update PRONOM to v118

richardlehane · May 27, 2024 · 17f350d · 17f350d
1 parent 8af011e
commit 17f350d
Show file tree

Hide file tree

Showing 391 changed files with 9,918 additions and 1,277 deletions.
diff --git a/cmd/roy/data/DROID_SignatureFile_V116.xml → cmd/roy/data/DROID_SignatureFile_V118.xml b/cmd/roy/data/DROID_SignatureFile_V116.xml → cmd/roy/data/DROID_SignatureFile_V118.xml
diff --git a/cmd/roy/data/archivematica.sig b/cmd/roy/data/archivematica.sig
diff --git a/...roy/data/container-signature-20231127.xml → ...roy/data/container-signature-20240501.xml b/...roy/data/container-signature-20231127.xml → ...roy/data/container-signature-20240501.xml
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 
-<ContainerSignatureMapping schemaVersion="1.0" signatureVersion="36">
+<ContainerSignatureMapping schemaVersion="1.0" signatureVersion="37">
   <ContainerSignatures>
     <ContainerSignature Id="1000" ContainerType="OLE2">
       <Description>Microsoft Word 6.0/95 OLE2</Description>
@@ -5970,6 +5970,26 @@
     </ContainerSignature>
 
     <ContainerSignature Id="52100" ContainerType="OLE2">
+      <Description>GST Art 1</Description>
+      <Files>
+        <File>
+          <Path>CONTENTS</Path>
+          <BinarySignatures>
+            <InternalSignatureCollection>
+              <InternalSignature ID="52000">
+                <ByteSequence Reference="BOFoffset">
+                  <SubSequence Position="1" SubSeqMinOffset="16" SubSeqMaxOffset="0">
+                    <Sequence>47 53 54 3A 41 52 54 00</Sequence>
+                  </SubSequence>
+                </ByteSequence>
+              </InternalSignature>
+            </InternalSignatureCollection>
+          </BinarySignatures>
+        </File>
+      </Files>
+    </ContainerSignature>
+
+	<ContainerSignature Id="52150" ContainerType="OLE2">
       <Description>GST Art 2</Description>
       <Files>
         <File>
@@ -5978,7 +5998,7 @@
             <InternalSignatureCollection>
               <InternalSignature ID="52000">
                 <ByteSequence Reference="BOFoffset">
-                  <SubSequence Position="1" SubSeqMinOffset="16" SubSeqMaxOffset="16">
+                  <SubSequence Position="1" SubSeqMinOffset="16" SubSeqMaxOffset="0">
                     <Sequence>47 53 54 3A 41 52 54 00</Sequence>
                   </SubSequence>
                 </ByteSequence>
@@ -6625,28 +6645,26 @@
         </File>
       </Files>
     </ContainerSignature>
-
-    <ContainerSignature Id="80000" ContainerType="ZIP">
-      <Description>Web Archive Collection Zipped</Description>
-      <Files>
-        <File>
-          <Path>datapackage.json</Path>
-          <BinarySignatures>
-            <InternalSignatureCollection>
-              <InternalSignature ID="80000">
-                <ByteSequence Reference="BOFoffset">
-                  <SubSequence Position="1" SubSeqMinOffset="0" SubSeqMaxOffset="4096">
-                    <Sequence>'wacz_version'</Sequence>
-                  </SubSequence>
-                </ByteSequence>
-              </InternalSignature>
-            </InternalSignatureCollection>
-          </BinarySignatures>
-        </File>
-      </Files>
-    </ContainerSignature>
-
-    <ContainerSignature Id="90000" ContainerType="OLE2">
+<ContainerSignature Id="80000" ContainerType="ZIP">
+<Description>Web Archive Collection Zipped</Description>
+<Files>
+<File>
+<Path>datapackage.json</Path>
+<BinarySignatures>
+<InternalSignatureCollection>
+<InternalSignature ID="80000">
+<ByteSequence Reference="Variable">
+<SubSequence Position="1">
+<Sequence>'wacz_version'</Sequence>
+</SubSequence>
+</ByteSequence>
+</InternalSignature>
+</InternalSignatureCollection>
+</BinarySignatures>
+</File>
+</Files>
+</ContainerSignature>
+<ContainerSignature Id="90000" ContainerType="OLE2">
       <Description>Camtasia Recording File</Description>
       <Files>
         <File>
@@ -6943,7 +6961,6 @@
         </File>
       </Files>
     </ContainerSignature>
-
     <ContainerSignature Id="101100" ContainerType="ZIP">
       <Description>CorelDRAW Drawing 2022</Description>
       <Files>
@@ -6995,6 +7012,70 @@
         </File>
       </Files>
     </ContainerSignature>
+	<ContainerSignature Id="110000" ContainerType="ZIP">
+            <Description>Finale Notation file</Description>
+            <Files>
+                <File>
+                    <Path>NotationMetadata.xml</Path>
+                </File>
+					 <File>
+                    <Path>mimetype</Path>
+                    <BinarySignatures>
+                        <InternalSignatureCollection>                    
+	                        <InternalSignature ID="300">
+	                            <ByteSequence Reference="BOFoffset">
+	                                <SubSequence Position="1" SubSeqMinOffset="0" SubSeqMaxOffset="0">
+	                                    <Sequence>'application/vnd.makemusic.notation'</Sequence>
+	                                </SubSequence>
+	                            </ByteSequence>
+	                        </InternalSignature>
+	                    </InternalSignatureCollection>
+                    </BinarySignatures>
+                </File>             
+            </Files>
+        </ContainerSignature>
+
+        <ContainerSignature Id="111000" ContainerType="ZIP">
+            <Description>Compressed MusicXML file</Description>
+            <Files>
+					 <File>
+                    <Path>mimetype</Path>
+                    <BinarySignatures>
+                        <InternalSignatureCollection>                    
+	                        <InternalSignature ID="300">
+	                            <ByteSequence Reference="BOFoffset">
+	                                <SubSequence Position="1" SubSeqMinOffset="0" SubSeqMaxOffset="0">
+	                                    <Sequence>'application/vnd.recordare.musicxml'</Sequence>
+	                                </SubSequence>
+	                            </ByteSequence>
+	                        </InternalSignature>
+	                    </InternalSignatureCollection>
+                    </BinarySignatures>
+                </File>             
+            </Files>
+        </ContainerSignature>
+
+<ContainerSignature Id="112000" ContainerType="OLE2">
+            <Description>Melco Project File</Description>
+            <Files>
+				<File>
+                    <Path>EdsIV Object</Path>
+                    <BinarySignatures>
+                        <InternalSignatureCollection>                    
+	                        <InternalSignature ID="300">
+	                            <ByteSequence Reference="BOFoffset">
+	                                <SubSequence Position="1" SubSeqMinOffset="16" SubSeqMaxOffset="48">
+	                                    <Sequence>43 50 72 6A 44 65 66 61 75 6C 74 73</Sequence>
+	                                </SubSequence>
+	                            </ByteSequence>
+	                        </InternalSignature>
+	                    </InternalSignatureCollection>
+                    </BinarySignatures>
+                </File>               
+            </Files>
+        </ContainerSignature>
+
+
   </ContainerSignatures>
 
