added lambda layer for thingsboard rest api

AWS Lambda Layer/python/lib/python3.9/site-packages/certifi/__init__.py

@@ -0,0 +1,4 @@
+from .core import contents, where
+
+__all__ = ["contents", "where"]
+__version__ = "2022.05.18.1"

AWS Lambda Layer/python/lib/python3.9/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())

AWS Lambda Layer/python/lib/python3.9/site-packages/certifi/core.py

@@ -0,0 +1,68 @@
+"""
+certifi.py
+~~~~~~~~~~
+
+This module returns the installation location of cacert.pem or its contents.
+"""
+import os
+import types
+from typing import Union
+
+try:
+    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__())
+
+        return _CACERT_PATH
+
+
+except ImportError:
+    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")

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/__init__.py

@@ -0,0 +1,56 @@
+# -*- 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, normalize
+from .legacy import (
+    CharsetDetector,
+    CharsetDoctor,
+    CharsetNormalizerMatch,
+    CharsetNormalizerMatches,
+    detect,
+)
+from .models import CharsetMatch, CharsetMatches
+from .utils import set_logging_handler
+from .version import VERSION, __version__
+
+__all__ = (
+    "from_fp",
+    "from_path",
+    "from_bytes",
+    "normalize",
+    "detect",
+    "CharsetMatch",
+    "CharsetMatches",
+    "CharsetNormalizerMatch",
+    "CharsetNormalizerMatches",
+    "CharsetDetector",
+    "CharsetDoctor",
+    "__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())

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/api.py

@@ -0,0 +1,608 @@
+import logging
+from os.path import basename, splitext
+from typing import BinaryIO, List, Optional, Set
+
+try:
+    from os import PathLike
+except ImportError:  # pragma: no cover
+    PathLike = str  # type: ignore
+
+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,
+    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: bytes,
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.2,
+    cp_isolation: List[str] = None,
+    cp_exclusion: List[str] = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+) -> 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 blocs 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 = logger.level  # type: int
+        logger.addHandler(explain_handler)
+        logger.setLevel(TRACE)
+
+    length = len(sequences)  # type: int
+
+    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 = len(sequences) < TOO_SMALL_SEQUENCE  # type: bool
+    is_too_large_sequence = len(sequences) >= TOO_BIG_SEQUENCE  # type: bool
+
+    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 = []  # type: List[str]
+
+    specified_encoding = (
+        any_specified_encoding(sequences) if preemptive_behaviour else None
+    )  # type: Optional[str]
+
+    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()  # type: Set[str]
+    tested_but_hard_failure = []  # type: List[str]
+    tested_but_soft_failure = []  # type: List[str]
+
+    fallback_ascii = None  # type: Optional[CharsetMatch]
+    fallback_u8 = None  # type: Optional[CharsetMatch]
+    fallback_specified = None  # type: Optional[CharsetMatch]
+
+    results = CharsetMatches()  # type: 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 = None  # type: Optional[str]
+        bom_or_sig_available = sig_encoding == encoding_iana  # type: bool
+        strip_sig_or_bom = bom_or_sig_available and should_strip_sig_or_bom(
+            encoding_iana
+        )  # type: bool
+
+        if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
+            logger.log(
+                TRACE,
+                "Encoding %s wont be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
+                encoding_iana,
+            )
+            continue
+
+        try:
+            is_multi_byte_decoder = is_multi_byte_encoding(encoding_iana)  # type: bool
+        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 = False  # type: bool
+
+        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 = (
+            is_multi_byte_decoder
+            and decoded_payload is not None
+            and len(decoded_payload) < length
+        )  # type: bool
+
+        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(len(r_) / 4)  # type: int
+
+        max_chunk_gave_up = max(max_chunk_gave_up, 2)
+        early_stop_count = 0  # type: int
+        lazy_str_hard_failure = False
+
+        md_chunks = []  # type: List[str]
+        md_ratios = []
+
+        for i in r_:
+            if i + chunk_size > length + 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
+
+            try:
+                chunk = cut_sequence.decode(
+                    encoding_iana,
+                    errors="ignore" if is_multi_byte_decoder else "strict",
+                )  # type: str
+            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
+                break
+
+            # 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 and sequences[i] >= 0x80:
+
+                chunk_partial_size_chk = min(chunk_size, 16)  # type: int
+
+                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 : 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 chunk[:chunk_partial_size_chk] in decoded_payload:
+                            break
+
+            md_chunks.append(chunk)
+
+            md_ratios.append(mess_ratio(chunk, threshold))
+
+            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
+
+        # 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 = (
+            sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
+        )  # type: float
+        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 (
+                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 = encoding_languages(encoding_iana)  # type: List[str]
+        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, 0.1, ",".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: List[str] = None,
+    cp_exclusion: List[str] = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+) -> 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,
+    )
+
+
+def from_path(
+    path: PathLike,
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: List[str] = None,
+    cp_exclusion: List[str] = None,
+    preemptive_behaviour: bool = True,
+    explain: bool = False,
+) -> 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,
+        )
+
+
+def normalize(
+    path: PathLike,
+    steps: int = 5,
+    chunk_size: int = 512,
+    threshold: float = 0.20,
+    cp_isolation: List[str] = None,
+    cp_exclusion: List[str] = None,
+    preemptive_behaviour: bool = True,
+) -> CharsetMatch:
+    """
+    Take a (text-based) file path and try to create another file next to it, this time using UTF-8.
+    """
+    results = from_path(
+        path,
+        steps,
+        chunk_size,
+        threshold,
+        cp_isolation,
+        cp_exclusion,
+        preemptive_behaviour,
+    )
+
+    filename = basename(path)
+    target_extensions = list(splitext(filename))
+
+    if len(results) == 0:
+        raise IOError(
+            'Unable to normalize "{}", no encoding charset seems to fit.'.format(
+                filename
+            )
+        )
+
+    result = results.best()
+
+    target_extensions[0] += "-" + result.encoding  # type: ignore
+
+    with open(
+        "{}".format(str(path).replace(filename, "".join(target_extensions))), "wb"
+    ) as fp:
+        fp.write(result.output())  # type: ignore
+
+    return result  # type: ignore

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/cd.py

@@ -0,0 +1,340 @@
+import importlib
+from codecs import IncrementalDecoder
+from collections import Counter, OrderedDict
+from functools import lru_cache
+from typing import Dict, List, Optional, Tuple
+
+from .assets import FREQUENCIES
+from .constant import 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  # type: ignore
+
+    p = decoder(errors="ignore")  # type: IncrementalDecoder
+    seen_ranges = {}  # type: Dict[str, int]
+    character_count = 0  # type: int
+
+    for i in range(0x40, 0xFF):
+        chunk = p.decode(bytes([i]))  # type: str
+
+        if chunk:
+            character_range = unicode_range(chunk)  # type: Optional[str]
+
+            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 = []  # type: 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 = encoding_unicode_range(iana_name)  # type: List[str]
+    primary_range = None  # type: Optional[str]
+
+    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", "Classical 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 = False  # type: bool
+    target_pure_latin = True  # type: bool
+
+    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 = []  # type: 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 = len(language_characters)  # type: int
+
+        character_match_count = len(
+            [c for c in language_characters if c in characters]
+        )  # type: int
+
+        ratio = character_match_count / character_count  # type: float
+
+        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 = 0  # type: int
+
+    for character in ordered_characters:
+        if character not in FREQUENCIES[language]:
+            continue
+
+        characters_before_source = FREQUENCIES[language][
+            0 : FREQUENCIES[language].index(character)
+        ]  # type: List[str]
+        characters_after_source = FREQUENCIES[language][
+            FREQUENCIES[language].index(character) :
+        ]  # type: List[str]
+
+        characters_before = ordered_characters[
+            0 : ordered_characters.index(character)
+        ]  # type: List[str]
+        characters_after = ordered_characters[
+            ordered_characters.index(character) :
+        ]  # type: List[str]
+
+        before_match_count = [
+            e in characters_before for e in characters_before_source
+        ].count(
+            True
+        )  # type: int
+        after_match_count = [
+            e in characters_after for e in characters_after_source
+        ].count(
+            True
+        )  # type: int
+
+        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 = OrderedDict()  # type: Dict[str, str]
+
+    for character in decoded_sequence:
+        if character.isalpha() is False:
+            continue
+
+        character_range = unicode_range(character)  # type: Optional[str]
+
+        if character_range is None:
+            continue
+
+        layer_target_range = None  # type: Optional[str]
+
+        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 = OrderedDict()  # type: 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)
+
+
+@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 = []  # type: List[Tuple[str, float]]
+    ignore_non_latin = False  # type: bool
+
+    sufficient_match_count = 0  # type: int
+
+    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 = Counter(layer)  # type: Counter
+        most_common = sequence_frequencies.most_common()
+
+        character_count = sum(o for c, o in most_common)  # type: int
+
+        if character_count <= TOO_SMALL_SEQUENCE:
+            continue
+
+        popular_character_ordered = [c for c, o in most_common]  # type: List[str]
+
+        for language in lg_inclusion_list or alphabet_languages(
+            popular_character_ordered, ignore_non_latin
+        ):
+            ratio = characters_popularity_compare(
+                language, popular_character_ordered
+            )  # type: float
+
+            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(results, key=lambda x: x[1], reverse=True)

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/cli/normalizer.py

@@ -0,0 +1,290 @@
+import argparse
+import sys
+from json import dumps
+from os.path import abspath
+from platform import python_version
+from typing import List
+
+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: 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=0.1,
+        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 {}".format(
+            __version__, python_version()
+        ),
+        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
+
+                o_ = my_file.name.split(".")  # type: List[str]
+
+                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 = abspath("./{}".format(".".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()

