swisstip-builder 0.1.0__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 (118) hide show
  1. swisstip_builder-0.1.0/LICENSE +202 -0
  2. swisstip_builder-0.1.0/NOTICE +17 -0
  3. swisstip_builder-0.1.0/PKG-INFO +81 -0
  4. swisstip_builder-0.1.0/README.md +44 -0
  5. swisstip_builder-0.1.0/pyproject.toml +88 -0
  6. swisstip_builder-0.1.0/setup.cfg +4 -0
  7. swisstip_builder-0.1.0/src/swisstip/admin_console/__init__.py +11 -0
  8. swisstip_builder-0.1.0/src/swisstip/admin_console/app.py +218 -0
  9. swisstip_builder-0.1.0/src/swisstip/admin_console/calls.py +115 -0
  10. swisstip_builder-0.1.0/src/swisstip/admin_console/checks.py +188 -0
  11. swisstip_builder-0.1.0/src/swisstip/admin_console/data.py +408 -0
  12. swisstip_builder-0.1.0/src/swisstip/admin_console/jobs.py +211 -0
  13. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/__init__.py +5 -0
  14. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/documents.py +206 -0
  15. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/operations.py +97 -0
  16. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/packs.py +75 -0
  17. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/release.py +159 -0
  18. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/review.py +356 -0
  19. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/runs.py +163 -0
  20. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/sandbox.py +166 -0
  21. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/sources.py +239 -0
  22. swisstip_builder-0.1.0/src/swisstip/admin_console/screens/workbench.py +479 -0
  23. swisstip_builder-0.1.0/src/swisstip/admin_console/static/console.css +124 -0
  24. swisstip_builder-0.1.0/src/swisstip/admin_console/static/console.js +149 -0
  25. swisstip_builder-0.1.0/src/swisstip/admin_console/static/htmx.min.js +2 -0
  26. swisstip_builder-0.1.0/src/swisstip/admin_console/views/base.html +40 -0
  27. swisstip_builder-0.1.0/src/swisstip/admin_console/views/conflict.html +11 -0
  28. swisstip_builder-0.1.0/src/swisstip/admin_console/views/documents/diff.html +57 -0
  29. swisstip_builder-0.1.0/src/swisstip/admin_console/views/documents/excerpt.html +2 -0
  30. swisstip_builder-0.1.0/src/swisstip/admin_console/views/documents/excerpt_body.html +38 -0
  31. swisstip_builder-0.1.0/src/swisstip/admin_console/views/documents/index.html +115 -0
  32. swisstip_builder-0.1.0/src/swisstip/admin_console/views/documents/reading.html +111 -0
  33. swisstip_builder-0.1.0/src/swisstip/admin_console/views/fragment.html +2 -0
  34. swisstip_builder-0.1.0/src/swisstip/admin_console/views/macros.html +44 -0
  35. swisstip_builder-0.1.0/src/swisstip/admin_console/views/operations/index.html +131 -0
  36. swisstip_builder-0.1.0/src/swisstip/admin_console/views/packs/audit.html +28 -0
  37. swisstip_builder-0.1.0/src/swisstip/admin_console/views/packs/index.html +110 -0
  38. swisstip_builder-0.1.0/src/swisstip/admin_console/views/refused.html +16 -0
  39. swisstip_builder-0.1.0/src/swisstip/admin_console/views/release/index.html +131 -0
  40. swisstip_builder-0.1.0/src/swisstip/admin_console/views/review/index.html +229 -0
  41. swisstip_builder-0.1.0/src/swisstip/admin_console/views/runs/index.html +123 -0
  42. swisstip_builder-0.1.0/src/swisstip/admin_console/views/runs/job.html +15 -0
  43. swisstip_builder-0.1.0/src/swisstip/admin_console/views/runs/preview.html +7 -0
