data-syncmaster 0.2.3__tar.gz → 0.2.5__tar.gz

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/PKG-INFO

@@ -1,8 +1,9 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: data-syncmaster
-Version: 0.2.3
+Version: 0.2.5
 Summary: Syncmaster REST API + Worker
 License: Apache-2.0
+License-File: LICENSE.txt
 Keywords: Syncmaster,REST,API,Worker,Spark,Transfer,ETL
 Author: DataOps.ETL
 Author-email: onetools@mts.ru
@@ -18,6 +19,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
@@ -31,24 +33,25 @@ Requires-Dist: asgi-correlation-id (>=4.3.4,<5.0.0) ; extra == "server" or extra
 Requires-Dist: asyncpg (>=0.30.0,<0.31.0) ; extra == "server" or extra == "scheduler"
 Requires-Dist: celery (>=5.5.0,<6.0.0) ; extra == "server" or extra == "worker" or extra == "scheduler"
 Requires-Dist: coloredlogs ; extra == "server" or extra == "worker" or extra == "scheduler"
-Requires-Dist: fastapi (>=0.115.12,<0.116.0) ; extra == "server"
+Requires-Dist: fastapi (>=0.115.12,<0.119.0) ; extra == "server"
 Requires-Dist: horizon-hwm-store (>=1.1.2,<2.0.0) ; extra == "worker"
 Requires-Dist: itsdangerous (>=2.2.0,<3.0.0) ; extra == "server"
 Requires-Dist: jinja2 (>=3.1.6,<4.0.0) ; extra == "server" or extra == "worker"
-Requires-Dist: onetl[all] (>=0.13.4,<0.14.0) ; extra == "worker"
+Requires-Dist: onetl[all] (>=0.13.5,<0.15.0) ; extra == "worker"
 Requires-Dist: psycopg2-binary (>=2.9.10,<3.0.0) ; extra == "server" or extra == "worker"
-Requires-Dist: pydantic (>=2.11.1,<3.0.0)
+Requires-Dist: pydantic (>=2.11.7,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.8.1,<3.0.0) ; extra == "server" or extra == "worker" or extra == "scheduler"
 Requires-Dist: pyjwt (>=2.10.1,<3.0.0) ; extra == "server"
+Requires-Dist: pyspark (<4.0.0) ; extra == "worker"
 Requires-Dist: python-json-logger ; extra == "server" or extra == "worker" or extra == "scheduler"
 Requires-Dist: python-keycloak (>=5.3.1,<6.0.0) ; extra == "server"
 Requires-Dist: python-multipart (>=0.0.20,<0.0.21) ; extra == "server"
 Requires-Dist: pyyaml ; extra == "server" or extra == "worker" or extra == "scheduler"
 Requires-Dist: sqlalchemy (>=2.0.40,<3.0.0) ; extra == "server" or extra == "worker" or extra == "scheduler"
-Requires-Dist: sqlalchemy-utils (>=0.41.2,<0.42.0) ; extra == "server" or extra == "worker" or extra == "scheduler"
+Requires-Dist: sqlalchemy-utils (>=0.41.2,<0.43.0) ; extra == "server" or extra == "worker" or extra == "scheduler"
 Requires-Dist: starlette-exporter (>=0.23.0,<0.24.0) ; extra == "server"
-Requires-Dist: uuid6 (>=2024.7.10,<2025.0.0) ; extra == "server" or extra == "worker"
-Requires-Dist: uvicorn (>=0.34.0,<0.35.0) ; extra == "server"
+Requires-Dist: uuid6 (>=2025.0.0,<2026.0.0) ; extra == "server" or extra == "worker"
+Requires-Dist: uvicorn (>=0.34,<0.38) ; extra == "server"
 Project-URL: CI/CD, https://github.com/MobileTeleSystems/syncmaster/actions
 Project-URL: Documentation, https://syncmaster.readthedocs.io
 Project-URL: Homepage, https://github.com/MobileTeleSystems/syncmaster
@@ -78,8 +81,9 @@ Data.SyncMaster
     :target: https://syncmaster.readthedocs.io
 .. |Build Status| image:: https://github.com/MobileTeleSystems/syncmaster/workflows/Run%20All%20Tests/badge.svg
     :target: https://github.com/MobileTeleSystems/syncmaster/actions
-.. |Coverage| image:: https://codecov.io/gh/MobileTeleSystems/syncmaster/graph/badge.svg?token=ky7UyUxolB
-    :target: https://codecov.io/gh/MobileTeleSystems/syncmaster
+.. |Coverage| image:: https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/
+    MTSOnGithub/03e73a82ecc4709934540ce8201cc3b4/raw/syncmaster_badge.json
+    :target: https://github.com/MobileTeleSystems/syncmaster/actions
 .. |pre-commit.ci| image:: https://results.pre-commit.ci/badge/github/MobileTeleSystems/syncmaster/develop.svg
     :target: https://results.pre-commit.ci/latest/github/MobileTeleSystems/syncmaster/develop
 

