opteryx-catalog 0.4.25__tar.gz

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.
Files changed (50) hide show
  1. opteryx_catalog-0.4.25/LICENSE +201 -0
  2. opteryx_catalog-0.4.25/PKG-INFO +461 -0
  3. opteryx_catalog-0.4.25/README.md +231 -0
  4. opteryx_catalog-0.4.25/opteryx_catalog/__init__.py +31 -0
  5. opteryx_catalog-0.4.25/opteryx_catalog/catalog/__init__.py +4 -0
  6. opteryx_catalog-0.4.25/opteryx_catalog/catalog/compaction.py +529 -0
  7. opteryx_catalog-0.4.25/opteryx_catalog/catalog/dataset.py +1544 -0
  8. opteryx_catalog-0.4.25/opteryx_catalog/catalog/manifest.py +337 -0
  9. opteryx_catalog-0.4.25/opteryx_catalog/catalog/metadata.py +84 -0
  10. opteryx_catalog-0.4.25/opteryx_catalog/catalog/metastore.py +68 -0
  11. opteryx_catalog-0.4.25/opteryx_catalog/catalog/view.py +12 -0
  12. opteryx_catalog-0.4.25/opteryx_catalog/exceptions.py +38 -0
  13. opteryx_catalog-0.4.25/opteryx_catalog/iops/__init__.py +6 -0
  14. opteryx_catalog-0.4.25/opteryx_catalog/iops/base.py +42 -0
  15. opteryx_catalog-0.4.25/opteryx_catalog/iops/fileio.py +125 -0
  16. opteryx_catalog-0.4.25/opteryx_catalog/iops/gcs.py +255 -0
  17. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/__init__.py +8 -0
  18. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/distogram.py +558 -0
  19. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/tests/_test_histogram.py +52 -0
  20. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/tests/test_bounds.py +24 -0
  21. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/tests/test_count.py +19 -0
  22. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/tests/test_count_at.py +89 -0
  23. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/tests/test_quantile.py +81 -0
  24. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/tests/test_stats.py +25 -0
  25. opteryx_catalog-0.4.25/opteryx_catalog/maki_nage/tests/test_update.py +44 -0
  26. opteryx_catalog-0.4.25/opteryx_catalog/opteryx_catalog.py +975 -0
  27. opteryx_catalog-0.4.25/opteryx_catalog/webhooks/__init__.py +230 -0
  28. opteryx_catalog-0.4.25/opteryx_catalog/webhooks/events.py +177 -0
  29. opteryx_catalog-0.4.25/opteryx_catalog.egg-info/PKG-INFO +461 -0
  30. opteryx_catalog-0.4.25/opteryx_catalog.egg-info/SOURCES.txt +88 -0
  31. opteryx_catalog-0.4.25/opteryx_catalog.egg-info/dependency_links.txt +1 -0
  32. opteryx_catalog-0.4.25/opteryx_catalog.egg-info/requires.txt +9 -0
  33. opteryx_catalog-0.4.25/opteryx_catalog.egg-info/top_level.txt +4 -0
  34. opteryx_catalog-0.4.25/pyproject.toml +65 -0
  35. opteryx_catalog-0.4.25/scripts/collect_byte_counts.py +42 -0
  36. opteryx_catalog-0.4.25/scripts/create_dataset.py +201 -0
  37. opteryx_catalog-0.4.25/scripts/emit_full_single_file.py +84 -0
  38. opteryx_catalog-0.4.25/scripts/inspect_manifest_dryrun.py +320 -0
  39. opteryx_catalog-0.4.25/scripts/inspect_single_file.py +150 -0
  40. opteryx_catalog-0.4.25/scripts/inspect_single_file_gcs.py +125 -0
  41. opteryx_catalog-0.4.25/scripts/read_dataset.py +268 -0
  42. opteryx_catalog-0.4.25/setup.cfg +4 -0
  43. opteryx_catalog-0.4.25/tests/test_collections.py +37 -0
  44. opteryx_catalog-0.4.25/tests/test_compaction.py +233 -0
  45. opteryx_catalog-0.4.25/tests/test_dataset_metadata.py +29 -0
  46. opteryx_catalog-0.4.25/tests/test_describe_uncompressed.py +127 -0
  47. opteryx_catalog-0.4.25/tests/test_import.py +5 -0
  48. opteryx_catalog-0.4.25/tests/test_pyproject.py +8 -0
  49. opteryx_catalog-0.4.25/tests/test_refresh_manifest.py +213 -0
  50. opteryx_catalog-0.4.25/tests/test_webhooks.py +177 -0
@@ -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 2025 Justin Joyce (@joocer)
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.
