tt-data-store 0.1.0__tar.gz

tt_data_store-0.1.0/LICENSE

@@ -0,0 +1,185 @@
+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.
+
+Copyright 2026 Apurv Salunke

tt_data_store-0.1.0/PKG-INFO

@@ -0,0 +1,244 @@
+Metadata-Version: 2.4
+Name: tt-data-store
+Version: 0.1.0
+Summary: Canonical market data archive library
+Author-email: Apurv Salunke <salunke.apurv7@gmail.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/Tiny-Trader/data-store
+Project-URL: Repository, https://github.com/Tiny-Trader/data-store
+Project-URL: Issues, https://github.com/Tiny-Trader/data-store/issues
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pyarrow
+Requires-Dist: tzdata
+Requires-Dist: boto3
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: moto[s3]; extra == "dev"
+Dynamic: license-file
+
+# data-store
+
+Canonical market data archive library. The only interface through which the filesystem may be modified.
+
+PyPI package: [`tt-data-store`](https://pypi.org/project/tt-data-store/) · GitHub: [`Tiny-Trader/data-store`](https://github.com/Tiny-Trader/data-store)
+
+**Parquet is the source of truth.** `metadata.db` (SQLite) catalogues instruments, files, ingestions, and validation — it is not a substitute for the archive.
+
+## Responsibilities
+
+- Push new data into the FS and maintain metadata
+  - Normalize
+  - Validate
+  - Store
+- Get a slice of data from the FS
+
+Callers own acquisition formats (e.g. CSV). Ingress is `candles.write`.
+
+## Mental model
+
+```text
+Your script / collector
+        ↓
+  store.candles.write(...)
+        ↓
+normalize → validate → merge → atomic Parquet write → update metadata.db
+```
+
+Acquisition (CSV download, API, manual script) is the caller's job. The store only accepts normalized candle data via `candles.write`.
+
+On disk, an archive looks like:
+
+```text
+data/
+├── market/          # Parquet files (human-readable layout)
+├── reference/       # calendars, etc.
+└── metadata.db      # catalogue
+```
+
+Canonical layout and semantics live in [docs/](docs/index.md).
+
+## Install
+
+```bash
+pip install tt-data-store
+# or from source:
+uv pip install -e .
+```
+
+```python
+from tt_data_store import MarketStore
+```
+
+## Opening an archive
+
+```python
+from tt_data_store import MarketStore
+
+store = MarketStore("/path/to/data")
+```
+
+Optional S3 config (or env vars `MARKETSTORE_S3_BUCKET`, `MARKETSTORE_S3_PREFIX`, `MARKETSTORE_S3_REGION`):
+
+```python
+from tt_data_store import MarketStore, RemoteConfig
+
+store = MarketStore(
+    "./data",
+    remote=RemoteConfig(bucket="my-bucket", prefix="archive", region="ap-south-1"),
+)
+```
+
+## Usage
+
+### Register instruments
+
+```python
+# NIFTY index
+spot = store.instruments.create(
+    exchange="NSE",
+    instrument_type="INDEX",
+    symbol="NIFTY",
+)
+# → instrument_key: "NSE:INDEX:NIFTY"
+
+# NIFTY option
+opt = store.instruments.create(
+    exchange="NSE",
+    instrument_type="OPTION",
+    symbol="NIFTY",
+    underlying_id=spot.id,
+    expiry_date="2026-08-27",
+    strike=25000,
+    option_type="CE",
+)
+# → "NSE:OPTION:NIFTY:2026-08-27:25000:CE"
+```
+
+Look up later by key:
+
+```python
+inst = store.instruments.get("NSE:INDEX:NIFTY")
+all_nifty = store.instruments.list(symbol="NIFTY")
+```
+
+### Write candles (main ingress)
+
+Pass a list of dicts or a PyArrow table. Each candle has:
+
+`timestamp`, `open`, `high`, `low`, `close`, `volume` (optional), `open_interest` (optional)
+
+```python
+from datetime import datetime
+from zoneinfo import ZoneInfo
+
+IST = ZoneInfo("Asia/Kolkata")
+
+rows = [
+    {
+        "timestamp": datetime(2026, 8, 11, 9, 15, tzinfo=IST),
+        "open": 100.0,
+        "high": 101.0,
+        "low": 99.0,
+        "close": 100.5,
+        "volume": 10,
+        "open_interest": 100,
+    },
+]
+
+result = store.candles.write(spot, rows, source="upstox")
+```
+
+`write` handles normalization, dedup, merge with existing data, gap detection, atomic file replacement, and ingestion provenance. It returns a `WriteResult` with row counts, gaps, quality status (`VALID` / `PARTIAL` / etc.), and the file path.
+
+Files land in deterministic locations — e.g. spot → `market/nifty/spot/2026.parquet`, options → `market/nifty/options/2026-08-27/25000_CE.parquet`.
+
+### Read candles
+
+```python
+table = store.candles.read(
+    spot,
+    start="2026-08-01",
+    end="2026-08-31",
+)
+```
+
+Returns a PyArrow table, filtered and sorted by timestamp. The store resolves which Parquet files to read.
+
+### Inspect files and quality
+
+```python
+file = store.files.get("market/nifty/spot/2026.parquet")
+
+result = store.validate(spot)          # or store.validate(file.path)
+
+report = store.inspect()
+```
+
+### Sync with S3
+
+Local writes go to disk first; S3 is separate:
+
+```python
+store.remote.push(files=["market/nifty/spot/2026.parquet", "metadata.db"])
+store.remote.pull(files=["market/nifty/options/2026-08-27/25000_CE.parquet"])
+store.remote.sync(files=[...])
+```
+
+## End-to-end producer flow
+
+```python
+store = MarketStore("./data")
+
+# 1. Ensure instrument exists
+inst = store.instruments.get("NSE:INDEX:NIFTY")
+if inst is None:
+    inst = store.instruments.create(
+        exchange="NSE", instrument_type="INDEX", symbol="NIFTY"
+    )
+
+# 2. Fetch from Upstox/NSE/CSV — convert to candle dicts yourself
+candles = parse_my_csv("NIFTY.csv")
+
+# 3. Single write call — store does the rest
+result = store.candles.write(
+    inst,
+    candles,
+    source="upstox",
+    source_instrument_id="NSE_INDEX|Nifty 50",
+    requested_start="2026-08-01",
+    requested_end="2026-08-31",
+)
+
+# 4. Optionally push to S3
+store.remote.push()
+```
+
+## What not to do
+
+- Don't write Parquet files directly
+- Don't run SQL against `metadata.db` in normal workflows
+- Don't parse CSV inside `tt_data_store` — convert to candles first
+- Don't use paths as the primary interface (use instrument keys and date ranges)
+
+## Public API
+
+```python
+store.instruments.get(...) / .list(...) / .create(...)
+store.candles.read(...) / .write(...)
+store.files.get(...) / .list(...)
+store.validate(...)
+store.inspect()
+store.remote.pull(...) / .push(...) / .sync(...)
+```
+
+## Repository layout
+
+```text
+data-store/
+├── docs/
+├── pyproject.toml
+├── src/            # tt_data_store package modules
+└── tests/
+```

