Spaces:
Configuration error
Configuration error
Moved multiple instances of 'pylint: disable=broad-exception-caught' to top of file
Browse files- functions/github.py +5 -3
- functions/gradio.py +5 -1
- functions/job_call.py +3 -1
- functions/linkedin_resume.py +5 -3
- functions/writer_agent.py +3 -1
- tests/test_linkedin_resume.py +54 -34
functions/github.py
CHANGED
|
@@ -12,6 +12,8 @@ from pathlib import Path
|
|
| 12 |
|
| 13 |
import requests
|
| 14 |
|
|
|
|
|
|
|
| 15 |
# Set up logging
|
| 16 |
logging.basicConfig(level=logging.INFO)
|
| 17 |
logger = logging.getLogger(__name__)
|
|
@@ -99,12 +101,12 @@ def get_github_repositories(github_url: str) -> Dict:
|
|
| 99 |
json.dump(result, f, indent=2, ensure_ascii=False)
|
| 100 |
|
| 101 |
logger.info("GitHub repositories saved to %s", output_file)
|
| 102 |
-
except Exception as save_error:
|
| 103 |
logger.warning("Failed to save GitHub repositories to file: %s", str(save_error))
|
| 104 |
|
| 105 |
return result
|
| 106 |
|
| 107 |
-
except Exception as e:
|
| 108 |
logger.error("Error retrieving GitHub repositories: %s", str(e))
|
| 109 |
|
| 110 |
return {
|
|
@@ -146,7 +148,7 @@ def _extract_github_username(github_url: str) -> Optional[str]:
|
|
| 146 |
|
| 147 |
return None
|
| 148 |
|
| 149 |
-
except Exception as e:
|
| 150 |
logger.warning("Error extracting username from URL %s: %s", github_url, str(e))
|
| 151 |
|
| 152 |
return None
|
|
|
|
| 12 |
|
| 13 |
import requests
|
| 14 |
|
| 15 |
+
# pylint: disable=broad-exception-caught
|
| 16 |
+
|
| 17 |
# Set up logging
|
| 18 |
logging.basicConfig(level=logging.INFO)
|
| 19 |
logger = logging.getLogger(__name__)
|
|
|
|
| 101 |
json.dump(result, f, indent=2, ensure_ascii=False)
|
| 102 |
|
| 103 |
logger.info("GitHub repositories saved to %s", output_file)
|
| 104 |
+
except Exception as save_error:
|
| 105 |
logger.warning("Failed to save GitHub repositories to file: %s", str(save_error))
|
| 106 |
|
| 107 |
return result
|
| 108 |
|
| 109 |
+
except Exception as e:
|
| 110 |
logger.error("Error retrieving GitHub repositories: %s", str(e))
|
| 111 |
|
| 112 |
return {
|
|
|
|
| 148 |
|
| 149 |
return None
|
| 150 |
|
| 151 |
+
except Exception as e:
|
| 152 |
logger.warning("Error extracting username from URL %s: %s", github_url, str(e))
|
| 153 |
|
| 154 |
return None
|
functions/gradio.py
CHANGED
|
@@ -13,6 +13,8 @@ from functions.job_call import summarize_job_call
|
|
| 13 |
from functions.writer_agent import write_resume
|
| 14 |
from configuration import DEFAULT_GITHUB_PROFILE
|
| 15 |
|
|
|
|
|
|
|
| 16 |
# Set up logging
|
| 17 |
logging.basicConfig(level=logging.INFO)
|
| 18 |
logger = logging.getLogger(__name__)
|
|
@@ -82,6 +84,7 @@ def process_inputs(linkedin_pdf, github_url, job_post_text, user_instructions):
|
|
| 82 |
|
| 83 |
# Process LinkedIn PDF file
|
| 84 |
if linkedin_pdf is not None:
|
|
|
|
| 85 |
# Handle both file objects and mock file objects with path strings
|
| 86 |
file_path = linkedin_pdf.name
|
| 87 |
file_display_name = Path(file_path).name
|
|
@@ -103,6 +106,7 @@ def process_inputs(linkedin_pdf, github_url, job_post_text, user_instructions):
|
|
| 103 |
shutil.copy2(file_path, default_pdf_path)
|
| 104 |
result += " ✅ Saved as new default LinkedIn profile\n"
|
| 105 |
