datadile 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
datadile/__init__.py ADDED
@@ -0,0 +1,3 @@
1
+ from .core import main
2
+
3
+ __all__ = ["main"]
datadile/config.py ADDED
@@ -0,0 +1,125 @@
1
+ import os
2
+ from pathlib import Path
3
+ from typing import Any
4
+
5
+ import yaml
6
+
7
+ CONFIG_FILENAME = "datadile.yaml"
8
+ USER_CONFIG_PATH = Path.home() / ".datadile" / CONFIG_FILENAME
9
+ DEFAULT_API_KEY_ENV = "DATADILE_API_KEY"
10
+ DEFAULT_DATA_SOURCE_PASSWORD_ENV = "DATADILE_DATA_SOURCE_PASSWORD"
11
+
12
+ CONFIG_TEMPLATE = """\
13
+ # Optional. Only required for premium server-backed features.
14
+ api_key_env: DATADILE_API_KEY
15
+
16
+ # Optional. Used by tests that do not set data_source.
17
+ default_data_source: main
18
+
19
+ data_sources:
20
+ main:
21
+ type: postgresql
22
+ host: localhost
23
+ port: 5432
24
+ user: myuser
25
+ database: mydb
26
+ password_env: DATADILE_DATA_SOURCE_PASSWORD
27
+
28
+ # Premium server-backed data source example:
29
+ # data_sources:
30
+ # main:
31
+ # id: ds_abc123
32
+ """
33
+
34
+
35
+ def _find_config_file() -> Path | None:
36
+ local = Path(CONFIG_FILENAME)
37
+ if local.exists():
38
+ return local
39
+ if USER_CONFIG_PATH.exists():
40
+ return USER_CONFIG_PATH
41
+ return None
42
+
43
+
44
+ def load_config(required: bool = True) -> dict[str, Any]:
45
+ config_path = _find_config_file()
46
+ if config_path is None:
47
+ if not required:
48
+ return {}
49
+ raise FileNotFoundError(
50
+ f"No config file found. Create one at:\n"
51
+ f" ./{CONFIG_FILENAME}\n"
52
+ f" {USER_CONFIG_PATH}\n\n"
53
+ f"Template:\n{CONFIG_TEMPLATE}"
54
+ )
55
+
56
+ with config_path.open() as f:
57
+ config = yaml.safe_load(f) or {}
58
+
59
+ if not isinstance(config, dict):
60
+ raise ValueError(f"Config file {config_path} must contain a YAML mapping.")
61
+ return config
62
+
63
+
64
+ def get_api_key() -> str | None:
65
+ config = load_config(required=False)
66
+ if config.get("api_key"):
67
+ raise ValueError("Do not put API keys in datadile.yaml. Use api_key_env instead.")
68
+
69
+ api_key_env = str(config.get("api_key_env", DEFAULT_API_KEY_ENV))
70
+ return os.environ.get(api_key_env)
71
+
72
+
73
+ def get_api_host() -> str:
74
+ config = load_config(required=False)
75
+ return str(config.get("api_host", "datadile.io"))
76
+
77
+
78
+ def _resolve_data_source_config(data_source: Any, label: str) -> dict[str, Any]:
79
+ if not isinstance(data_source, dict):
80
+ raise KeyError(f"Missing {label} mapping in config file.")
81
+
82
+ if data_source.get("id"):
83
+ api_key = get_api_key()
84
+ if not api_key:
85
+ api_key_env = str(load_config(required=False).get("api_key_env", DEFAULT_API_KEY_ENV))
86
+ raise ValueError(
87
+ f"{label}.id requires an API key for server-backed data source access. "
88
+ f"Set the {api_key_env} environment variable."
89
+ )
90
+ return {"id": str(data_source["id"]), "api_key": api_key, "api_host": get_api_host()}
91
+
92
+ if data_source.get("password"):
93
+ raise ValueError(f"Do not put data source passwords in datadile.yaml. Use password_env instead.")
94
+
95
+ password_env = str(data_source.get("password_env", DEFAULT_DATA_SOURCE_PASSWORD_ENV))
96
+ password = os.environ.get(password_env)
97
+ if not password:
98
+ raise ValueError(f"Missing data source password. Set the {password_env} environment variable.")
99
+
100
+ return {
101
+ "type": data_source.get("type", "postgresql"),
102
+ "host": data_source.get("host", "localhost"),
103
+ "port": int(data_source.get("port", 5432)),
104
+ "user": data_source.get("user"),
105
+ "password": password,
106
+ "database": data_source.get("database"),
107
+ }
108
+
109
+
110
+ def get_data_source_config(name: str | None = None) -> dict[str, Any]:
111
+ config = load_config()
112
+
113
+ data_sources = config.get("data_sources")
114
+ if not isinstance(data_sources, dict):
115
+ raise KeyError("Missing data_sources mapping in config file.")
116
+
117
+ data_source_name = name or config.get("default_data_source")
118
+ if not data_source_name:
119
+ raise ValueError("Missing data source. Add default_data_source to datadile.yaml or data_source to the test.")
120
+
121
+ data_source_name = str(data_source_name)
122
+ if data_source_name not in data_sources:
123
+ raise KeyError(f"Unknown data source '{data_source_name}' in config file.")
