Dikootje/sqlfluff
1
0
Fork 0
forked from repo-mirrors/sqlfluff
Code Pull Requests Activity

Auto generate dialect docs (#6153)

Browse Source 
Co-authored-by: Cameron <105471409+keraion@users.noreply.github.com>
This commit is contained in:
Alan Cruickshank
2024-09-08 15:28:30 +01:00
committed by GitHub
parent f4229899ec
commit 2464d36c28
35 changed files with 249 additions and 274 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.readthedocs.yml
View File

@@ -25,6 +25,6 @@ build:
tools:
python: "3.11"
jobs:
# Before building, generate the rule docs
# Before building, generate the rule & dialect docs
pre_build:
- python docs/generate-rule-docs.py
- python docs/generate-auto-docs.py

2
docs/Makefile
View File

@@ -20,5 +20,5 @@ help:
# Catch-all target: route all unknown targets to Sphinx using the new
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
%: Makefile
python generate-rule-docs.py
python generate-auto-docs.py
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

45
docs/generate-rule-docs.py → docs/generate-auto-docs.py
View File

@@ -1,9 +1,24 @@
"""Generate rule documentation automatically."""
"""Generate some documentation automatically.
This script generates partial documentation sections (i.e. the content of
`/docs/source/_partials/`) by importing SQLFluff and extracting data about
rules and dialects.
It should run before every docs generation so that those partial .rst files
can then be correctly referenced by other sections of the docs. For example
this file builds the file `/docs/source/_partials/rule_summaries.rst`, which
is then inserted into `/docs/source/reference/rules.rst` using the directive
`.. include:: ../_partials/rule_summaries.rst`.
This script is referenced in the `Makefile` and the `make.bat` file to ensure
it is run at the appropriate moment.
"""
import json
from collections import defaultdict
from pathlib import Path
import sqlfluff
from sqlfluff.core.plugin.host import get_plugin_manager
base_path = Path(__file__).parent.absolute()
@@ -110,3 +125,31 @@ with open(base_path / "source/_partials/rule_summaries.rst", "w", encoding="utf8
f.write("\n\n")
print("Rule Docs Generation: Done")
# Extract all the dialects.
print("Dialect Docs Generation: Reading Dialects...")
# We make a dictionary of all of them first, because we want to force the ANSI
# one to be first.
dialect_dict = {dialect.label: dialect for dialect in sqlfluff.list_dialects()}
dialect_list = [dialect_dict["ansi"]] + [
dialect for dialect_name, dialect in dialect_dict.items() if dialect_name != "ansi"
]
# Write each of the summary files.
print("Dialect Docs Generation: Writing Dialect Summaries...")
with open(
base_path / "source/_partials/dialect_summaries.rst", "w", encoding="utf8"
) as f:
f.write(autogen_header)
for dialect in dialect_list:
f.write(
f".. _{dialect.label}_dialect_ref:\n\n"
f"{dialect.name}\n{'-' * len(dialect.name)}\n\n"
f"**Label**: ``{dialect.label}``\n\n"
)
if dialect.label != "ansi":
f.write(
f"**Inherits from**: :ref:`{dialect.inherits_from}_dialect_ref`\n\n"
)
if dialect.docstring:
f.write(dialect.docstring + "\n\n")

4
docs/make.bat
View File

@@ -25,8 +25,8 @@ if errorlevel 9009 (
exit /b 1
)
REM Generate the rule docs
python generate-rule-docs.py
REM Generate the rule & dialect docs
python generate-auto-docs.py
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
goto end

1
docs/source/_partials/.gitignore vendored
View File

@@ -1,3 +1,4 @@
rule_table.rst
rule_summaries.rst
rule_list.json
dialect_summaries.rst

2
docs/source/_partials/README.md
View File

@@ -6,4 +6,4 @@ Some of those files are also auto-generated by scripts,
in which case they should be included in the `.gitignore`
and not edited by hand.
See [generate-rule-docs.py](https://github.com/sqlfluff/sqlfluff/blob/main/docs/generate-rule-docs.py) for more info.
See [generate-auto-docs.py](https://github.com/sqlfluff/sqlfluff/blob/main/docs/generate-auto-docs.py) for more info.