logger.info("Saved uploaded LinkedIn PDF as new default: %s", default_pdf_path)
|
|
|
|
| 106 |
except Exception as save_error:
|
| 107 |
result += f" ⚠️ Could not save as default: {str(save_error)}\n"
|
| 108 |
logger.warning("Failed to save LinkedIn PDF as default: %s", str(save_error))
|
|
@@ -190,7 +194,7 @@ def process_inputs(linkedin_pdf, github_url, job_post_text, user_instructions):
|
|
| 190 |
result += "\n✅ Resume generated successfully\n"
|
| 191 |
logger.info("Resume generation completed successfully")
|
| 192 |
|
| 193 |
-
except Exception as e:
|
| 194 |
result += f"\n❌ Resume generation failed: {str(e)}\n"
|
| 195 |
logger.error("Resume generation failed: %s", str(e))
|
| 196 |
else:
|
|
|
|
| 13 |
from functions.writer_agent import write_resume
|
| 14 |
from configuration import DEFAULT_GITHUB_PROFILE
|
| 15 |
|
| 16 |
+
# pylint: disable=broad-exception-caught
|
| 17 |
+
|
| 18 |
# Set up logging
|
| 19 |
logging.basicConfig(level=logging.INFO)
|
| 20 |
logger = logging.getLogger(__name__)
|
|
|
|
| 84 |
|
| 85 |
# Process LinkedIn PDF file
|
| 86 |
if linkedin_pdf is not None:
|
| 87 |
+
|
| 88 |
# Handle both file objects and mock file objects with path strings
|
| 89 |
file_path = linkedin_pdf.name
|
| 90 |
file_display_name = Path(file_path).name
|
|
|
|
| 106 |
shutil.copy2(file_path, default_pdf_path)
|
| 107 |
result += " ✅ Saved as new default LinkedIn profile\n"
|
| 108 |
logger.info("Saved uploaded LinkedIn PDF as new default: %s", default_pdf_path)
|
| 109 |
+
|
| 110 |
except Exception as save_error:
|
| 111 |
result += f" ⚠️ Could not save as default: {str(save_error)}\n"
|
| 112 |
logger.warning("Failed to save LinkedIn PDF as default: %s", str(save_error))
|
|
|
|
| 194 |
result += "\n✅ Resume generated successfully\n"
|
| 195 |
logger.info("Resume generation completed successfully")
|
| 196 |
|
| 197 |
+
except Exception as e:
|
| 198 |
result += f"\n❌ Resume generation failed: {str(e)}\n"
|
| 199 |
logger.error("Resume generation failed: %s", str(e))
|
| 200 |
else:
|
functions/job_call.py
CHANGED
|
@@ -5,6 +5,8 @@ import logging
|
|
| 5 |
from openai import OpenAI
|
| 6 |
from configuration import JOB_CALL_EXTRACTION_PROMPT
|
| 7 |
|
|
|
|
|
|
|
| 8 |
# Set up logging
|
| 9 |
logging.basicConfig(level=logging.INFO)
|
| 10 |
logger = logging.getLogger(__name__)
|
|
@@ -47,7 +49,7 @@ def summarize_job_call(job_call: str) -> str:
|
|
| 47 |
try:
|
| 48 |
response = client.chat.completions.create(**completion_args)
|
| 49 |
|
| 50 |
-
except Exception as e:
|
| 51 |
response = None
|
| 52 |
logger.error('Error during Modal API call: %s', e)
|
| 53 |
|
|
|
|
| 5 |
from openai import OpenAI
|
| 6 |
from configuration import JOB_CALL_EXTRACTION_PROMPT
|
| 7 |
|
| 8 |
+
# pylint: disable=broad-exception-caught
|
| 9 |
+
|
| 10 |
# Set up logging
|
| 11 |
logging.basicConfig(level=logging.INFO)
|
| 12 |
logger = logging.getLogger(__name__)
|
|
|
|
| 49 |
try:
|
| 50 |
response = client.chat.completions.create(**completion_args)
|
| 51 |
|
| 52 |
+
except Exception as e:
|
| 53 |
response = None
|
| 54 |
logger.error('Error during Modal API call: %s', e)
|
| 55 |
|
functions/linkedin_resume.py
CHANGED
|
@@ -13,6 +13,8 @@ import json
|
|
| 13 |
from pathlib import Path
|
| 14 |
import PyPDF2
|
| 15 |
|
|
|
|
|
|
|
| 16 |
