Improve tax profit search relevance

backend/search/api.py

@@ -17,7 +17,7 @@ from search.reviews import ReviewSnapshots, ReviewStore
 
 
 API_VERSION = "v1"
-SEARCH_ALGORITHM_VERSION = "search-4"
+SEARCH_ALGORITHM_VERSION = "search-5"
 LANGUAGES = {"ru", "ky"}
 CODE = re.compile(r"^[0-9]+$")
 MAX_PAGE_SIZE = 100

backend/search/minjust_opensearch.py

@@ -17,7 +17,7 @@ from typing import Iterator
 
 from search.catalog import authority_codes, legal_force_code, source_code
 
-APP_VERSION = "0.10.2"
+APP_VERSION = "0.10.3"
 LANGUAGES = {"ru", "ky"}
 DEFAULT_MAPPING = Path(__file__).with_name("minjust-fragments-index.json")
 

backend/search/query.py

@@ -23,6 +23,7 @@ LEGAL_FORM_ALIASES = {
     },
 }
 COMPANY_REGISTRATION_DOCUMENTS = (("230044970", 3000), ("667", 2000), ("4", 1000))
+TAX_PROFIT_DOCUMENTS = (("112340", 3000),)
 
 
 def query_variants(language: str, query: str) -> list[str]:
@@ -34,6 +35,26 @@ def query_variants(language: str, query: str) -> list[str]:
     return list(dict.fromkeys(variants))
 
 
+def document_priority_clauses(language: str, documents: tuple[tuple[str, int], ...]) -> list[dict]:
+    status = {"ru": "Действует", "ky": "Күчүндө"}[language]
+    return [
+        {
+            "constant_score": {
+                "filter": {
+                    "bool": {
+                        "filter": [
+                            {"term": {"document_code": code}},
+                            {"term": {f"status_{language}": status}},
+                        ]
+                    }
+                },
+                "boost": boost,
+            }
+        }
+        for code, boost in documents
+    ]
+
+
 def company_registration_clauses(language: str, query: str) -> list[dict]:
     non_registration_context = {
         "ru": (r"\bсч[её]т\w*", r"\bбанк\w*", r"\bфилиал\w*", r"\bпредставительств\w*"),
@@ -66,38 +87,28 @@ def company_registration_clauses(language: str, query: str) -> list[dict]:
     if not any(re.search(pattern.format(form=forms), normalized_query) for pattern in patterns):
         return []
 
-    status = {"ru": "Действует", "ky": "Күчүндө"}[language]
-    # ponytail: curated legal mapping; replace with a reviewed intent catalog when coverage expands.
-    def clause(document_code: str, boost: int) -> dict:
-        return {
-            "constant_score": {
-                "filter": {
-                    "bool": {
-                        "filter": [
-                            {"term": {"document_code": document_code}},
-                            {"term": {f"status_{language}": status}},
-                        ]
-                    }
-                },
-                "boost": boost,
-            }
-        }
+    return document_priority_clauses(language, COMPANY_REGISTRATION_DOCUMENTS)
 
-    return [clause(code, boost) for code, boost in COMPANY_REGISTRATION_DOCUMENTS]
+
+def tax_profit_clauses(language: str, query: str) -> list[dict]:
+    if language != "ru" or not re.search(r"\bналог\w*\s+(?:на\s+)?прибыл\w*\b", query.casefold()):
+        return []
+    # ponytail: exact topic anchor; expand only with verified tax-code sources.
+    return document_priority_clauses(language, TAX_PROFIT_DOCUMENTS)
 
 
 def build_search_query(language: str, query: str) -> dict:
-    intent_clauses = company_registration_clauses(language, query)
+    registration_clauses = company_registration_clauses(language, query)
+    intent_clauses = [*registration_clauses, *tax_profit_clauses(language, query)]
+    operator = "OR" if registration_clauses else "AND"
     full_text = [
-        {
-            "multi_match": {
-                "query": variant,
-                "fields": [f"document_name_{language}^4", f"text_{language}"],
-                "type": "cross_fields",
-                "operator": "OR" if intent_clauses else "AND",
-            }
-        }
+        clause
         for variant in query_variants(language, query)
+        for clause in (
+            {"match": {f"text_{language}": {"query": variant, "operator": operator}}},
+            {"match": {f"document_name_{language}": {"query": variant, "operator": operator, "boost": 4}}},
+            {"match_phrase": {f"text_{language}": {"query": variant, "boost": 3}}},
+        )
     ]
     planned = {"should": [*full_text, *intent_clauses], "minimum_should_match": 1}
     return {"bool": planned}

backend/search/review.html

@@ -117,7 +117,7 @@
   <div class="review__actions"><div class="review__actions-inner"><label>Ваше имя или псевдоним<input id="reviewer" maxlength="120" autocomplete="name" placeholder="Например, Айжан К."></label> <label>Комментарий к выдаче <input id="overall-comment" maxlength="4000" placeholder="Что важно учесть? (необязательно)"></label> <button class="review__button--primary" id="save" type="button">Сохранить разметку</button></div></div>
   <dialog id="document-dialog"><button class="review__dialog-close" id="dialog-close" type="button">Закрыть</button><h2 id="dialog-heading">Документ</h2><div class="review__document-body" id="dialog-body"></div></dialog>
   <div class="review__tour-spotlight" id="tutorial-spotlight" hidden aria-hidden="true"></div><dialog class="review__tour" id="tutorial-dialog" aria-labelledby="tutorial-heading" aria-describedby="tutorial-text"><div class="review__tour-content"><p class="review__tour-kicker">Короткое знакомство</p><h2 id="tutorial-heading"></h2><p id="tutorial-text"></p><div class="review__tour-footer"><span class="review__tour-progress" id="tutorial-progress"></span><div class="review__tour-actions"><button id="tutorial-skip" type="button">Пропустить</button><button class="review__button--primary" id="tutorial-next" type="button">Далее</button></div></div></div></dialog>
-  <footer class="review__header">Акылдаш · Backend v0.10.2 · Внутренняя лаборатория релевантности</footer>
+  <footer class="review__header">Акылдаш · Backend v0.10.3 · Внутренняя лаборатория релевантности</footer>
   <script>
     const DRAFT_KEY = 'akyldash-search-review-draft';
     const TOUR_KEY = 'akyldash-search-review-tour-seen';