From 18a622f378b403788c67fc785d30f4609caa3fc7 Mon Sep 17 00:00:00 2001
From: Joel Klinghed <the_jk@spawned.biz>
Date: Mon, 15 Sep 2025 20:52:51 +0200
Subject: uio: Unicode reader

Reads UTF-8 and UTF-16 into UTF-8 or UTF-16 strings.
If strict is true, fails at first invalid character.
If strict is false, invalid characters are replaced with U+FFFD.
For the replacement, I changed behavior if uN::read_replace to only
jump one byte. Otherwise a common invalid case when ISO-8859-1 or
WIN-1252 are read as UTF-8 would skip many characters.

If skip_bom is true any bom at start of stream is ignored.
If skip_bom is false any bom will be included.

Input format can be forced, if not detect is used which will
try to guess and then fallback to UTF-8.
---
 meson.build | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

(limited to 'meson.build')

diff --git a/meson.build b/meson.build
index b0708c2..94519bc 100644
--- a/meson.build
+++ b/meson.build
@@ -149,6 +149,20 @@ unicode_lib = library(
 )
 unicode_dep = declare_dependency(link_with: unicode_lib)
 
+uio_lib = library(
+  'uio',
+  sources: [
+    'src/uio.cc',
+    'src/uio.hh',
+  ],
+  include_directories: inc,
+  dependencies: [buffer_dep, io_dep, unicode_dep],
+)
+uio_dep = declare_dependency(
+  link_with: uio_lib,
+  dependencies: [buffer_dep, io_dep, unicode_dep],
+)
+
 jkc = executable(
   'jkc',
   sources: [
@@ -265,6 +279,17 @@ test('decompress', executable(
   ],
 ))
 
+test('uio', executable(
+  'test_uio',
+  sources: ['test/uio.cc'],
+  include_directories: inc,
+  dependencies: [
+    io_test_helper_dep,
+    uio_dep,
+    test_dependencies,
+  ],
+))
+
 run_clang_tidy = find_program('run-clang-tidy', required: false)
 
 if run_clang_tidy.found()
-- 
cgit v1.3