Performance improvement of extract_info.xsl

README.md

@@ -206,8 +206,9 @@ File path | Document
 
 ## Release notes
 
-- **Jul 25, 2023**: Release v4.4.25
+- **Jul 27, 2023**: Release v4.4.25
 	- Update wwPDB Validation Information Dictionary to 4.375.
+	- Performance improvement of extract_info.xsl (XSLT 2.0 -> 1.0, though SAXON is required)
 
 - **Jul 24, 2023**: Release v4.4.24
 	- Update wwPDB Validation Information Dictionary to 4.374.

scripts/extract_info_worker.sh

@@ -91,6 +91,7 @@ do
 
    gunzip -c $pdbml_ext_file.gz > $pdbml_ext_file || exit 1
 
+   #xsltproc -o $info_alt_file --stringparam pdbml_ext_file ../$pdbml_ext_file $EXT_INFO_XSL $info_file 2> $err_file && rm -f $err_file $info_file $pdbml_ext_file || ( rm -f $info_file $info_alt_file $pdbml_ext_file ; cat $err_file ; exit 1 )
    java -jar $SAXON -s:$info_file -xsl:$EXT_INFO_XSL -o:$info_alt_file pdbml_ext_file=../$pdbml_ext_file 2> $err_file && rm -f $err_file $info_file $pdbml_ext_file || ( rm -f $info_file $info_alt_file $pdbml_ext_file ; cat $err_file ; exit 1 )
 
    xml_pretty $info_alt_file
@@ -159,6 +160,7 @@ do
 
    gunzip -c $pdbml_ext_file.gz > $pdbml_ext_file || exit 1
 
+   #xsltproc -o $info_alt_file --stringparam pdbml_ext_file ../$pdbml_ext_file $EXT_INFO_XSL $info_file 2> $err_file && rm -f $err_file $info_file $pdbml_ext_file || ( rm -f $info_file $info_alt_file $pdbml_ext_file ; cat $err_file ; exit 1 )
    java -jar $SAXON -s:$info_file -xsl:$EXT_INFO_XSL -o:$info_alt_file pdbml_ext_file=../$pdbml_ext_file 2> $err_file && rm -f $err_file $info_file $pdbml_ext_file || ( rm -f $info_file $info_alt_file $pdbml_ext_file ; cat $err_file ; exit 1 )
 
    xml_pretty $info_alt_file

stylesheet/append_xsd.xsl

@@ -42,7 +42,7 @@ VRPT PDBML Schema translated from wwPDB Validation Information Dictionary v4.375
     <xsl:if test="$name!='datablockType'">
       <xsd:complexType name="{$name}">
 	<xsl:call-template name="category_type">
-	  <xsl:with-param name="category"><xsl:value-of select="$name"/></xsl:with-param>
+	  <xsl:with-param name="category" select="$name"/>
 	</xsl:call-template>
       </xsd:complexType>
     </xsl:if>
@@ -76,16 +76,16 @@ VRPT PDBML Schema translated from wwPDB Validation Information Dictionary v4.375
 		  <xsd:all>
 		    <xsl:for-each select="xsd:complexType[1]/xsd:all[1]/xsd:element">
 		      <xsl:call-template name="data_item">
-			<xsl:with-param name="category"><xsl:value-of select="$category"/></xsl:with-param>
-			<xsl:with-param name="item"><xsl:value-of select="@name"/></xsl:with-param>
+			<xsl:with-param name="category" select="$category"/>
+			<xsl:with-param name="item" select="@name"/>
 		      </xsl:call-template>
 		    </xsl:for-each>
 		  </xsd:all>
 		</xsl:if>
 		<xsl:for-each select="xsd:complexType[1]/xsd:attribute">
 		  <xsl:call-template name="key_item">
-		    <xsl:with-param name="category"><xsl:value-of select="$category"/></xsl:with-param>
-		    <xsl:with-param name="item"><xsl:value-of select="@name"/></xsl:with-param>
+		    <xsl:with-param name="category" select="$category"/>
+		    <xsl:with-param name="item" select="@name"/>
 		  </xsl:call-template>
 		</xsl:for-each>
 	      </xsd:complexType>
@@ -123,8 +123,8 @@ VRPT PDBML Schema translated from wwPDB Validation Information Dictionary v4.375
 	</xsd:annotation>
       </xsl:for-each>
       <xsl:call-template name="fuse_copy">
-	<xsl:with-param name="category"><xsl:value-of select="replace($category,'Type$','')"/></xsl:with-param>
-	<xsl:with-param name="item"><xsl:value-of select="$item"/></xsl:with-param>
+	<xsl:with-param name="category" select="replace($category,'Type$','')"/>
+	<xsl:with-param name="item" select="$item"/>
       </xsl:call-template>
     </xsd:element>
   </xsl:template>
@@ -150,8 +150,8 @@ VRPT PDBML Schema translated from wwPDB Validation Information Dictionary v4.375
 	</xsd:annotation>
       </xsl:for-each>
       <xsl:call-template name="fuse_copy">
-	<xsl:with-param name="category"><xsl:value-of select="replace($category,'Type$','')"/></xsl:with-param>
-	<xsl:with-param name="item"><xsl:value-of select="$item"/></xsl:with-param>
+	<xsl:with-param name="category" select="replace($category,'Type$','')"/>
+	<xsl:with-param name="item" select="$item"/>
       </xsl:call-template>
     </xsd:attribute>
   </xsl:template>

