def test_include_taxons():
dbf = ProgramFilter(db)
taxons = ["O/J", "X/S/M/L", "non_existing_taxon"]
dbf.include_taxons(taxons)
print(sorted(dbf.selected_programs))
assert dbf.selected_programs.keys() == {
"prg1.py",
"prg3.py",
"prg4.py",
"prg6.py",
"prg7.py",
"prg8.py",
"prg9.py",
}
def test_include_taxons():
# The taxon "variable/assignment/single" is directly featured by assignment.py and
# collatz_print.py, but only indirectly by the other programs, which therefore cannot be
# included in the result. Note that this behavior contrasts with that of exclude_taxons.
dbf = ProgramFilter(db)
dbf.include_taxons({"variable/assignment/single"})
print(set(dbf.selected_programs.keys()))
assert set(
dbf.selected_programs.keys()) == {"assignment.py", "collatz_print.py"}
# "operator/arithmetic/addition" is directly featured by collatz_print.py only. Therefore,
# including this taxon keeps only collatz_print.py.
dbf = ProgramFilter(db)
dbf.include_taxons({"operator/arithmetic/addition"})
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == {"collatz_print.py"}
# "flow/conditional" is featured by collatz_print.py, fizzbuzz.py, and indirectly by
# is_even.py. Therefore, including this taxon keeps only the former two.
dbf = ProgramFilter(db)
dbf.include_taxons({"flow/conditional"})
print(set(dbf.selected_programs.keys()))
assert set(
dbf.selected_programs.keys()) == {"collatz_print.py", "fizzbuzz.py"}
# "type/sequence/string/literal" is directly featured by fizzbuzz.py only. Therefore, including
# this taxon keeps only fizzbuzz.py
dbf = ProgramFilter(db)
dbf.include_taxons({"type/sequence/string/literal"})
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == {"fizzbuzz.py"}
def test_include_taxons():
# The taxon "variable/assignment/single" is featured by assignment.py and collatz_print.py. In
# collatz_print.py, it appears after a taxon "io/standard/print". Consequently, it should be included
# in the results, but not the programs which import it: fizzbuzz.py and is_even.py.
dbf = ProgramFilter(db)
dbf.include_taxons({("after", "variable/assignment/single", "io/standard/print")})
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == {"collatz_print.py"}
# "operator/arithmetic/modulo" and "type/number/integer/literal" are both featured on
# the same line in all programs except assignment.py
dbf = ProgramFilter(db)
dbf.include_taxons({("equals", "operator/arithmetic/modulo", "type/number/integer/literal")})
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == {"collatz_print.py", "is_even.py", "fizzbuzz.py"}
# The same with "x == y" instead of "equals"
dbf = ProgramFilter(db)
dbf.include_taxons({("equals", "operator/arithmetic/modulo", "type/number/integer/literal")})
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == {"collatz_print.py", "is_even.py", "fizzbuzz.py"}
# "test/equality" is inside "subroutine/function" in is_even.py, which is not imported anywhere.
dbf = ProgramFilter(db)
dbf.include_taxons({("inside", "test/equality", "subroutine/function")})
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == {"is_even.py"}
# "test/equality" is inside "subroutine/function" in is_even.py and inside
# "subroutine/procedure" in collatz_print.py. Both will be included.
dbf = ProgramFilter(db)
taxons = dbf.preprocess_taxons([("inside", "test/equality", "subroutine/.*")])
print(taxons)
assert taxons == [
("inside", "test/equality", "subroutine/argument/arg"),
("inside", "test/equality", "subroutine/function"),
("inside", "test/equality", "subroutine/predicate"),
("inside", "test/equality", "subroutine/procedure"),
]
dbf.include_taxons(taxons)
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == {"collatz_print.py", "is_even.py"}
# "call/function/builtin/range" is not inside "flow/conditional" anywhere.
dbf = ProgramFilter(db)
dbf.include_taxons([("inside", "call/function/builtin/range", "flow/conditional")])
print(set(dbf.selected_programs.keys()))
assert set(dbf.selected_programs.keys()) == set()
