From a2c4b7a57fe6b64bdd7c71305d408e5030af3157 Mon Sep 17 00:00:00 2001
From: Jose Colon Rodriguez
Date: Thu, 28 Mar 2024 22:19:50 -0400
Subject: Split out Unicode tests to separate file

---
 src/grapheme.zig | 65 --------------------------------------------------------
 1 file changed, 65 deletions(-)

(limited to 'src/grapheme.zig')

diff --git a/src/grapheme.zig b/src/grapheme.zig
index ad43cfd..f4cc68c 100644
--- a/src/grapheme.zig
+++ b/src/grapheme.zig
@@ -230,71 +230,6 @@ pub fn graphemeBreak(
     return true;
 }
 
-test "Segmentation GraphemeIterator" {
-    const allocator = std.testing.allocator;
-    var file = try std.fs.cwd().openFile("data/unicode/auxiliary/GraphemeBreakTest.txt", .{});
-    defer file.close();
-    var buf_reader = std.io.bufferedReader(file.reader());
-    var input_stream = buf_reader.reader();
-
-    const data = try GraphemeData.init(allocator);
-    defer data.deinit();
-
-    var buf: [4096]u8 = undefined;
-    var line_no: usize = 1;
-
-    while (try input_stream.readUntilDelimiterOrEof(&buf, '\n')) |raw| : (line_no += 1) {
-        // Skip comments or empty lines.
-        if (raw.len == 0 or raw[0] == '#' or raw[0] == '@') continue;
-
-        // Clean up.
-        var line = std.mem.trimLeft(u8, raw, "÷ ");
-        if (std.mem.indexOf(u8, line, " ÷\t#")) |octo| {
-            line = line[0..octo];
-        }
-        // Iterate over fields.
-        var want = std.ArrayList(Grapheme).init(allocator);
-        defer want.deinit();
-
-        var all_bytes = std.ArrayList(u8).init(allocator);
-        defer all_bytes.deinit();
-
-        var graphemes = std.mem.split(u8, line, " ÷ ");
-        var bytes_index: u32 = 0;
-
-        while (graphemes.next()) |field| {
-            var code_points = std.mem.split(u8, field, " ");
-            var cp_buf: [4]u8 = undefined;
-            var cp_index: u32 = 0;
-            var gc_len: u8 = 0;
-
-            while (code_points.next()) |code_point| {
-                if (std.mem.eql(u8, code_point, "×")) continue;
-                const cp: u21 = try std.fmt.parseInt(u21, code_point, 16);
-                const len = try unicode.utf8Encode(cp, &cp_buf);
-                try all_bytes.appendSlice(cp_buf[0..len]);
-                cp_index += len;
-                gc_len += len;
-            }
-
-            try want.append(Grapheme{ .len = gc_len, .offset = bytes_index });
-            bytes_index += cp_index;
-        }
-
-        // std.debug.print("\nline {}: {s}\n", .{ line_no, all_bytes.items });
-        var iter = Iterator.init(all_bytes.items, &data);
-
-        // Chaeck.
-        for (want.items) |want_gc| {
-            const got_gc = (iter.next()).?;
-            try std.testing.expectEqualStrings(
-                want_gc.bytes(all_bytes.items),
-                got_gc.bytes(all_bytes.items),
-            );
-        }
-    }
-}
-
 test "Segmentation ZWJ and ZWSP emoji sequences" {
     const seq_1 = "\u{1F43B}\u{200D}\u{2744}\u{FE0F}";
     const seq_2 = "\u{1F43B}\u{200D}\u{2744}\u{FE0F}";
-- 
cgit v1.2.3