Skip to content

⚡ Bolt: Precompile regex in job parser #232

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 2 commits into
base: main
Choose a base branch
from
Open

⚡ Bolt: Precompile regex in job parser #232

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3e729e8
⚡ Bolt: Compile regex patterns in job_parser
google-labs-jules[bot] Apr 5, 2026
9f33c43
⚡ Bolt: Precompile regex in job parser and fix formatting
google-labs-jules[bot] Apr 5, 2026
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
56 changes: 31 additions & 25 deletions cli/integrations/job_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,31 @@
requests = None


# ⚡ Bolt Optimization: Pre-compile regex patterns at the module level to avoid
# recompilation and array instantiation overhead during every extraction function call.
_SALARY_PATTERNS = [
re.compile(r"\$[\d,]+(?:\s*[-–to]+\s*\$[\d,]+)?", re.IGNORECASE), # $100k - $150k
re.compile(r"\$[\d,]+k(?:\s*[-–to]+\s*\$[\d,]+k)?", re.IGNORECASE), # $100k - $150k
re.compile(r"[\d,]+k(?:\s*[-–to]+\s*[\d,]+k)", re.IGNORECASE), # 100k - 150k
re.compile(r"(?:salary|pay|compensation)[:\s]*(\$[^<>\n]+)", re.IGNORECASE), # Salary: $X
re.compile(r"(?:per|/)\s*(?:year|annum)[:\s]*(\$[^<>\n]+)", re.IGNORECASE), # per year: $X
]

_JOB_TYPE_PATTERNS = [
re.compile(
r"\b(full[- ]?time|part[- ]?time|contract|freelance|intern|temporary)\b", re.IGNORECASE
),
re.compile(r"\b(permanent|fixed[- ]?term)\b", re.IGNORECASE),
]

_EXPERIENCE_LEVEL_PATTERNS = [
re.compile(
r"\b(entry[- ]?level|junior|mid[- ]?level|senior|staff|principal|lead)\b", re.IGNORECASE
),
re.compile(r"\b(associate|vice[- ]?president|director|executive)\b", re.IGNORECASE),
]


@dataclass
class JobDetails:
"""Structured job posting data."""
Expand Down Expand Up @@ -555,17 +580,8 @@ def _extract_salary_from_text(self, text: str) -> Optional[str]:
Returns:
Salary string or None
"""
# Common salary patterns
patterns = [
r"\$[\d,]+(?:\s*[-–to]+\s*\$[\d,]+)?", # $100k - $150k
r"\$[\d,]+k(?:\s*[-–to]+\s*\$[\d,]+k)?", # $100k - $150k
r"[\d,]+k(?:\s*[-–to]+\s*[\d,]+k)", # 100k - 150k
r"(?:salary|pay|compensation)[:\s]*(\$[^<>\n]+)", # Salary: $X
r"(?:per|/)\s*(?:year|annum)[:\s]*(\$[^<>\n]+)", # per year: $X
]

for pattern in patterns:
match = re.search(pattern, text, re.IGNORECASE)
for pattern in _SALARY_PATTERNS:
match = pattern.search(text)
if match:
salary = match.group(0) if match.lastindex is None else match.group(1)
# Clean up the salary string
Expand Down Expand Up @@ -805,13 +821,8 @@ def _extract_job_type(self, html: str) -> Optional[str]:
Returns:
Job type string or None
"""
patterns = [
r"\b(full[- ]?time|part[- ]?time|contract|freelance|intern|temporary)\b",
r"\b(permanent|fixed[- ]?term)\b",
]

for pattern in patterns:
match = re.search(pattern, html, re.IGNORECASE)
for pattern in _JOB_TYPE_PATTERNS:
match = pattern.search(html)
if match:
return match.group(1).lower().replace("-", "-")

Expand All @@ -827,13 +838,8 @@ def _extract_experience_level(self, html: str) -> Optional[str]:
Returns:
Experience level string or None
"""
patterns = [
r"\b(entry[- ]?level|junior|mid[- ]?level|senior|staff|principal|lead)\b",
r"\b(associate|vice[- ]?president|director|executive)\b",
]

for pattern in patterns:
match = re.search(pattern, html, re.IGNORECASE)
for pattern in _EXPERIENCE_LEVEL_PATTERNS:
match = pattern.search(html)
if match:
return match.group(1).lower().replace("-", "-")

Expand Down
Loading