Files
sci-gui-agent-benchmark/evaluation_examples/examples/libreoffice_impress/b8adbc24-cef2-4b15-99d5-ecbe7ff445eb.json
Shenzhennan 29caebb765 Impress check and fix (all font compare issue) (#247)
* Enhance PPTX comparison logic in slides.py

- Improved alignment comparison to treat None and LEFT as equivalent.
- Added special handling for font bold and italic properties to consider None and False as equivalent.
- Introduced a new bullet comparison function that allows for minor differences and tolerates formatting variations.
- Updated JSON examples to support multiple file comparisons and results.

* fix all fonts json file f23ac

* fix clean the shape examination in unrelevatn part-top position check

* Refactor JSON structure for PPTX comparison

- Updated the instruction formatting for clarity.
- Modified the comparison logic to support multiple expected and result files, enhancing flexibility in evaluations.
- Changed the function key to an array to accommodate multiple comparison functions.
- Introduced a conjunction key to specify logical relationships between comparisons.

* fix impress-e4ef0baf by adding all fonts gold file

* update impress bf4e9888 task ins

* fix impress b8adbc24 font size

* Enhance PPTX comparison functionality in slides.py

- Introduced a debug logger for detailed output during PPTX comparisons.
- Added a new function to recursively retrieve all text shapes, including those within groups.
- Enabled debug logging to provide insights on slide and shape comparisons.
- Updated JSON examples to support multiple expected and result files for enhanced evaluation flexibility.

* Enable debug logging by default in PPTX comparison and enhance debug output for shape mismatches. Updated JSON examples to support multiple expected and result files for improved evaluation consistency.

* fix impress all fons compare file

* Refactor PPTX comparison logic and JSON examples for height modification tasks

- Added critical notes in slides.py to clarify the execution order of shape examination and height modification checks.
- Updated JSON examples to support multiple expected and result files, enhancing evaluation consistency.
- Ensured that examine_shape must be set to False for examine_modify_height to function correctly, preventing premature termination of comparisons.

* Enhance debug logging in PPTX comparison for detailed font attribute mismatches

- Added debug logging for differences in font color, bold, italic, and underline attributes during table cell comparisons.
- Improved clarity of debug output by including specific slide, shape, and cell indices for mismatches.
- Ensured that existing comparison logic remains intact while enhancing debugging capabilities.

* Enhance debug logging for font attribute mismatches in PPTX comparison

- Added detailed debug logging for font name and size mismatches during PPTX comparisons, including specific slide, shape, and paragraph indices.
- Updated JSON examples to support multiple expected and result files, improving evaluation consistency.
- Maintained existing comparison logic while enhancing debugging capabilities.

* fix impress 3161de json file

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-07-10 00:36:32 +08:00

81 lines
2.0 KiB
JSON

{
"id": "b8adbc24-cef2-4b15-99d5-ecbe7ff445eb",
"snapshot": "libreoffice_impress",
"instruction": "Go to the second slide and name its title as \"Online Shopping\", same color with previous title.",
"source": "https://arxiv.org/pdf/2311.01767.pdf",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_impress/b8adbc24-cef2-4b15-99d5-ecbe7ff445eb/189_4.pptx",
"path": "/home/user/Desktop/189_4.pptx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/189_4.pptx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_impress"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "189_4.pptx - LibreOffice Impress",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_pptx_files",
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_impress/b8adbc24-cef2-4b15-99d5-ecbe7ff445eb/189_4_Gold.pptx",
"dest": "189_4_Gold.pptx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/189_4.pptx",
"dest": "189_4.pptx"
},
"options": {
"examine_alignment": false,
"examine_font_name": false,
"examine_shape": false,
"examine_font_size": false
}
},
"proxy": false
}