@@ -0,0 +1,461 @@
1
+ Metadata-Version: 2.4
2
+ Name: opteryx-catalog
3
+ Version: 0.4.25
4
+ Summary: Opteryx Cloud Catalog
5
+ Author-email: joocer <justin.joyce@joocer.com>
6
+ License: Apache License
7
+ Version 2.0, January 2004
8
+ http://www.apache.org/licenses/
9
+
10
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
11
+
12
+ 1. Definitions.
13
+
14
+ "License" shall mean the terms and conditions for use, reproduction,
15
+ and distribution as defined by Sections 1 through 9 of this document.
16
+
17
+ "Licensor" shall mean the copyright owner or entity authorized by
18
+ the copyright owner that is granting the License.
19
+
20
+ "Legal Entity" shall mean the union of the acting entity and all
21
+ other entities that control, are controlled by, or are under common
22
+ control with that entity. For the purposes of this definition,
23
+ "control" means (i) the power, direct or indirect, to cause the
24
+ direction or management of such entity, whether by contract or
25
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
26
+ outstanding shares, or (iii) beneficial ownership of such entity.
27
+
28
+ "You" (or "Your") shall mean an individual or Legal Entity
29
+ exercising permissions granted by this License.
30
+
31
+ "Source" form shall mean the preferred form for making modifications,
32
+ including but not limited to software source code, documentation
33
+ source, and configuration files.
34
+
35
+ "Object" form shall mean any form resulting from mechanical
36
+ transformation or translation of a Source form, including but
37
+ not limited to compiled object code, generated documentation,
38
+ and conversions to other media types.
39
+
40
+ "Work" shall mean the work of authorship, whether in Source or
41
+ Object form, made available under the License, as indicated by a
42
+ copyright notice that is included in or attached to the work
43
+ (an example is provided in the Appendix below).
44
+
45
+ "Derivative Works" shall mean any work, whether in Source or Object
46
+ form, that is based on (or derived from) the Work and for which the
47
+ editorial revisions, annotations, elaborations, or other modifications
48
+ represent, as a whole, an original work of authorship. For the purposes
49
+ of this License, Derivative Works shall not include works that remain
50
+ separable from, or merely link (or bind by name) to the interfaces of,
51
+ the Work and Derivative Works thereof.
52
+
53
+ "Contribution" shall mean any work of authorship, including
54
+ the original version of the Work and any modifications or additions
55
+ to that Work or Derivative Works thereof, that is intentionally
56
+ submitted to Licensor for inclusion in the Work by the copyright owner
57
+ or by an individual or Legal Entity authorized to submit on behalf of
58
+ the copyright owner. For the purposes of this definition, "submitted"
59
+ means any form of electronic, verbal, or written communication sent
60
+ to the Licensor or its representatives, including but not limited to
61
+ communication on electronic mailing lists, source code control systems,
62
+ and issue tracking systems that are managed by, or on behalf of, the
63
+ Licensor for the purpose of discussing and improving the Work, but
64
+ excluding communication that is conspicuously marked or otherwise
65
+ designated in writing by the copyright owner as "Not a Contribution."
66
+
67
+ "Contributor" shall mean Licensor and any individual or Legal Entity
68
+ on behalf of whom a Contribution has been received by Licensor and
69
+ subsequently incorporated within the Work.
70
+
71
+ 2. Grant of Copyright License. Subject to the terms and conditions of
72
+ this License, each Contributor hereby grants to You a perpetual,
73
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
74
+ copyright license to reproduce, prepare Derivative Works of,
75
+ publicly display, publicly perform, sublicense, and distribute the
76
+ Work and such Derivative Works in Source or Object form.
77
+
78
+ 3. Grant of Patent License. Subject to the terms and conditions of
79
+ this License, each Contributor hereby grants to You a perpetual,
80
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
81
+ (except as stated in this section) patent license to make, have made,
82
+ use, offer to sell, sell, import, and otherwise transfer the Work,
83
+ where such license applies only to those patent claims licensable
84
+ by such Contributor that are necessarily infringed by their
85
+ Contribution(s) alone or by combination of their Contribution(s)
86
+ with the Work to which such Contribution(s) was submitted. If You
87
+ institute patent litigation against any entity (including a
88
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
89
+ or a Contribution incorporated within the Work constitutes direct
90
+ or contributory patent infringement, then any patent licenses
91
+ granted to You under this License for that Work shall terminate
92
+ as of the date such litigation is filed.
