From ae979671706c36c3f12294afe85a1d0bfb41e637 Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel@debian.org>
Date: Wed, 12 Feb 2025 21:44:30 +0100
Subject: [PATCH] Merging upstream version 2.1.0.

Signed-off-by: Daniel Baumann <daniel@debian.org>
---
 .pre-commit-config.yaml     | 29 +++++++-----
 README.md                   |  6 +--
 bin/vendor-licenses         | 12 ++---
 identify/cli.py             |  8 ++--
 identify/extensions.py      |  6 +--
 identify/identify.py        | 89 +++++++++++++++++++++----------------
 identify/interpreters.py    |  4 --
 identify/vendor/licenses.py |  3 --
 setup.cfg                   | 27 ++++++++---
 setup.py                    |  4 --
 tests/cli_test.py           |  4 --
 tests/extensions_test.py    |  4 --
 tests/identify_test.py      | 38 +++++++++++++---
 tox.ini                     |  2 +-
 14 files changed, 132 insertions(+), 104 deletions(-)

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index c3381ff..a1dc351 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -2,22 +2,24 @@ repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v3.4.0
     hooks:
-    -   id: trailing-whitespace
-    -   id: end-of-file-fixer
     -   id: check-docstring-first
-    -   id: check-merge-conflict
     -   id: check-yaml
     -   id: debug-statements
     -   id: double-quote-string-fixer
+    -   id: end-of-file-fixer
     -   id: name-tests-test
-    -   id: check-added-large-files
-    -   id: check-byte-order-marker
-    -   id: fix-encoding-pragma
+    -   id: requirements-txt-fixer
+    -   id: trailing-whitespace
+-   repo: https://github.com/asottile/setup-cfg-fmt
+    rev: v1.16.0
+    hooks:
+    -   id: setup-cfg-fmt
 -   repo: https://gitlab.com/pycqa/flake8
     rev: 3.8.4
     hooks:
     -   id: flake8
         exclude: ^identify/vendor/licenses\.py$
+        additional_dependencies: [flake8-typing-imports==1.10.1]
 -   repo: https://github.com/pre-commit/mirrors-autopep8
     rev: v1.5.4
     hooks:
@@ -26,11 +28,18 @@ repos:
     rev: v2.4.0
     hooks:
     -   id: reorder-python-imports
-        args: [
-            '--add-import', 'from __future__ import absolute_import',
-            '--add-import', 'from __future__ import unicode_literals',
-        ]
+        args: [--py3-plus]
 -   repo: https://github.com/asottile/add-trailing-comma
     rev: v2.1.0
     hooks:
     -   id: add-trailing-comma
+        args: [--py36-plus]
+-   repo: https://github.com/asottile/pyupgrade
+    rev: v2.10.0
+    hooks:
+    -   id: pyupgrade
+        args: [--py36-plus]
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.812
+    hooks:
+    -   id: mypy
diff --git a/README.md b/README.md
index accf29b..788b7c4 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,7 @@ If you have an actual file on disk, you can get the most information possible
 
 When using a file on disk, the checks performed are:
 
-* File type (file, symlink, directory)
+* File type (file, symlink, directory, socket)
 * Mode (is it executable?)
 * File name (mostly based on extension)
 * If executable, the shebang is read and the interpreter interpreted
@@ -76,11 +76,11 @@ optional arguments:
   --filename-only
 ```
 
-```bash
+```console
 $ identify-cli setup.py; echo $?
 ["file", "non-executable", "python", "text"]
 0
-identify setup.py --filename-only; echo $?
+$ identify setup.py --filename-only; echo $?