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/README.rst

@@ -20,8 +20,9 @@ Data.SyncMaster
     :target: https://syncmaster.readthedocs.io
 .. |Build Status| image:: https://github.com/MobileTeleSystems/syncmaster/workflows/Run%20All%20Tests/badge.svg
     :target: https://github.com/MobileTeleSystems/syncmaster/actions
-.. |Coverage| image:: https://codecov.io/gh/MobileTeleSystems/syncmaster/graph/badge.svg?token=ky7UyUxolB
-    :target: https://codecov.io/gh/MobileTeleSystems/syncmaster
+.. |Coverage| image:: https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/
+    MTSOnGithub/03e73a82ecc4709934540ce8201cc3b4/raw/syncmaster_badge.json
+    :target: https://github.com/MobileTeleSystems/syncmaster/actions
 .. |pre-commit.ci| image:: https://results.pre-commit.ci/badge/github/MobileTeleSystems/syncmaster/develop.svg
     :target: https://results.pre-commit.ci/latest/github/MobileTeleSystems/syncmaster/develop
 

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "data-syncmaster"
-version = "0.2.3"
+version = "0.2.5"
 license = "Apache-2.0"
 description = "Syncmaster REST API + Worker"
 authors = ["DataOps.ETL <onetools@mts.ru>"]
@@ -44,22 +44,23 @@ exclude = [
 
 [tool.poetry.dependencies]
 python = "^3.11"
-pydantic = "^2.11.1"
+pydantic = "^2.11.7"
 pydantic-settings = { version = "^2.8.1", optional = true }
 sqlalchemy = { version = "^2.0.40", optional = true }
-sqlalchemy-utils = { version = "^0.41.2", optional = true }
-fastapi = { version = "^0.115.12", optional = true}
+sqlalchemy-utils = { version = ">=0.41.2,<0.43.0", optional = true }
+fastapi = { version = ">=0.115.12,<0.119.0", optional = true}
 asgi-correlation-id = {version = "^4.3.4", optional = true}
-uvicorn = { version = "^0.34.0", optional = true }
+uvicorn = { version = ">=0.34,<0.38", optional = true }
 alembic = { version = "^1.15.2", optional = true }
 pyjwt = { version = "^2.10.1", optional = true }
 jinja2 = { version = "^3.1.6", optional = true }
 python-multipart = { version = "^0.0.20", optional = true }
 celery = { version = "^5.5.0", optional = true }
-onetl = { version = "^0.13.4", extras = ["all"], optional = true }
+onetl = { version = ">=0.13.5,<0.15.0", extras = ["all"], optional = true }
+pyspark = { version = "<4.0.0", optional = true }
 pyyaml = { version = "*", optional = true }
 psycopg2-binary = { version = "^2.9.10", optional = true }
-uuid6 = {version = "^2024.7.10", optional = true}
+uuid6 = {version = "^2025.0.0", optional = true}
 coloredlogs = {version = "*", optional = true}
 python-json-logger = {version = "*", optional = true}
 asyncpg = { version = "^0.30.0", optional = true }
@@ -99,6 +100,7 @@ worker = [
     "sqlalchemy-utils",
     "celery",
     "onetl",
+    "pyspark",
     "asgi-correlation-id",
     "jinja2",
     "psycopg2-binary",
@@ -124,16 +126,17 @@ scheduler = [
 [tool.poetry.group.test.dependencies]
 pytest = "^8.3.5"
 httpx = "^0.28.1"
-pytest-asyncio = "^0.26.0"
-pytest-randomly = "^3.15.0"
-pytest-rerunfailures = "^15.0"
+pytest-asyncio = ">=0.26.0,<1.0"
+pytest-randomly = ">=3.15,<5.0"
+pytest-rerunfailures = ">=15,<17"
 pytest-deadfixtures = "^2.2.1"
 pytest-mock = "^3.14.0"
 pytest-lazy-fixtures = "^1.1.1"
-faker = "^37.1.0"
-coverage = "^7.8.0"
-gevent = "^24.11.1"
-responses = "^0.25.7"
+faker = "^37.4.0"
+coverage = "^7.9.1"
+gevent = ">=24.11.1,<26.0.0"
+respx = "^0.22.0"
+dirty-equals = "^0.9.0"
 