124
+
125
+ return _resolve_data_source_config(data_sources[data_source_name], f"data_sources.{data_source_name}")
datadile/core.py ADDED
@@ -0,0 +1,270 @@
1
+ import argparse
2
+ import ast
3
+ import operator
4
+ import shutil
5
+ import sys
6
+ from dataclasses import dataclass
7
+ from decimal import Decimal
8
+ from importlib import resources
9
+ from pathlib import Path
10
+ from typing import Any, Callable
11
+
12
+ import yaml
13
+ from rich.console import Console
14
+ from rich.table import Table
15
+ from sqlalchemy import create_engine, text
16
+
17
+ from .config import get_data_source_config
18
+
19
+ console = Console()
20
+
21
+ DATA_TEST_FILE_PATTERN = "*.dile.yaml"
22
+ DEFAULT_SKILL_INSTALL_PATH = Path(".opencode") / "skills" / "datadile" / "SKILL.md"
23
+ SEVERITIES = {"LOW", "MEDIUM", "HIGH"}
24
+ EXPECT_OPERATORS = {
25
+ ">=": operator.ge,
26
+ "<=": operator.le,
27
+ "!=": operator.ne,
28
+ "=": operator.eq,
29
+ ">": operator.gt,
30
+ "<": operator.lt,
31
+ }
32
+
33
+
34
+ @dataclass(frozen=True)
35
+ class DataTest:
36
+ name: str
37
+ description: str
38
+ query: str
39
+ expect: str
40
+ severity: str = "MEDIUM"
41
+ data_source: str | None = None
42
+
43
+
44
+ @dataclass(frozen=True)
45
+ class DataTestResult:
46
+ test: DataTest
47
+ actual: Any = None
48
+ passed: bool = False
49
+ error: str | None = None
50
+
51
+
52
+ def _build_postgres_connection_url(data_source_config: dict) -> str:
53
+ return (
54
+ f"postgresql+psycopg2://{data_source_config['user']}:{data_source_config['password']}"
55
+ f"@{data_source_config['host']}:{data_source_config['port']}/{data_source_config['database']}"
56
+ )
57
+
58
+
59
+ def load_data_tests(path: str | Path) -> list[DataTest]:
60
+ test_path = Path(path)
61
+ with test_path.open() as f:
62
+ raw = yaml.safe_load(f)
63
+
64
+ if isinstance(raw, dict) and "tests" in raw:
65
+ raw_tests = raw["tests"]
66
+ else:
67
+ raw_tests = raw
68
+
69
+ if not isinstance(raw_tests, list):
70
+ raise ValueError("Data test file must contain a list of tests or a top-level 'tests' list.")
71
+
72
+ return [_parse_data_test(item, index) for index, item in enumerate(raw_tests, start=1)]
73
+
74
+
75
+ def discover_data_test_files(root: str | Path = ".") -> list[Path]:
76
+ return sorted(Path(root).rglob(DATA_TEST_FILE_PATTERN))
77
+
78
+
79
+ def _parse_data_test(raw: Any, index: int) -> DataTest:
80
+ if not isinstance(raw, dict):
81
+ raise ValueError(f"Test #{index} must be a mapping.")
82
+
83
+ missing = [field for field in ("name", "description", "query", "expect") if field not in raw]
84
+ if missing:
85
+ raise ValueError(f"Test #{index} is missing required field(s): {', '.join(missing)}.")
86
+
87
+ severity = str(raw.get("severity", "MEDIUM")).upper()
88
+ if severity not in SEVERITIES:
89
+ raise ValueError(f"Test #{index} has invalid severity '{severity}'. Use LOW, MEDIUM, or HIGH.")
90
+
91
+ return DataTest(
92
+ name=str(raw["name"]),
93
+ description=str(raw["description"]),
94
+ query=str(raw["query"]),
95
+ expect=str(raw["expect"]),
96
+ severity=severity,
97
+ data_source=str(raw["data_source"]) if raw.get("data_source") else None,
98
+ )
99
+
100
+
101
+ def evaluate_expectation(actual: Any, expectation: str) -> bool:
102
+ op_symbol, expected = _parse_expectation(expectation)
103
+ return EXPECT_OPERATORS[op_symbol](actual, expected)
104
+
105
+
106
+ def _parse_expectation(expectation: str) -> tuple[str, Any]:
107
+ expression = expectation.strip()
108
+ for op_symbol in sorted(EXPECT_OPERATORS, key=len, reverse=True):
109
+ if expression.startswith(op_symbol):
110
+ rhs = expression[len(op_symbol) :].strip()
111
+ if not rhs:
112
+ raise ValueError(f"Expectation '{expectation}' is missing a comparison value.")
113
+ return op_symbol, _parse_expected_value(rhs)
114
+ raise ValueError(
115
+ f"Expectation '{expectation}' must start with one of: "
116
+ f"{', '.join(sorted(EXPECT_OPERATORS, key=len, reverse=True))}."
117
+ )
118
+
119
+
120
+ def _parse_expected_value(value: str) -> Any:
121
+ try:
122
+ return ast.literal_eval(value)
123
+ except (SyntaxError, ValueError):
124
+ return yaml.safe_load(value)
125
+
126
+
127
+ def run_data_tests(tests: list[DataTest], data_source_config: dict | Callable[[str | None], dict]) -> list[DataTestResult]:
128
+ query_runners: dict[str | None, Callable[[str], list[dict[str, Any]]]] = {}
129
+ default_run_query = None if callable(data_source_config) else _build_query_runner(data_source_config)
130
+ results = []
131
+
132
+ for test in tests:
133
+ try:
134
+ if callable(data_source_config):
135
+ if test.data_source not in query_runners:
136
+ query_runners[test.data_source] = _build_query_runner(data_source_config(test.data_source))
137
+ run_query = query_runners[test.data_source]
138
+ else:
139
+ run_query = default_run_query
140
+
141
+ rows = run_query(test.query)
142
+ actual = _normalize_query_result(rows)
143
+ passed = evaluate_expectation(actual, test.expect)
144
+ results.append(DataTestResult(test=test, actual=actual, passed=passed))
145
+ except Exception as exc:
146
+ results.append(DataTestResult(test=test, passed=False, error=str(exc)))
147
+
148
+ return results
149
+
150
+
151
+ def _build_query_runner(data_source_config: dict) -> Callable[[str], list[dict[str, Any]]]:
152
+ if data_source_config.get("id"):
153
+ data_source_id = data_source_config["id"]
154
+ raise ValueError(
155
+ f"Server-backed data source '{data_source_id}' is configured, but remote test execution "
156
+ "is not implemented in this package yet."