   <FileFormatMappings>
@@ -7559,6 +7640,7 @@
 
     <!-- GST Art 2 (OLE2)-->
     <FileFormatMapping signatureId="52100" Puid="fmt/1878"/>
+	<FileFormatMapping signatureId="52150" Puid="fmt/1878"/>
 
     <!-- Corel Print House 1 (OLE2)-->
     <FileFormatMapping signatureId="53000" Puid="fmt/1417"/>
@@ -7641,28 +7723,49 @@
 
     <!-- CorelDraw X4 -->
     <FileFormatMapping signatureId="101000" Puid="fmt/429"/>
+
     <!-- CorelDraw X5 -->
     <FileFormatMapping signatureId="101010" Puid="fmt/430"/>
+
     <!-- CorelDraw X6 -->
     <FileFormatMapping signatureId="101020" Puid="fmt/1925"/>
+
     <!-- CorelDraw X7 -->
     <FileFormatMapping signatureId="101030" Puid="fmt/1926"/>
+
     <!-- CorelDraw X8 -->
     <FileFormatMapping signatureId="101040" Puid="fmt/1927"/>
+
     <!-- CorelDraw 2017 -->
     <FileFormatMapping signatureId="101050" Puid="fmt/1928"/>
+
     <!-- CorelDraw 2018 -->
     <FileFormatMapping signatureId="101060" Puid="fmt/1929"/>
+
     <!-- CorelDraw 2019 -->
     <FileFormatMapping signatureId="101070" Puid="fmt/1930"/>
+
     <!-- CorelDraw 2020 -->
     <FileFormatMapping signatureId="101080" Puid="fmt/1931"/>
+
     <!-- CorelDraw 2021 -->
     <FileFormatMapping signatureId="101090" Puid="fmt/1932"/>
+
     <!-- CorelDraw 2022 -->
     <FileFormatMapping signatureId="101100" Puid="fmt/1933"/>
+
     <!-- CorelDraw 2023 -->
     <FileFormatMapping signatureId="101110" Puid="fmt/1934"/>
+
+	<!--   Melco OFM Project pre v.11 -->
+	<FileFormatMapping signatureId="112000" Puid="fmt/1959"/>
+
+	<!--   Finale Notation File -->
+	<FileFormatMapping signatureId="110000" Puid="fmt/1974"/>
+
+	<!--   Compressed Music XML -->
+	<FileFormatMapping signatureId="111000" Puid="fmt/2005"/>
+
 
