Add to_list() analogous to to_tree()

.github/workflows/index.yml

@@ -9,15 +9,15 @@ jobs:
       matrix:
         python-version: ["3.6", "3.7", "3.8", "3.9", "3.10"]
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
+        cache: 'pip'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install tox tox-gh-actions
+        python -m pip install tox tox-gh-actions
     - name: Run tests
-      run: |
-        tox
+      run: tox

.gitignore

@@ -5,3 +5,4 @@
 .tox
 /build
 /dist
+.python-version

conllu/models.py

@@ -247,23 +247,26 @@ def __eq__(self, other: T.Any) -> bool:
                 and self.metadata == other.metadata
         return False
 
-    def serialize(self) -> str:
-        if not self.token or "id" not in self.token:
-            raise ParseException("Could not serialize tree, missing 'id' field.")
-
-        def flatten_tree(root_token: TokenTree, token_list: T.List[Token] = []) -> T.List[Token]:
+    def to_list(self):
+        def _to_list(root_token: TokenTree, token_list: T.List[Token] = []) -> T.List[Token]:
             token_list.append(root_token.token)
 
             for child_token in root_token.children:
-                flatten_tree(child_token, token_list)
+                _to_list(child_token, token_list)
 
             return token_list
 
-        tokens = flatten_tree(self)
-        tokens = sorted(tokens, key=lambda t: t['id'])
-        tokenlist = TokenList(tokens, self.metadata)
+        if not self.token or "id" not in self.token:
+            raise ParseException("Could not flatten tree; missing 'id' field.")
 
-        return serialize(tokenlist)
+        token_list = _to_list(self)
+        token_list = sorted(token_list, key=lambda t: t['id'])
+        token_list = TokenList(token_list, self.metadata)
+
+        return token_list
+
+    def serialize(self) -> str:
+        return serialize(self.to_list())
 
     def print_tree(self, depth: int = 0, indent: int = 4,
                    exclude_fields: T.Sequence[str] = DEFAULT_EXCLUDE_FIELDS) -> None:

pyproject.toml

@@ -0,0 +1,67 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "conllu"
+version = "4.5.3"
+description = "CoNLL-U Parser parses a CoNLL-U formatted string into a nested python dictionary"
+readme = "README.md"
+requires-python = ">=3.6"
+authors = [{name = "Emil Stenström", email = "emil@emilstenstrom.se"}]
+license = {file = "LICENSE"}
+keywords = ["conllu", "conll", "conll-u", "parser", "nlp"]
+classifiers = [
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.6",
+    "Programming Language :: Python :: 3.7",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Operating System :: OS Independent",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/EmilStenstrom/conllu/"
+
+[project.optional-dependencies]
+test = ["tox"]
+
+[tool.setuptools.packages.find]
+where = ["conllu"]
+include = ["conllu"]
+
+[tool.setuptools.package-data]
+"conllu" = ["py.typed"]
+
+[tool.pytest.ini_options]
+markers = [
+    "integration: marks tests as integration tests (deselect with '-m \"not integration\"')",
+]
+[tool.flake8]
+ignore = "E302, W503"
+max-line-length = 119
+
+[tool.coverage.report]
+fail_under = 100
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    'if T\.TYPE_CHECKING',
+    'TT\.Protocol',
+]
+
+[tool.coverage.run]
+branch = true
+source = ["conllu"]
+omit = [
+    "conllu/__init__.py",
+]
+
+[tool.isort]
+line_length = 119
+multi_line_output = 5
+include_trailing_comma = true
+known_first_party = ["conllu", "tests"]