157
+ )
158
+
159
+ data_source_type = str(data_source_config.get("type", "postgresql")).lower()
160
+ if data_source_type in {"postgres", "postgresql"}:
161
+ engine = create_engine(_build_postgres_connection_url(data_source_config))
162
+
163
+ def run_postgres_query(query: str) -> list[dict[str, Any]]:
164
+ with engine.connect() as conn:
165
+ return [dict(row._mapping) for row in conn.execute(text(query))]
166
+
167
+ return run_postgres_query
168
+
169
+ raise ValueError(f"Unsupported data source type '{data_source_type}'.")
170
+
171
+
172
+ def _normalize_query_result(rows: list[dict[str, Any]]) -> Any:
173
+ normalized_rows = [_normalize_value(row) for row in rows]
174
+ if not normalized_rows:
175
+ return None
176
+
177
+ if len(normalized_rows) == 1:
178
+ row = normalized_rows[0]
179
+ values = list(row.values())
180
+ return values[0] if len(values) == 1 else row
181
+
182
+ if all(len(row) == 1 for row in normalized_rows):
183
+ return [next(iter(row.values())) for row in normalized_rows]
184
+ return normalized_rows
185
+
186
+
187
+ def _normalize_value(value: Any) -> Any:
188
+ if isinstance(value, dict):
189
+ return {key: _normalize_value(inner) for key, inner in value.items()}
190
+ if isinstance(value, list):
191
+ return [_normalize_value(inner) for inner in value]
192
+ if isinstance(value, Decimal):
193
+ if value == value.to_integral_value():
194
+ return int(value)
195
+ return float(value)
196
+ return value
197
+
198
+
199
+ def print_results(results: list[DataTestResult]) -> None:
200
+ table = Table(title="Datadile Data Tests")
201
+ table.add_column("Status")
202
+ table.add_column("Severity")
203
+ table.add_column("Name")
204
+ table.add_column("Expect")
205
+ table.add_column("Actual")
206
+
207
+ for result in results:
208
+ status = "PASS" if result.passed else "FAIL"
209
+ style = "green" if result.passed else "red"
210
+ actual = result.error if result.error else repr(result.actual)
211
+ table.add_row(
212
+ f"[{style}]{status}[/{style}]",
213
+ result.test.severity,
214
+ result.test.name,
215
+ result.test.expect,
216
+ actual,
217
+ )
218
+
219
+ console.print(table)
220
+
221
+ failures = [result for result in results if not result.passed]
222
+ console.print(f"{len(results) - len(failures)} passed, {len(failures)} failed")
223
+
224
+
225
+ def test_command(args: argparse.Namespace) -> None:
226
+ test_paths = [Path(args.filepath)] if args.filepath else discover_data_test_files()
227
+ if not test_paths:
228
+ console.print(f"No data test files found matching {DATA_TEST_FILE_PATTERN}")
229
+ sys.exit(1)
230
+
231
+ tests = []
232
+ for test_path in test_paths:
233
+ tests.extend(load_data_tests(test_path))
234
+
235
+ results = run_data_tests(tests, get_data_source_config)
236
+ print_results(results)
237
+
238
+ if any(not result.passed for result in results):
239
+ sys.exit(1)
240
+
241
+
242
+ def install_skill_command(args: argparse.Namespace) -> None:
243
+ destination = Path(args.destination)
244
+ destination.parent.mkdir(parents=True, exist_ok=True)
245
+
246
+ with resources.path("datadile.skill", "SKILL.md") as source:
247
+ shutil.copyfile(source, destination)
248
+
249
+ console.print(f"Installed Datadile skill to {destination}")
250
+
251
+
252
+ def main() -> None:
253
+ parser = argparse.ArgumentParser(description="Datadile data quality CLI")
254
+ subparsers = parser.add_subparsers(dest="command", required=True)
255
+
256
+ test_parser = subparsers.add_parser("test", help="Run YAML data tests")
257
+ test_parser.add_argument("filepath", nargs="?", help="Path to a YAML data test file")
258
+ test_parser.set_defaults(func=test_command)
259
+
260
+ skill_parser = subparsers.add_parser("install-skill", help="Install the bundled coding-agent skill")
261
+ skill_parser.add_argument(
262
+ "destination",
263
+ nargs="?",
264
+ default=DEFAULT_SKILL_INSTALL_PATH,
265
+ help=f"Where to write SKILL.md (default: {DEFAULT_SKILL_INSTALL_PATH})",
266
+ )
267
+ skill_parser.set_defaults(func=install_skill_command)
268
+
269
+ args = parser.parse_args()
270
+ args.func(args)
@@ -0,0 +1,167 @@
1
+ import ast
2
+ import re
3
+ from pathlib import Path
4
+
5
+
6
+ DEFAULT_CONTEXT_CHAR_LIMIT = 50_000
7
+ _SQL_START_RE = re.compile(r"^\s*(select|with|insert|update|delete|create|alter|drop)\b", re.I)
8
+
9
+
10
+ def detect_script_language(script: str, script_path: str | Path | None = None) -> str:
11
+ if script_path is not None:
12
+ suffix = Path(script_path).suffix.lower()
13
+ if suffix == ".py":
14
+ return "python"
15
+ if suffix == ".sql":
16
+ return "sql"
17
+
18
+ try:
19
+ ast.parse(script)
20
+ except SyntaxError:
21
+ if _SQL_START_RE.search(script):
22
+ return "sql"
23
+ return "unknown"
24
+
25
+ return "python"
26
+
27
+
28
+ def expand_python_internal_dependencies(
29
+ script: str,
30
+ script_path: str | Path,
31
+ char_limit: int = DEFAULT_CONTEXT_CHAR_LIMIT,
32
+ ) -> str:
33
+ """Append local Python dependencies imported by script, recursively, within char_limit."""
34
+ root_path = Path(script_path).resolve()
35
+ dependency_blocks = []
36
+ remaining = max(0, char_limit - len(script))
37
+
38
+ for dependency_path in _iter_internal_dependencies(script, root_path):
39
+ if remaining <= 0:
40
+ break
41
+
42
+ try:
43
+ dependency_code = dependency_path.read_text()
44
+ except OSError:
45
+ continue
46
+
47
+ block = f"\n\n# Internal dependency: {dependency_path}\n{dependency_code}"
48
+ if len(block) > remaining:
49
+ block = block[:remaining]
50
+ dependency_blocks.append(block)
51
+ remaining -= len(block)
52
+
53
+ return script + "".join(dependency_blocks)
54
+
55
+
56
+ def build_api_code(
57
+ script: str,
58
+ script_path: str | Path,
59
+ char_limit: int = DEFAULT_CONTEXT_CHAR_LIMIT,
60
+ ) -> str:
61
+ if detect_script_language(script, script_path) != "python":
62
+ return script
63
+ return expand_python_internal_dependencies(script, script_path, char_limit)
64
+
65
+
66
+ def _iter_internal_dependencies(script: str, script_path: Path):
67
+ seen = {script_path}
68
+ queued = list(_resolve_imports(script, script_path))
69
+
70
+ while queued:
71
+ dependency_path = queued.pop(0)
72
+ if dependency_path in seen:
73
+ continue
74
+ seen.add(dependency_path)
75
+ yield dependency_path
76
+
77
+ try:
78
+ dependency_code = dependency_path.read_text()
79
+ except OSError:
80
+ continue
81
+ queued.extend(_resolve_imports(dependency_code, dependency_path))
82
+
83
+
84
+ def _resolve_imports(script: str, source_path: Path) -> list[Path]:
85
+ try:
86
+ tree = ast.parse(script)
87
+ except SyntaxError:
88
+ return []
89
+
90
+ dependencies = []
91
+ seen = set()
92
+ for import_node in ast.walk(tree):
93
+ candidates = []
94
+ if isinstance(import_node, ast.Import):
95
+ for alias in import_node.names:
96
+ candidates.extend(_resolve_absolute_module(alias.name, source_path))
97
+ elif isinstance(import_node, ast.ImportFrom):
98
+ candidates.extend(_resolve_import_from(import_node, source_path))
99
+
100
+ for candidate in candidates:
101
+ if candidate == source_path or candidate in seen:
102
+ continue
103
+ seen.add(candidate)
104
+ dependencies.append(candidate)
105
+
106
+ return dependencies
107
+
108
+
109
+ def _resolve_import_from(import_node: ast.ImportFrom, source_path: Path) -> list[Path]:
110
+ module_parts = import_node.module.split(".") if import_node.module else []
111
+ if import_node.level:
112
+ base_dir = _relative_import_base(source_path, import_node.level)
113
+ paths = _module_candidates(base_dir, module_parts)
114
+ for alias in import_node.names:
115
+ if alias.name != "*":
116
+ paths.extend(_module_candidates(base_dir, [*module_parts, alias.name]))
117
+ return _existing_python_files(paths)
118
+
119
+ paths = []
120
+ if import_node.module:
121
+ paths.extend(_resolve_absolute_module(import_node.module, source_path))
122
+ for alias in import_node.names:
123
+ if alias.name != "*":
124
+ paths.extend(_resolve_absolute_module(f"{import_node.module}.{alias.name}", source_path))
125
+ return paths
126
+
127
+
128
+ def _resolve_absolute_module(module_name: str, source_path: Path) -> list[Path]:
129
+ module_parts = module_name.split(".")
130
+ candidates = []
131
+ for root in _candidate_roots(source_path):
132
+ candidates.extend(_module_candidates(root, module_parts))
133
+ return _existing_python_files(candidates)
134
+
135
+
136
+ def _candidate_roots(source_path: Path) -> list[Path]:
137
+ roots = [source_path.parent, Path.cwd().resolve()]
138
+ return list(dict.fromkeys(roots))
139
+
140
+
141
+ def _relative_import_base(source_path: Path, level: int) -> Path:
142
+ base = source_path.parent
143
+ for _ in range(max(0, level - 1)):
144
+ base = base.parent
145
+ return base
146
+
147
+
148
+ def _module_candidates(root: Path, module_parts: list[str]) -> list[Path]:
149
+ if not module_parts:
150
+ return [root / "__init__.py"]
151
+
152
+ module_path = root.joinpath(*module_parts)
153
+ return [module_path.with_suffix(".py"), module_path / "__init__.py"]
154
+
155
+
156
+ def _existing_python_files(paths: list[Path]) -> list[Path]:
157
+ existing = []
158
+ seen = set()
159
+ for path in paths:
160
+ resolved = path.resolve()
161
+ if resolved in seen or not resolved.is_file():
162
+ continue
163
+ if any(part in {"site-packages", "dist-packages", ".venv", "venv"} for part in resolved.parts):
164
+ continue
165
+ seen.add(resolved)
166
+ existing.append(resolved)
167
+ return existing
datadile/search.py ADDED
@@ -0,0 +1,61 @@
1
+ import os
2
+ import re
3
+ from pathlib import Path
4
+
5
+ from rank_bm25 import BM25Plus
6
+
7
+
8
+ def _is_text_file(path: Path) -> bool:
9
+ try:
10
+ with open(path, "rb") as f:
11
+ chunk = f.read(8192)
12
+ return b"\x00" not in chunk
13
+ except OSError:
14
+ return False
15
+
16
+
17
+ def search_codebase(search_dirs: list[str], column_names: list[str]) -> list[dict]:
18
+ """Search directories recursively for files mentioning column names, ranked by BM25."""