 [tool.poetry.group.dev.dependencies]
 mypy = "^1.15.0"
@@ -142,12 +145,13 @@ black = "^25.1.0"
 flake8 = "^7.2.0"
 flake8-pyproject = "^1.2.3"
 sqlalchemy = {extras = ["mypy"], version = "^2.0.40"}
+types-jwcrypto = "^1.5.0"
 
 [tool.poetry.group.docs.dependencies]
 autodoc-pydantic = "^2.2.0"
 numpydoc = "^1.8.0"
 sphinx = "^8.2.3"
-furo = "^2024.8.6"
+furo = ">=2024.8.6,<2026.0.0"
 sphinx-copybutton = "^0.5.2"
 sphinxcontrib-towncrier = "^0.5.0a0"
 towncrier = "^24.8.0"

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/__init__.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2023-2024 MTS PJSC
 # SPDX-License-Identifier: Apache-2.0
 
-_raw_version = "0.2.3"
+_raw_version = "0.2.5"
 # version always contain only release number like 0.0.1
 __version__ = ".".join(_raw_version.split(".")[:3])  # noqa: WPS410

data_syncmaster-0.2.5/syncmaster/db/migrations/versions/2025-08-10_0012_update_ts.py

@@ -0,0 +1,243 @@
+# SPDX-FileCopyrightText: 2023-2024 MTS PJSC
+# SPDX-License-Identifier: Apache-2.0
+"""Update text search
+
+Revision ID: 0012
+Revises: 0011
+Create Date: 2025-08-10 20:03:02.105470
+
+"""
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "0012"
+down_revision = "0011"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.drop_index(op.f("idx_connection_search_vector"), table_name="connection", postgresql_using="gin")
+    op.drop_column("connection", "search_vector")
+    op.drop_column("group", "search_vector")
+    op.drop_index(op.f("idx_transfer_search_vector"), table_name="transfer", postgresql_using="gin")
+    op.drop_column("transfer", "search_vector")
+    op.drop_column("queue", "search_vector")
+
+    op.add_column(
+        "connection",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed(
+                """
+                -- === NAME FIELD ===
+                -- Russian stemming for better morphological matching of regular words
+                to_tsvector('russian', coalesce(name, ''))
+                -- Simple dictionary (no stemming) for exact token match
+                || to_tsvector('simple', coalesce(name, ''))
+                -- Simple dictionary with translate(): split by . / - _ : \
+                -- (used when 'name' contains technical fields)
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(name, ''), './-_:\\', '      ')
+                )
+
+                -- === HOST FIELD (from JSON) ===
+                -- Simple dictionary (no stemming) for exact match
+                || to_tsvector('simple', coalesce(data->>'host', ''))
+                -- Simple dictionary with translate(): split by . / - _ : \\ for partial token matching
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(data->>'host', ''), './-_:\\', '      ')
+                )
+                """,
+                persisted=True,
+            ),
+            nullable=False,
+        ),
+    )
+    op.create_index(
+        "idx_connection_search_vector",
+        "connection",
+        ["search_vector"],
+        unique=False,
+        postgresql_using="gin",
+    )
+
+    op.add_column(
+        "group",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed(
+                """
+                -- === NAME FIELD ===
+                -- Russian stemming for better morphological matching of regular words
+                to_tsvector('russian', coalesce(name, ''))
+                -- Simple dictionary (no stemming) for exact token match
+                || to_tsvector('simple', coalesce(name, ''))
+                -- Simple dictionary with translate(): split by . / - _ : \
+                -- (used when 'name' contains technical fields)
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(name, ''), './-_:\\', '      ')
+                )
+                """,
+                persisted=True,
+            ),
+            nullable=False,
+        ),
+    )
+
+    op.add_column(
+        "queue",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed(
+                """
+                -- === NAME FIELD ===
+                -- Russian stemming for better morphological matching of regular words
+                to_tsvector('russian', coalesce(name, ''))
+                -- Simple dictionary (no stemming) for exact token match
+                || to_tsvector('simple', coalesce(name, ''))
+                -- Simple dictionary with translate(): split by . / - _ : \
+                -- (used when 'name' contains technical fields)
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(name, ''), './-_:\\', '      ')
+                )
+                """,
+                persisted=True,
+            ),
+            nullable=False,
+        ),
+    )
+
+    op.add_column(
+        "transfer",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed(
+                """
+                -- === NAME FIELD ===
+                -- Russian stemming for better morphological matching of regular words
+                to_tsvector('russian', coalesce(name, ''))
+                -- Simple dictionary (no stemming) for exact token match
+                || to_tsvector('simple', coalesce(name, ''))
