use locale en_US & other cleanup

.dockerignore

@@ -48,4 +48,8 @@ dmypy.json
 
 # docker bits
 Dockerfile*
-docker-compose*
+docker-compose*
+
+# Temp files
+tmp/
+

CHANGELOG.md

@@ -5,6 +5,14 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## Unreleased
+
+### Changed
+- Use locale en_US instead of c.utf-8
+
+### Removed
+- Generic fulltext search and tests
+
 ## [0.0.19] - 2022-04-15
 ### Added
 - github actions to build `develop`, `pr-x` and released version (e.g. `1.2.3`) Tags

Makefile

@@ -13,8 +13,7 @@ shell:
 	docker-compose run re_api sh
 
 reset:
-	docker-compose --rmi all -v
-	docker-compose build
+	docker-compose down --rmi all -v
 
 full_query_testing:
 	DO_QUERY_TESTING=full time python -m pytest -s $(QUERY_TESTING_FILE)

client_src/test/test_integration.py

@@ -2,7 +2,7 @@
 import os
 from uuid import uuid4
 
-from relation_engine_client import REClient
+from relation_engine_client.main import REClient
 from relation_engine_client.exceptions import RERequestError, RENotFound
 
 _API_URL = os.environ.get("RE_API_URL", "http://localhost:5000")

relation_engine_server/utils/json_validation.py

@@ -159,7 +159,7 @@ def resolve_remote(self, uri):
 
         if scheme in self.handlers:
             result = self.handlers[scheme](uri)
-        elif scheme in [u"http", u"https"]:
+        elif scheme in ["http", "https"]:
             # Requests has support for detecting the correct encoding of
             # json over http
             result = requests.get(uri).json()

spec/analyzers/icu_tokenize.json

@@ -2,7 +2,7 @@
     "name": "icu_tokenize",
     "type": "text",
     "properties": {
-        "locale": "c.utf-8",
+        "locale": "en_US",
         "accent": false,
         "case": "lower",
         "stemming": false,

spec/test/stored_queries/test_fulltext_search.py

@@ -1,12 +1,9 @@
 """
 Tests for stored queries involving a fulltext search:
-* Generic fulltext_search (should be used with caution because it can be slow and timeout at 60s)
 * Taxonomy taxonomy_search_species_strain
 * Taxonomy taxonomy_search_species_strain_no_sort
 
 The latter two are switched between depending on the length of the search text.
-These stored query tests  are all bundled in one test file because their original purpose is to do a species/strain
-name search on the ncbi_taxon collection
 
 These tests run within the re_api docker image, and require access to the ArangoDB, auth, and workspace images.
 """
@@ -251,148 +248,6 @@ def test_prefix_hit(self):
         )
 
 
-class TestFulltextSearchStoredQuery(unittest.TestCase):
-    @classmethod
-    def setUpClass(cls):
-        check_spec_test_env()
-        create_test_docs("ncbi_taxon", ncbi_taxa)
-
-    def test_ncbi_taxon_scinames(self):
-        """Happy path"""
-        for sciname in scinames_test_all:
-            _fulltext_search_query(
-                self,
-                coll="ncbi_taxon",
-                search_attrkey="scientific_name",
-                search_text=sciname,
-                ts=_NOW if sciname in scinames_test_latest else None,
-                filter_attr_expr=[
-                    {"rank": "species"},
-                    {"rank": "strain"},
-                    {"strain": True},
-                ],
-                offset=None,
-                limit=LIMIT,
-                select="scientific_name",
-                # ---
-                expect_error=False,
-                expect_hit=True,
-            )
-
-    def test_null_bind_params(self):
-        """Leave off parameters"""
-        for sciname in scinames_test_all:
-            _fulltext_search_query(
-                self,
-                coll="ncbi_taxon",
-                search_attrkey="scientific_name",
-                search_text=sciname,
-                ts=None,
-                filter_attr_expr=None,
-                offset=None,
-                limit=None,
-                select=None,
-                # ---
-                expect_error=False,
-                expect_hit=True,
-            )
-
-    def test_fully_specified_bind_params(self):
-        """Specify all parameters"""
-        for sciname in scinames_test_all:
-            _fulltext_search_query(
-                self,
-                coll="ncbi_taxon",
-                search_attrkey="scientific_name",
-                search_text=sciname,
-                ts=_NOW if sciname in scinames_test_latest else None,
-                filter_attr_expr=[
-                    {"rank": "species"},
-                    {"rank": "strain"},
-                    {"strain": True},
-                ],
-                offset=0,
-                limit=LIMIT,
-                select=["id", "scientific_name"],
-                # ---
-                expect_error=False,
-                expect_hit=True,
-            )
-
-    def test_extra_params(self):
-        """Extra params not in spec/aql"""
-        _fulltext_search_query(
-            self,
-            coll="ncbi_taxon",
-            search_attrkey="scientific_name",
-            search_text="esch",
-            ts=None,
-            filter_attr_expr=[
-                {"rank": "species"},
-                {"rank": "strain"},
-                {"strain": True},
-            ],
-            offset=0,
-            limit=LIMIT,
-            select=["id", "scientific_name"],
-            extra_unused_param=42,
-            # ---
-            expect_error=("Additional properties are not allowed"),
-        )
-
-    def test_validation_fail(self):
-        _fulltext_search_query(
-            self,
-            coll=[],
-            search_attrkey=42,
-            search_text={"hi": 1},
-            ts=None,
-            filter_attr_expr=None,
-            offset=None,
-            limit=None,
-            select=None,
-            # ---
-            expect_error="[] is not of type 'string'",
-        )
-
-    def test_aql_error(self):
-        for sciname in scinames_test_all:
-            _fulltext_search_query(
-                self,
-                coll="ncbi_taxon",
-                search_attrkey="fake_attrkey",
-                search_text=sciname,
-                ts=None,
-                filter_attr_expr=None,
-                offset=None,
-                limit=None,
-                select=None,
-                # ---
-                expect_error=True,
-            )
-
-    def test_no_hit(self):
-        for sciname in scinames_test_all:
-            _fulltext_search_query(
-                self,
-                coll="ncbi_taxon",
-                search_attrkey="scientific_name",
-                search_text=sciname[::-1],
-                ts=None,
-                filter_attr_expr=None,
-                offset=None,
-                limit=None,
-                select=None,
-                # ---
-                expect_error=False,
-                expect_hit=False,
-                expected_hits=[],
-            )
-
-
-# --- Test helpers ---
-
-
 def _switch_taxonomy_search_species_strain_queries(search_text):
     return (
         "taxonomy_search_species_strain_no_sort"