pyautoscene 0.1.0__tar.gz → 0.2.0__tar.gz

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/.gitignore

@@ -9,4 +9,7 @@ wheels/
 # Virtual environments
 .venv
 
+# Environment variables
+.env
+
 explore/

pyautoscene-0.2.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/PKG-INFO

@@ -1,15 +1,14 @@
 Metadata-Version: 2.4
 Name: pyautoscene
-Version: 0.1.0
+Version: 0.2.0
 Summary: Advance GUI automation
 Author-email: pritam-dey3 <pritam.pritamdey.984@gmail.com>
+License-File: LICENSE
 Requires-Python: >=3.13
 Requires-Dist: networkx>=3.5
-Requires-Dist: onnxruntime>=1.22.0
 Requires-Dist: pillow>=11.3.0
 Requires-Dist: pyautogui>=0.9.54
 Requires-Dist: python-statemachine[diagrams]
-Requires-Dist: rapidocr>=3.2.0
 Description-Content-Type: text/markdown
 
 # PyAutoScene
@@ -21,7 +20,8 @@ PyAutoScene is a Python library that provides a declarative approach to GUI auto
 ## 🌟 Features
 
 - **Scene-Based Architecture**: Model your application as a collection of scenes with defined elements and transitions
-- **Visual Element Detection**: Supports both image-based element recognition. (Text recognition support coming soon!)
+- **Visual Element Detection**: Supports both image-based and text-based element recognition
+- **Region Specification**: Flexible region syntax for targeting specific screen areas
 - **Automatic Navigation**: Intelligent pathfinding between scenes using graph algorithms
 - **Action Decorators**: Clean, declarative syntax for defining scene actions and transitions
 
@@ -39,15 +39,15 @@ Here's how to automate a simple login flow:
 
 ```python
 import pyautogui as gui
-from pyautoscene import ReferenceImage, ReferenceText, Scene, Session
+from pyautoscene import ImageElement, TextElement, Scene, Session
 from pyautoscene.utils import locate_and_click
 
 # Define scenes
 login = Scene(
     "Login",
     elements=[
-        ReferenceText("Welcome to Login"),
-        ReferenceImage("references/login_button.png"),
+        TextElement("Welcome to Login"),
+        ImageElement("references/login_button.png"),
     ],
     initial=True,
 )
@@ -55,8 +55,8 @@ login = Scene(
 dashboard = Scene(
     "Dashboard",
     elements=[
-        ReferenceText("Dashboard"),
-        ReferenceImage("references/user_menu.png"),
+        TextElement("Dashboard"),
+        ImageElement("references/user_menu.png"),
     ],
 )
 
@@ -89,8 +89,8 @@ A **Scene** represents a distinct state in your application's UI. Each scene con
 scene = Scene(
     "SceneName",
     elements=[
-        ReferenceImage("path/to/image.png"),
-        ReferenceText("Expected Text"),
+        ImageElement("path/to/image.png"),
+        TextElement("Expected Text"),
     ],
     initial=False  # Set to True for starting scene
 )
@@ -100,20 +100,33 @@ scene = Scene(
 
 PyAutoScene supports two types of reference elements:
 
-#### ReferenceImage
+#### ImageElement
 
 Detects scenes using image matching:
 
 ```python
-ReferenceImage("path/to/reference/image.png")
+ImageElement("path/to/reference/image.png")
 ```
 
-#### ReferenceText
-(Coming soon)
+#### TextElement
+
 Detects scenes using text recognition:
 
 ```python
-ReferenceText("Expected text on screen")
+TextElement("Expected text on screen")
+```
+
+Both elements support region specification for limiting search areas. You can specify regions using a string format like `"x:2/3 y:(1-2)/3"` to easily define screen regions:
+
+```python
+# Search for text in the top-left third of the screen
+TextElement("Login", region="x:1/3 y:1/3")
+
+# Search in a horizontal band across the middle third of the screen
+ImageElement("button.png", region="y:2/3")
+
+# Search in a specific area spanning columns 1-2 out of 3 columns
+TextElement("Welcome", region="x:(1-2)/3 y:1/3")
 ```
 
 ### Actions and Transitions
@@ -194,7 +207,15 @@ This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENS
 
 ## 🔮 Roadmap
 
-- [ ] Text recognition implementation
 - [ ] Enhanced image matching algorithms
+- [ ] TemplateScene
+- [ ] Relation between images
 - [ ] Multiple session support
 
+## 🙏 Credits
+
+PyAutoScene builds on the work of several open-source projects:
+
+- [PyAutoGUI](https://github.com/asweigart/pyautogui) by Al Sweigart
+- [python-statemachine](https://github.com/fgmacedo/python-statemachine) by Filipe Macedo
+- [RapidOCR](https://github.com/RapidAI/RapidOCR) by RapidAI contributors

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/README.md

@@ -7,7 +7,8 @@ PyAutoScene is a Python library that provides a declarative approach to GUI auto
 ## 🌟 Features
 
 - **Scene-Based Architecture**: Model your application as a collection of scenes with defined elements and transitions
-- **Visual Element Detection**: Supports both image-based element recognition. (Text recognition support coming soon!)
+- **Visual Element Detection**: Supports both image-based and text-based element recognition
+- **Region Specification**: Flexible region syntax for targeting specific screen areas
 - **Automatic Navigation**: Intelligent pathfinding between scenes using graph algorithms
 - **Action Decorators**: Clean, declarative syntax for defining scene actions and transitions
 
@@ -25,15 +26,15 @@ Here's how to automate a simple login flow:
 
 ```python
 import pyautogui as gui
-from pyautoscene import ReferenceImage, ReferenceText, Scene, Session
+from pyautoscene import ImageElement, TextElement, Scene, Session
 from pyautoscene.utils import locate_and_click
 
 # Define scenes
 login = Scene(
     "Login",
     elements=[
-        ReferenceText("Welcome to Login"),
-        ReferenceImage("references/login_button.png"),
+        TextElement("Welcome to Login"),
+        ImageElement("references/login_button.png"),
     ],
     initial=True,
 )
@@ -41,8 +42,8 @@ login = Scene(
 dashboard = Scene(
     "Dashboard",
     elements=[
-        ReferenceText("Dashboard"),
-        ReferenceImage("references/user_menu.png"),
+        TextElement("Dashboard"),
+        ImageElement("references/user_menu.png"),
     ],
 )
 
