diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 3ba55576..89941e32 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -16,7 +16,7 @@ Please include: Always redact sensitive information like passwords before pasting. -Check [existing issues](https://github.com/datafold/data-diff/issues) before filing a new one. +Check [existing issues](https://github.com/dtsong/data-diff/issues) before filing a new one. ## Suggesting Enhancements @@ -27,7 +27,7 @@ Open an issue for feature requests, new database support, or documentation impro ### Setup ```bash -git clone https://github.com/datafold/data-diff.git +git clone https://github.com/dtsong/data-diff.git cd data-diff uv sync # install all dependencies uv run pre-commit install # set up pre-commit hooks diff --git a/README.md b/README.md index 7b0deb15..7c29ab7a 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # data-diff -- Efficiently diff rows across databases -[![Community Maintained](https://img.shields.io/badge/maintained-community-blue)](https://github.com/datafold/data-diff) +[![Community Maintained](https://img.shields.io/badge/maintained-community-blue)](https://github.com/dtsong/data-diff) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![PyPI](https://img.shields.io/pypi/v/data-diff)](https://pypi.org/project/data-diff/) @@ -89,8 +89,8 @@ See the [full documentation](https://data-diff.readthedocs.io/) for configuratio ## Contributors - - + + ## License diff --git a/data_diff/dbt.py b/data_diff/dbt.py index 02a332d0..31ba681b 100644 --- a/data_diff/dbt.py +++ b/data_diff/dbt.py @@ -58,7 +58,7 @@ def dbt_diff( config = dbt_parser.get_datadiff_config() if not state and not (config.prod_database or config.prod_schema): - doc_url = "https://github.com/datafold/data-diff" + doc_url = "https://github.com/dtsong/data-diff" raise DataDiffDbtProjectVarsNotFoundError( f"""vars: data_diff: section not found in dbt_project.yml.\n\nTo solve this, please configure your dbt project: \n{doc_url}\n\nOr specify a production manifest using the `--state` flag.""" ) @@ -200,7 +200,7 @@ def _get_prod_path_from_config(config, model, dev_database, dev_schema) -> tuple if not config.prod_custom_schema: raise DataDiffCustomSchemaNoConfigError( f"Found a custom schema on model {model.name}, but no value for\nvars:\n data_diff:\n prod_custom_schema:\nPlease set a value or utilize the `--state` flag!\n\n" - + "For more details see: https://github.com/datafold/data-diff" + + "For more details see: https://github.com/dtsong/data-diff" ) prod_schema = config.prod_custom_schema.replace("", custom_schema) # no custom schema, use the default diff --git a/data_diff/dbt_parser.py b/data_diff/dbt_parser.py index bb863b32..bc4f1387 100644 --- a/data_diff/dbt_parser.py +++ b/data_diff/dbt_parser.py @@ -265,7 +265,7 @@ def get_run_results_models(self) -> list[ManifestJsonConfig.Nodes]: ) if dbt_version >= parse_version(UPPER_DBT_V): logger.warning( - f"{dbt_version} is a recent version of dbt and may not be fully tested with data-diff! \nPlease report any issues to https://github.com/datafold/data-diff/issues" + f"{dbt_version} is a recent version of dbt and may not be fully tested with data-diff! \nPlease report any issues to https://github.com/dtsong/data-diff/issues" ) success_models = [x.unique_id for x in run_results_validated.results if x.status == x.Status.success] diff --git a/docs/conf.py b/docs/conf.py index 1e5ea23b..b9cd7167 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -59,7 +59,7 @@ # General information about the project. project = "data-diff" -copyright = "Datafold" +copyright = "data-diff contributors" author = "Erez Shinan" # The version info for the project you're documenting, acts as replacement for diff --git a/docs/index.rst b/docs/index.rst index ffe3bf6b..1211ba83 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -11,14 +11,11 @@ data-diff **Data-diff** is a command-line tool and Python library for comparing tables in and across databases. -For more information, `See our README `_ +For more information, `See our README `_ Resources --------- -- Source code (git): ``_ -- The rest of the `documentation`_ - -.. _documentation: https://docs.datafold.com/guides/os_data_diff +- Source code (git): ``_ diff --git a/docs/new-database-driver-guide.rst b/docs/new-database-driver-guide.rst index 28c9588b..5b9c4878 100644 --- a/docs/new-database-driver-guide.rst +++ b/docs/new-database-driver-guide.rst @@ -1,7 +1,7 @@ How to implement a new database driver for data-diff ==================================================== -First, read through the `CONTRIBUTING.md `_ document. +First, read through the `CONTRIBUTING.md `_ document. Make sure data-diff is set up for development, and that all the tests pass (try to at least set it up for mysql and postgresql) diff --git a/docs/usage_analytics.md b/docs/usage_analytics.md deleted file mode 100644 index 35923cee..00000000 --- a/docs/usage_analytics.md +++ /dev/null @@ -1,31 +0,0 @@ -# Usage Analytics & Data Privacy - -data-diff collects anonymous usage data to help our team improve the tool and to apply development efforts to where our users need them most. - -We capture two events: one when the data-diff run starts, and one when it is finished. No user data or potentially sensitive information is or ever will be collected. The captured data is limited to: - -- Operating System and Python version -- Types of databases used (postgresql, mysql, etc.) -- Sizes of tables diffed, run time, and diff row count (numbers only) -- Error message, if any, truncated to the first 20 characters. -- A persistent UUID to indentify the session, stored in `~/.datadiff.toml` -- IP address of the machine running diff - -When using the `--dbt` feature, we also collect: - -- dbt generated UUIDs (user_id and project_id) -- dbt-core version (e.g. 1.2.0) -- Users can also choose to provide an email address - - When tracking is not disabled, we will prompt the user once to opt-in to release notifications - - Users can decide not to opt-in by leaving the prompt blank - -To disable, use one of the following methods: - -* **CLI**: use the `--no-tracking` flag. -* **Config file**: set `no_tracking = true` (for example, under `[run.default]`) -* **Python API**: - ```python - import data_diff - # Invoke the following before making any API calls - data_diff.disable_tracking() - ``` diff --git a/pyproject.toml b/pyproject.toml index 098573c0..4bba9418 100755 --- a/pyproject.toml +++ b/pyproject.toml @@ -64,9 +64,9 @@ all-dbs = [ data-diff = "data_diff.__main__:main" [project.urls] -Repository = "https://github.com/datafold/data-diff" -Issues = "https://github.com/datafold/data-diff/issues" -Changelog = "https://github.com/datafold/data-diff/blob/master/CHANGELOG.md" +Repository = "https://github.com/dtsong/data-diff" +Issues = "https://github.com/dtsong/data-diff/issues" +Changelog = "https://github.com/dtsong/data-diff/blob/master/CHANGELOG.md" [dependency-groups] dev = [