 ["python", "text"]
 0
 $ identify-cli wat.wat; echo $?
diff --git a/bin/vendor-licenses b/bin/vendor-licenses
index 83c0c4e..2dbde36 100755
--- a/bin/vendor-licenses
+++ b/bin/vendor-licenses
@@ -1,19 +1,15 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 """Usage:
 
     ./bin/vendor-licenses > identify/vendor/licenses.py
 """
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 import argparse
 import os.path
 import subprocess
 import tempfile
 
 
-def main():
+def main() -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument('--revision', default='HEAD')
     args = parser.parse_args()
@@ -45,18 +41,16 @@ def main():
 
             licenses.append((spdx, license_text))
 
-        print('# -*- coding: utf-8 -*-')
-        print('from __future__ import absolute_import')
-        print('from __future__ import unicode_literals')
         print('LICENSES = (')
         for spdx, text in sorted(licenses):
             print('    (')
-            print('        {!r},'.format(spdx))
+            print(f'        {spdx!r},')
             print("        '''\\")
             print(text.replace('\t', '    ').replace(' \n', '').strip())
             print("''',")
             print('    ),')
         print(')')
+    return 0
 
 
 if __name__ == '__main__':
diff --git a/identify/cli.py b/identify/cli.py
index 511caf6..28e6155 100644
--- a/identify/cli.py
+++ b/identify/cli.py
@@ -1,14 +1,12 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 import argparse
 import json
+from typing import Optional
+from typing import Sequence
 
 from identify import identify
 
 
-def main(argv=None):
+def main(argv: Optional[Sequence[str]] = None) -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument('--filename-only', action='store_true')
     parser.add_argument('path')
diff --git a/identify/extensions.py b/identify/extensions.py
index 62a7f5b..778b695 100644
--- a/identify/extensions.py
+++ b/identify/extensions.py
@@ -1,13 +1,9 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
-
 EXTENSIONS = {
     'adoc': {'text', 'asciidoc'},
     'asciidoc': {'text', 'asciidoc'},
     'apinotes': {'text', 'apinotes'},
     'asar': {'binary', 'asar'},
+    'avif': {'binary', 'image', 'avif'},
     'bash': {'text', 'shell', 'bash'},
     'bat': {'text', 'batch'},
     'bib': {'text', 'bib'},
diff --git a/identify/identify.py b/identify/identify.py
index 1c0e677..51c1288 100644
--- a/identify/identify.py
+++ b/identify/identify.py
@@ -1,14 +1,14 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import unicode_literals
-
-import io
 import os.path
 import re
 import shlex
+import stat
 import string
 import sys
+from typing import IO
+from typing import List
+from typing import Optional
+from typing import Set
+from typing import Tuple
 
 from identify import extensions
 from identify import interpreters
@@ -19,27 +19,37 @@ printable = frozenset(string.printable)
 
 DIRECTORY = 'directory'
 SYMLINK = 'symlink'
+SOCKET = 'socket'
 FILE = 'file'
 EXECUTABLE = 'executable'
 NON_EXECUTABLE = 'non-executable'
 TEXT = 'text'
 BINARY = 'binary'
 
-ALL_TAGS = {DIRECTORY, SYMLINK, FILE, EXECUTABLE, NON_EXECUTABLE, TEXT, BINARY}
-ALL_TAGS.update(*extensions.EXTENSIONS.values())
-ALL_TAGS.update(*extensions.EXTENSIONS_NEED_BINARY_CHECK.values())
-ALL_TAGS.update(*extensions.NAMES.values())
-ALL_TAGS.update(*interpreters.INTERPRETERS.values())
-ALL_TAGS = frozenset(ALL_TAGS)
+TYPE_TAGS = frozenset((DIRECTORY, FILE, SYMLINK, SOCKET))
+MODE_TAGS = frozenset((EXECUTABLE, NON_EXECUTABLE))
+ENCODING_TAGS = frozenset((BINARY, TEXT))
+_ALL_TAGS = {*TYPE_TAGS, *MODE_TAGS, *ENCODING_TAGS}
+_ALL_TAGS.update(*extensions.EXTENSIONS.values())
+_ALL_TAGS.update(*extensions.EXTENSIONS_NEED_BINARY_CHECK.values())
+_ALL_TAGS.update(*extensions.NAMES.values())
+_ALL_TAGS.update(*interpreters.INTERPRETERS.values())
+ALL_TAGS = frozenset(_ALL_TAGS)
 
 
-def tags_from_path(path):
-    if not os.path.lexists(path):
-        raise ValueError('{} does not exist.'.format(path))
-    if os.path.isdir(path):
+def tags_from_path(path: str) -> Set[str]:
+    try:
+        sr = os.lstat(path)
+    except (OSError, ValueError):  # same error-handling as `os.lexists()`
+        raise ValueError(f'{path} does not exist.')