   </FileFormatMappings>
 

diff --git a/cmd/roy/data/default.sig b/cmd/roy/data/default.sig
diff --git a/cmd/roy/data/deluxe.sig b/cmd/roy/data/deluxe.sig
diff --git a/cmd/roy/data/freedesktop.sig b/cmd/roy/data/freedesktop.sig
diff --git a/cmd/roy/data/loc.sig b/cmd/roy/data/loc.sig
diff --git a/cmd/roy/data/pronom/fmt101.xml b/cmd/roy/data/pronom/fmt101.xml
@@ -736,6 +736,41 @@
         <RelatedFormatVersion>
         </RelatedFormatVersion>
       </RelatedFormat>
+      <RelatedFormat>
+        <RelationshipType>Has lower priority than</RelationshipType>
+        <RelatedFormatID>2808</RelatedFormatID>
+        <RelatedFormatName>Draw.io Diagram (XML) File</RelatedFormatName>
+        <RelatedFormatVersion>
+        </RelatedFormatVersion>
+      </RelatedFormat>
+      <RelatedFormat>
+        <RelationshipType>Has lower priority than</RelationshipType>
+        <RelatedFormatID>2827</RelatedFormatID>
+        <RelatedFormatName>SolidWorks Material Database File</RelatedFormatName>
+        <RelatedFormatVersion>
+        </RelatedFormatVersion>
+      </RelatedFormat>
+      <RelatedFormat>
+        <RelationshipType>Has lower priority than</RelationshipType>
+        <RelatedFormatID>2871</RelatedFormatID>
+        <RelatedFormatName>IMF Package Asset Map</RelatedFormatName>
+        <RelatedFormatVersion>
+        </RelatedFormatVersion>
+      </RelatedFormat>
+      <RelatedFormat>
+        <RelationshipType>Has lower priority than</RelationshipType>
+        <RelatedFormatID>2872</RelatedFormatID>
+        <RelatedFormatName>IMF Package Packing List</RelatedFormatName>
+        <RelatedFormatVersion>
+        </RelatedFormatVersion>
+      </RelatedFormat>
+      <RelatedFormat>
+        <RelationshipType>Has lower priority than</RelationshipType>
+        <RelatedFormatID>2873</RelatedFormatID>
+        <RelatedFormatName>IMF Package Composition Playlist</RelatedFormatName>
+        <RelatedFormatVersion>
+        </RelatedFormatVersion>
+      </RelatedFormat>
       <RelatedFormat>
         <RelationshipType>Has priority over</RelationshipType>
         <RelatedFormatID>639</RelatedFormatID>

diff --git a/cmd/roy/data/pronom/fmt1176.xml b/cmd/roy/data/pronom/fmt1176.xml
@@ -25,9 +25,8 @@
       <ProvenanceSourceID>1</ProvenanceSourceID>
       <ProvenanceName>Digital Preservation Department / The National Archives</ProvenanceName>
       <ProvenanceSourceDate>02 Aug 2018</ProvenanceSourceDate>
-      <ProvenanceDescription>
-      </ProvenanceDescription>
-      <LastUpdatedDate>02 Aug 2018</LastUpdatedDate>
+      <ProvenanceDescription>04/2024 (v.117)- Signature named 'Nullsoft Video with optional header' updated to extend byte range between two strings. Submitted by Preservica.</ProvenanceDescription>
+      <LastUpdatedDate>18 Apr 2024</LastUpdatedDate>
       <FormatNote>
       </FormatNote>
       <FormatRisk>
@@ -46,7 +45,7 @@
       <InternalSignature>
         <SignatureID>1557</SignatureID>
         <SignatureName>Nullsoft Video with optional header</SignatureName>
-        <SignatureNote>BOF: 'NSVf'{24-2048}'NSVs' (must have minimum 24 byte header but can include variable amount of metadata, Table of Contents)</SignatureNote>
+        <SignatureNote>BOF: 'NSVf'{24-16384}'NSVs' (must have minimum 24 byte header but can include variable amount of metadata, Table of Contents)</SignatureNote>
         <ByteSequence>
           <ByteSequenceID>1825</ByteSequenceID>
           <PositionType>Absolute from BOF</PositionType>
@@ -58,7 +57,7 @@
           </IndirectOffsetLength>
           <Endianness>
           </Endianness>
-          <ByteSequenceValue>4E535666{24-2048}4E535673</ByteSequenceValue>
+          <ByteSequenceValue>4E535666{24-16384}4E535673</ByteSequenceValue>
         </ByteSequence>
       </InternalSignature>
       <InternalSignature>