19
+ if not column_names:
20
+ return []
21
+
22
+ file_paths = []
23
+ file_contents = []
24
+
25
+ for search_dir in search_dirs:
26
+ for root, dirs, files in os.walk(search_dir):
27
+ dirs[:] = [d for d in dirs if not d.startswith(".")]
28
+ for fname in sorted(files):
29
+ fpath = Path(root) / fname
30
+ if not _is_text_file(fpath):
31
+ continue
32
+ try:
33
+ content = fpath.read_text(errors="ignore")
34
+ except OSError:
35
+ continue
36
+ file_paths.append(str(fpath))
37
+ file_contents.append(content)
38
+
39
+ if not file_contents:
40
+ return []
41
+
42
+ def tokenize(text: str) -> list[str]:
43
+ return re.findall(r"\w+", text.lower())
44
+
45
+ tokenized_corpus = [tokenize(c) for c in file_contents]
46
+ bm25 = BM25Plus(tokenized_corpus)
47
+
48
+ query_tokens = [col.lower() for col in column_names]
49
+ scores = bm25.get_scores(query_tokens)
50
+
51
+ ranked = sorted(
52
+ [
53
+ {"path": file_paths[i], "content": file_contents[i], "score": float(scores[i])}
54
+ for i in range(len(file_paths))
55
+ if scores[i] > 0
56
+ ],
57
+ key=lambda x: x["score"],
58
+ reverse=True,
59
+ )
60
+
61
+ return ranked
@@ -0,0 +1,102 @@
1
+ ---
2
+ name: datadile
3
+ description: Use when creating, editing, reviewing, or debugging Datadile data tests, datadile.yaml config, *.dile.yaml files, SQL expectations, or the datadile CLI/package code. Load this skill before changing data test YAML, connection configuration, test discovery, expectation parsing, result normalization, or CLI behavior.
4
+ ---
5
+
6
+ # Datadile
7
+
8
+ Datadile runs YAML-defined data tests against query results. Use this skill when work involves Datadile test files, configuration, CLI behavior, or package internals.
9
+
10
+ ## Use Cases
11
+
12
+ - Add or update `*.dile.yaml` files near application code.
13
+ - Review data tests for safe SQL, clear expectations, and valid severities.
14
+ - Create or edit `datadile.yaml` without storing secrets in the file.
15
+ - Debug `datadile test` failures, test discovery, config lookup, or data source selection.
16
+ - Modify Datadile internals such as parsing, expectation evaluation, result normalization, or CLI commands.
17
+
18
+ ## Core Rules
19
+
20
+ - Datadile discovers only files named `*.dile.yaml` when `datadile test` is run without a path.
21
+ - Each test needs `name`, `description`, `query`, and `expect`.
22
+ - `severity` is optional and must be `LOW`, `MEDIUM`, or `HIGH`; it defaults to `MEDIUM`.
23
+ - `data_source` is optional; without it, Datadile uses `default_data_source` from `datadile.yaml`.
24
+ - Keep passwords and API keys in environment variables. Use `password_env` and `api_key_env`; do not put secret values directly in YAML.
25
+ - PostgreSQL is the local execution target today. Keep test YAML generic enough that other query engines can be added later.
26
+
27
+ ## Data Test Examples
28
+
29
+ Use this shape for count checks:
30
+
31
+ ```yaml
32
+ tests:
33
+ - name: no_failed_orders_today
34
+ description: Orders should not fail during the current day.
35
+ severity: HIGH
36
+ data_source: app_db
37
+ query: |
38
+ select count(*) as failed_orders
39
+ from orders
40
+ where status = 'failed'
41
+ and created_at >= current_date
42
+ expect: "= 0"
43
+ ```
44
+
45
+ Use list expectations for one-column multi-row checks:
46
+
47
+ ```yaml
48
+ tests:
49
+ - name: active_plan_ids_are_known
50
+ description: Active subscriptions should only use known plan IDs.
51
+ query: |
52
+ select distinct plan_id
53
+ from subscriptions
54
+ where status = 'active'
55
+ order by plan_id
56
+ expect: "= [1, 2, 3]"
57
+ ```
58
+
59
+ ## Config Examples
60
+
61
+ Local config lives at `./datadile.yaml`; user config lives at `~/.datadile/datadile.yaml`. Local config takes precedence.
62
+
63
+ ```yaml
64
+ api_key_env: DATADILE_API_KEY
65
+ default_data_source: main
66
+
67
+ data_sources:
68
+ main:
69
+ type: postgresql
70
+ host: localhost
71
+ port: 5432
72
+ user: myuser
73
+ database: mydb
74
+ password_env: DATADILE_DATA_SOURCE_PASSWORD
75
+ ```
76
+
77
+ Server-backed data sources can reference an ID, but remote execution is not implemented in the local package yet:
78
+
79
+ ```yaml
80
+ api_key_env: DATADILE_API_KEY
81
+ default_data_source: warehouse
82
+
83
+ data_sources:
84
+ warehouse:
85
+ id: ds_abc123
86
+ ```
87
+
88
+ ## Expectation Semantics
89
+
90
+ - Supported operators are `=`, `!=`, `>`, `>=`, `<`, and `<=`.
91
+ - One-row, one-column results compare as a scalar, such as `= 0`.
92
+ - Multi-row, one-column results compare as a list, such as `= [1, 2, 3]`.
93
+ - Wider rows compare as dictionaries or lists of dictionaries.
94
+ - Empty result sets normalize to `None`, so use `= null` when that is intentional.
95
+
96
+ ## Coding Guidance
97
+
98
+ - Preserve the `*.dile.yaml` discovery rule unless the user explicitly asks to broaden it.