239
docs/source/reference/dialects.rst
View File

@@ -36,241 +36,4 @@ current dialects available on your installation of SQLFluff.
- Will the feature I'm adding break any *downstream* dependencies
within dialects which inherit from this one?
.. _ansi_dialect_ref:
ANSI
----
This is the base dialect which holds most of the definitions of common
SQL commands and structures. If the dialect which you're actually using
isn't specifically implemented by SQLFluff, using this dialect is a good
place to start.
This dialect doesn't intend to be brutal in adhering to (and only to) the
ANSI SQL spec *(mostly because ANSI charges for access to that spec)*. It aims
to be a representation of vanilla SQL before any other project adds their
spin to it, and so may contain a slightly wider set of functions than actually
available in true ANSI SQL.
.. _athena_dialect_ref:
Athena
--------
The dialect for `Amazon Athena`_.
.. _`Amazon Athena`: https://aws.amazon.com/athena/
.. _bigquery_dialect_ref:
BigQuery
--------
The dialect for `Google BigQuery`_.
.. _`Google BigQuery`: https://cloud.google.com/bigquery/
.. _clickhouse_dialect_ref:
ClickHouse
----------
The dialect for `ClickHouse`_.
.. _`ClickHouse`: https://clickhouse.com/
.. _databricks_dialect_ref:
Databricks
----------
The dialect `Databricks`_.
.. _`Databricks`: https://databricks.com/
.. _db2_dialect_ref:
Db2
------
The dialect for `Db2`_.
.. _`Db2`: https://www.ibm.com/analytics/db2
.. _duck_dialect_ref:
DuckDB
------
The dialect for `DuckDB`_.
.. _`DuckDB`: https://duckdb.org/
.. _exasol_dialect_ref:
Exasol
------
The dialect for `Exasol`_.
.. _`Exasol`: https://www.exasol.com/
.. _hive_dialect_ref:
Greenplum
---------
The dialect for `Greenplum`_.
.. _`Greenplum`: https://www.greenplum.org/
.. _greens_dialect_ref:
Hive
----
The dialect for `Hive`_.
.. _`Hive`: https://hive.apache.org/
.. _materialize_dialect_ref:
Materialize
-----------
The dialect for `Materialize`_.
.. _`Materialize`: https://materialize.com/
.. _mariadb_dialect_ref:
MariaDB
-------
The dialect for `MariaDB`_.
.. _`MariaDB`: https://www.mariadb.org/
.. _mysql_dialect_ref:
MySQL
-----
The dialect for `MySQL`_.
.. _`MySQL`: https://www.mysql.com/
.. _oracle_dialect_ref:
Oracle
------
The dialect for `Oracle`_ SQL. Note: this does not include PL/SQL.
.. _`Oracle`: https://www.oracle.com/database/technologies/appdev/sql.html
.. _postgres_dialect_ref:
PostgreSQL
----------
This is based around the `PostgreSQL spec`_. Many other SQL instances are often
based on PostreSQL syntax. If you're running an unsupported dialect, then
this is often the dialect to use (until someone makes a specific dialect).
.. _`PostgreSQL spec`: https://www.postgresql.org/docs/9.6/reference.html
.. _redshift_dialect_ref:
Redshift
----------
The dialect for `Amazon Redshift`_.
.. _`Amazon Redshift`: https://aws.amazon.com/redshift/
.. _snowflake_dialect_ref:
Snowflake
---------
The dialect for `Snowflake`_, which has much of its syntax
inherited from :ref:`postgres_dialect_ref`.
.. _`Snowflake`: https://docs.snowflake.com/en/sql-reference.html
.. _soql_dialect_ref:
SOQL
----
The dialect for `SOQL`_ (Salesforce Object Query Language).
.. _`SOQL`: https://developer.salesforce.com/docs/atlas.en-us.soql_sosl.meta/soql_sosl/sforce_api_calls_soql.htm
.. _sparksql_dialect_ref:
SparkSQL
--------
The dialect for Apache `Spark SQL`_. It inherits from :ref:`ansi_dialect_ref`
and includes relevant syntax from :ref:`hive_dialect_ref` for commands that
permit Hive Format. Spark SQL extensions provided by the `Delta Lake`_ project
are also implemented in this dialect.
This implementation focuses on the `Ansi Compliant Mode`_ introduced in
Spark3, instead of being Hive Compliant. The introduction of ANSI Compliance
provides better data quality and easier migration from traditional DBMS.
Versions of Spark prior to 3.x will only support the Hive dialect.
.. _`Spark SQL`: https://spark.apache.org/docs/latest/sql-ref.html
.. _`Delta Lake`: https://docs.delta.io/latest/quick-start.html#set-up-apache-spark-with-delta-lake
.. _`Ansi Compliant Mode`: https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html
.. _sqlite_dialect_ref:
SQLite
------
The dialect for `SQLite`_.
.. _`SQLite`: https://www.sqlite.org/
.. _tsql_dialect_ref:
T-SQL
-----
The dialect for `T-SQL`_ (aka Transact-SQL).
.. _`T-SQL`: https://docs.microsoft.com/en-us/sql/t-sql/language-reference
.. _teradata_dialect_ref:
Teradata
--------
The dialect for `Teradata`_.
.. _`Teradata`: https://www.teradata.co.uk/
.. _trino_dialect_ref:
Trino
--------
The dialect for `Trino`_.
.. _`Trino`: https://trino.io/docs/current/
.. _vertica_dialect_ref:
Vertica
--------
The dialect for `Vertica`_.
.. _`Vertica`: https://www.vertica.com/documentation/vertica/all/
.. include:: ../_partials/dialect_summaries.rst

