Remove the superseded v5/v6/v7 search schema revisions

src/palace/manager/search/revision.py

@@ -21,7 +21,7 @@ def version(self) -> int:
 
     def name_for_index(self, base_name: str) -> str:
         """Produce the name of the index as it will appear in Opensearch,
-        such as 'circulation-works-v5'."""
+        such as 'circulation-works-v8'."""
         return f"{base_name}-v{self.version}"
 
     def script_name(self, script_name: str) -> str:

src/palace/manager/search/revision_directory.py

@@ -2,11 +2,9 @@
 
 from palace.manager.core.config import CannotLoadConfiguration
 from palace.manager.search.revision import SearchSchemaRevision
-from palace.manager.search.v5 import SearchV5
-from palace.manager.search.v6 import SearchV6
-from palace.manager.search.v7 import SearchV7
+from palace.manager.search.v8 import SearchV8
 
-REVISIONS = [SearchV5(), SearchV6(), SearchV7()]
+REVISIONS = [SearchV8()]
 
 
 class SearchRevisionDirectory:

src/palace/manager/search/v5.py → src/palace/manager/search/v8.py

@@ -15,23 +15,40 @@
 from palace.manager.search.revision import SearchSchemaRevision
 
 
-class SearchV5(SearchSchemaRevision):
+class SearchV8(SearchSchemaRevision):
+    """The version 8 search schema revision.
+
+    This revision is intentionally **self-contained**: it does not inherit from
+    any previous revision and defines its complete mapping (analyzers, filters,
+    and fields) directly. This is how new schema revisions are to be defined.
+
+    Every search revision should stand alone so that, once nothing in production
+    is using an older version, that version's module can simply be deleted.
+
+    Changes in v8:
+      - The shard and replica counts are set explicitly.
+      - sets search slow-query-log thresholds
+    """
+
     @property
     def version(self) -> int:
-        return 5
+        return 8
 
-    """
-    The body of this mapping looks for bibliographic information in
-    the core document, primarily used for matching search
-    requests. It also has nested documents, which are used for
-    filtering and ranking Works when generating other types of
-    feeds:
-
-    * licensepools -- the Work has these LicensePools (includes current
-      availability as a boolean, but not detailed availability information)
-    * customlists -- the Work is on these CustomLists
-    * contributors -- these Contributors worked on the Work
-    """
+    # The number of primary shards for indexes created by this revision.
+    # This setting is immutable once an index is created.
+    NUMBER_OF_SHARDS = 1
+
+    # The number of replicas for indexes created by this revision.
+    NUMBER_OF_REPLICAS = 1
+
+    # Slow-query-log thresholds applied to every index this revision creates.
+    #  Keys are relative to "index".
+    SEARCH_SLOWLOG_THRESHOLDS = {
+        "search.slowlog.threshold.query.warn": "3s",
+        "search.slowlog.threshold.query.info": "1s",
+        "search.slowlog.threshold.fetch.warn": "3s",
+        "search.slowlog.threshold.fetch.info": "1s",
+    }
 
     # Use regular expressions to normalized values in sortable fields.
     # These regexes are applied in order; that way "H. G. Wells"
@@ -71,7 +88,6 @@ def __init__(self) -> None:
         super().__init__()
 
         self._normalizers = {}
-        self._char_filters = {}
         self._filters = {}
         self._analyzers = {}
 
@@ -213,6 +229,8 @@ def __init__(self) -> None:
             "published": LONG,
             "audience": keyword(),
             "language": keyword(),
+            # Added in v6.
+            "lane_priority_level": INTEGER,
         }
 
         contributors = nested()
@@ -233,6 +251,8 @@ def __init__(self) -> None:
         licensepools.add_property("suppressed", BOOLEAN)
         licensepools.add_property("licensed", BOOLEAN)
         licensepools.add_property("medium", keyword())
+        # Added in v7.
+        licensepools.add_property("last_updated", LONG)
         self._fields["licensepools"] = licensepools
 
         identifiers = nested()
@@ -261,5 +281,11 @@ def mapping_document(self) -> SearchMappingDocument:
             normalizer=dict(self._normalizers),
             analyzer=dict(self._analyzers),
         )
+        # Index settings
+        document.settings["index"] = {
+            "number_of_shards": self.NUMBER_OF_SHARDS,
+            "number_of_replicas": self.NUMBER_OF_REPLICAS,
+            **self.SEARCH_SLOWLOG_THRESHOLDS,
+        }
         document.properties = self._fields
         return document

tests/manager/search/test_external_search.py

@@ -1,4 +1,3 @@
-import re
 from collections.abc import Callable
 
 import pytest
@@ -18,7 +17,6 @@
 )
 from palace.manager.search.filter import Filter
 from palace.manager.search.pagination import Pagination, SortKeyPagination
-from palace.manager.search.v5 import SearchV5
 from palace.manager.sqlalchemy.model.classification import Genre
 from palace.manager.sqlalchemy.model.collection import Collection
 from palace.manager.sqlalchemy.model.customlist import CustomList
@@ -169,54 +167,6 @@ def test_clear_search_documents(
         end_to_end_search_fixture.expect_results([], "")
 
