Packaging with rye, CLI for latin2shaw

.gitignore

@@ -1,2 +1,7 @@
-
+target
+.venv
+.env
+__pycache__
+.idea
+dist
 .DS_Store

.python-version

@@ -0,0 +1 @@
+3.12.3

README.md

@@ -28,17 +28,33 @@ The files readlex_converter.json and readlex_converter_phrases.json have been de
 
 The file readlex.dict (and addendum.dict) is adapted for use with Dave Coffin's scrips available at [Dechifro.org](https://www.dechifro.org/shavian/).
 
-## latin2shaw.py
+## src/readlex/latin2shaw.py
 
-The file latin2shaw.py is the script I use for the ReadLex Converter. It uses spaCy for part of speech tagging. 
+The file latin2shaw.py contains the code I use for the ReadLex Converter. It uses spaCy for part of speech tagging. 
 
-To use latin2shaw.py you'll need to install the following packages with it:
-- spaCy and an English language model (I use en_core_web_sm), following the instructions [here](https://spacy.io/usage)
-- unidecode
-- smartypants
-- bs4 (BeautifulSoup)
+To use it as a command line tool:
 
-You will also need to make sure that latin2shaw.py points to the locations where you have saved readlex_converter.json and readlex_converter_phrases.json.
+```bash
+pip install readlex
+
+# the script can read from stdin and print to stdout
+echo "hello world" | latin2shaw 
+
+# or use files
+latin2shaw --in_file in.txt --out_file out.txt
+```
+
+Once installed, it can also be used from python:
+
+```python
+from readlex import latin2shaw
+
+print(latin2shaw("hello world"))
+```
+
+### For contributors
+
+Once you have cloned the repo and [installed rye](https://rye.astral.sh/), you can install/sync dependencies with `rye sync` and run the script with `rye run latin2shaw`
 
 ## Futher information
 

pyproject.toml

@@ -0,0 +1,43 @@
+[project]
+name = "readlex"
+version = "0.1.0"
+description = "Auto-transliteration of English language text from latin to Shaw script using the Read Lexicon"
+authors = [
+    { name = "Shavian-info", email = "contact@shavian.info" },
+    { name = "Ingrid", email = "git@ingrids.email" }
+]
+dependencies = [
+    "spacy>=3.7.4",
+    "unidecode>=1.3.8",
+    "smartypants>=2.0.1",
+    "bs4>=0.0.2",
+    "en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl",
+    "typed-argument-parser>=1.10.0",
+]
+readme = "README.md"
+requires-python = ">= 3.8"
+exclude = [
+    "readlex.json",
+    "kingsleyreadlexicon.tsv",
+    "readlex.dict",
+    "addendum.dict"
+]
+
+[project.scripts]
+latin2shaw = "readlex.latin2shaw:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.rye]
+managed = true
+dev-dependencies = [
+    "pytest>=8.2.1",
+]
+
+[tool.hatch.metadata]
+allow-direct-references = true
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/readlex"]

requirements-dev.lock

@@ -0,0 +1,136 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+#   generate-hashes: false
+
+-e file:.
+annotated-types==0.7.0
+    # via pydantic
+beautifulsoup4==4.12.3
+    # via bs4
+blis==0.7.11
+    # via thinc
+bs4==0.0.2
+    # via readlex
+catalogue==2.0.10
+    # via spacy
+    # via srsly
+    # via thinc
+certifi==2024.2.2
+    # via requests
+charset-normalizer==3.3.2
+    # via requests
+click==8.1.7
+    # via typer
+cloudpathlib==0.16.0
+    # via weasel
+confection==0.1.5
+    # via thinc
+    # via weasel
+cymem==2.0.8
+    # via preshed
+    # via spacy
+    # via thinc
+docstring-parser==0.16
+    # via typed-argument-parser
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl
+    # via readlex
+idna==3.7
+    # via requests
+iniconfig==2.0.0
+    # via pytest
+jinja2==3.1.4
+    # via spacy
+langcodes==3.4.0
+    # via spacy
+language-data==1.2.0
+    # via langcodes
+marisa-trie==1.1.1
+    # via language-data
+markupsafe==2.1.5
+    # via jinja2
+murmurhash==1.0.10
+    # via preshed
+    # via spacy
+    # via thinc
+mypy-extensions==1.0.0
+    # via typing-inspect
+numpy==1.26.4
+    # via blis
+    # via spacy
+    # via thinc
+packaging==24.0
+    # via pytest
+    # via spacy
+    # via thinc
+    # via weasel
+pluggy==1.5.0
+    # via pytest
+preshed==3.0.9
+    # via spacy
+    # via thinc
+pydantic==2.7.2
+    # via confection
+    # via spacy
+    # via thinc
+    # via weasel
+pydantic-core==2.18.3
+    # via pydantic
+pytest==8.2.1
+requests==2.32.3
+    # via spacy
+    # via weasel
+setuptools==70.0.0
+    # via marisa-trie
+    # via spacy
+    # via thinc
+smart-open==6.4.0
+    # via spacy
+    # via weasel
+smartypants==2.0.1
+    # via readlex
+soupsieve==2.5
+    # via beautifulsoup4
+spacy==3.7.4
+    # via en-core-web-sm
+    # via readlex
+spacy-legacy==3.0.12
+    # via spacy
+spacy-loggers==1.0.5
+    # via spacy
+srsly==2.4.8
+    # via confection
+    # via spacy
+    # via thinc
+    # via weasel
+thinc==8.2.3
+    # via spacy
+tqdm==4.66.4
+    # via spacy
+typed-argument-parser==1.10.0
+    # via readlex
+typer==0.9.4
+    # via spacy
+    # via weasel
+typing-extensions==4.12.0
+    # via pydantic
+    # via pydantic-core
+    # via typer
+    # via typing-inspect
+typing-inspect==0.9.0
+    # via typed-argument-parser
+unidecode==1.3.8
+    # via readlex
+urllib3==2.2.1
+    # via requests
+wasabi==1.1.3
+    # via spacy
+    # via thinc
+    # via weasel
+weasel==0.3.4
+    # via spacy

