomain, e.g. 'Annotation' :)
-declare function domain:get-domains-by-metadomain($name as xs:string){
+declare function domain:get-domains-by-metadomain($name as xs:string) as element(domain)+ {
+  if ($name eq 'Uncategorized') 
+  then
+    $domain:domains[count(@orderBy) eq 0] (:add also @orderBy eq '' ? Let it bug out, rather... :)
+  else
     $domain:domains[@orderBy eq $name]
 };
 
+(: return a sequence of metadomain names together with "Uncategorized" :)
+declare function domain:get-all-metadomains() as xs:string+ {
+   (:distinct-values($domain:domains/@orderBy):)
+   (:distinct-values($domain:domains/@orderBy)[string-length() gt 0], "Uncategorized":)
+   distinct-values($domain:domains/@orderBy), "Uncategorized"
+};
+
+
+
+
+

SIS/clarin/modules/domain.xql

@@ -23,12 +23,17 @@ declare function dm:get-id-by-name($name as xs:string){
 };
 
 (: get the name of the metadomain by passing a domain name or a domain ID :)
-declare function dm:get-metadomain($nameOrId as xs:string){
-       domain:get-metadomain($nameOrId) 
+declare function dm:get-metadomain($nameOrId as xs:string) as xs:string {
+   let $domain-name := domain:get-metadomain($nameOrId)
+   let $metadomain := if ($domain-name eq '')
+   then "Uncategorized"
+   else $domain-name
+
+    return $metadomain
 };
 
 (: return a sequence of full domain nodes by passing the name of a metadomain, e.g. 'Annotation' :)
-declare function dm:get-domains-by-metadomain($name as xs:string){
+declare function dm:get-domains-by-metadomain($name as xs:string) as element(domain)+ {
     domain:get-domains-by-metadomain($name)
 };
 
@@ -38,8 +43,8 @@ declare function dm:get-domain-names-by-metadomain($name as xs:string){
 
 
 (: Generate the list of domains for the particular group :)
-declare function dm:list-domains($group as xs:string) {
-    for $domain in $domain:domains[@orderBy eq $group]
+declare function dm:list-domains($group as xs:string) as element(li)+ {
+    for $domain in domain:get-domains-by-metadomain($group)
        let $domain-id := $domain/@id
        let $domain-name := $domain/name/text()
        let $domain-snippet := $domain/desc
@@ -60,7 +65,7 @@ declare function dm:list-domains($group as xs:string) {
 
 (: iterate across the groups of domains :)
 declare function dm:list-domains-grouped() {
-    for $group in distinct-values($domain:domains/@orderBy)
+    for $group in domain:get-all-metadomains()
         order by $group
     return
         <li>
@@ -72,10 +77,10 @@ declare function dm:list-domains-grouped() {
 };
 
 
-declare function dm:create-domain-group-recommendation-link($group as xs:string){
+declare function dm:create-domain-group-recommendation-link($group as xs:string) as xs:string {
 
     let $domain-ids := 
-        for $id in $domain:domains[@orderBy eq $group]/@id
+        for $id in domain:get-domains-by-metadomain($group)/@id
         return concat("domain=",$id)
     let $joined-domains := fn:string-join($domain-ids,"&amp;")
 

SIS/clarin/schemas/domains.xsd

@@ -18,7 +18,7 @@
           <xs:documentation>This is an internal handle, used at some places for easier processing.</xs:documentation>
         </xs:annotation>
       </xs:attribute>
-      <xs:attribute name="orderBy" use="required">
+      <xs:attribute name="orderBy" use="optional">
         <xs:annotation><xs:documentation>This attribute identifies the metadomain, such as "Annotation" for various specific kinds of annotation.</xs:documentation></xs:annotation>
       </xs:attribute>
     </xs:complexType>