@@ -75,8 +76,8 @@ A **Scene** represents a distinct state in your application's UI. Each scene con
 scene = Scene(
     "SceneName",
     elements=[
-        ReferenceImage("path/to/image.png"),
-        ReferenceText("Expected Text"),
+        ImageElement("path/to/image.png"),
+        TextElement("Expected Text"),
     ],
     initial=False  # Set to True for starting scene
 )
@@ -86,20 +87,33 @@ scene = Scene(
 
 PyAutoScene supports two types of reference elements:
 
-#### ReferenceImage
+#### ImageElement
 
 Detects scenes using image matching:
 
 ```python
-ReferenceImage("path/to/reference/image.png")
+ImageElement("path/to/reference/image.png")
 ```
 
-#### ReferenceText
-(Coming soon)
+#### TextElement
+
 Detects scenes using text recognition:
 
 ```python
-ReferenceText("Expected text on screen")
+TextElement("Expected text on screen")
+```
+
+Both elements support region specification for limiting search areas. You can specify regions using a string format like `"x:2/3 y:(1-2)/3"` to easily define screen regions:
+
+```python
+# Search for text in the top-left third of the screen
+TextElement("Login", region="x:1/3 y:1/3")
+
+# Search in a horizontal band across the middle third of the screen
+ImageElement("button.png", region="y:2/3")
+
+# Search in a specific area spanning columns 1-2 out of 3 columns
+TextElement("Welcome", region="x:(1-2)/3 y:1/3")
 ```
 
 ### Actions and Transitions
@@ -180,7 +194,15 @@ This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENS
 
 ## 🔮 Roadmap
 
-- [ ] Text recognition implementation
 - [ ] Enhanced image matching algorithms
+- [ ] TemplateScene
+- [ ] Relation between images
 - [ ] Multiple session support
 
+## 🙏 Credits
+
+PyAutoScene builds on the work of several open-source projects:
+
+- [PyAutoGUI](https://github.com/asweigart/pyautogui) by Al Sweigart
+- [python-statemachine](https://github.com/fgmacedo/python-statemachine) by Filipe Macedo
+- [RapidOCR](https://github.com/RapidAI/RapidOCR) by RapidAI contributors

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/examples/saucedemo/main.py

@@ -1,13 +1,14 @@
 import pyautogui as gui
 
-from pyautoscene import ReferenceImage, ReferenceText, Scene, Session
+from pyautoscene import ImageElement, Scene, Session, TextElement
 from pyautoscene.utils import locate_and_click
 
 login = Scene(
     "Login",
     elements=[
-        ReferenceText("Welcome to Login"),
-        ReferenceImage("examples/saucedemo/references/login_button.png"),
+        TextElement("Username", region="x-1/3 y-(1-2)/3"),
+        TextElement("Password", region="x-1/3 y-(2-3)/3"),
+        # ReferenceImage("examples/saucedemo/references/login_button.png"),
     ],
     initial=True,
 )
@@ -15,17 +16,16 @@ login = Scene(
 dashboard = Scene(
     "Dashboard",
     elements=[
-        ReferenceText("Swag Labs"),
-        ReferenceText("Products"),
-        ReferenceImage("examples/saucedemo/references/cart_icon.png"),
+        TextElement("Swag Labs", region="x-2/3 y-1/3"),
+        TextElement("Products", region="x-1/3 y-1/3"),
     ],
 )
 
 cart = Scene(
     "Cart",
     elements=[
-        ReferenceText("Your Cart"),
-        ReferenceImage("examples/saucedemo/references/cart_icon.png"),
+        TextElement("Your Cart", region="x-1/3 y-1/3"),
+        ImageElement("examples/saucedemo/references/cart_icon.png"),
     ],
 )
 

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/examples/saucedemo/manual_flow.py

@@ -1,13 +1,13 @@
 import pyautogui as gui
 
-from pyautoscene import ReferenceImage, ReferenceText, Scene, Session
+from pyautoscene import ImageElement, Scene, Session, TextElement
 from pyautoscene.utils import locate_and_click
 
 login = Scene(
     "Login",
     elements=[
-        ReferenceText("Welcome to Login"),
-        ReferenceImage("examples/saucedemo/references/login_button.png"),
+        TextElement("Welcome to Login"),
+        ImageElement("examples/saucedemo/references/login_button.png"),
     ],
     initial=True,
 )
@@ -15,17 +15,17 @@ login = Scene(
 dashboard = Scene(
     "Dashboard",
     elements=[
-        ReferenceText("Swag Labs"),
-        ReferenceText("Products"),
-        ReferenceImage("examples/saucedemo/references/cart_icon.png"),
+        TextElement("Swag Labs"),
+        TextElement("Products"),
+        ImageElement("examples/saucedemo/references/cart_icon.png"),
     ],
 )
 
 cart = Scene(
     "Cart",
     elements=[
-        ReferenceText("Your Cart"),
-        ReferenceImage("examples/saucedemo/references/cart_icon.png"),
+        TextElement("Your Cart"),
+        ImageElement("examples/saucedemo/references/cart_icon.png"),
     ],
 )
 

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/pyproject.toml

@@ -4,17 +4,15 @@ authors = [
 ]
 dependencies = [
   "networkx>=3.5",
-  "onnxruntime>=1.22.0",
   "pillow>=11.3.0",
   "pyautogui>=0.9.54",
   "python-statemachine[diagrams]",
-  "rapidocr>=3.2.0",
 ]
 description = "Advance GUI automation"
 name = "pyautoscene"
 readme = "README.md"
 requires-python = ">=3.13"
-version = "0.1.0"
+version = "0.2.0"
 
 [project.scripts]
 pyautoscene = "pyautoscene:main"
@@ -28,9 +26,17 @@ python-statemachine = {git = "https://github.com/fgmacedo/python-statemachine.gi
 