 
-class TestSearchV5:
-    def test_character_filters(self):
-        # Verify the functionality of the regular expressions we tell
-        # Opensearch to use when normalizing fields that will be used
-        # for searching.
-        filters = []
-        for filter_name in SearchV5.AUTHOR_CHAR_FILTER_NAMES:
-            configuration = SearchV5.CHAR_FILTERS[filter_name]
-            find = re.compile(configuration["pattern"])
-            replace = configuration["replacement"]
-            # Hack to (imperfectly) convert Java regex format to Python format.
-            # $1 -> \1
-            replace = replace.replace("$", "\\")
-            filters.append((find, replace))
-
-        def filters_to(start, finish):
-            """When all the filters are applied to `start`,
-            the result is `finish`.
-            """
-            for find, replace in filters:
-                start = find.sub(replace, start)
-            assert start == finish
-
-        # Only the primary author is considered for sorting purposes.
-        filters_to("Adams, John Joseph ; Yu, Charles", "Adams, John Joseph")
-
-        # The special system author '[Unknown]' is replaced with
-        # REPLACEMENT CHARACTER so it will be last in sorted lists.
-        filters_to("[Unknown]", "\N{REPLACEMENT CHARACTER}")
-
-        # Periods are removed.
-        filters_to("Tepper, Sheri S.", "Tepper, Sheri S")
-        filters_to("Tepper, Sheri S", "Tepper, Sheri S")
-
-        # The initials of authors who go by initials are normalized
-        # so that their books all sort together.
-        filters_to("Wells, HG", "Wells, HG")
-        filters_to("Wells, H G", "Wells, HG")
-        filters_to("Wells, H.G.", "Wells, HG")
-        filters_to("Wells, H. G.", "Wells, HG")
-
-        # It works with up to three initials.
-        filters_to("Tolkien, J. R. R.", "Tolkien, JRR")
-
-        # Parentheticals are removed.
-        filters_to("Wells, H. G. (Herbert George)", "Wells, HG")
-
-
 class TestExternalSearchWithWorksData:
     adult_work: Work
     age_2_10: Work

tests/manager/search/test_search_v8.py

@@ -0,0 +1,73 @@
+import re
+
+from palace.manager.search.revision import SearchSchemaRevision
+from palace.manager.search.v8 import SearchV8
+
+
+class TestSearchV8:
+    def test_version(self):
+        assert SearchV8().version == 8
+
+    def test_self_contained(self):
+        """v8 must not chain off any previous revision, so old revisions can be
+        deleted once nothing in production uses them."""
+        assert SearchV8.__bases__ == (SearchSchemaRevision,)
+
+    def test_pins_index_settings(self):
+        """v8 sets the expected index settings."""
+        index = SearchV8().mapping_document().settings["index"]
+        for setting in [
+            "number_of_shards",
+            "number_of_replicas",
+            "search.slowlog.threshold.query.warn",
+            "search.slowlog.threshold.query.info",
+            "search.slowlog.threshold.fetch.warn",
+            "search.slowlog.threshold.fetch.info",
+        ]:
+            assert setting in index
+
+    def test_character_filters(self):
+        # Verify the functionality of the regular expressions we tell
+        # Opensearch to use when normalizing fields that will be used
+        # for searching.
+        filters = []
+        for filter_name in SearchV8.AUTHOR_CHAR_FILTER_NAMES:
+            configuration = SearchV8.CHAR_FILTERS[filter_name]
+            find = re.compile(configuration["pattern"])
+            replace = configuration["replacement"]
+            # Hack to (imperfectly) convert Java regex format to Python format.
+            # $1 -> \1
+            replace = replace.replace("$", "\\")
+            filters.append((find, replace))
+
+        def filters_to(start, finish):
+            """When all the filters are applied to `start`,
+            the result is `finish`.
+            """
+            for find, replace in filters:
+                start = find.sub(replace, start)
+            assert start == finish
+
+        # Only the primary author is considered for sorting purposes.
+        filters_to("Adams, John Joseph ; Yu, Charles", "Adams, John Joseph")
+
+        # The special system author '[Unknown]' is replaced with
+        # REPLACEMENT CHARACTER so it will be last in sorted lists.
+        filters_to("[Unknown]", "\N{REPLACEMENT CHARACTER}")
+
+        # Periods are removed.
+        filters_to("Tepper, Sheri S.", "Tepper, Sheri S")
+        filters_to("Tepper, Sheri S", "Tepper, Sheri S")
+
+        # The initials of authors who go by initials are normalized
+        # so that their books all sort together.
+        filters_to("Wells, HG", "Wells, HG")
+        filters_to("Wells, H G", "Wells, HG")
+        filters_to("Wells, H.G.", "Wells, HG")
+        filters_to("Wells, H. G.", "Wells, HG")
+
+        # It works with up to three initials.
+        filters_to("Tolkien, J. R. R.", "Tolkien, JRR")
+
+        # Parentheticals are removed.
+        filters_to("Wells, H. G. (Herbert George)", "Wells, HG")

tests/mocks/search.py

@@ -17,7 +17,7 @@
     SearchService,
     SearchServiceFailedDocument,
 )
-from palace.manager.search.v5 import SearchV5
+from palace.manager.search.v8 import SearchV8
 from palace.manager.sqlalchemy.model.work import Work
 
 
@@ -280,4 +280,4 @@ def mapping_document(self) -> SearchMappingDocument:
 class MockSearchSchemaRevisionLatest(MockSearchSchemaRevision):
     def __init__(self, version: int) -> None:
         super().__init__(version)
-        self._document = SearchV5().mapping_document()
+        self._document = SearchV8().mapping_document()