From c208799af319b10c5d68871f937ea7000b57b08a Mon Sep 17 00:00:00 2001
From: Mike Dalessio <mike.dalessio@gmail.com>
Date: Tue, 2 Jul 2024 16:49:53 -0400
Subject: [PATCH] test: add test coverage describing how pushparser handles
 empty docs

The behavior is different between Java and C impls in a way that I
don't care enough to fix. Let's document the difference and move on
with our lives.
---
 lib/nokogiri/xml/sax/push_parser.rb |  3 +++
 test/xml/sax/test_push_parser.rb    | 33 ++++++++++++++++++++++++++---
 2 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/lib/nokogiri/xml/sax/push_parser.rb b/lib/nokogiri/xml/sax/push_parser.rb
index 2b890a690a..5295b0cf3e 100644
--- a/lib/nokogiri/xml/sax/push_parser.rb
+++ b/lib/nokogiri/xml/sax/push_parser.rb
@@ -52,6 +52,9 @@ def write(chunk, last_chunk = false)
         ###
         # Finish the parsing.  This method is only necessary for
         # Nokogiri::XML::SAX::Document#end_document to be called.
+        #
+        # ⚠ Note that empty documents are treated as an error when using the libxml2-based
+        # implementation (CRuby), but are fine when using the Xerces-based implementation (JRuby).
         def finish
           write("", true)
         end
diff --git a/test/xml/sax/test_push_parser.rb b/test/xml/sax/test_push_parser.rb
index aa7ce84e8e..a0dea3b99e 100644
--- a/test/xml/sax/test_push_parser.rb
+++ b/test/xml/sax/test_push_parser.rb
@@ -32,9 +32,36 @@
 
   it :test_empty_doc do
     parser.options |= Nokogiri::XML::ParseOptions::RECOVER
-    parser.write("", true)
-    assert_nil parser.document.start_elements
-    assert_nil parser.document.end_elements
+    parser.finish
+
+    assert_nil(parser.document.start_elements)
+    assert_nil(parser.document.end_elements)
+    if Nokogiri.jruby?
+      assert_empty(parser.document.errors)
+    elsif Nokogiri.uses_libxml?(">= 2.12.0") # gnome/libxml2@53050b1d
+      assert_match(/Document is empty/, parser.document.errors.first)
+    end
+    assert(parser.document.end_document_called)
+  end
+
+  it :test_empty_doc_without_recovery do
+    # behavior is different between implementations
+    # https://github.com/sparklemotion/nokogiri/issues/1758
+    if Nokogiri.jruby?
+      parser.finish
+
+      assert_nil(parser.document.start_elements)
+      assert_nil(parser.document.end_elements)
+      assert_empty(parser.document.errors)
+      assert(parser.document.end_document_called)
+    else
+      e = assert_raises(Nokogiri::XML::SyntaxError) do
+        parser.finish
+      end
+      if Nokogiri.uses_libxml?(">= 2.12.0") # gnome/libxml2@53050b1d
+        assert_match(/Document is empty/, e.message)
+      end
+    end
   end
 
   it :test_finish_should_rethrow_last_error do