# Set up logging
|
| 17 |
logging.basicConfig(level=logging.INFO)
|
| 18 |
logger = logging.getLogger(__name__)
|
|
@@ -66,7 +68,7 @@ def extract_text_from_linkedin_pdf(pdf_file) -> dict:
|
|
| 66 |
page_text = page.extract_text()
|
| 67 |
extracted_text += page_text + "\n\n"
|
| 68 |
|
| 69 |
-
except Exception as e:
|
| 70 |
logger.warning("Error extracting text from page %d: %s", page_num + 1, str(e))
|
| 71 |
|
| 72 |
continue
|
|
@@ -115,12 +117,12 @@ def extract_text_from_linkedin_pdf(pdf_file) -> dict:
|
|
| 115 |
|
| 116 |
logger.info("LinkedIn resume extraction saved to %s", output_file)
|
| 117 |
|
| 118 |
-
except Exception as save_error:
|
| 119 |
logger.warning("Failed to save LinkedIn resume extraction to file: %s", str(save_error))
|
| 120 |
|
| 121 |
return result
|
| 122 |
|
| 123 |
-
except Exception as e:
|
| 124 |
logger.error("Error processing PDF file: %s", str(e))
|
| 125 |
|
| 126 |
return {
|
|
|
|
| 13 |
from pathlib import Path
|
| 14 |
import PyPDF2
|
| 15 |
|
| 16 |
+
# pylint: disable=broad-exception-caught
|
| 17 |
+
|
| 18 |
# Set up logging
|
| 19 |
logging.basicConfig(level=logging.INFO)
|
| 20 |
logger = logging.getLogger(__name__)
|
|
|
|
| 68 |
page_text = page.extract_text()
|
| 69 |
extracted_text += page_text + "\n\n"
|
| 70 |
|
| 71 |
+
except Exception as e:
|
| 72 |
logger.warning("Error extracting text from page %d: %s", page_num + 1, str(e))
|
| 73 |
|
| 74 |
continue
|
|
|
|
| 117 |
|
| 118 |
logger.info("LinkedIn resume extraction saved to %s", output_file)
|
| 119 |
|
| 120 |
+
except Exception as save_error:
|
| 121 |
logger.warning("Failed to save LinkedIn resume extraction to file: %s", str(save_error))
|
| 122 |
|
| 123 |
return result
|
| 124 |
|
| 125 |
+
except Exception as e:
|
| 126 |
logger.error("Error processing PDF file: %s", str(e))
|
| 127 |
|
| 128 |
return {
|
functions/writer_agent.py
CHANGED
|
@@ -6,6 +6,8 @@ import os
|
|
| 6 |
from smolagents import CodeAgent
|
| 7 |
from configuration import AGENT_MODEL, INSTRUCTIONS
|
| 8 |
|
|
|
|
|
|
|
| 9 |
logging.basicConfig(level=logging.INFO)
|
| 10 |
logger = logging.getLogger(__name__)
|
| 11 |
|
|
@@ -65,7 +67,7 @@ def write_resume(content: str, user_instructions: str = None) -> str:
|
|
| 65 |
|
| 66 |
logger.info("Resume saved to: %s", resume_file_path)
|
| 67 |
|
| 68 |
-
except Exception as e:
|
| 69 |
logger.error("Failed to save resume to file: %s", e)
|
| 70 |
|
| 71 |
return submitted_answer
|
|
|
|
| 6 |
from smolagents import CodeAgent
|
| 7 |
from configuration import AGENT_MODEL, INSTRUCTIONS
|
| 8 |
|
| 9 |
+
# pylint: disable=broad-exception-caught
|
| 10 |
+
|
| 11 |
logging.basicConfig(level=logging.INFO)
|
| 12 |
logger = logging.getLogger(__name__)
|
| 13 |
|
|
|
|
| 67 |
|
| 68 |
logger.info("Resume saved to: %s", resume_file_path)
|
| 69 |
|
| 70 |
+
except Exception as e:
|
| 71 |
logger.error("Failed to save resume to file: %s", e)
|
| 72 |
|
| 73 |
return submitted_answer
|
tests/test_linkedin_resume.py
CHANGED
|
@@ -8,45 +8,55 @@ import os
|
|
| 8 |
from unittest.mock import patch, MagicMock
|
| 9 |
from functions import linkedin_resume as ca
|
| 10 |
|
|
|
|
|
|
|
| 11 |
|
| 12 |
class TestCleanExtractedText(unittest.TestCase):
|
| 13 |
"""Test cases for the _clean_extracted_text function."""