+                -- Simple dictionary with translate(): split by . / - _ : \
+                -- (used when 'name' contains technical fields)
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(name, ''), './-_:\\', '      ')
+                )
+
+                -- === TABLE NAME FIELDS ===
+                -- Simple dictionary (no stemming) for exact match
+                || to_tsvector('simple', coalesce(source_params->>'table_name', ''))
+                || to_tsvector('simple', coalesce(target_params->>'table_name', ''))
+                -- Simple dictionary with translate(): split by . / - _ : \\ for partial token matching
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(source_params->>'table_name', ''), './-_:\\', '      ')
+                )
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(target_params->>'table_name', ''), './-_:\\', '      ')
+                )
+
+                -- === DIRECTORY PATH FIELDS ===
+                -- Simple dictionary (no stemming) for exact match
+                || to_tsvector('simple', coalesce(source_params->>'directory_path', ''))
+                || to_tsvector('simple', coalesce(target_params->>'directory_path', ''))
+                -- Simple dictionary with translate(): split by . / - _ : \\ for partial token matching
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(source_params->>'directory_path', ''), './-_:\\', '      ')
+                )
+                || to_tsvector(
+                    'simple',
+                    translate(coalesce(target_params->>'directory_path', ''), './-_:\\', '      ')
+                )
+                """,
+                persisted=True,
+            ),
+            nullable=False,
+        ),
+    )
+    op.create_index("idx_transfer_search_vector", "transfer", ["search_vector"], unique=False, postgresql_using="gin")
+
+
+def downgrade() -> None:
+    op.drop_index("idx_transfer_search_vector", table_name="transfer", postgresql_using="gin")
+    op.drop_column("transfer", "search_vector")
+    op.drop_column("group", "search_vector")
+    op.drop_index("idx_connection_search_vector", table_name="connection", postgresql_using="gin")
+    op.drop_column("connection", "search_vector")
+    op.drop_column("queue", "search_vector")
+
+    op.add_column(
+        "transfer",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed(
+                "to_tsvector('english'::regconfig, (((((((((((((((((((name)::text || ' '::text) || COALESCE(json_extract_path_text(source_params, VARIADIC ARRAY['table_name'::text]), ''::text)) || ' '::text) || COALESCE(json_extract_path_text(target_params, VARIADIC ARRAY['table_name'::text]), ''::text)) || ' '::text) || COALESCE(json_extract_path_text(source_params, VARIADIC ARRAY['directory_path'::text]), ''::text)) || ' '::text) || COALESCE(json_extract_path_text(target_params, VARIADIC ARRAY['directory_path'::text]), ''::text)) || ' '::text) || translate((name)::text, './'::text, '  '::text)) || ' '::text) || COALESCE(translate(json_extract_path_text(source_params, VARIADIC ARRAY['table_name'::text]), './'::text, '  '::text), ''::text)) || ' '::text) || COALESCE(translate(json_extract_path_text(target_params, VARIADIC ARRAY['table_name'::text]), './'::text, '  '::text), ''::text)) || ' '::text) || COALESCE(translate(json_extract_path_text(source_params, VARIADIC ARRAY['directory_path'::text]), './'::text, '  '::text), ''::text)) || ' '::text) || COALESCE(translate(json_extract_path_text(target_params, VARIADIC ARRAY['directory_path'::text]), './'::text, '  '::text), ''::text)))",
+                persisted=True,
+            ),
+            autoincrement=False,
+            nullable=False,
+        ),
+    )
+    op.create_index(
+        op.f("idx_transfer_search_vector"),
+        "transfer",
+        ["search_vector"],
+        unique=False,
+        postgresql_using="gin",
+    )
+    op.add_column(
+        "group",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed("to_tsvector('english'::regconfig, (name)::text)", persisted=True),
+            autoincrement=False,
+            nullable=False,
+        ),
+    )
+    op.add_column(
+        "connection",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed(
+                "to_tsvector('english'::regconfig, (((((name)::text || ' '::text) || COALESCE(json_extract_path_text(data, VARIADIC ARRAY['host'::text]), ''::text)) || ' '::text) || COALESCE(translate(json_extract_path_text(data, VARIADIC ARRAY['host'::text]), '.'::text, ' '::text), ''::text)))",
+                persisted=True,
+            ),
+            autoincrement=False,
+            nullable=False,
+        ),
+    )
+    op.create_index(
+        op.f("idx_connection_search_vector"),
+        "connection",
+        ["search_vector"],
+        unique=False,
+        postgresql_using="gin",
+    )
+    op.add_column(
+        "queue",
+        sa.Column(
+            "search_vector",
+            postgresql.TSVECTOR(),
+            sa.Computed("to_tsvector('english'::regconfig, (name)::text)", persisted=True),
+            autoincrement=False,
+            nullable=False,
+        ),
+    )