tt_data_store-0.1.0/README.md

@@ -0,0 +1,224 @@
+# data-store
+
+Canonical market data archive library. The only interface through which the filesystem may be modified.
+
+PyPI package: [`tt-data-store`](https://pypi.org/project/tt-data-store/) · GitHub: [`Tiny-Trader/data-store`](https://github.com/Tiny-Trader/data-store)
+
+**Parquet is the source of truth.** `metadata.db` (SQLite) catalogues instruments, files, ingestions, and validation — it is not a substitute for the archive.
+
+## Responsibilities
+
+- Push new data into the FS and maintain metadata
+  - Normalize
+  - Validate
+  - Store
+- Get a slice of data from the FS
+
+Callers own acquisition formats (e.g. CSV). Ingress is `candles.write`.
+
+## Mental model
+
+```text
+Your script / collector
+        ↓
+  store.candles.write(...)
+        ↓
+normalize → validate → merge → atomic Parquet write → update metadata.db
+```
+
+Acquisition (CSV download, API, manual script) is the caller's job. The store only accepts normalized candle data via `candles.write`.
+
+On disk, an archive looks like:
+
+```text
+data/
+├── market/          # Parquet files (human-readable layout)
+├── reference/       # calendars, etc.
+└── metadata.db      # catalogue
+```
+
+Canonical layout and semantics live in [docs/](docs/index.md).
+
+## Install
+
+```bash
+pip install tt-data-store
+# or from source:
+uv pip install -e .
+```
+
+```python
+from tt_data_store import MarketStore
+```
+
+## Opening an archive
+
+```python
+from tt_data_store import MarketStore
+
+store = MarketStore("/path/to/data")
+```
+
+Optional S3 config (or env vars `MARKETSTORE_S3_BUCKET`, `MARKETSTORE_S3_PREFIX`, `MARKETSTORE_S3_REGION`):
+
+```python
+from tt_data_store import MarketStore, RemoteConfig
+
+store = MarketStore(
+    "./data",
+    remote=RemoteConfig(bucket="my-bucket", prefix="archive", region="ap-south-1"),
+)
+```
+
+## Usage
+
+### Register instruments
+
+```python
+# NIFTY index
+spot = store.instruments.create(
+    exchange="NSE",
+    instrument_type="INDEX",
+    symbol="NIFTY",
+)
+# → instrument_key: "NSE:INDEX:NIFTY"
+
+# NIFTY option
+opt = store.instruments.create(
+    exchange="NSE",
+    instrument_type="OPTION",
+    symbol="NIFTY",
+    underlying_id=spot.id,
+    expiry_date="2026-08-27",
+    strike=25000,
+    option_type="CE",
+)
+# → "NSE:OPTION:NIFTY:2026-08-27:25000:CE"
+```
+
+Look up later by key:
+
+```python
+inst = store.instruments.get("NSE:INDEX:NIFTY")
+all_nifty = store.instruments.list(symbol="NIFTY")
+```
+
+### Write candles (main ingress)
+
+Pass a list of dicts or a PyArrow table. Each candle has:
+
+`timestamp`, `open`, `high`, `low`, `close`, `volume` (optional), `open_interest` (optional)
+
+```python
+from datetime import datetime
+from zoneinfo import ZoneInfo
+
+IST = ZoneInfo("Asia/Kolkata")
+
+rows = [
+    {
+        "timestamp": datetime(2026, 8, 11, 9, 15, tzinfo=IST),
+        "open": 100.0,
+        "high": 101.0,
+        "low": 99.0,
+        "close": 100.5,
+        "volume": 10,
+        "open_interest": 100,
+    },
+]
+
+result = store.candles.write(spot, rows, source="upstox")
+```
+
+`write` handles normalization, dedup, merge with existing data, gap detection, atomic file replacement, and ingestion provenance. It returns a `WriteResult` with row counts, gaps, quality status (`VALID` / `PARTIAL` / etc.), and the file path.
