seanchai 0.1.0__tar.gz

seanchai-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 sliva0
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

seanchai-0.1.0/PKG-INFO

@@ -0,0 +1,128 @@
+Metadata-Version: 2.4
+Name: seanchai
+Version: 0.1.0
+Summary: Machine-readable Diameter schemas from 3GPP documents and RFCs
+Keywords: diameter,3gpp,avp,abnf,rfc6733
+Author: sliva0
+Author-email: sliva0 <sliva0mk@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Telecommunications Industry
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Communications :: Telephony
+Classifier: Topic :: Software Development :: Code Generators
+Classifier: Topic :: System :: Networking
+Classifier: Typing :: Typed
+Requires-Dist: click>=8.5.1
+Requires-Dist: pydantic>=2.14.3
+Requires-Dist: seanchai-corpus>=2026.11.11 ; extra == 'corpus'
+Requires-Dist: pypdf[crypto]>=7.0.1 ; extra == 'extract'
+Requires-Dist: python-docx>=1.2.0 ; extra == 'extract'
+Requires-Python: >=3.12
+Project-URL: Homepage, https://github.com/sliva0/seanchai
+Project-URL: Documentation, https://github.com/sliva0/seanchai/tree/main/docs
+Project-URL: Issues, https://github.com/sliva0/seanchai/issues
+Provides-Extra: corpus
+Provides-Extra: extract
+Description-Content-Type: text/markdown
+
+# Seanchaí
+
+Seanchaí extracts Diameter command ABNFs and AVP definitions from 3GPP
+specifications, RFCs and a few other documents into one plain-text format,
+`.dad`. It gives you a parser and a resolved model over the result, so
+generating your stack's dictionary, or checking it against the
+specifications, takes a short script.
+
+Each `.dad` file records what its source document says, mistakes included.
+The only edits are declared patches and corrections, each with its reason.
+The [linter][linter] reports contradictions, and the
+[Wireshark oracle][oracle] compares the corpus with Wireshark's dictionary.
+
+## Installing
+
+Seanchaí needs Python 3.12 or newer.
+
+```sh
+pip install "seanchai[corpus]"   # the library and the corpus
+pip install "seanchai[extract]"  # also rebuild the corpus from source documents
+```
+
+The library (`seanchai`) and the data (`seanchai-corpus`) are separate
+packages with separate versions ([what the version covers][versions]).
+
+```python
+from seanchai.model import Model
+
+model = Model.installed()
+model.resolve("TS29.229", "Public-Identity")
+```
+
+## Commands
+
+Read the installed corpus, with no checkout and no downloads:
+
+```sh
+seanchai show NAME_OR_IDENTITY [--json] # one AVP and its other readings
+seanchai commands [REF | --application ID] [--json]
+seanchai dictionary -o OUT.json         # the corpus as JSON, to generate from
+seanchai export -o DIR                  # the corpus as JSON for the static site
+seanchai export -o DIR --include-pdfs --specifications specifications
+```
+
+Check and rewrite `.dad` files, the corpus's or your own sidecars:
+
+```sh
+seanchai lint [--corpus DIR | --no-corpus] [--show-accepted] [FILE.dad | DIR]...
+seanchai format [--check] [FILE.dad | DIR]...  # canonical form, ;; comments kept
+```
+
+Maintain the corpus, from the root of a checkout:
+
+```sh
+seanchai corpus download                    # fetch the catalog into specifications/
+seanchai corpus download --no-convert       # without LibreOffice; .doc unread
+seanchai corpus download --only wireshark   # one source, keeping the others
+seanchai corpus download --only transcribed # the hand transcriptions' PDFs
+seanchai corpus download --spec SPECREF --version X.Y.Z   # an older version
+seanchai corpus regenerate [--add SPECREF]  # rebuild the corpus from the downloads
+seanchai corpus regenerate --expand-ranges  # also widen stale declaration ranges
+seanchai corpus extract DOCX --pdf PDF --link URL [--corrections DIR] -o OUT.dad
+seanchai corpus extract-rfc RFC.txt --link URL [--corrections DIR] -o OUT.dad
+seanchai corpus correct RAW.dad --corrections DIR -o OUT.dad
+seanchai corpus crosscheck [FILE.dad | DIR]...  # against Wireshark's dictionary
+```
+
+Commands exit 1 on an error or a finding and 2 on a usage error.
+`corpus crosscheck` exits 0 on findings.
+
+## Documentation
+
+- [Using the model, the CLI's JSON and the corpus][consumers]
+- [The site export][website]
+- [The `.dad` format][format]
+- [Extraction][extractor] and [corrections][corrections]
+- [Checking traffic with a Wireshark plugin][validator]
+- [Development][development]
+
+## License
+
+MIT, see [LICENSE][license]. The corpus contains text from 3GPP, ETSI, 3GPP2,
+OMA, oneM2M and IETF documents, which stay under their publishers' terms.
+
+[consumers]: https://github.com/sliva0/seanchai/blob/main/docs/consumers.md
+[corrections]: https://github.com/sliva0/seanchai/blob/main/docs/corrections.md
+[development]: https://github.com/sliva0/seanchai/blob/main/docs/development.md
+[extractor]: https://github.com/sliva0/seanchai/blob/main/docs/extractor.md
+[format]: https://github.com/sliva0/seanchai/blob/main/docs/dad-format.md
+[license]: https://github.com/sliva0/seanchai/blob/main/LICENSE
+[linter]: https://github.com/sliva0/seanchai/blob/main/docs/linter.md
+[oracle]: https://github.com/sliva0/seanchai/blob/main/docs/oracle.md
+[validator]: https://github.com/sliva0/seanchai/blob/main/integrations/wireshark/validator/README.md
+[versions]: https://github.com/sliva0/seanchai/blob/main/docs/consumers.md#what-the-version-covers
+[website]: https://github.com/sliva0/seanchai/blob/main/docs/website.md