  44. swisstip_builder-0.1.0/src/swisstip/admin_console/views/runs/relocation.html +113 -0
  45. swisstip_builder-0.1.0/src/swisstip/admin_console/views/sandbox/checks.html +22 -0
  46. swisstip_builder-0.1.0/src/swisstip/admin_console/views/sandbox/index.html +144 -0
  47. swisstip_builder-0.1.0/src/swisstip/admin_console/views/sandbox/result.html +118 -0
  48. swisstip_builder-0.1.0/src/swisstip/admin_console/views/sources/form.html +83 -0
  49. swisstip_builder-0.1.0/src/swisstip/admin_console/views/sources/index.html +138 -0
  50. swisstip_builder-0.1.0/src/swisstip/admin_console/views/workbench/concept.html +90 -0
  51. swisstip_builder-0.1.0/src/swisstip/admin_console/views/workbench/fact.html +112 -0
  52. swisstip_builder-0.1.0/src/swisstip/admin_console/views/workbench/index.html +64 -0
  53. swisstip_builder-0.1.0/src/swisstip/admin_console/views/workbench/pack.html +44 -0
  54. swisstip_builder-0.1.0/src/swisstip/admin_console/views/workbench/topic.html +16 -0
  55. swisstip_builder-0.1.0/src/swisstip/admin_console/writes.py +202 -0
  56. swisstip_builder-0.1.0/src/swisstip/build/__init__.py +6 -0
  57. swisstip_builder-0.1.0/src/swisstip/build/acceptance.py +29 -0
  58. swisstip_builder-0.1.0/src/swisstip/build/build_cli.py +48 -0
  59. swisstip_builder-0.1.0/src/swisstip/build/curation.py +111 -0
  60. swisstip_builder-0.1.0/src/swisstip/build/release_build.py +213 -0
  61. swisstip_builder-0.1.0/src/swisstip/build/source_terms.py +71 -0
  62. swisstip_builder-0.1.0/src/swisstip/builder/__init__.py +8 -0
  63. swisstip_builder-0.1.0/src/swisstip/builder/cli.py +60 -0
  64. swisstip_builder-0.1.0/src/swisstip/builder/pipeline.py +354 -0
  65. swisstip_builder-0.1.0/src/swisstip/concepts/__init__.py +6 -0
  66. swisstip_builder-0.1.0/src/swisstip/concepts/budget.py +141 -0
  67. swisstip_builder-0.1.0/src/swisstip/concepts/checkpoints.py +201 -0
  68. swisstip_builder-0.1.0/src/swisstip/concepts/chunks.py +115 -0
  69. swisstip_builder-0.1.0/src/swisstip/concepts/concepts_cli.py +292 -0
  70. swisstip_builder-0.1.0/src/swisstip/concepts/extract.py +287 -0
  71. swisstip_builder-0.1.0/src/swisstip/concepts/legacy.py +173 -0
  72. swisstip_builder-0.1.0/src/swisstip/concepts/package.py +269 -0
  73. swisstip_builder-0.1.0/src/swisstip/concepts/package_cli.py +65 -0
  74. swisstip_builder-0.1.0/src/swisstip/concepts/prompts/concept_extraction_v2.md +31 -0
  75. swisstip_builder-0.1.0/src/swisstip/concepts/prompts/concept_extraction_v3_extension.md +11 -0
  76. swisstip_builder-0.1.0/src/swisstip/concepts/prompts/concept_review_v3.md +28 -0
  77. swisstip_builder-0.1.0/src/swisstip/concepts/prompts.py +52 -0
  78. swisstip_builder-0.1.0/src/swisstip/concepts/providers/__init__.py +6 -0
  79. swisstip_builder-0.1.0/src/swisstip/concepts/providers/base.py +340 -0
  80. swisstip_builder-0.1.0/src/swisstip/concepts/providers/config.py +170 -0
  81. swisstip_builder-0.1.0/src/swisstip/concepts/providers/deepseek.py +17 -0
  82. swisstip_builder-0.1.0/src/swisstip/concepts/providers/exchange.py +216 -0
  83. swisstip_builder-0.1.0/src/swisstip/concepts/providers/groq.py +21 -0
  84. swisstip_builder-0.1.0/src/swisstip/concepts/providers/huggingface.py +47 -0
  85. swisstip_builder-0.1.0/src/swisstip/concepts/providers/ollama.py +50 -0
  86. swisstip_builder-0.1.0/src/swisstip/concepts/results.py +172 -0
  87. swisstip_builder-0.1.0/src/swisstip/concepts/schemas.py +46 -0