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/db/models/connection.py

@@ -41,11 +41,25 @@ class Connection(Base, ResourceMixin, TimestampMixin):
         TSVECTOR,
         Computed(
             """
-            to_tsvector(
-                'english'::regconfig,
-                name || ' ' ||
-                COALESCE(json_extract_path_text(data, 'host'), '') || ' ' ||
-                COALESCE(translate(json_extract_path_text(data, 'host'), '.', ' '), '')
+            -- === NAME FIELD ===
+            -- Russian stemming for better morphological matching of regular words
+            to_tsvector('russian', coalesce(name, ''))
+            -- Simple dictionary (no stemming) for exact token match
+            || to_tsvector('simple', coalesce(name, ''))
+            -- Simple dictionary with translate(): split by . / - _ : \
+            -- (used when 'name' contains technical fields)
+            || to_tsvector(
+                'simple',
+                translate(coalesce(name, ''), './-_:\\', '      ')
+            )
+
+            -- === HOST FIELD (from JSON) ===
+            -- Simple dictionary (no stemming) for exact match
+            || to_tsvector('simple', coalesce(data->>'host', ''))
+            -- Simple dictionary with translate(): split by . / - _ : \\ for partial token matching
+            || to_tsvector(
+                'simple',
+                translate(coalesce(data->>'host', ''), './-_:\\', '      ')
             )
             """,
             persisted=True,

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/db/models/group.py

@@ -77,13 +77,26 @@ class Group(Base, TimestampMixin):
 
     owner: Mapped[User] = relationship(User)
     queue: Mapped[Queue] = relationship(back_populates="group", cascade="all, delete-orphan")
-
     search_vector: Mapped[str] = mapped_column(
         TSVECTOR,
-        Computed("to_tsvector('english'::regconfig, name)", persisted=True),
+        Computed(
+            """
+            -- === NAME FIELD ===
+            -- Russian stemming for better morphological matching of regular words
+            to_tsvector('russian', coalesce(name, ''))
+            -- Simple dictionary (no stemming) for exact token match
+            || to_tsvector('simple', coalesce(name, ''))
+            -- Simple dictionary with translate(): split by . / - _ : \
+            -- (used when 'name' contains technical fields)
+            || to_tsvector(
+                'simple',
+                translate(coalesce(name, ''), './-_:\\', '      ')
+            )
+            """,
+            persisted=True,
+        ),
         nullable=False,
         deferred=True,
-        doc="Full-text search vector",
     )
 
     def __repr__(self) -> str:

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/db/models/queue.py

@@ -25,10 +25,24 @@ class Queue(Base, ResourceMixin, TimestampMixin):
 
     search_vector: Mapped[str] = mapped_column(
         TSVECTOR,
-        Computed("to_tsvector('english'::regconfig, name)", persisted=True),
+        Computed(
+            """
+            -- === NAME FIELD ===
+            -- Russian stemming for better morphological matching of regular words
+            to_tsvector('russian', coalesce(name, ''))
+            -- Simple dictionary (no stemming) for exact token match
+            || to_tsvector('simple', coalesce(name, ''))
+            -- Simple dictionary with translate(): split by . / - _ : \
+            -- (used when 'name' contains technical fields)
+            || to_tsvector(
+                'simple',
+                translate(coalesce(name, ''), './-_:\\', '      ')
+            )
+            """,
+            persisted=True,
+        ),
         nullable=False,
         deferred=True,
-        doc="Full-text search vector",
     )
 
     def __repr__(self):

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/db/models/transfer.py

@@ -65,18 +65,44 @@ class Transfer(
         TSVECTOR,
         Computed(
             """
-            to_tsvector(
-                'english'::regconfig,
-                name || ' ' ||
-                COALESCE(json_extract_path_text(source_params, 'table_name'), '') || ' ' ||
-                COALESCE(json_extract_path_text(target_params, 'table_name'), '') || ' ' ||
-                COALESCE(json_extract_path_text(source_params, 'directory_path'), '') || ' ' ||
-                COALESCE(json_extract_path_text(target_params, 'directory_path'), '') || ' ' ||
-                translate(name, './', '  ') || ' ' ||
-                COALESCE(translate(json_extract_path_text(source_params, 'table_name'), './', '  '), '') || ' ' ||
-                COALESCE(translate(json_extract_path_text(target_params, 'table_name'), './', '  '), '') || ' ' ||
-                COALESCE(translate(json_extract_path_text(source_params, 'directory_path'), './', '  '), '') || ' ' ||
-                COALESCE(translate(json_extract_path_text(target_params, 'directory_path'), './', '  '), '')
+            -- === NAME FIELD ===
+            -- Russian stemming for better morphological matching of regular words
+            to_tsvector('russian', coalesce(name, ''))
+            -- Simple dictionary (no stemming) for exact token match
+            || to_tsvector('simple', coalesce(name, ''))
+            -- Simple dictionary with translate(): split by . / - _ : \
+            -- (used when 'name' contains technical fields)
+            || to_tsvector(
+                'simple',
+                translate(coalesce(name, ''), './-_:\\', '      ')
+            )
+
+            -- === TABLE NAME FIELDS ===
+            -- Simple dictionary (no stemming) for exact match
+            || to_tsvector('simple', coalesce(source_params->>'table_name', ''))
+            || to_tsvector('simple', coalesce(target_params->>'table_name', ''))
+            -- Simple dictionary with translate(): split by . / - _ : \\ for partial token matching
+            || to_tsvector(
+                'simple',
+                translate(coalesce(source_params->>'table_name', ''), './-_:\\', '      ')
+            )
+            || to_tsvector(
+                'simple',
+                translate(coalesce(target_params->>'table_name', ''), './-_:\\', '      ')
+            )
+
+            -- === DIRECTORY PATH FIELDS ===
+            -- Simple dictionary (no stemming) for exact match
+            || to_tsvector('simple', coalesce(source_params->>'directory_path', ''))
+            || to_tsvector('simple', coalesce(target_params->>'directory_path', ''))
+            -- Simple dictionary with translate(): split by . / - _ : \\ for partial token matching
+            || to_tsvector(
+                'simple',
+                translate(coalesce(source_params->>'directory_path', ''), './-_:\\', '      ')
+            )
+            || to_tsvector(
+                'simple',
+                translate(coalesce(target_params->>'directory_path', ''), './-_:\\', '      ')
             )
             """,
             persisted=True,

