From bbe6709834e0e35b30f9c918cc1b0ef3136f1193 Mon Sep 17 00:00:00 2001
From: AshenWELI <ashenset@gmail.com>
Date: Wed, 20 May 2026 17:14:21 +0200
Subject: [PATCH] Added Sinhala test cases for spaCy, implemented si_tokenizer
 and si_vocab, and fixed version issues in the requirements file.

---
 git_info.py                           |   3 +
 requirements.txt                      |   2 +-
 run_test_si.py                        |  11 ++
 spacy/lang/si/lex_attrs.py            | 106 ++++++++++++-------
 spacy/tests/conftest.py               |   8 ++
 spacy/tests/lang/si/__init__.py       |   0
 spacy/tests/lang/si/test_text.py      |  69 ++++++++++++
 spacy/tests/lang/si/test_tokenizer.py |  23 ++++
 spacy/tests/package/test.cfg          | 147 ++++++++++++++++++++++++++
 spacy/tests/package/test.toml         |  74 +++++++++++++
 spacy/tests/package/test.txt          |  37 +++++++
 11 files changed, 438 insertions(+), 42 deletions(-)
 create mode 100644 git_info.py
 create mode 100644 run_test_si.py
 create mode 100644 spacy/tests/lang/si/__init__.py
 create mode 100644 spacy/tests/lang/si/test_text.py
 create mode 100644 spacy/tests/lang/si/test_tokenizer.py
 create mode 100644 spacy/tests/package/test.cfg
 create mode 100644 spacy/tests/package/test.toml
 create mode 100644 spacy/tests/package/test.txt

diff --git a/git_info.py b/git_info.py
new file mode 100644
index 00000000000..373b9f10599
--- /dev/null
+++ b/git_info.py
@@ -0,0 +1,3 @@
+# THIS FILE IS GENERATED FROM SPACY SETUP.PY
+#
+GIT_VERSION = "Unknown"
diff --git a/requirements.txt b/requirements.txt
index 50c6382bea3..a36209c4b25 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -34,4 +34,4 @@ types-requests
 types-setuptools>=57.0.0
 ruff>=0.9.0
 cython-lint>=0.15.0
-confection>=1.1.0,<2.0.0
+confection>=1.3.2,<2.0.0
diff --git a/run_test_si.py b/run_test_si.py
new file mode 100644
index 00000000000..81c8969207b
--- /dev/null
+++ b/run_test_si.py
@@ -0,0 +1,11 @@
+import spacy
+
+nlp = spacy.blank("si")
+
+text = "එහි අරමුණු කිහිපයකි. ඒවා අතර;"
+doc = nlp(text)
+
+print(f"Total tokens: {len(doc)}")
+print()
+for i, token in enumerate(doc):
+    print(f"{i+1:>3}  {token.text}")
\ No newline at end of file
diff --git a/spacy/lang/si/lex_attrs.py b/spacy/lang/si/lex_attrs.py
index aa061852d07..092f83b4710 100644
--- a/spacy/lang/si/lex_attrs.py
+++ b/spacy/lang/si/lex_attrs.py
@@ -2,48 +2,55 @@
 
 _num_words = [
     "බින්දුව",
-    "බිංදුව",
-    "එක",
-    "දෙක",
-    "තුන",
-    "හතර",
-    "පහ",
-    "හය",
-    "හත",
-    "අට",
-    "නවය",
-    "නමය",
-    "දහය",
-    "එකොළහ",
-    "දොළහ",
-    "දහතුන",
-    "දහහතර",
-    "දාහතර",
-    "පහළව",
-    "පහළොව",
-    "දහසය",
-    "දහහත",
-    "දාහත",
-    "දහඅට",
-    "දහනවය",
-    "විස්ස",
-    "තිහ",
-    "හතළිහ",
-    "පනහ",
-    "හැට",
-    "හැත්තෑව",
-    "අසූව",
-    "අනූව",
-    "සියය",
-    "දහස",
-    "දාහ",
-    "ලක්ෂය",
-    "මිලියනය",
-    "කෝටිය",
-    "බිලියනය",
-    "ට්‍රිලියනය",
-]
+    "බිංදුව","එක","දෙක","තුන","හතර","පහ","හය","හත","අට","නවය","නමය","දහය",
+    "එකොළහ","දොළහ","දහතුන","දහහතර","දාහතර","පහළව","පහළොව","දහසය","දහහත","දාහත","දහඅට","දහනවය",
+    "විස්ස","තිහ","හතළිහ","පනහ","හැට","හැත්තෑව","අසූව","අනූව","සියය","සියවෙනි"
+    "දහස","දාහ","ලක්ෂය","මිලියනය","කෝටිය","බිලියනය","ට්‍රිලියනය",
+    ]
 
+_ordinal_words = [