4
src/sqlfluff/core/dialects/__init__.py
View File

@@ -78,6 +78,7 @@ class DialectTuple(NamedTuple):
label: str
name: str
inherits_from: str
docstring: str
def dialect_readout() -> Iterator[DialectTuple]:
@@ -86,8 +87,9 @@ def dialect_readout() -> Iterator[DialectTuple]:
dialect = load_raw_dialect(dialect_label)
yield DialectTuple(
label=dialect_label,
name=dialect.name,
name=dialect.formatted_name,
inherits_from=dialect.inherits_from or "nothing",
docstring=dialect.docstring,
)

15
src/sqlfluff/core/dialects/base.py
View File

@@ -33,6 +33,8 @@ class Dialect:
library: Optional[Dict[str, DialectElementType]] = None,
sets: Optional[Dict[str, Set[Union[str, BracketPairTuple]]]] = None,
inherits_from: Optional[str] = None,
formatted_name: Optional[str] = None,
docstring: Optional[str] = None,
) -> None:
self._library = library or {}
self.name = name
@@ -41,6 +43,9 @@ class Dialect:
self._sets = sets or {}
self.inherits_from = inherits_from
self.root_segment_name = root_segment_name
# Attributes for documentation
self.formatted_name: str = formatted_name or name
self.docstring = docstring or f"The dialect for {self.formatted_name}."
def __repr__(self) -> str: # pragma: no cover
return f"<Dialect: {self.name}>"
@@ -123,7 +128,12 @@ class Dialect:
[n.strip().upper() for n in values.strip().split("\n")]
)
def copy_as(self, name: str) -> "Dialect":
def copy_as(
self,
name: str,
formatted_name: Optional[str] = None,
docstring: Optional[str] = None,
) -> "Dialect":
"""Copy this dialect and create a new one with a different name.
This is the primary method for inheritance, after which, the
@@ -149,6 +159,9 @@ class Dialect:
sets=new_sets,
inherits_from=self.name,
root_segment_name=self.root_segment_name,
# NOTE: We don't inherit the documentation fields.
formatted_name=formatted_name,
docstring=docstring,
)
def add(self, **kwargs: DialectElementType) -> None:

16
src/sqlfluff/dialects/dialect_ansi.py
View File

@@ -64,7 +64,21 @@ from sqlfluff.dialects.dialect_ansi_keywords import (
ansi_unreserved_keywords,
)
ansi_dialect = Dialect("ansi", root_segment_name="FileSegment")
ansi_dialect = Dialect(
"ansi",
root_segment_name="FileSegment",
formatted_name="ANSI",
docstring="""This is the base dialect which holds most of the definitions of common
SQL commands and structures. If the dialect which you're actually using
isn't specifically implemented by SQLFluff, using this dialect is a good
place to start.
This dialect doesn't intend to be brutal in adhering to (and only to) the
ANSI SQL spec *(mostly because ANSI charges for access to that spec)*. It aims
to be a representation of vanilla SQL before any other project adds their
spin to it, and so may contain a slightly wider set of functions than actually
available in true ANSI SQL.""",
)
ansi_dialect.set_lexer_matchers(
[