stylesheet/extract_info.xsl

@@ -1 +1 @@
-extract_info_v5.xsl
+extract_info_v6.xsl

stylesheet/extract_info_v1.xsl

@@ -190,7 +190,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_missing_nmr_star_itemCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_missing_nmr_star_item">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_missing_nmr_star_itemCategory>
@@ -199,7 +199,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
       <VRPTx:pdbx_nmr_assigned_chem_shift_listCategory>
 	<xsl:for-each select="chemical_shift_list">
 	  <xsl:call-template name="pdbx_nmr_assigned_chem_shift_list">
-	     <xsl:with-param name="id"><xsl:value-of select="position()"/></xsl:with-param>
+	     <xsl:with-param name="id" select="position()"/>
 	  </xsl:call-template>
 	</xsl:for-each>
       </VRPTx:pdbx_nmr_assigned_chem_shift_listCategory>
@@ -208,7 +208,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_chem_shift_annotationCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_chem_shift_annotation">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_chem_shift_annotationCategory>
@@ -219,7 +219,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	  <VRPTx:pdbx_nmr_chem_shift_completenessCategory>
 	    <xsl:for-each select="chemical_shift_list">
 	      <xsl:call-template name="pdbx_nmr_chem_shift_completeness_well_defined">
-		<xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+		<xsl:with-param name="list_id" select="position()"/>
 	      </xsl:call-template>
 	    </xsl:for-each>
 	  </VRPTx:pdbx_nmr_chem_shift_completenessCategory>
@@ -229,7 +229,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	    <VRPTx:pdbx_nmr_chem_shift_completenessCategory>
 	      <xsl:for-each select="chemical_shift_list">
 		<xsl:call-template name="pdbx_nmr_chem_shift_completeness_full_length">
-		  <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+		  <xsl:with-param name="list_id" select="position()"/>
 		</xsl:call-template>
 	      </xsl:for-each>
 	    </VRPTx:pdbx_nmr_chem_shift_completenessCategory>
@@ -241,7 +241,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_chem_shift_re_offsetCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_chem_shift_re_offset">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_chem_shift_re_offsetCategory>
@@ -251,7 +251,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_unmapped_chem_shiftCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_unmapped_chem_shift">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_unmapped_chem_shiftCategory>
@@ -261,7 +261,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_unparsed_chem_shiftCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_unparsed_chem_shift">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_unparsed_chem_shiftCategory>
@@ -271,7 +271,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_validate_nmr_chem_shiftCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_validate_nmr_chem_shift">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_validate_nmr_chem_shiftCategory>
@@ -3325,7 +3325,7 @@ xsd:decimal
       <xsl:element name="VRPTx:auth_atom_id_1"><xsl:value-of select="@atom0"/></xsl:element>
       <xsl:element name="VRPTx:auth_atom_id_2"><xsl:value-of select="@atom1"/></xsl:element>
       <xsl:element name="VRPTx:auth_atom_id_3"><xsl:value-of select="@atom2"/></xsl:element>
-      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obs)-number(@mean),'0.00')"/></xsl:element>
+      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obs)-number(@mean),'0.000')"/></xsl:element>
       <xsl:element name="VRPTx:angle_standard_deviation"><xsl:value-of select="@stdev"/></xsl:element>
       <xsl:element name="VRPTx:angle_target_value"><xsl:value-of select="@mean"/></xsl:element>
       <xsl:element name="VRPTx:angle_value"><xsl:value-of select="@obs"/></xsl:element>
@@ -3566,7 +3566,7 @@ Unmatched components exist in atoms, <xsl:value-of select="position()"/>, found
 	  </xsl:otherwise>
 	</xsl:choose>
       </xsl:for-each>
-      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obsval)-number(@mean),'0.00')"/></xsl:element>
+      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obsval)-number(@mean),'0.000')"/></xsl:element>
       <xsl:element name="VRPTx:angle_standard_deviation"><xsl:value-of select="@stdev"/></xsl:element>
       <xsl:element name="VRPTx:angle_target_value"><xsl:value-of select="@mean"/></xsl:element>
       <xsl:element name="VRPTx:angle_value"><xsl:value-of select="@obsval"/></xsl:element>

