NEW: Example of putting python3 library in lambda layer

examples/lambda-layers/.terraform.lock.hcl

@@ -0,0 +1,37 @@
+# This file is maintained automatically by "tofu init".
+# Manual edits may be lost in future updates.
+
+provider "registry.opentofu.org/hashicorp/archive" {
+  version = "2.5.0"
+  hashes = [
+    "h1:yKfaZ2J55VStfwgrdXX3ApAnWBZlKvOXHlS0Ucwujfw=",
+    "zh:0e7c2d37160cab82a9aa9471f82a9b891ace9612de3f65f3a4c4adc11ed79e0e",
+    "zh:13bfe59219ff933a6f110b7ec7516b6a908317d1c356cd097799d492770a72b0",
+    "zh:1e0b22c18c5b3b20a6df090e1fa1e3f83e4f71be94a4f4cf48e62618d2d10c6a",
+    "zh:2898e058ae3e3e678967f928d3d20e4035b0db7543d32f06a4b33e0859ffde90",
+    "zh:591b2f97ef1ec0f284994dedb33b82b01e07c706d32cba7df7ff249453a6e52f",
+    "zh:69a49b4e0ef3a6a23c1ea08931b8f287d39ecf9e2706289f8f67c5ad1266817f",
+    "zh:89463997a628373ecedfdd9129235cd6d5f2d3d6a7ca45b0b13cf64c60e245d4",
+    "zh:95ab51e9e743fcec8d439a13e9c00550e7ab5424994d06401d7914922aaad690",
+    "zh:d53f08bf3257f4f54d3aa0e0f427f9bdb41f5836bfe747d0b52176ed0bce28f5",
+    "zh:dfb3c0c2420290573f21cbab355817daceb3ca7db5e09f575c53022bdcb5e0e5",
+  ]
+}
+
+provider "registry.opentofu.org/hashicorp/aws" {
+  version     = "5.64.0"
+  constraints = ">= 4.40.0"
+  hashes = [
+    "h1:5X3S/+HlvmebHPYrKPGmXS+a7iJ7OyW26fjrpvEAKCQ=",
+    "zh:0751c0c154b4b6cee673bb047f95c527f984e3066206dceea69a5357db4157cb",
+    "zh:375f116ae66a90f7c455852606acd78e4e005e476abcf681cea6883c8ca5b592",
+    "zh:4ad242818b4ca904d69d8653edd652e7c27261a33cc32bff894d4a4e76f68e5c",
+    "zh:596d8180e5c18d1a3b7d234966df33fbab7012d3e4e964d891787898f771f979",
+    "zh:8aa86de8fccb3a0afbe71c4b2eb2d0fd413b2fd767b5d76731cd87c9cc648585",
+    "zh:93b429af32dc39b8f90081c2067adb37541d89033930034fb6307837b8a20d15",
+    "zh:9bde1c074b2122ab6374832b690c7164a484f50e22448cba272aaff2d6957f01",
+    "zh:d54f3da5a88b8d4eca1792114c9aa07a22be0691fc0b1109dfe667f61c03840b",
+    "zh:e5199b5b7a6d7c7cce17d345d56d06779ec4b00e95339f7fa628085725b139a2",
+    "zh:f4e26c016eccef5d36ed9adec6d3abca83a9c5544215c89002bae9ffd6b64be4",
+  ]
+}

examples/lambda-layers/.terraform/providers/registry.opentofu.org/hashicorp/archive/2.5.0/linux_amd64

@@ -0,0 +1 @@
+/home/kn/.terraform.d/plugin-cache/registry.opentofu.org/hashicorp/archive/2.5.0/linux_amd64

examples/lambda-layers/.terraform/providers/registry.opentofu.org/hashicorp/aws/5.64.0/linux_amd64

@@ -0,0 +1 @@
+/home/kn/.terraform.d/plugin-cache/registry.opentofu.org/hashicorp/aws/5.64.0/linux_amd64

examples/lambda-layers/README.md

@@ -0,0 +1,6 @@
+# Prepare lambda-layer1 with the following command.
+The path is hard-required by AWS. See https://docs.aws.amazon.com/lambda/latest/dg/packaging-layers.html
+
+```bash
+pip install requests -t python/lib/python3.12/site-packages/
+```

examples/lambda-layers/function.py

@@ -0,0 +1,10 @@
+# reference: https://aws.amazon.com/premiumsupport/knowledge-center/start-stop-lambda-eventbridge/
+import requests
+
+def lambda_handler(event, context):
+    r = requests.get('https://ipinfo.io/')
+    return {
+        "HttpResponseCode": r.status_code
+    }
+
+

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/bin/normalizer

@@ -0,0 +1,8 @@
+#!/usr/bin/python3
+# -*- coding: utf-8 -*-
+import re
+import sys
+from charset_normalizer.cli import cli_detect
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli_detect())

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi-2024.7.4.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi-2024.7.4.dist-info/LICENSE

@@ -0,0 +1,20 @@
+This package contains a modified version of ca-bundle.crt:
+
+ca-bundle.crt -- Bundle of CA Root Certificates
+
+This is a bundle of X.509 certificates of public Certificate Authorities
+(CA). These were automatically extracted from Mozilla's root certificates
+file (certdata.txt).  This file can be found in the mozilla source tree:
+https://hg.mozilla.org/mozilla-central/file/tip/security/nss/lib/ckfw/builtins/certdata.txt
+It contains the certificates in PEM format and therefore
+can be directly used with curl / libcurl / php_curl, or with
+an Apache+mod_ssl webserver for SSL client authentication.
+Just configure this file as the SSLCACertificateFile.#
+
+***** BEGIN LICENSE BLOCK *****
+This Source Code Form is subject to the terms of the Mozilla Public License,
+v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
+one at http://mozilla.org/MPL/2.0/.
+
+***** END LICENSE BLOCK *****
+@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi-2024.7.4.dist-info/METADATA

@@ -0,0 +1,67 @@
+Metadata-Version: 2.1
+Name: certifi
+Version: 2024.7.4
+Summary: Python package for providing Mozilla's CA Bundle.
+Home-page: https://github.com/certifi/python-certifi
+Author: Kenneth Reitz
+Author-email: me@kennethreitz.com
+License: MPL-2.0
+Project-URL: Source, https://github.com/certifi/python-certifi
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.6
+License-File: LICENSE
+
+Certifi: Python SSL Certificates
+================================
+
+Certifi provides Mozilla's carefully curated collection of Root Certificates for
+validating the trustworthiness of SSL certificates while verifying the identity
+of TLS hosts. It has been extracted from the `Requests`_ project.
+
+Installation
+------------
+
+``certifi`` is available on PyPI. Simply install it with ``pip``::
+
+    $ pip install certifi
+
+Usage
+-----
+
+To reference the installed certificate authority (CA) bundle, you can use the
+built-in function::
+
+    >>> import certifi
+
+    >>> certifi.where()
+    '/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
+
+Or from the command line::
+
+    $ python -m certifi
+    /usr/local/lib/python3.7/site-packages/certifi/cacert.pem
+
+Enjoy!
+
+.. _`Requests`: https://requests.readthedocs.io/en/master/
+
+Addition/Removal of Certificates
+--------------------------------
+
+Certifi does not support any addition/removal or other modification of the
+CA trust store content. This project is intended to provide a reliable and
+highly portable root of trust to python deployments. Look to upstream projects
+for methods to use alternate trust.

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi-2024.7.4.dist-info/RECORD

@@ -0,0 +1,14 @@
+certifi-2024.7.4.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+certifi-2024.7.4.dist-info/LICENSE,sha256=6TcW2mucDVpKHfYP5pWzcPBpVgPSH2-D8FPkLPwQyvc,989
+certifi-2024.7.4.dist-info/METADATA,sha256=L9_EuPoQQvHFzxu03_ctaEZxhEty7inz569jGWjlLGo,2221
+certifi-2024.7.4.dist-info/RECORD,,
+certifi-2024.7.4.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+certifi-2024.7.4.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
+certifi/__init__.py,sha256=LHXz7E80YJYBzCBv6ZyidQ5-ciYSkSebpY2E5OM0l7o,94
+certifi/__main__.py,sha256=xBBoj905TUWBLRGANOcf7oi6e-3dMP4cEoG9OyMs11g,243
+certifi/__pycache__/__init__.cpython-312.pyc,,
+certifi/__pycache__/__main__.cpython-312.pyc,,
+certifi/__pycache__/core.cpython-312.pyc,,
+certifi/cacert.pem,sha256=SIupYGAr8HzGP073rsEIaS_sQYIPwzKKjj894DgUmu4,291528
+certifi/core.py,sha256=qRDDFyXVJwTB_EmoGppaXU_R9qCZvhl-EzxPMuV3nTA,4426
+certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi-2024.7.4.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (70.2.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi-2024.7.4.dist-info/top_level.txt

@@ -0,0 +1 @@
+certifi

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi/__init__.py

@@ -0,0 +1,4 @@
+from .core import contents, where
+
+__all__ = ["contents", "where"]
+__version__ = "2024.07.04"

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi/__main__.py

@@ -0,0 +1,12 @@
+import argparse
+
+from certifi import contents, where
+
+parser = argparse.ArgumentParser()
+parser.add_argument("-c", "--contents", action="store_true")
+args = parser.parse_args()
+
+if args.contents:
+    print(contents())
+else:
+    print(where())

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/certifi/core.py

@@ -0,0 +1,114 @@
+"""
+certifi.py
+~~~~~~~~~~
+
+This module returns the installation location of cacert.pem or its contents.
+"""
+import sys
+import atexit
+
+def exit_cacert_ctx() -> None:
+    _CACERT_CTX.__exit__(None, None, None)  # type: ignore[union-attr]
+
+
+if sys.version_info >= (3, 11):
+
+    from importlib.resources import as_file, files
+
+    _CACERT_CTX = None
+    _CACERT_PATH = None
+
+    def where() -> str:
+        # This is slightly terrible, but we want to delay extracting the file
+        # in cases where we're inside of a zipimport situation until someone
+        # actually calls where(), but we don't want to re-extract the file
+        # on every call of where(), so we'll do it once then store it in a
+        # global variable.
+        global _CACERT_CTX
+        global _CACERT_PATH
+        if _CACERT_PATH is None:
+            # This is slightly janky, the importlib.resources API wants you to
+            # manage the cleanup of this file, so it doesn't actually return a
+            # path, it returns a context manager that will give you the path
+            # when you enter it and will do any cleanup when you leave it. In
+            # the common case of not needing a temporary file, it will just
+            # return the file system location and the __exit__() is a no-op.
+            #
+            # We also have to hold onto the actual context manager, because
+            # it will do the cleanup whenever it gets garbage collected, so
+            # we will also store that at the global level as well.
+            _CACERT_CTX = as_file(files("certifi").joinpath("cacert.pem"))
+            _CACERT_PATH = str(_CACERT_CTX.__enter__())
+            atexit.register(exit_cacert_ctx)
+
+        return _CACERT_PATH
+
+    def contents() -> str:
+        return files("certifi").joinpath("cacert.pem").read_text(encoding="ascii")
+
+elif sys.version_info >= (3, 7):
+
+    from importlib.resources import path as get_path, read_text
+
+    _CACERT_CTX = None
+    _CACERT_PATH = None
+
+    def where() -> str:
+        # This is slightly terrible, but we want to delay extracting the
+        # file in cases where we're inside of a zipimport situation until
+        # someone actually calls where(), but we don't want to re-extract
+        # the file on every call of where(), so we'll do it once then store
+        # it in a global variable.
+        global _CACERT_CTX
+        global _CACERT_PATH
+        if _CACERT_PATH is None:
+            # This is slightly janky, the importlib.resources API wants you
+            # to manage the cleanup of this file, so it doesn't actually
+            # return a path, it returns a context manager that will give
+            # you the path when you enter it and will do any cleanup when
+            # you leave it. In the common case of not needing a temporary
+            # file, it will just return the file system location and the
+            # __exit__() is a no-op.
+            #
+            # We also have to hold onto the actual context manager, because
+            # it will do the cleanup whenever it gets garbage collected, so
+            # we will also store that at the global level as well.
+            _CACERT_CTX = get_path("certifi", "cacert.pem")
+            _CACERT_PATH = str(_CACERT_CTX.__enter__())
+            atexit.register(exit_cacert_ctx)
+
+        return _CACERT_PATH
+
+    def contents() -> str:
+        return read_text("certifi", "cacert.pem", encoding="ascii")
+
+else:
+    import os
+    import types
+    from typing import Union
+
+    Package = Union[types.ModuleType, str]
+    Resource = Union[str, "os.PathLike"]
+
+    # This fallback will work for Python versions prior to 3.7 that lack the
+    # importlib.resources module but relies on the existing `where` function
+    # so won't address issues with environments like PyOxidizer that don't set
+    # __file__ on modules.
+    def read_text(
+        package: Package,
+        resource: Resource,
+        encoding: str = 'utf-8',
+        errors: str = 'strict'
+    ) -> str:
+        with open(where(), encoding=encoding) as data:
+            return data.read()
+
+    # If we don't have importlib.resources, then we will just do the old logic
+    # of assuming we're on the filesystem and munge the path directly.
+    def where() -> str:
+        f = os.path.dirname(__file__)
+
+        return os.path.join(f, "cacert.pem")
+
+    def contents() -> str:
+        return read_text("certifi", "cacert.pem", encoding="ascii")

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer-3.3.2.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer-3.3.2.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019 TAHRI Ahmed R.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer-3.3.2.dist-info/METADATA

