defee62d99
* docs: fix codestyle placeholders in CONTRIBUTING.md
Replace unresolved {codestyle} and {URLofCodestyle} template
variables with Ruff, the project's actual linter/formatter
as configured in .pre-commit-config.yaml.
* fix: replace bare except clauses with specific exception types
- quantization.py: use except ImportError for optional torchao imports
(consistent with line 48 which already uses ImportError correctly)
- cli/config.py: use except (RuntimeError, AssertionError) for CUDA
device property query
Prevents masking unrelated errors like KeyboardInterrupt or SystemExit.
* test: add unit tests for convert.py JSON/JSONL utilities
Cover FileReader, FileWriter, StdoutWriter, JsonParser,
JsonlSerializer, and JsonToJsonlConverter with 8 test cases
including roundtrip and edge case (empty list) scenarios.
Previously this module had zero test coverage.
* fix: address CodeRabbit review feedback
- quantization.py: catch (ImportError, RuntimeError) for optional
torchao imports; CUDA wheel/GPU mismatches raise RuntimeError,
not ImportError
- convert.py: remove unused output_file_path parameter from
JsonToJsonlConverter.convert() — FileWriter already holds the
output path from construction
- tests/test_convert.py: update call site to match new signature
92 lines
2.6 KiB
Python
92 lines
2.6 KiB
Python
"""Unit tests for src/axolotl/convert.py"""
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
from axolotl.convert import (
|
|
FileReader,
|
|
FileWriter,
|
|
JsonlSerializer,
|
|
JsonParser,
|
|
JsonToJsonlConverter,
|
|
StdoutWriter,
|
|
)
|
|
|
|
|
|
class TestJsonParser:
|
|
def test_parse_valid_json_array(self):
|
|
parser = JsonParser()
|
|
result = parser.parse('[{"key": "value"}]')
|
|
assert result == [{"key": "value"}]
|
|
|
|
def test_parse_valid_json_object(self):
|
|
parser = JsonParser()
|
|
result = parser.parse('{"key": "value"}')
|
|
assert result == {"key": "value"}
|
|
|
|
def test_parse_invalid_json_raises(self):
|
|
parser = JsonParser()
|
|
with pytest.raises(json.JSONDecodeError):
|
|
parser.parse("not valid json")
|
|
|
|
|
|
class TestJsonlSerializer:
|
|
def test_serialize_single_item(self):
|
|
serializer = JsonlSerializer()
|
|
result = serializer.serialize([{"a": 1}])
|
|
assert result == '{"a": 1}'
|
|
|
|
def test_serialize_multiple_items(self):
|
|
serializer = JsonlSerializer()
|
|
result = serializer.serialize([{"a": 1}, {"b": 2}])
|
|
lines = result.split("\n")
|
|
assert len(lines) == 2
|
|
assert json.loads(lines[0]) == {"a": 1}
|
|
assert json.loads(lines[1]) == {"b": 2}
|
|
|
|
def test_serialize_empty_list(self):
|
|
serializer = JsonlSerializer()
|
|
result = serializer.serialize([])
|
|
assert result == ""
|
|
|
|
|
|
class TestFileReaderWriter:
|
|
def test_read_write_roundtrip(self, tmp_path):
|
|
test_file = tmp_path / "test.txt"
|
|
content = '{"hello": "world"}'
|
|
writer = FileWriter(str(test_file))
|
|
writer.write(content)
|
|
|
|
reader = FileReader()
|
|
result = reader.read(str(test_file))
|
|
assert result == content
|
|
|
|
|
|
class TestStdoutWriter:
|
|
def test_write_to_stdout(self, capsys):
|
|
writer = StdoutWriter()
|
|
writer.write("hello")
|
|
captured = capsys.readouterr()
|
|
assert captured.out == "hello\n"
|
|
|
|
|
|
class TestJsonToJsonlConverter:
|
|
def test_convert_json_to_jsonl(self, tmp_path):
|
|
input_data = [{"name": "Alice"}, {"name": "Bob"}]
|
|
input_file = tmp_path / "input.json"
|
|
output_file = tmp_path / "output.jsonl"
|
|
|
|
input_file.write_text(json.dumps(input_data), encoding="utf-8")
|
|
|
|
converter = JsonToJsonlConverter(
|
|
FileReader(), FileWriter(str(output_file)), JsonParser(), JsonlSerializer()
|
|
)
|
|
converter.convert(str(input_file))
|
|
|
|
result = output_file.read_text(encoding="utf-8")
|
|
lines = result.split("\n")
|
|
assert len(lines) == 2
|
|
assert json.loads(lines[0]) == {"name": "Alice"}
|
|
assert json.loads(lines[1]) == {"name": "Bob"}
|