requirements.lock

@@ -0,0 +1,130 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+#   generate-hashes: false
+
+-e file:.
+annotated-types==0.7.0
+    # via pydantic
+beautifulsoup4==4.12.3
+    # via bs4
+blis==0.7.11
+    # via thinc
+bs4==0.0.2
+    # via readlex
+catalogue==2.0.10
+    # via spacy
+    # via srsly
+    # via thinc
+certifi==2024.2.2
+    # via requests
+charset-normalizer==3.3.2
+    # via requests
+click==8.1.7
+    # via typer
+cloudpathlib==0.16.0
+    # via weasel
+confection==0.1.5
+    # via thinc
+    # via weasel
+cymem==2.0.8
+    # via preshed
+    # via spacy
+    # via thinc
+docstring-parser==0.16
+    # via typed-argument-parser
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl
+    # via readlex
+idna==3.7
+    # via requests
+jinja2==3.1.4
+    # via spacy
+langcodes==3.4.0
+    # via spacy
+language-data==1.2.0
+    # via langcodes
+marisa-trie==1.1.1
+    # via language-data
+markupsafe==2.1.5
+    # via jinja2
+murmurhash==1.0.10
+    # via preshed
+    # via spacy
+    # via thinc
+mypy-extensions==1.0.0
+    # via typing-inspect
+numpy==1.26.4
+    # via blis
+    # via spacy
+    # via thinc
+packaging==24.0
+    # via spacy
+    # via thinc
+    # via weasel
+preshed==3.0.9
+    # via spacy
+    # via thinc
+pydantic==2.7.2
+    # via confection
+    # via spacy
+    # via thinc
+    # via weasel
+pydantic-core==2.18.3
+    # via pydantic
+requests==2.32.3
+    # via spacy
+    # via weasel
+setuptools==70.0.0
+    # via marisa-trie
+    # via spacy
+    # via thinc
+smart-open==6.4.0
+    # via spacy
+    # via weasel
+smartypants==2.0.1
+    # via readlex
+soupsieve==2.5
+    # via beautifulsoup4
+spacy==3.7.4
+    # via en-core-web-sm
+    # via readlex
+spacy-legacy==3.0.12
+    # via spacy
+spacy-loggers==1.0.5
+    # via spacy
+srsly==2.4.8
+    # via confection
+    # via spacy
+    # via thinc
+    # via weasel
+thinc==8.2.3
+    # via spacy
+tqdm==4.66.4
+    # via spacy
+typed-argument-parser==1.10.0
+    # via readlex
+typer==0.9.4
+    # via spacy
+    # via weasel
+typing-extensions==4.12.0
+    # via pydantic
+    # via pydantic-core
+    # via typer
+    # via typing-inspect
+typing-inspect==0.9.0
+    # via typed-argument-parser
+unidecode==1.3.8
+    # via readlex
+urllib3==2.2.1
+    # via requests
+wasabi==1.1.3
+    # via spacy
+    # via thinc
+    # via weasel
+weasel==0.3.4
+    # via spacy

src/readlex/__init__.py

@@ -0,0 +1,5 @@
+from readlex.latin2shaw import latin2shaw
+
+__all__ = [
+    "latin2shaw",
+]