  88. swisstip_builder-0.1.0/src/swisstip/concepts/sections.py +111 -0
  89. swisstip_builder-0.1.0/src/swisstip/concepts/validation.py +146 -0
  90. swisstip_builder-0.1.0/src/swisstip/extraction/__init__.py +10 -0
  91. swisstip_builder-0.1.0/src/swisstip/extraction/anchors.py +134 -0
  92. swisstip_builder-0.1.0/src/swisstip/extraction/dataset.py +214 -0
  93. swisstip_builder-0.1.0/src/swisstip/extraction/extract_cli.py +129 -0
  94. swisstip_builder-0.1.0/src/swisstip/extraction/html_blocks.py +363 -0
  95. swisstip_builder-0.1.0/src/swisstip/extraction/legacy.py +77 -0
  96. swisstip_builder-0.1.0/src/swisstip/extraction/office_text.py +154 -0
  97. swisstip_builder-0.1.0/src/swisstip/extraction/pdf_text.py +95 -0
  98. swisstip_builder-0.1.0/src/swisstip/extraction/reading_view.py +75 -0
  99. swisstip_builder-0.1.0/src/swisstip/extraction/records.py +163 -0
  100. swisstip_builder-0.1.0/src/swisstip/extraction/run_reader.py +161 -0
  101. swisstip_builder-0.1.0/src/swisstip/extraction/validate.py +133 -0
  102. swisstip_builder-0.1.0/src/swisstip/ingestion/__init__.py +8 -0
  103. swisstip_builder-0.1.0/src/swisstip/ingestion/acquisition.py +302 -0
  104. swisstip_builder-0.1.0/src/swisstip/ingestion/catalog.py +173 -0
  105. swisstip_builder-0.1.0/src/swisstip/ingestion/crawler.py +782 -0
  106. swisstip_builder-0.1.0/src/swisstip/ingestion/discovery.py +101 -0
  107. swisstip_builder-0.1.0/src/swisstip/ingestion/download_cli.py +152 -0
  108. swisstip_builder-0.1.0/src/swisstip/ingestion/fedlex.py +64 -0
  109. swisstip_builder-0.1.0/src/swisstip/ingestion/gap_report.py +280 -0
  110. swisstip_builder-0.1.0/src/swisstip/ingestion/plugin_downloads.py +139 -0
  111. swisstip_builder-0.1.0/src/swisstip/ingestion/plugins.py +107 -0
  112. swisstip_builder-0.1.0/src/swisstip/ingestion/review_decisions.py +128 -0
  113. swisstip_builder-0.1.0/src/swisstip_builder.egg-info/PKG-INFO +81 -0
  114. swisstip_builder-0.1.0/src/swisstip_builder.egg-info/SOURCES.txt +116 -0
  115. swisstip_builder-0.1.0/src/swisstip_builder.egg-info/dependency_links.txt +1 -0
  116. swisstip_builder-0.1.0/src/swisstip_builder.egg-info/entry_points.txt +10 -0
  117. swisstip_builder-0.1.0/src/swisstip_builder.egg-info/requires.txt +14 -0
  118. swisstip_builder-0.1.0/src/swisstip_builder.egg-info/top_level.txt +1 -0
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
@@ -0,0 +1,17 @@
1
+ Swiss TIP - Swisscom Trusted Information Platform
2
+ Copyright 2026 The UBS Hackathon 2026 team: Alexander Bobrovsky and contributors
3
+
4
+ Licensed under the Apache License, Version 2.0 (see LICENSE).
5
+
6
+ The source catalogues under releases/ contain URLs and planning metadata
7
+ only. Any future release bundle that quotes excerpts of official publications
8
+ of the Swiss Confederation, the cantons or municipalities reproduces those
9
+ texts as cited evidence with their source URLs and access times; they remain
10
+ the property of their publishers and are not relicensed under the Apache
11
+ License. Consult the publishers' terms of use before redistributing them.
12
+
13
+ The admin console vendors HTMX 2.0.7
14
+ (apps/admin-console/src/swisstip/admin_console/static/htmx.min.js), which is
15
+ distributed by the htmx authors under the Zero-Clause BSD licence. It is
16
+ included verbatim so the console needs no network access and no JavaScript
17
+ build step.
