103 lines
2.9 KiB
Python
103 lines
2.9 KiB
Python
"""
|
|
# Summary
|
|
|
|
Message header parsing utilities for Mail Intake.
|
|
|
|
This module provides helper functions for normalizing and extracting
|
|
useful information from provider-native message headers.
|
|
|
|
The functions here are intentionally simple and tolerant of malformed
|
|
or incomplete header data.
|
|
"""
|
|
|
|
from typing import Dict, List, Tuple, Optional
|
|
|
|
|
|
def parse_headers(raw_headers: List[Dict[str, str]]) -> Dict[str, str]:
|
|
"""
|
|
Convert a list of Gmail-style headers into a normalized dict.
|
|
|
|
Args:
|
|
raw_headers (List[Dict[str, str]]):
|
|
List of header dictionaries, each containing `name` and `value` keys.
|
|
|
|
Returns:
|
|
Dict[str, str]:
|
|
Dictionary mapping lowercase header names to stripped values.
|
|
|
|
Notes:
|
|
**Guarantees:**
|
|
|
|
- Provider payloads (such as Gmail) typically represent headers as a
|
|
list of name/value mappings.
|
|
- This function normalizes them into a case-insensitive dictionary
|
|
keyed by lowercase header names.
|
|
|
|
Example:
|
|
Typical usage:
|
|
|
|
```python
|
|
Input:
|
|
[
|
|
{"name": "From", "value": "John Doe <john@example.com>"},
|
|
{"name": "Subject", "value": "Re: Interview Update"},
|
|
]
|
|
|
|
Output:
|
|
{
|
|
"from": "John Doe <john@example.com>",
|
|
"subject": "Re: Interview Update",
|
|
}
|
|
```
|
|
"""
|
|
headers: Dict[str, str] = {}
|
|
|
|
for header in raw_headers or []:
|
|
name = header.get("name")
|
|
value = header.get("value")
|
|
|
|
if not name or value is None:
|
|
continue
|
|
|
|
headers[name.lower()] = value.strip()
|
|
|
|
return headers
|
|
|
|
|
|
def extract_sender(headers: Dict[str, str]) -> Tuple[str, Optional[str]]:
|
|
"""
|
|
Extract sender email and optional display name from headers.
|
|
|
|
Args:
|
|
headers (Dict[str, str]):
|
|
Normalized header dictionary as returned by `parse_headers()`.
|
|
|
|
Returns:
|
|
Tuple[str, Optional[str]]:
|
|
A tuple `(email, name)` where `email` is the sender email address
|
|
and `name` is the display name, or `None` if unavailable.
|
|
|
|
Notes:
|
|
**Responsibilities:**
|
|
|
|
- This function parses the `From` header and attempts to extract
|
|
sender email address and optional human-readable display name.
|
|
|
|
Example:
|
|
Typical values:
|
|
|
|
- `"John Doe <john@example.com>"` -> `("john@example.com", "John Doe")`
|
|
- `"john@example.com"` -> `("john@example.com", None)`
|
|
"""
|
|
from_header = headers.get("from")
|
|
if not from_header:
|
|
return "", None
|
|
|
|
if "<" in from_header and ">" in from_header:
|
|
name_part, email_part = from_header.split("<", 1)
|
|
email = email_part.rstrip(">").strip()
|
|
name = name_part.strip().strip('"') or None
|
|
return email, name
|
|
|
|
return from_header.strip(), None
|