diff --git a/cmd/roy/data/pronom/fmt129.xml b/cmd/roy/data/pronom/fmt129.xml
@@ -11,7 +11,7 @@
       <FormatTypes>Spreadsheet</FormatTypes>
       <FormatDisclosure>
       </FormatDisclosure>
-      <FormatDescription>All OpenOffice v1.0 documents (Calc, Draw, Impress, Writer) use the extensible Markup Language (XML) for representing the elements and attributes of each structural component of the document. As XML has no native support for binary objects, OpenOffice.org files use a standard Zip file to store the XML content together with its associated binary data. Information about the files contained in the Zip file is stored in an XML file called the manifest file. The manifest file is always stored at the pathname META-INF/manifest.xml. The manifest file contains a list of all the files in the Zip file, the media type of each file, and the information necessary to decrypt any encrypted files included in the Zip file.</FormatDescription>
+      <FormatDescription>All OpenOffice v1.0 documents (Calc, Draw, Impress, Writer) use the extenele Markup Language (XML) for representing the elements and attributes of each structural component of the document. As XML has no native support for binary objects, OpenOffice.org files use a standard Zip file to store the XML content together with its associated binary data. Information about the files contained in the Zip file is stored in an XML file called the manifest file. The manifest file is always stored at the pathname META-INF/manifest.xml. The manifest file contains a list of all the files in the Zip file, the media type of each file, and the information necessary to decrypt any encrypted files included in the Zip file.</FormatDescription>
       <BinaryFileFormat>Binary</BinaryFileFormat>
       <ByteOrders>
       </ByteOrders>

diff --git a/cmd/roy/data/pronom/fmt134.xml b/cmd/roy/data/pronom/fmt134.xml
@@ -491,6 +491,12 @@
         <RelatedFormatVersion>
         </RelatedFormatVersion>
       </RelatedFormat>
+      <RelatedFormat>
+        <RelationshipType>Has lower priority than</RelationshipType>
+        <RelatedFormatID>2731</RelatedFormatID>
+        <RelatedFormatName>GST Art File</RelatedFormatName>
+        <RelatedFormatVersion>1</RelatedFormatVersion>
+      </RelatedFormat>
       <RelatedFormat>
         <RelationshipType>Has lower priority than</RelationshipType>
         <RelatedFormatID>2762</RelatedFormatID>

diff --git a/cmd/roy/data/pronom/fmt1451.xml b/cmd/roy/data/pronom/fmt1451.xml
@@ -26,9 +26,8 @@ PDF Portfolio files can specify a "default view", which is a file in the collect
       <ProvenanceSourceID>244</ProvenanceSourceID>
       <ProvenanceName>Preservica / Preservica</ProvenanceName>
       <ProvenanceSourceDate>16 Oct 2021</ProvenanceSourceDate>
-      <ProvenanceDescription>
-      </ProvenanceDescription>
-      <LastUpdatedDate>16 Oct 2021</LastUpdatedDate>
+      <ProvenanceDescription>04/2024 (v.117)-Signature modified to no longer search for '&lt;&lt;/Cl&lt;&lt;' block. Submitted by the Archeological Data Service and Preservica.</ProvenanceDescription>
+      <LastUpdatedDate>22 Apr 2024</LastUpdatedDate>
       <FormatNote>
       </FormatNote>
       <FormatRisk>
@@ -61,7 +60,7 @@ PDF Portfolio files can specify a "default view", which is a file in the collect
       <InternalSignature>
         <SignatureID>1814</SignatureID>
         <SignatureName>PDF Portfolio 1.7</SignatureName>
-        <SignatureNote>BOF: %PDF-1.7 followed by '/Collection ' and '&lt;&lt;/CI&lt;&lt;'. EOF (offset up to 1024 bytes): '%%EOFF(.|F.|F..|F..)'</SignatureNote>
+        <SignatureNote>BOF: %PDF-1.7 followed by '/Collection '. EOF (offset up to 1024 bytes): '%%EOFF(.|F.|F..|F..)'</SignatureNote>
         <ByteSequence>
           <ByteSequenceID>2106</ByteSequenceID>
           <PositionType>Absolute from BOF</PositionType>
@@ -74,7 +73,7 @@ PDF Portfolio files can specify a "default view", which is a file in the collect
           </IndirectOffsetLength>
           <Endianness>
           </Endianness>
-          <ByteSequenceValue>255044462D312E37*2F436F6C6C656374696F6E20*3C3C2F43493C3C</ByteSequenceValue>
+          <ByteSequenceValue>255044462D312E37*2F436F6C6C656374696F6E20</ByteSequenceValue>
         </ByteSequence>
         <ByteSequence>
           <ByteSequenceID>2107</ByteSequenceID>