seanchai-0.1.0/README.md

@@ -0,0 +1,95 @@
+# Seanchaí
+
+Seanchaí extracts Diameter command ABNFs and AVP definitions from 3GPP
+specifications, RFCs and a few other documents into one plain-text format,
+`.dad`. It gives you a parser and a resolved model over the result, so
+generating your stack's dictionary, or checking it against the
+specifications, takes a short script.
+
+Each `.dad` file records what its source document says, mistakes included.
+The only edits are declared patches and corrections, each with its reason.
+The [linter][linter] reports contradictions, and the
+[Wireshark oracle][oracle] compares the corpus with Wireshark's dictionary.
+
+## Installing
+
+Seanchaí needs Python 3.12 or newer.
+
+```sh
+pip install "seanchai[corpus]"   # the library and the corpus
+pip install "seanchai[extract]"  # also rebuild the corpus from source documents
+```
+
+The library (`seanchai`) and the data (`seanchai-corpus`) are separate
+packages with separate versions ([what the version covers][versions]).
+
+```python
+from seanchai.model import Model
+
+model = Model.installed()
+model.resolve("TS29.229", "Public-Identity")
+```
+
+## Commands
+
+Read the installed corpus, with no checkout and no downloads:
+
+```sh
+seanchai show NAME_OR_IDENTITY [--json] # one AVP and its other readings
+seanchai commands [REF | --application ID] [--json]
+seanchai dictionary -o OUT.json         # the corpus as JSON, to generate from
+seanchai export -o DIR                  # the corpus as JSON for the static site
+seanchai export -o DIR --include-pdfs --specifications specifications
+```
+
+Check and rewrite `.dad` files, the corpus's or your own sidecars:
+
+```sh
+seanchai lint [--corpus DIR | --no-corpus] [--show-accepted] [FILE.dad | DIR]...
+seanchai format [--check] [FILE.dad | DIR]...  # canonical form, ;; comments kept
+```
+
+Maintain the corpus, from the root of a checkout:
+
+```sh
+seanchai corpus download                    # fetch the catalog into specifications/
+seanchai corpus download --no-convert       # without LibreOffice; .doc unread
+seanchai corpus download --only wireshark   # one source, keeping the others
+seanchai corpus download --only transcribed # the hand transcriptions' PDFs
+seanchai corpus download --spec SPECREF --version X.Y.Z   # an older version
+seanchai corpus regenerate [--add SPECREF]  # rebuild the corpus from the downloads
+seanchai corpus regenerate --expand-ranges  # also widen stale declaration ranges
+seanchai corpus extract DOCX --pdf PDF --link URL [--corrections DIR] -o OUT.dad
+seanchai corpus extract-rfc RFC.txt --link URL [--corrections DIR] -o OUT.dad
+seanchai corpus correct RAW.dad --corrections DIR -o OUT.dad
+seanchai corpus crosscheck [FILE.dad | DIR]...  # against Wireshark's dictionary
+```
+
+Commands exit 1 on an error or a finding and 2 on a usage error.
+`corpus crosscheck` exits 0 on findings.
+
+## Documentation
+
+- [Using the model, the CLI's JSON and the corpus][consumers]
+- [The site export][website]
+- [The `.dad` format][format]
+- [Extraction][extractor] and [corrections][corrections]
+- [Checking traffic with a Wireshark plugin][validator]
+- [Development][development]
+
+## License
+
+MIT, see [LICENSE][license]. The corpus contains text from 3GPP, ETSI, 3GPP2,
+OMA, oneM2M and IETF documents, which stay under their publishers' terms.
+
+[consumers]: https://github.com/sliva0/seanchai/blob/main/docs/consumers.md
+[corrections]: https://github.com/sliva0/seanchai/blob/main/docs/corrections.md
+[development]: https://github.com/sliva0/seanchai/blob/main/docs/development.md
+[extractor]: https://github.com/sliva0/seanchai/blob/main/docs/extractor.md
+[format]: https://github.com/sliva0/seanchai/blob/main/docs/dad-format.md
+[license]: https://github.com/sliva0/seanchai/blob/main/LICENSE
+[linter]: https://github.com/sliva0/seanchai/blob/main/docs/linter.md
+[oracle]: https://github.com/sliva0/seanchai/blob/main/docs/oracle.md
+[validator]: https://github.com/sliva0/seanchai/blob/main/integrations/wireshark/validator/README.md
+[versions]: https://github.com/sliva0/seanchai/blob/main/docs/consumers.md#what-the-version-covers
+[website]: https://github.com/sliva0/seanchai/blob/main/docs/website.md