stylesheet/extract_info_v2.xsl

@@ -186,7 +186,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_missing_nmr_star_itemCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_missing_nmr_star_item">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_missing_nmr_star_itemCategory>
@@ -195,7 +195,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
       <VRPTx:pdbx_nmr_assigned_chem_shift_listCategory>
 	<xsl:for-each select="chemical_shift_list">
 	  <xsl:call-template name="pdbx_nmr_assigned_chem_shift_list">
-	     <xsl:with-param name="id"><xsl:value-of select="position()"/></xsl:with-param>
+	     <xsl:with-param name="id" select="position()"/>
 	  </xsl:call-template>
 	</xsl:for-each>
       </VRPTx:pdbx_nmr_assigned_chem_shift_listCategory>
@@ -204,7 +204,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_chem_shift_annotationCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_chem_shift_annotation">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_chem_shift_annotationCategory>
@@ -215,7 +215,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	  <VRPTx:pdbx_nmr_chem_shift_completenessCategory>
 	    <xsl:for-each select="chemical_shift_list">
 	      <xsl:call-template name="pdbx_nmr_chem_shift_completeness_well_defined">
-		<xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+		<xsl:with-param name="list_id" select="position()"/>
 	      </xsl:call-template>
 	    </xsl:for-each>
 	  </VRPTx:pdbx_nmr_chem_shift_completenessCategory>
@@ -225,7 +225,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	    <VRPTx:pdbx_nmr_chem_shift_completenessCategory>
 	      <xsl:for-each select="chemical_shift_list">
 		<xsl:call-template name="pdbx_nmr_chem_shift_completeness_full_length">
-		  <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+		  <xsl:with-param name="list_id" select="position()"/>
 		</xsl:call-template>
 	      </xsl:for-each>
 	    </VRPTx:pdbx_nmr_chem_shift_completenessCategory>
@@ -237,7 +237,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_chem_shift_re_offsetCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_chem_shift_re_offset">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_chem_shift_re_offsetCategory>
@@ -247,7 +247,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_unmapped_chem_shiftCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_unmapped_chem_shift">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_unmapped_chem_shiftCategory>
@@ -257,7 +257,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_nmr_unparsed_chem_shiftCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_nmr_unparsed_chem_shift">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_nmr_unparsed_chem_shiftCategory>
@@ -267,7 +267,7 @@ Unmatched entry ID in both documents (<xsl:value-of select="$entry_id"/> and <xs
 	<VRPTx:pdbx_validate_nmr_chem_shiftCategory>
 	  <xsl:for-each select="chemical_shift_list">
 	    <xsl:call-template name="pdbx_validate_nmr_chem_shift">
-	      <xsl:with-param name="list_id"><xsl:value-of select="position()"/></xsl:with-param>
+	      <xsl:with-param name="list_id" select="position()"/>
 	    </xsl:call-template>
 	  </xsl:for-each>
 	</VRPTx:pdbx_validate_nmr_chem_shiftCategory>
@@ -3309,7 +3309,7 @@ xsd:decimal
       <xsl:element name="VRPTx:auth_atom_id_1"><xsl:value-of select="@atom0"/></xsl:element>
       <xsl:element name="VRPTx:auth_atom_id_2"><xsl:value-of select="@atom1"/></xsl:element>
       <xsl:element name="VRPTx:auth_atom_id_3"><xsl:value-of select="@atom2"/></xsl:element>
-      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obs)-number(@mean),'0.00')"/></xsl:element>
+      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obs)-number(@mean),'0.000')"/></xsl:element>
       <xsl:element name="VRPTx:angle_standard_deviation"><xsl:value-of select="@stdev"/></xsl:element>
       <xsl:element name="VRPTx:angle_target_value"><xsl:value-of select="@mean"/></xsl:element>
       <xsl:element name="VRPTx:angle_value"><xsl:value-of select="@obs"/></xsl:element>
@@ -3544,7 +3544,7 @@ Unmatched components exist in atoms, <xsl:value-of select="position()"/>, found
 	  </xsl:otherwise>
 	</xsl:choose>
       </xsl:for-each>
-      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obsval)-number(@mean),'0.00')"/></xsl:element>
+      <xsl:element name="VRPTx:angle_deviation"><xsl:value-of select="format-number(number(@obsval)-number(@mean),'0.000')"/></xsl:element>
       <xsl:element name="VRPTx:angle_standard_deviation"><xsl:value-of select="@stdev"/></xsl:element>
       <xsl:element name="VRPTx:angle_target_value"><xsl:value-of select="@mean"/></xsl:element>
       <xsl:element name="VRPTx:angle_value"><xsl:value-of select="@obsval"/></xsl:element>