canon 0.3.45 → 0.3.46

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a17cd55bc56c7287d027191b11cd33a6bc0999b29abce17bb8c368758379e4ad
-  data.tar.gz: 7b7c89255ad4134219b512265b6b26c08a1352742dfc1500a821a830fa3cd2d3
+  metadata.gz: 2dc57b150c1a0a2b9179f4b88a78c22aeb1529aa74d30857d8ca71a6159d6639
+  data.tar.gz: 65db8a7cadb8718b11a475858d3bfd5d4adcf0a4c738a7c940a6dfa60a6bfd3e
 SHA512:
-  metadata.gz: d4673a7e48e7fb4aa901ece0c6fc3c097e3c046af4aee63b959b218d8809a32ac9e8f4ea3db990ff969f521d9842e826e03f4815da8610fba7138070cc420f8e
-  data.tar.gz: f5771189aed0ef86eb98b32b9bd94261221688aece84f6f7b44861c66afcde65d80b3b0a2cb599bb96c18aaa575da4ff86d1bb385b48ff7a3ff34c858342a632
+  metadata.gz: d411dc92e7978a904f303a95397f301286e9a12a3fc3732bb91919c2564375221b12cb13db64198f41942edeb5bbe2dfc8512b173cbfbdab44d27409d5a009a9
+  data.tar.gz: eaa339eae29ca147aa6ee9a5cecf9a328e69fc9b1f64b3acb742d11f4d451bef89efc11cde012e06e15f21b10ec09f95fbf36e0456c718ba925c015e47dba0ce

data/lib/canon/diff/diff_line_builder.rb

@@ -21,19 +21,22 @@ module Canon
       # @param text1 [String] The first document (preprocessed)
       # @param text2 [String] The second document (preprocessed)
       # @return [Array<DiffLine>] The assembled diff lines
-      def self.build(diff_nodes, text1, text2)
+      def self.build(diff_nodes, text1, text2, lines1: nil, lines2: nil)
         return [] if diff_nodes.nil? || diff_nodes.empty?
         return [] if text1.nil? || text2.nil?
 
-        new(diff_nodes, text1, text2).build
+        new(diff_nodes, text1, text2, lines1, lines2).build
       end
 
-      def initialize(diff_nodes, text1, text2)
+      def initialize(diff_nodes, text1, text2, lines1 = nil, lines2 = nil)
         @diff_nodes = diff_nodes
         @text1 = text1
         @text2 = text2
-        @lines1 = text1.split("\n")
-        @lines2 = text2.split("\n")
+        # The caller may hand in the already-split lines (the
+        # formatter splits these documents too); re-splitting both
+        # documents per pipeline stage was ~2x the line strings.
+        @lines1 = lines1 || text1.split("\n")
+        @lines2 = lines2 || text2.split("\n")
         # Build reverse indices for efficient content lookup in gap handling.
         # Maps content string to array of line indices where that content appears.
         @line_to_indices1 = build_line_index(@lines1)

data/lib/canon/diff/diff_node_enricher.rb

@@ -22,21 +22,22 @@ module Canon
       # @param text1 [String] The first document (preprocessed)
       # @param text2 [String] The second document (preprocessed)
       # @return [Array<DiffNode>] The same DiffNodes, enriched in place
-      def self.build(diff_nodes, text1, text2)
+      def self.build(diff_nodes, text1, text2, lines1: nil, lines2: nil)
         return diff_nodes if diff_nodes.nil? || diff_nodes.empty?
         return diff_nodes if text1.nil? || text2.nil?
 
-        new(diff_nodes, text1, text2).enrich
+        new(diff_nodes, text1, text2, lines1, lines2).enrich
       end
 
-      def initialize(diff_nodes, text1, text2)
+      def initialize(diff_nodes, text1, text2, lines1 = nil, lines2 = nil)
         @diff_nodes = diff_nodes
         @text1 = text1
         @text2 = text2
         @line_map1 = SourceLocator.build_line_map(text1)
         @line_map2 = SourceLocator.build_line_map(text2)
-        @lines1 = text1.split("\n")
-        @lines2 = text2.split("\n")
+        # Shared split — see DiffLineBuilder's note.
+        @lines1 = lines1 || text1.split("\n")
+        @lines2 = lines2 || text2.split("\n")
         # Track occurrences for text_content dimension to find correct element instance
         @text_occurrence1 = Hash.new(0)
         @text_occurrence2 = Hash.new(0)

data/lib/canon/diff_formatter/by_line/xml_formatter.rb

@@ -44,12 +44,22 @@ module Canon
           # Compute line number width BEFORE formatting
           compute_line_num_width(doc1, doc2)
 
+          # The pipeline splits both documents once here; every stage
+          # downstream reuses the arrays (three redundant full-doc
+          # splits per render before).
+          @pipeline_lines1 = doc1.split("\n")
+          @pipeline_lines2 = doc2.split("\n")
+
           # Phase 1: Enrich DiffNodes with character positions
-          Canon::Diff::DiffNodeEnricher.build(@differences, doc1, doc2)
+          Canon::Diff::DiffNodeEnricher.build(@differences, doc1, doc2,
+                                              lines1: @pipeline_lines1,
+                                              lines2: @pipeline_lines2)
 
           # Phase 2: Assemble DiffLines from enriched DiffNodes
           diff_lines = Canon::Diff::DiffLineBuilder.build(@differences, doc1,
-                                                          doc2)
+                                                          doc2,
+                                                          lines1: @pipeline_lines1,
+                                                          lines2: @pipeline_lines2)
 
           # Layers 3-5: Build report through pipeline
           report = Canon::Diff::DiffReportBuilder.build(
@@ -178,8 +188,8 @@ module Canon
         def format_report(report, doc1, doc2)
           return "" if report.contexts.empty?
 
-          lines1 = doc1.split("\n")
-          lines2 = doc2.split("\n")
+          lines1 = @pipeline_lines1 || doc1.split("\n")
+          lines2 = @pipeline_lines2 || doc2.split("\n")
 
           output = []
 

data/lib/canon/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Canon
-  VERSION = "0.3.45"
+  VERSION = "0.3.46"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: canon
 version: !ruby/object:Gem::Version
-  version: 0.3.45
+  version: 0.3.46
 platform: ruby
 authors:
 - Ribose Inc.