93
+
94
+ 4. Redistribution. You may reproduce and distribute copies of the
95
+ Work or Derivative Works thereof in any medium, with or without
96
+ modifications, and in Source or Object form, provided that You
97
+ meet the following conditions:
98
+
99
+ (a) You must give any other recipients of the Work or
100
+ Derivative Works a copy of this License; and
101
+
102
+ (b) You must cause any modified files to carry prominent notices
103
+ stating that You changed the files; and
104
+
105
+ (c) You must retain, in the Source form of any Derivative Works
106
+ that You distribute, all copyright, patent, trademark, and
107
+ attribution notices from the Source form of the Work,
108
+ excluding those notices that do not pertain to any part of
109
+ the Derivative Works; and
110
+
111
+ (d) If the Work includes a "NOTICE" text file as part of its
112
+ distribution, then any Derivative Works that You distribute must
113
+ include a readable copy of the attribution notices contained
114
+ within such NOTICE file, excluding those notices that do not
115
+ pertain to any part of the Derivative Works, in at least one
116
+ of the following places: within a NOTICE text file distributed
117
+ as part of the Derivative Works; within the Source form or
118
+ documentation, if provided along with the Derivative Works; or,
119
+ within a display generated by the Derivative Works, if and
120
+ wherever such third-party notices normally appear. The contents
121
+ of the NOTICE file are for informational purposes only and
122
+ do not modify the License. You may add Your own attribution
123
+ notices within Derivative Works that You distribute, alongside
124
+ or as an addendum to the NOTICE text from the Work, provided
125
+ that such additional attribution notices cannot be construed
126
+ as modifying the License.
127
+
128
+ You may add Your own copyright statement to Your modifications and
129
+ may provide additional or different license terms and conditions
130
+ for use, reproduction, or distribution of Your modifications, or
131
+ for any such Derivative Works as a whole, provided Your use,
132
+ reproduction, and distribution of the Work otherwise complies with
133
+ the conditions stated in this License.
134
+
135
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
136
+ any Contribution intentionally submitted for inclusion in the Work
137
+ by You to the Licensor shall be under the terms and conditions of
138
+ this License, without any additional terms or conditions.
139
+ Notwithstanding the above, nothing herein shall supersede or modify
140
+ the terms of any separate license agreement you may have executed
141
+ with Licensor regarding such Contributions.
142
+
143
+ 6. Trademarks. This License does not grant permission to use the trade
144
+ names, trademarks, service marks, or product names of the Licensor,
145
+ except as required for reasonable and customary use in describing the
146
+ origin of the Work and reproducing the content of the NOTICE file.
147
+
148
+ 7. Disclaimer of Warranty. Unless required by applicable law or
149
+ agreed to in writing, Licensor provides the Work (and each
150
+ Contributor provides its Contributions) on an "AS IS" BASIS,
151
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
152
+ implied, including, without limitation, any warranties or conditions
153
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
154
+ PARTICULAR PURPOSE. You are solely responsible for determining the
155
+ appropriateness of using or redistributing the Work and assume any
156
+ risks associated with Your exercise of permissions under this License.
157
+
158
+ 8. Limitation of Liability. In no event and under no legal theory,
159
+ whether in tort (including negligence), contract, or otherwise,
160
+ unless required by applicable law (such as deliberate and grossly
161
+ negligent acts) or agreed to in writing, shall any Contributor be
162
+ liable to You for damages, including any direct, indirect, special,
163
+ incidental, or consequential damages of any character arising as a
164
+ result of this License or out of the use or inability to use the
165
+ Work (including but not limited to damages for loss of goodwill,
166
+ work stoppage, computer failure or malfunction, or any and all
167
+ other commercial damages or losses), even if such Contributor
168
+ has been advised of the possibility of such damages.
