Use pgSphere 1.5.2 and improve ADQL 2.1

.github/workflows/pytest.yml

@@ -23,7 +23,7 @@ jobs:
 
       - name: Build queryparser
         run: |
-          wget http://www.antlr.org/download/antlr-4.13.1-complete.jar
+          wget http://www.antlr.org/download/antlr-4.13.2-complete.jar
           make
           pip install -I -e .[test]
           pip install pytest-cov

README.md

@@ -42,7 +42,7 @@ To generate the parsers you need `python3` , `java` above version
 The current version of `antlr-4.*-complete.jar` can be downloaded via
 
 ```bash
-wget http://www.antlr.org/download/antlr-4.13.1-complete.jar
+wget http://www.antlr.org/download/antlr-4.13.2-complete.jar
 ```
 
 After cloning the project run
@@ -63,9 +63,9 @@ to install the generated parser in your virtual environment.
 Additional requirements
 -----------------------
 The queryparser assumes that the PostgreSQL database has the extension
-[pg_sphere](https://github.com/kimakan/pgsphere/tree/aiprdbms16) installed.
-Although the `pg_sphere` is not required for the python module, the PostgreSQL
-**queries will not run** without this extension installed on the database.
+[pg_sphere](https://github.com/postgrespro/pgsphere) installed.
+Although `pg_sphere` is not required for the Python module, PostgreSQL
+**queries will not run** without this extension installed in the database.
 
 
 Parsing MySQL and PostgreSQL
@@ -120,7 +120,7 @@ the `ADQLQueryTranslator` class
 
 ```python
 from queryparser.adql import ADQLQueryTranslator
-adql = "SELECT TOP 100 POINT('ICRS', ra, de) FROM db.tab;"
+adql = "SELECT TOP 100 POINT('ICRS', ra, dec) FROM db.tab;"
 adt = ADQLQueryTranslator(adql)
 ```
 
@@ -130,7 +130,7 @@ and calling
 adt.to_postgresql()
 ```
 
-which returns a translated string representing a valid MySQL query if
+which returns a translated string representing a valid PostgreSQL query if
 the ADQL query had no errors. The PostgreSQL query can then be parsed with the
 `PostgreSQLQueryProcessor` in the same way as shown above.
 
@@ -149,4 +149,3 @@ then run the test suite with
 ```bash
 python -m pytest lib/
 ```
-

docs/development.md

@@ -9,8 +9,7 @@ processed and can be used to check, for example, for permissions before the
 query is sent to the server.
 
 In addition, queryparser can also work with ADQL queries which can be translated
-to either MySQL or PostgreSQL language and then further processed the same
-way.
+to PostgreSQL and then further processed the same way.
 
 Below is a more detailed description along with instructions for anyone who is
 interested in further developing the package.
@@ -49,14 +48,14 @@ Individual dialect functionality (MySQL in this case) with increased verbosity
 can be tested with
 
 ```bash
-pytest /lib/queryparser/testing/test_mysql.py -v
+pytest lib/queryparser/testing/test_mysql.py -v
 ```
 
 Individual tests (20th MySQL test in this case, but otherwise any test
 that includes the string 't20') are ran with
 