@@ -0,0 +1,683 @@
+Metadata-Version: 2.1
+Name: charset-normalizer
+Version: 3.3.2
+Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
+Home-page: https://github.com/Ousret/charset_normalizer
+Author: Ahmed TAHRI
+Author-email: ahmed.tahri@cloudnursery.dev
+License: MIT
+Project-URL: Bug Reports, https://github.com/Ousret/charset_normalizer/issues
+Project-URL: Documentation, https://charset-normalizer.readthedocs.io/en/latest
+Keywords: encoding,charset,charset-detector,detector,normalization,unicode,chardet,detect
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Topic :: Utilities
+Classifier: Typing :: Typed
+Requires-Python: >=3.7.0
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: unicode_backport
+
+<h1 align="center">Charset Detection, for Everyone 👋</h1>
+
+<p align="center">
+  <sup>The Real First Universal Charset Detector</sup><br>
+  <a href="https://pypi.org/project/charset-normalizer">
+    <img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
+  </a>
+  <a href="https://pepy.tech/project/charset-normalizer/">
+    <img alt="Download Count Total" src="https://static.pepy.tech/badge/charset-normalizer/month" />
+  </a>
+  <a href="https://bestpractices.coreinfrastructure.org/projects/7297">
+    <img src="https://bestpractices.coreinfrastructure.org/projects/7297/badge">
+  </a>
+</p>
+<p align="center">
+  <sup><i>Featured Packages</i></sup><br>
+  <a href="https://github.com/jawah/niquests">
+   <img alt="Static Badge" src="https://img.shields.io/badge/Niquests-HTTP_1.1%2C%202%2C_and_3_Client-cyan">
+  </a>
+  <a href="https://github.com/jawah/wassima">
+   <img alt="Static Badge" src="https://img.shields.io/badge/Wassima-Certifi_Killer-cyan">
+  </a>
+</p>
+<p align="center">
+  <sup><i>In other language (unofficial port - by the community)</i></sup><br>
+  <a href="https://github.com/nickspring/charset-normalizer-rs">
+   <img alt="Static Badge" src="https://img.shields.io/badge/Rust-red">
+  </a>
+</p>
+
+> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
+> I'm trying to resolve the issue by taking a new approach.
+> All IANA character set names for which the Python core library provides codecs are supported.
+
+<p align="center">
+  >>>>> <a href="https://charsetnormalizerweb.ousret.now.sh" target="_blank">👉 Try Me Online Now, Then Adopt Me 👈 </a> <<<<<
+</p>
+
+This project offers you an alternative to **Universal Charset Encoding Detector**, also known as **Chardet**.
+
+| Feature                                          | [Chardet](https://github.com/chardet/chardet) |                                         Charset Normalizer                                         | [cChardet](https://github.com/PyYoshi/cChardet) |
+|--------------------------------------------------|:---------------------------------------------:|:--------------------------------------------------------------------------------------------------:|:-----------------------------------------------:|
+| `Fast`                                           |                       ❌                       |                                                 ✅                                                  |                        ✅                        |
+| `Universal**`                                    |                       ❌                       |                                                 ✅                                                  |                        ❌                        |
+| `Reliable` **without** distinguishable standards |                       ❌                       |                                                 ✅                                                  |                        ✅                        |
+| `Reliable` **with** distinguishable standards    |                       ✅                       |                                                 ✅                                                  |                        ✅                        |
+| `License`                                        |           LGPL-2.1<br>_restrictive_           |                                                MIT                                                 |            MPL-1.1<br>_restrictive_             |
+| `Native Python`                                  |                       ✅                       |                                                 ✅                                                  |                        ❌                        |
+| `Detect spoken language`                         |                       ❌                       |                                                 ✅                                                  |                       N/A                       |
+| `UnicodeDecodeError Safety`                      |                       ❌                       |                                                 ✅                                                  |                        ❌                        |
+| `Whl Size (min)`                                 |                   193.6 kB                    |                                               42 kB                                                |                     ~200 kB                     |
+| `Supported Encoding`                             |                      33                       | 🎉 [99](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) |                       40                        |
+
+<p align="center">
+<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
+</p>
+
+*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one*<br> 
+Did you got there because of the logs? See [https://charset-normalizer.readthedocs.io/en/latest/user/miscellaneous.html](https://charset-normalizer.readthedocs.io/en/latest/user/miscellaneous.html)
+
+## ⚡ Performance
+
+This package offer better performance than its counterpart Chardet. Here are some numbers.
+
+| Package                                       | Accuracy | Mean per file (ms) | File per sec (est) |
+|-----------------------------------------------|:--------:|:------------------:|:------------------:|
+| [chardet](https://github.com/chardet/chardet) |   86 %   |       200 ms       |     5 file/sec     |
+| charset-normalizer                            | **98 %** |     **10 ms**      |    100 file/sec    |
+
+| Package                                       | 99th percentile | 95th percentile | 50th percentile |
+|-----------------------------------------------|:---------------:|:---------------:|:---------------:|
+| [chardet](https://github.com/chardet/chardet) |     1200 ms     |     287 ms      |      23 ms      |
+| charset-normalizer                            |     100 ms      |      50 ms      |      5 ms       |
+
+Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.
+
+> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
+> And yes, these results might change at any time. The dataset can be updated to include more files.
+> The actual delays heavily depends on your CPU capabilities. The factors should remain the same.
+> Keep in mind that the stats are generous and that Chardet accuracy vs our is measured using Chardet initial capability
+> (eg. Supported Encoding) Challenge-them if you want.
+
+## ✨ Installation
+
+Using pip:
+
+```sh
+pip install charset-normalizer -U
+```
+
+## 🚀 Basic Usage
+
+### CLI
+This package comes with a CLI.
+
+```
+usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
+                  file [file ...]
+
+The Real First Universal Charset Detector. Discover originating encoding used
+on text file. Normalize text to unicode.
+
+positional arguments:
+  files                 File(s) to be analysed
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -v, --verbose         Display complementary information about file if any.
+                        Stdout will contain logs about the detection process.
+  -a, --with-alternative
+                        Output complementary possibilities if any. Top-level
+                        JSON WILL be a list.
+  -n, --normalize       Permit to normalize input file. If not set, program
+                        does not write anything.
+  -m, --minimal         Only output the charset detected to STDOUT. Disabling
+                        JSON output.
+  -r, --replace         Replace file when trying to normalize it instead of
+                        creating a new one.
+  -f, --force           Replace file without asking if you are sure, use this
+                        flag with caution.
+  -t THRESHOLD, --threshold THRESHOLD
+                        Define a custom maximum amount of chaos allowed in
+                        decoded content. 0. <= chaos <= 1.
+  --version             Show version information and exit.
+```
+
+```bash
+normalizer ./data/sample.1.fr.srt
+```
+
+or
+
+```bash
+python -m charset_normalizer ./data/sample.1.fr.srt
+```
+
+🎉 Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
+
+```json
+{
+    "path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
+    "encoding": "cp1252",
+    "encoding_aliases": [
+        "1252",
+        "windows_1252"
+    ],
+    "alternative_encodings": [
+        "cp1254",
+        "cp1256",
+        "cp1258",
+        "iso8859_14",
+        "iso8859_15",
+        "iso8859_16",
+        "iso8859_3",
+        "iso8859_9",
+        "latin_1",
+        "mbcs"
+    ],
+    "language": "French",
+    "alphabets": [
+        "Basic Latin",
+        "Latin-1 Supplement"
+    ],
+    "has_sig_or_bom": false,
+    "chaos": 0.149,
+    "coherence": 97.152,
+    "unicode_path": null,
+    "is_preferred": true
+}
+```
+
+### Python
+*Just print out normalized text*
+```python
+from charset_normalizer import from_path
+
+results = from_path('./my_subtitle.srt')
+
+print(str(results.best()))
+```
+
+*Upgrade your code without effort*
+```python
+from charset_normalizer import detect
+```
+
+The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
+
+See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
+
+## 😇 Why
+
+When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
+reliable alternative using a completely different method. Also! I never back down on a good challenge!
+
+I **don't care** about the **originating charset** encoding, because **two different tables** can
+produce **two identical rendered string.**
+What I want is to get readable text, the best I can. 
+
+In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
+
+Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
+
+## 🍰 How
+
+  - Discard all charset encoding table that could not fit the binary content.
+  - Measure noise, or the mess once opened (by chunks) with a corresponding charset encoding.
+  - Extract matches with the lowest mess detected.
+  - Additionally, we measure coherence / probe for a language.
+
+**Wait a minute**, what is noise/mess and coherence according to **YOU ?**
+
+*Noise :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
+**I established** some ground rules about **what is obvious** when **it seems like** a mess.
+ I know that my interpretation of what is noise is probably incomplete, feel free to contribute in order to
+ improve or rewrite it.
+
+*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
+that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
+
+## ⚡ Known limitations
+
+  - Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
+  - Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
+
+## ⚠️ About Python EOLs
+
+**If you are running:**
+
+- Python >=2.7,<3.5: Unsupported
+- Python 3.5: charset-normalizer < 2.1
+- Python 3.6: charset-normalizer < 3.1
+- Python 3.7: charset-normalizer < 4.0
+
+Upgrade your Python interpreter as soon as possible.
+
+## 👤 Contributing
+
+Contributions, issues and feature requests are very much welcome.<br />
+Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
+
+## 📝 License
+
+Copyright © [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
+This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
+
+Characters frequencies used in this project © 2012 [Denny Vrandečić](http://simia.net/letters/)
+
+## 💼 For Enterprise
+
+Professional support for charset-normalizer is available as part of the [Tidelift
+Subscription][1]. Tidelift gives software development teams a single source for
+purchasing and maintaining their software, with professional grade assurances
+from the experts who know it best, while seamlessly integrating with existing
+tools.
+
+[1]: https://tidelift.com/subscription/pkg/pypi-charset-normalizer?utm_source=pypi-charset-normalizer&utm_medium=readme
+
+# Changelog
+All notable changes to charset-normalizer will be documented in this file. This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
+
+## [3.3.2](https://github.com/Ousret/charset_normalizer/compare/3.3.1...3.3.2) (2023-10-31)
+
+### Fixed
+- Unintentional memory usage regression when using large payload that match several encoding (#376)
+- Regression on some detection case showcased in the documentation (#371)
+
+### Added
+- Noise (md) probe that identify malformed arabic representation due to the presence of letters in isolated form (credit to my wife)
+
+## [3.3.1](https://github.com/Ousret/charset_normalizer/compare/3.3.0...3.3.1) (2023-10-22)
+
+### Changed
+- Optional mypyc compilation upgraded to version 1.6.1 for Python >= 3.8
+- Improved the general detection reliability based on reports from the community
+
+## [3.3.0](https://github.com/Ousret/charset_normalizer/compare/3.2.0...3.3.0) (2023-09-30)
+
+### Added
+- Allow to execute the CLI (e.g. normalizer) through `python -m charset_normalizer.cli` or `python -m charset_normalizer`
+- Support for 9 forgotten encoding that are supported by Python but unlisted in `encoding.aliases` as they have no alias (#323)
+
+### Removed
+- (internal) Redundant utils.is_ascii function and unused function is_private_use_only
+- (internal) charset_normalizer.assets is moved inside charset_normalizer.constant
+
+### Changed
+- (internal) Unicode code blocks in constants are updated using the latest v15.0.0 definition to improve detection
+- Optional mypyc compilation upgraded to version 1.5.1 for Python >= 3.8
+
+### Fixed
+- Unable to properly sort CharsetMatch when both chaos/noise and coherence were close due to an unreachable condition in \_\_lt\_\_ (#350)
+
+## [3.2.0](https://github.com/Ousret/charset_normalizer/compare/3.1.0...3.2.0) (2023-06-07)
+
+### Changed
+- Typehint for function `from_path` no longer enforce `PathLike` as its first argument
+- Minor improvement over the global detection reliability
+
+### Added
+- Introduce function `is_binary` that relies on main capabilities, and optimized to detect binaries
+- Propagate `enable_fallback` argument throughout `from_bytes`, `from_path`, and `from_fp` that allow a deeper control over the detection (default True)
+- Explicit support for Python 3.12
+
+### Fixed
+- Edge case detection failure where a file would contain 'very-long' camel cased word (Issue #289)
+
+## [3.1.0](https://github.com/Ousret/charset_normalizer/compare/3.0.1...3.1.0) (2023-03-06)
+
+### Added
+- Argument `should_rename_legacy` for legacy function `detect` and disregard any new arguments without errors (PR #262)
+
+### Removed
+- Support for Python 3.6 (PR #260)
+
+### Changed
+- Optional speedup provided by mypy/c 1.0.1
+
+## [3.0.1](https://github.com/Ousret/charset_normalizer/compare/3.0.0...3.0.1) (2022-11-18)
+
+### Fixed
+- Multi-bytes cutter/chunk generator did not always cut correctly (PR #233)
+
+### Changed
+- Speedup provided by mypy/c 0.990 on Python >= 3.7
+
+## [3.0.0](https://github.com/Ousret/charset_normalizer/compare/2.1.1...3.0.0) (2022-10-20)
+
+### Added
+- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
+- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
+- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
+- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
+
+### Changed
+- Build with static metadata using 'build' frontend
+- Make the language detection stricter
+- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
+
+### Fixed
+- CLI with opt --normalize fail when using full path for files
+- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
+- Sphinx warnings when generating the documentation
+
+### Removed
+- Coherence detector no longer return 'Simple English' instead return 'English'
+- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
+- Breaking: Method `first()` and `best()` from CharsetMatch
+- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
+- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
+- Breaking: Top-level function `normalize`
+- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
+- Support for the backport `unicodedata2`
+
+## [3.0.0rc1](https://github.com/Ousret/charset_normalizer/compare/3.0.0b2...3.0.0rc1) (2022-10-18)
+
+### Added
+- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
+- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
+- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
+
+### Changed
+- Build with static metadata using 'build' frontend
+- Make the language detection stricter
+
+### Fixed
+- CLI with opt --normalize fail when using full path for files
+- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
+
+### Removed
+- Coherence detector no longer return 'Simple English' instead return 'English'
+- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
+
+## [3.0.0b2](https://github.com/Ousret/charset_normalizer/compare/3.0.0b1...3.0.0b2) (2022-08-21)
+
+### Added
+- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
+
+### Removed
+- Breaking: Method `first()` and `best()` from CharsetMatch
+- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
+
+### Fixed
+- Sphinx warnings when generating the documentation
+
+## [3.0.0b1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...3.0.0b1) (2022-08-15)
+
+### Changed
+- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
+
+### Removed
+- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
+- Breaking: Top-level function `normalize`
+- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
+- Support for the backport `unicodedata2`
+
+## [2.1.1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...2.1.1) (2022-08-19)
+
+### Deprecated
+- Function `normalize` scheduled for removal in 3.0
+
+### Changed
+- Removed useless call to decode in fn is_unprintable (#206)
+
+### Fixed
+- Third-party library (i18n xgettext) crashing not recognizing utf_8 (PEP 263) with underscore from [@aleksandernovikov](https://github.com/aleksandernovikov) (#204)
+
+## [2.1.0](https://github.com/Ousret/charset_normalizer/compare/2.0.12...2.1.0) (2022-06-19)
+
+### Added
+- Output the Unicode table version when running the CLI with `--version` (PR #194)
+
+### Changed
+- Re-use decoded buffer for single byte character sets from [@nijel](https://github.com/nijel) (PR #175)
+- Fixing some performance bottlenecks from [@deedy5](https://github.com/deedy5) (PR #183)
+
+### Fixed
+- Workaround potential bug in cpython with Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space (PR #175)
+- CLI default threshold aligned with the API threshold from [@oleksandr-kuzmenko](https://github.com/oleksandr-kuzmenko) (PR #181)
+
+### Removed
+- Support for Python 3.5 (PR #192)
+
+### Deprecated
+- Use of backport unicodedata from `unicodedata2` as Python is quickly catching up, scheduled for removal in 3.0 (PR #194)
+
+## [2.0.12](https://github.com/Ousret/charset_normalizer/compare/2.0.11...2.0.12) (2022-02-12)
+
+### Fixed
+- ASCII miss-detection on rare cases (PR #170) 
+
+## [2.0.11](https://github.com/Ousret/charset_normalizer/compare/2.0.10...2.0.11) (2022-01-30)
+
+### Added
+- Explicit support for Python 3.11 (PR #164)
+
+### Changed
+- The logging behavior have been completely reviewed, now using only TRACE and DEBUG levels (PR #163 #165)
+
+## [2.0.10](https://github.com/Ousret/charset_normalizer/compare/2.0.9...2.0.10) (2022-01-04)
+
+### Fixed
+- Fallback match entries might lead to UnicodeDecodeError for large bytes sequence (PR #154)
+
+### Changed
+- Skipping the language-detection (CD) on ASCII (PR #155)
+
+## [2.0.9](https://github.com/Ousret/charset_normalizer/compare/2.0.8...2.0.9) (2021-12-03)
+
+### Changed
+- Moderating the logging impact (since 2.0.8) for specific environments (PR #147)
+
+### Fixed
+- Wrong logging level applied when setting kwarg `explain` to True (PR #146)
+
+## [2.0.8](https://github.com/Ousret/charset_normalizer/compare/2.0.7...2.0.8) (2021-11-24)
+### Changed
+- Improvement over Vietnamese detection (PR #126)
+- MD improvement on trailing data and long foreign (non-pure latin) data (PR #124)
+- Efficiency improvements in cd/alphabet_languages from [@adbar](https://github.com/adbar) (PR #122)
+- call sum() without an intermediary list following PEP 289 recommendations from [@adbar](https://github.com/adbar) (PR #129)
+- Code style as refactored by Sourcery-AI (PR #131) 
+- Minor adjustment on the MD around european words (PR #133)
+- Remove and replace SRTs from assets / tests (PR #139)
+- Initialize the library logger with a `NullHandler` by default from [@nmaynes](https://github.com/nmaynes) (PR #135)
+- Setting kwarg `explain` to True will add provisionally (bounded to function lifespan) a specific stream handler (PR #135)
+
+### Fixed
+- Fix large (misleading) sequence giving UnicodeDecodeError (PR #137)
+- Avoid using too insignificant chunk (PR #137)
+
+### Added
+- Add and expose function `set_logging_handler` to configure a specific StreamHandler from [@nmaynes](https://github.com/nmaynes) (PR #135)
+- Add `CHANGELOG.md` entries, format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) (PR #141)
+
+## [2.0.7](https://github.com/Ousret/charset_normalizer/compare/2.0.6...2.0.7) (2021-10-11)
+### Added
+- Add support for Kazakh (Cyrillic) language detection (PR #109)
+
+### Changed
+- Further, improve inferring the language from a given single-byte code page (PR #112)
+- Vainly trying to leverage PEP263 when PEP3120 is not supported (PR #116)
+- Refactoring for potential performance improvements in loops from [@adbar](https://github.com/adbar) (PR #113)
+- Various detection improvement (MD+CD) (PR #117)
+
+### Removed
+- Remove redundant logging entry about detected language(s) (PR #115)
+
+### Fixed
+- Fix a minor inconsistency between Python 3.5 and other versions regarding language detection (PR #117 #102)
+
+## [2.0.6](https://github.com/Ousret/charset_normalizer/compare/2.0.5...2.0.6) (2021-09-18)
+### Fixed
+- Unforeseen regression with the loss of the backward-compatibility with some older minor of Python 3.5.x (PR #100)
+- Fix CLI crash when using --minimal output in certain cases (PR #103)
+
+### Changed
+- Minor improvement to the detection efficiency (less than 1%) (PR #106 #101)
+
+## [2.0.5](https://github.com/Ousret/charset_normalizer/compare/2.0.4...2.0.5) (2021-09-14)
+### Changed
+- The project now comply with: flake8, mypy, isort and black to ensure a better overall quality (PR #81)
+- The BC-support with v1.x was improved, the old staticmethods are restored (PR #82)
+- The Unicode detection is slightly improved (PR #93)
+- Add syntax sugar \_\_bool\_\_ for results CharsetMatches list-container (PR #91)
+
+### Removed
+- The project no longer raise warning on tiny content given for detection, will be simply logged as warning instead (PR #92)
+
+### Fixed
+- In some rare case, the chunks extractor could cut in the middle of a multi-byte character and could mislead the mess detection (PR #95)
+- Some rare 'space' characters could trip up the UnprintablePlugin/Mess detection (PR #96)
+- The MANIFEST.in was not exhaustive (PR #78)
+
+## [2.0.4](https://github.com/Ousret/charset_normalizer/compare/2.0.3...2.0.4) (2021-07-30)
+### Fixed
+- The CLI no longer raise an unexpected exception when no encoding has been found (PR #70)
+- Fix accessing the 'alphabets' property when the payload contains surrogate characters (PR #68)
+- The logger could mislead (explain=True) on detected languages and the impact of one MBCS match (PR #72)
+- Submatch factoring could be wrong in rare edge cases (PR #72)
+- Multiple files given to the CLI were ignored when publishing results to STDOUT. (After the first path) (PR #72)
+- Fix line endings from CRLF to LF for certain project files (PR #67)
+
+### Changed
+- Adjust the MD to lower the sensitivity, thus improving the global detection reliability (PR #69 #76)
+- Allow fallback on specified encoding if any (PR #71)
+
+## [2.0.3](https://github.com/Ousret/charset_normalizer/compare/2.0.2...2.0.3) (2021-07-16)
+### Changed
+- Part of the detection mechanism has been improved to be less sensitive, resulting in more accurate detection results. Especially ASCII. (PR #63)
+- According to the community wishes, the detection will fall back on ASCII or UTF-8 in a last-resort case. (PR #64)
+
+## [2.0.2](https://github.com/Ousret/charset_normalizer/compare/2.0.1...2.0.2) (2021-07-15)
+### Fixed
+- Empty/Too small JSON payload miss-detection fixed. Report from [@tseaver](https://github.com/tseaver) (PR #59) 
+
+### Changed
+- Don't inject unicodedata2 into sys.modules from [@akx](https://github.com/akx) (PR #57)
+
+## [2.0.1](https://github.com/Ousret/charset_normalizer/compare/2.0.0...2.0.1) (2021-07-13)
+### Fixed
+- Make it work where there isn't a filesystem available, dropping assets frequencies.json. Report from [@sethmlarson](https://github.com/sethmlarson). (PR #55)
+- Using explain=False permanently disable the verbose output in the current runtime (PR #47)
+- One log entry (language target preemptive) was not show in logs when using explain=True (PR #47)
+- Fix undesired exception (ValueError) on getitem of instance CharsetMatches (PR #52)
+
+### Changed
+- Public function normalize default args values were not aligned with from_bytes (PR #53)
+
+### Added
+- You may now use charset aliases in cp_isolation and cp_exclusion arguments (PR #47)
+
+## [2.0.0](https://github.com/Ousret/charset_normalizer/compare/1.4.1...2.0.0) (2021-07-02)
+### Changed
+- 4x to 5 times faster than the previous 1.4.0 release. At least 2x faster than Chardet.
+- Accent has been made on UTF-8 detection, should perform rather instantaneous.
+- The backward compatibility with Chardet has been greatly improved. The legacy detect function returns an identical charset name whenever possible.
+- The detection mechanism has been slightly improved, now Turkish content is detected correctly (most of the time)
+- The program has been rewritten to ease the readability and maintainability. (+Using static typing)+
+- utf_7 detection has been reinstated.
+
+### Removed
+- This package no longer require anything when used with Python 3.5 (Dropped cached_property)
+- Removed support for these languages: Catalan, Esperanto, Kazakh, Baque, Volapük, Azeri, Galician, Nynorsk, Macedonian, and Serbocroatian.
+- The exception hook on UnicodeDecodeError has been removed.
+
+### Deprecated
+- Methods coherence_non_latin, w_counter, chaos_secondary_pass of the class CharsetMatch are now deprecated and scheduled for removal in v3.0
+
+### Fixed
+- The CLI output used the relative path of the file(s). Should be absolute.
+
+## [1.4.1](https://github.com/Ousret/charset_normalizer/compare/1.4.0...1.4.1) (2021-05-28)
+### Fixed
+- Logger configuration/usage no longer conflict with others (PR #44)
+
+## [1.4.0](https://github.com/Ousret/charset_normalizer/compare/1.3.9...1.4.0) (2021-05-21)
+### Removed
+- Using standard logging instead of using the package loguru.
+- Dropping nose test framework in favor of the maintained pytest.
+- Choose to not use dragonmapper package to help with gibberish Chinese/CJK text.
+- Require cached_property only for Python 3.5 due to constraint. Dropping for every other interpreter version.
+- Stop support for UTF-7 that does not contain a SIG.
+- Dropping PrettyTable, replaced with pure JSON output in CLI.
+
+### Fixed
+- BOM marker in a CharsetNormalizerMatch instance could be False in rare cases even if obviously present. Due to the sub-match factoring process.
+- Not searching properly for the BOM when trying utf32/16 parent codec.
+
+### Changed
+- Improving the package final size by compressing frequencies.json.
+- Huge improvement over the larges payload.
+
+### Added
+- CLI now produces JSON consumable output.
+- Return ASCII if given sequences fit. Given reasonable confidence.
+
+## [1.3.9](https://github.com/Ousret/charset_normalizer/compare/1.3.8...1.3.9) (2021-05-13)
+
+### Fixed
+- In some very rare cases, you may end up getting encode/decode errors due to a bad bytes payload (PR #40)
+
+## [1.3.8](https://github.com/Ousret/charset_normalizer/compare/1.3.7...1.3.8) (2021-05-12)
+
+### Fixed
+- Empty given payload for detection may cause an exception if trying to access the `alphabets` property. (PR #39)
+
+## [1.3.7](https://github.com/Ousret/charset_normalizer/compare/1.3.6...1.3.7) (2021-05-12)
+
+### Fixed
+- The legacy detect function should return UTF-8-SIG if sig is present in the payload. (PR #38)
+
+## [1.3.6](https://github.com/Ousret/charset_normalizer/compare/1.3.5...1.3.6) (2021-02-09)
+
+### Changed
+- Amend the previous release to allow prettytable 2.0 (PR #35)
+
+## [1.3.5](https://github.com/Ousret/charset_normalizer/compare/1.3.4...1.3.5) (2021-02-08)
+
+### Fixed
+- Fix error while using the package with a python pre-release interpreter (PR #33)
+
+### Changed
+- Dependencies refactoring, constraints revised.
+
+### Added
+- Add python 3.9 and 3.10 to the supported interpreters
+
+MIT License
+
+Copyright (c) 2019 TAHRI Ahmed R.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer-3.3.2.dist-info/RECORD