169
+
170
+ 9. Accepting Warranty or Additional Liability. While redistributing
171
+ the Work or Derivative Works thereof, You may choose to offer,
172
+ and charge a fee for, acceptance of support, warranty, indemnity,
173
+ or other liability obligations and/or rights consistent with this
174
+ License. However, in accepting such obligations, You may act only
175
+ on Your own behalf and on Your sole responsibility, not on behalf
176
+ of any other Contributor, and only if You agree to indemnify,
177
+ defend, and hold each Contributor harmless for any liability
178
+ incurred by, or claims asserted against, such Contributor by reason
179
+ of your accepting any such warranty or additional liability.
180
+
181
+ END OF TERMS AND CONDITIONS
182
+
183
+ APPENDIX: How to apply the Apache License to your work.
184
+
185
+ To apply the Apache License to your work, attach the following
186
+ boilerplate notice, with the fields enclosed by brackets "[]"
187
+ replaced with your own identifying information. (Don't include
188
+ the brackets!) The text should be enclosed in the appropriate
189
+ comment syntax for the file format. We also recommend that a
190
+ file or class name and description of purpose be included on the
191
+ same "printed page" as the copyright notice for easier
192
+ identification within third-party archives.
193
+
194
+ Copyright 2025 Justin Joyce (@joocer)
195
+
196
+ Licensed under the Apache License, Version 2.0 (the "License");
197
+ you may not use this file except in compliance with the License.
198
+ You may obtain a copy of the License at
199
+
200
+ http://www.apache.org/licenses/LICENSE-2.0
201
+
202
+ Unless required by applicable law or agreed to in writing, software
203
+ distributed under the License is distributed on an "AS IS" BASIS,
204
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
205
+ See the License for the specific language governing permissions and
206
+ limitations under the License.
207
+ Project-URL: Homepage, https://github.com/mabel-dev/opteryx-catalog
208
+ Keywords: opteryx,catalog,firestore,gcs
209
+ Classifier: Development Status :: 4 - Beta
210
+ Classifier: Intended Audience :: Developers
211
+ Classifier: License :: OSI Approved :: MIT License
212
+ Classifier: Programming Language :: Python :: 3
213
+ Classifier: Programming Language :: Python :: 3 :: Only
214
+ Classifier: Programming Language :: Python :: 3.11
215
+ Classifier: Programming Language :: Python :: 3.12
216
+ Classifier: Programming Language :: Python :: 3.13
217
+ Classifier: Operating System :: OS Independent
218
+ Requires-Python: >=3.9
219
+ Description-Content-Type: text/markdown
220
+ License-File: LICENSE
221
+ Requires-Dist: google-cloud-firestore==2.23.0
222
+ Requires-Dist: google-cloud-storage==3.8.0
223
+ Requires-Dist: orso==0.0.226
224
+ Requires-Dist: opteryx-core
225
+ Requires-Dist: pyarrow==23.0.0
226
+ Requires-Dist: requests==2.32.5
227
+ Provides-Extra: webhooks
228
+ Requires-Dist: google-cloud-tasks>=2.16.0; extra == "webhooks"
229
+ Dynamic: license-file
230
+
231
+ # pyiceberg-firestore-gcs
232
+
233
+ A Firestore + Google Cloud Storage (GCS) backed implementation of a
234
+ lightweight catalog interface. This package provides an opinionated
235
+ catalog implementation for storing table metadata documents in Firestore and
236
+ consolidated Parquet manifests in GCS.
237
+
238
+ **Important:** This library is *modelled after* Apache Iceberg but is **not
239
+ compatible** with Iceberg; it is a separate implementation with different
240
+ storage conventions and metadata layout. This library is the catalog and
241
+ metastore used by [opteryx.app](https://opteryx.app/) and uses **Firestore** as the primary
242
+ metastore and **GCS** for data and manifest storage.
243
+
244
+ ---
245
+
246
+ ## Features โœ…
247
+
248
+ - Firestore-backed catalog and collection storage
249
+ - GCS-based table metadata storage; export/import utilities available for artifact conversion
250
+ - Table creation, registration, listing, loading, renaming, and deletion
251
+ - Commit operations that write updated metadata to GCS and persist references in Firestore
252
+ - Simple, opinionated defaults (e.g., default GCS location derived from catalog properties)
253
+ - Lightweight schema handling (supports pyarrow schemas)
254
+
255
+ ## Quick start ๐Ÿ’ก
256
+
257
+ 1. Ensure you have GCP credentials available to the environment. Typical approaches:
258
+ - Set `GOOGLE_APPLICATION_CREDENTIALS` to a service account JSON key file, or
259
+ - Use `gcloud auth application-default login` for local development.
