Merge pull request #36 from benoitc/feature/explicit-bytes-conversion

Add explicit bytes conversion with {bytes, Binary} tuple

Author: benoitc

c_src/py_convert.c

@@ -520,6 +520,27 @@ static PyObject *term_to_py(ErlNifEnv *env, ERL_NIF_TERM term) {
         return PyBytes_FromStringAndSize((char *)bin.data, bin.size);
     }
 
+    /*
+     * Check for {bytes, Binary} tagged tuple - explicit bytes conversion.
+     * This allows users to explicitly send raw bytes without UTF-8 decoding.
+     */
+    {
+        int tuple_arity;
+        const ERL_NIF_TERM *tuple_elements;
+        if (enif_get_tuple(env, term, &tuple_arity, &tuple_elements) && tuple_arity == 2) {
+            char tag_buf[16];
+            if (enif_get_atom(env, tuple_elements[0], tag_buf, sizeof(tag_buf), ERL_NIF_LATIN1)) {
+                if (strcmp(tag_buf, "bytes") == 0) {
+                    ErlNifBinary bytes_bin;
+                    if (enif_inspect_binary(env, tuple_elements[1], &bytes_bin)) {
+                        return PyBytes_FromStringAndSize((char *)bytes_bin.data, bytes_bin.size);
+                    }
+                    /* Not a binary - fall through to normal tuple handling */
+                }
+            }
+        }
+    }
+
     /* Check list (must come after binary to preserve structure) */
     if (enif_get_list_length(env, term, &list_len)) {
         PyObject *list = PyList_New(list_len);

docs/type-conversion.md

@@ -11,6 +11,7 @@ When calling Python functions or evaluating expressions, Erlang values are autom
 | `integer()` | `int` | Arbitrary precision supported |
 | `float()` | `float` | IEEE 754 double precision |
 | `binary()` | `str` | UTF-8 encoded |
+| `{bytes, binary()}` | `bytes` | Explicit bytes (no UTF-8 decode) |
 | `atom()` | `str` | Converted to string (except special atoms) |
 | `true` | `True` | Boolean |
 | `false` | `False` | Boolean |
@@ -56,6 +57,38 @@ py:call(mymod, func, [{1, 2, 3}]).    %% Python receives: (1, 2, 3)
 py:call(mymod, func, [#{a => 1, b => 2}]).  %% Python receives: {"a": 1, "b": 2}
 ```
 
+### Explicit Bytes Conversion
+
+By default, Erlang binaries are converted to Python `str` using UTF-8 decoding.
+To explicitly send raw bytes without string conversion, use the `{bytes, Binary}` tuple:
+
+```erlang
+%% Default: binary -> str
+py:call(mymod, func, [<<"hello">>]).  %% Python sees: "hello" (str)
+
+%% Explicit: {bytes, binary} -> bytes
+py:call(mymod, func, [{bytes, <<"hello">>}]).  %% Python sees: b"hello" (bytes)
+
+%% Useful for binary protocols, images, compressed data
+py:call(image_processor, load, [{bytes, ImageData}]).
+```
+
+This is useful when you need to ensure binary data is treated as raw bytes in Python,
+for example when working with binary protocols, image data, or compressed content.
+
+Note that on the return path, both Python `str` and `bytes` become Erlang `binary()`:
+
+```erlang
+%% Python str -> Erlang binary
+{ok, <<"hello">>} = py:eval(<<"'hello'">>).
+
+%% Python bytes -> Erlang binary
+{ok, <<"hello">>} = py:eval(<<"b'hello'">>).
+
+%% Non-UTF8 bytes also work
+{ok, <<255, 254>>} = py:eval(<<"b'\\xff\\xfe'">>).
+```
+
 ## Python to Erlang
 
 Return values from Python are converted back to Erlang:

test/py_api_SUITE.erl

@@ -29,7 +29,9 @@
     test_context_management/1,
     test_start_stop_contexts/1,
     %% Mixed usage
-    test_mixed_api_usage/1
+    test_mixed_api_usage/1,
+    %% Type conversion
+    test_explicit_bytes/1
 ]).
 
 %% ============================================================================
@@ -52,7 +54,9 @@ all() ->
         test_context_management,
         test_start_stop_contexts,
         %% Mixed usage
-        test_mixed_api_usage
+        test_mixed_api_usage,
+        %% Type conversion
+        test_explicit_bytes
     ].
 
 init_per_suite(Config) ->
@@ -223,3 +227,35 @@ test_mixed_api_usage(_Config) ->
     %% Both should work correctly
     {ok, 6} = py:eval(<<"2 + 4">>),
     {ok, 7} = py:eval(Ctx, <<"3 + 4">>, #{}).
+
+%% ============================================================================
+%% Type Conversion Tests
+%% ============================================================================
+
+%% @doc Test explicit bytes conversion using {bytes, Binary} tuple.
+test_explicit_bytes(_Config) ->
+    Ctx = py:context(1),
+
+    %% Define test functions
+    ok = py:exec(Ctx, <<"
+def check_type(val):
+    return type(val).__name__
+
+def check_bytes_value(val):
+    return val == b'hello'
+">>),
+
+    %% Regular binary -> str (default UTF-8 decoding)
+    {ok, <<"str">>} = py:eval(Ctx, <<"check_type(val)">>, #{<<"val">> => <<"hello">>}),
+
+    %% Explicit bytes tuple -> bytes
+    {ok, <<"bytes">>} = py:eval(Ctx, <<"check_type(val)">>, #{<<"val">> => {bytes, <<"hello">>}}),
+
+    %% Verify value is correct
+    {ok, true} = py:eval(Ctx, <<"check_bytes_value(val)">>, #{<<"val">> => {bytes, <<"hello">>}}),
+
+    %% Test with binary data (non-UTF8)
+    NonUtf8 = <<255, 254, 0, 1>>,
+    {ok, <<"bytes">>} = py:eval(Ctx, <<"check_type(val)">>, #{<<"val">> => {bytes, NonUtf8}}),
+
+    ok.