sqlsure 0.1.0__tar.gz

sqlsure-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 [yyyy] [name of copyright owner]
+
+   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.

sqlsure-0.1.0/PKG-INFO

@@ -0,0 +1,141 @@
+Metadata-Version: 2.4
+Name: sqlsure
+Version: 0.1.0
+Summary: AI writes your SQL. sqlsure makes sure it's right — a deterministic semantic inspector that catches fan-out double-counting, summed averages, wrong join keys, and PII exposure before the query runs. Zero false alarms on 2,568 benchmark gold queries.
+Author-email: Tejus Arora <iam.tejusarora@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://sqlsure.ai
+Project-URL: Repository, https://github.com/sqlsure/sqlsure
+Project-URL: Documentation, https://github.com/sqlsure/sqlsure#readme
+Project-URL: Issues, https://github.com/sqlsure/sqlsure/issues
+Keywords: sql,semantic-layer,dbt,text-to-sql,linter,data-quality,mcp
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Database
+Classifier: Topic :: Software Development :: Quality Assurance
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: sqlglot>=30.0
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0; extra == "mcp"
+Dynamic: license-file
+
+# sqlsure
+
+**AI writes your SQL. sqlsure makes sure it's right.**
+
+A query can be perfectly valid, run without error, and return a number
+that's silently wrong — revenue double-counted by a join, an average
+summed, a patient identifier exposed. Databases don't catch this.
+Linters don't catch this. LLMs reviewing their own SQL don't catch this.
+
+sqlsure does — deterministically, in 0.1 ms, before the query runs.
+
+> **Proof, not promises:** we ran sqlsure over the gold answers of the two
+> benchmarks every text-to-SQL model is graded on. **2,568 expert-written
+> queries, 45 flags, zero false alarms** — including a BIRD dev gold answer
+> that is [provably wrong by 8×](docs/reports/bird-audit.md) from the exact
+> bug class sqlsure targets, and a schema defect
+> [now filed upstream](https://github.com/bird-bench/mini_dev/issues/37).
+
+## How it works
+
+sqlsure judges SQL against facts your team already declared — dbt `unique`
+tests become grain, `relationships` tests become join cardinality, one-line
+`meta` tags mark what's safe to sum. No new language to learn, no model to
+maintain by hand. Rules are dictionary lookups, not LLM calls: same input,
+same verdict, every time, offline.
+
+Every rejection carries a machine-actionable `fix`, so AI agents
+self-repair: **draft → check → fix → check → execute.** In our benchmark,
+applying the fix verbatim produced a passing query 10/10 times.
+
+## Quick start
+
+```bash
+pip install sqlsure
+```
+
+```python
+from sqlsure import SemanticModel, check
+violations = check(sql, model)   # [] means semantically safe
+```
+
+Or clone and run the 30-second demo:
+
+```bash
+python check.py                   # 5 wrong queries rejected, 1 approved — with fixes
+python -m sqlsure.scan path/to/dbt-repo --report report.md   # audit any dbt repo
+```
+
+## Three doors, one engine
+
+**1. CI gate** — blocks the merge when a PR double-counts:
+
+```bash
+python -m sqlsure.cli --model model.json query.sql   # exit 1 on violations
+```
+
+**2. MCP server** — your AI agent must pass inspection before executing:
+
+```bash
+claude mcp add sqlsure -- python -m sqlsure.mcp_server --model /abs/path/model.json
+```
+
+See [docs/MCP.md](docs/MCP.md) for tool reference and agent-loop patterns.
+
+**3. Library** — embed `check()` inside any text-to-SQL product or agent
+framework. A drop-in [SemanticGate](integrations/semantic_gate.py) wraps
+Vanna/WrenAI-style generators; a
+[semantic eval metric](integrations/eval_metric.py) scores NL2SQL output
+where execution-accuracy is blind.
+
+## The rules (v0.1)
+
+| Rule | Severity | Catches |
+|---|---|---|
+| FANOUT | error | SUM/COUNT of additive measure after one-to-many join |
+| CHASM | error | two+ fan-out joins multiplying each other |
+| ADDITIVITY | error | SUM of a non-additive measure (rates, averages) |
+| SEMI_ADDITIVE | error | balances/censuses summed across their snapshot dimension |
+| JOIN_KEY | error | join on columns matching no declared relationship |
+| CROSS_JOIN | error | join with no predicate |
+| WEIGHTED_AVG | warning | AVG silently re-weighted by fan-out |
+| UNDECLARED_JOIN | warning | join with no declared relationship (unverifiable ≠ safe) |
+| SENSITIVE_COLUMN | policy | PHI/PII column exposed in query output |
+
+When sqlsure can't verify something, it says "can't verify" — never "looks
+fine." Honest uncertainty is a feature.
+
+## Where the rulebook comes from
+
+- **dbt** (works today): `manifest.json` or `schema.yml` — the tests teams
+  already wrote become enforceable semantics, zero config
+- **Plain PK/FK declarations** (works today — powered the benchmark audits)
+- **Hand-written JSON** — [model.example.json](model.example.json)
+- Cube, Snowflake Semantic Views, OSI — adapters on the roadmap; the
+  engine only ever sees one `SemanticModel`
+
+## Validated on
+
+- **16/16 rule tests, 100% recall / 0% false positives** on the paired
+  benchmark ([docs/METRICS.md](docs/METRICS.md))
+- **Real production repos** (Mattermost's warehouse, Fivetran packages,
+  dbt's jaffle shop) — [docs/TEST-REPORTS.md](docs/TEST-REPORTS.md)
+- **Spider + BIRD gold queries** — the zero-noise external audit above
+
+## Learn more
+
+- [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) — how it physically works,
+  ELI5 → god level, with real intermediate outputs
+- [docs/FOR-DUMMIES.md](docs/FOR-DUMMIES.md) — every concept from zero
+- [docs/INTEGRATIONS.md](docs/INTEGRATIONS.md) — GitHub Action, pre-commit,
+  MCP, Snowflake UDF / Cortex Agent tool, query-history audit
+- [docs/MCP.md](docs/MCP.md) — MCP server documentation
+- [CONTRIBUTING.md](CONTRIBUTING.md) — adding rules and loaders
+
+Apache-2.0 · [sqlsure.ai](https://sqlsure.ai)