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/constant.py

@@ -0,0 +1,503 @@
+from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE
+from collections import OrderedDict
+from encodings.aliases import aliases
+from re import IGNORECASE, compile as re_compile
+from typing import Dict, List, Set, Union
+
+from .assets import FREQUENCIES
+
+# Contain for each eligible encoding a list of/item bytes SIG/BOM
+ENCODING_MARKS = OrderedDict(
+    [
+        ("utf_8", BOM_UTF8),
+        (
+            "utf_7",
+            [
+                b"\x2b\x2f\x76\x38",
+                b"\x2b\x2f\x76\x39",
+                b"\x2b\x2f\x76\x2b",
+                b"\x2b\x2f\x76\x2f",
+                b"\x2b\x2f\x76\x38\x2d",
+            ],
+        ),
+        ("gb18030", b"\x84\x31\x95\x33"),
+        ("utf_32", [BOM_UTF32_BE, BOM_UTF32_LE]),
+        ("utf_16", [BOM_UTF16_BE, BOM_UTF16_LE]),
+    ]
+)  # type: Dict[str, Union[bytes, List[bytes]]]
+
+TOO_SMALL_SEQUENCE = 32  # type: int
+TOO_BIG_SEQUENCE = int(10e6)  # type: int
+
+UTF8_MAXIMAL_ALLOCATION = 1112064  # type: int
+
+UNICODE_RANGES_COMBINED = {
+    "Control character": range(31 + 1),
+    "Basic Latin": range(32, 127 + 1),
+    "Latin-1 Supplement": range(128, 255 + 1),
+    "Latin Extended-A": range(256, 383 + 1),
+    "Latin Extended-B": range(384, 591 + 1),
+    "IPA Extensions": range(592, 687 + 1),
+    "Spacing Modifier Letters": range(688, 767 + 1),
+    "Combining Diacritical Marks": range(768, 879 + 1),
+    "Greek and Coptic": range(880, 1023 + 1),
+    "Cyrillic": range(1024, 1279 + 1),
+    "Cyrillic Supplement": range(1280, 1327 + 1),
+    "Armenian": range(1328, 1423 + 1),
+    "Hebrew": range(1424, 1535 + 1),
+    "Arabic": range(1536, 1791 + 1),
+    "Syriac": range(1792, 1871 + 1),
+    "Arabic Supplement": range(1872, 1919 + 1),
+    "Thaana": range(1920, 1983 + 1),
+    "NKo": range(1984, 2047 + 1),
+    "Samaritan": range(2048, 2111 + 1),
+    "Mandaic": range(2112, 2143 + 1),
+    "Syriac Supplement": range(2144, 2159 + 1),
+    "Arabic Extended-A": range(2208, 2303 + 1),
+    "Devanagari": range(2304, 2431 + 1),
+    "Bengali": range(2432, 2559 + 1),
+    "Gurmukhi": range(2560, 2687 + 1),
+    "Gujarati": range(2688, 2815 + 1),
+    "Oriya": range(2816, 2943 + 1),
+    "Tamil": range(2944, 3071 + 1),
+    "Telugu": range(3072, 3199 + 1),
+    "Kannada": range(3200, 3327 + 1),
+    "Malayalam": range(3328, 3455 + 1),
+    "Sinhala": range(3456, 3583 + 1),
+    "Thai": range(3584, 3711 + 1),
+    "Lao": range(3712, 3839 + 1),
+    "Tibetan": range(3840, 4095 + 1),
+    "Myanmar": range(4096, 4255 + 1),
+    "Georgian": range(4256, 4351 + 1),
+    "Hangul Jamo": range(4352, 4607 + 1),
+    "Ethiopic": range(4608, 4991 + 1),
+    "Ethiopic Supplement": range(4992, 5023 + 1),
+    "Cherokee": range(5024, 5119 + 1),
+    "Unified Canadian Aboriginal Syllabics": range(5120, 5759 + 1),
+    "Ogham": range(5760, 5791 + 1),
+    "Runic": range(5792, 5887 + 1),
+    "Tagalog": range(5888, 5919 + 1),
+    "Hanunoo": range(5920, 5951 + 1),
+    "Buhid": range(5952, 5983 + 1),
+    "Tagbanwa": range(5984, 6015 + 1),
+    "Khmer": range(6016, 6143 + 1),
+    "Mongolian": range(6144, 6319 + 1),
+    "Unified Canadian Aboriginal Syllabics Extended": range(6320, 6399 + 1),
+    "Limbu": range(6400, 6479 + 1),
+    "Tai Le": range(6480, 6527 + 1),
+    "New Tai Lue": range(6528, 6623 + 1),
+    "Khmer Symbols": range(6624, 6655 + 1),
+    "Buginese": range(6656, 6687 + 1),
+    "Tai Tham": range(6688, 6831 + 1),
+    "Combining Diacritical Marks Extended": range(6832, 6911 + 1),
+    "Balinese": range(6912, 7039 + 1),
+    "Sundanese": range(7040, 7103 + 1),
+    "Batak": range(7104, 7167 + 1),
+    "Lepcha": range(7168, 7247 + 1),
+    "Ol Chiki": range(7248, 7295 + 1),
+    "Cyrillic Extended C": range(7296, 7311 + 1),
+    "Sundanese Supplement": range(7360, 7375 + 1),
+    "Vedic Extensions": range(7376, 7423 + 1),
+    "Phonetic Extensions": range(7424, 7551 + 1),
+    "Phonetic Extensions Supplement": range(7552, 7615 + 1),
+    "Combining Diacritical Marks Supplement": range(7616, 7679 + 1),
+    "Latin Extended Additional": range(7680, 7935 + 1),
+    "Greek Extended": range(7936, 8191 + 1),
+    "General Punctuation": range(8192, 8303 + 1),
+    "Superscripts and Subscripts": range(8304, 8351 + 1),
+    "Currency Symbols": range(8352, 8399 + 1),
+    "Combining Diacritical Marks for Symbols": range(8400, 8447 + 1),
+    "Letterlike Symbols": range(8448, 8527 + 1),
+    "Number Forms": range(8528, 8591 + 1),
+    "Arrows": range(8592, 8703 + 1),
+    "Mathematical Operators": range(8704, 8959 + 1),
+    "Miscellaneous Technical": range(8960, 9215 + 1),
+    "Control Pictures": range(9216, 9279 + 1),
+    "Optical Character Recognition": range(9280, 9311 + 1),
+    "Enclosed Alphanumerics": range(9312, 9471 + 1),
+    "Box Drawing": range(9472, 9599 + 1),
+    "Block Elements": range(9600, 9631 + 1),
+    "Geometric Shapes": range(9632, 9727 + 1),
+    "Miscellaneous Symbols": range(9728, 9983 + 1),
+    "Dingbats": range(9984, 10175 + 1),
+    "Miscellaneous Mathematical Symbols-A": range(10176, 10223 + 1),
+    "Supplemental Arrows-A": range(10224, 10239 + 1),
+    "Braille Patterns": range(10240, 10495 + 1),
+    "Supplemental Arrows-B": range(10496, 10623 + 1),
+    "Miscellaneous Mathematical Symbols-B": range(10624, 10751 + 1),
+    "Supplemental Mathematical Operators": range(10752, 11007 + 1),
+    "Miscellaneous Symbols and Arrows": range(11008, 11263 + 1),
+    "Glagolitic": range(11264, 11359 + 1),
+    "Latin Extended-C": range(11360, 11391 + 1),
+    "Coptic": range(11392, 11519 + 1),
+    "Georgian Supplement": range(11520, 11567 + 1),
+    "Tifinagh": range(11568, 11647 + 1),
+    "Ethiopic Extended": range(11648, 11743 + 1),
+    "Cyrillic Extended-A": range(11744, 11775 + 1),
+    "Supplemental Punctuation": range(11776, 11903 + 1),
+    "CJK Radicals Supplement": range(11904, 12031 + 1),
+    "Kangxi Radicals": range(12032, 12255 + 1),
+    "Ideographic Description Characters": range(12272, 12287 + 1),
+    "CJK Symbols and Punctuation": range(12288, 12351 + 1),
+    "Hiragana": range(12352, 12447 + 1),
+    "Katakana": range(12448, 12543 + 1),
+    "Bopomofo": range(12544, 12591 + 1),
+    "Hangul Compatibility Jamo": range(12592, 12687 + 1),
+    "Kanbun": range(12688, 12703 + 1),
+    "Bopomofo Extended": range(12704, 12735 + 1),
+    "CJK Strokes": range(12736, 12783 + 1),
+    "Katakana Phonetic Extensions": range(12784, 12799 + 1),
+    "Enclosed CJK Letters and Months": range(12800, 13055 + 1),
+    "CJK Compatibility": range(13056, 13311 + 1),
+    "CJK Unified Ideographs Extension A": range(13312, 19903 + 1),
+    "Yijing Hexagram Symbols": range(19904, 19967 + 1),
+    "CJK Unified Ideographs": range(19968, 40959 + 1),
+    "Yi Syllables": range(40960, 42127 + 1),
+    "Yi Radicals": range(42128, 42191 + 1),
+    "Lisu": range(42192, 42239 + 1),
+    "Vai": range(42240, 42559 + 1),
+    "Cyrillic Extended-B": range(42560, 42655 + 1),
+    "Bamum": range(42656, 42751 + 1),
+    "Modifier Tone Letters": range(42752, 42783 + 1),
+    "Latin Extended-D": range(42784, 43007 + 1),
+    "Syloti Nagri": range(43008, 43055 + 1),
+    "Common Indic Number Forms": range(43056, 43071 + 1),
+    "Phags-pa": range(43072, 43135 + 1),
+    "Saurashtra": range(43136, 43231 + 1),
+    "Devanagari Extended": range(43232, 43263 + 1),
+    "Kayah Li": range(43264, 43311 + 1),
+    "Rejang": range(43312, 43359 + 1),
+    "Hangul Jamo Extended-A": range(43360, 43391 + 1),
+    "Javanese": range(43392, 43487 + 1),
+    "Myanmar Extended-B": range(43488, 43519 + 1),
+    "Cham": range(43520, 43615 + 1),
+    "Myanmar Extended-A": range(43616, 43647 + 1),
+    "Tai Viet": range(43648, 43743 + 1),
+    "Meetei Mayek Extensions": range(43744, 43775 + 1),
+    "Ethiopic Extended-A": range(43776, 43823 + 1),
+    "Latin Extended-E": range(43824, 43887 + 1),
+    "Cherokee Supplement": range(43888, 43967 + 1),
+    "Meetei Mayek": range(43968, 44031 + 1),
+    "Hangul Syllables": range(44032, 55215 + 1),
+    "Hangul Jamo Extended-B": range(55216, 55295 + 1),
+    "High Surrogates": range(55296, 56191 + 1),
+    "High Private Use Surrogates": range(56192, 56319 + 1),
+    "Low Surrogates": range(56320, 57343 + 1),
+    "Private Use Area": range(57344, 63743 + 1),
+    "CJK Compatibility Ideographs": range(63744, 64255 + 1),
+    "Alphabetic Presentation Forms": range(64256, 64335 + 1),
+    "Arabic Presentation Forms-A": range(64336, 65023 + 1),
+    "Variation Selectors": range(65024, 65039 + 1),
+    "Vertical Forms": range(65040, 65055 + 1),
+    "Combining Half Marks": range(65056, 65071 + 1),
+    "CJK Compatibility Forms": range(65072, 65103 + 1),
+    "Small Form Variants": range(65104, 65135 + 1),
+    "Arabic Presentation Forms-B": range(65136, 65279 + 1),
+    "Halfwidth and Fullwidth Forms": range(65280, 65519 + 1),
+    "Specials": range(65520, 65535 + 1),
+    "Linear B Syllabary": range(65536, 65663 + 1),
+    "Linear B Ideograms": range(65664, 65791 + 1),
+    "Aegean Numbers": range(65792, 65855 + 1),
+    "Ancient Greek Numbers": range(65856, 65935 + 1),
+    "Ancient Symbols": range(65936, 65999 + 1),
+    "Phaistos Disc": range(66000, 66047 + 1),
+    "Lycian": range(66176, 66207 + 1),
+    "Carian": range(66208, 66271 + 1),
+    "Coptic Epact Numbers": range(66272, 66303 + 1),
+    "Old Italic": range(66304, 66351 + 1),
+    "Gothic": range(66352, 66383 + 1),
+    "Old Permic": range(66384, 66431 + 1),
+    "Ugaritic": range(66432, 66463 + 1),
+    "Old Persian": range(66464, 66527 + 1),
+    "Deseret": range(66560, 66639 + 1),
+    "Shavian": range(66640, 66687 + 1),
+    "Osmanya": range(66688, 66735 + 1),
+    "Osage": range(66736, 66815 + 1),
+    "Elbasan": range(66816, 66863 + 1),
+    "Caucasian Albanian": range(66864, 66927 + 1),
+    "Linear A": range(67072, 67455 + 1),
+    "Cypriot Syllabary": range(67584, 67647 + 1),
