Vishesh 'ironeagle' Bangotra
f22af90e98
- docs(mail_intake/__init__.py): document module-based public API and usage patterns - docs(mail_intake/ingestion/reader.py): document high-level ingestion orchestration - docs(mail_intake/adapters/base.py): document adapter contract for mail providers - docs(mail_intake/adapters/gmail.py): document Gmail adapter implementation and constraints - docs(mail_intake/auth/base.py): document authentication provider contract - docs(mail_intake/auth/google.py): document Google OAuth authentication provider - docs(mail_intake/models/message.py): document canonical email message model - docs(mail_intake/models/thread.py): document canonical email thread model - docs(mail_intake/parsers/body.py): document message body extraction logic - docs(mail_intake/parsers/headers.py): document message header normalization utilities - docs(mail_intake/parsers/subject.py): document subject normalization utilities - docs(mail_intake/config.py): document global configuration model - docs(mail_intake/exceptions.py): document library exception hierarchy
53 lines
1.5 KiB
Python
53 lines
1.5 KiB
Python
"""
|
|
Subject line normalization utilities for Mail Intake.
|
|
|
|
This module provides helper functions for normalizing email subject lines
|
|
to enable reliable thread-level comparison and grouping.
|
|
|
|
Normalization is intentionally conservative to avoid altering semantic
|
|
meaning while removing common reply and forward prefixes.
|
|
"""
|
|
|
|
import re
|
|
|
|
|
|
_PREFIX_RE = re.compile(r"^(re|fw|fwd)\s*:\s*", re.IGNORECASE)
|
|
"""Regular expression matching common reply/forward subject prefixes."""
|
|
|
|
|
|
def normalize_subject(subject: str) -> str:
|
|
"""
|
|
Normalize an email subject for thread-level comparison.
|
|
|
|
Operations:
|
|
- Strips common prefixes such as ``Re:``, ``Fwd:``, and ``FW:``
|
|
- Repeats prefix stripping to handle stacked prefixes
|
|
- Collapses excessive whitespace
|
|
- Preserves original casing (no lowercasing)
|
|
|
|
This function is intentionally conservative and avoids aggressive
|
|
transformations that could alter the semantic meaning of the subject.
|
|
|
|
Args:
|
|
subject: Raw subject line from a message header.
|
|
|
|
Returns:
|
|
Normalized subject string suitable for thread grouping.
|
|
"""
|
|
if not subject:
|
|
return ""
|
|
|
|
normalized = subject.strip()
|
|
|
|
# Strip prefixes repeatedly (e.g., Re: Fwd: Re:)
|
|
while True:
|
|
new_value = _PREFIX_RE.sub("", normalized)
|
|
if new_value == normalized:
|
|
break
|
|
normalized = new_value.strip()
|
|
|
|
# Normalize whitespace
|
|
normalized = " ".join(normalized.split())
|
|
|
|
return normalized
|