 ```bash
-pytest /lib/queryparser/testing/test_mysql.py -k t20
+pytest lib/queryparser/testing/test_mysql.py -k t20
 ```
 
 If the package `pytest-cov` is installed then the detailed coverage report
@@ -120,7 +119,7 @@ and an ADQL translator. The processors accept any SELECT-like query and
 after the process_query() method has been executed, several elements of
 the query are extracted (all touch columns and tables, used keywords and functions).
 Before the processing the query is validated and invalid queries are rejected.
-The ADQL translator allows translating valid ADQL queries to MySQL or PostgreSQL.
+The ADQL translator allows translating valid ADQL queries to PostgreSQL.
 
 Most of the processor code is shared between MySQL and PostgreSQL and is
 therefore merged together inside of the `common.py`. This file consists

generate.py

@@ -6,7 +6,7 @@
 import subprocess
 import re
 
-ANTLR_JAR = 'antlr-4.13.1-complete.jar'
+ANTLR_JAR = 'antlr-4.13.2-complete.jar'
 ANTLR_DIRS = ('.', '/usr/local/lib/', '/usr/local/bin/')
 
 QUERYPARSER_SRC = 'src/queryparser/'

pyproject.toml

@@ -8,10 +8,12 @@ description = "Package for parsing PostgreSQL/MySQL and translating ADQL to Post
 readme = "README.md"
 dynamic = ["version"]
 license = { text = "Apache-2.0" }
-authors = [{ name = "Gal Matijevic", email = "gmatijevic@aip.de" }]
+authors = [
+  { name = "Kirill Makan", email = "kmakan@aip.de" },
+  { name = "Gal Matijevic", email = "gmatijevic@aip.de" }
+]
 maintainers = [
   { name = "Kirill Makan", email = "kmakan@aip.de" },
-  { name = "Simeon Reusch", email = "sreusch@aip.de" },
 ]
 requires-python = ">=3.9"
 classifiers = [
@@ -24,8 +26,10 @@ classifiers = [
   "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
 ]
-dependencies = ["antlr4-python3-runtime==4.13.1"]
+dependencies = ["antlr4-python3-runtime==4.13.2"]
 
 [project.optional-dependencies]
 test = ["pytest~=8.2.0", "PyYAML~=6.0"]

src/queryparser/__init__.py

@@ -1 +1 @@
-__version__ = '0.7.4'
+__version__ = '0.8.0'

src/queryparser/adql/ADQLLexer.g4

@@ -316,14 +316,14 @@ HEX_DIGIT:
 	(  '0x'     (HEX_DIGIT_FRAGMENT)+  )
 ;
 
-CSL: SQ ('\u0020' .. '\u0026' | '\u0028' .. '\u007f')+ SQ;
+CSL: SQ ( SQ SQ | '\u0020' .. '\u0026' | '\u0028' .. '\u007f' )* SQ;
 
-ID:
-	(( 'A'..'Z' | 'a'..'z' | '_' | '%' | '$') ( 'A'..'Z' | 'a'..'z' | '_' | '$' | '%' | '0'..'9' )*) |
-	//(DQ NQC+ DQ)
-	(DQ ('\u0020' .. '\u0021' | '\u0023' .. '\u007f')+ DQ)
-;
+DELIMITED_ID:
+	DQ ('\u0020' .. '\u0021' | '\u0023' .. '\u007f')+ DQ;
 
+ID:
+	( 'A'..'Z' | 'a'..'z' )
+	( 'A'..'Z' | 'a'..'z' | '_' | '0'..'9' )*;
 
 //NDQC: 'A'..'Z' | 'a'..'z' | '_' | '0'..'9' ;
 

src/queryparser/adql/ADQLParser.g4

@@ -23,7 +23,7 @@ box:
           ( coord_sys COMMA )?
           coordinates COMMA numeric_value_expression COMMA numeric_value_expression
           RPAREN ;
-catalog_name:                   ID ;
+catalog_name:                   ID | DELIMITED_ID ;
 // centroid:                       CENTROID LPAREN geometry_value_expression RPAREN ;
 // character_representation:       nonquote_character ;// | SQ SQ ;
 char_function:                  LOWER LPAREN character_string_literal RPAREN ;
@@ -52,7 +52,7 @@ coordinates:                    coordinate1 COMMA coordinate2 ;
 correlation_name:               identifier ;
 correlation_specification:      ( AS )? correlation_name ;
 //default_function_prefix:      // this is empty in the document!
-delimited_identifier:           DQ ID DQ ;
+delimited_identifier:           DELIMITED_ID ;
 derived_column:                 value_expression ( as_clause )? ;
 derived_table:                  table_subquery ;
 distance:
@@ -70,9 +70,9 @@ factor:                         ( sign )? numeric_primary ;
 from_clause:                    FROM table_reference ( COMMA table_reference )* ;
 general_literal:                character_string_literal ;
 general_set_function:           set_function_type LPAREN ( set_quantifier )? value_expression RPAREN ;
-geometry_value_expression:      box | circle | point | polygon | user_defined_function ; //| centroid | region
+geometry_value_expression:      value_expression_primary | box | circle | point | polygon | user_defined_function ; //| centroid | region
 group_by_clause:                GROUP BY grouping_column_reference_list ;
-grouping_column_reference:      column_reference ;
+grouping_column_reference:      value_expression ;
 grouping_column_reference_list: grouping_column_reference ( COMMA grouping_column_reference )* ;
 having_clause:                  HAVING search_condition ;
 identifier:                     regular_identifier | delimited_identifier ;
@@ -160,7 +160,7 @@ query_term:                     non_join_query_primary | query_term INTERSECT (
 radius:                         numeric_value_expression ;
 //region:                         REGION LPAREN string_value_expression RPAREN ;
 regular_identifier:             ID ;
-schema_name:                    ID ; //( catalog_name DOT )? unqualified_schema_name ;
+schema_name:                    ID | DELIMITED_ID ; //( catalog_name DOT )? unqualified_schema_name ;
 search_condition:               boolean_term | search_condition OR boolean_term ;
 select_list:                    ( select_sublist ( COMMA select_sublist )* ) | ( ASTERISK ( COMMA select_sublist ( COMMA select_sublist )* )? ) ;
 select_query:                   SELECT ( set_quantifier )? ( set_limit )? select_list table_expression ;
@@ -194,15 +194,14 @@ table_reference:
 table_subquery:                 subquery ;
 term:                           factor | term ASTERISK factor | term SOLIDUS factor | term MOD_SYM factor;
 trig_function:                  ACOS LPAREN numeric_value_expression RPAREN
-        | ACOS LPAREN numeric_value_expression RPAREN
         | ASIN LPAREN numeric_value_expression RPAREN
         | ATAN LPAREN numeric_value_expression RPAREN
         | ATAN2 LPAREN numeric_value_expression COMMA numeric_value_expression RPAREN
         | COS LPAREN numeric_value_expression RPAREN
         | COT LPAREN numeric_value_expression RPAREN
         | SIN LPAREN numeric_value_expression RPAREN
         | TAN LPAREN numeric_value_expression RPAREN ;
-unqualified_schema_name:        ID ;
+unqualified_schema_name:        ID | DELIMITED_ID ;
 unsigned_decimal:               INT ;
 unsigned_hexadecimal:           HEX_DIGIT ;
 unsigned_literal:               unsigned_numeric_literal | general_literal ;
@@ -216,7 +215,8 @@ user_defined_function:
 user_defined_function_name:     regular_identifier ; //( default_function_prefix )? regular_identifier ;
 user_defined_function_param:    value_expression ;
 value_expression:
-          numeric_value_expression
+          NULL
+        | numeric_value_expression
         | string_value_expression
         | boolean_value_expression
         | geometry_value_expression ;