 [dependency-groups]
 dev = [
-    "pre-commit>=4.2.0",
-    "types-networkx>=3.5.0.20250712",
+  "pre-commit>=4.2.0",
+  "types-networkx>=3.5.0.20250712",
+]
+ocr = [
+  "rapidocr>=3.2.0",
+  "onnxruntime>=1.22.0",
+]
+opencv = [
+  "opencv-python-headless>=4.12.0.88",
 ]
 
 [tool.poe.tasks]
 precmt = "pre-commit run --all-files"
+

pyautoscene-0.2.0/src/pyautoscene/__init__.py

@@ -0,0 +1,5 @@
+from .references import ImageElement, TextElement
+from .scene import Scene
+from .session import Session
+
+__all__ = ["Scene", "Session", "ImageElement", "TextElement"]

pyautoscene-0.2.0/src/pyautoscene/ocr.py

@@ -0,0 +1,70 @@
+import logging
+from hashlib import sha256
+from pathlib import Path
+
+import numpy as np
+from PIL import Image
+
+from .screen import Region
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+try:
+    from rapidocr import RapidOCR
+    from rapidocr.utils.output import RapidOCROutput
+except ImportError:
+    raise ImportError(
+        "RapidOCR is not installed. Please install it using 'pip install pyautoscene[ocr]'."
+    )
+
+ocr_config_path = Path(__file__).parent / "ocr_config.yaml"
+
+
+def hash_image(img: Image.Image) -> str:
+    return sha256(img.tobytes()).hexdigest()
+
+
+def convert_points_to_ltwh(points: np.ndarray) -> Region:
+    if points.shape[0] == 0:
+        raise ValueError("Points array is empty")
+
+    x_min = np.min(points[:, 0])
+    y_min = np.min(points[:, 1])
+    x_max = np.max(points[:, 0])
+    y_max = np.max(points[:, 1])
+
+    return Region(left=x_min, top=y_min, width=x_max - x_min, height=y_max - y_min)
+
+
+class OCR:
+    engine: RapidOCR | None = None
+    img_cache: dict[str, tuple[tuple[str, Region], ...]] = {}
+
+    def __new__(cls):
+        if cls.engine is None:
+            cls.engine = RapidOCR(config_path=ocr_config_path.as_posix())
+        return super().__new__(cls)
+
+    def recognize_text(self, img: Image.Image) -> tuple[tuple[str, Region], ...]:
+        img_gray = img.convert("L")
+        img_hash = hash_image(img_gray)
+        if img_hash in self.img_cache:
+            logger.debug(f"Using cached result for image hash: {img_hash}")
+            return self.img_cache[img_hash]
+
+        assert self.engine is not None, "Engine should be initialized in __new__"
+        result = self.engine(np.array(img_gray))
+        assert isinstance(result, RapidOCROutput), (
+            "Result should be of type RapidOCROutput"
+        )
+        assert result.txts is not None and result.boxes is not None, (
+            "Text recognition failed, txts and boxes should not be None"
+        )
+
+        detections = tuple(
+            (txt, convert_points_to_ltwh(box))
+            for txt, box in zip(result.txts, result.boxes)
+        )
+        self.img_cache[img_hash] = detections
+        return detections

pyautoscene-0.2.0/src/pyautoscene/ocr_config.yaml

@@ -0,0 +1,112 @@
+Global:
+    text_score: 0.5
+
+    use_det: true
+    use_cls: false
+    use_angle_cls: false
+    use_rec: true
+
+    min_height: 30
+    width_height_ratio: 8
+    max_side_len: 2000
+    min_side_len: 30
+
+    return_word_box: false
+    return_single_char_box: false
+
+    font_path: null
+
+EngineConfig:
+    onnxruntime:
+        intra_op_num_threads: -1
+        inter_op_num_threads: -1
+        enable_cpu_mem_arena: false
+
+        cpu_ep_cfg:
+            arena_extend_strategy: "kSameAsRequested"
+
+        use_cuda: false
+        cuda_ep_cfg:
+            device_id: 0
+            arena_extend_strategy: "kNextPowerOfTwo"
+            cudnn_conv_algo_search: "EXHAUSTIVE"
+            do_copy_in_default_stream: true
+
+        use_dml: false
+        dm_ep_cfg: null
+
+        use_cann: false
+        cann_ep_cfg:
+            device_id: 0
+            arena_extend_strategy: "kNextPowerOfTwo"
+            npu_mem_limit:  21474836480 # 20 * 1024 * 1024 * 1024
+            op_select_impl_mode: "high_performance"
+            optypelist_for_implmode: "Gelu"
+            enable_cann_graph: true
+
+    openvino:
+        inference_num_threads: -1
+
+    paddle:
+        cpu_math_library_num_threads: -1
+        use_cuda: false
+        gpu_id: 0
+        gpu_mem: 500
+
+    torch:
+        use_cuda: false
+        gpu_id: 0
+
+Det:
+    engine_type: "onnxruntime"
+    lang_type: "en"
+    model_type: "mobile"
+    ocr_version: "PP-OCRv4"
+
+    task_type: "det"
+
+    model_path: null
+    model_dir: null
+
+    limit_side_len: 736
+    limit_type: min
+    std: [ 0.5, 0.5, 0.5 ]
+    mean: [ 0.5, 0.5, 0.5 ]
+
+    thresh: 0.3
+    box_thresh: 0.5
+    max_candidates: 1000
+    unclip_ratio: 1.6
+    use_dilation: true
+    score_mode: fast
+
+Cls:
+    engine_type: "onnxruntime"
+    lang_type: "ch"
+    model_type: "mobile"
+    ocr_version: "PP-OCRv4"
+
+    task_type: "cls"
+
+    model_path: null
+    model_dir: null
+
+    cls_image_shape: [3, 48, 192]
+    cls_batch_num: 6
+    cls_thresh: 0.9
+    label_list: ["0", "180"]
+
+Rec:
+    engine_type: "onnxruntime"
+    lang_type: "en"
+    model_type: "mobile"
+    ocr_version: "PP-OCRv4"
+
+    task_type: "rec"
+
+    model_path: null
+    model_dir: null
+
+    rec_keys_path: null
+    rec_img_shape: [3, 48, 320]
+    rec_batch_num: 6