|
| 14 |
-
|
| 15 |
def test_normalize_multiple_newlines(self):
|
| 16 |
"""Test normalization of multiple newlines."""
|
|
|
|
| 17 |
raw = "Line 1\n\nLine 2\n\n\nLine 3"
|
| 18 |
expected = "Line 1\nLine 2\nLine 3"
|
| 19 |
self.assertEqual(ca._clean_extracted_text(raw), expected)
|
| 20 |
-
|
| 21 |
def test_remove_artifacts(self):
|
| 22 |
"""Test removal of PDF artifacts."""
|
|
|
|
| 23 |
raw = " 123 \n|---|\nSome text\n"
|
| 24 |
expected = "Some text"
|
| 25 |
self.assertEqual(ca._clean_extracted_text(raw), expected)
|
| 26 |
-
|
| 27 |
def test_normalize_spaces(self):
|
| 28 |
"""Test normalization of multiple spaces."""
|
|
|
|
| 29 |
raw = "A B C"
|
| 30 |
expected = "A B C"
|
| 31 |
self.assertEqual(ca._clean_extracted_text(raw), expected)
|
| 32 |
-
|
| 33 |
def test_empty_string(self):
|
| 34 |
"""Test handling of empty string."""
|
|
|
|
| 35 |
self.assertEqual(ca._clean_extracted_text(""), "")
|
| 36 |
-
|
| 37 |
def test_none_input(self):
|
| 38 |
"""Test handling of None input."""
|
|
|
|
| 39 |
self.assertEqual(ca._clean_extracted_text(None), "")
|
| 40 |
|
| 41 |
|
| 42 |
class TestStructureResumeText(unittest.TestCase):
|
| 43 |
"""Test cases for the _structure_resume_text function."""
|
| 44 |
-
|
| 45 |
def test_basic_structure(self):
|
| 46 |
"""Test basic resume text structuring."""
|
| 47 |
-
|
|
|
|
|
|
|
|
|
|
| 48 |
result = ca._structure_resume_text(text)
|
| 49 |
-
|
| 50 |
self.assertIn("contact_info", result["sections"])
|
| 51 |
self.assertIn("summary", result["sections"])
|
| 52 |
self.assertIn("experience", result["sections"])
|
|
@@ -54,21 +64,23 @@ class TestStructureResumeText(unittest.TestCase):
|
|
| 54 |
self.assertIn("skills", result["sections"])
|
| 55 |
self.assertGreater(result["word_count"], 0)
|
| 56 |
self.assertGreaterEqual(result["section_count"], 5)
|
| 57 |
-
|
| 58 |
def test_empty_text(self):
|
| 59 |
"""Test handling of empty text."""
|
|
|
|
| 60 |
result = ca._structure_resume_text("")
|
| 61 |
self.assertEqual(result["sections"], {})
|
| 62 |
self.assertEqual(result["full_text"], "")
|
| 63 |
self.assertEqual(result["word_count"], 0)
|
| 64 |
self.assertEqual(result["section_count"], 0)
|
| 65 |
-
|
| 66 |
def test_contains_required_fields(self):
|
| 67 |
"""Test that result contains all required fields."""
|
|
|
|
| 68 |
text = "Some basic text"
|
| 69 |
result = ca._structure_resume_text(text)
|
| 70 |
-
|
| 71 |
-
required_fields = ["sections", "full_text", "llm_formatted", "summary",
|
| 72 |
"format", "word_count", "section_count"]
|
| 73 |
for field in required_fields:
|
| 74 |
self.assertIn(field, result)
|
|
@@ -76,9 +88,10 @@ class TestStructureResumeText(unittest.TestCase):
|
|
| 76 |
|
| 77 |
class TestFormatForLLM(unittest.TestCase):
|
| 78 |
"""Test cases for the _format_for_llm function."""
