From 15a66ebc3dcf7fbebb7c14ec49515228c96de59a Mon Sep 17 00:00:00 2001
From: Araozu <fernando@araozu.dev>
Date: Mon, 18 Nov 2024 21:08:37 -0500
Subject: [PATCH] feat: lex datatype

---
 build.zig                   |  1 +
 src/01_lexic/datatype.zig   | 53 +++++++++++++++++++++++++++++++++++++
 src/01_lexic/identifier.zig |  1 +
 src/01_lexic/root.zig       |  2 --
 src/01_lexic/utils.zig      |  4 +++
 5 files changed, 59 insertions(+), 2 deletions(-)
 create mode 100644 src/01_lexic/datatype.zig

diff --git a/build.zig b/build.zig
index c5fbdea..81a2adf 100644
--- a/build.zig
+++ b/build.zig
@@ -94,6 +94,7 @@ pub fn build(b: *std.Build) void {
         "src/01_lexic/root.zig",
         "src/01_lexic/number.zig",
         "src/01_lexic/identifier.zig",
+        "src/01_lexic/datatype.zig",
         "src/01_lexic/token.zig",
         "src/01_lexic/utils.zig",
     };
diff --git a/src/01_lexic/datatype.zig b/src/01_lexic/datatype.zig
new file mode 100644
index 0000000..a05433b
--- /dev/null
+++ b/src/01_lexic/datatype.zig
@@ -0,0 +1,53 @@
+const std = @import("std");
+const token = @import("./token.zig");
+const utils = @import("./utils.zig");
+
+const Token = token.Token;
+const TokenType = token.TokenType;
+const LexError = token.LexError;
+const LexReturn = token.LexReturn;
+
+/// Lexes a Datatype
+pub fn lex(input: []const u8, start: usize) LexError!?LexReturn {
+    const cap = input.len;
+    var final_pos = start;
+
+    if (start >= cap) {
+        return null;
+    }
+
+    // lex uppercase
+    if (!utils.is_uppercase(input[start])) {
+        return null;
+    }
+    final_pos += 1;
+
+    // lex many lowercase/uppercase/underscore/number
+    if (utils.lex_many(utils.is_identifier_char, input, final_pos)) |new_pos| {
+        final_pos = new_pos;
+    }
+
+    return .{
+        Token.init(input[start..final_pos], TokenType.Identifier, start),
+        final_pos,
+    };
+}
+
+test "should lex datatype" {
+    const input = "MyType";
+    const output = try lex(input, 0);
+
+    if (output) |tuple| {
+        const t = tuple[0];
+        try std.testing.expectEqualDeep("MyType", t.value);
+    } else {
+        try std.testing.expect(false);
+    }
+}
+
+test "shouldnt lex identifier" {
+    const input = "myDatatype";
+    const output = try lex(input, 0);
+
+    try std.testing.expect(output == null);
+}
diff --git a/src/01_lexic/identifier.zig b/src/01_lexic/identifier.zig
index 7201686..a5509c8 100644
--- a/src/01_lexic/identifier.zig
+++ b/src/01_lexic/identifier.zig
@@ -7,6 +7,7 @@ const TokenType = token.TokenType;
 const LexError = token.LexError;
 const LexReturn = token.LexReturn;
 
+/// Lexes a datatype
 pub fn lex(input: []const u8, start: usize) LexError!?LexReturn {
     const cap = input.len;
     var final_pos = start;
diff --git a/src/01_lexic/root.zig b/src/01_lexic/root.zig
index 8e0db11..8334fbb 100644
--- a/src/01_lexic/root.zig
+++ b/src/01_lexic/root.zig
@@ -27,8 +27,6 @@ pub fn tokenize(input: []const u8, alloc: std.mem.Allocator) !void {
             break;
         }
     }
-
-    std.debug.print("array list len: {d}", .{tokens.items.len});
 }
 
 /// Ignores all whitespace on `input` since `start`
diff --git a/src/01_lexic/utils.zig b/src/01_lexic/utils.zig
index 17ad51e..98b2820 100644
--- a/src/01_lexic/utils.zig
+++ b/src/01_lexic/utils.zig
@@ -22,6 +22,10 @@ pub fn is_lowercase(c: u8) bool {
     return 'a' <= c and c <= 'z';
 }
 
+pub fn is_uppercase(c: u8) bool {
+    return 'A' <= c and c <= 'Z';
+}
+
 pub fn is_lowercase_underscore(c: u8) bool {
     return c == '_' or ('a' <= c and c <= 'z');
 }