Merge branch 'master' into python-Levenshtein-name

.github/workflows/main.yml

@@ -0,0 +1,77 @@
+name: main
+
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - uses: arduino/setup-task@v1
+        with:
+          repo-token: ${{ github.token }}
+      - run: task lint
+
+  pytest-pure:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          # - "3.12.0-rc.1"
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - uses: arduino/setup-task@v1
+        with:
+          repo-token: ${{ github.token }}
+      - run: task pytest-pure
+
+  # pytest-external:
+  #   runs-on: ubuntu-latest
+  #   strategy:
+  #     fail-fast: false
+  #     matrix:
+  #       python-version:
+  #         - "3.8"
+  #         - "3.9"
+  #         - "3.10"
+  #         - "3.11"
+  #         # - "3.12.0-rc.1"
+  #   steps:
+  #     - uses: actions/checkout@v3
+  #     - uses: actions/setup-python@v4
+  #       with:
+  #         python-version: ${{ matrix.python-version }}
+  #     - uses: arduino/setup-task@v1
+  #       with:
+  #         repo-token: ${{ github.token }}
+  #     - run: task pytest-external
+
+  markdownlint-cli:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: nosborn/[email protected]
+        with:
+          files: .
+          config_file: .markdownlint.yaml
+          dot: true

.markdownlint.yaml

@@ -0,0 +1,8 @@
+# https://github.com/DavidAnson/markdownlint/blob/main/schema/.markdownlint.yaml
+default: true   # enable all by default
+MD007:          # unordered list indentation
+  indent: 2
+MD013: false    # do not validate line length
+MD014: false    # allow $ before command output
+MD029:          # ordered list prefix
+  style: "one"

README.md

@@ -148,23 +148,23 @@ pip install -e ".[benchmark]"
 All algorithms have 2 interfaces:
 
 1. Class with algorithm-specific params for customizing.
-2. Class instance with default params for quick and simple usage.
+1. Class instance with default params for quick and simple usage.
 
 All algorithms have some common methods:
 
 1. `.distance(*sequences)` -- calculate distance between sequences.
-2. `.similarity(*sequences)` -- calculate similarity for sequences.
-3. `.maximum(*sequences)` -- maximum possible value for distance and similarity. For any sequence: `distance + similarity == maximum`.
-4. `.normalized_distance(*sequences)` -- normalized distance between sequences. The return value is a float between 0 and 1, where 0 means equal, and 1 totally different.
-5. `.normalized_similarity(*sequences)` -- normalized similarity for sequences. The return value is a float between 0 and 1, where 0 means totally different, and 1 equal.
+1. `.similarity(*sequences)` -- calculate similarity for sequences.
+1. `.maximum(*sequences)` -- maximum possible value for distance and similarity. For any sequence: `distance + similarity == maximum`.
+1. `.normalized_distance(*sequences)` -- normalized distance between sequences. The return value is a float between 0 and 1, where 0 means equal, and 1 totally different.
+1. `.normalized_similarity(*sequences)` -- normalized similarity for sequences. The return value is a float between 0 and 1, where 0 means totally different, and 1 equal.
 
 Most common init arguments:
 
 1. `qval` -- q-value for split sequences into q-grams. Possible values:
     - 1 (default) -- compare sequences by chars.
     - 2 or more -- transform sequences to q-grams.
     - None -- split sequences by words.
-2. `as_set` -- for token-based algorithms:
+1. `as_set` -- for token-based algorithms:
     - True -- `t` and `ttt` is equal.
     - False (default) -- `t` and `ttt` is different.
 

Taskfile.yml

@@ -48,19 +48,18 @@ tasks:
     cmds:
       - "{{.LINT_ENV}}/bin/twine upload dist/textdistance-*"
 
-  flake8:run:
+  flake8:
     deps:
       - lint:install
     cmds:
       - "{{.LINT_ENV}}/bin/flake8 ."
-  mypy:run:
+  mypy:
     deps:
       - lint:install
     cmds:
       - "{{.LINT_ENV}}/bin/mypy"
 
-
-  pytest-pure:run:
+  pytest-pure:
     deps:
       - task: pip:install
         vars:
@@ -69,7 +68,7 @@ tasks:
     cmds:
       - "{{.TEST_PURE_ENV}}/bin/pytest  -m 'not external' {{.CLI_ARGS}}"
 
-  pytest-external:run:
+  pytest-external:
     deps:
       - task: pip:install
         vars:
@@ -78,12 +77,18 @@ tasks:
     cmds:
       - "{{.TEST_EXT_ENV}}/bin/pytest {{.CLI_ARGS}}"
 
-  isort:run:
+  isort:
     deps:
       - lint:install
     cmds:
       - "{{.LINT_ENV}}/bin/isort ."
 
+  isort:check:
+    deps:
+      - lint:install
+    cmds:
+      - "{{.LINT_ENV}}/bin/isort --check ."
+
   benchmark:
     deps:
       - task: pip:install
@@ -92,3 +97,26 @@ tasks:
           EXTRA: benchmark
     cmds:
       - "{{.BENCHMARK_ENV}}/bin/python3 -m textdistance.benchmark"
+
+  # groups
+  format:
+    desc: "run all code formatters"
+    cmds:
+      - task: isort
+  lint:
+    desc: "run all linters"
+    cmds:
+      - task: flake8
+      # - task: mypy
+      - task: isort:check
+  test:
+    desc: "run all tests"
+    cmds:
+      - task: pytest-pure
+      - task: pytest-external
+  all:
+    desc: "run all code formatters, linters, and tests"
+    cmds:
+      - task: format
+      - task: lint
+      - task: test

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 description_file = README.md
-license_file = LICENSE
+license_files = LICENSE
 
 [flake8]
 max-line-length=120

tests/test_edit/test_damerau_levenshtein.py

@@ -4,6 +4,7 @@
 # project
 import textdistance
 
+
 ALG = textdistance.DamerauLevenshtein
 
 COMMON = [

textdistance/algorithms/base.py

@@ -1,4 +1,5 @@
 from __future__ import annotations
+
 # built-in
 from collections import Counter
 from contextlib import suppress

textdistance/algorithms/compression_based.py

@@ -1,4 +1,5 @@
 from __future__ import annotations
+
 # built-in
 import codecs
 import math
@@ -12,6 +13,7 @@
 
 
 try:
+    # built-in
     import lzma
 except ImportError:
     lzma = None  # type: ignore[assignment]

textdistance/algorithms/edit_based.py

@@ -1,15 +1,17 @@
 from __future__ import annotations
+
 # built-in
 from collections import defaultdict
 from itertools import zip_longest
 from typing import Any, Sequence, TypeVar
 
 # app
 from .base import Base as _Base, BaseSimilarity as _BaseSimilarity
-from .types import TestFunc, SimFunc
+from .types import SimFunc, TestFunc
 
 
 try:
+    # external
     import numpy
 except ImportError:
     numpy = None  # type: ignore[assignment]

textdistance/algorithms/phonetic.py

@@ -1,15 +1,16 @@
 from __future__ import annotations
+
 # built-in
 from collections import defaultdict
-from itertools import groupby
+from itertools import groupby, zip_longest
+from typing import Any, Iterator, Sequence, TypeVar
 
 # app
 from .base import Base as _Base, BaseSimilarity as _BaseSimilarity
 
 
-from itertools import zip_longest
-from typing import Any, Iterator, Sequence, TypeVar
 try:
+    # external
     import numpy
 except ImportError:
     numpy = None  # type: ignore[assignment]

textdistance/algorithms/sequence_based.py

@@ -1,4 +1,5 @@
 from __future__ import annotations
+
 # built-in
 from difflib import SequenceMatcher as _SequenceMatcher
 from typing import Any
@@ -8,9 +9,12 @@
 from .base import BaseSimilarity as _BaseSimilarity
 from .types import TestFunc
 
+
 try:
+    # external
     import numpy
 except ImportError:
+    # built-in
     from array import array
     numpy = None  # type: ignore[assignment]
 

textdistance/algorithms/simple.py

@@ -1,4 +1,5 @@
 from __future__ import annotations
+
 # built-in
 from itertools import takewhile
 from typing import Sequence
@@ -7,6 +8,7 @@
 from .base import Base as _Base, BaseSimilarity as _BaseSimilarity
 from .types import SimFunc
 
+
 __all__ = [
     'Prefix', 'Postfix', 'Length', 'Identity', 'Matrix',
     'prefix', 'postfix', 'length', 'identity', 'matrix',

textdistance/algorithms/token_based.py

@@ -1,4 +1,5 @@
 from __future__ import annotations
+
 # built-in
 from functools import reduce
 from itertools import islice, permutations, repeat

textdistance/algorithms/types.py

@@ -1,4 +1,5 @@
 
+# built-in
 from typing import Callable, Optional, TypeVar
 
 

textdistance/algorithms/vector_based.py

@@ -3,13 +3,14 @@
 """
 # built-in
 from functools import reduce
+from typing import Any
 
 # app
 from .base import Base as _Base, BaseSimilarity as _BaseSimilarity
 
 
-from typing import Any
 try:
+    # external
     import numpy
 except ImportError:
     numpy = None  # type: ignore[assignment]

textdistance/benchmark.py

@@ -1,8 +1,9 @@
 from __future__ import annotations
+
 # built-in
 import json
-from collections import defaultdict
 import math
+from collections import defaultdict
 from timeit import timeit
 from typing import Iterable, Iterator, NamedTuple