7
src/sqlfluff/dialects/dialect_athena.py
View File

@@ -36,7 +36,12 @@ from sqlfluff.dialects.dialect_athena_keywords import (
ansi_dialect = load_raw_dialect("ansi")
athena_dialect = ansi_dialect.copy_as("athena")
athena_dialect = ansi_dialect.copy_as(
"athena",
formatted_name="AWS Athena",
docstring="""The dialect for `Athena <https://aws.amazon.com/athena/>`_
on Amazon Web Services (AWS).""",
)
athena_dialect.sets("unreserved_keywords").update(athena_unreserved_keywords)
athena_dialect.sets("reserved_keywords").update(athena_reserved_keywords)

7
src/sqlfluff/dialects/dialect_bigquery.py
View File

@@ -43,7 +43,12 @@ from sqlfluff.dialects.dialect_bigquery_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
bigquery_dialect = ansi_dialect.copy_as("bigquery")
bigquery_dialect = ansi_dialect.copy_as(
"bigquery",
formatted_name="Google BigQuery",
docstring="""The dialect for `BigQuery <https://cloud.google.com/bigquery/>`_
on Google Cloud Platform (GCP).""",
)
bigquery_dialect.insert_lexer_matchers(
# JSON Operators: https://www.postgresql.org/docs/9.5/functions-json.html

6
src/sqlfluff/dialects/dialect_clickhouse.py
View File

@@ -40,7 +40,11 @@ from sqlfluff.dialects.dialect_clickhouse_keywords import (
ansi_dialect = load_raw_dialect("ansi")
clickhouse_dialect = ansi_dialect.copy_as("clickhouse")
clickhouse_dialect = ansi_dialect.copy_as(
"clickhouse",
formatted_name="ClickHouse",
docstring="The dialect for `ClickHouse <https://clickhouse.com/>`_.",
)
clickhouse_dialect.sets("unreserved_keywords").update(UNRESERVED_KEYWORDS)
clickhouse_dialect.insert_lexer_matchers(

6
src/sqlfluff/dialects/dialect_databricks.py
View File

@@ -34,7 +34,11 @@ from sqlfluff.dialects.dialect_databricks_keywords import (
)
sparksql_dialect = load_raw_dialect("sparksql")
databricks_dialect = sparksql_dialect.copy_as("databricks")
databricks_dialect = sparksql_dialect.copy_as(
"databricks",
formatted_name="Databricks",
docstring="The dialect for `Databricks <https://databricks.com/>`_.",
)
databricks_dialect.sets("unreserved_keywords").update(UNRESERVED_KEYWORDS)
databricks_dialect.sets("unreserved_keywords").update(

6
src/sqlfluff/dialects/dialect_db2.py
View File

@@ -34,7 +34,11 @@ from sqlfluff.dialects.dialect_db2_keywords import UNRESERVED_KEYWORDS
ansi_dialect = load_raw_dialect("ansi")
db2_dialect = ansi_dialect.copy_as("db2")
db2_dialect = ansi_dialect.copy_as(
"db2",
formatted_name="IBM Db2",
docstring="The dialect for IBM `Db2 <https://www.ibm.com/analytics/db2>`_.",
)
db2_dialect.sets("reserved_keywords").remove("NATURAL")
db2_dialect.sets("unreserved_keywords").update(UNRESERVED_KEYWORDS)

6
src/sqlfluff/dialects/dialect_duckdb.py
View File

@@ -31,7 +31,11 @@ from sqlfluff.dialects import dialect_postgres as postgres
ansi_dialect = load_raw_dialect("ansi")
postgres_dialect = load_raw_dialect("postgres")
duckdb_dialect = postgres_dialect.copy_as("duckdb")
duckdb_dialect = postgres_dialect.copy_as(
"duckdb",
formatted_name="DuckDB",
docstring="The dialect for `DuckDB <https://duckdb.org/>`_.",
)
duckdb_dialect.sets("reserved_keywords").update(
[