@@ -0,0 +1,35 @@
+../../bin/normalizer,sha256=O1tLXvRzeuQHDVSDjsuiUko8eeXdZtA_eGTgJcdT5qs,233
+charset_normalizer-3.3.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+charset_normalizer-3.3.2.dist-info/LICENSE,sha256=6zGgxaT7Cbik4yBV0lweX5w1iidS_vPNcgIT0cz-4kE,1070
+charset_normalizer-3.3.2.dist-info/METADATA,sha256=cfLhl5A6SI-F0oclm8w8ux9wshL1nipdeCdVnYb4AaA,33550
+charset_normalizer-3.3.2.dist-info/RECORD,,
+charset_normalizer-3.3.2.dist-info/WHEEL,sha256=4ZiCdXIWMxJyEClivrQv1QAHZpQh8kVYU92_ZAVwaok,152
+charset_normalizer-3.3.2.dist-info/entry_points.txt,sha256=ADSTKrkXZ3hhdOVFi6DcUEHQRS0xfxDIE_pEz4wLIXA,65
+charset_normalizer-3.3.2.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
+charset_normalizer/__init__.py,sha256=UzI3xC8PhmcLRMzSgPb6minTmRq0kWznnCBJ8ZCc2XI,1577
+charset_normalizer/__main__.py,sha256=JxY8bleaENOFlLRb9HfoeZCzAMnn2A1oGR5Xm2eyqg0,73
+charset_normalizer/__pycache__/__init__.cpython-312.pyc,,
+charset_normalizer/__pycache__/__main__.cpython-312.pyc,,
+charset_normalizer/__pycache__/api.cpython-312.pyc,,
+charset_normalizer/__pycache__/cd.cpython-312.pyc,,
+charset_normalizer/__pycache__/constant.cpython-312.pyc,,
+charset_normalizer/__pycache__/legacy.cpython-312.pyc,,
+charset_normalizer/__pycache__/md.cpython-312.pyc,,
+charset_normalizer/__pycache__/models.cpython-312.pyc,,
+charset_normalizer/__pycache__/utils.cpython-312.pyc,,
+charset_normalizer/__pycache__/version.cpython-312.pyc,,
+charset_normalizer/api.py,sha256=WOlWjy6wT8SeMYFpaGbXZFN1TMXa-s8vZYfkL4G29iQ,21097
+charset_normalizer/cd.py,sha256=xwZliZcTQFA3jU0c00PRiu9MNxXTFxQkFLWmMW24ZzI,12560
+charset_normalizer/cli/__init__.py,sha256=D5ERp8P62llm2FuoMzydZ7d9rs8cvvLXqE-1_6oViPc,100
+charset_normalizer/cli/__main__.py,sha256=2F-xURZJzo063Ye-2RLJ2wcmURpbKeAzKwpiws65dAs,9744
+charset_normalizer/cli/__pycache__/__init__.cpython-312.pyc,,
+charset_normalizer/cli/__pycache__/__main__.cpython-312.pyc,,
+charset_normalizer/constant.py,sha256=p0IsOVcEbPWYPOdWhnhRbjK1YVBy6fs05C5vKC-zoxU,40481
+charset_normalizer/legacy.py,sha256=T-QuVMsMeDiQEk8WSszMrzVJg_14AMeSkmHdRYhdl1k,2071
+charset_normalizer/md.cpython-312-x86_64-linux-gnu.so,sha256=W654QTU3QZI6eWJ0fanScAr0_O6sL0I61fyRSdC-39Y,16064
+charset_normalizer/md.py,sha256=NkSuVLK13_a8c7BxZ4cGIQ5vOtGIWOdh22WZEvjp-7U,19624
+charset_normalizer/md__mypyc.cpython-312-x86_64-linux-gnu.so,sha256=IlObIV4dmRhFV8V7H-zK4rTxPzTSi9JmrWZD26JQfxI,272640
+charset_normalizer/models.py,sha256=I5i0s4aKCCgLPY2tUY3pwkgFA-BUbbNxQ7hVkVTt62s,11624
+charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+charset_normalizer/utils.py,sha256=teiosMqzKjXyAHXnGdjSBOgnBZwx-SkBbCLrx0UXy8M,11894
+charset_normalizer/version.py,sha256=iHKUfHD3kDRSyrh_BN2ojh43TA5-UZQjvbVIEFfpHDs,79

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer-3.3.2.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.41.2)
+Root-Is-Purelib: false
+Tag: cp312-cp312-manylinux_2_17_x86_64
+Tag: cp312-cp312-manylinux2014_x86_64
+

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer-3.3.2.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+normalizer = charset_normalizer.cli:cli_detect

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer-3.3.2.dist-info/top_level.txt

@@ -0,0 +1 @@
+charset_normalizer

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/__init__.py

@@ -0,0 +1,46 @@
+# -*- coding: utf-8 -*-
+"""
+Charset-Normalizer
+~~~~~~~~~~~~~~
+The Real First Universal Charset Detector.
+A library that helps you read text from an unknown charset encoding.
+Motivated by chardet, This package is trying to resolve the issue by taking a new approach.
+All IANA character set names for which the Python core library provides codecs are supported.
+
+Basic usage:
+   >>> from charset_normalizer import from_bytes
+   >>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8'))
+   >>> best_guess = results.best()
+   >>> str(best_guess)
+   'Bсеки човек има право на образование. Oбразованието!'
+
+Others methods and usages are available - see the full documentation
+at <https://github.com/Ousret/charset_normalizer>.
+:copyright: (c) 2021 by Ahmed TAHRI
+:license: MIT, see LICENSE for more details.
+"""
+import logging
+
+from .api import from_bytes, from_fp, from_path, is_binary
+from .legacy import detect
+from .models import CharsetMatch, CharsetMatches
+from .utils import set_logging_handler
+from .version import VERSION, __version__
+
+__all__ = (
+    "from_fp",
+    "from_path",
+    "from_bytes",
+    "is_binary",
+    "detect",
+    "CharsetMatch",
+    "CharsetMatches",
+    "__version__",
+    "VERSION",
+    "set_logging_handler",
+)
+
+# Attach a NullHandler to the top level logger by default
+# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library
+
+logging.getLogger("charset_normalizer").addHandler(logging.NullHandler())

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/__main__.py

@@ -0,0 +1,4 @@
+from .cli import cli_detect
+
+if __name__ == "__main__":
+    cli_detect()

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/api.py

@@ -0,0 +1,626 @@
+import logging
+from os import PathLike
+from typing import BinaryIO, List, Optional, Set, Union
+
+from .cd import (
+    coherence_ratio,
+    encoding_languages,
+    mb_encoding_languages,
+    merge_coherence_ratios,
+)
+from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE
+from .md import mess_ratio
+from .models import CharsetMatch, CharsetMatches
+from .utils import (
+    any_specified_encoding,
+    cut_sequence_chunks,
+    iana_name,
+    identify_sig_or_bom,
+    is_cp_similar,
+    is_multi_byte_encoding,
+    should_strip_sig_or_bom,
+)
+
+# Will most likely be controversial
+# logging.addLevelName(TRACE, "TRACE")
+logger = logging.getLogger("charset_normalizer")
+explain_handler = logging.StreamHandler()
+explain_handler.setFormatter(
+    logging.Formatter("%(asctime)s | %(levelname)s | %(message)s")
+)
+
+
+def from_bytes(
+    sequences: Union[bytes, bytearray],
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.2,
+    cp_isolation: Optional[List[str]] = None,
+    cp_exclusion: Optional[List[str]] = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = True,
+) -> CharsetMatches:
+    """
+    Given a raw bytes sequence, return the best possibles charset usable to render str objects.
+    If there is no results, it is a strong indicator that the source is binary/not text.
+    By default, the process will extract 5 blocks of 512o each to assess the mess and coherence of a given sequence.
+    And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.
+
+    The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
+    but never take it for granted. Can improve the performance.
+
+    You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
+    purpose.
+
+    This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
+    By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain'
+    toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging.
+    Custom logging format and handler can be set manually.
+    """
+
+    if not isinstance(sequences, (bytearray, bytes)):
+        raise TypeError(
+            "Expected object of type bytes or bytearray, got: {0}".format(
+                type(sequences)
+            )
+        )
+
+    if explain:
+        previous_logger_level: int = logger.level
+        logger.addHandler(explain_handler)
+        logger.setLevel(TRACE)
+
+    length: int = len(sequences)
+
+    if length == 0:
+        logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.")
+        if explain:
+            logger.removeHandler(explain_handler)
+            logger.setLevel(previous_logger_level or logging.WARNING)
+        return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")])
+
+    if cp_isolation is not None:
+        logger.log(
+            TRACE,
+            "cp_isolation is set. use this flag for debugging purpose. "
+            "limited list of encoding allowed : %s.",
+            ", ".join(cp_isolation),
+        )
+        cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
+    else:
+        cp_isolation = []
+
+    if cp_exclusion is not None:
+        logger.log(
+            TRACE,
+            "cp_exclusion is set. use this flag for debugging purpose. "
+            "limited list of encoding excluded : %s.",
+            ", ".join(cp_exclusion),
+        )
+        cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
+    else:
+        cp_exclusion = []
+
+    if length <= (chunk_size * steps):
+        logger.log(
+            TRACE,
+            "override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.",
+            steps,
+            chunk_size,
+            length,
+        )
+        steps = 1
+        chunk_size = length
+
+    if steps > 1 and length / steps < chunk_size:
+        chunk_size = int(length / steps)
+
+    is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE
+    is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE
+
+    if is_too_small_sequence:
+        logger.log(
+            TRACE,
+            "Trying to detect encoding from a tiny portion of ({}) byte(s).".format(
+                length
+            ),
+        )
+    elif is_too_large_sequence:
+        logger.log(
+            TRACE,
+            "Using lazy str decoding because the payload is quite large, ({}) byte(s).".format(
+                length
+            ),
+        )
+
+    prioritized_encodings: List[str] = []
+
+    specified_encoding: Optional[str] = (
+        any_specified_encoding(sequences) if preemptive_behaviour else None
+    )
+
+    if specified_encoding is not None:
+        prioritized_encodings.append(specified_encoding)
+        logger.log(
+            TRACE,
+            "Detected declarative mark in sequence. Priority +1 given for %s.",
+            specified_encoding,
+        )
+
+    tested: Set[str] = set()
+    tested_but_hard_failure: List[str] = []
+    tested_but_soft_failure: List[str] = []
+
+    fallback_ascii: Optional[CharsetMatch] = None
+    fallback_u8: Optional[CharsetMatch] = None
+    fallback_specified: Optional[CharsetMatch] = None
+
+    results: CharsetMatches = CharsetMatches()
+
+    sig_encoding, sig_payload = identify_sig_or_bom(sequences)
+
+    if sig_encoding is not None:
+        prioritized_encodings.append(sig_encoding)
+        logger.log(
+            TRACE,
+            "Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.",
+            len(sig_payload),
+            sig_encoding,
+        )
+
+    prioritized_encodings.append("ascii")
+
+    if "utf_8" not in prioritized_encodings:
+        prioritized_encodings.append("utf_8")
+
+    for encoding_iana in prioritized_encodings + IANA_SUPPORTED:
+        if cp_isolation and encoding_iana not in cp_isolation:
+            continue
+
+        if cp_exclusion and encoding_iana in cp_exclusion:
+            continue
+
+        if encoding_iana in tested:
+            continue
+
+        tested.add(encoding_iana)
+
+        decoded_payload: Optional[str] = None
+        bom_or_sig_available: bool = sig_encoding == encoding_iana
+        strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom(
+            encoding_iana
+        )
+
+        if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
+            logger.log(
+                TRACE,
+                "Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
+                encoding_iana,
+            )
+            continue
+        if encoding_iana in {"utf_7"} and not bom_or_sig_available:
+            logger.log(
+                TRACE,
+                "Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.",
+                encoding_iana,
+            )
+            continue
+
+        try:
+            is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana)
+        except (ModuleNotFoundError, ImportError):
+            logger.log(
+                TRACE,
+                "Encoding %s does not provide an IncrementalDecoder",
+                encoding_iana,
+            )
+            continue
+
+        try:
+            if is_too_large_sequence and is_multi_byte_decoder is False:
+                str(
+                    sequences[: int(50e4)]
+                    if strip_sig_or_bom is False
+                    else sequences[len(sig_payload) : int(50e4)],
+                    encoding=encoding_iana,
+                )
+            else:
+                decoded_payload = str(
+                    sequences
+                    if strip_sig_or_bom is False
+                    else sequences[len(sig_payload) :],
+                    encoding=encoding_iana,
+                )
+        except (UnicodeDecodeError, LookupError) as e:
+            if not isinstance(e, LookupError):
+                logger.log(
+                    TRACE,
+                    "Code page %s does not fit given bytes sequence at ALL. %s",
+                    encoding_iana,
+                    str(e),
+                )
+            tested_but_hard_failure.append(encoding_iana)
+            continue
+
+        similar_soft_failure_test: bool = False
+
+        for encoding_soft_failed in tested_but_soft_failure:
+            if is_cp_similar(encoding_iana, encoding_soft_failed):
+                similar_soft_failure_test = True
+                break
+
+        if similar_soft_failure_test:
+            logger.log(
+                TRACE,
+                "%s is deemed too similar to code page %s and was consider unsuited already. Continuing!",
+                encoding_iana,
+                encoding_soft_failed,
+            )
+            continue
+
+        r_ = range(
+            0 if not bom_or_sig_available else len(sig_payload),
+            length,
+            int(length / steps),
+        )
+
+        multi_byte_bonus: bool = (
+            is_multi_byte_decoder
+            and decoded_payload is not None
+            and len(decoded_payload) < length
+        )
+
+        if multi_byte_bonus:
+            logger.log(
+                TRACE,
+                "Code page %s is a multi byte encoding table and it appear that at least one character "
+                "was encoded using n-bytes.",
+                encoding_iana,
+            )
+
+        max_chunk_gave_up: int = int(len(r_) / 4)
+
+        max_chunk_gave_up = max(max_chunk_gave_up, 2)
+        early_stop_count: int = 0
+        lazy_str_hard_failure = False
+
+        md_chunks: List[str] = []
+        md_ratios = []
+
+        try:
+            for chunk in cut_sequence_chunks(
+                sequences,
+                encoding_iana,
+                r_,
+                chunk_size,
+                bom_or_sig_available,
+                strip_sig_or_bom,
+                sig_payload,
+                is_multi_byte_decoder,
+                decoded_payload,
+            ):
+                md_chunks.append(chunk)
+
+                md_ratios.append(
+                    mess_ratio(
+                        chunk,
+                        threshold,
+                        explain is True and 1 <= len(cp_isolation) <= 2,
+                    )
+                )
+
+                if md_ratios[-1] >= threshold:
+                    early_stop_count += 1
+
+                if (early_stop_count >= max_chunk_gave_up) or (
+                    bom_or_sig_available and strip_sig_or_bom is False
+                ):
+                    break
+        except (
+            UnicodeDecodeError
+        ) as e:  # Lazy str loading may have missed something there
+            logger.log(
+                TRACE,
+                "LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s",
+                encoding_iana,
+                str(e),
+            )
+            early_stop_count = max_chunk_gave_up
+            lazy_str_hard_failure = True
+
+        # We might want to check the sequence again with the whole content
+        # Only if initial MD tests passes
+        if (
+            not lazy_str_hard_failure
+            and is_too_large_sequence
+            and not is_multi_byte_decoder
+        ):
+            try:
+                sequences[int(50e3) :].decode(encoding_iana, errors="strict")
+            except UnicodeDecodeError as e:
+                logger.log(
+                    TRACE,
+                    "LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
+                    encoding_iana,
+                    str(e),
+                )
+                tested_but_hard_failure.append(encoding_iana)
+                continue
+
+        mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
+        if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
+            tested_but_soft_failure.append(encoding_iana)
+            logger.log(
+                TRACE,
+                "%s was excluded because of initial chaos probing. Gave up %i time(s). "
+                "Computed mean chaos is %f %%.",
+                encoding_iana,
+                early_stop_count,
+                round(mean_mess_ratio * 100, ndigits=3),
+            )
+            # Preparing those fallbacks in case we got nothing.
+            if (
+                enable_fallback
+                and encoding_iana in ["ascii", "utf_8", specified_encoding]
+                and not lazy_str_hard_failure
+            ):
+                fallback_entry = CharsetMatch(
+                    sequences, encoding_iana, threshold, False, [], decoded_payload
+                )
+                if encoding_iana == specified_encoding:
+                    fallback_specified = fallback_entry
+                elif encoding_iana == "ascii":
+                    fallback_ascii = fallback_entry
+                else:
+                    fallback_u8 = fallback_entry
+            continue
+
+        logger.log(
+            TRACE,
+            "%s passed initial chaos probing. Mean measured chaos is %f %%",
+            encoding_iana,
+            round(mean_mess_ratio * 100, ndigits=3),
+        )
+
+        if not is_multi_byte_decoder:
+            target_languages: List[str] = encoding_languages(encoding_iana)
+        else:
+            target_languages = mb_encoding_languages(encoding_iana)
+
+        if target_languages:
+            logger.log(
+                TRACE,
+                "{} should target any language(s) of {}".format(
+                    encoding_iana, str(target_languages)
+                ),
+            )
+
+        cd_ratios = []
+
+        # We shall skip the CD when its about ASCII
+        # Most of the time its not relevant to run "language-detection" on it.
+        if encoding_iana != "ascii":
+            for chunk in md_chunks:
+                chunk_languages = coherence_ratio(
+                    chunk,
+                    language_threshold,
+                    ",".join(target_languages) if target_languages else None,
+                )
+
+                cd_ratios.append(chunk_languages)
+
+        cd_ratios_merged = merge_coherence_ratios(cd_ratios)
+
+        if cd_ratios_merged:
+            logger.log(
+                TRACE,
+                "We detected language {} using {}".format(
+                    cd_ratios_merged, encoding_iana
+                ),
+            )
+
+        results.append(
+            CharsetMatch(
+                sequences,
+                encoding_iana,
+                mean_mess_ratio,
+                bom_or_sig_available,
+                cd_ratios_merged,
+                decoded_payload,
+            )
+        )
+
+        if (
+            encoding_iana in [specified_encoding, "ascii", "utf_8"]
+            and mean_mess_ratio < 0.1
+        ):
+            logger.debug(
+                "Encoding detection: %s is most likely the one.", encoding_iana
+            )
+            if explain:
+                logger.removeHandler(explain_handler)
+                logger.setLevel(previous_logger_level)
+            return CharsetMatches([results[encoding_iana]])
+
+        if encoding_iana == sig_encoding:
+            logger.debug(
+                "Encoding detection: %s is most likely the one as we detected a BOM or SIG within "
+                "the beginning of the sequence.",
+                encoding_iana,
+            )
+            if explain:
+                logger.removeHandler(explain_handler)
+                logger.setLevel(previous_logger_level)
+            return CharsetMatches([results[encoding_iana]])
+
+    if len(results) == 0:
+        if fallback_u8 or fallback_ascii or fallback_specified:
+            logger.log(
+                TRACE,
+                "Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.",
+            )
+
+        if fallback_specified:
+            logger.debug(
+                "Encoding detection: %s will be used as a fallback match",
+                fallback_specified.encoding,
+            )
+            results.append(fallback_specified)
+        elif (
+            (fallback_u8 and fallback_ascii is None)
+            or (
+                fallback_u8
+                and fallback_ascii
+                and fallback_u8.fingerprint != fallback_ascii.fingerprint
+            )
+            or (fallback_u8 is not None)
+        ):
+            logger.debug("Encoding detection: utf_8 will be used as a fallback match")
+            results.append(fallback_u8)
+        elif fallback_ascii:
+            logger.debug("Encoding detection: ascii will be used as a fallback match")
+            results.append(fallback_ascii)
+
+    if results:
+        logger.debug(
+            "Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.",
+            results.best().encoding,  # type: ignore
+            len(results) - 1,
+        )
+    else:
+        logger.debug("Encoding detection: Unable to determine any suitable charset.")
+
+    if explain:
+        logger.removeHandler(explain_handler)
+        logger.setLevel(previous_logger_level)
+
+    return results
+
+
+def from_fp(
+    fp: BinaryIO,
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: Optional[List[str]] = None,
+    cp_exclusion: Optional[List[str]] = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = True,
+) -> CharsetMatches:
+    """
+    Same thing than the function from_bytes but using a file pointer that is already ready.
+    Will not close the file pointer.
+    """
+    return from_bytes(
+        fp.read(),
+        steps,
+        chunk_size,
+        threshold,
+        cp_isolation,
+        cp_exclusion,
+        preemptive_behaviour,
+        explain,
+        language_threshold,
+        enable_fallback,
+    )
+
+
+def from_path(
+    path: Union[str, bytes, PathLike],  # type: ignore[type-arg]
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: Optional[List[str]] = None,
+    cp_exclusion: Optional[List[str]] = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = True,
+) -> CharsetMatches:
+    """
+    Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
+    Can raise IOError.
+    """
+    with open(path, "rb") as fp:
+        return from_fp(
+            fp,
+            steps,
+            chunk_size,
+            threshold,
+            cp_isolation,
+            cp_exclusion,
+            preemptive_behaviour,
+            explain,
+            language_threshold,
+            enable_fallback,
+        )
+
+
+def is_binary(
+    fp_or_path_or_payload: Union[PathLike, str, BinaryIO, bytes],  # type: ignore[type-arg]
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: Optional[List[str]] = None,
+    cp_exclusion: Optional[List[str]] = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+    language_threshold: float = 0.1,
+    enable_fallback: bool = False,
+) -> bool:
+    """
+    Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string.
+    Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match
+    are disabled to be stricter around ASCII-compatible but unlikely to be a string.
+    """
+    if isinstance(fp_or_path_or_payload, (str, PathLike)):
+        guesses = from_path(
+            fp_or_path_or_payload,
+            steps=steps,
+            chunk_size=chunk_size,
+            threshold=threshold,
+            cp_isolation=cp_isolation,
+            cp_exclusion=cp_exclusion,
+            preemptive_behaviour=preemptive_behaviour,
+            explain=explain,
+            language_threshold=language_threshold,
+            enable_fallback=enable_fallback,
+        )
+    elif isinstance(
+        fp_or_path_or_payload,
+        (
+            bytes,
+            bytearray,
+        ),
+    ):
+        guesses = from_bytes(
+            fp_or_path_or_payload,
+            steps=steps,
+            chunk_size=chunk_size,
+            threshold=threshold,
+            cp_isolation=cp_isolation,
+            cp_exclusion=cp_exclusion,
+            preemptive_behaviour=preemptive_behaviour,
+            explain=explain,
+            language_threshold=language_threshold,
+            enable_fallback=enable_fallback,
+        )
+    else:
+        guesses = from_fp(
+            fp_or_path_or_payload,
+            steps=steps,
+            chunk_size=chunk_size,
+            threshold=threshold,
+            cp_isolation=cp_isolation,
+            cp_exclusion=cp_exclusion,
+            preemptive_behaviour=preemptive_behaviour,
+            explain=explain,
+            language_threshold=language_threshold,
+            enable_fallback=enable_fallback,
+        )
+
+    return not guesses