+
+    mode = sr.st_mode
+    if stat.S_ISDIR(mode):
         return {DIRECTORY}
-    if os.path.islink(path):
+    if stat.S_ISLNK(mode):
         return {SYMLINK}
+    if stat.S_ISSOCK(mode):
+        return {SOCKET}
 
     tags = {FILE}
 
@@ -62,19 +72,19 @@ def tags_from_path(path):
 
     # some extensions can be both binary and text
     # see EXTENSIONS_NEED_BINARY_CHECK
-    if not {TEXT, BINARY} & tags:
+    if not ENCODING_TAGS & tags:
         if file_is_text(path):
             tags.add(TEXT)
         else:
             tags.add(BINARY)
 
-    assert {TEXT, BINARY} & tags, tags
-    assert {EXECUTABLE, NON_EXECUTABLE} & tags, tags
+    assert ENCODING_TAGS & tags, tags
+    assert MODE_TAGS & tags, tags
     return tags
 
 
-def tags_from_filename(filename):
-    _, filename = os.path.split(filename)
+def tags_from_filename(path: str) -> Set[str]:
+    _, filename = os.path.split(path)
     _, ext = os.path.splitext(filename)
 
     ret = set()
@@ -95,7 +105,7 @@ def tags_from_filename(filename):
     return ret
 
 
-def tags_from_interpreter(interpreter):
+def tags_from_interpreter(interpreter: str) -> Set[str]:
     _, _, interpreter = interpreter.rpartition('/')
 
     # Try "python3.5.2" => "python3.5" => "python3" until one matches.
@@ -108,7 +118,7 @@ def tags_from_interpreter(interpreter):
     return set()
 
 
-def is_text(bytesio):
+def is_text(bytesio: IO[bytes]) -> bool:
     """Return whether the first KB of contents seems to be binary.
 
     This is roughly based on libmagic's binary/text detection:
@@ -122,14 +132,14 @@ def is_text(bytesio):
     return not bool(bytesio.read(1024).translate(None, text_chars))
 
 
-def file_is_text(path):
+def file_is_text(path: str) -> bool:
     if not os.path.lexists(path):
-        raise ValueError('{} does not exist.'.format(path))
+        raise ValueError(f'{path} does not exist.')
     with open(path, 'rb') as f:
         return is_text(f)
 
 
-def _shebang_split(line):
+def _shebang_split(line: str) -> List[str]:
     try:
         # shebangs aren't supposed to be quoted, though some tools such as
         # setuptools will write them with quotes so we'll best-guess parse
@@ -141,11 +151,14 @@ def _shebang_split(line):
         return line.split()
 
 
-def _parse_nix_shebang(bytesio, cmd):
+def _parse_nix_shebang(
+        bytesio: IO[bytes],
+        cmd: Tuple[str, ...],
+) -> Tuple[str, ...]:
     while bytesio.read(2) == b'#!':
-        next_line = bytesio.readline()
+        next_line_b = bytesio.readline()
         try:
-            next_line = next_line.decode('UTF-8')
+            next_line = next_line_b.decode('UTF-8')
         except UnicodeDecodeError:
             return cmd
 
@@ -162,13 +175,13 @@ def _parse_nix_shebang(bytesio, cmd):
     return cmd
 
 
-def parse_shebang(bytesio):
+def parse_shebang(bytesio: IO[bytes]) -> Tuple[str, ...]:
     """Parse the shebang from a file opened for reading binary."""
     if bytesio.read(2) != b'#!':
         return ()
-    first_line = bytesio.readline()
+    first_line_b = bytesio.readline()
     try:
-        first_line = first_line.decode('UTF-8')
+        first_line = first_line_b.decode('UTF-8')
     except UnicodeDecodeError:
         return ()
 
@@ -185,10 +198,10 @@ def parse_shebang(bytesio):
     return cmd
 
 
-def parse_shebang_from_file(path):
+def parse_shebang_from_file(path: str) -> Tuple[str, ...]:
     """Parse the shebang given a file path."""
     if not os.path.lexists(path):
-        raise ValueError('{} does not exist.'.format(path))
+        raise ValueError(f'{path} does not exist.')
     if not os.access(path, os.X_OK):
         return ()
 
@@ -200,13 +213,13 @@ COPYRIGHT_RE = re.compile(r'^\s*(Copyright|\(C\)) .*$', re.I | re.MULTILINE)
 WS_RE = re.compile(r'\s+')
 
 
-def _norm_license(s):
+def _norm_license(s: str) -> str:
     s = COPYRIGHT_RE.sub('', s)
     s = WS_RE.sub(' ', s)
     return s.strip()
 
 
-def license_id(filename):
+def license_id(filename: str) -> Optional[str]:
     """Return the spdx id for the license contained in `filename`.  If no
     license is detected, returns `None`.
 
@@ -222,7 +235,7 @@ def license_id(filename):
     """
     import editdistance  # `pip install identify[license]`
 
-    with io.open(filename, encoding='UTF-8') as f:
+    with open(filename, encoding='UTF-8') as f:
         contents = f.read()
 
     norm = _norm_license(contents)
diff --git a/identify/interpreters.py b/identify/interpreters.py
index 7feb4b1..dabf36c 100644
--- a/identify/interpreters.py
+++ b/identify/interpreters.py
@@ -1,7 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 INTERPRETERS = {
     'ash': {'shell', 'ash'},
     'awk': {'awk'},
diff --git a/identify/vendor/licenses.py b/identify/vendor/licenses.py
index 912b5c8..3478d0f 100644
--- a/identify/vendor/licenses.py
+++ b/identify/vendor/licenses.py
@@ -1,6 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
 LICENSES = (
     (
         '0BSD',
diff --git a/setup.cfg b/setup.cfg
index c5dce83..4aafd64 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,6 +1,6 @@
 [metadata]
 name = identify
-version = 1.5.14
+version = 2.1.0
 description = File identification library for Python
 long_description = file: README.md
 long_description_content_type = text/markdown
@@ -11,26 +11,26 @@ license = MIT
 license_file = LICENSE
 classifiers =
     License :: OSI Approved :: MIT License
-    Programming Language :: Python :: 2
-    Programming Language :: Python :: 2.7
     Programming Language :: Python :: 3
-    Programming Language :: Python :: 3.4
-    Programming Language :: Python :: 3.5
+    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 :: Implementation :: CPython
     Programming Language :: Python :: Implementation :: PyPy
 
 [options]
 packages = find:
-python_requires = >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*
+python_requires = >=3.6.1
 
 [options.entry_points]
 console_scripts =
     identify-cli=identify.cli:main
 
 [options.extras_require]
-license = editdistance
+license =
+    editdistance
 
 [options.packages.find]
 exclude =
@@ -42,3 +42,16 @@ universal = True
 
 [coverage:run]
 plugins = covdefaults
+
+[mypy]
+check_untyped_defs = true
+disallow_any_generics = true