6
src/sqlfluff/dialects/dialect_exasol.py
View File

@@ -44,7 +44,11 @@ from sqlfluff.dialects.dialect_exasol_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
exasol_dialect = ansi_dialect.copy_as("exasol")
exasol_dialect = ansi_dialect.copy_as(
"exasol",
formatted_name="Exasol",
docstring="The dialect for `Exasol <https://www.exasol.com/>`_.",
)
# Clear ANSI Keywords and add all EXASOL keywords
exasol_dialect.sets("unreserved_keywords").clear()

6
src/sqlfluff/dialects/dialect_greenplum.py
View File

@@ -27,7 +27,11 @@ from sqlfluff.dialects.dialect_postgres_keywords import get_keywords
postgres_dialect = load_raw_dialect("postgres")
greenplum_dialect = postgres_dialect.copy_as("greenplum")
greenplum_dialect = postgres_dialect.copy_as(
"greenplum",
formatted_name="Greenplum",
docstring="The dialect for `Greenplum <https://www.greenplum.org/>`_.",
)
greenplum_dialect.sets("reserved_keywords").update(
get_keywords(greenplum_keywords, "reserved")

6
src/sqlfluff/dialects/dialect_hive.py
View File

@@ -31,7 +31,11 @@ from sqlfluff.dialects.dialect_hive_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
hive_dialect = ansi_dialect.copy_as("hive")
hive_dialect = ansi_dialect.copy_as(
"hive",
formatted_name="Apache Hive",
docstring="The dialect for Apache `Hive <https://hive.apache.org/>`_.",
)
# Clear ANSI Keywords and add all Hive keywords
# Commented clearing for now as some are needed for some statements imported

6
src/sqlfluff/dialects/dialect_mariadb.py
View File

@@ -26,7 +26,11 @@ from sqlfluff.dialects.dialect_mariadb_keywords import (
# ansi_dialect = load_raw_dialect("ansi")
mysql_dialect = load_raw_dialect("mysql")
mariadb_dialect = mysql_dialect.copy_as("mariadb")
mariadb_dialect = mysql_dialect.copy_as(
"mariadb",
formatted_name="MariaDB",
docstring="The dialect for `MariaDB <https://www.mariadb.org/>`_.",
)
mariadb_dialect.update_keywords_set_from_multiline_string(
"unreserved_keywords", mariadb_unreserved_keywords
)

6
src/sqlfluff/dialects/dialect_materialize.py
View File

@@ -24,7 +24,11 @@ from sqlfluff.dialects.dialect_materialize_keywords import (
postgres_dialect = load_raw_dialect("postgres")
materialize_dialect = postgres_dialect.copy_as("materialize")
materialize_dialect = postgres_dialect.copy_as(
"materialize",
formatted_name="Materialize",
docstring="The dialect for `Materialize <https://materialize.com/>`_.",
)
materialize_dialect.update_keywords_set_from_multiline_string(
"unreserved_keywords", materialize_unreserved_keywords
)

6
src/sqlfluff/dialects/dialect_mysql.py
View File

@@ -41,7 +41,11 @@ from sqlfluff.dialects.dialect_mysql_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
mysql_dialect = ansi_dialect.copy_as("mysql")
mysql_dialect = ansi_dialect.copy_as(
"mysql",
formatted_name="MySQL",
docstring="The dialect for `MySQL <https://www.mysql.com/>`_.",
)
mysql_dialect.patch_lexer_matchers(
[

8
src/sqlfluff/dialects/dialect_oracle.py
View File

@@ -38,7 +38,13 @@ from sqlfluff.core.parser import (
from sqlfluff.dialects import dialect_ansi as ansi
ansi_dialect = load_raw_dialect("ansi")
oracle_dialect = ansi_dialect.copy_as("oracle")
oracle_dialect = ansi_dialect.copy_as(
"oracle",
formatted_name="Oracle",
docstring="""The dialect for `Oracle`_ SQL. Note: this does not include PL/SQL.
.. _`Oracle`: https://www.oracle.com/database/technologies/appdev/sql.html""",
)
oracle_dialect.sets("unreserved_keywords").difference_update(["COMMENT"])
oracle_dialect.sets("reserved_keywords").update(