@@ -0,0 +1,81 @@
1
+ Metadata-Version: 2.4
2
+ Name: swisstip-builder
3
+ Version: 0.1.0
4
+ Summary: Swiss TIP workstation tools: source acquisition, text extraction, release build and the admin console
5
+ Author: Alexander Bobrovsky
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/bobrovsky420/hackathon2026
8
+ Project-URL: Source, https://github.com/bobrovsky420/hackathon2026
9
+ Project-URL: Issues, https://github.com/bobrovsky420/hackathon2026/issues
10
+ Keywords: mcp,grounding,switzerland,crawler,curation
11
+ Classifier: Development Status :: 3 - Alpha
12
+ Classifier: Environment :: Web Environment
13
+ Classifier: Framework :: FastAPI
14
+ Classifier: Intended Audience :: Developers
15
+ Classifier: Operating System :: OS Independent
16
+ Classifier: Programming Language :: Python :: 3
17
+ Classifier: Programming Language :: Python :: 3 :: Only
18
+ Classifier: Programming Language :: Python :: 3.14
19
+ Requires-Python: >=3.14
20
+ Description-Content-Type: text/markdown
21
+ License-File: LICENSE
22
+ License-File: NOTICE
23
+ Requires-Dist: fastapi<1,>=0.115
24
+ Requires-Dist: jinja2<4,>=3.1
25
+ Requires-Dist: lxml==6.1.3
26
+ Requires-Dist: pydantic<3,>=2.11
27
+ Requires-Dist: pypdf==6.18.0
28
+ Requires-Dist: pypdfium2==5.13.0
29
+ Requires-Dist: python-multipart<1,>=0.0.20
30
+ Requires-Dist: pyyaml==6.0.3
31
+ Requires-Dist: swisstip-core==0.1.0
32
+ Requires-Dist: uvicorn<1,>=0.30
33
+ Provides-Extra: office
34
+ Requires-Dist: olefile==0.47; extra == "office"
35
+ Requires-Dist: striprtf==0.0.33; extra == "office"
36
+ Dynamic: license-file
37
+
38
+ # swisstip-builder
39
+
40
+ **Last update:** 15 September 2026
41
+
42
+ The workstation tools of Swiss TIP, the grounding MCP server for Swiss public
43
+ information. They turn a source catalogue into a validated, reviewed knowledge
44
+ release that `swisstip-mcp` serves.
45
+
46
+ | Command | Does |
47
+ | --- | --- |
48
+ | `swisstip-admin` | Local web console: sources, saved documents, reading view, review queue, tool sandbox, release |
49
+ | `swisstip-build` | The whole pipeline of a pack: acquire, gaps, extract, validate, build, accept, ready |
50
+ | `swisstip-download`, `swisstip-gaps` | Bounded source acquisition (robots.txt, rate limits, request budget) and the gap report |
51
+ | `swisstip-extract`, `swisstip-extract-validate` | Saved pages and PDFs to labelled text blocks with offsets and hashes |
52
+ | `swisstip-build-release` | Curation file plus text dataset to `release.json` |
53
+ | `swisstip-concepts`, `swisstip-concepts-package` | Model-proposed concept candidates with a separate review |
54
+
55
+ ## Install
56
+
57
+ Python 3.14 or newer. Install it as an isolated tool; the extraction
58
+ libraries are pinned exactly, because the text hashes of a release depend on
59
+ them:
60
+
61
+ ```bash
62
+ uv tool install swisstip-builder # or: pipx install swisstip-builder
63
+ uv tool install "swisstip-builder[office]" # adds legacy Office and RTF extraction
64
+ ```
65
+
66
+ ## Use
67
+
68
+ The tools work on a directory that holds `releases/<pack>/` (a source
69
+ catalogue, a curation file, saved pages and a text dataset), for example a
70
+ clone of the repository or an unpacked pack workspace. Pass it as `--root`:
71
+
72
+ ```bash
73
+ swisstip-admin --root . # console on http://127.0.0.1:8765
74
+ swisstip-build mvp-zurich --root . --from build --until accept
75
+ swisstip-build mvp-zurich --root . --from accept --until ready --attested-by "A. Person"
76
+ ```
77
+
78
+ The resulting `releases/<pack>/release.json` and `readiness.json` are what
79
+ `swisstip-mcp --release` serves.
80
+
81
+ Licence: Apache-2.0.
@@ -0,0 +1,44 @@
1
+ # swisstip-builder
2
+
3
+ **Last update:** 15 September 2026
4
+
5
+ The workstation tools of Swiss TIP, the grounding MCP server for Swiss public
6
+ information. They turn a source catalogue into a validated, reviewed knowledge
7
+ release that `swisstip-mcp` serves.