pyautoscene-0.2.0/src/pyautoscene/references.py

@@ -0,0 +1,78 @@
+from abc import ABC, abstractmethod
+from typing import override
+
+import pyautogui as gui
+
+from .screen import RegionSpec, generate_region_from_spec, locate_on_screen
+
+
+class ReferenceElement(ABC):
+    """Base class for reference elements used to identify scenes."""
+
+    @abstractmethod
+    def is_visible(self, region: RegionSpec | None = None) -> RegionSpec | None:
+        """Detect the presence of the reference element."""
+        raise NotImplementedError("Subclasses must implement this method")
+
+
+class ImageElement(ReferenceElement):
+    """Reference element that identifies a scene by an image."""
+
+    def __init__(
+        self,
+        path: str | list[str],
+        confidence: float = 0.999,
+        region: RegionSpec | None = None,
+    ):
+        self.path = path
+        self.confidence = confidence
+        self.region = region
+
+    @override
+    def is_visible(self, region: RegionSpec | None = None):
+        """Method to detect the presence of the image in the current screen."""
+        if isinstance(self.path, str):
+            path = [self.path]  # Ensure path is a list for consistency
+        else:
+            path = self.path
+        for image_path in path:
+            try:
+                location = locate_on_screen(
+                    image_path, region=region or self.region, confidence=self.confidence
+                )
+                return location
+            except gui.ImageNotFoundException:
+                continue
+
+
+class TextElement(ReferenceElement):
+    """Reference element that identifies a scene by text."""
+
+    def __init__(
+        self,
+        text: str,
+        region: RegionSpec | None = None,
+        case_sensitive: bool = False,
+    ):
+        self.text = text
+        self.region = region
+        self.case_sensitive = case_sensitive
+        if not case_sensitive:
+            self.text = self.text.lower()
+
+    def is_visible(self, region: RegionSpec | None = None):
+        """Method to detect the presence of the text in the current screen."""
+        from .ocr import OCR
+
+        ocr = OCR()
+        region = region or self.region
+        for text, detected_region in ocr.recognize_text(
+            gui.screenshot(
+                region=generate_region_from_spec(region).to_box() if region else None
+            )
+        ):
+            if not self.case_sensitive:
+                text = text.lower()
+            if text.strip() == self.text.strip():
+                return detected_region
+        return None

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/src/pyautoscene/scene.py

@@ -2,12 +2,12 @@ from __future__ import annotations
 
 from typing import Callable, TypedDict
 
-from pyscreeze import Box
 from statemachine import State
 
 from pyautoscene.utils import is_valid_variable_name
 
-from .references import ReferenceElement, ReferenceImage
+from .references import ReferenceElement
+from .screen import Region
 
 
 class ActionInfo(TypedDict):
@@ -51,11 +51,11 @@ class Scene(State):
         """Get an action by name."""
         return self.actions.get(action_name)
 
-    def is_on_screen(self, region: Box | None = None) -> bool:
+    def is_on_screen(self, region: Region | None = None) -> bool:
         """Check if any reference element is currently on screen."""
         # TODO: Refactor after text recognition is implemented
-        elements = (elem for elem in self.elements if isinstance(elem, ReferenceImage))
-        return all(elem.is_visible(region) for elem in elements)
+        # elements = (elem for elem in self.elements if isinstance(elem, ReferenceImage))
+        return all(elem.is_visible(region) for elem in self.elements)
 
     def __repr__(self):
         return f"Scene({self.name!r}, elements={len(self.elements)})"

pyautoscene-0.2.0/src/pyautoscene/screen.py

@@ -0,0 +1,79 @@
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+
+import numpy as np
+import pyautogui as gui
+from PIL import Image
+from pyscreeze import Box
+
+axis_pattern = re.compile(r"(?P<d>[xy]):\(?(?P<i>\d+)(?:-(?P<j>\d+))?\)?/(?P<n>\d+)")
+
+
+@dataclass(frozen=True, slots=True)
+class Region:
+    left: int
+    top: int
+    width: int
+    height: int
+
+    def to_box(self) -> Box:
+        """Convert to a pyscreeze Box."""
+        return Box(self.left, self.top, self.width, self.height)
+
+    @classmethod
+    def from_box(cls, box: Box) -> Region:
+        """Create a Region from a pyscreeze Box."""
+        return cls(left=box.left, top=box.top, width=box.width, height=box.height)
+
+
+RegionSpec = Region | str
+
+
+def generate_region_from_spec(
+    spec: RegionSpec, shape: tuple[int, int] | None = None
+) -> Region:
+    if isinstance(spec, Region):
+        return spec
+    if shape is None:
+        img = np.array(gui.screenshot())
+        shape = (img.shape[0]), (img.shape[1])
+
+    default_region = {"left": 0, "top": 0, "width": shape[1], "height": shape[0]}
+
+    axis_mapping = {"x": ("left", "width", 1), "y": ("top", "height", 0)}
+    for axis, i, j, n in axis_pattern.findall(spec):
+        alignment, size_attr, dim_index = axis_mapping[axis]
+        size = shape[dim_index] // int(n)
+        i, j = int(i), int(j) if j else int(i)
+        default_region.update({
+            alignment: (i - 1) * size,
+            size_attr: (j - i + 1) * size,
+        })
+
+    return Region(**default_region)
+
+
+def locate_on_screen(
+    reference: Image.Image | str,
+    region: RegionSpec | None = None,
+    confidence: float = 0.999,
+    grayscale: bool = True,
+    limit: int = 1,
+) -> Region | None:
+    """Locate a region on the screen."""
+    try:
+        location = gui.locateOnScreen(
+            reference,
+            region=generate_region_from_spec(region).to_box() if region else None,
+            grayscale=grayscale,
+            confidence=confidence,
+            limit=limit,
+        )
+        if location:
+            return Region.from_box(location)
+    except gui.ImageNotFoundException:
+        return None
+    except FileNotFoundError:
+        return None

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/src/pyautoscene/session.py

@@ -3,13 +3,13 @@ from __future__ import annotations
 from typing import Callable
 
 import networkx as nx
-from pyscreeze import Box
 from statemachine import State, StateMachine
 from statemachine.factory import StateMachineMetaclass
 from statemachine.states import States
 from statemachine.transition_list import TransitionList
 
 from .scene import Scene
+from .screen import Region
 
 
 class SceneRecognitionError(Exception):
@@ -45,7 +45,7 @@ def build_dynamic_state_machine(
     return session_sm, transitions, leaf_actions
 
 
-def get_current_scene(scenes: list[Scene], region: Box | None = None) -> Scene:
+def get_current_scene(scenes: list[Scene], region: Region | None = None) -> Scene:
     """Get the current scene from the list of scenes."""
     current_scenes = [scene for scene in scenes if scene.is_on_screen(region)]
     if len(current_scenes) == 1:

{pyautoscene-0.1.0 → pyautoscene-0.2.0}/uv.lock

@@ -183,32 +183,30 @@ wheels = [
 
 [[package]]
 name = "numpy"
-version = "2.3.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/2e/19/d7c972dfe90a353dbd3efbbe1d14a5951de80c99c9dc1b93cd998d51dc0f/numpy-2.3.1.tar.gz", hash = "sha256:1ec9ae20a4226da374362cca3c62cd753faf2f951440b0e3b98e93c235441d2b", size = 20390372, upload-time = "2025-06-21T12:28:33.469Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/d4/bd/35ad97006d8abff8631293f8ea6adf07b0108ce6fec68da3c3fcca1197f2/numpy-2.3.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:25a1992b0a3fdcdaec9f552ef10d8103186f5397ab45e2d25f8ac51b1a6b97e8", size = 20889381, upload-time = "2025-06-21T12:19:04.103Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/4f/df5923874d8095b6062495b39729178eef4a922119cee32a12ee1bd4664c/numpy-2.3.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:7dea630156d39b02a63c18f508f85010230409db5b2927ba59c8ba4ab3e8272e", size = 14152726, upload-time = "2025-06-21T12:19:25.599Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/0f/a1f269b125806212a876f7efb049b06c6f8772cf0121139f97774cd95626/numpy-2.3.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:bada6058dd886061f10ea15f230ccf7dfff40572e99fef440a4a857c8728c9c0", size = 5105145, upload-time = "2025-06-21T12:19:34.782Z" },
-    { url = "https://files.pythonhosted.org/packages/6d/63/a7f7fd5f375b0361682f6ffbf686787e82b7bbd561268e4f30afad2bb3c0/numpy-2.3.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:a894f3816eb17b29e4783e5873f92faf55b710c2519e5c351767c51f79d8526d", size = 6639409, upload-time = "2025-06-21T12:19:45.228Z" },
-    { url = "https://files.pythonhosted.org/packages/bf/0d/1854a4121af895aab383f4aa233748f1df4671ef331d898e32426756a8a6/numpy-2.3.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:18703df6c4a4fee55fd3d6e5a253d01c5d33a295409b03fda0c86b3ca2ff41a1", size = 14257630, upload-time = "2025-06-21T12:20:06.544Z" },
-    { url = "https://files.pythonhosted.org/packages/50/30/af1b277b443f2fb08acf1c55ce9d68ee540043f158630d62cef012750f9f/numpy-2.3.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:5902660491bd7a48b2ec16c23ccb9124b8abfd9583c5fdfa123fe6b421e03de1", size = 16627546, upload-time = "2025-06-21T12:20:31.002Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/ec/3b68220c277e463095342d254c61be8144c31208db18d3fd8ef02712bcd6/numpy-2.3.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:36890eb9e9d2081137bd78d29050ba63b8dab95dff7912eadf1185e80074b2a0", size = 15562538, upload-time = "2025-06-21T12:20:54.322Z" },
-    { url = "https://files.pythonhosted.org/packages/77/2b/4014f2bcc4404484021c74d4c5ee8eb3de7e3f7ac75f06672f8dcf85140a/numpy-2.3.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a780033466159c2270531e2b8ac063704592a0bc62ec4a1b991c7c40705eb0e8", size = 18360327, upload-time = "2025-06-21T12:21:21.053Z" },
-    { url = "https://files.pythonhosted.org/packages/40/8d/2ddd6c9b30fcf920837b8672f6c65590c7d92e43084c25fc65edc22e93ca/numpy-2.3.1-cp313-cp313-win32.whl", hash = "sha256:39bff12c076812595c3a306f22bfe49919c5513aa1e0e70fac756a0be7c2a2b8", size = 6312330, upload-time = "2025-06-21T12:25:07.447Z" },
-    { url = "https://files.pythonhosted.org/packages/dd/c8/beaba449925988d415efccb45bf977ff8327a02f655090627318f6398c7b/numpy-2.3.1-cp313-cp313-win_amd64.whl", hash = "sha256:8d5ee6eec45f08ce507a6570e06f2f879b374a552087a4179ea7838edbcbfa42", size = 12731565, upload-time = "2025-06-21T12:25:26.444Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/c3/5c0c575d7ec78c1126998071f58facfc124006635da75b090805e642c62e/numpy-2.3.1-cp313-cp313-win_arm64.whl", hash = "sha256:0c4d9e0a8368db90f93bd192bfa771ace63137c3488d198ee21dfb8e7771916e", size = 10190262, upload-time = "2025-06-21T12:25:42.196Z" },
-    { url = "https://files.pythonhosted.org/packages/ea/19/a029cd335cf72f79d2644dcfc22d90f09caa86265cbbde3b5702ccef6890/numpy-2.3.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:b0b5397374f32ec0649dd98c652a1798192042e715df918c20672c62fb52d4b8", size = 20987593, upload-time = "2025-06-21T12:21:51.664Z" },
-    { url = "https://files.pythonhosted.org/packages/25/91/8ea8894406209107d9ce19b66314194675d31761fe2cb3c84fe2eeae2f37/numpy-2.3.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:c5bdf2015ccfcee8253fb8be695516ac4457c743473a43290fd36eba6a1777eb", size = 14300523, upload-time = "2025-06-21T12:22:13.583Z" },
-    { url = "https://files.pythonhosted.org/packages/a6/7f/06187b0066eefc9e7ce77d5f2ddb4e314a55220ad62dd0bfc9f2c44bac14/numpy-2.3.1-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:d70f20df7f08b90a2062c1f07737dd340adccf2068d0f1b9b3d56e2038979fee", size = 5227993, upload-time = "2025-06-21T12:22:22.53Z" },
-    { url = "https://files.pythonhosted.org/packages/e8/ec/a926c293c605fa75e9cfb09f1e4840098ed46d2edaa6e2152ee35dc01ed3/numpy-2.3.1-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:2fb86b7e58f9ac50e1e9dd1290154107e47d1eef23a0ae9145ded06ea606f992", size = 6736652, upload-time = "2025-06-21T12:22:33.629Z" },
-    { url = "https://files.pythonhosted.org/packages/e3/62/d68e52fb6fde5586650d4c0ce0b05ff3a48ad4df4ffd1b8866479d1d671d/numpy-2.3.1-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:23ab05b2d241f76cb883ce8b9a93a680752fbfcbd51c50eff0b88b979e471d8c", size = 14331561, upload-time = "2025-06-21T12:22:55.056Z" },
-    { url = "https://files.pythonhosted.org/packages/fc/ec/b74d3f2430960044bdad6900d9f5edc2dc0fb8bf5a0be0f65287bf2cbe27/numpy-2.3.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:ce2ce9e5de4703a673e705183f64fd5da5bf36e7beddcb63a25ee2286e71ca48", size = 16693349, upload-time = "2025-06-21T12:23:20.53Z" },
-    { url = "https://files.pythonhosted.org/packages/0d/15/def96774b9d7eb198ddadfcbd20281b20ebb510580419197e225f5c55c3e/numpy-2.3.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:c4913079974eeb5c16ccfd2b1f09354b8fed7e0d6f2cab933104a09a6419b1ee", size = 15642053, upload-time = "2025-06-21T12:23:43.697Z" },
-    { url = "https://files.pythonhosted.org/packages/2b/57/c3203974762a759540c6ae71d0ea2341c1fa41d84e4971a8e76d7141678a/numpy-2.3.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:010ce9b4f00d5c036053ca684c77441f2f2c934fd23bee058b4d6f196efd8280", size = 18434184, upload-time = "2025-06-21T12:24:10.708Z" },
-    { url = "https://files.pythonhosted.org/packages/22/8a/ccdf201457ed8ac6245187850aff4ca56a79edbea4829f4e9f14d46fa9a5/numpy-2.3.1-cp313-cp313t-win32.whl", hash = "sha256:6269b9edfe32912584ec496d91b00b6d34282ca1d07eb10e82dfc780907d6c2e", size = 6440678, upload-time = "2025-06-21T12:24:21.596Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/7e/7f431d8bd8eb7e03d79294aed238b1b0b174b3148570d03a8a8a8f6a0da9/numpy-2.3.1-cp313-cp313t-win_amd64.whl", hash = "sha256:2a809637460e88a113e186e87f228d74ae2852a2e0c44de275263376f17b5bdc", size = 12870697, upload-time = "2025-06-21T12:24:40.644Z" },
-    { url = "https://files.pythonhosted.org/packages/d4/ca/af82bf0fad4c3e573c6930ed743b5308492ff19917c7caaf2f9b6f9e2e98/numpy-2.3.1-cp313-cp313t-win_arm64.whl", hash = "sha256:eccb9a159db9aed60800187bc47a6d3451553f0e1b08b068d8b277ddfbb9b244", size = 10260376, upload-time = "2025-06-21T12:24:56.884Z" },
+version = "2.2.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/76/21/7d2a95e4bba9dc13d043ee156a356c0a8f0c6309dff6b21b4d71a073b8a8/numpy-2.2.6.tar.gz", hash = "sha256:e29554e2bef54a90aa5cc07da6ce955accb83f21ab5de01a62c8478897b264fd", size = 20276440, upload-time = "2025-05-17T22:38:04.611Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f9/5c/6657823f4f594f72b5471f1db1ab12e26e890bb2e41897522d134d2a3e81/numpy-2.2.6-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0811bb762109d9708cca4d0b13c4f67146e3c3b7cf8d34018c722adb2d957c84", size = 20867828, upload-time = "2025-05-17T21:37:56.699Z" },
+    { url = "https://files.pythonhosted.org/packages/dc/9e/14520dc3dadf3c803473bd07e9b2bd1b69bc583cb2497b47000fed2fa92f/numpy-2.2.6-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:287cc3162b6f01463ccd86be154f284d0893d2b3ed7292439ea97eafa8170e0b", size = 14143006, upload-time = "2025-05-17T21:38:18.291Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/06/7e96c57d90bebdce9918412087fc22ca9851cceaf5567a45c1f404480e9e/numpy-2.2.6-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:f1372f041402e37e5e633e586f62aa53de2eac8d98cbfb822806ce4bbefcb74d", size = 5076765, upload-time = "2025-05-17T21:38:27.319Z" },
+    { url = "https://files.pythonhosted.org/packages/73/ed/63d920c23b4289fdac96ddbdd6132e9427790977d5457cd132f18e76eae0/numpy-2.2.6-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:55a4d33fa519660d69614a9fad433be87e5252f4b03850642f88993f7b2ca566", size = 6617736, upload-time = "2025-05-17T21:38:38.141Z" },
