fix: make employee detail page human-readable

app/services/admin_data.py

@@ -46,6 +46,25 @@ def employee_display_payload(employee: Employee) -> dict[str, Any]:
     }
 
 
+def employee_detail_payload(employee: Employee) -> dict[str, Any]:
+    data = employee.current_data or {}
+    contacts = data.get("contacts") or {}
+    return {
+        **employee_display_payload(employee),
+        "profile_type": employee.profile_type or data.get("profile_type"),
+        "profile_id": employee.profile_id or data.get("profile_id"),
+        "parser_version": employee.parser_version or data.get("parser_version"),
+        "contacts": {
+            "emails": _clean_list(contacts.get("emails")),
+            "phones": _clean_list(contacts.get("phones")),
+            "address": contacts.get("address"),
+            "items": _normalize_contact_items(contacts.get("items")),
+        },
+        "external_ids": _normalize_external_ids(data.get("external_ids")),
+        "sections": [_normalize_section(section) for section in data.get("sections") or []],
+    }
+
+
 def build_employee_query(
     *,
     status: str | None = None,
@@ -157,3 +176,144 @@ def _count_section_items(sections: list[dict[str, Any]], section_type: str) -> i
         elif section_type == "courses_by_year":
             total += len(section.get("courses") or [])
     return total
+
+
+def _clean_list(values: Any) -> list[str]:
+    if not isinstance(values, list):
+        return []
+    return [str(value).strip() for value in values if str(value or "").strip()]
+
+
+def _normalize_contact_items(items: Any) -> list[str]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if isinstance(item, dict):
+            value = item.get("raw") or item.get("value") or item.get("text")
+        else:
+            value = item
+        value = str(value or "").strip()
+        if value:
+            normalized.append(value)
+    return normalized
+
+
+def _normalize_external_ids(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        system = str(item.get("system") or "").strip()
+        value = str(item.get("value") or "").strip()
+        url = str(item.get("url") or "").strip()
+        if system or value or url:
+            normalized.append({"system": system or "ID", "value": value or url, "url": url or None})
+    return normalized
+
+
+def _normalize_section(section: Any) -> dict[str, Any]:
+    if not isinstance(section, dict):
+        return {"title": "Раздел", "type": "generic", "paragraphs": [str(section)], "items": [], "links": []}
+
+    section_type = section.get("type") or "generic"
+    paragraphs = _clean_list(section.get("paragraphs"))
+    items = _clean_list(section.get("items"))
+    raw_text = str(section.get("raw_text") or "").strip()
+    if not paragraphs and not items and raw_text:
+        paragraphs = [raw_text]
+
+    return {
+        "title": section.get("title") or "Раздел",
+        "type": section_type,
+        "raw_text": raw_text,
+        "paragraphs": paragraphs,
+        "items": items,
+        "links": _normalize_links(section.get("links")),
+        "year_entries": _normalize_year_entries(section.get("year_entries")),
+        "publications": _normalize_publications(section.get("publications")),
+        "publications_count": section.get("publications_count"),
+        "academic_year": section.get("academic_year"),
+        "courses": _normalize_courses(section.get("courses")),
+        "table": _normalize_table(section.get("table")),
+    }
+
+
+def _normalize_links(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        text = str(item.get("text") or item.get("url") or "").strip()
+        url = str(item.get("url") or "").strip()
+        if text and url:
+            normalized.append({"text": text, "url": url})
+    return normalized
+
+
+def _normalize_year_entries(items: Any) -> list[dict[str, Any]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        text = str(item.get("text") or "").strip()
+        if text:
+            normalized.append({"year": item.get("year"), "text": text, "links": _normalize_links(item.get("links"))})
+    return normalized
+
+
+def _normalize_publications(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            text = str(item or "").strip()
+            if text:
+                normalized.append({"title": text, "text": text, "url": None})
+            continue
+        title = str(item.get("title") or "").strip()
+        text = str(item.get("text") or title).strip()
+        url = str(item.get("url") or "").strip()
+        if title or text:
+            normalized.append({"title": title or text, "text": text or title, "url": url or None})
+    return normalized
+
+
+def _normalize_courses(items: Any) -> list[dict[str, str | None]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            title = str(item or "").strip()
+            if title:
+                normalized.append({"title": title, "url": None})
+            continue
+        title = str(item.get("title") or "").strip()
+        url = str(item.get("url") or "").strip()
+        if title or url:
+            normalized.append({"title": title or url, "url": url or None})
+    return normalized
+
+
+def _normalize_table(table: Any) -> dict[str, Any] | None:
+    if not isinstance(table, dict):
+        return None
+    headers = _clean_list(table.get("headers"))
+    rows = []
+    for row in table.get("rows") or []:
+        if not isinstance(row, dict):
+            continue
+        cells = _clean_list(row.get("cells"))
+        if cells:
+            rows.append({"cells": cells, "link_url": row.get("link_url")})
+    if not headers and not rows:
+        return None
+    return {"headers": headers, "rows": rows}