metanorma-standoc 3.0.7 → 3.0.8

data/lib/metanorma/standoc/validate.rb

@@ -12,7 +12,7 @@ module Metanorma
     module Validate
       def content_validate(doc)
         @doctype = doc.at("//bibdata/ext/doctype")&.text
-        repeat_id_validate(doc.root) # feeds xref_validate
+        repeat_id_validate(doc.root) # feeds xref_validate, termsect_validate
         xref_validate(doc) # feeds nested_asset_validate
         nested_asset_validate(doc)
         section_validate(doc)
@@ -92,7 +92,7 @@ module Metanorma
       end
 
       def nested_asset_xref_report(outer, inner, _doc)
-        i = @doc_xrefs[inner["id"]] or return
+        i = @doc_xrefs[inner["anchor"]] or return
         err2 = "There is a crossreference to an instance of #{inner.name} " \
                "nested within #{outer.name}: #{i.to_xml}"
         @log.add("Style", i, err2)
@@ -158,37 +158,63 @@ module Metanorma
         schema_validate(formattedstr_strip(doc.dup), schema_location)
       end
 
+      # Check should never happen with content ids, but will check it anyway
+      # since consequences are so catastrophic
       def repeat_id_validate1(elem)
         if @doc_ids[elem["id"]]
           @log.add("Anchors", elem,
-                   "Anchor #{elem['id']} has already been " \
-                   "used at line #{@doc_ids[elem['id']]}", severity: 0)
+                   "ID #{elem['id']} has already been " \
+                   "used at line #{@doc_ids[elem['id']][:line]}", severity: 0)
         else
-          @doc_ids[elem["id"]] = elem.line
+          @doc_ids[elem["id"]] =
+            { line: elem.line, anchor: elem["anchor"] }.compact
         end
       end
 
+      def repeat_anchor_validate1(elem)
+        if @doc_anchors[elem["anchor"]]
+          @log.add("Anchors", elem,
+                   "Anchor #{elem['anchor']} has already been used at line " \
+                   "#{@doc_anchors[elem['anchor']][:line]}", severity: 0)
+        else
+          @doc_anchors[elem["anchor"]] = { line: elem.line, id: elem["id"] }
+          @doc_anchor_seq << elem["anchor"]
+        end
+      end
+
+      # Check should never happen with content ids, but will check it anyway
       def repeat_id_validate(doc)
-        @doc_ids = {} # hash of all ids in document to line number
-        @doc_id_seq = [] # ordered list of all ids in document
+        repeat_id_validate_prep
         doc.xpath("//*[@id]").each do |x|
           @doc_id_seq << x["id"]
           repeat_id_validate1(x)
+          x["anchor"] and repeat_anchor_validate1(x)
         end
-        @doc_id_seq.sort!
+        @doc_id_seq_hash = @doc_id_seq.each_with_index
+          .with_object({}) do |(x, i), m|
+          m[x] = i
+        end
+        @doc_anchor_seq_hash = @doc_anchor_seq.each_with_index
+          .with_object({}) do |(x, i), m|
+          m[x] = i
+        end
+      end
+
+      def repeat_id_validate_prep
+        @doc_ids = {} # hash of all ids in document to line number, anchor
+        @doc_anchors = {} # hash of all anchors in document to line number, id
+        @doc_id_seq = [] # ordered list of all ids in document
+        @doc_anchor_seq = [] # ordered list of all anchors in document
       end
 
-      # Retrieve IDs between two nominated values
+      # Retrieve anchors between two nominated values
       # (exclusive of start_id AND exclusive of end_id)
-      def get_ids_between(start_id, end_id)
-        start_index = @doc_id_seq.bsearch_index { |id| id > start_id }
-        end_index = @doc_id_seq.bsearch_index { |id| id >= end_id }
-        # start_id is greater than or equal to all elements
-        start_index.nil? and return []
-        # end_id is greater than all elements
-        end_index.nil? and end_index = @doc_id_seq.length
+      def get_anchors_between(start_id, end_id)
+        start_index = @doc_anchor_seq_hash[start_id]
+        end_index = @doc_anchor_seq_hash[end_id]
+        start_index.nil? || end_index.nil? and return []
         start_index >= end_index and return []
-        @doc_id_seq[start_index...end_index]
+        @doc_anchor_seq[start_index...end_index]
       end
 
       # manually check for xref/@target et sim. integrity
@@ -198,14 +224,15 @@ module Metanorma
       end
 
       def xref_validate_exists(doc)
-        @doc_xrefs =
-          doc.xpath("//xref/@target | //xref//location/@target | //index/@to")
-            .each_with_object({}) do |x, m|
-            m[x.text] = x.parent
-            @doc_ids[x.text] and next
+        @doc_xrefs = {}
+        Metanorma::Utils::anchor_attributes.each do |a|
+          doc.xpath("//#{a[0]}/@#{a[1]}").each do |x|
+            @doc_xrefs[x.text] = x.parent
+            @doc_anchors[x.text] and next
             @log.add("Anchors", x.parent,
                      "Crossreference target #{x} is undefined", severity: 1)
           end
+        end
       end
 