|
| 79 |
-
|
| 80 |
def test_section_formatting(self):
|
| 81 |
"""Test proper formatting of sections for LLM."""
|
|
|
|
| 82 |
sections = {
|
| 83 |
"summary": "A summary.",
|
| 84 |
"contact_info": "Contact details.",
|
|
@@ -86,9 +99,8 @@ class TestFormatForLLM(unittest.TestCase):
|
|
| 86 |
"education": "School info.",
|
| 87 |
"skills": "Python, C++"
|
| 88 |
}
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
self.assertIn("[SUMMARY]", formatted)
|
| 93 |
self.assertIn("[CONTACT INFO]", formatted)
|
| 94 |
self.assertIn("[EXPERIENCE]", formatted)
|
|
@@ -96,46 +108,50 @@ class TestFormatForLLM(unittest.TestCase):
|
|
| 96 |
self.assertIn("[SKILLS]", formatted)
|
| 97 |
self.assertTrue(formatted.startswith("=== RESUME CONTENT ==="))
|
| 98 |
self.assertTrue(formatted.endswith("=== END RESUME ==="))
|
| 99 |
-
|
| 100 |
def test_empty_sections(self):
|
| 101 |
"""Test handling of empty sections."""
|
|
|
|
| 102 |
sections = {}
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
self.assertTrue(formatted.startswith("=== RESUME CONTENT ==="))
|
| 107 |
self.assertTrue(formatted.endswith("=== END RESUME ==="))
|
| 108 |
|
| 109 |
|
| 110 |
class TestGetLLMContextFromResume(unittest.TestCase):
|
| 111 |
"""Test cases for the get_llm_context_from_resume function."""
|
| 112 |
-
|
| 113 |
def test_success_with_llm_formatted(self):
|
| 114 |
"""Test successful extraction with LLM formatted text."""
|
|
|
|
| 115 |
extraction_result = {
|
| 116 |
"status": "success",
|
| 117 |
"structured_text": {"llm_formatted": "LLM text", "full_text": "Full text"}
|
| 118 |
}
|
| 119 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 120 |
self.assertEqual(result, "LLM text")
|
| 121 |
-
|
| 122 |
def test_fallback_to_full_text(self):
|
| 123 |
"""Test fallback to full text when LLM formatted not available."""
|
|
|
|
| 124 |
extraction_result = {
|
| 125 |
"status": "success",
|
| 126 |
"structured_text": {"full_text": "Full text"}
|
| 127 |
}
|
| 128 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 129 |
self.assertEqual(result, "Full text")
|
| 130 |
-
|
| 131 |
def test_error_status(self):
|
| 132 |
"""Test handling of error status."""
|
|
|
|
| 133 |
extraction_result = {"status": "error"}
|
| 134 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 135 |
self.assertEqual(result, "")
|
| 136 |
-
|
| 137 |
def test_missing_structured_text(self):
|
| 138 |
"""Test handling of missing structured_text."""
|
|
|
|
| 139 |
extraction_result = {"status": "success"}
|
| 140 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 141 |
self.assertEqual(result, "")
|
|
@@ -143,50 +159,54 @@ class TestGetLLMContextFromResume(unittest.TestCase):
|
|
| 143 |
|
| 144 |
class TestExtractTextFromLinkedInPDF(unittest.TestCase):
|
| 145 |
"""Test cases for the extract_text_from_linkedin_pdf function."""
|
| 146 |
-
|
| 147 |
def test_none_input(self):
|
| 148 |
"""Test handling of None input."""
|
|
|
|
| 149 |
result = ca.extract_text_from_linkedin_pdf(None)
|
| 150 |
self.assertEqual(result["status"], "error")
|
| 151 |
self.assertIn("No PDF file provided", result["message"])
|
| 152 |
-
|
| 153 |
@patch('PyPDF2.PdfReader')
|
| 154 |
@patch('builtins.open')
|
| 155 |
def test_successful_extraction(self, mock_open, mock_pdf_reader):
|
| 156 |
"""Test successful PDF text extraction with mocked PyPDF2."""