+    "Imperial Aramaic": range(67648, 67679 + 1),
+    "Palmyrene": range(67680, 67711 + 1),
+    "Nabataean": range(67712, 67759 + 1),
+    "Hatran": range(67808, 67839 + 1),
+    "Phoenician": range(67840, 67871 + 1),
+    "Lydian": range(67872, 67903 + 1),
+    "Meroitic Hieroglyphs": range(67968, 67999 + 1),
+    "Meroitic Cursive": range(68000, 68095 + 1),
+    "Kharoshthi": range(68096, 68191 + 1),
+    "Old South Arabian": range(68192, 68223 + 1),
+    "Old North Arabian": range(68224, 68255 + 1),
+    "Manichaean": range(68288, 68351 + 1),
+    "Avestan": range(68352, 68415 + 1),
+    "Inscriptional Parthian": range(68416, 68447 + 1),
+    "Inscriptional Pahlavi": range(68448, 68479 + 1),
+    "Psalter Pahlavi": range(68480, 68527 + 1),
+    "Old Turkic": range(68608, 68687 + 1),
+    "Old Hungarian": range(68736, 68863 + 1),
+    "Rumi Numeral Symbols": range(69216, 69247 + 1),
+    "Brahmi": range(69632, 69759 + 1),
+    "Kaithi": range(69760, 69839 + 1),
+    "Sora Sompeng": range(69840, 69887 + 1),
+    "Chakma": range(69888, 69967 + 1),
+    "Mahajani": range(69968, 70015 + 1),
+    "Sharada": range(70016, 70111 + 1),
+    "Sinhala Archaic Numbers": range(70112, 70143 + 1),
+    "Khojki": range(70144, 70223 + 1),
+    "Multani": range(70272, 70319 + 1),
+    "Khudawadi": range(70320, 70399 + 1),
+    "Grantha": range(70400, 70527 + 1),
+    "Newa": range(70656, 70783 + 1),
+    "Tirhuta": range(70784, 70879 + 1),
+    "Siddham": range(71040, 71167 + 1),
+    "Modi": range(71168, 71263 + 1),
+    "Mongolian Supplement": range(71264, 71295 + 1),
+    "Takri": range(71296, 71375 + 1),
+    "Ahom": range(71424, 71487 + 1),
+    "Warang Citi": range(71840, 71935 + 1),
+    "Zanabazar Square": range(72192, 72271 + 1),
+    "Soyombo": range(72272, 72367 + 1),
+    "Pau Cin Hau": range(72384, 72447 + 1),
+    "Bhaiksuki": range(72704, 72815 + 1),
+    "Marchen": range(72816, 72895 + 1),
+    "Masaram Gondi": range(72960, 73055 + 1),
+    "Cuneiform": range(73728, 74751 + 1),
+    "Cuneiform Numbers and Punctuation": range(74752, 74879 + 1),
+    "Early Dynastic Cuneiform": range(74880, 75087 + 1),
+    "Egyptian Hieroglyphs": range(77824, 78895 + 1),
+    "Anatolian Hieroglyphs": range(82944, 83583 + 1),
+    "Bamum Supplement": range(92160, 92735 + 1),
+    "Mro": range(92736, 92783 + 1),
+    "Bassa Vah": range(92880, 92927 + 1),
+    "Pahawh Hmong": range(92928, 93071 + 1),
+    "Miao": range(93952, 94111 + 1),
+    "Ideographic Symbols and Punctuation": range(94176, 94207 + 1),
+    "Tangut": range(94208, 100351 + 1),
+    "Tangut Components": range(100352, 101119 + 1),
+    "Kana Supplement": range(110592, 110847 + 1),
+    "Kana Extended-A": range(110848, 110895 + 1),
+    "Nushu": range(110960, 111359 + 1),
+    "Duployan": range(113664, 113823 + 1),
+    "Shorthand Format Controls": range(113824, 113839 + 1),
+    "Byzantine Musical Symbols": range(118784, 119039 + 1),
+    "Musical Symbols": range(119040, 119295 + 1),
+    "Ancient Greek Musical Notation": range(119296, 119375 + 1),
+    "Tai Xuan Jing Symbols": range(119552, 119647 + 1),
+    "Counting Rod Numerals": range(119648, 119679 + 1),
+    "Mathematical Alphanumeric Symbols": range(119808, 120831 + 1),
+    "Sutton SignWriting": range(120832, 121519 + 1),
+    "Glagolitic Supplement": range(122880, 122927 + 1),
+    "Mende Kikakui": range(124928, 125151 + 1),
+    "Adlam": range(125184, 125279 + 1),
+    "Arabic Mathematical Alphabetic Symbols": range(126464, 126719 + 1),
+    "Mahjong Tiles": range(126976, 127023 + 1),
+    "Domino Tiles": range(127024, 127135 + 1),
+    "Playing Cards": range(127136, 127231 + 1),
+    "Enclosed Alphanumeric Supplement": range(127232, 127487 + 1),
+    "Enclosed Ideographic Supplement": range(127488, 127743 + 1),
+    "Miscellaneous Symbols and Pictographs": range(127744, 128511 + 1),
+    "Emoticons range(Emoji)": range(128512, 128591 + 1),
+    "Ornamental Dingbats": range(128592, 128639 + 1),
+    "Transport and Map Symbols": range(128640, 128767 + 1),
+    "Alchemical Symbols": range(128768, 128895 + 1),
+    "Geometric Shapes Extended": range(128896, 129023 + 1),
+    "Supplemental Arrows-C": range(129024, 129279 + 1),
+    "Supplemental Symbols and Pictographs": range(129280, 129535 + 1),
+    "CJK Unified Ideographs Extension B": range(131072, 173791 + 1),
+    "CJK Unified Ideographs Extension C": range(173824, 177983 + 1),
+    "CJK Unified Ideographs Extension D": range(177984, 178207 + 1),
+    "CJK Unified Ideographs Extension E": range(178208, 183983 + 1),
+    "CJK Unified Ideographs Extension F": range(183984, 191471 + 1),
+    "CJK Compatibility Ideographs Supplement": range(194560, 195103 + 1),
+    "Tags": range(917504, 917631 + 1),
+    "Variation Selectors Supplement": range(917760, 917999 + 1),
+}  # type: Dict[str, range]
+
+
+UNICODE_SECONDARY_RANGE_KEYWORD = [
+    "Supplement",
+    "Extended",
+    "Extensions",
+    "Modifier",
+    "Marks",
+    "Punctuation",
+    "Symbols",
+    "Forms",
+    "Operators",
+    "Miscellaneous",
+    "Drawing",
+    "Block",
+    "Shapes",
+    "Supplemental",
+    "Tags",
+]  # type: List[str]
+
+RE_POSSIBLE_ENCODING_INDICATION = re_compile(
+    r"(?:(?:encoding)|(?:charset)|(?:coding))(?:[\:= ]{1,10})(?:[\"\']?)([a-zA-Z0-9\-_]+)(?:[\"\']?)",
+    IGNORECASE,
+)
+
+IANA_SUPPORTED = sorted(
+    filter(
+        lambda x: x.endswith("_codec") is False
+        and x not in {"rot_13", "tactis", "mbcs"},
+        list(set(aliases.values())),
+    )
+)  # type: List[str]
+
+IANA_SUPPORTED_COUNT = len(IANA_SUPPORTED)  # type: int
+
+# pre-computed code page that are similar using the function cp_similarity.
+IANA_SUPPORTED_SIMILAR = {
+    "cp037": ["cp1026", "cp1140", "cp273", "cp500"],
+    "cp1026": ["cp037", "cp1140", "cp273", "cp500"],
+    "cp1125": ["cp866"],
+    "cp1140": ["cp037", "cp1026", "cp273", "cp500"],
+    "cp1250": ["iso8859_2"],
+    "cp1251": ["kz1048", "ptcp154"],
+    "cp1252": ["iso8859_15", "iso8859_9", "latin_1"],
+    "cp1253": ["iso8859_7"],
+    "cp1254": ["iso8859_15", "iso8859_9", "latin_1"],
+    "cp1257": ["iso8859_13"],
+    "cp273": ["cp037", "cp1026", "cp1140", "cp500"],
+    "cp437": ["cp850", "cp858", "cp860", "cp861", "cp862", "cp863", "cp865"],
+    "cp500": ["cp037", "cp1026", "cp1140", "cp273"],
+    "cp850": ["cp437", "cp857", "cp858", "cp865"],
+    "cp857": ["cp850", "cp858", "cp865"],
+    "cp858": ["cp437", "cp850", "cp857", "cp865"],
+    "cp860": ["cp437", "cp861", "cp862", "cp863", "cp865"],
+    "cp861": ["cp437", "cp860", "cp862", "cp863", "cp865"],
+    "cp862": ["cp437", "cp860", "cp861", "cp863", "cp865"],
+    "cp863": ["cp437", "cp860", "cp861", "cp862", "cp865"],
+    "cp865": ["cp437", "cp850", "cp857", "cp858", "cp860", "cp861", "cp862", "cp863"],
+    "cp866": ["cp1125"],
+    "iso8859_10": ["iso8859_14", "iso8859_15", "iso8859_4", "iso8859_9", "latin_1"],
+    "iso8859_11": ["tis_620"],
+    "iso8859_13": ["cp1257"],
+    "iso8859_14": [
+        "iso8859_10",
+        "iso8859_15",
+        "iso8859_16",
+        "iso8859_3",
+        "iso8859_9",
+        "latin_1",
+    ],
+    "iso8859_15": [
+        "cp1252",
+        "cp1254",
+        "iso8859_10",
+        "iso8859_14",
+        "iso8859_16",
+        "iso8859_3",
+        "iso8859_9",
+        "latin_1",
+    ],
+    "iso8859_16": [
+        "iso8859_14",
+        "iso8859_15",
+        "iso8859_2",
+        "iso8859_3",
+        "iso8859_9",
+        "latin_1",
+    ],
+    "iso8859_2": ["cp1250", "iso8859_16", "iso8859_4"],
+    "iso8859_3": ["iso8859_14", "iso8859_15", "iso8859_16", "iso8859_9", "latin_1"],
+    "iso8859_4": ["iso8859_10", "iso8859_2", "iso8859_9", "latin_1"],
+    "iso8859_7": ["cp1253"],
+    "iso8859_9": [
+        "cp1252",
+        "cp1254",
+        "cp1258",
+        "iso8859_10",
+        "iso8859_14",
+        "iso8859_15",
+        "iso8859_16",
+        "iso8859_3",
+        "iso8859_4",
+        "latin_1",
+    ],
+    "kz1048": ["cp1251", "ptcp154"],
+    "latin_1": [
+        "cp1252",
+        "cp1254",
+        "cp1258",
+        "iso8859_10",
+        "iso8859_14",
+        "iso8859_15",
+        "iso8859_16",
+        "iso8859_3",
+        "iso8859_4",
+        "iso8859_9",
+    ],
+    "mac_iceland": ["mac_roman", "mac_turkish"],
+    "mac_roman": ["mac_iceland", "mac_turkish"],
+    "mac_turkish": ["mac_iceland", "mac_roman"],
+    "ptcp154": ["cp1251", "kz1048"],
+    "tis_620": ["iso8859_11"],
+}  # type: Dict[str, List[str]]
+
+
+CHARDET_CORRESPONDENCE = {
+    "iso2022_kr": "ISO-2022-KR",
+    "iso2022_jp": "ISO-2022-JP",
+    "euc_kr": "EUC-KR",
+    "tis_620": "TIS-620",
+    "utf_32": "UTF-32",
+    "euc_jp": "EUC-JP",
+    "koi8_r": "KOI8-R",
+    "iso8859_1": "ISO-8859-1",
+    "iso8859_2": "ISO-8859-2",
+    "iso8859_5": "ISO-8859-5",
+    "iso8859_6": "ISO-8859-6",
+    "iso8859_7": "ISO-8859-7",
+    "iso8859_8": "ISO-8859-8",
+    "utf_16": "UTF-16",
+    "cp855": "IBM855",
+    "mac_cyrillic": "MacCyrillic",
+    "gb2312": "GB2312",
+    "gb18030": "GB18030",
+    "cp932": "CP932",
+    "cp866": "IBM866",
+    "utf_8": "utf-8",
+    "utf_8_sig": "UTF-8-SIG",
+    "shift_jis": "SHIFT_JIS",
+    "big5": "Big5",
+    "cp1250": "windows-1250",
+    "cp1251": "windows-1251",
+    "cp1252": "Windows-1252",
+    "cp1253": "windows-1253",
+    "cp1255": "windows-1255",
+    "cp1256": "windows-1256",
+    "cp1254": "Windows-1254",
+    "cp949": "CP949",
+}  # type: Dict[str, str]
+
+
+COMMON_SAFE_ASCII_CHARACTERS = {
+    "<",
+    ">",
+    "=",
+    ":",
+    "/",
+    "&",
+    ";",
+    "{",
+    "}",
+    "[",
+    "]",
+    ",",
+    "|",
+    '"',
+    "-",
+}  # type: Set[str]
+
+
+KO_NAMES = {"johab", "cp949", "euc_kr"}  # type: Set[str]
+ZH_NAMES = {"big5", "cp950", "big5hkscs", "hz"}  # type: Set[str]
+
+NOT_PRINTABLE_PATTERN = re_compile(r"[0-9\W\n\r\t]+")
+
+LANGUAGE_SUPPORTED_COUNT = len(FREQUENCIES)  # type: int
+
+# Logging LEVEL bellow DEBUG
+TRACE = 5  # type: int

