[MOBY-guts] biomoby commit

[Paul Gordon]

gordonp
Mon Jul 23 18:01:22 EDT 2007
Update of /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/services/resources
In directory dev.open-bio.org:/tmp/cvs-serv17921/src/main/ca/ucalgary/services/resources

Modified Files:
	acdRules.xml 
Log Message:
Update to include nested parsing rule example
moby-live/Java/src/main/ca/ucalgary/services/resources acdRules.xml,1.2,1.3
===================================================================
RCS file: /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/services/resources/acdRules.xml,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/services/resources/acdRules.xml	2007/06/08 14:04:27	1.2
+++ /home/repository/moby/moby-live/Java/src/main/ca/ucalgary/services/resources/acdRules.xml	2007/07/23 22:01:22	1.3
@@ -78,45 +78,45 @@
   <member value="Length" whitespace="strip">string-length('$2')</member>
 </object>
 
-<!--
+
 <object name="rowWithWhitespaceSeparatedColumns">
-  <!- - Any number of non-whitespace data column values, separated by spaces (at least 2, or a tab so
-       as not to capture just any random space-separated words on a line). - ->
-  <regex>\A\s*(\S+(\x20{2,}|\t+|))+\n</regex>
+  <!-- Any number of non-whitespace data column values, separated by spaces (at least 2, or a tab so
+       as not to capture just any random space-separated words on a line). -->
+  <regex anchor="line">(?:\A|\n)\s*(\S+(\x20{2,}|\t+|))+(?=\n|\z)</regex>
   <datatype value="tableRow"/>
-  <!- - First capture group recorded as many times as it matches (HAS relationship for "cell" field) - ->
-  <member value="cell" whitespace="flanking">$1</member> 
-</object> -->
+  <!-- First regex capture group recorded as many times as it matches (HAS relationship for "cell" field) -->
+  <member value="cell" datatype="String" whitespace="flanking">$1</member> 
+</object>
+
 
-<!--
 <object name="tableWithWhitespaceSeparatedColumns">
-  <!- - A table is one or more rows of data. - ->
-  <regex anchor="line">(\p{rowWithWhitepaceSeparatedColumns})+</regex>
+  <!-- A table is one or more rows of data. -->
+  <regex>(\p{rowWithWhitespaceSeparatedColumns})+</regex>
   <datatype value="table"/>
-  <!- - First capture group recorded as many times as it matches (HAS relationship for "tableRow" field)
-       \p{rowWithSpaceSeparatedColumns} in the regex is known to generate objects of data type "tableRow". - ->
-  <member value="body">$1</member>
-</object> -->
+  <!-- First capture group recorded as many times as it matches (HAS relationship for "tableRow" field)
+       \p{rowWithSpaceSeparatedColumns} in the regex is known to generate objects of data type "tableRow". -->
+  <member value="row">$1</member>
+</object>
 
-<!-- Output from EMBOSS 'charge' program. 
+<!-- Output from EMBOSS 'charge' program. -->
 <object>
   <regex anchor="line">
-         (CHARGE \s of \s .*?)\n        # Description of input (used as caption)
+         (CHARGE \s of \s .*?)\n        # Description of input used as caption
          \n                             # Blank line
          (Position \s+ Charge\n)        # Column headers
-         ((?: \d+ \s+ -?\d+\.\d+ \n)+ ) # One or more lines of (integer) (spaces) (+/-decimal number)
-                                        # Ignore any trailing garbage (no \z given to anchor the end of the input being tested)
+         ((?: \d+ \s+ -?\d+\.\d+ \n)+ ) # One or more lines of integer spaces +/-decimal-number
+                                        # Ignore any trailing data, no \z given to anchor end of input being tested
   </regex>
-  <datatype value="PeptideChargeTable"/>
+  <datatype value="ProteinChargeTable"/>
   <member value="caption">$1</member>
-  <!- - Create a member of data type tableRow using another rule. - ->
+  <!-- Create a member of data type tableRow using another rule. -->
   <member value="header" rule="rowWithWhitespaceSeparatedColumns">$2</member>
-  <!- - Inherit parsing from other rule to fill in some members (IS-A field completion from rule for parent data type).
+  <!-- Inherit parsing from other rule to fill in some members (IS-A field completion from rule for parent data type).
        We are stating this explicitly because we wanted to ensure the (int) (sp) (-/+dec) format in the
        regex above instead of accepting any data matching the looser regex for rowWithSpaceSeparatedColumns
-       (any number of non-whitespace columns separated by spaces). - ->
+       (any number of non-whitespace columns separated by spaces). -->
   <inheritMembers rule="tableWithWhitespaceSeparatedColumns">$3</inheritMembers> 
-</object> -->
+</object>
 
 <!-- PNG image's magic signature at start of file -->
 <object>
@@ -133,4 +133,4 @@
   <member value="content" encoding="Base64">$0</member>
 </object>
 
-</mappings>
\ No newline at end of file
+</mappings>