|
|
|
|
| 157 |
# Create a temporary file
|
| 158 |
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
|
| 159 |
tmp_path = tmp.name
|
| 160 |
-
|
| 161 |
try:
|
| 162 |
# Mock file reading
|
| 163 |
mock_file = MagicMock()
|
| 164 |
mock_file.read.return_value = b"fake pdf content"
|
| 165 |
mock_open.return_value.__enter__.return_value = mock_file
|
| 166 |
-
|
| 167 |
# Mock PDF reader and page
|
| 168 |
mock_page = MagicMock()
|
| 169 |
-
mock_page.extract_text.return_value = "Contact Info\nJohn Doe\nSummary\
|
| 170 |
-
|
|
|
|
| 171 |
mock_reader_instance = MagicMock()
|
| 172 |
mock_reader_instance.pages = [mock_page]
|
| 173 |
mock_pdf_reader.return_value = mock_reader_instance
|
| 174 |
-
|
| 175 |
# Test the function
|
| 176 |
result = ca.extract_text_from_linkedin_pdf(tmp_path)
|
| 177 |
-
|
| 178 |
self.assertEqual(result["status"], "success")
|
| 179 |
self.assertIn("structured_text", result)
|
| 180 |
self.assertIn("metadata", result)
|
| 181 |
self.assertIn("contact_info", result["structured_text"]["sections"])
|
| 182 |
-
|
| 183 |
finally:
|
| 184 |
# Clean up
|
| 185 |
if os.path.exists(tmp_path):
|
| 186 |
os.remove(tmp_path)
|
| 187 |
-
|
| 188 |
def test_nonexistent_file(self):
|
| 189 |
"""Test handling of non-existent file."""
|
|
|
|
| 190 |
result = ca.extract_text_from_linkedin_pdf("/nonexistent/path.pdf")
|
| 191 |
self.assertEqual(result["status"], "error")
|
| 192 |
self.assertIn("Failed to extract text from PDF", result["message"])
|
|
|
|
| 8 |
from unittest.mock import patch, MagicMock
|
| 9 |
from functions import linkedin_resume as ca
|
| 10 |
|
| 11 |
+
# pylint: disable=protected-access
|
| 12 |
+
|
| 13 |
|
| 14 |
class TestCleanExtractedText(unittest.TestCase):
|
| 15 |
"""Test cases for the _clean_extracted_text function."""
|
| 16 |
+
|
| 17 |
def test_normalize_multiple_newlines(self):
|
| 18 |
"""Test normalization of multiple newlines."""
|
| 19 |
+
|
| 20 |
raw = "Line 1\n\nLine 2\n\n\nLine 3"
|
| 21 |
expected = "Line 1\nLine 2\nLine 3"
|
| 22 |
self.assertEqual(ca._clean_extracted_text(raw), expected)
|
| 23 |
+
|
| 24 |
def test_remove_artifacts(self):
|
| 25 |
"""Test removal of PDF artifacts."""
|
| 26 |
+
|
| 27 |
raw = " 123 \n|---|\nSome text\n"
|
| 28 |
expected = "Some text"
|
| 29 |
self.assertEqual(ca._clean_extracted_text(raw), expected)
|
| 30 |
+
|
| 31 |
def test_normalize_spaces(self):
|
| 32 |
"""Test normalization of multiple spaces."""
|
| 33 |
+
|
| 34 |
raw = "A B C"
|
| 35 |
expected = "A B C"
|
| 36 |
self.assertEqual(ca._clean_extracted_text(raw), expected)
|
| 37 |
+
|
| 38 |
def test_empty_string(self):
|
| 39 |
"""Test handling of empty string."""
|
| 40 |
+
|
| 41 |
self.assertEqual(ca._clean_extracted_text(""), "")
|
| 42 |
+
|
| 43 |
def test_none_input(self):
|
| 44 |
"""Test handling of None input."""
|
| 45 |
+
|
| 46 |
self.assertEqual(ca._clean_extracted_text(None), "")
|
| 47 |
|
| 48 |
|
| 49 |
class TestStructureResumeText(unittest.TestCase):
|
| 50 |
"""Test cases for the _structure_resume_text function."""
