mirror of
https://github.com/Sea-Haven-Industries/procurement-ingest.git
synced 2026-09-30 14:13:13 +00:00
30112cc680
Some checks are pending
Deploy / deploy (push) Waiting to run
Four modules move into the handbook-mandated lambdas/shared/ location, collapsing duplicated logic that had to be kept in sync by hand across the PO and WO pipelines: - ses_auth.py: the PO and WO copies were verified sha256-identical against the feature/phase-7-ops-recovery baseline before the move (no drift since the last audit). shared/ses_auth.py is the exact bytes of that one copy; both originals are git rm'd (the PO copy via rename, the WO copy as a straight delete). Bundling lands the module flat in /asset-output for both email processors, so the handlers keep `from ses_auth import authenticate_inbound_email` unchanged — zero handler diff for this move, which is what keeps fail-closed auth byte-identical through the change. - web_ui_auth.py: extracts the byte-identical _get_auth_token / _header / is_authenticated block plus the four token-cache globals out of both web_ui handlers. The per-stack INFRA-74 comments stay in each handler as-is (deliberately drifted wording, stack-specific) rather than being unified into the shared module. Fail-closed semantics (unset ARN or Secrets Manager exception -> deny) are unchanged. - email_parsing.py: parse_raw_email ships as the superset version that returns cc unconditionally. WO's output is bit-identical to before; PO simply ignores the cc field rather than being "cleaned up" to consume it. No second variant is kept. - emf.py: a generic emitter parameterized by namespace, dimension sets, and properties. Every call site's emitted EMF envelope is unchanged, including the load-bearing [["ParseMethod"],["ParseMethod","TemplateId"]] dimension-set shape the alarms and metric filters depend on. Emission ordering is untouched: PO still emits ai_fallback before the Bedrock call, WO still emits its mutually-exclusive ai_fallback/ai_fallback_rejected after its gate. The deliberate-double-count comments survive. _emit_derived_agreement_metric was found living inside derived_fields.py, so per the DERIVED-FIELDS exception it is left as a third, unconverted copy (derived_fields.py and the shadow DerivedFieldAgreement telemetry stay untouchable while that bake runs) — a comment there points at shared/emf.py for the eventual follow-up. Bundling: both email-processor cdk bundling commands gain a trailing `cp shared/*.py /asset-output/` (they were already cp-only post-Phase 7, so no pip step or manylinux pin is reintroduced). Both web_ui functions gain the same widened-root staging so web_ui_auth.py ships beside their handler; site_extractor's from_asset is untouched. Tests: PO_EXPECTED_TOP_LEVEL_MODULES gains the shared modules that now ship, the AST sibling-import check resolves imports whose source now lives under shared/, and the new shared cp line has its own revert/mutation detection. _SIBLING_MODULES resolution and _po_parser_support.py now load ses_auth/email_parsing/emf from shared/; the two-copy ses_auth byte-identity fixture-hygiene test is retired as obsolete now that there is one copy, and the ses_auth fixture parameterization over two identical copies is dropped. The sys.modules save/restore dance for template_parser (still duplicated per-pipeline) is left in place.
34 lines
905 B
Python
34 lines
905 B
Python
import email
|
|
from email import policy
|
|
|
|
|
|
def parse_raw_email(raw_bytes: bytes) -> dict:
|
|
"""Parse a raw email into subject, sender, body text."""
|
|
msg = email.message_from_bytes(raw_bytes, policy=policy.default)
|
|
|
|
subject = msg.get("Subject", "")
|
|
sender = msg.get("From", "")
|
|
to = msg.get("To", "")
|
|
cc = msg.get("Cc", "")
|
|
date = msg.get("Date", "")
|
|
|
|
body = ""
|
|
if msg.is_multipart():
|
|
for part in msg.walk():
|
|
content_type = part.get_content_type()
|
|
if content_type == "text/plain":
|
|
body = part.get_content()
|
|
break
|
|
elif content_type == "text/html" and not body:
|
|
body = part.get_content()
|
|
else:
|
|
body = msg.get_content()
|
|
|
|
return {
|
|
"subject": subject,
|
|
"sender": sender,
|
|
"to": to,
|
|
"cc": cc,
|
|
"date": date,
|
|
"body": body,
|
|
}
|