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/db/repositories/base.py

@@ -3,7 +3,16 @@
 from abc import ABC
 from typing import Any, Generic, TypeVar
 
-from sqlalchemy import ScalarResult, Select, delete, func, insert, select, update
+from sqlalchemy import (
+    ColumnElement,
+    ScalarResult,
+    Select,
+    delete,
+    func,
+    insert,
+    select,
+    update,
+)
 from sqlalchemy.exc import NoResultFound
 from sqlalchemy.ext.asyncio import AsyncSession
 
@@ -98,8 +107,7 @@ class Repository(Generic[Model], ABC):
             page_size=page_size,
         )
 
-    def _construct_vector_search(self, query: Select, search_query: str) -> Select:
-        ts_query = func.plainto_tsquery("english", search_query)
+    def _construct_vector_search(self, query: Select, ts_query: ColumnElement) -> Select:
         query = (
             query.where(self._model.search_vector.op("@@")(ts_query))
             .add_columns(func.ts_rank(self._model.search_vector, ts_query).label("rank"))

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/db/repositories/connection.py

@@ -8,6 +8,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from syncmaster.db.models import Connection
 from syncmaster.db.repositories.repository_with_owner import RepositoryWithOwner
+from syncmaster.db.repositories.search import make_tsquery
 from syncmaster.db.utils import Pagination
 from syncmaster.exceptions import EntityNotFoundError, SyncmasterError
 from syncmaster.exceptions.connection import (
@@ -35,9 +36,8 @@ class ConnectionRepository(RepositoryWithOwner[Connection]):
             Connection.group_id == group_id,
         )
         if search_query:
-            processed_query = search_query.replace(".", " ")
-            combined_query = f"{search_query} {processed_query}"
-            stmt = self._construct_vector_search(stmt, combined_query)
+            ts_query = make_tsquery(search_query)
+            stmt = self._construct_vector_search(stmt, ts_query)
 
         if connection_type is not None:
             stmt = stmt.where(Connection.type.in_(connection_type))

{data_syncmaster-0.2.3 → data_syncmaster-0.2.5}/syncmaster/db/repositories/group.py

@@ -10,6 +10,7 @@ from sqlalchemy.orm import joinedload
 
 from syncmaster.db.models import Group, GroupMemberRole, User, UserGroup
 from syncmaster.db.repositories.base import Repository
+from syncmaster.db.repositories.search import make_tsquery
 from syncmaster.db.utils import Pagination, Permission
 from syncmaster.exceptions import EntityNotFoundError, SyncmasterError
 from syncmaster.exceptions.group import (
@@ -33,7 +34,8 @@ class GroupRepository(Repository[Group]):
     ) -> Pagination:
         stmt = select(Group)
         if search_query:
-            stmt = self._construct_vector_search(stmt, search_query)
+            ts_query = make_tsquery(search_query)
+            stmt = self._construct_vector_search(stmt, ts_query)
 
         paginated_result = await self._paginate_scalar_result(
             query=stmt.order_by(Group.name),
@@ -78,7 +80,8 @@ class GroupRepository(Repository[Group]):
 
             # apply search filtering if a search query is provided
             if search_query:
-                owned_groups_stmt = self._construct_vector_search(owned_groups_stmt, search_query)
+                ts_query = make_tsquery(search_query)
+                owned_groups_stmt = self._construct_vector_search(owned_groups_stmt, ts_query)
 
             # get total count of owned groups
             total_owned_groups = (
@@ -114,7 +117,8 @@ class GroupRepository(Repository[Group]):
 
         # apply search filtering if a search query is provided
         if search_query:
-            user_groups_stmt = self._construct_vector_search(user_groups_stmt, search_query)
+            ts_query = make_tsquery(search_query)
+            user_groups_stmt = self._construct_vector_search(user_groups_stmt, ts_query)
 
         # get total count of user groups
         total_user_groups = (