11
src/sqlfluff/dialects/dialect_postgres.py
View File

@@ -44,7 +44,16 @@ from sqlfluff.dialects.dialect_postgres_keywords import (
ansi_dialect = load_raw_dialect("ansi")
postgres_dialect = ansi_dialect.copy_as("postgres")
postgres_dialect = ansi_dialect.copy_as(
"postgres",
formatted_name="PostgreSQL",
docstring="""This is based around the `PostgreSQL spec`_. Many other SQL
dialects are often based on the PostreSQL syntax. If you're running an unsupported
dialect, then this is often the dialect to use (until someone makes a specific
dialect).
.. _`PostgreSQL spec`: https://www.postgresql.org/docs/current/reference.html""",
)
postgres_dialect.insert_lexer_matchers(
# JSON Operators: https://www.postgresql.org/docs/9.5/functions-json.html

7
src/sqlfluff/dialects/dialect_redshift.py
View File

@@ -35,7 +35,12 @@ from sqlfluff.dialects.dialect_redshift_keywords import (
postgres_dialect = load_raw_dialect("postgres")
ansi_dialect = load_raw_dialect("ansi")
redshift_dialect = postgres_dialect.copy_as("redshift")
redshift_dialect = postgres_dialect.copy_as(
"redshift",
formatted_name="AWS Redshift",
docstring="""The dialect for `Redshift <https://aws.amazon.com/redshift/>`_
on Amazon Web Services (AWS).""",
)
# Set Keywords
redshift_dialect.sets("unreserved_keywords").clear()

8
src/sqlfluff/dialects/dialect_snowflake.py
View File

@@ -42,7 +42,13 @@ from sqlfluff.dialects.dialect_snowflake_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
snowflake_dialect = ansi_dialect.copy_as("snowflake")
snowflake_dialect = ansi_dialect.copy_as(
"snowflake",
formatted_name="Snowflake",
docstring="""The dialect for
`Snowflake <https://docs.snowflake.com/en/sql-reference.html>`_,
which has much of its syntax inherited from :ref:`postgres_dialect_ref`.""",
)
snowflake_dialect.patch_lexer_matchers(
[

10
src/sqlfluff/dialects/dialect_soql.py
View File

@@ -18,7 +18,15 @@ from sqlfluff.dialects import dialect_ansi as ansi
ansi_dialect = load_raw_dialect("ansi")
soql_dialect = ansi_dialect.copy_as("soql")
soql_dialect = ansi_dialect.copy_as(
"soql",
formatted_name="Salesforce Object Query Language (SOQL)",
docstring=(
"The dialect for `SOQL <https://developer.salesforce.com/docs/"
"atlas.en-us.soql_sosl.meta/soql_sosl/sforce_api_calls_soql.htm>`_ "
"(Salesforce Object Query Language)."
),
)
soql_dialect.insert_lexer_matchers(
[

19
src/sqlfluff/dialects/dialect_sparksql.py
View File

@@ -52,7 +52,24 @@ from sqlfluff.dialects.dialect_sparksql_keywords import (
ansi_dialect = load_raw_dialect("ansi")
hive_dialect = load_raw_dialect("hive")
sparksql_dialect = ansi_dialect.copy_as("sparksql")
sparksql_dialect = ansi_dialect.copy_as(
"sparksql",
formatted_name="Apache Spark SQL",
docstring="""The dialect for Apache `Spark SQL`_. This includes relevant
syntax from :ref:`hive_dialect_ref` for commands that permit Hive Format.
Spark SQL extensions provided by the `Delta Lake`_ project are also implemented
in this dialect.
This implementation focuses on the `Ansi Compliant Mode`_ introduced in
Spark3, instead of being Hive Compliant. The introduction of ANSI Compliance
provides better data quality and easier migration from traditional DBMS.
Versions of Spark prior to 3.x will only support the Hive dialect.
.. _`Spark SQL`: https://spark.apache.org/docs/latest/sql-ref.html
.. _`Delta Lake`: https://docs.delta.io/latest/quick-start.html#set-up-apache-spark-with-delta-lake
.. _`Ansi Compliant Mode`: https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html""", # noqa: E501
)
sparksql_dialect.patch_lexer_matchers(
[

