fix(aiocqhttp): normalize base64 media payloads (#2296)

* fix(aiocqhttp): normalize image and voice base64 payloads

* fix(aiocqhttp): support file messages from base64 payloads

* test(aiocqhttp): use package import path

src/langbot/pkg/platform/sources/aiocqhttp.py

@@ -16,6 +16,14 @@ from ...utils import image
 import langbot_plugin.api.definition.abstract.platform.event_logger as abstract_platform_logger
 
 
+def _normalize_base64_payload(value: str) -> str:
+    if value.startswith('base64://'):
+        return value.removeprefix('base64://')
+    if value.startswith('data:') and ';base64,' in value:
+        return value.split(';base64,', 1)[1]
+    return value
+
+
 class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
     @staticmethod
     async def yiri2target(
@@ -35,7 +43,7 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
             elif type(msg) is platform_message.Image:
                 arg = ''
                 if msg.base64:
-                    arg = msg.base64
+                    arg = _normalize_base64_payload(msg.base64)
                     msg_list.append(aiocqhttp.MessageSegment.image(f'base64://{arg}'))
                 elif msg.url:
                     arg = msg.url
@@ -50,7 +58,7 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
             elif type(msg) is platform_message.Voice:
                 arg = ''
                 if msg.base64:
-                    arg = msg.base64
+                    arg = _normalize_base64_payload(msg.base64)
                     msg_list.append(aiocqhttp.MessageSegment.record(f'base64://{arg}'))
                 elif msg.url:
                     arg = msg.url
@@ -62,7 +70,10 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
                 for node in msg.node_list:
                     msg_list.extend((await AiocqhttpMessageConverter.yiri2target(node.message_chain))[0])
             elif isinstance(msg, platform_message.File):
-                msg_list.append({'type': 'file', 'data': {'file': msg.url, 'name': msg.name}})
+                file = msg.url or msg.path
+                if not file and msg.base64:
+                    file = f'base64://{_normalize_base64_payload(msg.base64)}'
+                msg_list.append({'type': 'file', 'data': {'file': file, 'name': msg.name}})
             elif isinstance(msg, platform_message.Face):
                 if msg.face_type == 'face':
                     msg_list.append(aiocqhttp.MessageSegment.face(msg.face_id))
@@ -433,9 +444,7 @@ class AiocqhttpAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
                     elif isinstance(component, platform_message.Image):
                         img_data = {}
                         if component.base64:
-                            b64 = component.base64
+                            b64 = _normalize_base64_payload(component.base64)
-                            if b64.startswith('data:'):
-                                b64 = b64.split(',', 1)[-1] if ',' in b64 else b64
                             img_data['file'] = f'base64://{b64}'
                         elif component.url:
                             img_data['file'] = component.url

tests/unit_tests/platform/test_aiocqhttp_message_converter.py

@@ -0,0 +1,105 @@
+import pytest
+
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
+from langbot.pkg.platform.sources.aiocqhttp import AiocqhttpAdapter, AiocqhttpMessageConverter
+
+
+async def _convert_single(component: platform_message.MessageComponent):
+    chain = platform_message.MessageChain([component])
+    message, _, _ = await AiocqhttpMessageConverter.yiri2target(chain)
+    return message[0]
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    ('payload', 'expected'),
+    [
+        ('data:image/jpeg;base64,raw-image', 'base64://raw-image'),
+        ('raw-image', 'base64://raw-image'),
+        ('base64://raw-image', 'base64://raw-image'),
+    ],
+)
+async def test_image_base64_payload_is_normalized(payload, expected):
+    segment = await _convert_single(platform_message.Image(base64=payload))
+
+    assert segment.type == 'image'
+    assert segment.data['file'] == expected
+
+
+@pytest.mark.asyncio
+async def test_voice_data_uri_base64_payload_is_normalized():
+    segment = await _convert_single(platform_message.Voice(base64='data:audio/wav;base64,raw-voice'))
+
+    assert segment.type == 'record'
+    assert segment.data['file'] == 'base64://raw-voice'
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    ('component', 'expected'),
+    [
+        (
+            platform_message.File(name='report.txt', base64='data:text/plain;base64,raw-file'),
+            {'file': 'base64://raw-file', 'name': 'report.txt'},
+        ),
+        (
+            platform_message.File(name='report.txt', base64='raw-file'),
+            {'file': 'base64://raw-file', 'name': 'report.txt'},
+        ),
+        (
+            platform_message.File(name='a.txt', url='http://example.com/a.txt'),
+            {'file': 'http://example.com/a.txt', 'name': 'a.txt'},
+        ),
+        (
+            platform_message.File(name='a.txt', path='/tmp/a.txt'),
+            {'file': '/tmp/a.txt', 'name': 'a.txt'},
+        ),
+    ],
+)
+async def test_file_message_uses_available_file_source(component, expected):
+    segment = await _convert_single(component)
+
+    assert segment.type == 'file'
+    assert segment.data == expected
+
+
+@pytest.mark.asyncio
+async def test_forward_image_base64_payload_is_normalized():
+    forward = platform_message.Forward(
+        node_list=[
+            platform_message.ForwardMessageNode(
+                sender_id='10001',
+                sender_name='Tester',
+                message_chain=platform_message.MessageChain(
+                    [platform_message.Image(base64='data:image/png;base64,raw-forward-image')]
+                ),
+            )
+        ]
+    )
+    messages = []
+
+    class Logger:
+        async def info(self, _message):
+            return None
+
+        async def error(self, _message):
+            return None
+
+    class Bot:
+        async def call_action(self, action, **kwargs):
+            assert action == 'send_forward_msg'
+            messages.append(kwargs)
+
+    platform = AiocqhttpAdapter.model_construct(
+        bot_account_id='10000',
+        config={},
+        logger=Logger(),
+        bot=Bot(),
+    )
+
+    await platform._send_forward_message(1000, forward)
+
+    assert messages[0]['messages'][0]['data']['content'][0] == {
+        'type': 'image',
+        'data': {'file': 'base64://raw-forward-image'},
+    }