[MOBY-guts] biomoby commit

Paul Gordon gordonp at dev.open-bio.org
Thu Apr 26 15:30:01 UTC 2007


gordonp
Thu Apr 26 11:30:01 EDT 2007
Update of /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/seahawk/resources
In directory dev.open-bio.org:/tmp/cvs-serv976/src/main/ca/ucalgary/seahawk/resources

Modified Files:
	mobyBuilderRules.xml 
Log Message:
Added binary object rules for images and ABI trace files, plus DNASequence
moby-live/Java/src/main/ca/ucalgary/seahawk/resources mobyBuilderRules.xml,1.3,1.4
===================================================================
RCS file: /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/seahawk/resources/mobyBuilderRules.xml,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/seahawk/resources/mobyBuilderRules.xml	2007/04/03 02:37:43	1.3
+++ /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/seahawk/resources/mobyBuilderRules.xml	2007/04/26 15:30:01	1.4
@@ -4,6 +4,77 @@
 <prefix value="tigr">http://www.bioxml.info/dtd/tigrxml.dtd</prefix>
 <prefix value="bioseq">http://www.bioxml.info/dtd/Bioseq.dtd</prefix>
 
+<!-- Creates a DNASequence, \N is IUPAC nucleotide shorthand -->
+<object>
+  <regex>(\N+(?:\x20|\r|\t|\n)?)+</regex>
+  <datatype value="DNASequence"/>
+  <namespace>
+    <ns value="unknown">unknown</ns>
+  </namespace>
+  <member value="SequenceString" whitespace="strip">$2</member>
+  <member value="Length" whitespace="strip">string-length('$2')</member>
+</object>
+
+<!-- ABI sequence trace's magic signature at start of file -->
+<object>
+  <regex>\AABIF.*\z</regex>
+  <namespace>
+    <ns value="unknown">unknown</ns>
+  </namespace>
+  <datatype value="ABISequenceChromatogram"/>
+  <member value="content" encoding="Base64">$0</member>
+</object>
+
+<!-- PNG image's magic signature at start of file -->
+<object>
+<!--  <regex>\A\x89PNG\r\n\x1A\n.*\z</regex>-->
+  <regex>\A.PNG\r\n\x1A\n.*\z</regex>
+  <datatype value="PNGFormatImage"/>
+  <member value="content" encoding="Base64">$0</member>
+</object>
+
+<!-- GIF image's magic signature at start of file -->
+<object>
+  <regex>\AGIF8.*\z</regex>
+  <datatype value="GIFFormatImage"/>
+  <member value="content" encoding="Base64">$0</member>
+</object>
+
+<!-- JPG image's magic signature at start of file -->
+<object>
+ <!-- <regex>\A\xf1\x00\x40\xbb.*\z</regex> -->
+  <regex>\A......(?:JFIF|Exif).*\z</regex>
+  <datatype value="JPEGFormatImage"/>
+  <member value="content" encoding="Base64">$0</member>
+</object>
+
+<!-- A Link object, representing a URL -->
+<object>
+  <regex>((?:http|ftp|file)://
+         ([^/\x20\r\t\n]+)?     # host name (non-whitespace, non-slash), maybe
+         \S*?)                  # rest of the URL until
+         ([,\.\)\(]\s|\z)       # trailing punctuation and whitespace, or just EOD
+         </regex>
+  <namespace>
+    <ns value="URL">$1</ns>
+  </namespace>
+  <datatype value="Link"/>
+  <member value="url">$1</member>
+</object>
+
+<!-- An EmailAddress object -->
+<object>
+  <regex>(\S+@                 # user name (non-whitespace)
+         [^/\x20\r\t\n]+       # host name (non-whitespace, non-slash chars)
+         \.                    # literal dot
+         [A-Za-z]{2,4})        # top level domain (2 to 4 letters)
+         (?:\W|\z)             # must be followed by non-word char, or EOD                  
+         </regex>
+  <datatype value="EmailAddress"/>
+  <articlename>$1</articlename>
+  <member value="address">$1</member>
+</object>
+
 <!-- A base object in the NCBI Genbank's GI namespace -->
 <object>
   <regex>(?:GI|gi)[|:](\d+)</regex>
@@ -23,7 +94,7 @@
 
 <!-- Digital Object Identifier, with header -->
 <object>
-  <regex>(?:DOI|doi):?\s*(10\.\d+/[^%"\# \t\r\n]+)</regex>
+  <regex>(?:DOI|doi):?\s*(10\.\d+/[^%"\#\x20\t\r\n]+)</regex>
   <namespace>
     <ns value="DOI">$1</ns>
   </namespace>
@@ -31,7 +102,7 @@
 
 <!-- Digital Object Identifier, likely guess since you don't divide numbers by letters -->
 <object>
-  <regex>(?:\s|\A|/)(10\.\d+/[A-Za-z]+[^%"\# \t\r\n]+)</regex>
+  <regex>(?:\s|\A|/)(10\.\d+/[A-Za-z]+[^%"\#\x20\t\r\n]+)</regex>
   <namespace>
     <ns value="DOI">$1</ns>
   </namespace>
@@ -122,4 +193,4 @@
   <datatype value="FASTA_AA"/>
   <member value="content">$1</member>
 </object>
-</mappings>
\ No newline at end of file
+</mappings>




More information about the MOBY-guts mailing list