From 3e3855bc8a5831199c81e0fb6d3997cdf9e274a6 Mon Sep 17 00:00:00 2001
From: "Christoph J. Scherr" <Christoph.Scherr@newtec.de>
Date: Thu, 15 Feb 2024 14:21:10 +0100
Subject: [PATCH] arg tokenizer

---
 tokenize_args.lua | 71 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)
 create mode 100644 tokenize_args.lua

diff --git a/tokenize_args.lua b/tokenize_args.lua
new file mode 100644
index 0000000..16b3b76
--- /dev/null
+++ b/tokenize_args.lua
@@ -0,0 +1,71 @@
+function tokenize_args(raw)
+    -- NOTE: string.gmatch is does not use regex, but a smaller pattern matcher!
+    -- A complete regex parser would be larger than lua itself. See
+    -- [Programming in Lua 20.2](https://www.lua.org/pil/20.2.html).
+    --
+    -- Notable differences:
+    -- '-' is ungreedy wildcard
+    -- '*?' does not work
+    -- '|' is not or
+    --
+    -- This means we're better of implementing a programatic lexer.
+    local t = {}
+    local current = ""
+    local in_str = false
+    local str_seek
+    for c in string.gmatch(raw, ".") do -- iterate through all chars
+        if c == ' ' and not in_str then
+            if string.len(current) > 0 then
+                table.insert(t, current)
+                current = ""
+            end
+        elseif c == '"' and not in_str then
+            in_str = true
+            str_seek = '"'
+        elseif c == "'" and not in_str then
+            in_str = true
+            str_seek = "'"
+        elseif c == str_seek and in_str then
+            in_str = false
+            table.insert(t, current)
+            current = ""
+        else
+            current = current .. c
+        end
+    end
+    table.insert(t, current)
+    return t
+end
+
+--- dumps a variable into a string, so it can be printed. This is meant for
+--- debug prints
+--- @param any t any variable
+--- @return string t_dumped t dumped to string
+function dump(t)
+    if type(t) == 'table' then
+        local s = '{ '
+        for k, v in pairs(t) do
+            if type(k) ~= 'number' then k = '"' .. k .. '"' end
+            if k ~= 1 then
+                s = s .. ', '
+            end
+            s = s .. '[' .. k .. '] = \'' .. dump(v) .. '\''
+        end
+        return s .. ' }'
+    else
+        return tostring(t)
+    end
+end
+
+function main()
+    local mockargs = [[-iab --foo '{"QUX": "BAR"}' --ala=boa]]
+    print(mockargs)
+    local split = tokenize_args(mockargs)
+    print(dump(split))
+end
+
+if pcall(getfenv, 4) then
+    print("Library")
+else
+    main()
+end