+    "පළමු",        # first
+    "දෙවන",        # second
+    "තෙවන","තුන්වන",        # third
+    "සතරවන",       # fourth
+    "පස්වන",       # fifth
+    "හයවන",        # sixth
+    "හත්වන",       # seventh
+    "අටවන",        # eighth
+    "නවවන",        # ninth
+    "දහවන",        # tenth
+    "එකොළොස්වන",   # eleventh
+    "දොළොස්වන",    # twelfth
+    "දහතුන්වන",    # thirteenth
+    "දහහතරවන",     # fourteenth
+    "පහලොස්වන",     # fifteenth
+    "දහසයවන",      # sixteenth
+    "දහහත්වන",     # seventeenth
+    "දහඅටවන",      # eighteenth
+    "දහනවවන",      # nineteenth
+    "විසිවන",       # twentieth
+    "තිස්වන",       # thirtieth
+    "හතළිස්වන",    # fortieth
+    "පනස්වන",      # fiftieth
+    "හැටවන",       # sixtieth
+    "හැත්තෑවන",    # seventieth
+    "අසූවන",       # eightieth
+    "අනූවන",       # ninetieth
+    "සියවන",       # hundredth
+    "දහස්වන",      # thousandth
+    "මිලියනවන",   # millionth
+    "බිලියනවන",   # billionth
+    "ට්‍රිලියනවන",    # trillionth
+    "ක්වාඩ්‍රිලියන්වන", # quadrillionth
+    "ක්වින්ටිලියන්වන",  # quintillionth
+    "සෙක්ස්ටිලියන්වන",  # sextillionth
+    "සෙප්ටිලියන්වන",    # septillionth
+    "ඔක්ටිලියන්වන",     # octillionth
+    "නොනිලියන්වන",      # nonillionth
+    "ඩෙසිලියන්වන",      # decillionth
+    "ගජිලියන්වන",       # gajillionth  (informal/made-up)
+    "බසිලියන්වන",       # bazillionth  (informal/made-up)
+]
 
 def like_num(text):
     text = text.replace(",", "").replace(".", "")
@@ -55,7 +62,24 @@ def like_num(text):
             return True
     if text.lower() in _num_words:
         return True
+    # Sinhala ordinal suffix check — no .lower() needed
+    if text in _ordinal_words:
+        return True
+    # "23 වෙනි" / "100 වන" — with space
+    parts = text.split()
+    if len(parts) == 2 and parts[0].isdigit() and parts[1] in ("වන", "වෙනි"):
+        return True
+    # "තුන්වන", "සියවන" — suffix attached
+    if text.endswith("වෙනි"):
+        stem = text[:-4]
+        if stem.isdigit() or stem in _num_words:
+            return True
+    if text.endswith("වන"):
+        stem = text[:-2]
+        if stem.isdigit() or stem in _num_words:
+            return True
     return False
 
 
+
 LEX_ATTRS = {LIKE_NUM: like_num}
diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py
index ae5255c287b..b6cf0a22462 100644
--- a/spacy/tests/conftest.py
+++ b/spacy/tests/conftest.py
@@ -401,6 +401,14 @@ def sl_tokenizer():
 def sr_tokenizer():
     return get_lang_class("sr")().tokenizer
 
+@pytest.fixture(scope="session")
+def si_tokenizer():
+    return get_lang_class("si")().tokenizer
+
+
+@pytest.fixture(scope="session")
+def si_vocab():
+    return get_lang_class("si")().vocab
 
 @pytest.fixture(scope="session")
 def sq_tokenizer():
diff --git a/spacy/tests/lang/si/__init__.py b/spacy/tests/lang/si/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/spacy/tests/lang/si/test_text.py b/spacy/tests/lang/si/test_text.py
new file mode 100644
index 00000000000..d1850ece0d9
--- /dev/null
+++ b/spacy/tests/lang/si/test_text.py
@@ -0,0 +1,69 @@
+import pytest
+
+from spacy.lang.si.lex_attrs import like_num
+
+# note: this text taken from https://www.bbc.com/sinhala/articles/cgmpy0kpljno
+def test_si_tokenizer_handles_long_text(si_tokenizer):
+    text = """දිනය 2025 නොවැම්බර් 27 වන දා යි.
+
+එදින මහනුවර සිට නාවලපිටිය බලා ධාවනය වන මගී දුම්රිය පස්වරු 2.06ට පමණ මහනුවර දුම්රිය ස්ථානයෙන් තම දුම්රිය ගමන ආරම්භ කර තිබුණේ, 
+දැඩි වර්ෂාව මධ්‍යයේ ය.මැදිරි හතරකින් සමන්විත මෙම දුම්රිය කෙටිදුර ධාවනයේ නිරත වන මන්දගාමී දුම්රියකි.
+එදින මෙම දුම්රිය ගමනාන්තය කරා ගෙන යාමේ කාර්යය භාර වී තිබුණේ, විශේෂ පන්ති දුම්රිය රියැදුරෙකු වු ජයම්පති මඩිගසේකරට ය.
+
+1982 වසරේ දුම්රිය සේවයට එක්වූ ජයම්පති මඩිගසේකර දැනට විශ්‍රාම ගොස් වසර 6කි."""
+    tokens = si_tokenizer(text)
+    assert len(tokens) == 83
+
+
+@pytest.mark.parametrize(
+    "text,length",
+    [
+        ("""හැන්දෑවේ 4 - 5ට විතර හොඳට ම වැස්සා මගේ ජීවිතේට ම දැකල නැති වැස්සක්.""", 15),
+        ("ඩොලරයේ අගය ඉහළ ගියේ ඇයි ?", 6),
+        ("මහනුවර සිට නාවලපිටිය", 3),
+        ("ශ්‍රී ලාංකිකයන් බොහෝ දෙනෙකු සිංහල අලුත් අවුරුද්ද සැමරීමට සූදානම්.", 10),
+        ("සිසුන් 110,000කට පමණ වෘත්තීය අධ්‍යාපනය ලබා දීම", 7),
+        ("එහෙමද? මම එහෙම කීවේ නැ!", 7),
+        ("එහි අරමුණු කිහිපයකි. ඒවා අතර;", 7),
+    ],
+)
+def test_si_tokenizer_handles_cnts(si_tokenizer, text, length):
+    tokens = si_tokenizer(text)
+    assert len(tokens) == length
+
+
+@pytest.mark.parametrize(
+    "text,match",
+    [
+        ("10", True),
+        ("1", True),
+        ("10,000", True),
+        ("1,000", True),
+        ("999.0", True),
+        ("එක", True),
+        ("දෙක", True),
+        ("බිලියනය", True),
+        ("බල්ලා", False),
+        (",", False),
+        ("1/2", True),
+        ("අශේන්", False),
+        ("වැලිගල්ල", False),
+    ],
+)
+def test_lex_attrs_like_number(si_tokenizer, text, match):
+    tokens = si_tokenizer(text)
+    assert len(tokens) == 1
+    assert tokens[0].like_num == match
+
+
+@pytest.mark.parametrize(
+    "word", ["තෙවන", "මිලියනවන", "100වන", "සියවන", "23වෙනි", "52වෙනි"]
+)
+def test_si_lex_attrs_like_number_for_ordinal(word):
+    assert like_num(word)
+
+
+@pytest.mark.parametrize("word", ["එකොළොස්වන"])
+def test_si_lex_attrs_capitals(word):
+    assert like_num(word)
+    assert like_num(word.upper())
diff --git a/spacy/tests/lang/si/test_tokenizer.py b/spacy/tests/lang/si/test_tokenizer.py
new file mode 100644
index 00000000000..2c10da7a982
--- /dev/null
+++ b/spacy/tests/lang/si/test_tokenizer.py
@@ -0,0 +1,23 @@
+import pytest
+
+SI_TOKEN_EXCEPTION_TESTS = [
+    (
+        "ශ්‍රී ලංකා හමුදාව නිර්භීතව ත්‍රස්තවාදීන් පරාජය කලහ.",
+        ["ශ්‍රී", "ලංකා", "හමුදාව", "නිර්භීතව", "ත්‍රස්තවාදීන්", "පරාජය", "කලහ","."],
+    ),
+    (
+        "සමන්, කරුණාකරලා 10වෙනි පිටුව පෙරලලා කියවන්න.",
+        ["සමන්",",", "කරුණාකරලා", "10වෙනි", "පිටුව", "පෙරලලා", "කියවන්න", "."],
+    ),
+    (
+        "දෙවන විමලධර්මසූරිය රජුගේ කාලයේ බුද්ධාගම ප්‍රචලිත කලේය.",
+        ["දෙවන", "විමලධර්මසූරිය", "රජුගේ", "කාලයේ", "බුද්ධාගම", "ප්‍රචලිත", "කලේය","."],
+    ),
+]
+
+
+@pytest.mark.parametrize("text,expected_tokens", SI_TOKEN_EXCEPTION_TESTS)
+def test_si_tokenizer_handles_exception_cases(si_tokenizer, text, expected_tokens):
+    tokens = si_tokenizer(text)
+    token_list = [token.text for token in tokens if not token.is_space]
+    assert token_list == expected_tokens
diff --git a/spacy/tests/package/test.cfg b/spacy/tests/package/test.cfg
new file mode 100644
index 00000000000..7f9b200caed
--- /dev/null
+++ b/spacy/tests/package/test.cfg
@@ -0,0 +1,147 @@
+[metadata]
+description = Industrial-strength Natural Language Processing (NLP) in Python
+url = https://spacy.io
+author = Explosion
+author_email = contact@explosion.ai
+license = MIT
+long_description = file: README.md
+long_description_content_type = text/markdown
+classifiers =
+    Development Status :: 5 - Production/Stable
+    Environment :: Console
+    Intended Audience :: Developers
+    Intended Audience :: Science/Research
+    License :: OSI Approved :: MIT License
+    Operating System :: POSIX :: Linux
+    Operating System :: MacOS :: MacOS X
+    Operating System :: Microsoft :: Windows
+    Programming Language :: Cython
+    Programming Language :: Python :: 3
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
+    Programming Language :: Python :: 3.11
+    Programming Language :: Python :: 3.12
+    Programming Language :: Python :: 3.13
+    Programming Language :: Python :: 3.14
+    Topic :: Scientific/Engineering
+project_urls =
+    Release notes = https://github.com/explosion/spaCy/releases
+    Source = https://github.com/explosion/spaCy
+
+[options]
+zip_safe = false
+include_package_data = true
+python_requires = >=3.9,<3.15
+# NOTE: This section is superseded by pyproject.toml and will be removed in
+# spaCy v4
+setup_requires =
+    cython>=3.0,<4.0
+    numpy>=2.0.0,<3.0.0; python_version < "3.9"
+    numpy>=2.0.0,<3.0.0; python_version >= "3.9"
+    # We also need our Cython packages here to compile against
+    cymem>=2.0.2,<2.1.0
+    preshed>=3.0.2,<3.1.0
+    murmurhash>=0.28.0,<1.1.0
+    thinc>=8.3.12,<8.4.0
+install_requires =
+    # Our libraries
+    spacy-legacy>=3.0.11,<3.1.0
+    spacy-loggers>=1.0.0,<2.0.0
+    murmurhash>=0.28.0,<1.1.0
+    cymem>=2.0.2,<2.1.0
+    preshed>=3.0.2,<3.1.0
+    thinc>=8.3.12,<8.4.0
+    wasabi>=0.9.1,<1.2.0
+    srsly>=2.5.3,<3.0.0
+    catalogue>=2.0.6,<2.1.0
+    weasel>=1.0.0,<2.0.0
+    confection>=1.3.2,<2.0.0
+    # Third-party dependencies
+    typer>=0.3.0,<1.0.0
+    tqdm>=4.38.0,<5.0.0
+    numpy>=1.15.0; python_version < "3.9"
+    numpy>=1.19.0; python_version >= "3.9"
+    requests>=2.13.0,<3.0.0
+    pydantic>=2.0.0,<3.0.0
+    jinja2
+    # Official Python utilities
+    setuptools
+    packaging>=20.0
+
+[options.entry_points]
+console_scripts =
+    spacy = spacy.cli:setup_cli
+
+[options.extras_require]
+lookups =
+    spacy_lookups_data>=1.0.3,<1.1.0
+transformers =
+    spacy_transformers>=1.1.2,<1.4.0
+cuda =
+    cupy>=5.0.0b4,<13.0.0
+cuda80 =
+    cupy-cuda80>=5.0.0b4,<13.0.0
+cuda90 =
+    cupy-cuda90>=5.0.0b4,<13.0.0
+cuda91 =
+    cupy-cuda91>=5.0.0b4,<13.0.0
+cuda92 =
+    cupy-cuda92>=5.0.0b4,<13.0.0
+cuda100 =
+    cupy-cuda100>=5.0.0b4,<13.0.0
+cuda101 =
+    cupy-cuda101>=5.0.0b4,<13.0.0
+cuda102 =
+    cupy-cuda102>=5.0.0b4,<13.0.0
+cuda110 =
+    cupy-cuda110>=5.0.0b4,<13.0.0
+cuda111 =
+    cupy-cuda111>=5.0.0b4,<13.0.0
+cuda112 =
+    cupy-cuda112>=5.0.0b4,<13.0.0
+cuda113 =
+    cupy-cuda113>=5.0.0b4,<13.0.0
+cuda114 =
+    cupy-cuda114>=5.0.0b4,<13.0.0
+cuda115 =
+    cupy-cuda115>=5.0.0b4,<13.0.0
+cuda116 =
+    cupy-cuda116>=5.0.0b4,<13.0.0
+cuda117 =
+    cupy-cuda117>=5.0.0b4,<13.0.0
+cuda11x =
+    cupy-cuda11x>=11.0.0,<13.0.0
+cuda12x =
+    cupy-cuda12x>=11.5.0,<13.0.0
+cuda-autodetect =
+    cupy-wheel>=11.0.0,<13.0.0
+apple =
+    thinc-apple-ops>=1.0.0,<2.0.0
+# Language tokenizers with external dependencies
+ja =
+    sudachipy>=0.5.2,!=0.6.1
+    sudachidict_core>=20211220
+ko =
+    natto-py>=0.9.0
+th =
+    pythainlp>=2.0
+
+[bdist_wheel]
+universal = false
+
+[sdist]
+formats = gztar
+
+[tool:pytest]
+markers =
+    slow: mark a test as slow
+    issue: reference specific issue
+filterwarnings =
+    error
+    ignore:Core Pydantic V1:UserWarning:pydantic
+
+[mypy]
+ignore_missing_imports = True
+no_implicit_optional = True
+plugins = pydantic.mypy, thinc.mypy
+allow_redefinition = True
diff --git a/spacy/tests/package/test.toml b/spacy/tests/package/test.toml
new file mode 100644
index 00000000000..395c2f7a108
--- /dev/null
+++ b/spacy/tests/package/test.toml
@@ -0,0 +1,74 @@
+[build-system]
+requires = [
+    "setuptools",
+    "cython>=3.0,<4.0",
+    "cymem>=2.0.2,<2.1.0",
+    "preshed>=3.0.2,<3.1.0",
+    "murmurhash>=0.28.0,<1.1.0",
+    "thinc>=8.3.12,<8.4.0",
+    "numpy>=2.0.0,<3.0.0"
+]
+build-backend = "setuptools.build_meta"
+
+[tool.cibuildwheel]
+build = "*"
+skip = "cp39* *-win32 *i686* cp3??t-* *cp310-win_arm64"
+test-skip = ""
+
+archs = ["native"]
+
+build-frontend = "default"
+config-settings = {}
+dependency-versions = "pinned"
+environment = { PIP_CONSTRAINT = "build-constraints.txt" }
+
+environment-pass = []
+build-verbosity = 0
+
+before-all = "curl https://sh.rustup.rs -sSf | sh -s -- -y --profile minimal --default-toolchain stable"
+before-build = "pip install -r requirements.txt && python setup.py clean"
+repair-wheel-command = ""
+
+test-command = ""
+before-test = ""
+test-requires = []
+test-extras = []
+
+container-engine = "docker"
+
+manylinux-x86_64-image = "manylinux2014"
+manylinux-i686-image = "manylinux2014"
+manylinux-aarch64-image = "manylinux2014"
+manylinux-ppc64le-image = "manylinux2014"
+manylinux-s390x-image = "manylinux2014"
+manylinux-pypy_x86_64-image = "manylinux2014"
+manylinux-pypy_i686-image = "manylinux2014"
+manylinux-pypy_aarch64-image = "manylinux2014"
+
+musllinux-x86_64-image = "musllinux_1_2"
+musllinux-i686-image = "musllinux_1_2"
+musllinux-aarch64-image = "musllinux_1_2"
+musllinux-ppc64le-image = "musllinux_1_2"
+musllinux-s390x-image = "musllinux_1_2"
+
+[tool.cibuildwheel.linux]
+repair-wheel-command = "auditwheel repair -w {dest_dir} {wheel}"
+
+[tool.cibuildwheel.macos]
+repair-wheel-command = "delocate-wheel --require-archs {delocate_archs} -w {dest_dir} -v {wheel}"
+
+[tool.cibuildwheel.windows]
+
+[tool.cibuildwheel.pyodide]
+
+
+[tool.ruff]
+line-length = 88
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "C", "B", "B9"]
+ignore = ["E203", "E266", "E501", "E731", "E741", "F541"]
+
+[tool.ruff.lint.isort]
+combine-as-imports = true
+split-on-trailing-comma = true
diff --git a/spacy/tests/package/test.txt b/spacy/tests/package/test.txt
new file mode 100644
index 00000000000..a36209c4b25
--- /dev/null
+++ b/spacy/tests/package/test.txt
@@ -0,0 +1,37 @@
+# Our libraries
+spacy-legacy>=3.0.11,<3.1.0
+spacy-loggers>=1.0.0,<2.0.0
+cymem>=2.0.2,<2.1.0
+preshed>=3.0.2,<3.1.0
+thinc>=8.3.12,<8.4.0
+ml_datasets>=0.2.1,<0.3.0
+murmurhash>=0.28.0,<1.1.0
+wasabi>=0.9.1,<1.2.0
+srsly>=2.5.3,<3.0.0
+catalogue>=2.0.6,<2.1.0
+typer>=0.3.0,<1.0.0
+weasel>=1.0.0,<2.0.0
+# Third party dependencies
+numpy>=2.0.0,<3.0.0
+requests>=2.13.0,<3.0.0
+tqdm>=4.38.0,<5.0.0
+pydantic>=2.0.0,<3.0.0
+jinja2
+# Official Python utilities
+setuptools
+packaging>=20.0
+# Development dependencies
+pre-commit>=2.13.0
+cython>=3.0,<4.0
+pytest>=5.2.0,!=7.1.0
+pytest-timeout>=1.3.0,<2.0.0
+mock>=2.0.0,<3.0.0
+hypothesis>=3.27.0,<7.0.0
+mypy>=1.5.0,<1.6.0; platform_machine != "aarch64" and python_version >= "3.8"
+types-mock>=0.1.1
+types-setuptools>=57.0.0
+types-requests
+types-setuptools>=57.0.0
+ruff>=0.9.0
+cython-lint>=0.15.0
+confection>=1.3.2,<2.0.0