Skip to content

⚡ Bolt: [performance improvement] Pre-compile regex patterns in keyword density #245

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
anchapin wants to merge 1 commit into
base: main
Choose a base branch
from
Open

⚡ Bolt: [performance improvement] Pre-compile regex patterns in keyword density #245

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 16 additions & 15 deletions cli/utils/keyword_density.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,18 @@

console = Console()

# Pre-compiled regex patterns for extracting job details to optimize performance
_TITLE_PATTERNS = [
re.compile(r"(?:job title|position|title):\s*([^\n]+)", re.IGNORECASE | re.MULTILINE),
re.compile(r"^([^\n]+)\s*[-|]\s*[^|]+$", re.IGNORECASE | re.MULTILINE),
re.compile(r"#\s*([^\n]+)", re.IGNORECASE | re.MULTILINE),
]

_COMPANY_PATTERNS = [
re.compile(r"(?:company|organization):\s*([^\n]+)", re.IGNORECASE),
re.compile(r"(?:at|from)\s+([A-Z][^\n]+?)(?:\s+[-\u2014]|\s+$)", re.IGNORECASE),
]


@dataclass
class KeywordInfo:
Expand Down Expand Up @@ -208,26 +220,15 @@ def _extract_job_details(self, job_description: str) -> Tuple[str, str]:
company = ""

# Try to extract job title (common patterns)
title_patterns = [
r"(?:job title|position|title):\s*([^\n]+)",
r"^([^\n]+)\s*[-|]\s*[^|]+$",
r"#\s*([^\n]+)", # Markdown headers often have job title
]

for pattern in title_patterns:
match = re.search(pattern, job_description, re.IGNORECASE | re.MULTILINE)
for pattern in _TITLE_PATTERNS:
match = pattern.search(job_description)
if match:
job_title = match.group(1).strip()
break

# Try to extract company name
company_patterns = [
r"(?:company|organization):\s*([^\n]+)",
r"(?:at|from)\s+([A-Z][^\n]+?)(?:\s+[-\u2014]|\s+$)",
]

for pattern in company_patterns:
match = re.search(pattern, job_description, re.IGNORECASE)
for pattern in _COMPANY_PATTERNS:
match = pattern.search(job_description)
if match:
company = match.group(1).strip()
break
Expand Down
Loading