feat: initialize bangwen recruitment aggregation and search engine

- 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

collectors/common/content.py

@@ -0,0 +1,56 @@
+from typing import Optional
+
+ATTACHMENT_EXTENSIONS = (
+    ".pdf",
+    ".docx",
+    ".doc",
+    ".xlsx",
+    ".xls",
+    ".zip",
+    ".rar",
+    ".7z",
+    ".tar",
+    ".gz",
+)
+
+ANTI_CRAWLER_KEYWORDS = (
+    "环境异常",
+    "完成验证",
+    "访问过于频繁",
+    "请进行验证",
+    "滑动验证",
+    "安全验证",
+    "robot check",
+    "access denied",
+)
+
+MIN_BODY_LENGTH = 60
+MAX_ATTACHMENT_FILENAME_LENGTH = 120
+MAX_ANTI_CRAWLER_TEXT_LENGTH = 300
+
+
+def is_attachment_name(text: str) -> bool:
+    s = text.strip()
+    if not s or len(s) >= MAX_ATTACHMENT_FILENAME_LENGTH:
+        return False
+    return s.lower().endswith(ATTACHMENT_EXTENSIONS)
+
+
+def is_anti_crawler(text: str) -> bool:
+    s = text.strip()
+    if not s or len(s) >= MAX_ANTI_CRAWLER_TEXT_LENGTH:
+        return False
+    return any(kw in s for kw in ANTI_CRAWLER_KEYWORDS)
+
+
+def sanitize_body_text(raw_text: Optional[str]) -> Optional[str]:
+    if not raw_text:
+        return None
+    cleaned = raw_text.strip()
+    if len(cleaned) < MIN_BODY_LENGTH:
+        return None
+    if is_anti_crawler(cleaned):
+        return None
+    if is_attachment_name(cleaned):
+        return None
+    return cleaned