- Rust core engine with HTTP ingestion gateway, hybrid search, and white-box resume matching - Python edge collectors supporting declarative TOML and specialized adapters - PostgreSQL schema migrations with pgvector embedding support - Hardened security controls: strict CSP, terminal sanitization, and input boundary validation - Multi-service container orchestration with dedicated non-root execution
30 lines
566 B
Python
30 lines
566 B
Python
from .content import (
|
|
ATTACHMENT_EXTENSIONS,
|
|
is_anti_crawler,
|
|
is_attachment_name,
|
|
sanitize_body_text,
|
|
)
|
|
from .fetcher import PoliteFetcher
|
|
from .protocol import (
|
|
AnnouncementItem,
|
|
AttachmentItem,
|
|
CollectorMeta,
|
|
IngestPayload,
|
|
PositionItem,
|
|
emit_payload,
|
|
)
|
|
|
|
__all__ = [
|
|
"ATTACHMENT_EXTENSIONS",
|
|
"AnnouncementItem",
|
|
"AttachmentItem",
|
|
"CollectorMeta",
|
|
"IngestPayload",
|
|
"PoliteFetcher",
|
|
"PositionItem",
|
|
"emit_payload",
|
|
"is_anti_crawler",
|
|
"is_attachment_name",
|
|
"sanitize_body_text",
|
|
]
|