Verify all examples in the spec with validator

optimade/validator/filters.txt

@@ -0,0 +1,42 @@
+filter=_exmpl1_bandgap<2.0 OR _exmpl2_bandgap<2.5
+NOT ( chemical_formula_hill = "Al" AND chemical_formula_anonymous = "A" OR chemical_formula_anonymous = "H2O" AND NOT chemical_formula_hill = "Ti" )
+nelements > 3
+chemical_formula_hill = "H2O" AND chemical_formula_anonymous != "AB"
+_exmpl_aax <= +.1e8 OR nelements >= 10 AND NOT ( _exmpl_x != "Some string" OR NOT _exmpl_a = 7)
+_exmpl_spacegroup="P2"
+_exmpl_cell_volume<100.0
+_exmpl_bandgap > 5.0 AND _exmpl_molecular_weight < 350
+_exmpl_melting_point<300 AND nelements=4 AND elements="Si,O2"
+_exmpl_some_string_property = 42
+5 < _exmpl_a
+identifier CONTAINS x
+identifier STARTS WITH x
+identifier ENDS WITH x
+chemical_formula_anonymous CONTAINS "C2" AND chemical_formula_anonymous STARTS WITH "A2"
+chemical_formula_anonymous STARTS "B2" AND chemical_formula_anonymous ENDS WITH "D2"
+list HAS value
+list HAS ALL values
+list HAS ANY values
+list LENGTH value
+list HAS ONLY values
+inverse
+list HAS < 3
+list HAS ALL < 3, > 3
+list:list HAS >=2:<=5
+references
+identifier
+chemical_formula_hill IS KNOWN AND NOT chemical_formula_anonymous IS UNKNOWN
+NOT a > b OR c = 100 AND f = "C2 H6"
+a >= 0 AND NOT b < c OR c = 0
+elements HAS ALL "Si", "Al", "O"
+elements HAS ALL "Si", "Al", "O" AND elements LENGTH 3
+nelements=4
+nelements>=2 AND nelements<=7
+elements:elements_ratios HAS ALL "Al":>0.3333, "Al":<0.3334
+chemical_formula_descriptive="(H2O)2 Na"
+chemical_formula_descriptive CONTAINS "H2O"
+chemical_formula_reduced="H2NaO"
+chemical_formula_hill="H2O2"
+chemical_formula_anonymous="A2B"
+nsites=4
+nsites>=2 AND nsites<=7

optimade/validator/validator.py

@@ -12,6 +12,7 @@
 import json
 import traceback
 
+from pathlib import Path
 from typing import Union
 
 from pydantic import ValidationError
@@ -34,13 +35,17 @@
 LINKS_ENDPOINT = "links"
 REQUIRED_ENTRY_ENDPOINTS = ["references", "structures"]
 
+with open(Path(__file__).parent.joinpath("filters.txt"), "r") as f:
+    SPEC_FILTERS = f.readlines()
+
 ENDPOINT_MANDATORY_QUERIES = {
     "structures": [
         'elements HAS "Na"',
         'elements HAS ANY "Na","Cl"',
         'elements HAS ALL "Na","Cl"',
-    ],
-    "references": [],
+    ]
+    + SPEC_FILTERS,
+    "references": SPEC_FILTERS,
 }
 
 RESPONSE_CLASSES = {