diff --git a/cmd/roy/data/pronom/fmt1543.xml b/cmd/roy/data/pronom/fmt1543.xml
@@ -26,8 +26,8 @@
       <ProvenanceName>
       </ProvenanceName>
       <ProvenanceSourceDate>03 Nov 2021</ProvenanceSourceDate>
-      <ProvenanceDescription>09/2023 (v.115)- MIME Type added 'application/eaf+xml' and modified file type to 'Text (Structured) submitted by the Max Plank Insitute of Phsycholinguisitcs and Monash University.</ProvenanceDescription>
-      <LastUpdatedDate>25 Aug 2023</LastUpdatedDate>
+      <ProvenanceDescription>09/2023 (v.115)- MIME Type added 'application/eaf+xml' and modified file type to 'Text (Structured) submitted by the Max Plank Insitute of Phsycholinguisitcs and Monash University. 04/2024 (v.117)- Signature updated to allow flexibility for byte length between tags. Submitted by Preservica based on samples provided by The Endanagered Languages Archive.</ProvenanceDescription>
+      <LastUpdatedDate>22 Apr 2024</LastUpdatedDate>
       <FormatNote>EAF Specification für Version 3.0 (2017): www.mpi.nl/tools/elan/EAF_Annotation_Format_3.0_and_ELAN.pdf</FormatNote>
       <FormatRisk>
       </FormatRisk>
@@ -63,19 +63,19 @@
       <InternalSignature>
         <SignatureID>1889</SignatureID>
         <SignatureName>ELAN Annotation File</SignatureName>
-        <SignatureNote>Magic bytes, BOF, min offset 27, max offset 57:  ANNOTATION_DOCUMENT AUTHOR= and EOF, offset 0: &lt;/ANNOTATION_DOCUMENT&gt;.</SignatureNote>
+        <SignatureNote>Magic bytes, BOF; Offset: 27-56; Magic Bytes: 'ANNOTATION_DOCUMENT' {0-256} 'AUTHOR='; EOF; Offset: 0; Magic Bytes: '&lt;/ANNOTATION_DOCUMENT&gt;' followed by either 0x0A, 0x0D, 0x0D0A</SignatureNote>
         <ByteSequence>
           <ByteSequenceID>2185</ByteSequenceID>
           <PositionType>Absolute from BOF</PositionType>
           <Offset>27</Offset>
-          <MaxOffset>57</MaxOffset>
+          <MaxOffset>30</MaxOffset>
           <IndirectOffsetLocation>
           </IndirectOffsetLocation>
           <IndirectOffsetLength>
           </IndirectOffsetLength>
           <Endianness>
           </Endianness>
-          <ByteSequenceValue>414E4E4F544154494F4E5F444F43554D454E5420415554484F523D</ByteSequenceValue>
+          <ByteSequenceValue>414E4E4F544154494F4E5F444F43554D454E5420{0-256}415554484F523D</ByteSequenceValue>
         </ByteSequence>
         <ByteSequence>
           <ByteSequenceID>2186</ByteSequenceID>
@@ -88,7 +88,7 @@
           </IndirectOffsetLength>
           <Endianness>
           </Endianness>
-          <ByteSequenceValue>3C2F414E4E4F544154494F4E5F444F43554D454E543E0A</ByteSequenceValue>
+          <ByteSequenceValue>3C2F414E4E4F544154494F4E5F444F43554D454E543E(0A|0D|0D0A)</ByteSequenceValue>
         </ByteSequence>
       </InternalSignature>
       <RelatedFormat>