260
+
261
+ 2. Install locally (or publish to your package repo):
262
+
263
+ ```bash
264
+ python -m pip install -e .
265
+ ```
266
+
267
+ 3. Create a `FirestoreCatalog` and use it in your application:
268
+
269
+ ```python
270
+ from pyiceberg_firestore_gcs import create_catalog
271
+ from pyiceberg.schema import Schema, NestedField
272
+ from pyiceberg.types import IntegerType, StringType
273
+
274
+ catalog = create_catalog(
275
+ "my_catalog",
276
+ firestore_project="my-gcp-project",
277
+ gcs_bucket="my-default-bucket",
278
+ )
279
+
280
+ # Create a collection
281
+ catalog.create_collection("example_collection")
282
+
283
+ # Create a simple PyIceberg schema
284
+ schema = Schema(
285
+ NestedField(field_id=1, name="id", field_type=IntegerType(), required=True),
286
+ NestedField(field_id=2, name="name", field_type=StringType(), required=False),
287
+ )
288
+
289
+ # Create a new dataset (metadata written to a GCS path derived from the bucket property)
290
+ table = catalog.create_dataset(("example_collection", "users"), schema)
291
+
292
+ # Or register a table if you already have a metadata JSON in GCS
293
+ catalog.register_table(("example_namespace", "events"), "gs://my-bucket/path/to/events/metadata/00000001.json")
294
+
295
+ # Load a table
296
+ tbl = catalog.load_dataset(("example_namespace", "users"))
297
+ print(tbl.metadata)
298
+ ```
299
+
300
+ ## Configuration and environment ๐Ÿ”ง
301
+
302
+ - GCP authentication: Use `GOOGLE_APPLICATION_CREDENTIALS` or Application Default Credentials
303
+ - `firestore_project` and `firestore_database` can be supplied when creating the catalog
304
+ - `gcs_bucket` is recommended to allow `create_dataset` to write metadata automatically; otherwise pass `location` explicitly to `create_dataset`
305
+ - The catalog writes consolidated Parquet manifests and does not write manifest-list artifacts in the hot path. Use the provided export/import utilities for artifact conversion when necessary.
306
+
307
+ Example environment variables:
308
+
309
+ ```bash
310
+ export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
311
+ export GOOGLE_CLOUD_PROJECT="my-gcp-project"
312
+ ```
313
+
314
+ ### Manifest format
315
+
316
+ This catalog writes consolidated Parquet manifests for fast query planning and stores table metadata in Firestore. Manifests and data files are stored in GCS. If you need different artifact formats, use the provided export/import utilities to convert manifests outside the hot path.
317
+
318
+ ## API overview ๐Ÿ“š
319
+
320
+ The package exports a factory helper `create_catalog` and the `FirestoreCatalog` class.
321
+
322
+ Key methods include:
323
+ - `create_collection(collection, properties={}, exists_ok=False)`
324
+ - `drop_namespace(namespace)`
325
+ - `list_namespaces()`
326
+ - `create_dataset(identifier, schema, location=None, partition_spec=None, sort_order=None, properties={})`
327
+ - `register_table(identifier, metadata_location)`
328
+ - `load_dataset(identifier)`
329
+ - `list_datasets(namespace)`
330
+ - `drop_dataset(identifier)`
331
+ - `rename_table(from_identifier, to_identifier)`
332
+ - `commit_table(table, requirements, updates)`
333
+ - `create_view(identifier, sql, schema=None, author=None, description=None, properties={})`
334
+ - `load_view(identifier)`
335
+ - `list_views(namespace)`
336
+ - `view_exists(identifier)`
337
+ - `drop_view(identifier)`
338
+ - `update_view_execution_metadata(identifier, row_count=None, execution_time=None)`
339
+
340
+ ### Views ๐Ÿ‘๏ธ
341
+
342
+ Views are SQL queries stored in the catalog that can be referenced like tables. Each view includes:
343
+ - **SQL statement**: The query that defines the view
344
+ - **Schema**: The expected result schema (optional but recommended)
345
+ - **Metadata**: Author, description, creation/update timestamps
346
+ - **Execution history**: Last run time, row count, execution time
347
+
348
+ Example usage:
349
+ ```python
350
+ from pyiceberg.schema import Schema, NestedField
351
+ from pyiceberg.types import IntegerType, StringType
352
+
353
+ # Create a schema for the view
354
+ schema = Schema(
355
+ NestedField(field_id=1, name="user_id", field_type=IntegerType(), required=True),
356
+ NestedField(field_id=2, name="username", field_type=StringType(), required=False),
357
+ )
358
+
359
+ # Create a view
360
+ view = catalog.create_view(
361
+ identifier=("my_namespace", "active_users"),
362
+ sql="SELECT user_id, username FROM users WHERE active = true",
363
+ schema=schema,
364
+ author="data_team",
365
+ description="View of all active users in the system"
366
+ )
367
+
368
+ # Load a view
369
+ view = catalog.load_view(("my_namespace", "active_users"))
370
+ print(f"SQL: {view.sql}")
371
+ print(f"Schema: {view.metadata.schema}")
372
+
373
+ # Update execution metadata after running the view
374
+ catalog.update_view_execution_metadata(
375
+ ("my_namespace", "active_users"),
376
+ row_count=1250,
377
+ execution_time=0.45
378
+ )
379
+ ```
380
+
381
+ Notes about behavior:
382
+ - `create_dataset` will try to infer a default GCS location using the provided `gcs_bucket` property if `location` is omitted.