99
+ - Do not add support for inline passwords or API keys.
100
+ - Keep YAML examples quoted around expectation strings, especially values beginning with comparison operators.
101
+ - When changing CLI behavior, keep `datadile test [filepath]` working.
102
+ - When changing config behavior, keep local `datadile.yaml` precedence over `~/.datadile/datadile.yaml`.
File without changes
@@ -0,0 +1,340 @@
1
+ Metadata-Version: 2.4
2
+ Name: datadile
3
+ Version: 0.1.0
4
+ Summary: YAML-defined data tests for SQL query results
5
+ Project-URL: Homepage, https://github.com/Sand1929/datadile
6
+ Project-URL: Repository, https://github.com/Sand1929/datadile
7
+ Author-email: Sandy Suh <sandy@parsagon.io>
8
+ License: Apache License
9
+ Version 2.0, January 2004
10
+ http://www.apache.org/licenses/
11
+
12
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
13
+
14
+ 1. Definitions.
15
+
16
+ "License" shall mean the terms and conditions for use, reproduction,
17
+ and distribution as defined by Sections 1 through 9 of this document.
18
+
19
+ "Licensor" shall mean the copyright owner or entity authorized by
20
+ the copyright owner that is granting the License.
21
+
22
+ "Legal Entity" shall mean the union of the acting entity and all
23
+ other entities that control, are controlled by, or are under common
24
+ control with that entity. For the purposes of this definition,
25
+ "control" means (i) the power, direct or indirect, to cause the
26
+ direction or management of such entity, whether by contract or
27
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
28
+ outstanding shares, or (iii) beneficial ownership of such entity.
29
+
30
+ "You" (or "Your") shall mean an individual or Legal Entity
31
+ exercising permissions granted by this License.
32
+
33
+ "Source" form shall mean the preferred form for making modifications,
34
+ including but not limited to software source code, documentation
35
+ source, and configuration files.
36
+
37
+ "Object" form shall mean any form resulting from mechanical
38
+ transformation or translation of a Source form, including but
39
+ not limited to compiled object code, generated documentation,
40
+ and conversions to other media types.
41
+
42
+ "Work" shall mean the work of authorship, whether in Source or
43
+ Object form, made available under the License, as indicated by a
44
+ copyright notice that is included in or attached to the work
45
+ (an example is provided in the Appendix below).
46
+
47
+ "Derivative Works" shall mean any work, whether in Source or Object
48
+ form, that is based on (or derived from) the Work and for which the
49
+ editorial revisions, annotations, elaborations, or other modifications
50
+ represent, as a whole, an original work of authorship. For the purposes
51
+ of this License, Derivative Works shall not include works that remain
52
+ separable from, or merely link (or bind by name) to the interfaces of,
53
+ the Work and Derivative Works thereof.
54
+
55
+ "Contribution" shall mean any work of authorship, including
56
+ the original version of the Work and any modifications or additions
57
+ to that Work or Derivative Works thereof, that is intentionally
58
+ submitted to Licensor for inclusion in the Work by the copyright owner
59
+ or by an individual or Legal Entity authorized to submit on behalf of
60
+ the copyright owner. For the purposes of this definition, "submitted"
61
+ means any form of electronic, verbal, or written communication sent
62
+ to the Licensor or its representatives, including but not limited to
63
+ communication on electronic mailing lists, source code control systems,
64
+ and issue tracking systems that are managed by, or on behalf of, the
65
+ Licensor for the purpose of discussing and improving the Work, but
66
+ excluding communication that is conspicuously marked or otherwise
67
+ designated in writing by the copyright owner as "Not a Contribution."
68
+
69
+ "Contributor" shall mean Licensor and any individual or Legal Entity
70
+ on behalf of whom a Contribution has been received by Licensor and
71
+ subsequently incorporated within the Work.
72
+
73
+ 2. Grant of Copyright License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ copyright license to reproduce, prepare Derivative Works of,
77
+ publicly display, publicly perform, sublicense, and distribute the
78
+ Work and such Derivative Works in Source or Object form.
79
+
80
+ 3. Grant of Patent License. Subject to the terms and conditions of
81
+ this License, each Contributor hereby grants to You a perpetual,
82
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
83
+ (except as stated in this section) patent license to make, have made,
84
+ use, offer to sell, sell, import, and otherwise transfer the Work,
85
+ where such license applies only to those patent claims licensable
86
+ by such Contributor that are necessarily infringed by their
87
+ Contribution(s) alone or by combination of their Contribution(s)
88
+ with the Work to which such Contribution(s) was submitted. If You
89
+ institute patent litigation against any entity (including a
90
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
91
+ or a Contribution incorporated within the Work constitutes direct
92
+ or contributory patent infringement, then any patent licenses
93
+ granted to You under this License for that Work shall terminate
94
+ as of the date such litigation is filed.
95
+
96
+ 4. Redistribution. You may reproduce and distribute copies of the
97
+ Work or Derivative Works thereof in any medium, with or without
98
+ modifications, and in Source or Object form, provided that You
99
+ meet the following conditions:
100
+
101
+ (a) You must give any other recipients of the Work or
102
+ Derivative Works a copy of this License; and
103
+
104
+ (b) You must cause any modified files to carry prominent notices
105
+ stating that You changed the files; and
106
+
107
+ (c) You must retain, in the Source form of any Derivative Works
108
+ that You distribute, all copyright, patent, trademark, and
109
+ attribution notices from the Source form of the Work,
110
+ excluding those notices that do not pertain to any part of
111
+ the Derivative Works; and
112
+
113
+ (d) If the Work includes a "NOTICE" text file as part of its
114
+ distribution, then any Derivative Works that You distribute must
115
+ include a readable copy of the attribution notices contained
116
+ within such NOTICE file, excluding those notices that do not
117
+ pertain to any part of the Derivative Works, in at least one
118
+ of the following places: within a NOTICE text file distributed
119
+ as part of the Derivative Works; within the Source form or
120
+ documentation, if provided along with the Derivative Works; or,
121
+ within a display generated by the Derivative Works, if and
122
+ wherever such third-party notices normally appear. The contents
123
+ of the NOTICE file are for informational purposes only and
124
+ do not modify the License. You may add Your own attribution
125
+ notices within Derivative Works that You distribute, alongside
126
+ or as an addendum to the NOTICE text from the Work, provided
127
+ that such additional attribution notices cannot be construed
128
+ as modifying the License.