sqlsure-0.1.0/README.md

@@ -0,0 +1,115 @@
+# sqlsure
+
+**AI writes your SQL. sqlsure makes sure it's right.**
+
+A query can be perfectly valid, run without error, and return a number
+that's silently wrong — revenue double-counted by a join, an average
+summed, a patient identifier exposed. Databases don't catch this.
+Linters don't catch this. LLMs reviewing their own SQL don't catch this.
+
+sqlsure does — deterministically, in 0.1 ms, before the query runs.
+
+> **Proof, not promises:** we ran sqlsure over the gold answers of the two
+> benchmarks every text-to-SQL model is graded on. **2,568 expert-written
+> queries, 45 flags, zero false alarms** — including a BIRD dev gold answer
+> that is [provably wrong by 8×](docs/reports/bird-audit.md) from the exact
+> bug class sqlsure targets, and a schema defect
+> [now filed upstream](https://github.com/bird-bench/mini_dev/issues/37).
+
+## How it works
+
+sqlsure judges SQL against facts your team already declared — dbt `unique`
+tests become grain, `relationships` tests become join cardinality, one-line
+`meta` tags mark what's safe to sum. No new language to learn, no model to
+maintain by hand. Rules are dictionary lookups, not LLM calls: same input,
+same verdict, every time, offline.
+
+Every rejection carries a machine-actionable `fix`, so AI agents
+self-repair: **draft → check → fix → check → execute.** In our benchmark,
+applying the fix verbatim produced a passing query 10/10 times.
+
+## Quick start
+
+```bash
+pip install sqlsure
+```
+
+```python
+from sqlsure import SemanticModel, check
+violations = check(sql, model)   # [] means semantically safe
+```
+
+Or clone and run the 30-second demo:
+
+```bash
+python check.py                   # 5 wrong queries rejected, 1 approved — with fixes
+python -m sqlsure.scan path/to/dbt-repo --report report.md   # audit any dbt repo
+```
+
+## Three doors, one engine
+
+**1. CI gate** — blocks the merge when a PR double-counts:
+
+```bash
+python -m sqlsure.cli --model model.json query.sql   # exit 1 on violations
+```
+
+**2. MCP server** — your AI agent must pass inspection before executing:
+
+```bash
+claude mcp add sqlsure -- python -m sqlsure.mcp_server --model /abs/path/model.json
+```
+
+See [docs/MCP.md](docs/MCP.md) for tool reference and agent-loop patterns.
+
+**3. Library** — embed `check()` inside any text-to-SQL product or agent
+framework. A drop-in [SemanticGate](integrations/semantic_gate.py) wraps
+Vanna/WrenAI-style generators; a
+[semantic eval metric](integrations/eval_metric.py) scores NL2SQL output
+where execution-accuracy is blind.
+
+## The rules (v0.1)
+
+| Rule | Severity | Catches |
+|---|---|---|
+| FANOUT | error | SUM/COUNT of additive measure after one-to-many join |
+| CHASM | error | two+ fan-out joins multiplying each other |
+| ADDITIVITY | error | SUM of a non-additive measure (rates, averages) |
+| SEMI_ADDITIVE | error | balances/censuses summed across their snapshot dimension |
+| JOIN_KEY | error | join on columns matching no declared relationship |
+| CROSS_JOIN | error | join with no predicate |
+| WEIGHTED_AVG | warning | AVG silently re-weighted by fan-out |
+| UNDECLARED_JOIN | warning | join with no declared relationship (unverifiable ≠ safe) |