8
+
9
+ | Command | Does |
10
+ | --- | --- |
11
+ | `swisstip-admin` | Local web console: sources, saved documents, reading view, review queue, tool sandbox, release |
12
+ | `swisstip-build` | The whole pipeline of a pack: acquire, gaps, extract, validate, build, accept, ready |
13
+ | `swisstip-download`, `swisstip-gaps` | Bounded source acquisition (robots.txt, rate limits, request budget) and the gap report |
14
+ | `swisstip-extract`, `swisstip-extract-validate` | Saved pages and PDFs to labelled text blocks with offsets and hashes |
15
+ | `swisstip-build-release` | Curation file plus text dataset to `release.json` |
16
+ | `swisstip-concepts`, `swisstip-concepts-package` | Model-proposed concept candidates with a separate review |
17
+
18
+ ## Install
19
+
20
+ Python 3.14 or newer. Install it as an isolated tool; the extraction
21
+ libraries are pinned exactly, because the text hashes of a release depend on
22
+ them:
23
+
24
+ ```bash
25
+ uv tool install swisstip-builder # or: pipx install swisstip-builder
26
+ uv tool install "swisstip-builder[office]" # adds legacy Office and RTF extraction
27
+ ```
28
+
29
+ ## Use
30
+
31
+ The tools work on a directory that holds `releases/<pack>/` (a source
32
+ catalogue, a curation file, saved pages and a text dataset), for example a
33
+ clone of the repository or an unpacked pack workspace. Pass it as `--root`:
34
+
35
+ ```bash
36
+ swisstip-admin --root . # console on http://127.0.0.1:8765
37
+ swisstip-build mvp-zurich --root . --from build --until accept
38
+ swisstip-build mvp-zurich --root . --from accept --until ready --attested-by "A. Person"
39
+ ```
40
+
41
+ The resulting `releases/<pack>/release.json` and `readiness.json` are what
42
+ `swisstip-mcp --release` serves.
43
+
44
+ Licence: Apache-2.0.
@@ -0,0 +1,88 @@
1
+ # Generated by scripts/pypi/build_distributions.py; do not edit.
2
+ [build-system]
3
+ requires = [
4
+ "setuptools>=77",
5
+ ]
6
+ build-backend = "setuptools.build_meta"
7
+
8
+ [project]
9
+ name = "swisstip-builder"
10
+ version = "0.1.0"
11
+ description = "Swiss TIP workstation tools: source acquisition, text extraction, release build and the admin console"
12
+ readme = "README.md"
13
+ requires-python = ">=3.14"
14
+ license = "Apache-2.0"
15
+ license-files = [
16
+ "LICENSE",
17
+ "NOTICE",
18
+ ]
19
+ authors = [
20
+ { name = "Alexander Bobrovsky" },
21
+ ]
22
+ keywords = [
23
+ "mcp",
24
+ "grounding",
25
+ "switzerland",
26
+ "crawler",
27
+ "curation",
28
+ ]
29
+ classifiers = [
30
+ "Development Status :: 3 - Alpha",
31
+ "Environment :: Web Environment",
32
+ "Framework :: FastAPI",
33
+ "Intended Audience :: Developers",
34
+ "Operating System :: OS Independent",
35
+ "Programming Language :: Python :: 3",
36
+ "Programming Language :: Python :: 3 :: Only",
37
+ "Programming Language :: Python :: 3.14",
38
+ ]
39
+ dependencies = [
40
+ "fastapi<1,>=0.115",
41
+ "jinja2<4,>=3.1",
42
+ "lxml==6.1.3",
43
+ "pydantic<3,>=2.11",
44
+ "pypdf==6.18.0",
45
+ "pypdfium2==5.13.0",
46
+ "python-multipart<1,>=0.0.20",
47
+ "pyyaml==6.0.3",
48
+ "swisstip-core==0.1.0",
49
+ "uvicorn<1,>=0.30",
50
+ ]
51
+
52
+ [project.urls]
53
+ Homepage = "https://github.com/bobrovsky420/hackathon2026"
54
+ Source = "https://github.com/bobrovsky420/hackathon2026"
55
+ Issues = "https://github.com/bobrovsky420/hackathon2026/issues"
56
+
57
+ [project.optional-dependencies]
58
+ office = [
59
+ "olefile==0.47",
60
+ "striprtf==0.0.33",
61
+ ]
62
+
63
+ [project.scripts]
64
+ swisstip-admin = "swisstip.admin_console.app:main"
65
+ swisstip-build = "swisstip.builder.cli:main"
66
+ swisstip-build-release = "swisstip.build.build_cli:main"
67
+ swisstip-concepts = "swisstip.concepts.concepts_cli:main"
68
+ swisstip-concepts-package = "swisstip.concepts.package_cli:main"
69
+ swisstip-download = "swisstip.ingestion.download_cli:main"
70
+ swisstip-extract = "swisstip.extraction.extract_cli:main"
71
+ swisstip-extract-validate = "swisstip.extraction.validate:main"
72
+ swisstip-gaps = "swisstip.ingestion.gap_report:main"
73
+
74
+ [tool.setuptools.packages.find]
75
+ where = [
76
+ "src",
77
+ ]
78
+ namespaces = true
79
+
80
+ [tool.setuptools.package-data]
81
+ "swisstip.concepts" = [
82
+ "prompts/*.md",
83
+ ]
84
+ "swisstip.admin_console" = [
85
+ "views/*.html",
86
+ "views/**/*.html",
87
+ "static/*",
88
+ ]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
@@ -0,0 +1,11 @@
1
+ """Swiss TIP admin console: a local web interface over the files of a pack.