|
| 51 |
+
|
| 52 |
def test_basic_structure(self):
|
| 53 |
"""Test basic resume text structuring."""
|
| 54 |
+
|
| 55 |
+
text = "Contact Info\nJohn Doe\nSummary\nExperienced dev" + \
|
| 56 |
+
"\nExperience\nCompany X\nEducation\nMIT\nSkills\nPython, C++"
|
| 57 |
+
|
| 58 |
result = ca._structure_resume_text(text)
|
| 59 |
+
|
| 60 |
self.assertIn("contact_info", result["sections"])
|
| 61 |
self.assertIn("summary", result["sections"])
|
| 62 |
self.assertIn("experience", result["sections"])
|
|
|
|
| 64 |
self.assertIn("skills", result["sections"])
|
| 65 |
self.assertGreater(result["word_count"], 0)
|
| 66 |
self.assertGreaterEqual(result["section_count"], 5)
|
| 67 |
+
|
| 68 |
def test_empty_text(self):
|
| 69 |
"""Test handling of empty text."""
|
| 70 |
+
|
| 71 |
result = ca._structure_resume_text("")
|
| 72 |
self.assertEqual(result["sections"], {})
|
| 73 |
self.assertEqual(result["full_text"], "")
|
| 74 |
self.assertEqual(result["word_count"], 0)
|
| 75 |
self.assertEqual(result["section_count"], 0)
|
| 76 |
+
|
| 77 |
def test_contains_required_fields(self):
|
| 78 |
"""Test that result contains all required fields."""
|
| 79 |
+
|
| 80 |
text = "Some basic text"
|
| 81 |
result = ca._structure_resume_text(text)
|
| 82 |
+
|
| 83 |
+
required_fields = ["sections", "full_text", "llm_formatted", "summary",
|
| 84 |
"format", "word_count", "section_count"]
|
| 85 |
for field in required_fields:
|
| 86 |
self.assertIn(field, result)
|
|
|
|
| 88 |
|
| 89 |
class TestFormatForLLM(unittest.TestCase):
|
| 90 |
"""Test cases for the _format_for_llm function."""
|
| 91 |
+
|
| 92 |
def test_section_formatting(self):
|
| 93 |
"""Test proper formatting of sections for LLM."""
|
| 94 |
+
|
| 95 |
sections = {
|
| 96 |
"summary": "A summary.",
|
| 97 |
"contact_info": "Contact details.",
|
|
|
|
| 99 |
"education": "School info.",
|
| 100 |
"skills": "Python, C++"
|
| 101 |
}
|
| 102 |
+
formatted = ca._format_for_llm(sections)
|
| 103 |
+
|
|
|
|
| 104 |
self.assertIn("[SUMMARY]", formatted)
|
| 105 |
self.assertIn("[CONTACT INFO]", formatted)
|
| 106 |
self.assertIn("[EXPERIENCE]", formatted)
|
|
|
|
| 108 |
self.assertIn("[SKILLS]", formatted)
|
| 109 |
self.assertTrue(formatted.startswith("=== RESUME CONTENT ==="))
|
| 110 |
self.assertTrue(formatted.endswith("=== END RESUME ==="))
|
| 111 |
+
|
| 112 |
def test_empty_sections(self):
|
| 113 |
"""Test handling of empty sections."""
|
| 114 |
+
|
| 115 |
sections = {}
|
| 116 |
+
formatted = ca._format_for_llm(sections)
|
| 117 |
+
|
|
|
|
| 118 |
self.assertTrue(formatted.startswith("=== RESUME CONTENT ==="))
|
| 119 |
self.assertTrue(formatted.endswith("=== END RESUME ==="))
|
| 120 |
|
| 121 |
|
| 122 |
class TestGetLLMContextFromResume(unittest.TestCase):
|
| 123 |
"""Test cases for the get_llm_context_from_resume function."""
|
| 124 |
+
|
| 125 |
def test_success_with_llm_formatted(self):
|
| 126 |
"""Test successful extraction with LLM formatted text."""