+    { url = "https://files.pythonhosted.org/packages/85/c5/e19c8f99d83fd377ec8c7e0cf627a8049746da54afc24ef0a0cb73d5dfb5/numpy-2.2.6-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f92729c95468a2f4f15e9bb94c432a9229d0d50de67304399627a943201baa2f", size = 14010719, upload-time = "2025-05-17T21:38:58.433Z" },
+    { url = "https://files.pythonhosted.org/packages/19/49/4df9123aafa7b539317bf6d342cb6d227e49f7a35b99c287a6109b13dd93/numpy-2.2.6-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1bc23a79bfabc5d056d106f9befb8d50c31ced2fbc70eedb8155aec74a45798f", size = 16526072, upload-time = "2025-05-17T21:39:22.638Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/6c/04b5f47f4f32f7c2b0e7260442a8cbcf8168b0e1a41ff1495da42f42a14f/numpy-2.2.6-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:e3143e4451880bed956e706a3220b4e5cf6172ef05fcc397f6f36a550b1dd868", size = 15503213, upload-time = "2025-05-17T21:39:45.865Z" },
+    { url = "https://files.pythonhosted.org/packages/17/0a/5cd92e352c1307640d5b6fec1b2ffb06cd0dabe7d7b8227f97933d378422/numpy-2.2.6-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b4f13750ce79751586ae2eb824ba7e1e8dba64784086c98cdbbcc6a42112ce0d", size = 18316632, upload-time = "2025-05-17T21:40:13.331Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/3b/5cba2b1d88760ef86596ad0f3d484b1cbff7c115ae2429678465057c5155/numpy-2.2.6-cp313-cp313-win32.whl", hash = "sha256:5beb72339d9d4fa36522fc63802f469b13cdbe4fdab4a288f0c441b74272ebfd", size = 6244532, upload-time = "2025-05-17T21:43:46.099Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/3b/d58c12eafcb298d4e6d0d40216866ab15f59e55d148a5658bb3132311fcf/numpy-2.2.6-cp313-cp313-win_amd64.whl", hash = "sha256:b0544343a702fa80c95ad5d3d608ea3599dd54d4632df855e4c8d24eb6ecfa1c", size = 12610885, upload-time = "2025-05-17T21:44:05.145Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/9e/4bf918b818e516322db999ac25d00c75788ddfd2d2ade4fa66f1f38097e1/numpy-2.2.6-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0bca768cd85ae743b2affdc762d617eddf3bcf8724435498a1e80132d04879e6", size = 20963467, upload-time = "2025-05-17T21:40:44Z" },
+    { url = "https://files.pythonhosted.org/packages/61/66/d2de6b291507517ff2e438e13ff7b1e2cdbdb7cb40b3ed475377aece69f9/numpy-2.2.6-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:fc0c5673685c508a142ca65209b4e79ed6740a4ed6b2267dbba90f34b0b3cfda", size = 14225144, upload-time = "2025-05-17T21:41:05.695Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/25/480387655407ead912e28ba3a820bc69af9adf13bcbe40b299d454ec011f/numpy-2.2.6-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:5bd4fc3ac8926b3819797a7c0e2631eb889b4118a9898c84f585a54d475b7e40", size = 5200217, upload-time = "2025-05-17T21:41:15.903Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/4a/6e313b5108f53dcbf3aca0c0f3e9c92f4c10ce57a0a721851f9785872895/numpy-2.2.6-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:fee4236c876c4e8369388054d02d0e9bb84821feb1a64dd59e137e6511a551f8", size = 6712014, upload-time = "2025-05-17T21:41:27.321Z" },
+    { url = "https://files.pythonhosted.org/packages/b7/30/172c2d5c4be71fdf476e9de553443cf8e25feddbe185e0bd88b096915bcc/numpy-2.2.6-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e1dda9c7e08dc141e0247a5b8f49cf05984955246a327d4c48bda16821947b2f", size = 14077935, upload-time = "2025-05-17T21:41:49.738Z" },
+    { url = "https://files.pythonhosted.org/packages/12/fb/9e743f8d4e4d3c710902cf87af3512082ae3d43b945d5d16563f26ec251d/numpy-2.2.6-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f447e6acb680fd307f40d3da4852208af94afdfab89cf850986c3ca00562f4fa", size = 16600122, upload-time = "2025-05-17T21:42:14.046Z" },
+    { url = "https://files.pythonhosted.org/packages/12/75/ee20da0e58d3a66f204f38916757e01e33a9737d0b22373b3eb5a27358f9/numpy-2.2.6-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:389d771b1623ec92636b0786bc4ae56abafad4a4c513d36a55dce14bd9ce8571", size = 15586143, upload-time = "2025-05-17T21:42:37.464Z" },
+    { url = "https://files.pythonhosted.org/packages/76/95/bef5b37f29fc5e739947e9ce5179ad402875633308504a52d188302319c8/numpy-2.2.6-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:8e9ace4a37db23421249ed236fdcdd457d671e25146786dfc96835cd951aa7c1", size = 18385260, upload-time = "2025-05-17T21:43:05.189Z" },
+    { url = "https://files.pythonhosted.org/packages/09/04/f2f83279d287407cf36a7a8053a5abe7be3622a4363337338f2585e4afda/numpy-2.2.6-cp313-cp313t-win32.whl", hash = "sha256:038613e9fb8c72b0a41f025a7e4c3f0b7a1b5d768ece4796b674c8f3fe13efff", size = 6377225, upload-time = "2025-05-17T21:43:16.254Z" },
+    { url = "https://files.pythonhosted.org/packages/67/0e/35082d13c09c02c011cf21570543d202ad929d961c02a147493cb0c2bdf5/numpy-2.2.6-cp313-cp313t-win_amd64.whl", hash = "sha256:6031dd6dfecc0cf9f668681a37648373bddd6421fff6c66ec1624eed0180ee06", size = 12771374, upload-time = "2025-05-17T21:43:35.479Z" },
 ]
 