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/cd.py

@@ -0,0 +1,395 @@
+import importlib
+from codecs import IncrementalDecoder
+from collections import Counter
+from functools import lru_cache
+from typing import Counter as TypeCounter, Dict, List, Optional, Tuple
+
+from .constant import (
+    FREQUENCIES,
+    KO_NAMES,
+    LANGUAGE_SUPPORTED_COUNT,
+    TOO_SMALL_SEQUENCE,
+    ZH_NAMES,
+)
+from .md import is_suspiciously_successive_range
+from .models import CoherenceMatches
+from .utils import (
+    is_accentuated,
+    is_latin,
+    is_multi_byte_encoding,
+    is_unicode_range_secondary,
+    unicode_range,
+)
+
+
+def encoding_unicode_range(iana_name: str) -> List[str]:
+    """
+    Return associated unicode ranges in a single byte code page.
+    """
+    if is_multi_byte_encoding(iana_name):
+        raise IOError("Function not supported on multi-byte code page")
+
+    decoder = importlib.import_module(
+        "encodings.{}".format(iana_name)
+    ).IncrementalDecoder
+
+    p: IncrementalDecoder = decoder(errors="ignore")
+    seen_ranges: Dict[str, int] = {}
+    character_count: int = 0
+
+    for i in range(0x40, 0xFF):
+        chunk: str = p.decode(bytes([i]))
+
+        if chunk:
+            character_range: Optional[str] = unicode_range(chunk)
+
+            if character_range is None:
+                continue
+
+            if is_unicode_range_secondary(character_range) is False:
+                if character_range not in seen_ranges:
+                    seen_ranges[character_range] = 0
+                seen_ranges[character_range] += 1
+                character_count += 1
+
+    return sorted(
+        [
+            character_range
+            for character_range in seen_ranges
+            if seen_ranges[character_range] / character_count >= 0.15
+        ]
+    )
+
+
+def unicode_range_languages(primary_range: str) -> List[str]:
+    """
+    Return inferred languages used with a unicode range.
+    """
+    languages: List[str] = []
+
+    for language, characters in FREQUENCIES.items():
+        for character in characters:
+            if unicode_range(character) == primary_range:
+                languages.append(language)
+                break
+
+    return languages
+
+
+@lru_cache()
+def encoding_languages(iana_name: str) -> List[str]:
+    """
+    Single-byte encoding language association. Some code page are heavily linked to particular language(s).
+    This function does the correspondence.
+    """
+    unicode_ranges: List[str] = encoding_unicode_range(iana_name)
+    primary_range: Optional[str] = None
+
+    for specified_range in unicode_ranges:
+        if "Latin" not in specified_range:
+            primary_range = specified_range
+            break
+
+    if primary_range is None:
+        return ["Latin Based"]
+
+    return unicode_range_languages(primary_range)
+
+
+@lru_cache()
+def mb_encoding_languages(iana_name: str) -> List[str]:
+    """
+    Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
+    This function does the correspondence.
+    """
+    if (
+        iana_name.startswith("shift_")
+        or iana_name.startswith("iso2022_jp")
+        or iana_name.startswith("euc_j")
+        or iana_name == "cp932"
+    ):
+        return ["Japanese"]
+    if iana_name.startswith("gb") or iana_name in ZH_NAMES:
+        return ["Chinese"]
+    if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES:
+        return ["Korean"]
+
+    return []
+
+
+@lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT)
+def get_target_features(language: str) -> Tuple[bool, bool]:
+    """
+    Determine main aspects from a supported language if it contains accents and if is pure Latin.
+    """
+    target_have_accents: bool = False
+    target_pure_latin: bool = True
+
+    for character in FREQUENCIES[language]:
+        if not target_have_accents and is_accentuated(character):
+            target_have_accents = True
+        if target_pure_latin and is_latin(character) is False:
+            target_pure_latin = False
+
+    return target_have_accents, target_pure_latin
+
+
+def alphabet_languages(
+    characters: List[str], ignore_non_latin: bool = False
+) -> List[str]:
+    """
+    Return associated languages associated to given characters.
+    """
+    languages: List[Tuple[str, float]] = []
+
+    source_have_accents = any(is_accentuated(character) for character in characters)
+
+    for language, language_characters in FREQUENCIES.items():
+        target_have_accents, target_pure_latin = get_target_features(language)
+
+        if ignore_non_latin and target_pure_latin is False:
+            continue
+
+        if target_have_accents is False and source_have_accents:
+            continue
+
+        character_count: int = len(language_characters)
+
+        character_match_count: int = len(
+            [c for c in language_characters if c in characters]
+        )
+
+        ratio: float = character_match_count / character_count
+
+        if ratio >= 0.2:
+            languages.append((language, ratio))
+
+    languages = sorted(languages, key=lambda x: x[1], reverse=True)
+
+    return [compatible_language[0] for compatible_language in languages]
+
+
+def characters_popularity_compare(
+    language: str, ordered_characters: List[str]
+) -> float:
+    """
+    Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language.
+    The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit).
+    Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.)
+    """
+    if language not in FREQUENCIES:
+        raise ValueError("{} not available".format(language))
+
+    character_approved_count: int = 0
+    FREQUENCIES_language_set = set(FREQUENCIES[language])
+
+    ordered_characters_count: int = len(ordered_characters)
+    target_language_characters_count: int = len(FREQUENCIES[language])
+
+    large_alphabet: bool = target_language_characters_count > 26
+
+    for character, character_rank in zip(
+        ordered_characters, range(0, ordered_characters_count)
+    ):
+        if character not in FREQUENCIES_language_set:
+            continue
+
+        character_rank_in_language: int = FREQUENCIES[language].index(character)
+        expected_projection_ratio: float = (
+            target_language_characters_count / ordered_characters_count
+        )
+        character_rank_projection: int = int(character_rank * expected_projection_ratio)
+
+        if (
+            large_alphabet is False
+            and abs(character_rank_projection - character_rank_in_language) > 4
+        ):
+            continue
+
+        if (
+            large_alphabet is True
+            and abs(character_rank_projection - character_rank_in_language)
+            < target_language_characters_count / 3
+        ):
+            character_approved_count += 1
+            continue
+
+        characters_before_source: List[str] = FREQUENCIES[language][
+            0:character_rank_in_language
+        ]
+        characters_after_source: List[str] = FREQUENCIES[language][
+            character_rank_in_language:
+        ]
+        characters_before: List[str] = ordered_characters[0:character_rank]
+        characters_after: List[str] = ordered_characters[character_rank:]
+
+        before_match_count: int = len(
+            set(characters_before) & set(characters_before_source)
+        )
+
+        after_match_count: int = len(
+            set(characters_after) & set(characters_after_source)
+        )
+
+        if len(characters_before_source) == 0 and before_match_count <= 4:
+            character_approved_count += 1
+            continue
+
+        if len(characters_after_source) == 0 and after_match_count <= 4:
+            character_approved_count += 1
+            continue
+
+        if (
+            before_match_count / len(characters_before_source) >= 0.4
+            or after_match_count / len(characters_after_source) >= 0.4
+        ):
+            character_approved_count += 1
+            continue
+
+    return character_approved_count / len(ordered_characters)
+
+
+def alpha_unicode_split(decoded_sequence: str) -> List[str]:
+    """
+    Given a decoded text sequence, return a list of str. Unicode range / alphabet separation.
+    Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list;
+    One containing the latin letters and the other hebrew.
+    """
+    layers: Dict[str, str] = {}
+
+    for character in decoded_sequence:
+        if character.isalpha() is False:
+            continue
+
+        character_range: Optional[str] = unicode_range(character)
+
+        if character_range is None:
+            continue
+
+        layer_target_range: Optional[str] = None
+
+        for discovered_range in layers:
+            if (
+                is_suspiciously_successive_range(discovered_range, character_range)
+                is False
+            ):
+                layer_target_range = discovered_range
+                break
+
+        if layer_target_range is None:
+            layer_target_range = character_range
+
+        if layer_target_range not in layers:
+            layers[layer_target_range] = character.lower()
+            continue
+
+        layers[layer_target_range] += character.lower()
+
+    return list(layers.values())
+
+
+def merge_coherence_ratios(results: List[CoherenceMatches]) -> CoherenceMatches:
+    """
+    This function merge results previously given by the function coherence_ratio.
+    The return type is the same as coherence_ratio.
+    """
+    per_language_ratios: Dict[str, List[float]] = {}
+    for result in results:
+        for sub_result in result:
+            language, ratio = sub_result
+            if language not in per_language_ratios:
+                per_language_ratios[language] = [ratio]
+                continue
+            per_language_ratios[language].append(ratio)
+
+    merge = [
+        (
+            language,
+            round(
+                sum(per_language_ratios[language]) / len(per_language_ratios[language]),
+                4,
+            ),
+        )
+        for language in per_language_ratios
+    ]
+
+    return sorted(merge, key=lambda x: x[1], reverse=True)
+
+
+def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches:
+    """
+    We shall NOT return "English—" in CoherenceMatches because it is an alternative
+    of "English". This function only keeps the best match and remove the em-dash in it.
+    """
+    index_results: Dict[str, List[float]] = dict()
+
+    for result in results:
+        language, ratio = result
+        no_em_name: str = language.replace("—", "")
+
+        if no_em_name not in index_results:
+            index_results[no_em_name] = []
+
+        index_results[no_em_name].append(ratio)
+
+    if any(len(index_results[e]) > 1 for e in index_results):
+        filtered_results: CoherenceMatches = []
+
+        for language in index_results:
+            filtered_results.append((language, max(index_results[language])))
+
+        return filtered_results
+
+    return results
+
+
+@lru_cache(maxsize=2048)
+def coherence_ratio(
+    decoded_sequence: str, threshold: float = 0.1, lg_inclusion: Optional[str] = None
+) -> CoherenceMatches:
+    """
+    Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
+    A layer = Character extraction by alphabets/ranges.
+    """
+
+    results: List[Tuple[str, float]] = []
+    ignore_non_latin: bool = False
+
+    sufficient_match_count: int = 0
+
+    lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else []
+    if "Latin Based" in lg_inclusion_list:
+        ignore_non_latin = True
+        lg_inclusion_list.remove("Latin Based")
+
+    for layer in alpha_unicode_split(decoded_sequence):
+        sequence_frequencies: TypeCounter[str] = Counter(layer)
+        most_common = sequence_frequencies.most_common()
+
+        character_count: int = sum(o for c, o in most_common)
+
+        if character_count <= TOO_SMALL_SEQUENCE:
+            continue
+
+        popular_character_ordered: List[str] = [c for c, o in most_common]
+
+        for language in lg_inclusion_list or alphabet_languages(
+            popular_character_ordered, ignore_non_latin
+        ):
+            ratio: float = characters_popularity_compare(
+                language, popular_character_ordered
+            )
+
+            if ratio < threshold:
+                continue
+            elif ratio >= 0.8:
+                sufficient_match_count += 1
+
+            results.append((language, round(ratio, 4)))
+
+            if sufficient_match_count >= 3:
+                break
+
+    return sorted(
+        filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True
+    )

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/cli/__init__.py

@@ -0,0 +1,6 @@
+from .__main__ import cli_detect, query_yes_no
+
+__all__ = (
+    "cli_detect",
+    "query_yes_no",
+)

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/cli/__main__.py

@@ -0,0 +1,296 @@
+import argparse
+import sys
+from json import dumps
+from os.path import abspath, basename, dirname, join, realpath
+from platform import python_version
+from typing import List, Optional
+from unicodedata import unidata_version
+
+import charset_normalizer.md as md_module
+from charset_normalizer import from_fp
+from charset_normalizer.models import CliDetectionResult
+from charset_normalizer.version import __version__
+
+
+def query_yes_no(question: str, default: str = "yes") -> bool:
+    """Ask a yes/no question via input() and return their answer.
+
+    "question" is a string that is presented to the user.
+    "default" is the presumed answer if the user just hits <Enter>.
+        It must be "yes" (the default), "no" or None (meaning
+        an answer is required of the user).
+
+    The "answer" return value is True for "yes" or False for "no".
+
+    Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input
+    """
+    valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False}
+    if default is None:
+        prompt = " [y/n] "
+    elif default == "yes":
+        prompt = " [Y/n] "
+    elif default == "no":
+        prompt = " [y/N] "
+    else:
+        raise ValueError("invalid default answer: '%s'" % default)
+
+    while True:
+        sys.stdout.write(question + prompt)
+        choice = input().lower()
+        if default is not None and choice == "":
+            return valid[default]
+        elif choice in valid:
+            return valid[choice]
+        else:
+            sys.stdout.write("Please respond with 'yes' or 'no' " "(or 'y' or 'n').\n")
+
+
+def cli_detect(argv: Optional[List[str]] = None) -> int:
+    """
+    CLI assistant using ARGV and ArgumentParser
+    :param argv:
+    :return: 0 if everything is fine, anything else equal trouble
+    """
+    parser = argparse.ArgumentParser(
+        description="The Real First Universal Charset Detector. "
+        "Discover originating encoding used on text file. "
+        "Normalize text to unicode."
+    )
+
+    parser.add_argument(
+        "files", type=argparse.FileType("rb"), nargs="+", help="File(s) to be analysed"
+    )
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        action="store_true",
+        default=False,
+        dest="verbose",
+        help="Display complementary information about file if any. "
+        "Stdout will contain logs about the detection process.",
+    )
+    parser.add_argument(
+        "-a",
+        "--with-alternative",
+        action="store_true",
+        default=False,
+        dest="alternatives",
+        help="Output complementary possibilities if any. Top-level JSON WILL be a list.",
+    )
+    parser.add_argument(
+        "-n",
+        "--normalize",
+        action="store_true",
+        default=False,
+        dest="normalize",
+        help="Permit to normalize input file. If not set, program does not write anything.",
+    )
+    parser.add_argument(
+        "-m",
+        "--minimal",
+        action="store_true",
+        default=False,
+        dest="minimal",
+        help="Only output the charset detected to STDOUT. Disabling JSON output.",
+    )
+    parser.add_argument(
+        "-r",
+        "--replace",
+        action="store_true",
+        default=False,
+        dest="replace",
+        help="Replace file when trying to normalize it instead of creating a new one.",
+    )
+    parser.add_argument(
+        "-f",
+        "--force",
+        action="store_true",
+        default=False,
+        dest="force",
+        help="Replace file without asking if you are sure, use this flag with caution.",
+    )
+    parser.add_argument(
+        "-t",
+        "--threshold",
+        action="store",
+        default=0.2,
+        type=float,
+        dest="threshold",
+        help="Define a custom maximum amount of chaos allowed in decoded content. 0. <= chaos <= 1.",
+    )
+    parser.add_argument(
+        "--version",
+        action="version",
+        version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format(
+            __version__,
+            python_version(),
+            unidata_version,
+            "OFF" if md_module.__file__.lower().endswith(".py") else "ON",
+        ),
+        help="Show version information and exit.",
+    )
+
+    args = parser.parse_args(argv)
+
+    if args.replace is True and args.normalize is False:
+        print("Use --replace in addition of --normalize only.", file=sys.stderr)
+        return 1
+
+    if args.force is True and args.replace is False:
+        print("Use --force in addition of --replace only.", file=sys.stderr)
+        return 1
+
+    if args.threshold < 0.0 or args.threshold > 1.0:
+        print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr)
+        return 1
+
+    x_ = []
+
+    for my_file in args.files:
+        matches = from_fp(my_file, threshold=args.threshold, explain=args.verbose)
+
+        best_guess = matches.best()
+
+        if best_guess is None:
+            print(
+                'Unable to identify originating encoding for "{}". {}'.format(
+                    my_file.name,
+                    "Maybe try increasing maximum amount of chaos."
+                    if args.threshold < 1.0
+                    else "",
+                ),
+                file=sys.stderr,
+            )
+            x_.append(
+                CliDetectionResult(
+                    abspath(my_file.name),
+                    None,
+                    [],
+                    [],
+                    "Unknown",
+                    [],
+                    False,
+                    1.0,
+                    0.0,
+                    None,
+                    True,
+                )
+            )
+        else:
+            x_.append(
+                CliDetectionResult(
+                    abspath(my_file.name),
+                    best_guess.encoding,
+                    best_guess.encoding_aliases,
+                    [
+                        cp
+                        for cp in best_guess.could_be_from_charset
+                        if cp != best_guess.encoding
+                    ],
+                    best_guess.language,
+                    best_guess.alphabets,
+                    best_guess.bom,
+                    best_guess.percent_chaos,
+                    best_guess.percent_coherence,
+                    None,
+                    True,
+                )
+            )
+
+            if len(matches) > 1 and args.alternatives:
+                for el in matches:
+                    if el != best_guess:
+                        x_.append(
+                            CliDetectionResult(
+                                abspath(my_file.name),
+                                el.encoding,
+                                el.encoding_aliases,
+                                [
+                                    cp
+                                    for cp in el.could_be_from_charset
+                                    if cp != el.encoding
+                                ],
+                                el.language,
+                                el.alphabets,
+                                el.bom,
+                                el.percent_chaos,
+                                el.percent_coherence,
+                                None,
+                                False,
+                            )
+                        )
+
+            if args.normalize is True:
+                if best_guess.encoding.startswith("utf") is True:
+                    print(
+                        '"{}" file does not need to be normalized, as it already came from unicode.'.format(
+                            my_file.name
+                        ),
+                        file=sys.stderr,
+                    )
+                    if my_file.closed is False:
+                        my_file.close()
+                    continue
+
+                dir_path = dirname(realpath(my_file.name))
+                file_name = basename(realpath(my_file.name))
+
+                o_: List[str] = file_name.split(".")
+
+                if args.replace is False:
+                    o_.insert(-1, best_guess.encoding)
+                    if my_file.closed is False:
+                        my_file.close()
+                elif (
+                    args.force is False
+                    and query_yes_no(
+                        'Are you sure to normalize "{}" by replacing it ?'.format(
+                            my_file.name
+                        ),
+                        "no",
+                    )
+                    is False
+                ):
+                    if my_file.closed is False:
+                        my_file.close()
+                    continue
+
+                try:
+                    x_[0].unicode_path = join(dir_path, ".".join(o_))
+
+                    with open(x_[0].unicode_path, "w", encoding="utf-8") as fp:
+                        fp.write(str(best_guess))
+                except IOError as e:
+                    print(str(e), file=sys.stderr)
+                    if my_file.closed is False:
+                        my_file.close()
+                    return 2
+
+        if my_file.closed is False:
+            my_file.close()
+
+    if args.minimal is False:
+        print(
+            dumps(
+                [el.__dict__ for el in x_] if len(x_) > 1 else x_[0].__dict__,
+                ensure_ascii=True,
+                indent=4,
+            )
+        )
+    else:
+        for my_file in args.files:
+            print(
+                ", ".join(
+                    [
+                        el.encoding or "undefined"
+                        for el in x_
+                        if el.path == abspath(my_file.name)
+                    ]
+                )
+            )
+
+    return 0
+
+
+if __name__ == "__main__":
+    cli_detect()