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/legacy.py

@@ -0,0 +1,95 @@
+import warnings
+from typing import Dict, Optional, Union
+
+from .api import from_bytes, from_fp, from_path, normalize
+from .constant import CHARDET_CORRESPONDENCE
+from .models import CharsetMatch, CharsetMatches
+
+
+def detect(byte_str: bytes) -> 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.
+    """
+    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"
+
+    return {
+        "encoding": encoding
+        if encoding not in CHARDET_CORRESPONDENCE
+        else CHARDET_CORRESPONDENCE[encoding],
+        "language": language,
+        "confidence": confidence,
+    }
+
+
+class CharsetNormalizerMatch(CharsetMatch):
+    pass
+
+
+class CharsetNormalizerMatches(CharsetMatches):
+    @staticmethod
+    def from_fp(*args, **kwargs):  # type: ignore
+        warnings.warn(  # pragma: nocover
+            "staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
+            "and scheduled to be removed in 3.0",
+            DeprecationWarning,
+        )
+        return from_fp(*args, **kwargs)  # pragma: nocover
+
+    @staticmethod
+    def from_bytes(*args, **kwargs):  # type: ignore
+        warnings.warn(  # pragma: nocover
+            "staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
+            "and scheduled to be removed in 3.0",
+            DeprecationWarning,
+        )
+        return from_bytes(*args, **kwargs)  # pragma: nocover
+
+    @staticmethod
+    def from_path(*args, **kwargs):  # type: ignore
+        warnings.warn(  # pragma: nocover
+            "staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
+            "and scheduled to be removed in 3.0",
+            DeprecationWarning,
+        )
+        return from_path(*args, **kwargs)  # pragma: nocover
+
+    @staticmethod
+    def normalize(*args, **kwargs):  # type: ignore
+        warnings.warn(  # pragma: nocover
+            "staticmethod from_fp, from_bytes, from_path and normalize are deprecated "
+            "and scheduled to be removed in 3.0",
+            DeprecationWarning,
+        )
+        return normalize(*args, **kwargs)  # pragma: nocover
+
+
+class CharsetDetector(CharsetNormalizerMatches):
+    pass
+
+
+class CharsetDoctor(CharsetNormalizerMatches):
+    pass

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/md.py

@@ -0,0 +1,559 @@
+from functools import lru_cache
+from typing import List, Optional
+
+from .constant import COMMON_SAFE_ASCII_CHARACTERS, UNICODE_SECONDARY_RANGE_KEYWORD
+from .utils import (
+    is_accentuated,
+    is_ascii,
+    is_case_variable,
+    is_cjk,
+    is_emoticon,
+    is_hangul,
+    is_hiragana,
+    is_katakana,
+    is_latin,
+    is_punctuation,
+    is_separator,
+    is_symbol,
+    is_thai,
+    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 = 0  # type: int
+        self._symbol_count = 0  # type: int
+        self._character_count = 0  # type: int
+
+        self._last_printable_char = None  # type: Optional[str]
+        self._frenzy_symbol_in_word = False  # type: bool
+
+    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 = (
+            self._punctuation_count + self._symbol_count
+        ) / self._character_count  # type: float
+
+        return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0
+
+
+class TooManyAccentuatedPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._character_count = 0  # type: int
+        self._accentuated_count = 0  # type: int
+
+    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 == 0:
+            return 0.0
+        ratio_of_accentuation = (
+            self._accentuated_count / self._character_count
+        )  # type: float
+        return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0
+
+
+class UnprintablePlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._unprintable_count = 0  # type: int
+        self._character_count = 0  # type: int
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if (
+            character.isspace() is False  # includes \n \t \r \v
+            and character.isprintable() is False
+            and character != "\x1A"  # Why? Its the ASCII substitute 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 = 0  # type: int
+        self._character_count = 0  # type: int
+
+        self._last_latin_character = None  # type: Optional[str]
+
+    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 = 0  # type: int
+        self._character_count = 0  # type: int
+        self._last_printable_seen = None  # type: Optional[str]
+
+    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 = unicode_range(
+            self._last_printable_seen
+        )  # type: Optional[str]
+        unicode_range_b = unicode_range(character)  # type: Optional[str]
+
+        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 == 0:
+            return 0.0
+
+        ratio_of_suspicious_range_usage = (
+            self._suspicious_successive_range_count * 2
+        ) / self._character_count  # type: float
+
+        if ratio_of_suspicious_range_usage < 0.1:
+            return 0.0
+
+        return ratio_of_suspicious_range_usage
+
+
+class SuperWeirdWordPlugin(MessDetectorPlugin):
+    def __init__(self) -> None:
+        self._word_count = 0  # type: int
+        self._bad_word_count = 0  # type: int
+        self._foreign_long_count = 0  # type: int
+
+        self._is_current_word_bad = False  # type: bool
+        self._foreign_long_watch = False  # type: bool
+
+        self._character_count = 0  # type: int
+        self._bad_character_count = 0  # type: int
+
+        self._buffer = ""  # type: str
+        self._buffer_accent_count = 0  # type: int
+
+    def eligible(self, character: str) -> bool:
+        return True
+
+    def feed(self, character: str) -> None:
+        if character.isalpha():
+            self._buffer = "".join([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 = len(self._buffer)  # type: int
+
+            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 a 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():
+                    self._foreign_long_count += 1
+                    self._is_current_word_bad = True
+            if buffer_length >= 24 and self._foreign_long_watch:
+                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 = 0  # type: int
+        self._cjk_character_count = 0  # type: int
+
+    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 = False  # type: bool
+
+        self._character_count_since_last_sep = 0  # type: int
+
+        self._successive_upper_lower_count = 0  # type: int
+        self._successive_upper_lower_count_final = 0  # type: int
+
+        self._character_count = 0  # type: int
+
+        self._last_alpha_seen = None  # type: Optional[str]
+        self._current_ascii_only = True  # type: bool
+
+    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 is_ascii(character) 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
+
+
+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
+
+    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 = [
+        md_class() for md_class in MessDetectorPlugin.__subclasses__()
+    ]  # type: List[MessDetectorPlugin]
+
+    length = len(decoded_sequence) + 1  # type: int
+
+    mean_mess_ratio = 0.0  # type: float
+
+    if length < 512:
+        intermediary_mean_mess_ratio_calc = 32  # type: int
+    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:
+        for dt in detectors:  # pragma: nocover
+            print(dt.__class__, dt.ratio)
+
+    return round(mean_mess_ratio, 3)

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/models.py

@@ -0,0 +1,392 @@
+import warnings
+from collections import Counter
+from encodings.aliases import aliases
+from hashlib import sha256
+from json import dumps
+from re import sub
+from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
+
+from .constant import NOT_PRINTABLE_PATTERN, TOO_BIG_SEQUENCE
+from .md import mess_ratio
+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 = payload  # type: bytes
+
+        self._encoding = guessed_encoding  # type: str
+        self._mean_mess_ratio = mean_mess_ratio  # type: float
+        self._languages = languages  # type: CoherenceMatches
+        self._has_sig_or_bom = has_sig_or_bom  # type: bool
+        self._unicode_ranges = None  # type: Optional[List[str]]
+
+        self._leaves = []  # type: List[CharsetMatch]
+        self._mean_coherence_ratio = 0.0  # type: float
+
+        self._output_payload = None  # type: Optional[bytes]
+        self._output_encoding = None  # type: Optional[str]
+
+        self._string = decoded_payload  # type: Optional[str]
+
+    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 = abs(self.chaos - other.chaos)  # type: float
+        coherence_difference = abs(self.coherence - other.coherence)  # type: float
+
+        # Bellow 1% difference --> Use Coherence
+        if chaos_difference < 0.01 and coherence_difference > 0.02:
+            # When having a tough decision, use the result that decoded as many multi-byte as possible.
+            if chaos_difference == 0.0 and self.coherence == other.coherence:
+                return self.multi_byte_usage > other.multi_byte_usage
+            return self.coherence > other.coherence
+
+        return self.chaos < other.chaos
+
+    @property
+    def multi_byte_usage(self) -> float:
+        return 1.0 - len(str(self)) / len(self.raw)
+
+    @property
+    def chaos_secondary_pass(self) -> float:
+        """
+        Check once again chaos in decoded text, except this time, with full content.
+        Use with caution, this can be very slow.
+        Notice: Will be removed in 3.0
+        """
+        warnings.warn(
+            "chaos_secondary_pass is deprecated and will be removed in 3.0",
+            DeprecationWarning,
+        )
+        return mess_ratio(str(self), 1.0)
+
+    @property
+    def coherence_non_latin(self) -> float:
+        """
+        Coherence ratio on the first non-latin language detected if ANY.
+        Notice: Will be removed in 3.0
+        """
+        warnings.warn(
+            "coherence_non_latin is deprecated and will be removed in 3.0",
+            DeprecationWarning,
+        )
+        return 0.0
+
+    @property
+    def w_counter(self) -> Counter:
+        """
+        Word counter instance on decoded text.
+        Notice: Will be removed in 3.0
+        """
+        warnings.warn(
+            "w_counter is deprecated and will be removed in 3.0", DeprecationWarning
+        )
+
+        string_printable_only = sub(NOT_PRINTABLE_PATTERN, " ", str(self).lower())
+
+        return Counter(string_printable_only.split())
+
+    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 = []  # type: 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 = [
+            unicode_range(char) for char in str(self)
+        ]  # type: List[Optional[str]]
+        # 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 first(self) -> "CharsetMatch":
+        """
+        Kept for BC reasons. Will be removed in 3.0.
+        """
+        return self
+
+    def best(self) -> "CharsetMatch":
+        """
+        Kept for BC reasons. Will be removed in 3.0.
+        """
+        return self
+
+    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: List[CharsetMatch] = None):
+        self._results = sorted(results) if results else []  # type: List[CharsetMatch]
+
+    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 = path  # type: str
+        self.unicode_path = unicode_path  # type: Optional[str]
+        self.encoding = encoding  # type: Optional[str]
+        self.encoding_aliases = encoding_aliases  # type: List[str]
+        self.alternative_encodings = alternative_encodings  # type: List[str]
+        self.language = language  # type: str
+        self.alphabets = alphabets  # type: List[str]
+        self.has_sig_or_bom = has_sig_or_bom  # type: bool
+        self.chaos = chaos  # type: float
+        self.coherence = coherence  # type: float
+        self.is_preferred = is_preferred  # type: bool
+
+    @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)

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/utils.py

@@ -0,0 +1,342 @@
+try:
+    import unicodedata2 as unicodedata
+except ImportError:
+    import unicodedata  # type: ignore[no-redef]
+
+import importlib
+import logging
+from codecs import IncrementalDecoder
+from encodings.aliases import aliases
+from functools import lru_cache
+from re import findall
+from typing import List, Optional, Set, Tuple, Union
+
+from _multibytecodec import MultibyteIncrementalDecoder  # type: ignore
+
+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 = unicodedata.name(character)  # type: str
+    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
+    )
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def remove_accent(character: str) -> str:
+    decomposed = unicodedata.decomposition(character)  # type: str
+    if not decomposed:
+        return character
+
+    codes = decomposed.split(" ")  # type: List[str]
+
+    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 = ord(character)  # type: int
+
+    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 = unicodedata.name(character)  # type: str
+    except ValueError:
+        return False
+    return "LATIN" in description
+
+
+def is_ascii(character: str) -> bool:
+    try:
+        character.encode("ascii")
+    except UnicodeEncodeError:
+        return False
+    return True
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_punctuation(character: str) -> bool:
+    character_category = unicodedata.category(character)  # type: str
+
+    if "P" in character_category:
+        return True
+
+    character_range = unicode_range(character)  # type: Optional[str]
+
+    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 = unicodedata.category(character)  # type: str
+
+    if "S" in character_category or "N" in character_category:
+        return True
+
+    character_range = unicode_range(character)  # type: Optional[str]
+
+    if character_range is None:
+        return False
+
+    return "Forms" in character_range
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_emoticon(character: str) -> bool:
+    character_range = unicode_range(character)  # type: Optional[str]
+
+    if character_range is None:
+        return False
+
+    return "Emoticons" 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 = unicodedata.category(character)  # type: str
+
+    return "Z" in character_category
+
+
+@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION)
+def is_case_variable(character: str) -> bool:
+    return character.islower() != character.isupper()
+
+
+def is_private_use_only(character: str) -> bool:
+    character_category = unicodedata.category(character)  # type: str
+
+    return character_category == "Co"
+
+
+@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=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)
+
+
+def any_specified_encoding(sequence: bytes, search_zone: int = 4096) -> Optional[str]:
+    """
+    Extract using ASCII-only decoder any specified encoding in the first n-bytes.
+    """
+    if not isinstance(sequence, bytes):
+        raise TypeError
+
+    seq_len = len(sequence)  # type: int
+
+    results = findall(
+        RE_POSSIBLE_ENCODING_INDICATION,
+        sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"),
+    )  # type: List[str]
+
+    if len(results) == 0:
+        return None
+
+    for specified_encoding in results:
+        specified_encoding = specified_encoding.lower().replace("-", "_")
+
+        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,  # type: ignore
+        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 = ENCODING_MARKS[iana_encoding]  # type: Union[bytes, List[bytes]]
+
+        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("-", "_")
+
+    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()  # type: Set[str]
+
+    for character in decoded_sequence:
+        character_range = unicode_range(character)  # type: Optional[str]
+
+        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  # type: ignore
+    decoder_b = importlib.import_module("encodings.{}".format(iana_name_b)).IncrementalDecoder  # type: ignore
+
+    id_a = decoder_a(errors="ignore")  # type: IncrementalDecoder
+    id_b = decoder_b(errors="ignore")  # type: IncrementalDecoder
+
+    character_match_count = 0  # type: int
+
+    for i in range(255):
+        to_be_decoded = bytes([i])  # type: bytes
+        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)

AWS Lambda Layer/python/lib/python3.9/site-packages/charset_normalizer/version.py

@@ -0,0 +1,6 @@
+"""
+Expose version
+"""
+
+__version__ = "2.0.12"
+VERSION = __version__.split(".")

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/__init__.py

@@ -0,0 +1,8 @@
+# -*- coding: utf-8 -*-
+try:
+    from ._version import version as __version__
+except ImportError:
+    __version__ = 'unknown'
+
+__all__ = ['easter', 'parser', 'relativedelta', 'rrule', 'tz',
+           'utils', 'zoneinfo']

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/_common.py

@@ -0,0 +1,43 @@
+"""
+Common code used in multiple modules.
+"""
+
+
+class weekday(object):
+    __slots__ = ["weekday", "n"]
+
+    def __init__(self, weekday, n=None):
+        self.weekday = weekday
+        self.n = n
+
+    def __call__(self, n):
+        if n == self.n:
+            return self
+        else:
+            return self.__class__(self.weekday, n)
+
+    def __eq__(self, other):
+        try:
+            if self.weekday != other.weekday or self.n != other.n:
+                return False
+        except AttributeError:
+            return False
+        return True
+
+    def __hash__(self):
+        return hash((
+          self.weekday,
+          self.n,
+        ))
+
+    def __ne__(self, other):
+        return not (self == other)
+
+    def __repr__(self):
+        s = ("MO", "TU", "WE", "TH", "FR", "SA", "SU")[self.weekday]
+        if not self.n:
+            return s
+        else:
+            return "%s(%+d)" % (s, self.n)
+
+# vim:ts=4:sw=4:et

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/_version.py

@@ -0,0 +1,5 @@
+# coding: utf-8
+# file generated by setuptools_scm
+# don't change, don't track in version control
+version = '2.8.2'
+version_tuple = (2, 8, 2)

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/easter.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+"""
+This module offers a generic Easter computing method for any given year, using
+Western, Orthodox or Julian algorithms.
+"""
+
+import datetime
+
+__all__ = ["easter", "EASTER_JULIAN", "EASTER_ORTHODOX", "EASTER_WESTERN"]
+
+EASTER_JULIAN = 1
+EASTER_ORTHODOX = 2
+EASTER_WESTERN = 3
+
+
+def easter(year, method=EASTER_WESTERN):
+    """
+    This method was ported from the work done by GM Arts,
+    on top of the algorithm by Claus Tondering, which was
+    based in part on the algorithm of Ouding (1940), as
+    quoted in "Explanatory Supplement to the Astronomical
+    Almanac", P.  Kenneth Seidelmann, editor.
+
+    This algorithm implements three different Easter
+    calculation methods:
+
+    1. Original calculation in Julian calendar, valid in
+       dates after 326 AD
+    2. Original method, with date converted to Gregorian
+       calendar, valid in years 1583 to 4099
+    3. Revised method, in Gregorian calendar, valid in
+       years 1583 to 4099 as well
+
+    These methods are represented by the constants:
+
+    * ``EASTER_JULIAN   = 1``
+    * ``EASTER_ORTHODOX = 2``
+    * ``EASTER_WESTERN  = 3``
+
+    The default method is method 3.
+
+    More about the algorithm may be found at:
+
+    `GM Arts: Easter Algorithms <http://www.gmarts.org/index.php?go=415>`_
+
+    and
+
+    `The Calendar FAQ: Easter <https://www.tondering.dk/claus/cal/easter.php>`_
+
+    """
+
+    if not (1 <= method <= 3):
+        raise ValueError("invalid method")
+
+    # g - Golden year - 1
+    # c - Century
+    # h - (23 - Epact) mod 30
+    # i - Number of days from March 21 to Paschal Full Moon
+    # j - Weekday for PFM (0=Sunday, etc)
+    # p - Number of days from March 21 to Sunday on or before PFM
+    #     (-6 to 28 methods 1 & 3, to 56 for method 2)
+    # e - Extra days to add for method 2 (converting Julian
+    #     date to Gregorian date)
+
+    y = year
+    g = y % 19
+    e = 0
+    if method < 3:
+        # Old method
+        i = (19*g + 15) % 30
+        j = (y + y//4 + i) % 7
+        if method == 2:
+            # Extra dates to convert Julian to Gregorian date
+            e = 10
+            if y > 1600:
+                e = e + y//100 - 16 - (y//100 - 16)//4
+    else:
+        # New method
+        c = y//100
+        h = (c - c//4 - (8*c + 13)//25 + 19*g + 15) % 30
+        i = h - (h//28)*(1 - (h//28)*(29//(h + 1))*((21 - g)//11))
+        j = (y + y//4 + i + 2 - c + c//4) % 7
+
+    # p can be from -6 to 56 corresponding to dates 22 March to 23 May
+    # (later dates apply to method 2, although 23 May never actually occurs)
+    p = i - j + e
+    d = 1 + (p + 27 + (p + 6)//40) % 31
+    m = 3 + (p + 26)//30
+    return datetime.date(int(y), int(m), int(d))

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/parser/__init__.py

@@ -0,0 +1,61 @@
+# -*- coding: utf-8 -*-
+from ._parser import parse, parser, parserinfo, ParserError
+from ._parser import DEFAULTPARSER, DEFAULTTZPARSER
+from ._parser import UnknownTimezoneWarning
+
+from ._parser import __doc__
+
+from .isoparser import isoparser, isoparse
+
+__all__ = ['parse', 'parser', 'parserinfo',
+           'isoparse', 'isoparser',
+           'ParserError',
+           'UnknownTimezoneWarning']
+
+
+###
+# Deprecate portions of the private interface so that downstream code that
+# is improperly relying on it is given *some* notice.
+
+
+def __deprecated_private_func(f):
+    from functools import wraps
+    import warnings
+
+    msg = ('{name} is a private function and may break without warning, '
+           'it will be moved and or renamed in future versions.')
+    msg = msg.format(name=f.__name__)
+
+    @wraps(f)
+    def deprecated_func(*args, **kwargs):
+        warnings.warn(msg, DeprecationWarning)
+        return f(*args, **kwargs)
+
+    return deprecated_func
+
+def __deprecate_private_class(c):
+    import warnings
+
+    msg = ('{name} is a private class and may break without warning, '
+           'it will be moved and or renamed in future versions.')
+    msg = msg.format(name=c.__name__)
+
+    class private_class(c):
+        __doc__ = c.__doc__
+
+        def __init__(self, *args, **kwargs):
+            warnings.warn(msg, DeprecationWarning)
+            super(private_class, self).__init__(*args, **kwargs)
+
+    private_class.__name__ = c.__name__
+
+    return private_class
+
+
+from ._parser import _timelex, _resultbase
+from ._parser import _tzparser, _parsetz
+
+_timelex = __deprecate_private_class(_timelex)
+_tzparser = __deprecate_private_class(_tzparser)
+_resultbase = __deprecate_private_class(_resultbase)
+_parsetz = __deprecated_private_func(_parsetz)

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/parser/isoparser.py

@@ -0,0 +1,416 @@
+# -*- coding: utf-8 -*-
+"""
+This module offers a parser for ISO-8601 strings
+
+It is intended to support all valid date, time and datetime formats per the
+ISO-8601 specification.
+
+..versionadded:: 2.7.0
+"""
+from datetime import datetime, timedelta, time, date
+import calendar
+from dateutil import tz
+
+from functools import wraps
+
+import re
+import six
+
+__all__ = ["isoparse", "isoparser"]
+
+
+def _takes_ascii(f):
+    @wraps(f)
+    def func(self, str_in, *args, **kwargs):
+        # If it's a stream, read the whole thing
+        str_in = getattr(str_in, 'read', lambda: str_in)()
+
+        # If it's unicode, turn it into bytes, since ISO-8601 only covers ASCII
+        if isinstance(str_in, six.text_type):
+            # ASCII is the same in UTF-8
+            try:
+                str_in = str_in.encode('ascii')
+            except UnicodeEncodeError as e:
+                msg = 'ISO-8601 strings should contain only ASCII characters'
+                six.raise_from(ValueError(msg), e)
+
+        return f(self, str_in, *args, **kwargs)
+
+    return func
+
+
+class isoparser(object):
+    def __init__(self, sep=None):
+        """
+        :param sep:
+            A single character that separates date and time portions. If
+            ``None``, the parser will accept any single character.
+            For strict ISO-8601 adherence, pass ``'T'``.
+        """
+        if sep is not None:
+            if (len(sep) != 1 or ord(sep) >= 128 or sep in '0123456789'):
+                raise ValueError('Separator must be a single, non-numeric ' +
+                                 'ASCII character')
+
+            sep = sep.encode('ascii')
+
+        self._sep = sep
+
+    @_takes_ascii
+    def isoparse(self, dt_str):
+        """
+        Parse an ISO-8601 datetime string into a :class:`datetime.datetime`.
+
+        An ISO-8601 datetime string consists of a date portion, followed
+        optionally by a time portion - the date and time portions are separated
+        by a single character separator, which is ``T`` in the official
+        standard. Incomplete date formats (such as ``YYYY-MM``) may *not* be
+        combined with a time portion.
+
+        Supported date formats are:
+
+        Common:
+
+        - ``YYYY``
+        - ``YYYY-MM`` or ``YYYYMM``
+        - ``YYYY-MM-DD`` or ``YYYYMMDD``
+
+        Uncommon:
+
+        - ``YYYY-Www`` or ``YYYYWww`` - ISO week (day defaults to 0)
+        - ``YYYY-Www-D`` or ``YYYYWwwD`` - ISO week and day
+
+        The ISO week and day numbering follows the same logic as
+        :func:`datetime.date.isocalendar`.
+
+        Supported time formats are:
+
+        - ``hh``
+        - ``hh:mm`` or ``hhmm``
+        - ``hh:mm:ss`` or ``hhmmss``
+        - ``hh:mm:ss.ssssss`` (Up to 6 sub-second digits)
+
+        Midnight is a special case for `hh`, as the standard supports both
+        00:00 and 24:00 as a representation. The decimal separator can be
+        either a dot or a comma.
+
+
+        .. caution::
+
+            Support for fractional components other than seconds is part of the
+            ISO-8601 standard, but is not currently implemented in this parser.
+
+        Supported time zone offset formats are:
+
+        - `Z` (UTC)
+        - `±HH:MM`
+        - `±HHMM`
+        - `±HH`
+
+        Offsets will be represented as :class:`dateutil.tz.tzoffset` objects,
+        with the exception of UTC, which will be represented as
+        :class:`dateutil.tz.tzutc`. Time zone offsets equivalent to UTC (such
+        as `+00:00`) will also be represented as :class:`dateutil.tz.tzutc`.
+
+        :param dt_str:
+            A string or stream containing only an ISO-8601 datetime string
+
+        :return:
+            Returns a :class:`datetime.datetime` representing the string.
+            Unspecified components default to their lowest value.
+
+        .. warning::
+
+            As of version 2.7.0, the strictness of the parser should not be
+            considered a stable part of the contract. Any valid ISO-8601 string
+            that parses correctly with the default settings will continue to
+            parse correctly in future versions, but invalid strings that
+            currently fail (e.g. ``2017-01-01T00:00+00:00:00``) are not
+            guaranteed to continue failing in future versions if they encode
+            a valid date.
+
+        .. versionadded:: 2.7.0
+        """
+        components, pos = self._parse_isodate(dt_str)
+
+        if len(dt_str) > pos:
+            if self._sep is None or dt_str[pos:pos + 1] == self._sep:
+                components += self._parse_isotime(dt_str[pos + 1:])
+            else:
+                raise ValueError('String contains unknown ISO components')
+
+        if len(components) > 3 and components[3] == 24:
+            components[3] = 0
+            return datetime(*components) + timedelta(days=1)
+
+        return datetime(*components)
+
+    @_takes_ascii
+    def parse_isodate(self, datestr):
+        """
+        Parse the date portion of an ISO string.
+
+        :param datestr:
+            The string portion of an ISO string, without a separator
+
+        :return:
+            Returns a :class:`datetime.date` object
+        """
+        components, pos = self._parse_isodate(datestr)
+        if pos < len(datestr):
+            raise ValueError('String contains unknown ISO ' +
+                             'components: {!r}'.format(datestr.decode('ascii')))
+        return date(*components)
+
+    @_takes_ascii
+    def parse_isotime(self, timestr):
+        """
+        Parse the time portion of an ISO string.
+
+        :param timestr:
+            The time portion of an ISO string, without a separator
+
+        :return:
+            Returns a :class:`datetime.time` object
+        """
+        components = self._parse_isotime(timestr)
+        if components[0] == 24:
+            components[0] = 0
+        return time(*components)
+
+    @_takes_ascii
+    def parse_tzstr(self, tzstr, zero_as_utc=True):
+        """
+        Parse a valid ISO time zone string.
+
+        See :func:`isoparser.isoparse` for details on supported formats.
+
+        :param tzstr:
+            A string representing an ISO time zone offset
+
+        :param zero_as_utc:
+            Whether to return :class:`dateutil.tz.tzutc` for zero-offset zones
+
+        :return:
+            Returns :class:`dateutil.tz.tzoffset` for offsets and
+            :class:`dateutil.tz.tzutc` for ``Z`` and (if ``zero_as_utc`` is
+            specified) offsets equivalent to UTC.
+        """
+        return self._parse_tzstr(tzstr, zero_as_utc=zero_as_utc)
+
+    # Constants
+    _DATE_SEP = b'-'
+    _TIME_SEP = b':'
+    _FRACTION_REGEX = re.compile(b'[\\.,]([0-9]+)')
+
+    def _parse_isodate(self, dt_str):
+        try:
+            return self._parse_isodate_common(dt_str)
+        except ValueError:
+            return self._parse_isodate_uncommon(dt_str)
+
+    def _parse_isodate_common(self, dt_str):
+        len_str = len(dt_str)
+        components = [1, 1, 1]
+
+        if len_str < 4:
+            raise ValueError('ISO string too short')
+
+        # Year
+        components[0] = int(dt_str[0:4])
+        pos = 4
+        if pos >= len_str:
+            return components, pos
+
+        has_sep = dt_str[pos:pos + 1] == self._DATE_SEP
+        if has_sep:
+            pos += 1
+
+        # Month
+        if len_str - pos < 2:
+            raise ValueError('Invalid common month')
+
+        components[1] = int(dt_str[pos:pos + 2])
+        pos += 2
+
+        if pos >= len_str:
+            if has_sep:
+                return components, pos
+            else:
+                raise ValueError('Invalid ISO format')
+
+        if has_sep:
+            if dt_str[pos:pos + 1] != self._DATE_SEP:
+                raise ValueError('Invalid separator in ISO string')
+            pos += 1
+
+        # Day
+        if len_str - pos < 2:
+            raise ValueError('Invalid common day')
+        components[2] = int(dt_str[pos:pos + 2])
+        return components, pos + 2
+
+    def _parse_isodate_uncommon(self, dt_str):
+        if len(dt_str) < 4:
+            raise ValueError('ISO string too short')
+
+        # All ISO formats start with the year
+        year = int(dt_str[0:4])
+
+        has_sep = dt_str[4:5] == self._DATE_SEP
+
+        pos = 4 + has_sep       # Skip '-' if it's there
+        if dt_str[pos:pos + 1] == b'W':
+            # YYYY-?Www-?D?
+            pos += 1
+            weekno = int(dt_str[pos:pos + 2])
+            pos += 2
+
+            dayno = 1
+            if len(dt_str) > pos:
+                if (dt_str[pos:pos + 1] == self._DATE_SEP) != has_sep:
+                    raise ValueError('Inconsistent use of dash separator')
+
+                pos += has_sep
+
+                dayno = int(dt_str[pos:pos + 1])
+                pos += 1
+
+            base_date = self._calculate_weekdate(year, weekno, dayno)
+        else:
+            # YYYYDDD or YYYY-DDD
+            if len(dt_str) - pos < 3:
+                raise ValueError('Invalid ordinal day')
+
+            ordinal_day = int(dt_str[pos:pos + 3])
+            pos += 3
+
+            if ordinal_day < 1 or ordinal_day > (365 + calendar.isleap(year)):
+                raise ValueError('Invalid ordinal day' +
+                                 ' {} for year {}'.format(ordinal_day, year))
+
+            base_date = date(year, 1, 1) + timedelta(days=ordinal_day - 1)
+
+        components = [base_date.year, base_date.month, base_date.day]
+        return components, pos
+
+    def _calculate_weekdate(self, year, week, day):
+        """
+        Calculate the day of corresponding to the ISO year-week-day calendar.
+
+        This function is effectively the inverse of
+        :func:`datetime.date.isocalendar`.
+
+        :param year:
+            The year in the ISO calendar
+
+        :param week:
+            The week in the ISO calendar - range is [1, 53]
+
+        :param day:
+            The day in the ISO calendar - range is [1 (MON), 7 (SUN)]
+
+        :return:
+            Returns a :class:`datetime.date`
+        """
+        if not 0 < week < 54:
+            raise ValueError('Invalid week: {}'.format(week))
+
+        if not 0 < day < 8:     # Range is 1-7
+            raise ValueError('Invalid weekday: {}'.format(day))
+
+        # Get week 1 for the specific year:
+        jan_4 = date(year, 1, 4)   # Week 1 always has January 4th in it
+        week_1 = jan_4 - timedelta(days=jan_4.isocalendar()[2] - 1)
+
+        # Now add the specific number of weeks and days to get what we want
+        week_offset = (week - 1) * 7 + (day - 1)
+        return week_1 + timedelta(days=week_offset)
+
+    def _parse_isotime(self, timestr):
+        len_str = len(timestr)
+        components = [0, 0, 0, 0, None]
+        pos = 0
+        comp = -1
+
+        if len_str < 2:
+            raise ValueError('ISO time too short')
+
+        has_sep = False
+
+        while pos < len_str and comp < 5:
+            comp += 1
+
+            if timestr[pos:pos + 1] in b'-+Zz':
+                # Detect time zone boundary
+                components[-1] = self._parse_tzstr(timestr[pos:])
+                pos = len_str
+                break
+
+            if comp == 1 and timestr[pos:pos+1] == self._TIME_SEP:
+                has_sep = True
+                pos += 1
+            elif comp == 2 and has_sep:
+                if timestr[pos:pos+1] != self._TIME_SEP:
+                    raise ValueError('Inconsistent use of colon separator')
+                pos += 1
+
+            if comp < 3:
+                # Hour, minute, second
+                components[comp] = int(timestr[pos:pos + 2])
+                pos += 2
+
+            if comp == 3:
+                # Fraction of a second
+                frac = self._FRACTION_REGEX.match(timestr[pos:])
+                if not frac:
+                    continue
+
+                us_str = frac.group(1)[:6]  # Truncate to microseconds
+                components[comp] = int(us_str) * 10**(6 - len(us_str))
+                pos += len(frac.group())
+
+        if pos < len_str:
+            raise ValueError('Unused components in ISO string')
+
+        if components[0] == 24:
+            # Standard supports 00:00 and 24:00 as representations of midnight
+            if any(component != 0 for component in components[1:4]):
+                raise ValueError('Hour may only be 24 at 24:00:00.000')
+
+        return components
+
+    def _parse_tzstr(self, tzstr, zero_as_utc=True):
+        if tzstr == b'Z' or tzstr == b'z':
+            return tz.UTC
+
+        if len(tzstr) not in {3, 5, 6}:
+            raise ValueError('Time zone offset must be 1, 3, 5 or 6 characters')
+
+        if tzstr[0:1] == b'-':
+            mult = -1
+        elif tzstr[0:1] == b'+':
+            mult = 1
+        else:
+            raise ValueError('Time zone offset requires sign')
+
+        hours = int(tzstr[1:3])
+        if len(tzstr) == 3:
+            minutes = 0
+        else:
+            minutes = int(tzstr[(4 if tzstr[3:4] == self._TIME_SEP else 3):])
+
+        if zero_as_utc and hours == 0 and minutes == 0:
+            return tz.UTC
+        else:
+            if minutes > 59:
+                raise ValueError('Invalid minutes in time zone offset')
+
+            if hours > 23:
+                raise ValueError('Invalid hours in time zone offset')
+
+            return tz.tzoffset(None, mult * (hours * 60 + minutes) * 60)
+
+
+DEFAULT_ISOPARSER = isoparser()
+isoparse = DEFAULT_ISOPARSER.isoparse