6
src/sqlfluff/dialects/dialect_sqlite.py
View File

@@ -37,7 +37,11 @@ from sqlfluff.dialects.dialect_sqlite_keywords import (
ansi_dialect = load_raw_dialect("ansi")
sqlite_dialect = ansi_dialect.copy_as("sqlite")
sqlite_dialect = ansi_dialect.copy_as(
"sqlite",
formatted_name="SQLite",
docstring="""The dialect for `SQLite <https://www.sqlite.org/>`_.""",
)
sqlite_dialect.sets("reserved_keywords").clear()
sqlite_dialect.sets("reserved_keywords").update(RESERVED_KEYWORDS)

6
src/sqlfluff/dialects/dialect_teradata.py
View File

@@ -33,7 +33,11 @@ from sqlfluff.core.parser import (
from sqlfluff.dialects import dialect_ansi as ansi
ansi_dialect = load_raw_dialect("ansi")
teradata_dialect = ansi_dialect.copy_as("teradata")
teradata_dialect = ansi_dialect.copy_as(
"teradata",
formatted_name="Teradata",
docstring="""The dialect for `Teradata <https://www.teradata.co.uk/>`_.""",
)
teradata_dialect.patch_lexer_matchers(
[

6
src/sqlfluff/dialects/dialect_trino.py
View File

@@ -33,7 +33,11 @@ from sqlfluff.dialects.dialect_trino_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
trino_dialect = ansi_dialect.copy_as("trino")
trino_dialect = ansi_dialect.copy_as(
"trino",
formatted_name="Trino",
docstring="""The dialect for `Trino <https://trino.io/docs/current/>`_.""",
)
# Set the bare functions: https://trino.io/docs/current/functions/datetime.html
trino_dialect.sets("bare_functions").update(

8
src/sqlfluff/dialects/dialect_tsql.py
View File

@@ -47,7 +47,13 @@ from sqlfluff.dialects.dialect_tsql_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
tsql_dialect = ansi_dialect.copy_as("tsql")
tsql_dialect = ansi_dialect.copy_as(
"tsql",
formatted_name="Microsoft T-SQL",
docstring="""The dialect for `T-SQL`_ (aka Transact-SQL).
.. _`T-SQL`: https://docs.microsoft.com/en-us/sql/t-sql/language-reference""",
)
tsql_dialect.sets("reserved_keywords").clear()
tsql_dialect.sets("unreserved_keywords").clear()

7
src/sqlfluff/dialects/dialect_vertica.py
View File

@@ -39,7 +39,12 @@ from sqlfluff.dialects.dialect_vertica_keywords import (
)
ansi_dialect = load_raw_dialect("ansi")
vertica_dialect = ansi_dialect.copy_as("vertica")
vertica_dialect = ansi_dialect.copy_as(
"vertica",
formatted_name="Vertica",
docstring="""The dialect for
`Vertica <https://www.vertica.com/documentation/vertica/all/>`_.""",
)
vertica_dialect.insert_lexer_matchers(
# Allow ::! operator as in

17
test/api/info_test.py
View File

@@ -8,7 +8,22 @@ def test__api__info_dialects():
"""Basic linting of dialects."""
dialects = sqlfluff.list_dialects()
assert isinstance(dialects, list)
assert ("ansi", "ansi", "nothing") in dialects
# Turn it into a dict so we can look for items in there.
dialect_dict = {dialect.label: dialect for dialect in dialects}
# Check the ansi dialect works
assert "ansi" in dialect_dict
ansi = dialect_dict["ansi"]
assert ansi.label == "ansi"
assert ansi.name == "ANSI"
assert ansi.inherits_from == "nothing"
assert "This is the base dialect" in ansi.docstring
# Check one other works
assert "postgres" in dialect_dict
postgres = dialect_dict["postgres"]
assert postgres.label == "postgres"
assert postgres.name == "PostgreSQL"
assert postgres.inherits_from == "ansi"
assert "this is often the dialect to use" in postgres.docstring
def test__api__info_rules():

4
tox.ini
View File

@@ -99,9 +99,9 @@ commands = yamllint -c .yamllint .
deps =
-rdocs/requirements.txt
commands =
# Before linting, generate the rule docs.
# Before linting, generate the rule & dialect docs.
# If we don't we get import errors.
python {toxinidir}/docs/generate-rule-docs.py
python {toxinidir}/docs/generate-auto-docs.py
doc8 {toxinidir}/docs/source --file-encoding utf8
[testenv:docbuild]