|
| 127 |
+
|
| 128 |
extraction_result = {
|
| 129 |
"status": "success",
|
| 130 |
"structured_text": {"llm_formatted": "LLM text", "full_text": "Full text"}
|
| 131 |
}
|
| 132 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 133 |
self.assertEqual(result, "LLM text")
|
| 134 |
+
|
| 135 |
def test_fallback_to_full_text(self):
|
| 136 |
"""Test fallback to full text when LLM formatted not available."""
|
| 137 |
+
|
| 138 |
extraction_result = {
|
| 139 |
"status": "success",
|
| 140 |
"structured_text": {"full_text": "Full text"}
|
| 141 |
}
|
| 142 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 143 |
self.assertEqual(result, "Full text")
|
| 144 |
+
|
| 145 |
def test_error_status(self):
|
| 146 |
"""Test handling of error status."""
|
| 147 |
+
|
| 148 |
extraction_result = {"status": "error"}
|
| 149 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 150 |
self.assertEqual(result, "")
|
| 151 |
+
|
| 152 |
def test_missing_structured_text(self):
|
| 153 |
"""Test handling of missing structured_text."""
|
| 154 |
+
|
| 155 |
extraction_result = {"status": "success"}
|
| 156 |
result = ca.get_llm_context_from_resume(extraction_result)
|
| 157 |
self.assertEqual(result, "")
|
|
|
|
| 159 |
|
| 160 |
class TestExtractTextFromLinkedInPDF(unittest.TestCase):
|
| 161 |
"""Test cases for the extract_text_from_linkedin_pdf function."""
|
| 162 |
+
|
| 163 |
def test_none_input(self):
|
| 164 |
"""Test handling of None input."""
|
| 165 |
+
|
| 166 |
result = ca.extract_text_from_linkedin_pdf(None)
|
| 167 |
self.assertEqual(result["status"], "error")
|
| 168 |
self.assertIn("No PDF file provided", result["message"])
|
| 169 |
+
|
| 170 |
@patch('PyPDF2.PdfReader')
|
| 171 |
@patch('builtins.open')
|
| 172 |
def test_successful_extraction(self, mock_open, mock_pdf_reader):
|
| 173 |
"""Test successful PDF text extraction with mocked PyPDF2."""
|
| 174 |
+
|
| 175 |
# Create a temporary file
|
| 176 |
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
|
| 177 |
tmp_path = tmp.name
|
| 178 |
+
|
| 179 |
try:
|
| 180 |
# Mock file reading
|
| 181 |
mock_file = MagicMock()
|
| 182 |
mock_file.read.return_value = b"fake pdf content"
|
| 183 |
mock_open.return_value.__enter__.return_value = mock_file
|
| 184 |
+
|
| 185 |
# Mock PDF reader and page
|
| 186 |
mock_page = MagicMock()
|
| 187 |
+
mock_page.extract_text.return_value = "Contact Info\nJohn Doe\nSummary" + \
|
| 188 |
+
"\nDeveloper\nExperience\nCompany X"
|
| 189 |
+
|
| 190 |
mock_reader_instance = MagicMock()
|
| 191 |
mock_reader_instance.pages = [mock_page]
|
| 192 |
mock_pdf_reader.return_value = mock_reader_instance
|
| 193 |
+
|
| 194 |
# Test the function
|
| 195 |
result = ca.extract_text_from_linkedin_pdf(tmp_path)
|
| 196 |
+
|
| 197 |
self.assertEqual(result["status"], "success")
|
| 198 |
self.assertIn("structured_text", result)
|
| 199 |
self.assertIn("metadata", result)
|
| 200 |
self.assertIn("contact_info", result["structured_text"]["sections"])
|
| 201 |
+
|
| 202 |
finally:
|
| 203 |
# Clean up
|
| 204 |
if os.path.exists(tmp_path):
|
| 205 |
os.remove(tmp_path)
|
| 206 |
+
|
| 207 |
def test_nonexistent_file(self):
|
| 208 |
"""Test handling of non-existent file."""
|
| 209 |
+
|
| 210 |
result = ca.extract_text_from_linkedin_pdf("/nonexistent/path.pdf")
|
| 211 |
self.assertEqual(result["status"], "error")
|
| 212 |
self.assertIn("Failed to extract text from PDF", result["message"])
|