requirements-dev.in

@@ -1,5 +1,6 @@
 coverage
 flake8
+flake8-pyproject
 isort
 mypy
 pip-tools

requirements-dev.txt

@@ -1,140 +1,146 @@
 #
-# This file is autogenerated by pip-compile with python 3.11
-# To update, run:
+# This file is autogenerated by pip-compile with Python 3.12
+# by the following command:
 #
 #    pip-compile requirements-dev.in
 #
-attrs==22.2.0
-    # via pytest
-bleach==5.0.1
-    # via readme-renderer
-build==0.9.0
+build==1.2.1
     # via pip-tools
-cachetools==5.2.0
+cachetools==5.3.3
     # via tox
-certifi==2022.12.7
+certifi==2024.7.4
     # via requests
-cffi==1.15.1
+cffi==1.16.0
     # via cryptography
-chardet==5.1.0
+chardet==5.2.0
     # via tox
-charset-normalizer==2.1.1
+charset-normalizer==3.3.2
     # via requests
-click==8.1.3
+click==8.1.7
     # via pip-tools
 colorama==0.4.6
     # via tox
-commonmark==0.9.1
-    # via rich
-coverage==7.0.1
+coverage==7.6.0
     # via -r requirements-dev.in
-cryptography==41.0.0
+cryptography==42.0.8
     # via secretstorage
-distlib==0.3.6
+distlib==0.3.8
     # via virtualenv
-docutils==0.19
+docutils==0.21.2
     # via readme-renderer
-filelock==3.8.2
+filelock==3.15.4
     # via
     #   tox
     #   virtualenv
-flake8==6.0.0
+flake8==7.1.0
+    # via
+    #   -r requirements-dev.in
+    #   flake8-pyproject
+flake8-pyproject==1.2.3
     # via -r requirements-dev.in
-idna==3.4
+idna==3.7
     # via requests
-importlib-metadata==5.2.0
-    # via
-    #   keyring
-    #   twine
-iniconfig==1.1.1
+importlib-metadata==8.0.0
+    # via twine
+iniconfig==2.0.0
     # via pytest
-isort==5.11.4
+isort==5.13.2
     # via -r requirements-dev.in
-jaraco-classes==3.2.3
+jaraco-classes==3.4.0
+    # via keyring
+jaraco-context==5.3.0
+    # via keyring
+jaraco-functools==4.0.1
     # via keyring
 jeepney==0.8.0
     # via
     #   keyring
     #   secretstorage
-keyring==23.13.1
+keyring==25.2.1
     # via twine
+markdown-it-py==3.0.0
+    # via rich
 mccabe==0.7.0
     # via flake8
-more-itertools==9.0.0
-    # via jaraco-classes
-mypy==0.991
+mdurl==0.1.2
+    # via markdown-it-py
+more-itertools==10.3.0
+    # via
+    #   jaraco-classes
+    #   jaraco-functools
+mypy==1.10.1
     # via -r requirements-dev.in
-mypy-extensions==0.4.3
+mypy-extensions==1.0.0
     # via mypy
-packaging==22.0
+nh3==0.2.18
+    # via readme-renderer
+packaging==24.1
     # via
     #   build
     #   pyproject-api
     #   pytest
     #   tox
-pep517==0.13.0
-    # via build
-pip-tools==6.12.1
+pip-tools==7.4.1
     # via -r requirements-dev.in
-pkginfo==1.9.2
+pkginfo==1.10.0
     # via twine
-platformdirs==2.6.0
+platformdirs==4.2.2
     # via
     #   tox
     #   virtualenv
-pluggy==1.0.0
+pluggy==1.5.0
     # via
     #   pytest
     #   tox
-pycodestyle==2.10.0
+pycodestyle==2.12.0
     # via flake8
-pycparser==2.21
+pycparser==2.22
     # via cffi
-pyflakes==3.0.1
+pyflakes==3.2.0
     # via flake8
-pygments==2.13.0
+pygments==2.18.0
     # via
     #   readme-renderer
     #   rich
-pyproject-api==1.2.1
+pyproject-api==1.7.1
     # via tox
-pytest==7.2.0
+pyproject-hooks==1.1.0
+    # via
+    #   build
+    #   pip-tools
+pytest==8.2.2
     # via -r requirements-dev.in
-readme-renderer==37.3
+readme-renderer==44.0
     # via twine
-requests==2.31.0
+requests==2.32.3
     # via
     #   requests-toolbelt
     #   twine
-requests-toolbelt==0.10.1
+requests-toolbelt==1.0.0
     # via twine
 rfc3986==2.0.0
     # via twine
-rich==12.6.0
+rich==13.7.1
     # via twine
 secretstorage==3.3.3
     # via keyring
-six==1.16.0
-    # via bleach
-tox==4.0.17
+tox==4.16.0
     # via -r requirements-dev.in
-twine==4.0.2
+twine==5.1.1
     # via -r requirements-dev.in
-typing-extensions==4.4.0
+typing-extensions==4.12.2
     # via mypy
-urllib3==1.26.13
+urllib3==2.2.2
     # via
     #   requests
     #   twine
-virtualenv==20.17.1
+virtualenv==20.26.3
     # via tox
-webencodings==0.5.1
-    # via bleach
-wheel==0.38.4
+wheel==0.43.0
     # via
     #   -r requirements-dev.in
     #   pip-tools
-zipp==3.11.0
+zipp==3.19.2
     # via importlib-metadata
 
 # The following packages are considered to be unsafe in a requirements file: