From abfbeb17e56bd9abc275de0f7ace6c197e00e3bf Mon Sep 17 00:00:00 2001
From: Robin Haberkorn <robin.haberkorn@googlemail.com>
Date: Mon, 21 Oct 2024 02:10:44 +0300
Subject: fixed EOL conversion on UTF-8 texts

* The old bug of saving gchar in gints, so teco_eol_reader_t::last_char could become negative.
* When converting from an UTF-8 text with CRLF linebreaks, we could have data loss and corruptions.
* On strings ending in UTF-8 characters, teco_eol_reader_t::offset would overflow, resulting
  in invalid reads and potentially insertion of data garbage.
  I observed this with G~ on Gtk.
* Test cased updated. Couldn't reproduce the bug with the test suite, though.
---
 src/eol.c                | 2 +-
 tests/autoeol-input.txt  | 6 +++---
 tests/autoeol-output.txt | 4 ++--
 tests/testsuite.at       | 2 ++
 4 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/src/eol.c b/src/eol.c
index 0063bbd..3439869 100644
--- a/src/eol.c
+++ b/src/eol.c
@@ -239,7 +239,7 @@ teco_eol_reader_convert(teco_eol_reader_t *ctx, gchar **ret, gsize *data_len, GE
 				else if (ctx->eol_style != SC_EOL_CR)
 					ctx->eol_style_inconsistent = TRUE;
 			}
-			ctx->last_char = buffer[i];
+			ctx->last_char = (guchar)buffer[i];
 			break;
 		}
 	}
diff --git a/tests/autoeol-input.txt b/tests/autoeol-input.txt
index 237e7d1..705845d 100644
--- a/tests/autoeol-input.txt
+++ b/tests/autoeol-input.txt
@@ -1,4 +1,4 @@
-Hello
-world
 FOO
-BAR
\ No newline at end of file
+BAR
+Здравствуй
+мир
\ No newline at end of file
diff --git a/tests/autoeol-output.txt b/tests/autoeol-output.txt
index 5fb4c8e..9c1ef29 100644
--- a/tests/autoeol-output.txt
+++ b/tests/autoeol-output.txt
@@ -1,4 +1,4 @@
-Hello
-world
 FOO
 BAR
+Здравствуй
+мир
\ No newline at end of file
diff --git a/tests/testsuite.at b/tests/testsuite.at
index 7769cb7..729b3c8 100644
--- a/tests/testsuite.at
+++ b/tests/testsuite.at
@@ -134,6 +134,8 @@ AT_SETUP([Automatic EOL normalization])
 AT_CHECK([$SCITECO -e "@EB'${srcdir}/autoeol-input.txt' EL-2\"N(0/0)' 2LR 13@I'' 0EL @EW'autoeol-sciteco.txt'"],
          0, ignore, ignore)
 AT_CHECK([cmp autoeol-sciteco.txt ${srcdir}/autoeol-output.txt], 0, ignore, ignore)
+AT_CHECK([$SCITECO -e "@EB'autoeol-sciteco.txt' EL-0\"N(0/0)' 2EL @EW''"], 0, ignore, ignore)
+AT_CHECK([cmp autoeol-sciteco.txt ${srcdir}/autoeol-input.txt], 0, ignore, ignore)
 AT_CLEANUP
 
 AT_SETUP([Memory limiting])
-- 
cgit v1.2.3