383
+ - `register_table` validates that the provided `metadata_location` points to an existing GCS blob.
384
+ - Views are stored as Firestore documents with complete metadata including SQL, schema, authorship, and execution history.
385
+ - Table transactions are intentionally unimplemented.
386
+
387
+ ## Development & Linting ๐Ÿงช
388
+
389
+ This package includes a small `Makefile` target to run linting and formatting tools (`ruff`, `isort`, `pycln`).
390
+
391
+ Install dev tools and run linters with:
392
+
393
+ ```bash
394
+ python -m pip install --upgrade pycln isort ruff
395
+ make lint
396
+ ```
397
+
398
+ Running tests (if you add tests):
399
+
400
+ ```bash
401
+ python -m pytest
402
+ ```
403
+
404
+ ## Compaction ๐Ÿ”ง
405
+
406
+ This catalog supports small file compaction to improve query performance. See [COMPACTION.md](COMPACTION.md) for detailed design documentation.
407
+
408
+ ### Quick Start
409
+
410
+ ```python
411
+ from pyiceberg_firestore_gcs import create_catalog
412
+ from pyiceberg_firestore_gcs.compaction import compact_table, get_compaction_stats
413
+
414
+ catalog = create_catalog(...)
415
+
416
+ # Check if compaction is needed
417
+ table = catalog.load_dataset(("namespace", "dataset_name"))
418
+ stats = get_compaction_stats(table)
419
+ print(f"Small files: {stats['small_file_count']}")
420
+
421
+ # Run compaction
422
+ result = compact_table(catalog, ("namespace", "table_name"))
423
+ print(f"Compacted {result.files_rewritten} files")
424
+ ```
425
+
426
+ ### Configuration
427
+
428
+ Control compaction behavior via table properties:
429
+
430
+ ```python
431
+ table = catalog.create_dataset(
432
+ identifier=("namespace", "table_name"),
433
+ schema=schema,
434
+ properties={
435
+ "compaction.enabled": "true",
436
+ "compaction.min-file-count": "10",
437
+ "compaction.max-small-file-size-bytes": "33554432", # 32 MB
438
+ "write.target-file-size-bytes": "134217728" # 128 MB
439
+ }
440
+ )
441
+ ```
442
+
443
+ ## Limitations & KNOWN ISSUES โš ๏ธ
444
+
445
+ - No support for dataset-level transactions. `create_dataset_transaction` raises `NotImplementedError`.
446
+ - The catalog stores metadata location references in Firestore; purging metadata files from GCS is not implemented.
447
+ - This is an opinionated implementation intended for internal or controlled environments. Review for production constraints before use in multi-tenant environments.
448
+
449
+ ## Contributing ๐Ÿค
450
+
451
+ Contributions are welcome. Please follow these steps:
452
+
453
+ 1. Fork the repository and create a feature branch.
454
+ 2. Run and pass linting and tests locally.
455
+ 3. Submit a PR with a clear description of the change.
456
+
457
+ Please add unit tests and docs for new behaviors.
458
+
459
+ ---
460
+
461
+ If you'd like, I can also add usage examples that show inserting rows using PyIceberg readers/writers, or add CI testing steps to the repository. โœ