add uniform processors for altclip + chinese_clip (#31198)

* add initial design for uniform processors + align model

* add uniform processors for altclip + chinese_clip

* fix mutable default 👀

* add configuration test

* handle structured kwargs w defaults + add test

* protect torch-specific test

* fix style

* fix

* rebase

* update processor to generic kwargs + test

* fix style

* add sensible kwargs merge

* update test

* fix assertEqual

* move kwargs merging to processing common

* rework kwargs for type hinting

* just get Unpack from extensions

* run-slow[align]

* handle kwargs passed as nested dict

* add from_pretrained test for nested kwargs handling

* [run-slow]align

* update documentation + imports

* update audio inputs

* protect audio types, silly

* try removing imports

* make things simpler

* simplerer

* move out kwargs test to common mixin

* [run-slow]align

* skip tests for old processors

* [run-slow]align, clip

* !$#@!! protect imports, darn it

* [run-slow]align, clip

* [run-slow]align, clip

* update common processor testing

* add altclip

* add chinese_clip

* add pad_size

* [run-slow]align, clip, chinese_clip, altclip

* remove duplicated tests

* fix

* update doc

* improve documentation for default values

* add model_max_length testing

This parameter depends on tokenizers received.

* Raise if kwargs are specified in two places

* fix

* match defaults

* force padding

* fix tokenizer test

* clean defaults

* move tests to common

* remove try/catch block

* deprecate kwarg

* format

* add copyright + remove unused method

* [run-slow]altclip, chinese_clip

* clean imports

* fix version

* clean up deprecation

* fix style

* add corner case test on kwarg overlap

* resume processing - add Unpack as importable

* add tmpdirname

* fix altclip

* fix up

* add back crop_size to specific tests

* generalize tests to possible video_processor

* add back crop_size arg

* fixup overlapping kwargs test for qformer_tokenizer

* remove copied from

* fixup chinese_clip tests values

* fixup tests - qformer tokenizers

* [run-slow] altclip, chinese_clip

* remove prepare_image_inputs

tests/models/chinese_clip/test_processor_chinese_clip.py

@@ -206,3 +206,129 @@ class ChineseCLIPProcessorTest(ProcessorTesterMixin, unittest.TestCase):
         inputs = processor(text=input_str, images=image_input)
 
         self.assertListEqual(list(inputs.keys()), processor.model_input_names)
+
+    def test_unstructured_kwargs_batched(self):
+        if "image_processor" not in self.processor_class.attributes:
+            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
+        image_processor = self.get_component("image_processor")
+        tokenizer = self.get_component("tokenizer")
+
+        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
+        self.skip_processor_without_typed_kwargs(processor)
+
+        input_str = ["lower newer", "upper older longer string"]
+        image_input = self.prepare_image_inputs() * 2
+        inputs = processor(
+            text=input_str,
+            images=image_input,
+            return_tensors="pt",
+            crop_size={"height": 214, "width": 214},
+            padding="longest",
+            max_length=76,
+        )
+        self.assertEqual(inputs["pixel_values"].shape[2], 214)
+
+        self.assertEqual(len(inputs["input_ids"][0]), 6)
+
+    def test_structured_kwargs_nested(self):
+        if "image_processor" not in self.processor_class.attributes:
+            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
+        image_processor = self.get_component("image_processor")
+        tokenizer = self.get_component("tokenizer")
+
+        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
+        self.skip_processor_without_typed_kwargs(processor)
+
+        input_str = "lower newer"
+        image_input = self.prepare_image_inputs()
+
+        # Define the kwargs for each modality
+        all_kwargs = {
+            "common_kwargs": {"return_tensors": "pt"},
+            "images_kwargs": {"crop_size": {"height": 214, "width": 214}},
+            "text_kwargs": {"padding": "max_length", "max_length": 76},
+        }
+
+        inputs = processor(text=input_str, images=image_input, **all_kwargs)
+        self.skip_processor_without_typed_kwargs(processor)
+
+        self.assertEqual(inputs["pixel_values"].shape[2], 214)
+
+        self.assertEqual(len(inputs["input_ids"][0]), 76)
+
+    def test_structured_kwargs_nested_from_dict(self):
+        if "image_processor" not in self.processor_class.attributes:
+            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
+
+        image_processor = self.get_component("image_processor")
+        tokenizer = self.get_component("tokenizer")
+
+        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
+        self.skip_processor_without_typed_kwargs(processor)
+        input_str = "lower newer"
+        image_input = self.prepare_image_inputs()
+
+        # Define the kwargs for each modality
+        all_kwargs = {
+            "common_kwargs": {"return_tensors": "pt"},
+            "images_kwargs": {"crop_size": {"height": 214, "width": 214}},
+            "text_kwargs": {"padding": "max_length", "max_length": 76},
+        }
+
+        inputs = processor(text=input_str, images=image_input, **all_kwargs)
+        self.assertEqual(inputs["pixel_values"].shape[2], 214)
+
+        self.assertEqual(len(inputs["input_ids"][0]), 76)
+
+    def test_unstructured_kwargs(self):
+        if "image_processor" not in self.processor_class.attributes:
+            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
+        image_processor = self.get_component("image_processor")
+        tokenizer = self.get_component("tokenizer")
+
+        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
+        self.skip_processor_without_typed_kwargs(processor)
+
+        input_str = "lower newer"
+        image_input = self.prepare_image_inputs()
+        inputs = processor(
+            text=input_str,
+            images=image_input,
+            return_tensors="pt",
+            crop_size={"height": 214, "width": 214},
+            padding="max_length",
+            max_length=76,
+        )
+
+        self.assertEqual(inputs["pixel_values"].shape[2], 214)
+        self.assertEqual(len(inputs["input_ids"][0]), 76)
+
+    def test_image_processor_defaults_preserved_by_image_kwargs(self):
+        if "image_processor" not in self.processor_class.attributes:
+            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
+        image_processor = self.get_component("image_processor", crop_size=(234, 234))
+        tokenizer = self.get_component("tokenizer", max_length=117, padding="max_length")
+
+        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
+        self.skip_processor_without_typed_kwargs(processor)
+
+        input_str = "lower newer"
+        image_input = self.prepare_image_inputs()
+
+        inputs = processor(text=input_str, images=image_input)
+        self.assertEqual(len(inputs["pixel_values"][0][0]), 234)
+
+    def test_kwargs_overrides_default_image_processor_kwargs(self):
+        if "image_processor" not in self.processor_class.attributes:
+            self.skipTest(f"image_processor attribute not present in {self.processor_class}")
+        image_processor = self.get_component("image_processor", crop_size=(234, 234))
+        tokenizer = self.get_component("tokenizer", max_length=117, padding="max_length")
+
+        processor = self.processor_class(tokenizer=tokenizer, image_processor=image_processor)
+        self.skip_processor_without_typed_kwargs(processor)
+
+        input_str = "lower newer"
+        image_input = self.prepare_image_inputs()
+
+        inputs = processor(text=input_str, images=image_input, crop_size=[224, 224])
+        self.assertEqual(len(inputs["pixel_values"][0][0]), 224)