From f170a557edbd35d98f0b5338b99d745277f53746 Mon Sep 17 00:00:00 2001
From: Tom Alexander <tom@fizz.buzz>
Date: Tue, 29 Aug 2023 21:49:16 -0400
Subject: [PATCH] Use character offsets in diff.

---
 build.rs                            | 1 +
 org_mode_samples/unicode/hearts.org | 1 +
 src/compare/diff.rs                 | 3 ++-
 src/compare/util.rs                 | 2 +-
 4 files changed, 5 insertions(+), 2 deletions(-)
 create mode 100644 org_mode_samples/unicode/hearts.org

diff --git a/build.rs b/build.rs
index c8b3c1d..999e073 100644
--- a/build.rs
+++ b/build.rs
@@ -75,6 +75,7 @@ fn is_expect_fail(name: &str) -> Option<&str> {
         "autogen_greater_element_drawer_drawer_with_headline_inside" => Some("Apparently lines with :end: become their own paragraph. This odd behavior needs to be investigated more."),
         "autogen_element_container_priority_footnote_definition_dynamic_block" => Some("Apparently broken begin lines become their own paragraph."),
         "autogen_lesser_element_paragraphs_paragraph_with_backslash_line_breaks" => Some("The text we're getting out of the parse tree is already processed to remove line breaks, so our comparison needs to take that into account."),
+        "autogen_unicode_hearts" => Some("Unicode is coming out of emacs strange."),
         _ => None,
     }
 }
diff --git a/org_mode_samples/unicode/hearts.org b/org_mode_samples/unicode/hearts.org
new file mode 100644
index 0000000..f5f65d8
--- /dev/null
+++ b/org_mode_samples/unicode/hearts.org
@@ -0,0 +1 @@
+🧡💛💚💙💜
diff --git a/src/compare/diff.rs b/src/compare/diff.rs
index a32f208..f4f9450 100644
--- a/src/compare/diff.rs
+++ b/src/compare/diff.rs
@@ -115,12 +115,13 @@ impl<'s> DiffResult<'s> {
             }
         };
         let rust_offset = self.rust_source.as_ptr() as usize - original_document.as_ptr() as usize;
+        let preceding_text = &original_document[..rust_offset];
         println!(
             "{indentation}{status_text} {name} char({char_offset}) {message}",
             indentation = "  ".repeat(indentation),
             status_text = status_text,
             name = self.name,
-            char_offset = rust_offset + 1,
+            char_offset = preceding_text.chars().count() + 1,
             message = self.message.as_ref().map(|m| m.as_str()).unwrap_or("")
         );
         for child in self.children.iter() {
diff --git a/src/compare/util.rs b/src/compare/util.rs
index 25174f6..03c8e9b 100644
--- a/src/compare/util.rs
+++ b/src/compare/util.rs
@@ -51,7 +51,7 @@ pub fn assert_bounds<'s, S: Source<'s>>(
     );
     let (rust_begin, rust_end) = get_offsets(source, rust);
     if (rust_begin + 1) != begin || (rust_end + 1) != end {
-        Err(format!("Rust bounds ({rust_begin}, {rust_end}) do not match emacs bounds ({emacs_begin}, {emacs_end})", rust_begin = rust_begin + 1, rust_end = rust_end + 1, emacs_begin=begin, emacs_end=end))?;
+        Err(format!("Rust bounds (in bytes) ({rust_begin}, {rust_end}) do not match emacs bounds ({emacs_begin}, {emacs_end})", rust_begin = rust_begin + 1, rust_end = rust_end + 1, emacs_begin=begin, emacs_end=end))?;
     }
 
     Ok(())