thank you Q&A, now theres proper unicode support n shit

4 files changed, 97 insertions, 24 deletions

diff --git a/build.zig b/build.zig
index caf84f5..52d916b 100644
--- a/build.zig
+++ b/build.zig
@@ -7,15 +7,17 @@ pub fn build(b: *Build) void {
     const target = b.standardTargetOptions(.{});
     const optimize = b.standardOptimizeOption(.{});
 
+    const version = getVersion(b);
+
+    const config = b.addOptions();
+    config.addOption(SemanticVersion, "version", version);
+
     const sqlite = b.dependency("sqlite", .{
         .target = target,
         .optimize = optimize,
     });
 
-    const version = getVersion(b);
-
-    const config = b.addOptions();
-    config.addOption(SemanticVersion, "version", version);
+    const zg = b.dependency("zg", .{});
 
     const exe = b.addExecutable(.{
         .name = "ukkobot",
@@ -25,6 +27,8 @@ pub fn build(b: *Build) void {
         .optimize = optimize,
     });
     exe.root_module.addOptions("ukkobot-config", config);
+    exe.root_module.addImport("CaseData", zg.module("CaseData"));
+    exe.root_module.addImport("GenCatData", zg.module("GenCatData"));
     exe.root_module.addImport("sqlite", sqlite.module("sqlite"));
     exe.linkLibrary(sqlite.artifact("sqlite"));
     b.installArtifact(exe);
diff --git a/build.zig.zon b/build.zig.zon
index 0346cf0..4a582c0 100644
--- a/build.zig.zon
+++ b/build.zig.zon
@@ -7,5 +7,9 @@
             .url = "https://git.enes.lv/zig-sqlite/snapshot/zig-sqlite-e4afe26b30e03ee5d8b61946893b19c2585745f8.tar.xz",
             .hash = "122019ea6e071dbd932c3e51d9631d99f007240e3e08d5436a1da20ad088343ca4a7",
         },
+        .zg = .{
+            .url = "https://git.enes.lv/zg/snapshot/zg-0.13.2.tar.xz",
+            .hash = "122055beff332830a391e9895c044d33b15ea21063779557024b46169fb1984c6e40",
+        },
     },
 }
diff --git a/src/main.zig b/src/main.zig
index 544b105..2e33cfc 100644
--- a/src/main.zig
+++ b/src/main.zig
@@ -199,22 +199,29 @@ fn onTextMessage(bot: *Bot, msg: types.Message, text: []const u8) !void {
             },
         });
     } else if (std.ascii.startsWithIgnoreCase(text, "big ")) {
-        var output = ArrayList(u8).init(bot.allocator);
-        defer output.deinit();
+        const trimmed = try utils.trim(text[4..]);
+        const cd = try utils.getCD();
+        if (trimmed.len > 0) {
+            const uppercased = try cd.toUpperStr(bot.allocator, trimmed);
+            defer bot.allocator.free(uppercased);
 
-        try output.appendSlice("<b>");
-        try utils.escapeXml(output.writer(), text[4..]);
-        try output.appendSlice("</b>");
+            var output = ArrayList(u8).init(bot.allocator);
+            defer output.deinit();
 
-        try bot.sendMessage_(.{
-            .chat_id = msg.chat.id,
-            .text = output.items,
-            .parse_mode = .html,
-            .reply_parameters = .{
-                .message_id = msg.message_id,
+            try output.appendSlice("<b>");
+            try utils.escapeXml(output.writer(), uppercased);
+            try output.appendSlice("</b>");
+
+            try bot.sendMessage_(.{
                 .chat_id = msg.chat.id,
-            },
-        });
+                .text = output.items,
+                .parse_mode = .html,
+                .reply_parameters = .{
+                    .message_id = msg.message_id,
+                    .chat_id = msg.chat.id,
+                },
+            });
+        }
     } else if (std.ascii.eqlIgnoreCase(text, "forgor")) {
         try bot.sendMessage_(.{
             .chat_id = msg.chat.id,
@@ -244,14 +251,17 @@ fn onTextMessage(bot: *Bot, msg: types.Message, text: []const u8) !void {
             },
         });
     } else if (std.ascii.startsWithIgnoreCase(text, "say ")) {
-        try bot.sendMessage_(.{
-            .chat_id = msg.chat.id,
-            .text = text[4..],
-            .reply_parameters = .{
-                .message_id = msg.message_id,
+        const trimmed = try utils.trim(text[4..]);
+        if (trimmed.len > 0) {
+            try bot.sendMessage_(.{
                 .chat_id = msg.chat.id,
-            },
-        });
+                .text = trimmed,
+                .reply_parameters = .{
+                    .message_id = msg.message_id,
+                    .chat_id = msg.chat.id,
+                },
+            });
+        }
     } else if (std.ascii.eqlIgnoreCase(text, "uwu")) {
         try bot.sendMessage_(.{
             .chat_id = msg.chat.id,
diff --git a/src/utils.zig b/src/utils.zig
index c6e8508..631e464 100644
--- a/src/utils.zig
+++ b/src/utils.zig
@@ -2,6 +2,9 @@ const std = @import("std");
 
 const Allocator = std.mem.Allocator;
 const ArrayList = std.ArrayList;
+const CaseData = @import("CaseData");
+const GenCatData = @import("GenCatData");
+const Utf8View = std.unicode.Utf8View;
 
 pub fn escapeXml(writer: anytype, text: []const u8) !void {
     for (text) |ch| {
@@ -15,6 +18,26 @@ pub fn escapeXml(writer: anytype, text: []const u8) !void {
     }
 }
 
+var gcd_global: ?GenCatData = null;
+
+pub fn getGCD() !GenCatData {
+    if (gcd_global) |gcd| {
+        return gcd;
+    }
+    gcd_global = try GenCatData.init(std.heap.page_allocator);
+    return gcd_global.?;
+}
+
+var cd_global: ?CaseData = null;
+
+pub fn getCD() !CaseData {
+    if (cd_global) |cd| {
+        return cd;
+    }
+    cd_global = try CaseData.init(std.heap.page_allocator);
+    return cd_global.?;
+}
+
 pub inline fn isNull(value: anytype) bool {
     return switch (@typeInfo(@TypeOf(value))) {
         .Null => true,
@@ -22,3 +45,35 @@ pub inline fn isNull(value: anytype) bool {
         else => false,
     };
 }
+
+pub fn trim(str: []const u8) ![]const u8 {
+    const view = try Utf8View.init(str);
+    const gcd = try getGCD();
+
+    var it = view.iterator();
+    var idx: usize = 0;
+    const first = while (it.nextCodepoint()) |cp| {
+        if (!isTrimmable(gcd, cp)) {
+            break idx;
+        }
+        idx = it.i;
+    } else {
+        return "";
+    };
+
+    idx = it.i;
+
+    var last = first;
+    while (it.nextCodepoint()) |cp| {
+        if (!isTrimmable(gcd, cp)) {
+            last = idx + (std.unicode.utf8CodepointSequenceLength(cp) catch unreachable) - 1;
+        }
+        idx = it.i;
+    }
+
+    return str[first .. last + 1];
+}
+
+inline fn isTrimmable(gcd: GenCatData, cp: u21) bool {
+    return gcd.isSeparator(cp) or gcd.isControl(cp);
+}