+
+Files land in deterministic locations — e.g. spot → `market/nifty/spot/2026.parquet`, options → `market/nifty/options/2026-08-27/25000_CE.parquet`.
+
+### Read candles
+
+```python
+table = store.candles.read(
+    spot,
+    start="2026-08-01",
+    end="2026-08-31",
+)
+```
+
+Returns a PyArrow table, filtered and sorted by timestamp. The store resolves which Parquet files to read.
+
+### Inspect files and quality
+
+```python
+file = store.files.get("market/nifty/spot/2026.parquet")
+
+result = store.validate(spot)          # or store.validate(file.path)
+
+report = store.inspect()
+```
+
+### Sync with S3
+
+Local writes go to disk first; S3 is separate:
+
+```python
+store.remote.push(files=["market/nifty/spot/2026.parquet", "metadata.db"])
+store.remote.pull(files=["market/nifty/options/2026-08-27/25000_CE.parquet"])
+store.remote.sync(files=[...])
+```
+
+## End-to-end producer flow
+
+```python
+store = MarketStore("./data")
+
+# 1. Ensure instrument exists
+inst = store.instruments.get("NSE:INDEX:NIFTY")
+if inst is None:
+    inst = store.instruments.create(
+        exchange="NSE", instrument_type="INDEX", symbol="NIFTY"
+    )
+
+# 2. Fetch from Upstox/NSE/CSV — convert to candle dicts yourself
+candles = parse_my_csv("NIFTY.csv")
+
+# 3. Single write call — store does the rest
+result = store.candles.write(
+    inst,
+    candles,
+    source="upstox",
+    source_instrument_id="NSE_INDEX|Nifty 50",
+    requested_start="2026-08-01",
+    requested_end="2026-08-31",
+)
+
+# 4. Optionally push to S3
+store.remote.push()
+```
+
+## What not to do
+
+- Don't write Parquet files directly
+- Don't run SQL against `metadata.db` in normal workflows
+- Don't parse CSV inside `tt_data_store` — convert to candles first
+- Don't use paths as the primary interface (use instrument keys and date ranges)
+
+## Public API
+
+```python
+store.instruments.get(...) / .list(...) / .create(...)
+store.candles.read(...) / .write(...)
+store.files.get(...) / .list(...)
+store.validate(...)
+store.inspect()
+store.remote.pull(...) / .push(...) / .sync(...)
+```
+
+## Repository layout
+
+```text
+data-store/
+├── docs/
+├── pyproject.toml
+├── src/            # tt_data_store package modules
+└── tests/
+```

tt_data_store-0.1.0/pyproject.toml

@@ -0,0 +1,37 @@
+[project]
+name = "tt-data-store"
+version = "0.1.0"
+description = "Canonical market data archive library"
+readme = "README.md"
+requires-python = ">=3.11"
+license = "Apache-2.0"
+authors = [{ name = "Apurv Salunke", email = "salunke.apurv7@gmail.com" }]
+dependencies = [
+    "pyarrow",
+    "tzdata",
+    "boto3",
+]
+
+[project.urls]
+Homepage = "https://github.com/Tiny-Trader/data-store"
+Repository = "https://github.com/Tiny-Trader/data-store"
+Issues = "https://github.com/Tiny-Trader/data-store/issues"
+
+[project.optional-dependencies]
+dev = ["pytest", "moto[s3]"]
+
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.package-dir]
+tt_data_store = "src"
+
+[tool.setuptools]
+packages = ["tt_data_store"]
+
+[tool.setuptools.package-data]
+tt_data_store = ["schema.sql"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

tt_data_store-0.1.0/setup.cfg

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