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/relativedelta.py

@@ -0,0 +1,599 @@
+# -*- coding: utf-8 -*-
+import datetime
+import calendar
+
+import operator
+from math import copysign
+
+from six import integer_types
+from warnings import warn
+
+from ._common import weekday
+
+MO, TU, WE, TH, FR, SA, SU = weekdays = tuple(weekday(x) for x in range(7))
+
+__all__ = ["relativedelta", "MO", "TU", "WE", "TH", "FR", "SA", "SU"]
+
+
+class relativedelta(object):
+    """
+    The relativedelta type is designed to be applied to an existing datetime and
+    can replace specific components of that datetime, or represents an interval
+    of time.
+
+    It is based on the specification of the excellent work done by M.-A. Lemburg
+    in his
+    `mx.DateTime <https://www.egenix.com/products/python/mxBase/mxDateTime/>`_ extension.
+    However, notice that this type does *NOT* implement the same algorithm as
+    his work. Do *NOT* expect it to behave like mx.DateTime's counterpart.
+
+    There are two different ways to build a relativedelta instance. The
+    first one is passing it two date/datetime classes::
+
+        relativedelta(datetime1, datetime2)
+
+    The second one is passing it any number of the following keyword arguments::
+
+        relativedelta(arg1=x,arg2=y,arg3=z...)
+
+        year, month, day, hour, minute, second, microsecond:
+            Absolute information (argument is singular); adding or subtracting a
+            relativedelta with absolute information does not perform an arithmetic
+            operation, but rather REPLACES the corresponding value in the
+            original datetime with the value(s) in relativedelta.
+
+        years, months, weeks, days, hours, minutes, seconds, microseconds:
+            Relative information, may be negative (argument is plural); adding
+            or subtracting a relativedelta with relative information performs
+            the corresponding arithmetic operation on the original datetime value
+            with the information in the relativedelta.
+
+        weekday: 
+            One of the weekday instances (MO, TU, etc) available in the
+            relativedelta module. These instances may receive a parameter N,
+            specifying the Nth weekday, which could be positive or negative
+            (like MO(+1) or MO(-2)). Not specifying it is the same as specifying
+            +1. You can also use an integer, where 0=MO. This argument is always
+            relative e.g. if the calculated date is already Monday, using MO(1)
+            or MO(-1) won't change the day. To effectively make it absolute, use
+            it in combination with the day argument (e.g. day=1, MO(1) for first
+            Monday of the month).
+
+        leapdays:
+            Will add given days to the date found, if year is a leap
+            year, and the date found is post 28 of february.
+
+        yearday, nlyearday:
+            Set the yearday or the non-leap year day (jump leap days).
+            These are converted to day/month/leapdays information.
+
+    There are relative and absolute forms of the keyword
+    arguments. The plural is relative, and the singular is
+    absolute. For each argument in the order below, the absolute form
+    is applied first (by setting each attribute to that value) and
+    then the relative form (by adding the value to the attribute).
+
+    The order of attributes considered when this relativedelta is
+    added to a datetime is:
+
+    1. Year
+    2. Month
+    3. Day
+    4. Hours
+    5. Minutes
+    6. Seconds
+    7. Microseconds
+
+    Finally, weekday is applied, using the rule described above.
+
+    For example
+
+    >>> from datetime import datetime
+    >>> from dateutil.relativedelta import relativedelta, MO
+    >>> dt = datetime(2018, 4, 9, 13, 37, 0)
+    >>> delta = relativedelta(hours=25, day=1, weekday=MO(1))
+    >>> dt + delta
+    datetime.datetime(2018, 4, 2, 14, 37)
+
+    First, the day is set to 1 (the first of the month), then 25 hours
+    are added, to get to the 2nd day and 14th hour, finally the
+    weekday is applied, but since the 2nd is already a Monday there is
+    no effect.
+
+    """
+
+    def __init__(self, dt1=None, dt2=None,
+                 years=0, months=0, days=0, leapdays=0, weeks=0,
+                 hours=0, minutes=0, seconds=0, microseconds=0,
+                 year=None, month=None, day=None, weekday=None,
+                 yearday=None, nlyearday=None,
+                 hour=None, minute=None, second=None, microsecond=None):
+
+        if dt1 and dt2:
+            # datetime is a subclass of date. So both must be date
+            if not (isinstance(dt1, datetime.date) and
+                    isinstance(dt2, datetime.date)):
+                raise TypeError("relativedelta only diffs datetime/date")
+
+            # We allow two dates, or two datetimes, so we coerce them to be
+            # of the same type
+            if (isinstance(dt1, datetime.datetime) !=
+                    isinstance(dt2, datetime.datetime)):
+                if not isinstance(dt1, datetime.datetime):
+                    dt1 = datetime.datetime.fromordinal(dt1.toordinal())
+                elif not isinstance(dt2, datetime.datetime):
+                    dt2 = datetime.datetime.fromordinal(dt2.toordinal())
+
+            self.years = 0
+            self.months = 0
+            self.days = 0
+            self.leapdays = 0
+            self.hours = 0
+            self.minutes = 0
+            self.seconds = 0
+            self.microseconds = 0
+            self.year = None
+            self.month = None
+            self.day = None
+            self.weekday = None
+            self.hour = None
+            self.minute = None
+            self.second = None
+            self.microsecond = None
+            self._has_time = 0
+
+            # Get year / month delta between the two
+            months = (dt1.year - dt2.year) * 12 + (dt1.month - dt2.month)
+            self._set_months(months)
+
+            # Remove the year/month delta so the timedelta is just well-defined
+            # time units (seconds, days and microseconds)
+            dtm = self.__radd__(dt2)
+
+            # If we've overshot our target, make an adjustment
+            if dt1 < dt2:
+                compare = operator.gt
+                increment = 1
+            else:
+                compare = operator.lt
+                increment = -1
+
+            while compare(dt1, dtm):
+                months += increment
+                self._set_months(months)
+                dtm = self.__radd__(dt2)
+
+            # Get the timedelta between the "months-adjusted" date and dt1
+            delta = dt1 - dtm
+            self.seconds = delta.seconds + delta.days * 86400
+            self.microseconds = delta.microseconds
+        else:
+            # Check for non-integer values in integer-only quantities
+            if any(x is not None and x != int(x) for x in (years, months)):
+                raise ValueError("Non-integer years and months are "
+                                 "ambiguous and not currently supported.")
+
+            # Relative information
+            self.years = int(years)
+            self.months = int(months)
+            self.days = days + weeks * 7
+            self.leapdays = leapdays
+            self.hours = hours
+            self.minutes = minutes
+            self.seconds = seconds
+            self.microseconds = microseconds
+
+            # Absolute information
+            self.year = year
+            self.month = month
+            self.day = day
+            self.hour = hour
+            self.minute = minute
+            self.second = second
+            self.microsecond = microsecond
+
+            if any(x is not None and int(x) != x
+                   for x in (year, month, day, hour,
+                             minute, second, microsecond)):
+                # For now we'll deprecate floats - later it'll be an error.
+                warn("Non-integer value passed as absolute information. " +
+                     "This is not a well-defined condition and will raise " +
+                     "errors in future versions.", DeprecationWarning)
+
+            if isinstance(weekday, integer_types):
+                self.weekday = weekdays[weekday]
+            else:
+                self.weekday = weekday
+
+            yday = 0
+            if nlyearday:
+                yday = nlyearday
+            elif yearday:
+                yday = yearday
+                if yearday > 59:
+                    self.leapdays = -1
+            if yday:
+                ydayidx = [31, 59, 90, 120, 151, 181, 212,
+                           243, 273, 304, 334, 366]
+                for idx, ydays in enumerate(ydayidx):
+                    if yday <= ydays:
+                        self.month = idx+1
+                        if idx == 0:
+                            self.day = yday
+                        else:
+                            self.day = yday-ydayidx[idx-1]
+                        break
+                else:
+                    raise ValueError("invalid year day (%d)" % yday)
+
+        self._fix()
+
+    def _fix(self):
+        if abs(self.microseconds) > 999999:
+            s = _sign(self.microseconds)
+            div, mod = divmod(self.microseconds * s, 1000000)
+            self.microseconds = mod * s
+            self.seconds += div * s
+        if abs(self.seconds) > 59:
+            s = _sign(self.seconds)
+            div, mod = divmod(self.seconds * s, 60)
+            self.seconds = mod * s
+            self.minutes += div * s
+        if abs(self.minutes) > 59:
+            s = _sign(self.minutes)
+            div, mod = divmod(self.minutes * s, 60)
+            self.minutes = mod * s
+            self.hours += div * s
+        if abs(self.hours) > 23:
+            s = _sign(self.hours)
+            div, mod = divmod(self.hours * s, 24)
+            self.hours = mod * s
+            self.days += div * s
+        if abs(self.months) > 11:
+            s = _sign(self.months)
+            div, mod = divmod(self.months * s, 12)
+            self.months = mod * s
+            self.years += div * s
+        if (self.hours or self.minutes or self.seconds or self.microseconds
+                or self.hour is not None or self.minute is not None or
+                self.second is not None or self.microsecond is not None):
+            self._has_time = 1
+        else:
+            self._has_time = 0
+
+    @property
+    def weeks(self):
+        return int(self.days / 7.0)
+
+    @weeks.setter
+    def weeks(self, value):
+        self.days = self.days - (self.weeks * 7) + value * 7
+
+    def _set_months(self, months):
+        self.months = months
+        if abs(self.months) > 11:
+            s = _sign(self.months)
+            div, mod = divmod(self.months * s, 12)
+            self.months = mod * s
+            self.years = div * s
+        else:
+            self.years = 0
+
+    def normalized(self):
+        """
+        Return a version of this object represented entirely using integer
+        values for the relative attributes.
+
+        >>> relativedelta(days=1.5, hours=2).normalized()
+        relativedelta(days=+1, hours=+14)
+
+        :return:
+            Returns a :class:`dateutil.relativedelta.relativedelta` object.
+        """
+        # Cascade remainders down (rounding each to roughly nearest microsecond)
+        days = int(self.days)
+
+        hours_f = round(self.hours + 24 * (self.days - days), 11)
+        hours = int(hours_f)
+
+        minutes_f = round(self.minutes + 60 * (hours_f - hours), 10)
+        minutes = int(minutes_f)
+
+        seconds_f = round(self.seconds + 60 * (minutes_f - minutes), 8)
+        seconds = int(seconds_f)
+
+        microseconds = round(self.microseconds + 1e6 * (seconds_f - seconds))
+
+        # Constructor carries overflow back up with call to _fix()
+        return self.__class__(years=self.years, months=self.months,
+                              days=days, hours=hours, minutes=minutes,
+                              seconds=seconds, microseconds=microseconds,
+                              leapdays=self.leapdays, year=self.year,
+                              month=self.month, day=self.day,
+                              weekday=self.weekday, hour=self.hour,
+                              minute=self.minute, second=self.second,
+                              microsecond=self.microsecond)
+
+    def __add__(self, other):
+        if isinstance(other, relativedelta):
+            return self.__class__(years=other.years + self.years,
+                                 months=other.months + self.months,
+                                 days=other.days + self.days,
+                                 hours=other.hours + self.hours,
+                                 minutes=other.minutes + self.minutes,
+                                 seconds=other.seconds + self.seconds,
+                                 microseconds=(other.microseconds +
+                                               self.microseconds),
+                                 leapdays=other.leapdays or self.leapdays,
+                                 year=(other.year if other.year is not None
+                                       else self.year),
+                                 month=(other.month if other.month is not None
+                                        else self.month),
+                                 day=(other.day if other.day is not None
+                                      else self.day),
+                                 weekday=(other.weekday if other.weekday is not None
+                                          else self.weekday),
+                                 hour=(other.hour if other.hour is not None
+                                       else self.hour),
+                                 minute=(other.minute if other.minute is not None
+                                         else self.minute),
+                                 second=(other.second if other.second is not None
+                                         else self.second),
+                                 microsecond=(other.microsecond if other.microsecond
+                                              is not None else
+                                              self.microsecond))
+        if isinstance(other, datetime.timedelta):
+            return self.__class__(years=self.years,
+                                  months=self.months,
+                                  days=self.days + other.days,
+                                  hours=self.hours,
+                                  minutes=self.minutes,
+                                  seconds=self.seconds + other.seconds,
+                                  microseconds=self.microseconds + other.microseconds,
+                                  leapdays=self.leapdays,
+                                  year=self.year,
+                                  month=self.month,
+                                  day=self.day,
+                                  weekday=self.weekday,
+                                  hour=self.hour,
+                                  minute=self.minute,
+                                  second=self.second,
+                                  microsecond=self.microsecond)
+        if not isinstance(other, datetime.date):
+            return NotImplemented
+        elif self._has_time and not isinstance(other, datetime.datetime):
+            other = datetime.datetime.fromordinal(other.toordinal())
+        year = (self.year or other.year)+self.years
+        month = self.month or other.month
+        if self.months:
+            assert 1 <= abs(self.months) <= 12
+            month += self.months
+            if month > 12:
+                year += 1
+                month -= 12
+            elif month < 1:
+                year -= 1
+                month += 12
+        day = min(calendar.monthrange(year, month)[1],
+                  self.day or other.day)
+        repl = {"year": year, "month": month, "day": day}
+        for attr in ["hour", "minute", "second", "microsecond"]:
+            value = getattr(self, attr)
+            if value is not None:
+                repl[attr] = value
+        days = self.days
+        if self.leapdays and month > 2 and calendar.isleap(year):
+            days += self.leapdays
+        ret = (other.replace(**repl)
+               + datetime.timedelta(days=days,
+                                    hours=self.hours,
+                                    minutes=self.minutes,
+                                    seconds=self.seconds,
+                                    microseconds=self.microseconds))
+        if self.weekday:
+            weekday, nth = self.weekday.weekday, self.weekday.n or 1
+            jumpdays = (abs(nth) - 1) * 7
+            if nth > 0:
+                jumpdays += (7 - ret.weekday() + weekday) % 7
+            else:
+                jumpdays += (ret.weekday() - weekday) % 7
+                jumpdays *= -1
+            ret += datetime.timedelta(days=jumpdays)
+        return ret
+
+    def __radd__(self, other):
+        return self.__add__(other)
+
+    def __rsub__(self, other):
+        return self.__neg__().__radd__(other)
+
+    def __sub__(self, other):
+        if not isinstance(other, relativedelta):
+            return NotImplemented   # In case the other object defines __rsub__
+        return self.__class__(years=self.years - other.years,
+                             months=self.months - other.months,
+                             days=self.days - other.days,
+                             hours=self.hours - other.hours,
+                             minutes=self.minutes - other.minutes,
+                             seconds=self.seconds - other.seconds,
+                             microseconds=self.microseconds - other.microseconds,
+                             leapdays=self.leapdays or other.leapdays,
+                             year=(self.year if self.year is not None
+                                   else other.year),
+                             month=(self.month if self.month is not None else
+                                    other.month),
+                             day=(self.day if self.day is not None else
+                                  other.day),
+                             weekday=(self.weekday if self.weekday is not None else
+                                      other.weekday),
+                             hour=(self.hour if self.hour is not None else
+                                   other.hour),
+                             minute=(self.minute if self.minute is not None else
+                                     other.minute),
+                             second=(self.second if self.second is not None else
+                                     other.second),
+                             microsecond=(self.microsecond if self.microsecond
+                                          is not None else
+                                          other.microsecond))
+
+    def __abs__(self):
+        return self.__class__(years=abs(self.years),
+                              months=abs(self.months),
+                              days=abs(self.days),
+                              hours=abs(self.hours),
+                              minutes=abs(self.minutes),
+                              seconds=abs(self.seconds),
+                              microseconds=abs(self.microseconds),
+                              leapdays=self.leapdays,
+                              year=self.year,
+                              month=self.month,
+                              day=self.day,
+                              weekday=self.weekday,
+                              hour=self.hour,
+                              minute=self.minute,
+                              second=self.second,
+                              microsecond=self.microsecond)
+
+    def __neg__(self):
+        return self.__class__(years=-self.years,
+                             months=-self.months,
+                             days=-self.days,
+                             hours=-self.hours,
+                             minutes=-self.minutes,
+                             seconds=-self.seconds,
+                             microseconds=-self.microseconds,
+                             leapdays=self.leapdays,
+                             year=self.year,
+                             month=self.month,
+                             day=self.day,
+                             weekday=self.weekday,
+                             hour=self.hour,
+                             minute=self.minute,
+                             second=self.second,
+                             microsecond=self.microsecond)
+
+    def __bool__(self):
+        return not (not self.years and
+                    not self.months and
+                    not self.days and
+                    not self.hours and
+                    not self.minutes and
+                    not self.seconds and
+                    not self.microseconds and
+                    not self.leapdays and
+                    self.year is None and
+                    self.month is None and
+                    self.day is None and
+                    self.weekday is None and
+                    self.hour is None and
+                    self.minute is None and
+                    self.second is None and
+                    self.microsecond is None)
+    # Compatibility with Python 2.x
+    __nonzero__ = __bool__
+
+    def __mul__(self, other):
+        try:
+            f = float(other)
+        except TypeError:
+            return NotImplemented
+
+        return self.__class__(years=int(self.years * f),
+                             months=int(self.months * f),
+                             days=int(self.days * f),
+                             hours=int(self.hours * f),
+                             minutes=int(self.minutes * f),
+                             seconds=int(self.seconds * f),
+                             microseconds=int(self.microseconds * f),
+                             leapdays=self.leapdays,
+                             year=self.year,
+                             month=self.month,
+                             day=self.day,
+                             weekday=self.weekday,
+                             hour=self.hour,
+                             minute=self.minute,
+                             second=self.second,
+                             microsecond=self.microsecond)
+
+    __rmul__ = __mul__
+
+    def __eq__(self, other):
+        if not isinstance(other, relativedelta):
+            return NotImplemented
+        if self.weekday or other.weekday:
+            if not self.weekday or not other.weekday:
+                return False
+            if self.weekday.weekday != other.weekday.weekday:
+                return False
+            n1, n2 = self.weekday.n, other.weekday.n
+            if n1 != n2 and not ((not n1 or n1 == 1) and (not n2 or n2 == 1)):
+                return False
+        return (self.years == other.years and
+                self.months == other.months and
+                self.days == other.days and
+                self.hours == other.hours and
+                self.minutes == other.minutes and
+                self.seconds == other.seconds and
+                self.microseconds == other.microseconds and
+                self.leapdays == other.leapdays and
+                self.year == other.year and
+                self.month == other.month and
+                self.day == other.day and
+                self.hour == other.hour and
+                self.minute == other.minute and
+                self.second == other.second and
+                self.microsecond == other.microsecond)
+
+    def __hash__(self):
+        return hash((
+            self.weekday,
+            self.years,
+            self.months,
+            self.days,
+            self.hours,
+            self.minutes,
+            self.seconds,
+            self.microseconds,
+            self.leapdays,
+            self.year,
+            self.month,
+            self.day,
+            self.hour,
+            self.minute,
+            self.second,
+            self.microsecond,
+        ))
+
+    def __ne__(self, other):
+        return not self.__eq__(other)
+
+    def __div__(self, other):
+        try:
+            reciprocal = 1 / float(other)
+        except TypeError:
+            return NotImplemented
+
+        return self.__mul__(reciprocal)
+
+    __truediv__ = __div__
+
+    def __repr__(self):
+        l = []
+        for attr in ["years", "months", "days", "leapdays",
+                     "hours", "minutes", "seconds", "microseconds"]:
+            value = getattr(self, attr)
+            if value:
+                l.append("{attr}={value:+g}".format(attr=attr, value=value))
+        for attr in ["year", "month", "day", "weekday",
+                     "hour", "minute", "second", "microsecond"]:
+            value = getattr(self, attr)
+            if value is not None:
+                l.append("{attr}={value}".format(attr=attr, value=repr(value)))
+        return "{classname}({attrs})".format(classname=self.__class__.__name__,
+                                             attrs=", ".join(l))
+
+
+def _sign(x):
+    return int(copysign(1, x))
+
+# vim:ts=4:sw=4:et