+disallow_incomplete_defs = true
+disallow_untyped_defs = true
+no_implicit_optional = true
+
+[mypy-testing.*]
+disallow_untyped_defs = false
+
+[mypy-tests.*]
+disallow_untyped_defs = false
diff --git a/setup.py b/setup.py
index acf1ad4..8bf1ba9 100644
--- a/setup.py
+++ b/setup.py
@@ -1,6 +1,2 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 from setuptools import setup
 setup()
diff --git a/tests/cli_test.py b/tests/cli_test.py
index 9369a5e..94fb8ae 100644
--- a/tests/cli_test.py
+++ b/tests/cli_test.py
@@ -1,7 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 from identify import cli
 
 
diff --git a/tests/extensions_test.py b/tests/extensions_test.py
index 4527a58..c2a828c 100644
--- a/tests/extensions_test.py
+++ b/tests/extensions_test.py
@@ -1,7 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 import pytest
 
 from identify import extensions
diff --git a/tests/identify_test.py b/tests/identify_test.py
index 8e00f60..8cc5856 100644
--- a/tests/identify_test.py
+++ b/tests/identify_test.py
@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-from __future__ import absolute_import
-from __future__ import unicode_literals
-
 import io
 import os
+import socket
 import stat
+from tempfile import TemporaryDirectory
 
 import pytest
 
@@ -14,6 +12,21 @@ from identify import identify
 def test_all_tags_includes_basic_ones():
     assert 'file' in identify.ALL_TAGS
     assert 'directory' in identify.ALL_TAGS
+    assert 'executable' in identify.ALL_TAGS
+    assert 'text' in identify.ALL_TAGS
+    assert 'socket' in identify.ALL_TAGS
+
+
+@pytest.mark.parametrize(
+    'tag_group',
+    (
+        identify.TYPE_TAGS,
+        identify.MODE_TAGS,
+        identify.ENCODING_TAGS,
+    ),
+)
+def test_all_tags_contains_all_groups(tag_group):
+    assert tag_group < identify.ALL_TAGS
 
 
 def test_all_tags_contains_each_type():
@@ -41,6 +54,17 @@ def test_tags_from_path_symlink(tmpdir):
     assert identify.tags_from_path(x.strpath) == {'symlink'}
 
 
+def test_tags_from_path_socket():
+    tmproot = '/tmp'  # short path avoids `OSError: AF_UNIX path too long`
+    with TemporaryDirectory(dir=tmproot) as tmpdir:
+        socket_path = os.path.join(tmpdir, 'socket')
+        with socket.socket(socket.AF_UNIX) as sock:
+            sock.bind(socket_path)
+            tags = identify.tags_from_path(socket_path)
+
+    assert tags == {'socket'}
+
+
 def test_tags_from_path_broken_symlink(tmpdir):
     x = tmpdir.join('foo')
     x.mksymlinkto(tmpdir.join('lol'))
@@ -177,9 +201,9 @@ def test_tags_from_interpreter(interpreter, expected):
     (
         (b'hello world', True),
         (b'', True),
-        ('éóñəå  ⊂(◉‿◉)つ(ノ≥∇≤)ノ'.encode('utf8'), True),
-        (r'¯\_(ツ)_/¯'.encode('utf8'), True),
-        ('♪┏(・o･)┛♪┗ ( ･o･) ┓♪┏ ( ) ┛♪┗ (･o･ ) ┓♪'.encode('utf8'), True),
+        ('éóñəå  ⊂(◉‿◉)つ(ノ≥∇≤)ノ'.encode(), True),
+        (r'¯\_(ツ)_/¯'.encode(), True),
+        ('♪┏(・o･)┛♪┗ ( ･o･) ┓♪┏ ( ) ┛♪┗ (･o･ ) ┓♪'.encode(), True),
         ('éóñå'.encode('latin1'), True),
 
         (b'hello world\x00', False),
diff --git a/tox.ini b/tox.ini
index 2876390..a063c94 100644
--- a/tox.ini
+++ b/tox.ini
@@ -1,5 +1,5 @@
 [tox]
-envlist = py27,py35,py36,pypy,pre-commit
+envlist = py36,pypy3,pre-commit
 
 [testenv]
 deps = -rrequirements-dev.txt