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/legacy.py

@@ -0,0 +1,54 @@
+from typing import Any, Dict, Optional, Union
+from warnings import warn
+
+from .api import from_bytes
+from .constant import CHARDET_CORRESPONDENCE
+
+
+def detect(
+    byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any
+) -> Dict[str, Optional[Union[str, float]]]:
+    """
+    chardet legacy method
+    Detect the encoding of the given byte string. It should be mostly backward-compatible.
+    Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it)
+    This function is deprecated and should be used to migrate your project easily, consult the documentation for
+    further information. Not planned for removal.
+
+    :param byte_str:     The byte sequence to examine.
+    :param should_rename_legacy:  Should we rename legacy encodings
+                                  to their more modern equivalents?
+    """
+    if len(kwargs):
+        warn(
+            f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()"
+        )
+
+    if not isinstance(byte_str, (bytearray, bytes)):
+        raise TypeError(  # pragma: nocover
+            "Expected object of type bytes or bytearray, got: "
+            "{0}".format(type(byte_str))
+        )
+
+    if isinstance(byte_str, bytearray):
+        byte_str = bytes(byte_str)
+
+    r = from_bytes(byte_str).best()
+
+    encoding = r.encoding if r is not None else None
+    language = r.language if r is not None and r.language != "Unknown" else ""
+    confidence = 1.0 - r.chaos if r is not None else None
+
+    # Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process
+    # but chardet does return 'utf-8-sig' and it is a valid codec name.
+    if r is not None and encoding == "utf_8" and r.bom:
+        encoding += "_sig"
+
+    if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE:
+        encoding = CHARDET_CORRESPONDENCE[encoding]
+
+    return {
+        "encoding": encoding,
+        "language": language,
+        "confidence": confidence,
+    }

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/md.py

@@ -0,0 +1,615 @@
+from functools import lru_cache
+from logging import getLogger
+from typing import List, Optional
+
+from .constant import (
+    COMMON_SAFE_ASCII_CHARACTERS,
+    TRACE,
+    UNICODE_SECONDARY_RANGE_KEYWORD,
+)
+from .utils import (
+    is_accentuated,
+    is_arabic,
+    is_arabic_isolated_form,
+    is_case_variable,
+    is_cjk,
+    is_emoticon,
+    is_hangul,
+    is_hiragana,
+    is_katakana,
+    is_latin,
+    is_punctuation,
+    is_separator,
+    is_symbol,
+    is_thai,
+    is_unprintable,
+    remove_accent,
+    unicode_range,
+)
+
+
+class MessDetectorPlugin:
+    """
+    Base abstract class used for mess detection plugins.
+    All detectors MUST extend and implement given methods.
+    """
+
+    def eligible(self, character: str) -> bool:
+        """
+        Determine if given character should be fed in.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+    def feed(self, character: str) -> None:
+        """
+        The main routine to be executed upon character.
+        Insert the logic in witch the text would be considered chaotic.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+    def reset(self) -> None:  # pragma: no cover
+        """
+        Permit to reset the plugin to the initial state.
+        """
+        raise NotImplementedError
+
+    @property
+    def ratio(self) -> float:
+        """
+        Compute the chaos ratio based on what your feed() has seen.
+        Must NOT be lower than 0.; No restriction gt 0.
+        """
+        raise NotImplementedError  # pragma: nocover
+
+
+class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._punctuation_count: int = 0
+        self._symbol_count: int = 0
+        self._character_count: int = 0
+
+        self._last_printable_char: Optional[str] = None
+        self._frenzy_symbol_in_word: bool = False
+
+    def eligible(self, character: str) -> bool:
+        return character.isprintable()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if (
+            character != self._last_printable_char
+            and character not in COMMON_SAFE_ASCII_CHARACTERS
+        ):
+            if is_punctuation(character):
+                self._punctuation_count += 1
+            elif (
+                character.isdigit() is False
+                and is_symbol(character)
+                and is_emoticon(character) is False
+            ):
+                self._symbol_count += 2
+
+        self._last_printable_char = character
+
+    def reset(self) -> None:  # pragma: no cover
+        self._punctuation_count = 0
+        self._character_count = 0
+        self._symbol_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        ratio_of_punctuation: float = (
+            self._punctuation_count + self._symbol_count
+        ) / self._character_count
+
+        return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0
+
+
+class TooManyAccentuatedPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._character_count: int = 0
+        self._accentuated_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return character.isalpha()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if is_accentuated(character):
+            self._accentuated_count += 1
+
+    def reset(self) -> None:  # pragma: no cover
+        self._character_count = 0
+        self._accentuated_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count < 8:
+            return 0.0
+
+        ratio_of_accentuation: float = self._accentuated_count / self._character_count
+        return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0
+
+
+class UnprintablePlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._unprintable_count: int = 0
+        self._character_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if is_unprintable(character):
+            self._unprintable_count += 1
+        self._character_count += 1
+
+    def reset(self) -> None:  # pragma: no cover
+        self._unprintable_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        return (self._unprintable_count * 8) / self._character_count
+
+
+class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._successive_count: int = 0
+        self._character_count: int = 0
+
+        self._last_latin_character: Optional[str] = None
+
+    def eligible(self, character: str) -> bool:
+        return character.isalpha() and is_latin(character)
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+        if (
+            self._last_latin_character is not None
+            and is_accentuated(character)
+            and is_accentuated(self._last_latin_character)
+        ):
+            if character.isupper() and self._last_latin_character.isupper():
+                self._successive_count += 1
+            # Worse if its the same char duplicated with different accent.
+            if remove_accent(character) == remove_accent(self._last_latin_character):
+                self._successive_count += 1
+        self._last_latin_character = character
+
+    def reset(self) -> None:  # pragma: no cover
+        self._successive_count = 0
+        self._character_count = 0
+        self._last_latin_character = None
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        return (self._successive_count * 2) / self._character_count
+
+
+class SuspiciousRange(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._suspicious_successive_range_count: int = 0
+        self._character_count: int = 0
+        self._last_printable_seen: Optional[str] = None
+
+    def eligible(self, character: str) -> bool:
+        return character.isprintable()
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if (
+            character.isspace()
+            or is_punctuation(character)
+            or character in COMMON_SAFE_ASCII_CHARACTERS
+        ):
+            self._last_printable_seen = None
+            return
+
+        if self._last_printable_seen is None:
+            self._last_printable_seen = character
+            return
+
+        unicode_range_a: Optional[str] = unicode_range(self._last_printable_seen)
+        unicode_range_b: Optional[str] = unicode_range(character)
+
+        if is_suspiciously_successive_range(unicode_range_a, unicode_range_b):
+            self._suspicious_successive_range_count += 1
+
+        self._last_printable_seen = character
+
+    def reset(self) -> None:  # pragma: no cover
+        self._character_count = 0
+        self._suspicious_successive_range_count = 0
+        self._last_printable_seen = None
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count <= 24:
+            return 0.0
+
+        ratio_of_suspicious_range_usage: float = (
+            self._suspicious_successive_range_count * 2
+        ) / self._character_count
+
+        return ratio_of_suspicious_range_usage
+
+
+class SuperWeirdWordPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._word_count: int = 0
+        self._bad_word_count: int = 0
+        self._foreign_long_count: int = 0
+
+        self._is_current_word_bad: bool = False
+        self._foreign_long_watch: bool = False
+
+        self._character_count: int = 0
+        self._bad_character_count: int = 0
+
+        self._buffer: str = ""
+        self._buffer_accent_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character.isalpha():
+            self._buffer += character
+            if is_accentuated(character):
+                self._buffer_accent_count += 1
+            if (
+                self._foreign_long_watch is False
+                and (is_latin(character) is False or is_accentuated(character))
+                and is_cjk(character) is False
+                and is_hangul(character) is False
+                and is_katakana(character) is False
+                and is_hiragana(character) is False
+                and is_thai(character) is False
+            ):
+                self._foreign_long_watch = True
+            return
+        if not self._buffer:
+            return
+        if (
+            character.isspace() or is_punctuation(character) or is_separator(character)
+        ) and self._buffer:
+            self._word_count += 1
+            buffer_length: int = len(self._buffer)
+
+            self._character_count += buffer_length
+
+            if buffer_length >= 4:
+                if self._buffer_accent_count / buffer_length > 0.34:
+                    self._is_current_word_bad = True
+                # Word/Buffer ending with an upper case accentuated letter are so rare,
+                # that we will consider them all as suspicious. Same weight as foreign_long suspicious.
+                if (
+                    is_accentuated(self._buffer[-1])
+                    and self._buffer[-1].isupper()
+                    and all(_.isupper() for _ in self._buffer) is False
+                ):
+                    self._foreign_long_count += 1
+                    self._is_current_word_bad = True
+            if buffer_length >= 24 and self._foreign_long_watch:
+                camel_case_dst = [
+                    i
+                    for c, i in zip(self._buffer, range(0, buffer_length))
+                    if c.isupper()
+                ]
+                probable_camel_cased: bool = False
+
+                if camel_case_dst and (len(camel_case_dst) / buffer_length <= 0.3):
+                    probable_camel_cased = True
+
+                if not probable_camel_cased:
+                    self._foreign_long_count += 1
+                    self._is_current_word_bad = True
+
+            if self._is_current_word_bad:
+                self._bad_word_count += 1
+                self._bad_character_count += len(self._buffer)
+                self._is_current_word_bad = False
+
+            self._foreign_long_watch = False
+            self._buffer = ""
+            self._buffer_accent_count = 0
+        elif (
+            character not in {"<", ">", "-", "=", "~", "|", "_"}
+            and character.isdigit() is False
+            and is_symbol(character)
+        ):
+            self._is_current_word_bad = True
+            self._buffer += character
+
+    def reset(self) -> None:  # pragma: no cover
+        self._buffer = ""
+        self._is_current_word_bad = False
+        self._foreign_long_watch = False
+        self._bad_word_count = 0
+        self._word_count = 0
+        self._character_count = 0
+        self._bad_character_count = 0
+        self._foreign_long_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._word_count <= 10 and self._foreign_long_count == 0:
+            return 0.0
+
+        return self._bad_character_count / self._character_count
+
+
+class CjkInvalidStopPlugin(MessDetectorPlugin):
+    """
+    GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and
+    can be easily detected. Searching for the overuse of '丅' and '丄'.
+    """
+
+    def __init__(self) -> None:
+        self._wrong_stop_count: int = 0
+        self._cjk_character_count: int = 0
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character in {"丅", "丄"}:
+            self._wrong_stop_count += 1
+            return
+        if is_cjk(character):
+            self._cjk_character_count += 1
+
+    def reset(self) -> None:  # pragma: no cover
+        self._wrong_stop_count = 0
+        self._cjk_character_count = 0
+
+    @property
+    def ratio(self) -> float:
+        if self._cjk_character_count < 16:
+            return 0.0
+        return self._wrong_stop_count / self._cjk_character_count
+
+
+class ArchaicUpperLowerPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._buf: bool = False
+
+        self._character_count_since_last_sep: int = 0
+
+        self._successive_upper_lower_count: int = 0
+        self._successive_upper_lower_count_final: int = 0
+
+        self._character_count: int = 0
+
+        self._last_alpha_seen: Optional[str] = None
+        self._current_ascii_only: bool = True
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        is_concerned = character.isalpha() and is_case_variable(character)
+        chunk_sep = is_concerned is False
+
+        if chunk_sep and self._character_count_since_last_sep > 0:
+            if (
+                self._character_count_since_last_sep <= 64
+                and character.isdigit() is False
+                and self._current_ascii_only is False
+            ):
+                self._successive_upper_lower_count_final += (
+                    self._successive_upper_lower_count
+                )
+
+            self._successive_upper_lower_count = 0
+            self._character_count_since_last_sep = 0
+            self._last_alpha_seen = None
+            self._buf = False
+            self._character_count += 1
+            self._current_ascii_only = True
+
+            return
+
+        if self._current_ascii_only is True and character.isascii() is False:
+            self._current_ascii_only = False
+
+        if self._last_alpha_seen is not None:
+            if (character.isupper() and self._last_alpha_seen.islower()) or (
+                character.islower() and self._last_alpha_seen.isupper()
+            ):
+                if self._buf is True:
+                    self._successive_upper_lower_count += 2
+                    self._buf = False
+                else:
+                    self._buf = True
+            else:
+                self._buf = False
+
+        self._character_count += 1
+        self._character_count_since_last_sep += 1
+        self._last_alpha_seen = character
+
+    def reset(self) -> None:  # pragma: no cover
+        self._character_count = 0
+        self._character_count_since_last_sep = 0
+        self._successive_upper_lower_count = 0
+        self._successive_upper_lower_count_final = 0
+        self._last_alpha_seen = None
+        self._buf = False
+        self._current_ascii_only = True
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count == 0:
+            return 0.0
+
+        return self._successive_upper_lower_count_final / self._character_count
+
+
+class ArabicIsolatedFormPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._character_count: int = 0
+        self._isolated_form_count: int = 0
+
+    def reset(self) -> None:  # pragma: no cover
+        self._character_count = 0
+        self._isolated_form_count = 0
+
+    def eligible(self, character: str) -> bool:
+        return is_arabic(character)
+
+    def feed(self, character: str) -> None:
+        self._character_count += 1
+
+        if is_arabic_isolated_form(character):
+            self._isolated_form_count += 1
+
+    @property
+    def ratio(self) -> float:
+        if self._character_count < 8:
+            return 0.0
+
+        isolated_form_usage: float = self._isolated_form_count / self._character_count
+
+        return isolated_form_usage
+
+
+@lru_cache(maxsize=1024)
+def is_suspiciously_successive_range(
+    unicode_range_a: Optional[str], unicode_range_b: Optional[str]
+) -> bool:
+    """
+    Determine if two Unicode range seen next to each other can be considered as suspicious.
+    """
+    if unicode_range_a is None or unicode_range_b is None:
+        return True
+
+    if unicode_range_a == unicode_range_b:
+        return False
+
+    if "Latin" in unicode_range_a and "Latin" in unicode_range_b:
+        return False
+
+    if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b:
+        return False
+
+    # Latin characters can be accompanied with a combining diacritical mark
+    # eg. Vietnamese.
+    if ("Latin" in unicode_range_a or "Latin" in unicode_range_b) and (
+        "Combining" in unicode_range_a or "Combining" in unicode_range_b
+    ):
+        return False
+
+    keywords_range_a, keywords_range_b = unicode_range_a.split(
+        " "
+    ), unicode_range_b.split(" ")
+
+    for el in keywords_range_a:
+        if el in UNICODE_SECONDARY_RANGE_KEYWORD:
+            continue
+        if el in keywords_range_b:
+            return False
+
+    # Japanese Exception
+    range_a_jp_chars, range_b_jp_chars = (
+        unicode_range_a
+        in (
+            "Hiragana",
+            "Katakana",
+        ),
+        unicode_range_b in ("Hiragana", "Katakana"),
+    )
+    if (range_a_jp_chars or range_b_jp_chars) and (
+        "CJK" in unicode_range_a or "CJK" in unicode_range_b
+    ):
+        return False
+    if range_a_jp_chars and range_b_jp_chars:
+        return False
+
+    if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b:
+        if "CJK" in unicode_range_a or "CJK" in unicode_range_b:
+            return False
+        if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
+            return False
+
+    # Chinese/Japanese use dedicated range for punctuation and/or separators.
+    if ("CJK" in unicode_range_a or "CJK" in unicode_range_b) or (
+        unicode_range_a in ["Katakana", "Hiragana"]
+        and unicode_range_b in ["Katakana", "Hiragana"]
+    ):
+        if "Punctuation" in unicode_range_a or "Punctuation" in unicode_range_b:
+            return False
+        if "Forms" in unicode_range_a or "Forms" in unicode_range_b:
+            return False
+        if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin":
+            return False
+
+    return True
+
+
+@lru_cache(maxsize=2048)
+def mess_ratio(
+    decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False
+) -> float:
+    """
+    Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier.
+    """
+
+    detectors: List[MessDetectorPlugin] = [
+        md_class() for md_class in MessDetectorPlugin.__subclasses__()
+    ]
+
+    length: int = len(decoded_sequence) + 1
+
+    mean_mess_ratio: float = 0.0
+
+    if length < 512:
+        intermediary_mean_mess_ratio_calc: int = 32
+    elif length <= 1024:
+        intermediary_mean_mess_ratio_calc = 64
+    else:
+        intermediary_mean_mess_ratio_calc = 128
+
+    for character, index in zip(decoded_sequence + "\n", range(length)):
+        for detector in detectors:
+            if detector.eligible(character):
+                detector.feed(character)
+
+        if (
+            index > 0 and index % intermediary_mean_mess_ratio_calc == 0
+        ) or index == length - 1:
+            mean_mess_ratio = sum(dt.ratio for dt in detectors)
+
+            if mean_mess_ratio >= maximum_threshold:
+                break
+
+    if debug:
+        logger = getLogger("charset_normalizer")
+
+        logger.log(
+            TRACE,
+            "Mess-detector extended-analysis start. "
+            f"intermediary_mean_mess_ratio_calc={intermediary_mean_mess_ratio_calc} mean_mess_ratio={mean_mess_ratio} "
+            f"maximum_threshold={maximum_threshold}",
+        )
+
+        if len(decoded_sequence) > 16:
+            logger.log(TRACE, f"Starting with: {decoded_sequence[:16]}")
+            logger.log(TRACE, f"Ending with: {decoded_sequence[-16::]}")
+
+        for dt in detectors:  # pragma: nocover
+            logger.log(TRACE, f"{dt.__class__}: {dt.ratio}")
+
+    return round(mean_mess_ratio, 3)