       # If there is an xref range, record the IDs between the two targets
@@ -220,7 +247,7 @@ module Metanorma
         from = to_location.previous_element
         from && from.name == "location" or return
         from["target"] && to_location["target"] or return
-        get_ids_between(from["target"], to_location["target"])
+        get_anchors_between(from["target"], to_location["target"])
           .each { |id| @doc_xrefs[id] = from }
       end
     end

data/lib/metanorma/standoc/validate_schema.rb

@@ -99,6 +99,8 @@ module Metanorma
         doc.xpath("//m:svg", "m" => SVG_NS).each { |n| n.replace("<svg/>") }
         doc
       end
+
+      include ::Metanorma::Standoc::Utils
     end
   end
 end

data/lib/metanorma/standoc/validate_term.rb

@@ -16,7 +16,7 @@ module Metanorma
       def iev_validate(xmldoc)
         @iev = init_iev or return
         xmldoc.xpath("//term").each do |t|
-          t.xpath(".//termsource").each do |src|
+          t.xpath("./source | ./preferred/source | ./admitted/source | ./deprecates/source | ./related/source").each do |src|
             (/^IEC[  ]60050-/.match(src.at("./origin/@citeas")&.text) &&
           loc = src.xpath(SOURCELOCALITY)&.text) or next
             iev_validate1(t, loc, xmldoc)
@@ -46,15 +46,16 @@ module Metanorma
 
       def concept_validate_ids(doc)
         @concept_ids ||= doc.xpath("//term | //definitions//dt")
-          .each_with_object({}) { |x, m| m[x["id"]] = true }
+          .each_with_object({}) { |x, m| m[x["anchor"]] = true }
         @concept_terms_tags ||= doc.xpath("//terms")
-          .each_with_object({}) { |t, m| m[t["id"]] = true }
+          .each_with_object({}) { |t, m| m[t["anchor"]] = true }
         nil
       end
 
       def concept_validate_msg(_doc, tag, refterm, xref)
+        t = @doc_ids.dig(xref["target"], :anchor) || xref["target"]
         ret = <<~LOG
-          #{tag.capitalize} #{xref.at("../#{refterm}")&.text} is pointing to #{xref['target']}, which is not a term or symbol
+          #{tag.capitalize} #{xref.at("../#{refterm}")&.text} is pointing to #{t}, which is not a term or symbol
         LOG
         if @concept_terms_tags[xref["target"]]
           ret = ret.strip
@@ -79,7 +80,7 @@ module Metanorma
       def preferred_validate_report(terms)
         terms.each do |k, v|
           v.size > 1 or next
-          loc = v.map { |x| x["id"] }.join(", ")
+          loc = v.map { |x| x["anchor"] }.join(", ")
           err = "Term #{k} occurs twice as preferred designation: #{loc}"
           @log.add("Terms", v.first, err, severity: 1)
         end
@@ -92,7 +93,7 @@ module Metanorma
           c = d.ancestors.detect do |x|
             section_containers.include?(x.name)
           end
-          c["id"] ||= "_#{UUIDTools::UUID.random_create}"
+          c["id"] or add_id(c["id"])
           m[c["id"]] ||= { clause: c, designations: [] }
           m[c["id"]][:designations] << d
         end
@@ -106,7 +107,7 @@ module Metanorma
           end.join(", ")
           err = <<~ERROR
             Clause not recognised as a term clause, but contains designation markup
-             (preferred:[], admitted:[], alt:[], deprecated:[]):<br/>
+             (<code>preferred:[], admitted:[], alt:[], deprecated:[]</code>):<br/>
             #{desgns}</br>
             Ensure the parent clause is recognised as a terms clause by inserting <code>[heading=terms and definitions]</code> above the title,
             in case the heading is not automatically recognised. See also <a href="https://www.metanorma.org/author/topics/sections/concepts/#clause-title">Metanorma documentation</a>.

data/lib/metanorma/standoc/version.rb

@@ -19,6 +19,6 @@ module Metanorma
   end
 
   module Standoc
-    VERSION = "3.0.7".freeze
+    VERSION = "3.0.8".freeze
   end
 end

data/metanorma-standoc.gemspec

@@ -37,7 +37,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "metanorma-plugin-datastruct", "~> 0.3.0"
   spec.add_dependency "metanorma-plugin-glossarist", "~> 0.2.3"
   spec.add_dependency "metanorma-plugin-lutaml", "~> 0.7.0"
-  spec.add_dependency "metanorma-utils", "~> 1.10.0"
+  spec.add_dependency "metanorma-utils", "~> 1.11.0"
   spec.add_dependency "ruby-jing"
   # relaton-cli not just relaton, to avoid circular reference in metanorma
   spec.add_dependency "concurrent-ruby"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metanorma-standoc
 version: !ruby/object:Gem::Version
-  version: 3.0.7
+  version: 3.0.8
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-04-29 00:00:00.000000000 Z
+date: 2025-05-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -142,14 +142,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.0
+        version: 1.11.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.10.0
+        version: 1.11.0
 - !ruby/object:Gem::Dependency
   name: ruby-jing
   requirement: !ruby/object:Gem::Requirement