129
+
130
+ You may add Your own copyright statement to Your modifications and
131
+ may provide additional or different license terms and conditions
132
+ for use, reproduction, or distribution of Your modifications, or
133
+ for any such Derivative Works as a whole, provided Your use,
134
+ reproduction, and distribution of the Work otherwise complies with
135
+ the conditions stated in this License.
136
+
137
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
138
+ any Contribution intentionally submitted for inclusion in the Work
139
+ by You to the Licensor shall be under the terms and conditions of
140
+ this License, without any additional terms or conditions.
141
+ Notwithstanding the above, nothing herein shall supersede or modify
142
+ the terms of any separate license agreement you may have executed
143
+ with Licensor regarding such Contributions.
144
+
145
+ 6. Trademarks. This License does not grant permission to use the trade
146
+ names, trademarks, service marks, or product names of the Licensor,
147
+ except as required for reasonable and customary use in describing the
148
+ origin of the Work and reproducing the content of the NOTICE file.
149
+
150
+ 7. Disclaimer of Warranty. Unless required by applicable law or
151
+ agreed to in writing, Licensor provides the Work (and each
152
+ Contributor provides its Contributions) on an "AS IS" BASIS,
153
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
154
+ implied, including, without limitation, any warranties or conditions
155
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
156
+ PARTICULAR PURPOSE. You are solely responsible for determining the
157
+ appropriateness of using or redistributing the Work and assume any
158
+ risks associated with Your exercise of permissions under this License.
159
+
160
+ 8. Limitation of Liability. In no event and under no legal theory,
161
+ whether in tort (including negligence), contract, or otherwise,
162
+ unless required by applicable law (such as deliberate and grossly
163
+ negligent acts) or agreed to in writing, shall any Contributor be
164
+ liable to You for damages, including any direct, indirect, special,
165
+ incidental, or consequential damages of any character arising as a
166
+ result of this License or out of the use or inability to use the
167
+ Work (including but not limited to damages for loss of goodwill,
168
+ work stoppage, computer failure or malfunction, or any and all
169
+ other commercial damages or losses), even if such Contributor
170
+ has been advised of the possibility of such damages.
171
+
172
+ 9. Accepting Warranty or Additional Liability. While redistributing
173
+ the Work or Derivative Works thereof, You may choose to offer,
174
+ and charge a fee for, acceptance of support, warranty, indemnity,
175
+ or other liability obligations and/or rights consistent with this
176
+ License. However, in accepting such obligations, You may act only
177
+ on Your own behalf and on Your sole responsibility, not on behalf
178
+ of any other Contributor, and only if You agree to indemnify,
179
+ defend, and hold each Contributor harmless for any liability
180
+ incurred by, or claims asserted against, such Contributor by reason
181
+ of your accepting any such warranty or additional liability.
182
+
183
+ END OF TERMS AND CONDITIONS
184
+
185
+ APPENDIX: How to apply the Apache License to your work.
186
+
187
+ To apply the Apache License to your work, attach the following
188
+ boilerplate notice, with the fields enclosed by brackets "[]"
189
+ replaced with your own identifying information. (Don't include
190
+ the brackets!) The text should be enclosed in the appropriate
191
+ comment syntax for the file format. We also recommend that a
192
+ file or class name and description of purpose be included on the
193
+ same "printed page" as the copyright notice for easier
194
+ identification within third-party archives.
195
+
196
+ Copyright 2026 Sandy Suh
197
+
198
+ Licensed under the Apache License, Version 2.0 (the "License");
199
+ you may not use this file except in compliance with the License.
200
+ You may obtain a copy of the License at
201
+
202
+ http://www.apache.org/licenses/LICENSE-2.0
203
+
204
+ Unless required by applicable law or agreed to in writing, software
205
+ distributed under the License is distributed on an "AS IS" BASIS,
206
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
207
+ See the License for the specific language governing permissions and
208
+ limitations under the License.
209
+ License-File: LICENSE
210
+ Classifier: License :: OSI Approved :: Apache Software License
211
+ Classifier: Operating System :: OS Independent
212
+ Classifier: Programming Language :: Python :: 3
213
+ Requires-Python: >=3.10
214
+ Requires-Dist: httpx
215
+ Requires-Dist: prompt-toolkit
216
+ Requires-Dist: psycopg2-binary
217
+ Requires-Dist: pyyaml>=6.0
218
+ Requires-Dist: rank-bm25>=0.2
219
+ Requires-Dist: rich
220
+ Requires-Dist: sqlalchemy>=2.0
221
+ Requires-Dist: sqlparse>=0.4
222
+ Description-Content-Type: text/markdown
223
+
224
+ # datadile
225
+
226
+ Datadile runs YAML-defined data tests against query results.
227
+
228
+ ## Installation
229
+
230
+ ```bash
231
+ pip install datadile
232
+ ```
233
+
234
+ ## Configuration
235
+
236
+ datadile looks for a YAML config file in two locations (local takes precedence):
237
+
238
+ 1. `./datadile.yaml` (current directory)
239
+ 2. `~/.datadile/datadile.yaml` (user-level)
240
+
241
+ Copy the example and fill in your values:
242
+
243
+ ```bash
244
+ cp datadile.yaml.example datadile.yaml
245
+ ```
246
+
247
+ ```yaml
248
+ # Optional. Only required for premium server-backed features.
