firefrost-gaming/skill-seekers-reference
3
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

change max lenght

Browse Source
This commit is contained in:
Pablo Estevez
2026-01-17 17:48:15 +00:00
parent 97e597d9db
commit c33c6f9073
118 changed files with 3546 additions and 960 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
tests/test_pdf_scraper.py
View File

@@ -103,7 +103,11 @@ class TestCategorization(unittest.TestCase):
# Mock extracted data with different content
converter.extracted_data = {
"pages": [
{"page_number": 1, "text": "Introduction to the API", "chapter": "Chapter 1: Getting Started"},
{
"page_number": 1,
"text": "Introduction to the API",
"chapter": "Chapter 1: Getting Started",
},
{"page_number": 2, "text": "API reference for functions", "chapter": None},
]
}
@@ -140,7 +144,9 @@ class TestCategorization(unittest.TestCase):
converter = self.PDFToSkillConverter(config)
# Mock data without chapters
converter.extracted_data = {"pages": [{"page_number": 1, "text": "Some content", "chapter": None}]}
converter.extracted_data = {
"pages": [{"page_number": 1, "text": "Some content", "chapter": None}]
}
categories = converter.categorize_content()
@@ -270,7 +276,13 @@ class TestCodeBlockHandling(unittest.TestCase):
{
"page_number": 1,
"text": "Example code",
"code_blocks": [{"code": "def hello():\n print('world')", "language": "python", "quality": 8.0}],
"code_blocks": [
{
"code": "def hello():\n print('world')",
"language": "python",
"quality": 8.0,
}
],
"images": [],
}
],
@@ -305,7 +317,11 @@ class TestCodeBlockHandling(unittest.TestCase):
"text": "Code examples",
"code_blocks": [
{"code": "x = 1", "language": "python", "quality": 2.0},
{"code": "def process():\n return result", "language": "python", "quality": 9.0},
{
"code": "def process():\n return result",
"language": "python",
"quality": 9.0,
},
],
"images": [],
}
@@ -354,7 +370,15 @@ class TestImageHandling(unittest.TestCase):
"page_number": 1,
"text": "See diagram",
"code_blocks": [],
"images": [{"page": 1, "index": 0, "width": 100, "height": 100, "data": mock_image_bytes}],
"images": [
{
"page": 1,
"index": 0,
"width": 100,
"height": 100,
"data": mock_image_bytes,
}
],
}
],
"total_pages": 1,
@@ -384,7 +408,15 @@ class TestImageHandling(unittest.TestCase):
"page_number": 1,
"text": "Architecture diagram",
"code_blocks": [],
"images": [{"page": 1, "index": 0, "width": 200, "height": 150, "data": mock_image_bytes}],
"images": [
{
"page": 1,
"index": 0,
"width": 200,
"height": 150,
"data": mock_image_bytes,
}
],
}
],
"total_pages": 1,