 [[package]]
@@ -262,6 +260,23 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a4/7d/f1c30a92854540bf789e9cd5dde7ef49bbe63f855b85a2e6b3db8135c591/opencv_python-4.11.0.86-cp37-abi3-win_amd64.whl", hash = "sha256:085ad9b77c18853ea66283e98affefe2de8cc4c1f43eda4c100cf9b2721142ec", size = 39488044, upload-time = "2025-01-16T13:52:21.928Z" },
 ]
 
+[[package]]
+name = "opencv-python-headless"
+version = "4.12.0.88"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a4/63/6861102ec149c3cd298f4d1ea7ce9d6adbc7529221606ff1dab991a19adb/opencv-python-headless-4.12.0.88.tar.gz", hash = "sha256:cfdc017ddf2e59b6c2f53bc12d74b6b0be7ded4ec59083ea70763921af2b6c09", size = 95379675, upload-time = "2025-07-07T09:21:06.815Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f7/7d/414e243c5c8216a5277afd104a319cc1291c5e23f5eeef512db5629ee7f4/opencv_python_headless-4.12.0.88-cp37-abi3-macosx_13_0_arm64.whl", hash = "sha256:1e58d664809b3350c1123484dd441e1667cd7bed3086db1b9ea1b6f6cb20b50e", size = 37877864, upload-time = "2025-07-07T09:14:41.693Z" },
+    { url = "https://files.pythonhosted.org/packages/05/14/7e162714beed1cd5e7b5eb66fcbcba2f065c51b1d9da2463024c84d2f7c0/opencv_python_headless-4.12.0.88-cp37-abi3-macosx_13_0_x86_64.whl", hash = "sha256:365bb2e486b50feffc2d07a405b953a8f3e8eaa63865bc650034e5c71e7a5154", size = 57326608, upload-time = "2025-07-07T09:14:51.885Z" },
+    { url = "https://files.pythonhosted.org/packages/69/4e/116720df7f1f7f3b59abc608ca30fbec9d2b3ae810afe4e4d26483d9dfa0/opencv_python_headless-4.12.0.88-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:aeb4b13ecb8b4a0beb2668ea07928160ea7c2cd2d9b5ef571bbee6bafe9cc8d0", size = 33145800, upload-time = "2025-07-07T09:15:00.367Z" },
+    { url = "https://files.pythonhosted.org/packages/89/53/e19c21e0c4eb1275c3e2c97b081103b6dfb3938172264d283a519bf728b9/opencv_python_headless-4.12.0.88-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:236c8df54a90f4d02076e6f9c1cc763d794542e886c576a6fee46ec8ff75a7a9", size = 54023419, upload-time = "2025-07-07T09:15:10.164Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/9c/a76fd5414de6ec9f21f763a600058a0c3e290053cea87e0275692b1375c0/opencv_python_headless-4.12.0.88-cp37-abi3-win32.whl", hash = "sha256:fde2cf5c51e4def5f2132d78e0c08f9c14783cd67356922182c6845b9af87dbd", size = 30225230, upload-time = "2025-07-07T09:15:17.045Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/35/0858e9e71b36948eafbc5e835874b63e515179dc3b742cbe3d76bc683439/opencv_python_headless-4.12.0.88-cp37-abi3-win_amd64.whl", hash = "sha256:86b413bdd6c6bf497832e346cd5371995de148e579b9774f8eba686dee3f5528", size = 38923559, upload-time = "2025-07-07T09:15:25.229Z" },
+]
+
 [[package]]
 name = "packaging"
 version = "25.0"
@@ -387,11 +402,9 @@ version = "0.1.0"
 source = { editable = "." }
 dependencies = [
     { name = "networkx" },
-    { name = "onnxruntime" },
     { name = "pillow" },
     { name = "pyautogui" },
     { name = "python-statemachine", extra = ["diagrams"] },
-    { name = "rapidocr" },
 ]
 
 [package.dev-dependencies]
@@ -399,15 +412,20 @@ dev = [
     { name = "pre-commit" },
     { name = "types-networkx" },
 ]
+ocr = [
+    { name = "onnxruntime" },
+    { name = "rapidocr" },
+]
+opencv = [
+    { name = "opencv-python-headless" },
+]
 
 [package.metadata]
 requires-dist = [
     { name = "networkx", specifier = ">=3.5" },
-    { name = "onnxruntime", specifier = ">=1.22.0" },
     { name = "pillow", specifier = ">=11.3.0" },
     { name = "pyautogui", specifier = ">=0.9.54" },
     { name = "python-statemachine", extras = ["diagrams"], git = "https://github.com/fgmacedo/python-statemachine.git?rev=9a089edf61b4afd4abc08968b3cfa508fa332f7c" },
-    { name = "rapidocr", specifier = ">=3.2.0" },
 ]
 
 [package.metadata.requires-dev]
@@ -415,6 +433,11 @@ dev = [
     { name = "pre-commit", specifier = ">=4.2.0" },
     { name = "types-networkx", specifier = ">=3.5.0.20250712" },
 ]
+ocr = [
+    { name = "onnxruntime", specifier = ">=1.22.0" },
+    { name = "rapidocr", specifier = ">=3.2.0" },
+]
+opencv = [{ name = "opencv-python-headless", specifier = ">=4.12.0.88" }]
 
 [[package]]
 name = "pyclipper"

pyautoscene-0.1.0/src/pyautoscene/__init__.py

@@ -1,5 +0,0 @@
-from .references import ReferenceImage, ReferenceText
-from .scene import Scene
-from .session import Session
-
-__all__ = ["Scene", "Session", "ReferenceImage", "ReferenceText"]

pyautoscene-0.1.0/src/pyautoscene/references.py

@@ -1,38 +0,0 @@
-from abc import ABC, abstractmethod
-
-import pyautogui as gui
-from pyscreeze import Box
-
-
-class ReferenceElement(ABC):
-    """Base class for reference elements used to identify scenes."""
-
-    @abstractmethod
-    def is_visible(self):
-        """Detect the presence of the reference element."""
-        raise NotImplementedError("Subclasses must implement this method")
-
-
-class ReferenceImage(ReferenceElement):
-    """Reference element that identifies a scene by an image."""
-
-    def __init__(self, image_path: str):
-        self.image_path = image_path
-
-    def is_visible(self, region: Box | None = None):
-        """Method to detect the presence of the image in the current screen."""
-        try:
-            return gui.locateOnScreen(self.image_path, region=region)
-        except gui.ImageNotFoundException:
-            return None
-
-
-class ReferenceText(ReferenceElement):
-    """Reference element that identifies a scene by text."""
-
-    def __init__(self, text: str):
-        self.text = text
-
-    def is_visible(self):
-        """Method to detect the presence of the text in the current screen."""
-        raise NotImplementedError("Text recognition is not implemented yet.")