Metadata-Version: 2.4
Name: datadile
Version: 0.1.2
Summary: YAML-defined data tests for SQL query results
Project-URL: Homepage, https://github.com/Sand1929/datadile
Project-URL: Repository, https://github.com/Sand1929/datadile
Author-email: Sandy Suh <sandy@parsagon.io>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright 2026 Sandy Suh
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
License-File: LICENSE
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Requires-Dist: httpx
Requires-Dist: prompt-toolkit
Requires-Dist: psycopg2-binary
Requires-Dist: pyyaml>=6.0
Requires-Dist: rank-bm25>=0.2
Requires-Dist: rich
Requires-Dist: sqlalchemy>=2.0
Requires-Dist: sqlglot>=25.0
Requires-Dist: sqlparse>=0.4
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == 'dev'
Description-Content-Type: text/markdown

# datadile

Datadile runs YAML-defined data tests against query results.

Use Datadile to make the data assumptions behind your application, migrations, and backfills explicit and testable. Define lightweight checks in human-readable YAML, run them from the CLI against your database, and catch unsafe data states before they break code, block releases, or corrupt downstream workflows.

Datadile is AI-first: coding agents can add data tests as they edit code and use Datadile Cloud context to understand which assumptions are passing or failing. Datadile Cloud adds dashboards, alerts, anomaly detection, and adversarial algorithms that help catch data-related bugs agents might otherwise miss.

## Quick Start

Install Datadile:

```bash
pip install datadile
```

Add your project config file. Run this from your project or repo root, or use `--global` to add a user-level config file:

```bash
datadile init [--global]
```

Then fill in `datadile.yaml` with your PostgreSQL connection details:

```yaml
default_data_source: main

data_sources:
  main:
    type: postgresql
    host: localhost
    port: 5432
    user: myuser
    database: mydb
    password_env: DATABASE_PASSWORD
```

Put the password in an environment variable, not in `datadile.yaml`:

```bash
export DATABASE_PASSWORD='your_password_here'
```

Recommended: install the Datadile coding-agent skill so your agent can write data tests using Datadile's conventions:

```bash
datadile install-skill [--global]
```

The default install target is `.agents/skills/`. For agents that don't support `.agents/skills/` (e.g., Claude Code), pass `--agent`, for example:

```bash
datadile install-skill --agent claude
```

Then ask your coding agent to create data tests for your project, for example:

```text
Add tests for the key data assumptions in this code.
```

If you want to try Datadile without a coding agent, create your first data test in `smoke.dile.yaml`:

```yaml
# smoke.dile.yaml
tests:
  - name: database_connection_works
    description: Datadile can connect to the configured database and run a read-only query.
    query: |
      select 1 as value
    expect: "= 1"
```

Run the tests:

```bash
datadile test
```

Datadile prints a results table and a summary such as `1 passed, 0 failed`.
To save full, untruncated results to JSON, pass `--results-file`:

```bash
datadile test --results-file datadile-results.json
```

## Data Tests

Tests are defined in YAML files named `*.dile.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. `identity` is optional and gives Datadile Cloud a stable identifier for the test, even if the file path changes.

Use the `*.dile.yaml` naming convention and colocate data tests near the application code they protect:

```text
app/orders/orders.py
app/orders/orders.dile.yaml
app/billing/invoices.ts
app/billing/invoices.dile.yaml
```

For example, a test can set `data_source: app_db` after `app_db` is added under `data_sources`:

```yaml
tests:
  - name: no_failed_orders
    identity: orders.no_failed_orders
    description: There should be no failed orders today.
    severity: HIGH
    data_source: app_db
    query: |
      select count(*) as failed_orders
      from orders
      where status = 'failed'
        and created_at >= current_date
    expect: "= 0"

  - name: active_plan_ids
    description: Active subscriptions should only use known plan IDs.
    query: |
      select distinct plan_id
      from subscriptions
      where status = 'active'
      order by plan_id
    expect: "= [1, 2, 3]"
```

`expect` is a comparison string. Supported operators are `=`, `!=`, `>`, `>=`, `<`, and `<=`.

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.

Use `row_count` when the query should return inspectable rows but the assertion is about how many rows were returned:

```yaml
tests:
  - name: failed_orders_are_limited
    description: There should be at most one failed order today, with rows shown on failure.
    query: |
      select id, status, created_at
      from orders
      where status = 'failed'
        and created_at >= current_date
      order by created_at desc
    expect: "row_count <= 1"
```

## Configuration

Datadile looks for a YAML config file in two locations. Local config takes precedence:

1. `./datadile.yaml` (current directory)
2. `~/.datadile/datadile.yaml` (user-level)

Create a starter config with `datadile init`, then fill in your values. To write it somewhere else, pass a destination path. Existing files are not overwritten unless you pass `--force`.

```bash
datadile init path/to/datadile.yaml
datadile init --force
```

For a user-level config instead of a project-local one:

```bash
datadile init --global
```

```yaml
default_data_source: main

data_sources:
  main:
    type: postgresql
    host: localhost
    port: 5432
    user: myuser
    database: mydb
    password_env: DATABASE_PASSWORD
```

Put data source passwords in environment variables, not in `datadile.yaml`:

```bash
export DATABASE_PASSWORD='your_password_here'
```

Use `password_env` if you want Datadile to read a different environment variable name.

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.

`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.

## Usage

```bash
datadile test
datadile test <path/to/file.dile.yaml>
datadile test --results-file datadile-results.json
```

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.

Use `datadile context` to show existing data tests for the same data source and overlapping tables or columns:

```bash
datadile context --data-source app_db --table orders
datadile context --data-source app_db --column orders.status
datadile context --data-source app_db --table orders --format json
```

The context command loads local `*.dile.yaml` files. If an API key is configured, it also fetches matching uploaded tests from Datadile Cloud to determine what tests are currently passing and failing.

## Coding Agent Skill

Datadile includes a bundled coding-agent skill with Datadile-specific guidance. For many projects, the fastest path is to add `datadile.yaml`, install the skill, and ask your coding agent to write the first `*.dile.yaml` tests. The skill is optional and not required to run data tests.

Install it into the current working directory with:

```bash
datadile install-skill
```

By default, this writes the skill to `.agents/skills/datadile/SKILL.md` under the directory where you run the command. The command shows the full destination path and asks for confirmation before writing the file.

To install for a different coding agent, pass `--agent`, for example:

```bash
datadile install-skill --agent claude
```

To install into the selected agent's user-level skills directory instead, pass `--global`:

```bash
datadile install-skill --global
datadile install-skill --agent claude --global
```

To install it somewhere else, pass a destination path:

```bash
datadile install-skill path/to/SKILL.md
```

For non-interactive installs, pass `--yes` to skip the confirmation prompt.

## Datadile Cloud

Datadile Cloud and server-backed data sources are optional premium features. Local data tests do not require an API key.

To enable cloud features, put the API key in an environment variable and reference that variable from `datadile.yaml`:

```bash
export DATADILE_API_KEY='your_api_key_here'
```

```yaml
api_key_env: DATADILE_API_KEY
```

If an API key is configured, Datadile records completed local test runs in Datadile Cloud. Datadile monitors runs to alert you about failures and anomalies within your tests. Datadile also draws on this data to provide context to your coding agent, allowing it to take into account what data assumptions are failing while writing your code.

Data source entries can also reference an ID if the connection details are stored on your Datadile account:

```yaml
api_key_env: DATADILE_API_KEY

default_data_source: warehouse

data_sources:
  warehouse:
    id: ds_abc123
```