seanchai-0.1.0/pyproject.toml

@@ -0,0 +1,126 @@
+[project]
+name = "seanchai"
+version = "0.1.0"
+description = "Machine-readable Diameter schemas from 3GPP documents and RFCs"
+readme = "README.md"
+requires-python = ">=3.12"
+license = "MIT"
+license-files = ["LICENSE"]
+keywords = [
+    "diameter",
+    "3gpp",
+    "avp",
+    "abnf",
+    "rfc6733",
+]
+classifiers = [
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Telecommunications Industry",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Topic :: Communications :: Telephony",
+    "Topic :: Software Development :: Code Generators",
+    "Topic :: System :: Networking",
+    "Typing :: Typed",
+]
+dependencies = [
+    "click>=8.5.1",
+    "pydantic>=2.14.3",
+]
+
+[[project.authors]]
+name = "sliva0"
+email = "sliva0mk@gmail.com"
+
+[project.optional-dependencies]
+corpus = ["seanchai-corpus>=2026.11.11"]
+extract = [
+    "pypdf[crypto]>=7.0.1",
+    "python-docx>=1.2.0",
+]
+
+[project.scripts]
+seanchai = "seanchai.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/sliva0/seanchai"
+Documentation = "https://github.com/sliva0/seanchai/tree/main/docs"
+Issues = "https://github.com/sliva0/seanchai/issues"
+
+[build-system]
+requires = ["uv_build>=0.10.2,<0.14.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "basedpyright>=1.40.2",
+    "pytest>=9.2.0",
+    "python-diameter>=0.9.0",
+    "ruff>=0.17.4",
+    "rumdl>=0.3.2",
+    "seanchai-corpus",
+    "seanchai[extract]",
+    "ty>=0.0.100",
+]
+
+[tool.uv.workspace]
+members = ["packages/seanchai-corpus"]
+
+[tool.uv.sources.seanchai-corpus]
+workspace = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"
+markers = ["sources: needs the downloaded source documents under specifications/"]
+
+[tool.ruff]
+target-version = "py312"
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "F",
+    "I",
+    "UP",
+    "B",
+    "SIM",
+    "RUF",
+]
+
+[tool.rumdl]
+enable = ["MD013"]
+cache = false
+
+[tool.rumdl.MD013]
+line-length = 80
+code-blocks = false
+tables = false
+stern = true
+ignore-link-urls = false
+length-mode = "chars"
+
+[tool.ty.environment]
+python = ".venv"
+python-version = "3.12"
+
+[tool.ty.src]
+include = [
+    "src",
+    "packages/seanchai-corpus/src",
+    "tests",
+]
+
+[tool.basedpyright]
+typeCheckingMode = "standard"
+pythonVersion = "3.12"
+include = [
+    "src",
+    "packages/seanchai-corpus/src",
+    "tests",
+]
+venvPath = "."
+venv = ".venv"

