add tokenizer

src/main.zig

@@ -1,24 +1,18 @@
 const std = @import("std");
+const tkz = @import("tokenize.zig");
 
 pub fn main() !void {
-    // Prints to stderr (it's a shortcut based on `std.io.getStdErr()`)
-    std.debug.print("All your {s} are belong to us.\n", .{"codebase"});
+    var file = try std.fs.cwd().openFile("data/example.il", .{});
+    defer file.close();
 
-    // stdout is for the actual output of your application, for example if you
-    // are implementing gzip, then only the compressed bytes should be sent to
-    // stdout, not any debugging messages.
-    const stdout_file = std.io.getStdOut().writer();
-    var bw = std.io.bufferedWriter(stdout_file);
-    const stdout = bw.writer();
+    const content = try file.readToEndAlloc(std.heap.page_allocator, 4096 * ((1 << 10) << 10));
 
-    try stdout.print("Run `zig build test` to run the tests.\n", .{});
-
-    try bw.flush(); // don't forget to flush!
-}
-
-test "simple test" {
-    var list = std.ArrayList(i32).init(std.testing.allocator);
-    defer list.deinit(); // try commenting this out and see if zig detects the memory leak!
-    try list.append(42);
-    try std.testing.expectEqual(@as(i32, 42), list.pop());
+    const toks = try tkz.tokenizeContent(content);
+    for (toks.items) |tok| {
+        std.debug.print("{}:{} `{s}`\n", .{
+            tok.line,
+            tok.char,
+            tok.value,
+        });
+    }
 }

src/tokenize.zig

@@ -0,0 +1,97 @@
+const std = @import("std");
+
+const Token = struct {
+    /// 0-based index of token start in whole file
+    start: usize,
+    /// 1-based line numbert token starts at
+    line: usize,
+    /// 1-based char numbert token starts at in line
+    char: usize,
+
+    value: []const u8,
+};
+
+const TokenizationError = error{InvalidKeyword};
+
+pub fn tokenizeContent(content: []u8) !std.ArrayList(Token) {
+    var toks = std.ArrayList(Token).init(std.heap.page_allocator);
+    var lines = std.ArrayList(usize).init(std.heap.page_allocator);
+
+    var index: usize = 0;
+    while (index < content.len) {
+        var l: usize = 1;
+        const char = content[index];
+        _ = switch (char) {
+            '\n' => {
+                try lines.append(index);
+                index += l;
+                continue;
+            },
+            ';' => {
+                while (switch (content[index + l]) {
+                    '\n' => false,
+                    else => true,
+                }) : (l += 1) {}
+            },
+            '"' => {
+                while (switch (content[index + l]) {
+                    '"' => (content[index + l - 1] == '\\'),
+                    else => true,
+                }) : (l += 1) {}
+                l += 1;
+            },
+            'a'...'z', 'A'...'Z', '_' => {
+                while (switch (content[index + l]) {
+                    'a'...'z', 'A'...'Z', '0'...'9', '_' => true,
+                    else => false,
+                }) : (l += 1) {}
+            },
+            '0'...'9' => {
+                while (switch (content[index + l]) {
+                    '0'...'9', '.', 'e' => true,
+                    else => false,
+                }) : (l += 1) {}
+            },
+            '+', '-', '~', '*', '/', '%', '<', '>', '=', '?', '|', '&', '(', ')', '\'' => {
+                for ([_]*const [2]u8{ "->", "~>", "||", "&&", "/=", "*=", "+=", "-=", "'(" }) |op| {
+                    if (std.mem.eql(u8, op, content[index .. index + 2])) {
+                        l = 2;
+                        break;
+                    }
+                }
+            },
+            '@' => {
+                while (switch (content[index + l]) {
+                    'a'...'z', 'A'...'Z', '_', '0'...'9' => true,
+                    else => false,
+                }) : (l += 1) {}
+
+                if (std.mem.eql(u8, "@keys", content[index .. index + l])) {} else if (std.mem.eql(u8, "@rest", content[index .. index + l])) {} else {
+                    std.debug.print("line={d}, char={d}\n", .{
+                        .line = lines.items.len + 1,
+                        .char = switch (lines.items.len) {
+                            0 => index,
+                            else => index - lines.items[lines.items.len - 1],
+                        },
+                    });
+                }
+            },
+            else => {
+                index += l;
+                continue;
+            },
+        };
+        try toks.append(.{
+            .start = index,
+            .value = content[index .. index + l],
+            .line = lines.items.len + 1,
+            .char = switch (lines.items.len) {
+                0 => index,
+                else => index - lines.items[lines.items.len - 1],
+            },
+        });
+        index += l;
+    }
+
+    return toks;
+}