249
+ api_key_env: DATADILE_API_KEY
250
+
251
+ # Optional. Used by tests that do not set data_source.
252
+ default_data_source: main
253
+
254
+ data_sources:
255
+ main:
256
+ type: postgresql
257
+ host: localhost
258
+ port: 5432
259
+ user: myuser
260
+ database: mydb
261
+ password_env: DATADILE_DATA_SOURCE_PASSWORD
262
+ ```
263
+
264
+ Put data source passwords and API keys in environment variables, not in `datadile.yaml`:
265
+
266
+ ```bash
267
+ export DATADILE_DATA_SOURCE_PASSWORD='your_password_here'
268
+ export DATADILE_API_KEY='your_api_key_here'
269
+ ```
270
+
271
+ Use `password_env` or `api_key_env` if you want Datadile to read a different environment variable name.
272
+
273
+ Add more named entries under `data_sources` when tests need to run against multiple databases. `default_data_source` is optional, but tests that do not set `data_source` need a default.
274
+
275
+ `api_key_env` is optional. You only need it for premium features that access Datadile servers.
276
+
277
+ Data source entries can be defined inline, or referenced by ID if the connection details are stored on your Datadile account:
278
+
279
+ ```yaml
280
+ api_key_env: DATADILE_API_KEY
281
+
282
+ default_data_source: warehouse
283
+
284
+ data_sources:
285
+ warehouse:
286
+ id: ds_abc123
287
+ ```
288
+
289
+ `postgresql` is currently supported for local execution. Data tests keep `query` generic so query engines such as MongoDB can be added without changing the test format.
290
+
291
+ ## Usage
292
+
293
+ ```bash
294
+ datadile test
295
+ datadile test <path/to/file.dile.yaml>
296
+ ```
297
+
298
+ With no path, Datadile recursively discovers only files matching `*.dile.yaml` from the current directory. Other YAML files, such as `docker-compose.yaml`, GitHub Actions workflows, Helm values, and OpenAPI specs, are ignored.
299
+
300
+ ## Data Tests
301
+
302
+ Tests are defined in YAML. Each test has `name`, `description`, `query`, and `expect`. `severity` is optional and defaults to `MEDIUM`; valid values are `LOW`, `MEDIUM`, and `HIGH`. `data_source` is optional and references a named source from `data_sources`; otherwise Datadile uses `default_data_source` if one is configured.
303
+
304
+ For example, a test can set `data_source: app_db` after `app_db` is added under `data_sources`.
305
+
306
+ Use the `*.dile.yaml` naming convention and colocate data tests near the application code they protect:
307
+
308
+ ```text
309
+ app/orders/orders.py
310
+ app/orders/orders.dile.yaml
311
+ app/billing/invoices.ts
312
+ app/billing/invoices.dile.yaml
313
+ ```
314
+
315
+ ```yaml
316
+ tests:
317
+ - name: no_failed_orders
318
+ description: There should be no failed orders today.
319
+ severity: HIGH
320
+ data_source: app_db
321
+ query: |
322
+ select count(*) as failed_orders
323
+ from orders
324
+ where status = 'failed'
325
+ and created_at >= current_date
326
+ expect: "= 0"
327
+
328
+ - name: active_plan_ids
329
+ description: Active subscriptions should only use known plan IDs.
330
+ query: |
331
+ select distinct plan_id
332
+ from subscriptions
333
+ where status = 'active'
334
+ order by plan_id
335
+ expect: "= [1, 2, 3]"
336
+ ```
337
+
338
+ `expect` is a comparison string. Supported operators are `=`, `!=`, `>`, `>=`, `<`, and `<=`.
339
+
340
+ For one-row, one-column query results, Datadile compares the scalar value. For multi-row, one-column results, it compares a list of values. For wider results, it compares dictionaries or lists of dictionaries.
@@ -0,0 +1,12 @@
1
+ datadile/__init__.py,sha256=1V_F6lvCy82PQHLkHFzpaTtasq5D5RnaKNYNY6AfcOU,43
2
+ datadile/config.py,sha256=VpfsBRgAH6K5jKKNW2PEggDQor87grnsynb8_XQ_q_Y,4105
3
+ datadile/core.py,sha256=ywG2tj_7PgG6-BiY_nBdRxMeTwazRFHVQ-VeDwh5VWc,9144
4
+ datadile/script_context.py,sha256=yRlbBsArMcerzClruN1YbhnHHTAyVoQfpHzOGudQ5G0,5303
5
+ datadile/search.py,sha256=XTghjq-pqA4hc_JvzzxOlHR8wfgzZJWFtLIT44D1d80,1712
6
+ datadile/skill/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
7
+ datadile/skill/SKILL.md,sha256=1WkW29v_4i8sj82a_jvSM5J1vEKMoxGiPHaCm_qihpU,3721
8
+ datadile-0.1.0.dist-info/METADATA,sha256=QfKcJ3odgq9y9kBtLgeokBWruqz5fc9ddqcStPz8L9w,17271
9
+ datadile-0.1.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
10
+ datadile-0.1.0.dist-info/entry_points.txt,sha256=d68v93ozKg6FYneQutCIdepR6gntJduPRbHF-CvEmks,43
11
+ datadile-0.1.0.dist-info/licenses/LICENSE,sha256=f3t_-KHmcTzmw5cQW5ynF4U-qQZvojU0VuHWGiUcLoE,11339
12
+ datadile-0.1.0.dist-info/RECORD,,
@@ -0,0 +1,4 @@
1
+ Wheel-Version: 1.0
2
+ Generator: hatchling 1.29.0
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
@@ -0,0 +1,2 @@
1
+ [console_scripts]
2
+ datadile = datadile:main
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright 2026 Sandy Suh
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.