seanchai-0.1.0/pyproject.toml.orig

@@ -0,0 +1,115 @@
+[project]
+name = "seanchai"
+version = "0.1.0"
+description = "Machine-readable Diameter schemas from 3GPP documents and RFCs"
+readme = "README.md"
+authors = [
+    { name = "sliva0", email = "sliva0mk@gmail.com" }
+]
+requires-python = ">=3.12"
+license = "MIT"
+license-files = ["LICENSE"]
+keywords = ["diameter", "3gpp", "avp", "abnf", "rfc6733"]
+classifiers = [
+    "Environment :: Console",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Telecommunications Industry",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Topic :: Communications :: Telephony",
+    "Topic :: Software Development :: Code Generators",
+    "Topic :: System :: Networking",
+    "Typing :: Typed",
+]
+dependencies = [
+    "click>=8.5.1",
+    "pydantic>=2.14.3",
+]
+
+[project.optional-dependencies]
+corpus = ["seanchai-corpus>=2026.11.11"]
+# What reading and validating source documents takes (and lxml, through
+# python-docx). The model, the export and the lookup commands import neither.
+extract = [
+    "pypdf[crypto]>=7.0.1",
+    "python-docx>=1.2.0",
+]
+
+[project.scripts]
+seanchai = "seanchai.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/sliva0/seanchai"
+Documentation = "https://github.com/sliva0/seanchai/tree/main/docs"
+Issues = "https://github.com/sliva0/seanchai/issues"
+
+[build-system]
+requires = ["uv_build>=0.10.2,<0.14.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "basedpyright>=1.40.2",
+    "pytest>=9.2.0",
+    "python-diameter>=0.9.0",
+    "ruff>=0.17.4",
+    "rumdl>=0.3.2",
+    "seanchai-corpus",
+    "seanchai[extract]",
+    "ty>=0.0.100",
+]
+
+[tool.uv.workspace]
+members = ["packages/seanchai-corpus"]
+
+[tool.uv.sources]
+seanchai-corpus = { workspace = true }
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"
+markers = [
+    "sources: needs the downloaded source documents under specifications/",
+]
+
+# The floor requires-python names, not the 3.14 the venv runs, so that ruff
+# and both type checkers flag syntax and standard-library calls newer than it.
+[tool.ruff]
+target-version = "py312"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM", "RUF"]
+
+[tool.rumdl]
+# Line length only: the check is about formatting, not Markdown style.
+enable = ["MD013"]
+cache = false
+
+# Tables and fenced code may run long, and so may a line that is one unbroken
+# token or one whole link, even a link whose label could wrap. That is `stern`:
+# rumdl's default also passes a line whose last word merely crosses the limit,
+# and `strict` flags tables and code as well. Link targets count and columns are
+# plain characters, so 80 means what `len` says.
+[tool.rumdl.MD013]
+line-length = 80
+code-blocks = false
+tables = false
+stern = true
+ignore-link-urls = false
+length-mode = "chars"
+
+[tool.ty.environment]
+python = ".venv"
+python-version = "3.12"
+
+[tool.ty.src]
+include = ["src", "packages/seanchai-corpus/src", "tests"]
+
+[tool.basedpyright]
+typeCheckingMode = "standard"
+pythonVersion = "3.12"
+include = ["src", "packages/seanchai-corpus/src", "tests"]
+venvPath = "."
+venv = ".venv"

seanchai-0.1.0/src/seanchai/__init__.py

@@ -0,0 +1,41 @@
+"""Seanchaí: Diameter specifications as reviewable `.dad` files.
+
+This package holds only the shared error base and the version, so importing
+`seanchai` pulls in no docx, PDF or HTTP code. The command line lives in `cli`.
+
+- `seanchai.model`: the corpus resolved into objects a consumer uses, the place
+  to start (docs/consumers.md);
+- `seanchai.corpus`: a set of parsed `.dad` files, and the rules for resolving
+  between them;
+- `seanchai.dictionary`: the JSON `seanchai dictionary` writes, as pydantic
+  models, and its builder;
+- `seanchai.export` and `seanchai.export_schema`: the JSON `seanchai export`
+  writes for the static site, and its shape;
+- `seanchai.dad`: the `.dad` AST, parser, canonical formatter, corrections and
+  the ABNF syntax they share;
+- `seanchai.linter`: the rules reporting what a file or the corpus contradicts;
+- `seanchai.oracle`: the cross-check against Wireshark's Diameter dictionary;
+- `seanchai.errors`: the error base, and the error naming a missing extra;
+- `seanchai.extractor`: 3GPP docx/PDF and RFC text to AST, the former with the
+  `seanchai[extract]` extra;
+- `seanchai.downloader`: fetches the source documents the corpus is built from,
+  with that extra for whatever it has to open as docx or PDF.
+
+Semantic versioning covers the names in the `__all__` of this package and of
+each module listed above (for `seanchai.downloader`, the package's own; for
+`seanchai.extractor`, its modules'), the command line's commands, options and
+exit statuses, the format versions of the two JSON outputs
+(`dictionary.FORMAT_VERSION`, `export_schema.SCHEMA_VERSION`) and the corpus
+formats the library reads (`corpus.FORMATS`). Modules whose names start with an
+underscore, names outside an `__all__`, and the Python of `seanchai.cli` may
+change in any release.
+"""
+
+from importlib.metadata import version
+
+from .errors import SeanchaiError
+
+__all__ = ["SeanchaiError", "__version__"]
+
+# Kept once, in this package's pyproject.
+__version__ = version("seanchai")