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/models.py

@@ -0,0 +1,340 @@
+from encodings.aliases import aliases
+from hashlib import sha256
+from json import dumps
+from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
+
+from .constant import TOO_BIG_SEQUENCE
+from .utils import iana_name, is_multi_byte_encoding, unicode_range
+
+
+class CharsetMatch:
+    def __init__(
+        self,
+        payload: bytes,
+        guessed_encoding: str,
+        mean_mess_ratio: float,
+        has_sig_or_bom: bool,
+        languages: "CoherenceMatches",
+        decoded_payload: Optional[str] = None,
+    ):
+        self._payload: bytes = payload
+
+        self._encoding: str = guessed_encoding
+        self._mean_mess_ratio: float = mean_mess_ratio
+        self._languages: CoherenceMatches = languages
+        self._has_sig_or_bom: bool = has_sig_or_bom
+        self._unicode_ranges: Optional[List[str]] = None
+
+        self._leaves: List[CharsetMatch] = []
+        self._mean_coherence_ratio: float = 0.0
+
+        self._output_payload: Optional[bytes] = None
+        self._output_encoding: Optional[str] = None
+
+        self._string: Optional[str] = decoded_payload
+
+    def __eq__(self, other: object) -> bool:
+        if not isinstance(other, CharsetMatch):
+            raise TypeError(
+                "__eq__ cannot be invoked on {} and {}.".format(
+                    str(other.__class__), str(self.__class__)
+                )
+            )
+        return self.encoding == other.encoding and self.fingerprint == other.fingerprint
+
+    def __lt__(self, other: object) -> bool:
+        """
+        Implemented to make sorted available upon CharsetMatches items.
+        """
+        if not isinstance(other, CharsetMatch):
+            raise ValueError
+
+        chaos_difference: float = abs(self.chaos - other.chaos)
+        coherence_difference: float = abs(self.coherence - other.coherence)
+
+        # Below 1% difference --> Use Coherence
+        if chaos_difference < 0.01 and coherence_difference > 0.02:
+            return self.coherence > other.coherence
+        elif chaos_difference < 0.01 and coherence_difference <= 0.02:
+            # When having a difficult decision, use the result that decoded as many multi-byte as possible.
+            # preserve RAM usage!
+            if len(self._payload) >= TOO_BIG_SEQUENCE:
+                return self.chaos < other.chaos
+            return self.multi_byte_usage > other.multi_byte_usage
+
+        return self.chaos < other.chaos
+
+    @property
+    def multi_byte_usage(self) -> float:
+        return 1.0 - (len(str(self)) / len(self.raw))
+
+    def __str__(self) -> str:
+        # Lazy Str Loading
+        if self._string is None:
+            self._string = str(self._payload, self._encoding, "strict")
+        return self._string
+
+    def __repr__(self) -> str:
+        return "<CharsetMatch '{}' bytes({})>".format(self.encoding, self.fingerprint)
+
+    def add_submatch(self, other: "CharsetMatch") -> None:
+        if not isinstance(other, CharsetMatch) or other == self:
+            raise ValueError(
+                "Unable to add instance <{}> as a submatch of a CharsetMatch".format(
+                    other.__class__
+                )
+            )
+
+        other._string = None  # Unload RAM usage; dirty trick.
+        self._leaves.append(other)
+
+    @property
+    def encoding(self) -> str:
+        return self._encoding
+
+    @property
+    def encoding_aliases(self) -> List[str]:
+        """
+        Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855.
+        """
+        also_known_as: List[str] = []
+        for u, p in aliases.items():
+            if self.encoding == u:
+                also_known_as.append(p)
+            elif self.encoding == p:
+                also_known_as.append(u)
+        return also_known_as
+
+    @property
+    def bom(self) -> bool:
+        return self._has_sig_or_bom
+
+    @property
+    def byte_order_mark(self) -> bool:
+        return self._has_sig_or_bom
+
+    @property
+    def languages(self) -> List[str]:
+        """
+        Return the complete list of possible languages found in decoded sequence.
+        Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'.
+        """
+        return [e[0] for e in self._languages]
+
+    @property
+    def language(self) -> str:
+        """
+        Most probable language found in decoded sequence. If none were detected or inferred, the property will return
+        "Unknown".
+        """
+        if not self._languages:
+            # Trying to infer the language based on the given encoding
+            # Its either English or we should not pronounce ourselves in certain cases.
+            if "ascii" in self.could_be_from_charset:
+                return "English"
+
+            # doing it there to avoid circular import
+            from charset_normalizer.cd import encoding_languages, mb_encoding_languages
+
+            languages = (
+                mb_encoding_languages(self.encoding)
+                if is_multi_byte_encoding(self.encoding)
+                else encoding_languages(self.encoding)
+            )
+
+            if len(languages) == 0 or "Latin Based" in languages:
+                return "Unknown"
+
+            return languages[0]
+
+        return self._languages[0][0]
+
+    @property
+    def chaos(self) -> float:
+        return self._mean_mess_ratio
+
+    @property
+    def coherence(self) -> float:
+        if not self._languages:
+            return 0.0
+        return self._languages[0][1]
+
+    @property
+    def percent_chaos(self) -> float:
+        return round(self.chaos * 100, ndigits=3)
+
+    @property
+    def percent_coherence(self) -> float:
+        return round(self.coherence * 100, ndigits=3)
+
+    @property
+    def raw(self) -> bytes:
+        """
+        Original untouched bytes.
+        """
+        return self._payload
+
+    @property
+    def submatch(self) -> List["CharsetMatch"]:
+        return self._leaves
+
+    @property
+    def has_submatch(self) -> bool:
+        return len(self._leaves) > 0
+
+    @property
+    def alphabets(self) -> List[str]:
+        if self._unicode_ranges is not None:
+            return self._unicode_ranges
+        # list detected ranges
+        detected_ranges: List[Optional[str]] = [
+            unicode_range(char) for char in str(self)
+        ]
+        # filter and sort
+        self._unicode_ranges = sorted(list({r for r in detected_ranges if r}))
+        return self._unicode_ranges
+
+    @property
+    def could_be_from_charset(self) -> List[str]:
+        """
+        The complete list of encoding that output the exact SAME str result and therefore could be the originating
+        encoding.
+        This list does include the encoding available in property 'encoding'.
+        """
+        return [self._encoding] + [m.encoding for m in self._leaves]
+
+    def output(self, encoding: str = "utf_8") -> bytes:
+        """
+        Method to get re-encoded bytes payload using given target encoding. Default to UTF-8.
+        Any errors will be simply ignored by the encoder NOT replaced.
+        """
+        if self._output_encoding is None or self._output_encoding != encoding:
+            self._output_encoding = encoding
+            self._output_payload = str(self).encode(encoding, "replace")
+
+        return self._output_payload  # type: ignore
+
+    @property
+    def fingerprint(self) -> str:
+        """
+        Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one.
+        """
+        return sha256(self.output()).hexdigest()
+
+
+class CharsetMatches:
+    """
+    Container with every CharsetMatch items ordered by default from most probable to the less one.
+    Act like a list(iterable) but does not implements all related methods.
+    """
+
+    def __init__(self, results: Optional[List[CharsetMatch]] = None):
+        self._results: List[CharsetMatch] = sorted(results) if results else []
+
+    def __iter__(self) -> Iterator[CharsetMatch]:
+        yield from self._results
+
+    def __getitem__(self, item: Union[int, str]) -> CharsetMatch:
+        """
+        Retrieve a single item either by its position or encoding name (alias may be used here).
+        Raise KeyError upon invalid index or encoding not present in results.
+        """
+        if isinstance(item, int):
+            return self._results[item]
+        if isinstance(item, str):
+            item = iana_name(item, False)
+            for result in self._results:
+                if item in result.could_be_from_charset:
+                    return result
+        raise KeyError
+
+    def __len__(self) -> int:
+        return len(self._results)
+
+    def __bool__(self) -> bool:
+        return len(self._results) > 0
+
+    def append(self, item: CharsetMatch) -> None:
+        """
+        Insert a single match. Will be inserted accordingly to preserve sort.
+        Can be inserted as a submatch.
+        """
+        if not isinstance(item, CharsetMatch):
+            raise ValueError(
+                "Cannot append instance '{}' to CharsetMatches".format(
+                    str(item.__class__)
+                )
+            )
+        # We should disable the submatch factoring when the input file is too heavy (conserve RAM usage)
+        if len(item.raw) <= TOO_BIG_SEQUENCE:
+            for match in self._results:
+                if match.fingerprint == item.fingerprint and match.chaos == item.chaos:
+                    match.add_submatch(item)
+                    return
+        self._results.append(item)
+        self._results = sorted(self._results)
+
+    def best(self) -> Optional["CharsetMatch"]:
+        """
+        Simply return the first match. Strict equivalent to matches[0].
+        """
+        if not self._results:
+            return None
+        return self._results[0]
+
+    def first(self) -> Optional["CharsetMatch"]:
+        """
+        Redundant method, call the method best(). Kept for BC reasons.
+        """
+        return self.best()
+
+
+CoherenceMatch = Tuple[str, float]
+CoherenceMatches = List[CoherenceMatch]
+
+
+class CliDetectionResult:
+    def __init__(
+        self,
+        path: str,
+        encoding: Optional[str],
+        encoding_aliases: List[str],
+        alternative_encodings: List[str],
+        language: str,
+        alphabets: List[str],
+        has_sig_or_bom: bool,
+        chaos: float,
+        coherence: float,
+        unicode_path: Optional[str],
+        is_preferred: bool,
+    ):
+        self.path: str = path
+        self.unicode_path: Optional[str] = unicode_path
+        self.encoding: Optional[str] = encoding
+        self.encoding_aliases: List[str] = encoding_aliases
+        self.alternative_encodings: List[str] = alternative_encodings
+        self.language: str = language
+        self.alphabets: List[str] = alphabets
+        self.has_sig_or_bom: bool = has_sig_or_bom
+        self.chaos: float = chaos
+        self.coherence: float = coherence
+        self.is_preferred: bool = is_preferred
+
+    @property
+    def __dict__(self) -> Dict[str, Any]:  # type: ignore
+        return {
+            "path": self.path,
+            "encoding": self.encoding,
+            "encoding_aliases": self.encoding_aliases,
+            "alternative_encodings": self.alternative_encodings,
+            "language": self.language,
+            "alphabets": self.alphabets,
+            "has_sig_or_bom": self.has_sig_or_bom,
+            "chaos": self.chaos,
+            "coherence": self.coherence,
+            "unicode_path": self.unicode_path,
+            "is_preferred": self.is_preferred,
+        }
+
+    def to_json(self) -> str:
+        return dumps(self.__dict__, ensure_ascii=True, indent=4)

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/utils.py

@@ -0,0 +1,421 @@
+import importlib
+import logging
+import unicodedata
+from codecs import IncrementalDecoder
+from encodings.aliases import aliases
+from functools import lru_cache
+from re import findall
+from typing import Generator, List, Optional, Set, Tuple, Union
+
+from _multibytecodec import MultibyteIncrementalDecoder
+
+from .constant import (
+    ENCODING_MARKS,
+    IANA_SUPPORTED_SIMILAR,
+    RE_POSSIBLE_ENCODING_INDICATION,
+    UNICODE_RANGES_COMBINED,
+    UNICODE_SECONDARY_RANGE_KEYWORD,
+    UTF8_MAXIMAL_ALLOCATION,
+)
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_accentuated(character: str) -> bool:
+    try:
+        description: str = unicodedata.name(character)
+    except ValueError:
+        return False
+    return (
+        "WITH GRAVE" in description
+        or "WITH ACUTE" in description
+        or "WITH CEDILLA" in description
+        or "WITH DIAERESIS" in description
+        or "WITH CIRCUMFLEX" in description
+        or "WITH TILDE" in description
+        or "WITH MACRON" in description
+        or "WITH RING ABOVE" in description
+    )
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def remove_accent(character: str) -> str:
+    decomposed: str = unicodedata.decomposition(character)
+    if not decomposed:
+        return character
+
+    codes: List[str] = decomposed.split(" ")
+
+    return chr(int(codes[0], 16))
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def unicode_range(character: str) -> Optional[str]:
+    """
+    Retrieve the Unicode range official name from a single character.
+    """
+    character_ord: int = ord(character)
+
+    for range_name, ord_range in UNICODE_RANGES_COMBINED.items():
+        if character_ord in ord_range:
+            return range_name
+
+    return None
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_latin(character: str) -> bool:
+    try:
+        description: str = unicodedata.name(character)
+    except ValueError:
+        return False
+    return "LATIN" in description
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_punctuation(character: str) -> bool:
+    character_category: str = unicodedata.category(character)
+
+    if "P" in character_category:
+        return True
+
+    character_range: Optional[str] = unicode_range(character)
+
+    if character_range is None:
+        return False
+
+    return "Punctuation" in character_range
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_symbol(character: str) -> bool:
+    character_category: str = unicodedata.category(character)
+
+    if "S" in character_category or "N" in character_category:
+        return True
+
+    character_range: Optional[str] = unicode_range(character)
+
+    if character_range is None:
+        return False
+
+    return "Forms" in character_range and character_category != "Lo"
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_emoticon(character: str) -> bool:
+    character_range: Optional[str] = unicode_range(character)
+
+    if character_range is None:
+        return False
+
+    return "Emoticons" in character_range or "Pictographs" in character_range
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_separator(character: str) -> bool:
+    if character.isspace() or character in {"｜", "+", "<", ">"}:
+        return True
+
+    character_category: str = unicodedata.category(character)
+
+    return "Z" in character_category or character_category in {"Po", "Pd", "Pc"}
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_case_variable(character: str) -> bool:
+    return character.islower() != character.isupper()
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_cjk(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "CJK" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_hiragana(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "HIRAGANA" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_katakana(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "KATAKANA" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_hangul(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "HANGUL" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_thai(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "THAI" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_arabic(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "ARABIC" in character_name
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_arabic_isolated_form(character: str) -> bool:
+    try:
+        character_name = unicodedata.name(character)
+    except ValueError:
+        return False
+
+    return "ARABIC" in character_name and "ISOLATED FORM" in character_name
+
+
+@lru_cache(maxsize=len(UNICODE_RANGES_COMBINED))
+def is_unicode_range_secondary(range_name: str) -> bool:
+    return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD)
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_unprintable(character: str) -> bool:
+    return (
+        character.isspace() is False  # includes \n \t \r \v
+        and character.isprintable() is False
+        and character != "\x1A"  # Why? Its the ASCII substitute character.
+        and character != "\ufeff"  # bug discovered in Python,
+        # Zero Width No-Break Space located in 	Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space.
+    )
+
+
+def any_specified_encoding(sequence: bytes, search_zone: int = 8192) -> Optional[str]:
+    """
+    Extract using ASCII-only decoder any specified encoding in the first n-bytes.
+    """
+    if not isinstance(sequence, bytes):
+        raise TypeError
+
+    seq_len: int = len(sequence)
+
+    results: List[str] = findall(
+        RE_POSSIBLE_ENCODING_INDICATION,
+        sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"),
+    )
+
+    if len(results) == 0:
+        return None
+
+    for specified_encoding in results:
+        specified_encoding = specified_encoding.lower().replace("-", "_")
+
+        encoding_alias: str
+        encoding_iana: str
+
+        for encoding_alias, encoding_iana in aliases.items():
+            if encoding_alias == specified_encoding:
+                return encoding_iana
+            if encoding_iana == specified_encoding:
+                return encoding_iana
+
+    return None
+
+
+@lru_cache(maxsize=128)
+def is_multi_byte_encoding(name: str) -> bool:
+    """
+    Verify is a specific encoding is a multi byte one based on it IANA name
+    """
+    return name in {
+        "utf_8",
+        "utf_8_sig",
+        "utf_16",
+        "utf_16_be",
+        "utf_16_le",
+        "utf_32",
+        "utf_32_le",
+        "utf_32_be",
+        "utf_7",
+    } or issubclass(
+        importlib.import_module("encodings.{}".format(name)).IncrementalDecoder,
+        MultibyteIncrementalDecoder,
+    )
+
+
+def identify_sig_or_bom(sequence: bytes) -> Tuple[Optional[str], bytes]:
+    """
+    Identify and extract SIG/BOM in given sequence.
+    """
+
+    for iana_encoding in ENCODING_MARKS:
+        marks: Union[bytes, List[bytes]] = ENCODING_MARKS[iana_encoding]
+
+        if isinstance(marks, bytes):
+            marks = [marks]
+
+        for mark in marks:
+            if sequence.startswith(mark):
+                return iana_encoding, mark
+
+    return None, b""
+
+
+def should_strip_sig_or_bom(iana_encoding: str) -> bool:
+    return iana_encoding not in {"utf_16", "utf_32"}
+
+
+def iana_name(cp_name: str, strict: bool = True) -> str:
+    cp_name = cp_name.lower().replace("-", "_")
+
+    encoding_alias: str
+    encoding_iana: str
+
+    for encoding_alias, encoding_iana in aliases.items():
+        if cp_name in [encoding_alias, encoding_iana]:
+            return encoding_iana
+
+    if strict:
+        raise ValueError("Unable to retrieve IANA for '{}'".format(cp_name))
+
+    return cp_name
+
+
+def range_scan(decoded_sequence: str) -> List[str]:
+    ranges: Set[str] = set()
+
+    for character in decoded_sequence:
+        character_range: Optional[str] = unicode_range(character)
+
+        if character_range is None:
+            continue
+
+        ranges.add(character_range)
+
+    return list(ranges)
+
+
+def cp_similarity(iana_name_a: str, iana_name_b: str) -> float:
+    if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b):
+        return 0.0
+
+    decoder_a = importlib.import_module(
+        "encodings.{}".format(iana_name_a)
+    ).IncrementalDecoder
+    decoder_b = importlib.import_module(
+        "encodings.{}".format(iana_name_b)
+    ).IncrementalDecoder
+
+    id_a: IncrementalDecoder = decoder_a(errors="ignore")
+    id_b: IncrementalDecoder = decoder_b(errors="ignore")
+
+    character_match_count: int = 0
+
+    for i in range(255):
+        to_be_decoded: bytes = bytes([i])
+        if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded):
+            character_match_count += 1
+
+    return character_match_count / 254
+
+
+def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool:
+    """
+    Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using
+    the function cp_similarity.
+    """
+    return (
+        iana_name_a in IANA_SUPPORTED_SIMILAR
+        and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a]
+    )
+
+
+def set_logging_handler(
+    name: str = "charset_normalizer",
+    level: int = logging.INFO,
+    format_string: str = "%(asctime)s | %(levelname)s | %(message)s",
+) -> None:
+    logger = logging.getLogger(name)
+    logger.setLevel(level)
+
+    handler = logging.StreamHandler()
+    handler.setFormatter(logging.Formatter(format_string))
+    logger.addHandler(handler)
+
+
+def cut_sequence_chunks(
+    sequences: bytes,
+    encoding_iana: str,
+    offsets: range,
+    chunk_size: int,
+    bom_or_sig_available: bool,
+    strip_sig_or_bom: bool,
+    sig_payload: bytes,
+    is_multi_byte_decoder: bool,
+    decoded_payload: Optional[str] = None,
+) -> Generator[str, None, None]:
+    if decoded_payload and is_multi_byte_decoder is False:
+        for i in offsets:
+            chunk = decoded_payload[i : i + chunk_size]
+            if not chunk:
+                break
+            yield chunk
+    else:
+        for i in offsets:
+            chunk_end = i + chunk_size
+            if chunk_end > len(sequences) + 8:
+                continue
+
+            cut_sequence = sequences[i : i + chunk_size]
+
+            if bom_or_sig_available and strip_sig_or_bom is False:
+                cut_sequence = sig_payload + cut_sequence
+
+            chunk = cut_sequence.decode(
+                encoding_iana,
+                errors="ignore" if is_multi_byte_decoder else "strict",
+            )
+
+            # multi-byte bad cutting detector and adjustment
+            # not the cleanest way to perform that fix but clever enough for now.
+            if is_multi_byte_decoder and i > 0:
+                chunk_partial_size_chk: int = min(chunk_size, 16)
+
+                if (
+                    decoded_payload
+                    and chunk[:chunk_partial_size_chk] not in decoded_payload
+                ):
+                    for j in range(i, i - 4, -1):
+                        cut_sequence = sequences[j:chunk_end]
+
+                        if bom_or_sig_available and strip_sig_or_bom is False:
+                            cut_sequence = sig_payload + cut_sequence
+
+                        chunk = cut_sequence.decode(encoding_iana, errors="ignore")
+
+                        if chunk[:chunk_partial_size_chk] in decoded_payload:
+                            break
+
+            yield chunk

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/charset_normalizer/version.py

@@ -0,0 +1,6 @@
+"""
+Expose version
+"""
+
+__version__ = "3.3.2"
+VERSION = __version__.split(".")

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna-3.8.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna-3.8.dist-info/LICENSE.md

@@ -0,0 +1,31 @@
+BSD 3-Clause License
+
+Copyright (c) 2013-2024, Kim Davies and contributors.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+1. Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna-3.8.dist-info/METADATA

@@ -0,0 +1,245 @@
+Metadata-Version: 2.1
+Name: idna
+Version: 3.8
+Summary: Internationalized Domain Names in Applications (IDNA)
+Author-email: Kim Davies <kim+pypi@gumleaf.org>
+Requires-Python: >=3.6
+Description-Content-Type: text/x-rst
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Internet :: Name Service (DNS)
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Utilities
+Project-URL: Changelog, https://github.com/kjd/idna/blob/master/HISTORY.rst
+Project-URL: Issue tracker, https://github.com/kjd/idna/issues
+Project-URL: Source, https://github.com/kjd/idna
+
+Internationalized Domain Names in Applications (IDNA)
+=====================================================
+
+Support for the Internationalized Domain Names in
+Applications (IDNA) protocol as specified in `RFC 5891
+<https://tools.ietf.org/html/rfc5891>`_. This is the latest version of
+the protocol and is sometimes referred to as “IDNA 2008”.
+
+This library also provides support for Unicode Technical
+Standard 46, `Unicode IDNA Compatibility Processing
+<https://unicode.org/reports/tr46/>`_.
+
+This acts as a suitable replacement for the “encodings.idna”
+module that comes with the Python standard library, but which
+only supports the older superseded IDNA specification (`RFC 3490
+<https://tools.ietf.org/html/rfc3490>`_).
+
+Basic functions are simply executed:
+
+.. code-block:: pycon
+
+    >>> import idna
+    >>> idna.encode('ドメイン.テスト')
+    b'xn--eckwd4c7c.xn--zckzah'
+    >>> print(idna.decode('xn--eckwd4c7c.xn--zckzah'))
+    ドメイン.テスト
+
+
+Installation
+------------
+
+This package is available for installation from PyPI:
+
+.. code-block:: bash
+
+    $ python3 -m pip install idna
+
+
+Usage
+-----
+
+For typical usage, the ``encode`` and ``decode`` functions will take a
+domain name argument and perform a conversion to A-labels or U-labels
+respectively.
+
+.. code-block:: pycon
+
+    >>> import idna
+    >>> idna.encode('ドメイン.テスト')
+    b'xn--eckwd4c7c.xn--zckzah'
+    >>> print(idna.decode('xn--eckwd4c7c.xn--zckzah'))
+    ドメイン.テスト
+
+You may use the codec encoding and decoding methods using the
+``idna.codec`` module:
+
+.. code-block:: pycon
+
+    >>> import idna.codec
+    >>> print('домен.испытание'.encode('idna2008'))
+    b'xn--d1acufc.xn--80akhbyknj4f'
+    >>> print(b'xn--d1acufc.xn--80akhbyknj4f'.decode('idna2008'))
+    домен.испытание
+
+Conversions can be applied at a per-label basis using the ``ulabel`` or
+``alabel`` functions if necessary:
+
+.. code-block:: pycon
+
+    >>> idna.alabel('测试')
+    b'xn--0zwm56d'
+
+Compatibility Mapping (UTS #46)
++++++++++++++++++++++++++++++++
+
+As described in `RFC 5895 <https://tools.ietf.org/html/rfc5895>`_, the
+IDNA specification does not normalize input from different potential
+ways a user may input a domain name. This functionality, known as
+a “mapping”, is considered by the specification to be a local
+user-interface issue distinct from IDNA conversion functionality.
+
+This library provides one such mapping that was developed by the
+Unicode Consortium. Known as `Unicode IDNA Compatibility Processing
+<https://unicode.org/reports/tr46/>`_, it provides for both a regular
+mapping for typical applications, as well as a transitional mapping to
+help migrate from older IDNA 2003 applications. Strings are
+preprocessed according to Section 4.4 “Preprocessing for IDNA2008”
+prior to the IDNA operations.
+
+For example, “Königsgäßchen” is not a permissible label as *LATIN
+CAPITAL LETTER K* is not allowed (nor are capital letters in general).
+UTS 46 will convert this into lower case prior to applying the IDNA
+conversion.
+
+.. code-block:: pycon
+
+    >>> import idna
+    >>> idna.encode('Königsgäßchen')
+    ...
+    idna.core.InvalidCodepoint: Codepoint U+004B at position 1 of 'Königsgäßchen' not allowed
+    >>> idna.encode('Königsgäßchen', uts46=True)
+    b'xn--knigsgchen-b4a3dun'
+    >>> print(idna.decode('xn--knigsgchen-b4a3dun'))
+    königsgäßchen
+
+Transitional processing provides conversions to help transition from
+the older 2003 standard to the current standard. For example, in the
+original IDNA specification, the *LATIN SMALL LETTER SHARP S* (ß) was
+converted into two *LATIN SMALL LETTER S* (ss), whereas in the current
+IDNA specification this conversion is not performed.
+
+.. code-block:: pycon
+
+    >>> idna.encode('Königsgäßchen', uts46=True, transitional=True)
+    'xn--knigsgsschen-lcb0w'
+
+Implementers should use transitional processing with caution, only in
+rare cases where conversion from legacy labels to current labels must be
+performed (i.e. IDNA implementations that pre-date 2008). For typical
+applications that just need to convert labels, transitional processing
+is unlikely to be beneficial and could produce unexpected incompatible
+results.
+
+``encodings.idna`` Compatibility
+++++++++++++++++++++++++++++++++
+
+Function calls from the Python built-in ``encodings.idna`` module are
+mapped to their IDNA 2008 equivalents using the ``idna.compat`` module.
+Simply substitute the ``import`` clause in your code to refer to the new
+module name.
+
+Exceptions
+----------
+
+All errors raised during the conversion following the specification
+should raise an exception derived from the ``idna.IDNAError`` base
+class.
+
+More specific exceptions that may be generated as ``idna.IDNABidiError``
+when the error reflects an illegal combination of left-to-right and
+right-to-left characters in a label; ``idna.InvalidCodepoint`` when
+a specific codepoint is an illegal character in an IDN label (i.e.
+INVALID); and ``idna.InvalidCodepointContext`` when the codepoint is
+illegal based on its positional context (i.e. it is CONTEXTO or CONTEXTJ
+but the contextual requirements are not satisfied.)
+
+Building and Diagnostics
+------------------------
+
+The IDNA and UTS 46 functionality relies upon pre-calculated lookup
+tables for performance. These tables are derived from computing against
+eligibility criteria in the respective standards. These tables are
+computed using the command-line script ``tools/idna-data``.
+
+This tool will fetch relevant codepoint data from the Unicode repository
+and perform the required calculations to identify eligibility. There are
+three main modes:
+
+* ``idna-data make-libdata``. Generates ``idnadata.py`` and
+  ``uts46data.py``, the pre-calculated lookup tables used for IDNA and
+  UTS 46 conversions. Implementers who wish to track this library against
+  a different Unicode version may use this tool to manually generate a
+  different version of the ``idnadata.py`` and ``uts46data.py`` files.
+
+* ``idna-data make-table``. Generate a table of the IDNA disposition
+  (e.g. PVALID, CONTEXTJ, CONTEXTO) in the format found in Appendix
+  B.1 of RFC 5892 and the pre-computed tables published by `IANA
+  <https://www.iana.org/>`_.
+
+* ``idna-data U+0061``. Prints debugging output on the various
+  properties associated with an individual Unicode codepoint (in this
+  case, U+0061), that are used to assess the IDNA and UTS 46 status of a
+  codepoint. This is helpful in debugging or analysis.
+
+The tool accepts a number of arguments, described using ``idna-data
+-h``. Most notably, the ``--version`` argument allows the specification
+of the version of Unicode to be used in computing the table data. For
+example, ``idna-data --version 9.0.0 make-libdata`` will generate
+library data against Unicode 9.0.0.
+
+
+Additional Notes
+----------------
+
+* **Packages**. The latest tagged release version is published in the
+  `Python Package Index <https://pypi.org/project/idna/>`_.
+
+* **Version support**. This library supports Python 3.6 and higher.
+  As this library serves as a low-level toolkit for a variety of
+  applications, many of which strive for broad compatibility with older
+  Python versions, there is no rush to remove older interpreter support.
+  Removing support for older versions should be well justified in that the
+  maintenance burden has become too high.
+
+* **Python 2**. Python 2 is supported by version 2.x of this library.
+  Use "idna<3" in your requirements file if you need this library for
+  a Python 2 application. Be advised that these versions are no longer
+  actively developed.
+
+* **Testing**. The library has a test suite based on each rule of the
+  IDNA specification, as well as tests that are provided as part of the
+  Unicode Technical Standard 46, `Unicode IDNA Compatibility Processing
+  <https://unicode.org/reports/tr46/>`_.
+
+* **Emoji**. It is an occasional request to support emoji domains in
+  this library. Encoding of symbols like emoji is expressly prohibited by
+  the technical standard IDNA 2008 and emoji domains are broadly phased
+  out across the domain industry due to associated security risks. For
+  now, applications that need to support these non-compliant labels
+  may wish to consider trying the encode/decode operation in this library
+  first, and then falling back to using `encodings.idna`. See `the Github
+  project <https://github.com/kjd/idna/issues/18>`_ for more discussion.
+

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna-3.8.dist-info/RECORD

@@ -0,0 +1,22 @@
+idna-3.8.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+idna-3.8.dist-info/LICENSE.md,sha256=pZ8LDvNjWHQQmkRhykT_enDVBpboFHZ7-vch1Mmw2w8,1541
+idna-3.8.dist-info/METADATA,sha256=t8baHZrBTPkJi3Lr8ZHm0pbRKnelgO5AU7EGIeTvEcg,9948
+idna-3.8.dist-info/RECORD,,
+idna-3.8.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+idna/__init__.py,sha256=KJQN1eQBr8iIK5SKrJ47lXvxG0BJ7Lm38W4zT0v_8lk,849
+idna/__pycache__/__init__.cpython-312.pyc,,
+idna/__pycache__/codec.cpython-312.pyc,,
+idna/__pycache__/compat.cpython-312.pyc,,
+idna/__pycache__/core.cpython-312.pyc,,
+idna/__pycache__/idnadata.cpython-312.pyc,,
+idna/__pycache__/intranges.cpython-312.pyc,,
+idna/__pycache__/package_data.cpython-312.pyc,,
+idna/__pycache__/uts46data.cpython-312.pyc,,
+idna/codec.py,sha256=PS6m-XmdST7Wj7J7ulRMakPDt5EBJyYrT3CPtjh-7t4,3426
+idna/compat.py,sha256=0_sOEUMT4CVw9doD3vyRhX80X19PwqFoUBs7gWsFME4,321
+idna/core.py,sha256=OHDXwDVbb3R1gNXjHw7JWeeE2rn2u3a-QV-KCeznYcA,12884
+idna/idnadata.py,sha256=dqRwytzkjIHMBa2R1lYvHDwACenZPt8eGVu1Y8UBE-E,78320
+idna/intranges.py,sha256=YBr4fRYuWH7kTKS2tXlFjM24ZF1Pdvcir-aywniInqg,1881
+idna/package_data.py,sha256=DogtAD5vs_-I2Q0k3_ZA4egUq2YLJ4pBbbhI8APzOcY,21
+idna/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+idna/uts46data.py,sha256=1KuksWqLuccPXm2uyRVkhfiFLNIhM_H2m4azCcnOqEU,206503

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna-3.8.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: flit 3.9.0
+Root-Is-Purelib: true
+Tag: py3-none-any

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna/__init__.py

@@ -0,0 +1,44 @@
+from .package_data import __version__
+from .core import (
+    IDNABidiError,
+    IDNAError,
+    InvalidCodepoint,
+    InvalidCodepointContext,
+    alabel,
+    check_bidi,
+    check_hyphen_ok,
+    check_initial_combiner,
+    check_label,
+    check_nfc,
+    decode,
+    encode,
+    ulabel,
+    uts46_remap,
+    valid_contextj,
+    valid_contexto,
+    valid_label_length,
+    valid_string_length,
+)
+from .intranges import intranges_contain
+
+__all__ = [
+    "IDNABidiError",
+    "IDNAError",
+    "InvalidCodepoint",
+    "InvalidCodepointContext",
+    "alabel",
+    "check_bidi",
+    "check_hyphen_ok",
+    "check_initial_combiner",
+    "check_label",
+    "check_nfc",
+    "decode",
+    "encode",
+    "intranges_contain",
+    "ulabel",
+    "uts46_remap",
+    "valid_contextj",
+    "valid_contexto",
+    "valid_label_length",
+    "valid_string_length",
+]

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna/codec.py

@@ -0,0 +1,118 @@
+from .core import encode, decode, alabel, ulabel, IDNAError
+import codecs
+import re
+from typing import Any, Tuple, Optional
+
+_unicode_dots_re = re.compile('[\u002e\u3002\uff0e\uff61]')
+
+class Codec(codecs.Codec):
+
+    def encode(self, data: str, errors: str = 'strict') -> Tuple[bytes, int]:
+        if errors != 'strict':
+            raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
+
+        if not data:
+            return b"", 0
+
+        return encode(data), len(data)
+
+    def decode(self, data: bytes, errors: str = 'strict') -> Tuple[str, int]:
+        if errors != 'strict':
+            raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
+
+        if not data:
+            return '', 0
+
+        return decode(data), len(data)
+
+class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
+    def _buffer_encode(self, data: str, errors: str, final: bool) -> Tuple[bytes, int]:
+        if errors != 'strict':
+            raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
+
+        if not data:
+            return b'', 0
+
+        labels = _unicode_dots_re.split(data)
+        trailing_dot = b''
+        if labels:
+            if not labels[-1]:
+                trailing_dot = b'.'
+                del labels[-1]
+            elif not final:
+                # Keep potentially unfinished label until the next call
+                del labels[-1]
+                if labels:
+                    trailing_dot = b'.'
+
+        result = []
+        size = 0
+        for label in labels:
+            result.append(alabel(label))
+            if size:
+                size += 1
+            size += len(label)
+
+        # Join with U+002E
+        result_bytes = b'.'.join(result) + trailing_dot
+        size += len(trailing_dot)
+        return result_bytes, size
+
+class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
+    def _buffer_decode(self, data: Any, errors: str, final: bool) -> Tuple[str, int]:
+        if errors != 'strict':
+            raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
+
+        if not data:
+            return ('', 0)
+
+        if not isinstance(data, str):
+            data = str(data, 'ascii')
+
+        labels = _unicode_dots_re.split(data)
+        trailing_dot = ''
+        if labels:
+            if not labels[-1]:
+                trailing_dot = '.'
+                del labels[-1]
+            elif not final:
+                # Keep potentially unfinished label until the next call
+                del labels[-1]
+                if labels:
+                    trailing_dot = '.'
+
+        result = []
+        size = 0
+        for label in labels:
+            result.append(ulabel(label))
+            if size:
+                size += 1
+            size += len(label)
+
+        result_str = '.'.join(result) + trailing_dot
+        size += len(trailing_dot)
+        return (result_str, size)
+
+
+class StreamWriter(Codec, codecs.StreamWriter):
+    pass
+
+
+class StreamReader(Codec, codecs.StreamReader):
+    pass
+
+
+def search_function(name: str) -> Optional[codecs.CodecInfo]:
+    if name != 'idna2008':
+        return None
+    return codecs.CodecInfo(
+        name=name,
+        encode=Codec().encode,
+        decode=Codec().decode,
+        incrementalencoder=IncrementalEncoder,
+        incrementaldecoder=IncrementalDecoder,
+        streamwriter=StreamWriter,
+        streamreader=StreamReader,
+    )
+
+codecs.register(search_function)

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna/compat.py

@@ -0,0 +1,13 @@
+from .core import *
+from .codec import *
+from typing import Any, Union
+
+def ToASCII(label: str) -> bytes:
+    return encode(label)
+
+def ToUnicode(label: Union[bytes, bytearray]) -> str:
+    return decode(label)
+
+def nameprep(s: Any) -> None:
+    raise NotImplementedError('IDNA 2008 does not utilise nameprep protocol')
+

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna/core.py

@@ -0,0 +1,399 @@
+from . import idnadata
+import bisect
+import unicodedata
+import re
+from typing import Union, Optional
+from .intranges import intranges_contain
+
+_virama_combining_class = 9
+_alabel_prefix = b'xn--'
+_unicode_dots_re = re.compile('[\u002e\u3002\uff0e\uff61]')
+
+class IDNAError(UnicodeError):
+    """ Base exception for all IDNA-encoding related problems """
+    pass
+
+
+class IDNABidiError(IDNAError):
+    """ Exception when bidirectional requirements are not satisfied """
+    pass
+
+
+class InvalidCodepoint(IDNAError):
+    """ Exception when a disallowed or unallocated codepoint is used """
+    pass
+
+
+class InvalidCodepointContext(IDNAError):
+    """ Exception when the codepoint is not valid in the context it is used """
+    pass
+
+
+def _combining_class(cp: int) -> int:
+    v = unicodedata.combining(chr(cp))
+    if v == 0:
+        if not unicodedata.name(chr(cp)):
+            raise ValueError('Unknown character in unicodedata')
+    return v
+
+def _is_script(cp: str, script: str) -> bool:
+    return intranges_contain(ord(cp), idnadata.scripts[script])
+
+def _punycode(s: str) -> bytes:
+    return s.encode('punycode')
+
+def _unot(s: int) -> str:
+    return 'U+{:04X}'.format(s)
+
+
+def valid_label_length(label: Union[bytes, str]) -> bool:
+    if len(label) > 63:
+        return False
+    return True
+
+
+def valid_string_length(label: Union[bytes, str], trailing_dot: bool) -> bool:
+    if len(label) > (254 if trailing_dot else 253):
+        return False
+    return True
+
+
+def check_bidi(label: str, check_ltr: bool = False) -> bool:
+    # Bidi rules should only be applied if string contains RTL characters
+    bidi_label = False
+    for (idx, cp) in enumerate(label, 1):
+        direction = unicodedata.bidirectional(cp)
+        if direction == '':
+            # String likely comes from a newer version of Unicode
+            raise IDNABidiError('Unknown directionality in label {} at position {}'.format(repr(label), idx))
+        if direction in ['R', 'AL', 'AN']:
+            bidi_label = True
+    if not bidi_label and not check_ltr:
+        return True
+
+    # Bidi rule 1
+    direction = unicodedata.bidirectional(label[0])
+    if direction in ['R', 'AL']:
+        rtl = True
+    elif direction == 'L':
+        rtl = False
+    else:
+        raise IDNABidiError('First codepoint in label {} must be directionality L, R or AL'.format(repr(label)))
+
+    valid_ending = False
+    number_type = None  # type: Optional[str]
+    for (idx, cp) in enumerate(label, 1):
+        direction = unicodedata.bidirectional(cp)
+
+        if rtl:
+            # Bidi rule 2
+            if not direction in ['R', 'AL', 'AN', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
+                raise IDNABidiError('Invalid direction for codepoint at position {} in a right-to-left label'.format(idx))
+            # Bidi rule 3
+            if direction in ['R', 'AL', 'EN', 'AN']:
+                valid_ending = True
+            elif direction != 'NSM':
+                valid_ending = False
+            # Bidi rule 4
+            if direction in ['AN', 'EN']:
+                if not number_type:
+                    number_type = direction
+                else:
+                    if number_type != direction:
+                        raise IDNABidiError('Can not mix numeral types in a right-to-left label')
+        else:
+            # Bidi rule 5
+            if not direction in ['L', 'EN', 'ES', 'CS', 'ET', 'ON', 'BN', 'NSM']:
+                raise IDNABidiError('Invalid direction for codepoint at position {} in a left-to-right label'.format(idx))
+            # Bidi rule 6
+            if direction in ['L', 'EN']:
+                valid_ending = True
+            elif direction != 'NSM':
+                valid_ending = False
+
+    if not valid_ending:
+        raise IDNABidiError('Label ends with illegal codepoint directionality')
+
+    return True
+
+
+def check_initial_combiner(label: str) -> bool:
+    if unicodedata.category(label[0])[0] == 'M':
+        raise IDNAError('Label begins with an illegal combining character')
+    return True
+
+
+def check_hyphen_ok(label: str) -> bool:
+    if label[2:4] == '--':
+        raise IDNAError('Label has disallowed hyphens in 3rd and 4th position')
+    if label[0] == '-' or label[-1] == '-':
+        raise IDNAError('Label must not start or end with a hyphen')
+    return True
+
+
+def check_nfc(label: str) -> None:
+    if unicodedata.normalize('NFC', label) != label:
+        raise IDNAError('Label must be in Normalization Form C')
+
+
+def valid_contextj(label: str, pos: int) -> bool:
+    cp_value = ord(label[pos])
+
+    if cp_value == 0x200c:
+
+        if pos > 0:
+            if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
+                return True
+
+        ok = False
+        for i in range(pos-1, -1, -1):
+            joining_type = idnadata.joining_types.get(ord(label[i]))
+            if joining_type == ord('T'):
+                continue
+            elif joining_type in [ord('L'), ord('D')]:
+                ok = True
+                break
+            else:
+                break
+
+        if not ok:
+            return False
+
+        ok = False
+        for i in range(pos+1, len(label)):
+            joining_type = idnadata.joining_types.get(ord(label[i]))
+            if joining_type == ord('T'):
+                continue
+            elif joining_type in [ord('R'), ord('D')]:
+                ok = True
+                break
+            else:
+                break
+        return ok
+
+    if cp_value == 0x200d:
+
+        if pos > 0:
+            if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
+                return True
+        return False
+
+    else:
+
+        return False
+
+
+def valid_contexto(label: str, pos: int, exception: bool = False) -> bool:
+    cp_value = ord(label[pos])
+
+    if cp_value == 0x00b7:
+        if 0 < pos < len(label)-1:
+            if ord(label[pos - 1]) == 0x006c and ord(label[pos + 1]) == 0x006c:
+                return True
+        return False
+
+    elif cp_value == 0x0375:
+        if pos < len(label)-1 and len(label) > 1:
+            return _is_script(label[pos + 1], 'Greek')
+        return False
+
+    elif cp_value == 0x05f3 or cp_value == 0x05f4:
+        if pos > 0:
+            return _is_script(label[pos - 1], 'Hebrew')
+        return False
+
+    elif cp_value == 0x30fb:
+        for cp in label:
+            if cp == '\u30fb':
+                continue
+            if _is_script(cp, 'Hiragana') or _is_script(cp, 'Katakana') or _is_script(cp, 'Han'):
+                return True
+        return False
+
+    elif 0x660 <= cp_value <= 0x669:
+        for cp in label:
+            if 0x6f0 <= ord(cp) <= 0x06f9:
+                return False
+        return True
+
+    elif 0x6f0 <= cp_value <= 0x6f9:
+        for cp in label:
+            if 0x660 <= ord(cp) <= 0x0669:
+                return False
+        return True
+
+    return False
+
+
+def check_label(label: Union[str, bytes, bytearray]) -> None:
+    if isinstance(label, (bytes, bytearray)):
+        label = label.decode('utf-8')
+    if len(label) == 0:
+        raise IDNAError('Empty Label')
+
+    check_nfc(label)
+    check_hyphen_ok(label)
+    check_initial_combiner(label)
+
+    for (pos, cp) in enumerate(label):
+        cp_value = ord(cp)
+        if intranges_contain(cp_value, idnadata.codepoint_classes['PVALID']):
+            continue
+        elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTJ']):
+            try:
+                if not valid_contextj(label, pos):
+                    raise InvalidCodepointContext('Joiner {} not allowed at position {} in {}'.format(
+                        _unot(cp_value), pos+1, repr(label)))
+            except ValueError:
+                raise IDNAError('Unknown codepoint adjacent to joiner {} at position {} in {}'.format(
+                    _unot(cp_value), pos+1, repr(label)))
+        elif intranges_contain(cp_value, idnadata.codepoint_classes['CONTEXTO']):
+            if not valid_contexto(label, pos):
+                raise InvalidCodepointContext('Codepoint {} not allowed at position {} in {}'.format(_unot(cp_value), pos+1, repr(label)))
+        else:
+            raise InvalidCodepoint('Codepoint {} at position {} of {} not allowed'.format(_unot(cp_value), pos+1, repr(label)))
+
+    check_bidi(label)
+
+
+def alabel(label: str) -> bytes:
+    try:
+        label_bytes = label.encode('ascii')
+        ulabel(label_bytes)
+        if not valid_label_length(label_bytes):
+            raise IDNAError('Label too long')
+        return label_bytes
+    except UnicodeEncodeError:
+        pass
+
+    check_label(label)
+    label_bytes = _alabel_prefix + _punycode(label)
+
+    if not valid_label_length(label_bytes):
+        raise IDNAError('Label too long')
+
+    return label_bytes
+
+
+def ulabel(label: Union[str, bytes, bytearray]) -> str:
+    if not isinstance(label, (bytes, bytearray)):
+        try:
+            label_bytes = label.encode('ascii')
+        except UnicodeEncodeError:
+            check_label(label)
+            return label
+    else:
+        label_bytes = label
+
+    label_bytes = label_bytes.lower()
+    if label_bytes.startswith(_alabel_prefix):
+        label_bytes = label_bytes[len(_alabel_prefix):]
+        if not label_bytes:
+            raise IDNAError('Malformed A-label, no Punycode eligible content found')
+        if label_bytes.decode('ascii')[-1] == '-':
+            raise IDNAError('A-label must not end with a hyphen')
+    else:
+        check_label(label_bytes)
+        return label_bytes.decode('ascii')
+
+    try:
+        label = label_bytes.decode('punycode')
+    except UnicodeError:
+        raise IDNAError('Invalid A-label')
+    check_label(label)
+    return label
+
+
+def uts46_remap(domain: str, std3_rules: bool = True, transitional: bool = False) -> str:
+    """Re-map the characters in the string according to UTS46 processing."""
+    from .uts46data import uts46data
+    output = ''
+
+    for pos, char in enumerate(domain):
+        code_point = ord(char)
+        try:
+            uts46row = uts46data[code_point if code_point < 256 else
+                bisect.bisect_left(uts46data, (code_point, 'Z')) - 1]
+            status = uts46row[1]
+            replacement = None  # type: Optional[str]
+            if len(uts46row) == 3:
+                replacement = uts46row[2]
+            if (status == 'V' or
+                    (status == 'D' and not transitional) or
+                    (status == '3' and not std3_rules and replacement is None)):
+                output += char
+            elif replacement is not None and (status == 'M' or
+                    (status == '3' and not std3_rules) or
+                    (status == 'D' and transitional)):
+                output += replacement
+            elif status != 'I':
+                raise IndexError()
+        except IndexError:
+            raise InvalidCodepoint(
+                'Codepoint {} not allowed at position {} in {}'.format(
+                _unot(code_point), pos + 1, repr(domain)))
+
+    return unicodedata.normalize('NFC', output)
+
+
+def encode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False, transitional: bool = False) -> bytes:
+    if not isinstance(s, str):
+        try:
+            s = str(s, 'ascii')
+        except UnicodeDecodeError:
+            raise IDNAError('should pass a unicode string to the function rather than a byte string.')
+    if uts46:
+        s = uts46_remap(s, std3_rules, transitional)
+    trailing_dot = False
+    result = []
+    if strict:
+        labels = s.split('.')
+    else:
+        labels = _unicode_dots_re.split(s)
+    if not labels or labels == ['']:
+        raise IDNAError('Empty domain')
+    if labels[-1] == '':
+        del labels[-1]
+        trailing_dot = True
+    for label in labels:
+        s = alabel(label)
+        if s:
+            result.append(s)
+        else:
+            raise IDNAError('Empty label')
+    if trailing_dot:
+        result.append(b'')
+    s = b'.'.join(result)
+    if not valid_string_length(s, trailing_dot):
+        raise IDNAError('Domain too long')
+    return s
+
+
+def decode(s: Union[str, bytes, bytearray], strict: bool = False, uts46: bool = False, std3_rules: bool = False) -> str:
+    try:
+        if not isinstance(s, str):
+            s = str(s, 'ascii')
+    except UnicodeDecodeError:
+        raise IDNAError('Invalid ASCII in A-label')
+    if uts46:
+        s = uts46_remap(s, std3_rules, False)
+    trailing_dot = False
+    result = []
+    if not strict:
+        labels = _unicode_dots_re.split(s)
+    else:
+        labels = s.split('.')
+    if not labels or labels == ['']:
+        raise IDNAError('Empty domain')
+    if not labels[-1]:
+        del labels[-1]
+        trailing_dot = True
+    for label in labels:
+        s = ulabel(label)
+        if s:
+            result.append(s)
+        else:
+            raise IDNAError('Empty label')
+    if trailing_dot:
+        result.append('')
+    return '.'.join(result)