2
+
3
+ Build-side only; the MCP server never imports this package. Every screen
4
+ reads a file the pipeline already writes, and the console writes only the
5
+ curation file, the source catalogue and its own checks file. See
6
+ docs/architecture/admin-console.md.
7
+ """
8
+
9
+ CONSOLE_NAME = "swisstip-admin"
10
+ CONSOLE_VERSION = "0.1.0"
11
+ CHECKS_SCHEMA_VERSION = "swiss-tip-checks/v1"
@@ -0,0 +1,218 @@
1
+ """The console application: one FastAPI app over the files of the packs.
2
+
3
+ swisstip-admin edit mode on 127.0.0.1:8765
4
+ swisstip-admin --actor "Anna Meier" name the person who writes
5
+ swisstip-admin --read-only evaluator view: no write and no job route
6
+ swisstip-admin --host 0.0.0.0 --auth-file .local/console-users.txt
7
+
8
+ Routes are grouped by screen under `screens/`, one module and one template
9
+ folder per screen of section 4 of docs/architecture/admin-console.md. In
10
+ read-only mode the write and job routers are not registered at all, so a
11
+ missing button is not the only thing that stops a write.
12
+ """
13
+
14
+ import argparse
15
+ import base64
16
+ import hashlib
17
+ import json
18
+ import secrets
19
+ import sys
20
+ from pathlib import Path
21
+ from typing import Iterable
22
+
23
+ from fastapi import Depends, FastAPI, HTTPException, Request, status
24
+ from fastapi.responses import HTMLResponse, JSONResponse
25
+ from fastapi.staticfiles import StaticFiles
26
+ from fastapi.templating import Jinja2Templates
27
+
28
+ from . import CONSOLE_NAME, CONSOLE_VERSION
29
+ from .data import Console, PackData
30
+ from .jobs import JobRunner
31
+ from .writes import WriteConflict, WriteRefused
32
+
33
+ ROOT = Path(__file__).resolve().parents[5]
34
+ PACKAGE = Path(__file__).resolve().parent
35
+ DEFAULT_HOST = "127.0.0.1"
36
+ DEFAULT_PORT = 8765
37
+
38
+ templates = Jinja2Templates(directory=str(PACKAGE / "views"))
39
+
40
+
41
+ # --- shared template helpers ------------------------------------------------
42
+
43
+
44
+ def shorten(value, length: int = 12) -> str:
45
+ text = "" if value is None else str(value)
46
+ return text if len(text) <= length else text[:length] + "..."
47
+
48
+
49
+ def as_json(value) -> str:
50
+ return json.dumps(value, indent=2, ensure_ascii=False, default=str)
51
+
52
+
53
+ def block_number(block_id: str) -> int:
54
+ return int(str(block_id).rsplit(":b", 1)[-1])
55
+
56
+
57
+ templates.env.filters["shorten"] = shorten
58
+ templates.env.filters["as_json"] = as_json
59
+ templates.env.filters["block_number"] = block_number
60
+ templates.env.globals["console_version"] = CONSOLE_VERSION
61
+
62
+
63
+ def render(request: Request, name: str, *, status_code: int = 200, **context) -> HTMLResponse:
64
+ """Every screen renders through here, so the header is the same everywhere."""
65
+ app = request.app
66
+ pack = context.get("pack")
67
+ values = dict(
68
+ console=app.state.console, read_only=app.state.console.read_only, actor=actor_of(request),
69
+ layout="fragment.html" if request.headers.get("hx-request") else "base.html",
70
+ packs=app.state.console.pack_names(), pack_name=pack.pack if isinstance(pack, PackData) else pack,
71
+ notice=request.query_params.get("notice"), error=request.query_params.get("error"), active=None)
72
+ values.update(context) # a screen may name its own `error` or `notice`
73
+ return templates.TemplateResponse(request, name, values, status_code=status_code)
74
+
75
+
76
+ def actor_of(request: Request) -> str:
77
+ return getattr(request.state, "actor", None) or request.app.state.console.actor
78
+
79
+
80
+ # --- authentication (hosted mode, section 9) --------------------------------
81
+
82
+
83
+ def read_users(path: Path) -> dict[str, tuple[str, str]]:
84
+ """`user:<sha256 of password>:<editor|reader>` per line; the file lives outside Git."""
85
+ users: dict[str, tuple[str, str]] = {}
86
+ for line in Path(path).read_text(encoding="utf-8").splitlines():
87
+ line = line.strip()
88
+ if not line or line.startswith("#"):
89
+ continue
90
+ parts = line.split(":")
91
+ if len(parts) != 3:
92
+ raise ValueError(f"Bad line in {path}: expected user:sha256:role")
93
+ users[parts[0]] = (parts[1].lower(), parts[2].strip().lower())
94
+ return users
95
+
96
+
97
+ def authenticate(request: Request) -> str:
98
+ """HTTP basic; returns the user name. No secret is ever rendered."""
99
+ users = request.app.state.users
100
+ if not users:
101
+ return request.app.state.console.actor
102
+ header = request.headers.get("authorization", "")
103
+ unauthorized = HTTPException(status.HTTP_401_UNAUTHORIZED, "Authentication required",
104
+ headers={"WWW-Authenticate": "Basic realm=\"Swiss TIP admin console\""})
105
+ if not header.lower().startswith("basic "):
106
+ raise unauthorized
107
+ try:
108
+ name, _, password = base64.b64decode(header[6:]).decode("utf-8").partition(":")
109
+ except Exception as exc:
110
+ raise unauthorized from exc
111
+ expected = users.get(name)
112
+ if expected is None or not secrets.compare_digest(expected[0], hashlib.sha256(password.encode("utf-8")).hexdigest()):
113
+ raise unauthorized
114
+ request.state.actor = name
115
+ request.state.role = expected[1]
116
+ return name
117
+
118
+
119
+ def require_editor(request: Request, user: str = Depends(authenticate)) -> str:
120
+ """Write endpoints are for users listed as editors; in local mode there is one actor."""
121
+ if request.app.state.users and getattr(request.state, "role", "reader") != "editor":
122
+ raise HTTPException(status.HTTP_403_FORBIDDEN, "This user may read but not write")
123
+ return user
124
+
125
+
126
+ def get_pack(request: Request, pack: str) -> PackData:
127
+ try:
128
+ return request.app.state.console.pack(pack)
129
+ except KeyError as exc:
130
+ raise HTTPException(status.HTTP_404_NOT_FOUND, f"Unknown pack {pack!r}") from exc
131
+
132
+
133
+ # --- application ------------------------------------------------------------
134
+
135
+
136
+ def create_app(root: Path = ROOT, *, read_only: bool = False, actor: str = "operator",
137
+ run_dirs: dict[str, Path] | None = None, server_log: Path | None = None,
138
+ auth_file: Path | None = None) -> FastAPI:
139
+ from .screens import documents, operations, packs, release, review, runs, sandbox, sources, workbench
140
+
141
+ console = Console(root, read_only=read_only, actor=actor, run_dirs=run_dirs, server_log=server_log)
142
+ users = read_users(auth_file) if auth_file else {}
143
+ # Hosted: every page needs a user, so the actor on a write is the authenticated one.
144
+ app = FastAPI(title="Swiss TIP admin console", version=CONSOLE_VERSION, docs_url=None, redoc_url=None,
145
+ dependencies=[Depends(authenticate)] if users else [])
146
+ app.state.console = console
147
+ app.state.jobs = JobRunner()
148
+ app.state.users = users
149
+ app.mount("/static", StaticFiles(directory=str(PACKAGE / "static")), name="static")
150
+ for name in console.pack_names():
151
+ app.state.jobs.mark_interrupted(console.pack(name))
152
+
153
+ @app.exception_handler(WriteRefused)
154
+ async def refused(request: Request, exc: WriteRefused):
155
+ if wants_json(request):
156
+ return JSONResponse(status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
157
+ content=dict(refused=exc.message, issues=exc.issues, fields=exc.fields))
158
+ return render(request, "refused.html", status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
159
+ message=exc.message, issues=exc.issues, fields=exc.fields,
160
+ back=request.headers.get("referer", "/"))
161
+
162
+ @app.exception_handler(WriteConflict)
163
+ async def conflict(request: Request, exc: WriteConflict):
164
+ return render(request, "conflict.html", status_code=status.HTTP_409_CONFLICT, message=exc.message,
165
+ last_actor=exc.last_actor, current_sha256=exc.current_sha256,
166
+ back=request.headers.get("referer", "/"))
167
+
168
+ @app.get("/healthz")
169
+ def healthz():
170
+ return dict(status="ok", name=CONSOLE_NAME, version=CONSOLE_VERSION, root=str(console.root),
171
+ mode="read-only" if read_only else "edit", packs=console.pack_names())
172
+
173
+ for module in (packs, sources, runs, documents, workbench, review, release, sandbox, operations):
174
+ app.include_router(module.read_router)
175
+ if not read_only and hasattr(module, "write_router"):
176
+ app.include_router(module.write_router)
177
+ return app
178
+
179
+
180
+ def wants_json(request: Request) -> bool:
181
+ return "application/json" in request.headers.get("accept", "")
182
+
183
+
184
+ def main(argv: Iterable[str] | None = None) -> int:
185
+ parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
186
+ parser.add_argument("--root", type=Path, default=ROOT, help="repository root; default: this checkout")
187
+ parser.add_argument("--host", default=DEFAULT_HOST, help=f"bind address; default {DEFAULT_HOST}")
188
+ parser.add_argument("--port", type=int, default=DEFAULT_PORT)
189
+ parser.add_argument("--actor", default="operator", help="name recorded on every write")
190
+ parser.add_argument("--read-only", action="store_true", help="register no write and no job route")
191
+ parser.add_argument("--run-dir", action="append", default=[], metavar="PACK=DIR",
192
+ help="run directory of a pack; default releases/<pack> when it holds a run, else .local/<pack>")
193
+ parser.add_argument("--server-log", type=Path, help="log file of a served release, for the operations screen")
194
+ parser.add_argument("--auth-file", type=Path, help="HTTP basic users: user:sha256:editor|reader per line")
195
+ parser.add_argument("--hash-password", metavar="PASSWORD", help="print the SHA-256 for an --auth-file line and exit")
196
+ args = parser.parse_args(argv)
197
+ if args.hash_password:
198
+ print(hashlib.sha256(args.hash_password.encode("utf-8")).hexdigest())
199
+ return 0
200
+ run_dirs = {}
201
+ for item in args.run_dir:
202
+ name, _, path = item.partition("=")
203
+ if not path:
204
+ parser.error("--run-dir takes PACK=DIR")
205
+ run_dirs[name] = Path(path)
206
+ if args.host != DEFAULT_HOST and not args.auth_file:
207
+ print("warning: binding beyond 127.0.0.1 without --auth-file leaves the console open", file=sys.stderr)
208
+ app = create_app(args.root, read_only=args.read_only, actor=args.actor, run_dirs=run_dirs,
209
+ server_log=args.server_log, auth_file=args.auth_file)
210
+ import uvicorn
211
+ print(f"{CONSOLE_NAME} {CONSOLE_VERSION} on http://{args.host}:{args.port} "
212
+ f"({'read-only' if args.read_only else 'edit'} mode, actor {args.actor!r}, root {args.root})")
213
+ uvicorn.run(app, host=args.host, port=args.port, log_level="info")
214
+ return 0
215
+
216
+
217
+ if __name__ == "__main__":
218
+ raise SystemExit(main())