+| SENSITIVE_COLUMN | policy | PHI/PII column exposed in query output |
+
+When sqlsure can't verify something, it says "can't verify" — never "looks
+fine." Honest uncertainty is a feature.
+
+## Where the rulebook comes from
+
+- **dbt** (works today): `manifest.json` or `schema.yml` — the tests teams
+  already wrote become enforceable semantics, zero config
+- **Plain PK/FK declarations** (works today — powered the benchmark audits)
+- **Hand-written JSON** — [model.example.json](model.example.json)
+- Cube, Snowflake Semantic Views, OSI — adapters on the roadmap; the
+  engine only ever sees one `SemanticModel`
+
+## Validated on
+
+- **16/16 rule tests, 100% recall / 0% false positives** on the paired
+  benchmark ([docs/METRICS.md](docs/METRICS.md))
+- **Real production repos** (Mattermost's warehouse, Fivetran packages,
+  dbt's jaffle shop) — [docs/TEST-REPORTS.md](docs/TEST-REPORTS.md)
+- **Spider + BIRD gold queries** — the zero-noise external audit above
+
+## Learn more
+
+- [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) — how it physically works,
+  ELI5 → god level, with real intermediate outputs
+- [docs/FOR-DUMMIES.md](docs/FOR-DUMMIES.md) — every concept from zero
+- [docs/INTEGRATIONS.md](docs/INTEGRATIONS.md) — GitHub Action, pre-commit,
+  MCP, Snowflake UDF / Cortex Agent tool, query-history audit
+- [docs/MCP.md](docs/MCP.md) — MCP server documentation
+- [CONTRIBUTING.md](CONTRIBUTING.md) — adding rules and loaders
+
+Apache-2.0 · [sqlsure.ai](https://sqlsure.ai)

sqlsure-0.1.0/pyproject.toml

@@ -0,0 +1,40 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sqlsure"
+version = "0.1.0"
+description = "AI writes your SQL. sqlsure makes sure it's right — a deterministic semantic inspector that catches fan-out double-counting, summed averages, wrong join keys, and PII exposure before the query runs. Zero false alarms on 2,568 benchmark gold queries."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Tejus Arora", email = "iam.tejusarora@gmail.com" }]
+keywords = ["sql", "semantic-layer", "dbt", "text-to-sql", "linter", "data-quality", "mcp"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Topic :: Database",
+    "Topic :: Software Development :: Quality Assurance",
+]
+dependencies = [
+    "sqlglot>=30.0",
+    "pyyaml>=6.0",
+]
+
+[project.optional-dependencies]
+mcp = ["mcp>=1.0"]
+
+[project.urls]
+Homepage = "https://sqlsure.ai"
+Repository = "https://github.com/sqlsure/sqlsure"
+Documentation = "https://github.com/sqlsure/sqlsure#readme"
+Issues = "https://github.com/sqlsure/sqlsure/issues"
+
+[project.scripts]
+sqlsure = "sqlsure.cli:main"
+
+[tool.setuptools]
+packages = ["sqlsure"]

sqlsure-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sqlsure-0.1.0/sqlsure/__init__.py

@@ -0,0 +1,11 @@
+"""sqlsure — the semantic inspector for SQL.
+
+A semantic constraint checker ("the inspector") that validates SQL against a
+dimensional model — grain, join cardinality, measure additivity, join keys,
+and column policy — before the query runs. Works on human- or AI-generated SQL.
+"""
+from .model import SemanticModel
+from .checker import check, Violation
+
+__version__ = "0.1.0"
+__all__ = ["SemanticModel", "check", "Violation"]