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna/intranges.py

@@ -0,0 +1,54 @@
+"""
+Given a list of integers, made up of (hopefully) a small number of long runs
+of consecutive integers, compute a representation of the form
+((start1, end1), (start2, end2) ...). Then answer the question "was x present
+in the original list?" in time O(log(# runs)).
+"""
+
+import bisect
+from typing import List, Tuple
+
+def intranges_from_list(list_: List[int]) -> Tuple[int, ...]:
+    """Represent a list of integers as a sequence of ranges:
+    ((start_0, end_0), (start_1, end_1), ...), such that the original
+    integers are exactly those x such that start_i <= x < end_i for some i.
+
+    Ranges are encoded as single integers (start << 32 | end), not as tuples.
+    """
+
+    sorted_list = sorted(list_)
+    ranges = []
+    last_write = -1
+    for i in range(len(sorted_list)):
+        if i+1 < len(sorted_list):
+            if sorted_list[i] == sorted_list[i+1]-1:
+                continue
+        current_range = sorted_list[last_write+1:i+1]
+        ranges.append(_encode_range(current_range[0], current_range[-1] + 1))
+        last_write = i
+
+    return tuple(ranges)
+
+def _encode_range(start: int, end: int) -> int:
+    return (start << 32) | end
+
+def _decode_range(r: int) -> Tuple[int, int]:
+    return (r >> 32), (r & ((1 << 32) - 1))
+
+
+def intranges_contain(int_: int, ranges: Tuple[int, ...]) -> bool:
+    """Determine if `int_` falls into one of the ranges in `ranges`."""
+    tuple_ = _encode_range(int_, 0)
+    pos = bisect.bisect_left(ranges, tuple_)
+    # we could be immediately ahead of a tuple (start, end)
+    # with start < int_ <= end
+    if pos > 0:
+        left, right = _decode_range(ranges[pos-1])
+        if left <= int_ < right:
+            return True
+    # or we could be immediately behind a tuple (int_, end)
+    if pos < len(ranges):
+        left, _ = _decode_range(ranges[pos])
+        if left == int_:
+            return True
+    return False

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/idna/package_data.py

@@ -0,0 +1,2 @@
+__version__ = '3.8'
+

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/requests-2.32.3.dist-info/INSTALLER

@@ -0,0 +1 @@
+pip

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/requests-2.32.3.dist-info/LICENSE

@@ -0,0 +1,175 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/requests-2.32.3.dist-info/METADATA

@@ -0,0 +1,119 @@
+Metadata-Version: 2.1
+Name: requests
+Version: 2.32.3
+Summary: Python HTTP for Humans.
+Home-page: https://requests.readthedocs.io
+Author: Kenneth Reitz
+Author-email: me@kennethreitz.org
+License: Apache-2.0
+Project-URL: Documentation, https://requests.readthedocs.io
+Project-URL: Source, https://github.com/psf/requests
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Environment :: Web Environment
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: charset-normalizer <4,>=2
+Requires-Dist: idna <4,>=2.5
+Requires-Dist: urllib3 <3,>=1.21.1
+Requires-Dist: certifi >=2017.4.17
+Provides-Extra: security
+Provides-Extra: socks
+Requires-Dist: PySocks !=1.5.7,>=1.5.6 ; extra == 'socks'
+Provides-Extra: use_chardet_on_py3
+Requires-Dist: chardet <6,>=3.0.2 ; extra == 'use_chardet_on_py3'
+
+# Requests
+
+**Requests** is a simple, yet elegant, HTTP library.
+
+```python
+>>> import requests
+>>> r = requests.get('https://httpbin.org/basic-auth/user/pass', auth=('user', 'pass'))
+>>> r.status_code
+200
+>>> r.headers['content-type']
+'application/json; charset=utf8'
+>>> r.encoding
+'utf-8'
+>>> r.text
+'{"authenticated": true, ...'
+>>> r.json()
+{'authenticated': True, ...}
+```
+
+Requests allows you to send HTTP/1.1 requests extremely easily. There’s no need to manually add query strings to your URLs, or to form-encode your `PUT` & `POST` data — but nowadays, just use the `json` method!
+
+Requests is one of the most downloaded Python packages today, pulling in around `30M downloads / week`— according to GitHub, Requests is currently [depended upon](https://github.com/psf/requests/network/dependents?package_id=UGFja2FnZS01NzA4OTExNg%3D%3D) by `1,000,000+` repositories. You may certainly put your trust in this code.
+
+[![Downloads](https://static.pepy.tech/badge/requests/month)](https://pepy.tech/project/requests)
+[![Supported Versions](https://img.shields.io/pypi/pyversions/requests.svg)](https://pypi.org/project/requests)
+[![Contributors](https://img.shields.io/github/contributors/psf/requests.svg)](https://github.com/psf/requests/graphs/contributors)
+
+## Installing Requests and Supported Versions
+
+Requests is available on PyPI:
+
+```console
+$ python -m pip install requests
+```
+
+Requests officially supports Python 3.8+.
+
+## Supported Features & Best–Practices
+
+Requests is ready for the demands of building robust and reliable HTTP–speaking applications, for the needs of today.
+
+- Keep-Alive & Connection Pooling
+- International Domains and URLs
+- Sessions with Cookie Persistence
+- Browser-style TLS/SSL Verification
+- Basic & Digest Authentication
+- Familiar `dict`–like Cookies
+- Automatic Content Decompression and Decoding
+- Multi-part File Uploads
+- SOCKS Proxy Support
+- Connection Timeouts
+- Streaming Downloads
+- Automatic honoring of `.netrc`
+- Chunked HTTP Requests
+
+## API Reference and User Guide available on [Read the Docs](https://requests.readthedocs.io)
+
+[![Read the Docs](https://raw.githubusercontent.com/psf/requests/main/ext/ss.png)](https://requests.readthedocs.io)
+
+## Cloning the repository
+
+When cloning the Requests repository, you may need to add the `-c
+fetch.fsck.badTimezone=ignore` flag to avoid an error about a bad commit (see
+[this issue](https://github.com/psf/requests/issues/2690) for more background):
+
+```shell
+git clone -c fetch.fsck.badTimezone=ignore https://github.com/psf/requests.git
+```
+
+You can also apply this setting to your global Git config:
+
+```shell
+git config --global fetch.fsck.badTimezone ignore
+```
+
+---
+
+[![Kenneth Reitz](https://raw.githubusercontent.com/psf/requests/main/ext/kr.png)](https://kennethreitz.org) [![Python Software Foundation](https://raw.githubusercontent.com/psf/requests/main/ext/psf.png)](https://www.python.org/psf)

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/requests-2.32.3.dist-info/RECORD

@@ -0,0 +1,43 @@
+requests-2.32.3.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
+requests-2.32.3.dist-info/LICENSE,sha256=CeipvOyAZxBGUsFoaFqwkx54aPnIKEtm9a5u2uXxEws,10142
+requests-2.32.3.dist-info/METADATA,sha256=ZY7oRUweLnb7jCEnEW9hFWs7IpQbNVnAA4ncpwA4WBo,4610
+requests-2.32.3.dist-info/RECORD,,
+requests-2.32.3.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+requests-2.32.3.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+requests-2.32.3.dist-info/top_level.txt,sha256=fMSVmHfb5rbGOo6xv-O_tUX6j-WyixssE-SnwcDRxNQ,9
+requests/__init__.py,sha256=4xaAERmPDIBPsa2PsjpU9r06yooK-2mZKHTZAhWRWts,5072
+requests/__pycache__/__init__.cpython-312.pyc,,
+requests/__pycache__/__version__.cpython-312.pyc,,
+requests/__pycache__/_internal_utils.cpython-312.pyc,,
+requests/__pycache__/adapters.cpython-312.pyc,,
+requests/__pycache__/api.cpython-312.pyc,,
+requests/__pycache__/auth.cpython-312.pyc,,
+requests/__pycache__/certs.cpython-312.pyc,,
+requests/__pycache__/compat.cpython-312.pyc,,
+requests/__pycache__/cookies.cpython-312.pyc,,
+requests/__pycache__/exceptions.cpython-312.pyc,,
+requests/__pycache__/help.cpython-312.pyc,,
+requests/__pycache__/hooks.cpython-312.pyc,,
+requests/__pycache__/models.cpython-312.pyc,,
+requests/__pycache__/packages.cpython-312.pyc,,
+requests/__pycache__/sessions.cpython-312.pyc,,
+requests/__pycache__/status_codes.cpython-312.pyc,,
+requests/__pycache__/structures.cpython-312.pyc,,
+requests/__pycache__/utils.cpython-312.pyc,,
+requests/__version__.py,sha256=FVfglgZmNQnmYPXpOohDU58F5EUb_-VnSTaAesS187g,435
+requests/_internal_utils.py,sha256=nMQymr4hs32TqVo5AbCrmcJEhvPUh7xXlluyqwslLiQ,1495
+requests/adapters.py,sha256=KIcecscqam6reOCXRl4DwP4jX8Jcl8sd57ft17KR2cQ,27451
+requests/api.py,sha256=_Zb9Oa7tzVIizTKwFrPjDEY9ejtm_OnSRERnADxGsQs,6449
+requests/auth.py,sha256=kF75tqnLctZ9Mf_hm9TZIj4cQWnN5uxRz8oWsx5wmR0,10186
+requests/certs.py,sha256=Z9Sb410Anv6jUFTyss0jFFhU6xst8ctELqfy8Ev23gw,429
+requests/compat.py,sha256=C5w_DPLSurXPgcdWU78fora0APmbYkX2G89QvH5xzPA,1817
+requests/cookies.py,sha256=bNi-iqEj4NPZ00-ob-rHvzkvObzN3lEpgw3g6paS3Xw,18590
+requests/exceptions.py,sha256=jJPS1UWATs86ShVUaLorTiJb1SaGuoNEWgICJep-VkY,4260
+requests/help.py,sha256=gPX5d_H7Xd88aDABejhqGgl9B1VFRTt5BmiYvL3PzIQ,3875
+requests/hooks.py,sha256=CiuysiHA39V5UfcCBXFIx83IrDpuwfN9RcTUgv28ftQ,733
+requests/models.py,sha256=k42roXzC8u_OagAPQi9U4MkfO7i4r2FdaqvMqstPehc,35418
+requests/packages.py,sha256=_g0gZ681UyAlKHRjH6kanbaoxx2eAb6qzcXiODyTIoc,904
+requests/sessions.py,sha256=ykTI8UWGSltOfH07HKollH7kTBGw4WhiBVaQGmckTw4,30495
+requests/status_codes.py,sha256=iJUAeA25baTdw-6PfD0eF4qhpINDJRJI-yaMqxs4LEI,4322
+requests/structures.py,sha256=-IbmhVz06S-5aPSZuUthZ6-6D9XOjRuTXHOabY041XM,2912
+requests/utils.py,sha256=HiQC6Nq_Da3ktaMiFzQkh-dCk3iQHHKEsYS5kDc-8Cw,33619

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/requests-2.32.3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.43.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/requests-2.32.3.dist-info/top_level.txt

@@ -0,0 +1 @@
+requests

examples/lambda-layers/lambda-layer1/python/lib/python3.12/site-packages/requests/__init__.py

@@ -0,0 +1,184 @@
+#   __
+#  /__)  _  _     _   _ _/   _
+# / (   (- (/ (/ (- _)  /  _)
+#          /
+
+"""
+Requests HTTP Library
+~~~~~~~~~~~~~~~~~~~~~
+
+Requests is an HTTP library, written in Python, for human beings.
+Basic GET usage:
+
+   >>> import requests
+   >>> r = requests.get('https://www.python.org')
+   >>> r.status_code
+   200
+   >>> b'Python is a programming language' in r.content
+   True
+
+... or POST:
+
+   >>> payload = dict(key1='value1', key2='value2')
+   >>> r = requests.post('https://httpbin.org/post', data=payload)
+   >>> print(r.text)
+   {
+     ...
+     "form": {
+       "key1": "value1",
+       "key2": "value2"
+     },
+     ...
+   }
+
+The other HTTP methods are supported - see `requests.api`. Full documentation
+is at <https://requests.readthedocs.io>.
+
+:copyright: (c) 2017 by Kenneth Reitz.
+:license: Apache 2.0, see LICENSE for more details.
+"""
+
+import warnings
+
+import urllib3
+
+from .exceptions import RequestsDependencyWarning
+
+try:
+    from charset_normalizer import __version__ as charset_normalizer_version
+except ImportError:
+    charset_normalizer_version = None
+
+try:
+    from chardet import __version__ as chardet_version
+except ImportError:
+    chardet_version = None
+
+
+def check_compatibility(urllib3_version, chardet_version, charset_normalizer_version):
+    urllib3_version = urllib3_version.split(".")
+    assert urllib3_version != ["dev"]  # Verify urllib3 isn't installed from git.
+
+    # Sometimes, urllib3 only reports its version as 16.1.
+    if len(urllib3_version) == 2:
+        urllib3_version.append("0")
+
+    # Check urllib3 for compatibility.
+    major, minor, patch = urllib3_version  # noqa: F811
+    major, minor, patch = int(major), int(minor), int(patch)
+    # urllib3 >= 1.21.1
+    assert major >= 1
+    if major == 1:
+        assert minor >= 21
+
+    # Check charset_normalizer for compatibility.
+    if chardet_version:
+        major, minor, patch = chardet_version.split(".")[:3]
+        major, minor, patch = int(major), int(minor), int(patch)
+        # chardet_version >= 3.0.2, < 6.0.0
+        assert (3, 0, 2) <= (major, minor, patch) < (6, 0, 0)
+    elif charset_normalizer_version:
+        major, minor, patch = charset_normalizer_version.split(".")[:3]
+        major, minor, patch = int(major), int(minor), int(patch)
+        # charset_normalizer >= 2.0.0 < 4.0.0
+        assert (2, 0, 0) <= (major, minor, patch) < (4, 0, 0)
+    else:
+        warnings.warn(
+            "Unable to find acceptable character detection dependency "
+            "(chardet or charset_normalizer).",
+            RequestsDependencyWarning,
+        )
+
+
+def _check_cryptography(cryptography_version):
+    # cryptography < 1.3.4
+    try:
+        cryptography_version = list(map(int, cryptography_version.split(".")))
+    except ValueError:
+        return
+
+    if cryptography_version < [1, 3, 4]:
+        warning = "Old version of cryptography ({}) may cause slowdown.".format(
+            cryptography_version
+        )
+        warnings.warn(warning, RequestsDependencyWarning)
+
+
+# Check imported dependencies for compatibility.
+try:
+    check_compatibility(
+        urllib3.__version__, chardet_version, charset_normalizer_version
+    )
+except (AssertionError, ValueError):
+    warnings.warn(
+        "urllib3 ({}) or chardet ({})/charset_normalizer ({}) doesn't match a supported "
+        "version!".format(
+            urllib3.__version__, chardet_version, charset_normalizer_version
+        ),
+        RequestsDependencyWarning,
+    )
+
+# Attempt to enable urllib3's fallback for SNI support
+# if the standard library doesn't support SNI or the
+# 'ssl' library isn't available.
+try:
+    try:
+        import ssl
+    except ImportError:
+        ssl = None
+
+    if not getattr(ssl, "HAS_SNI", False):
+        from urllib3.contrib import pyopenssl
+
+        pyopenssl.inject_into_urllib3()
+
+        # Check cryptography version
+        from cryptography import __version__ as cryptography_version
+
+        _check_cryptography(cryptography_version)
+except ImportError:
+    pass
+
+# urllib3's DependencyWarnings should be silenced.
+from urllib3.exceptions import DependencyWarning
+
+warnings.simplefilter("ignore", DependencyWarning)
+
+# Set default logging handler to avoid "No handler found" warnings.
+import logging
+from logging import NullHandler
+
+from . import packages, utils
+from .__version__ import (
+    __author__,
+    __author_email__,
+    __build__,
+    __cake__,
+    __copyright__,
+    __description__,
+    __license__,
+    __title__,
+    __url__,
+    __version__,
+)
+from .api import delete, get, head, options, patch, post, put, request
+from .exceptions import (
+    ConnectionError,
+    ConnectTimeout,
+    FileModeWarning,
+    HTTPError,
+    JSONDecodeError,
+    ReadTimeout,
+    RequestException,
+    Timeout,
+    TooManyRedirects,
+    URLRequired,
+)
+from .models import PreparedRequest, Request, Response
+from .sessions import Session, session
+from .status_codes import codes
+
+logging.getLogger(__name__).addHandler(NullHandler())
+
+# FileModeWarnings go off per the default.
+warnings.simplefilter("default", FileModeWarning, append=True)