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/tz/__init__.py

@@ -0,0 +1,12 @@
+# -*- coding: utf-8 -*-
+from .tz import *
+from .tz import __doc__
+
+__all__ = ["tzutc", "tzoffset", "tzlocal", "tzfile", "tzrange",
+           "tzstr", "tzical", "tzwin", "tzwinlocal", "gettz",
+           "enfold", "datetime_ambiguous", "datetime_exists",
+           "resolve_imaginary", "UTC", "DeprecatedTzFormatWarning"]
+
+
+class DeprecatedTzFormatWarning(Warning):
+    """Warning raised when time zones are parsed from deprecated formats."""

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/tz/_common.py

@@ -0,0 +1,419 @@
+from six import PY2
+
+from functools import wraps
+
+from datetime import datetime, timedelta, tzinfo
+
+
+ZERO = timedelta(0)
+
+__all__ = ['tzname_in_python2', 'enfold']
+
+
+def tzname_in_python2(namefunc):
+    """Change unicode output into bytestrings in Python 2
+
+    tzname() API changed in Python 3. It used to return bytes, but was changed
+    to unicode strings
+    """
+    if PY2:
+        @wraps(namefunc)
+        def adjust_encoding(*args, **kwargs):
+            name = namefunc(*args, **kwargs)
+            if name is not None:
+                name = name.encode()
+
+            return name
+
+        return adjust_encoding
+    else:
+        return namefunc
+
+
+# The following is adapted from Alexander Belopolsky's tz library
+# https://github.com/abalkin/tz
+if hasattr(datetime, 'fold'):
+    # This is the pre-python 3.6 fold situation
+    def enfold(dt, fold=1):
+        """
+        Provides a unified interface for assigning the ``fold`` attribute to
+        datetimes both before and after the implementation of PEP-495.
+
+        :param fold:
+            The value for the ``fold`` attribute in the returned datetime. This
+            should be either 0 or 1.
+
+        :return:
+            Returns an object for which ``getattr(dt, 'fold', 0)`` returns
+            ``fold`` for all versions of Python. In versions prior to
+            Python 3.6, this is a ``_DatetimeWithFold`` object, which is a
+            subclass of :py:class:`datetime.datetime` with the ``fold``
+            attribute added, if ``fold`` is 1.
+
+        .. versionadded:: 2.6.0
+        """
+        return dt.replace(fold=fold)
+
+else:
+    class _DatetimeWithFold(datetime):
+        """
+        This is a class designed to provide a PEP 495-compliant interface for
+        Python versions before 3.6. It is used only for dates in a fold, so
+        the ``fold`` attribute is fixed at ``1``.
+
+        .. versionadded:: 2.6.0
+        """
+        __slots__ = ()
+
+        def replace(self, *args, **kwargs):
+            """
+            Return a datetime with the same attributes, except for those
+            attributes given new values by whichever keyword arguments are
+            specified. Note that tzinfo=None can be specified to create a naive
+            datetime from an aware datetime with no conversion of date and time
+            data.
+
+            This is reimplemented in ``_DatetimeWithFold`` because pypy3 will
+            return a ``datetime.datetime`` even if ``fold`` is unchanged.
+            """
+            argnames = (
+                'year', 'month', 'day', 'hour', 'minute', 'second',
+                'microsecond', 'tzinfo'
+            )
+
+            for arg, argname in zip(args, argnames):
+                if argname in kwargs:
+                    raise TypeError('Duplicate argument: {}'.format(argname))
+
+                kwargs[argname] = arg
+
+            for argname in argnames:
+                if argname not in kwargs:
+                    kwargs[argname] = getattr(self, argname)
+
+            dt_class = self.__class__ if kwargs.get('fold', 1) else datetime
+
+            return dt_class(**kwargs)
+
+        @property
+        def fold(self):
+            return 1
+
+    def enfold(dt, fold=1):
+        """
+        Provides a unified interface for assigning the ``fold`` attribute to
+        datetimes both before and after the implementation of PEP-495.
+
+        :param fold:
+            The value for the ``fold`` attribute in the returned datetime. This
+            should be either 0 or 1.
+
+        :return:
+            Returns an object for which ``getattr(dt, 'fold', 0)`` returns
+            ``fold`` for all versions of Python. In versions prior to
+            Python 3.6, this is a ``_DatetimeWithFold`` object, which is a
+            subclass of :py:class:`datetime.datetime` with the ``fold``
+            attribute added, if ``fold`` is 1.
+
+        .. versionadded:: 2.6.0
+        """
+        if getattr(dt, 'fold', 0) == fold:
+            return dt
+
+        args = dt.timetuple()[:6]
+        args += (dt.microsecond, dt.tzinfo)
+
+        if fold:
+            return _DatetimeWithFold(*args)
+        else:
+            return datetime(*args)
+
+
+def _validate_fromutc_inputs(f):
+    """
+    The CPython version of ``fromutc`` checks that the input is a ``datetime``
+    object and that ``self`` is attached as its ``tzinfo``.
+    """
+    @wraps(f)
+    def fromutc(self, dt):
+        if not isinstance(dt, datetime):
+            raise TypeError("fromutc() requires a datetime argument")
+        if dt.tzinfo is not self:
+            raise ValueError("dt.tzinfo is not self")
+
+        return f(self, dt)
+
+    return fromutc
+
+
+class _tzinfo(tzinfo):
+    """
+    Base class for all ``dateutil`` ``tzinfo`` objects.
+    """
+
+    def is_ambiguous(self, dt):
+        """
+        Whether or not the "wall time" of a given datetime is ambiguous in this
+        zone.
+
+        :param dt:
+            A :py:class:`datetime.datetime`, naive or time zone aware.
+
+
+        :return:
+            Returns ``True`` if ambiguous, ``False`` otherwise.
+
+        .. versionadded:: 2.6.0
+        """
+
+        dt = dt.replace(tzinfo=self)
+
+        wall_0 = enfold(dt, fold=0)
+        wall_1 = enfold(dt, fold=1)
+
+        same_offset = wall_0.utcoffset() == wall_1.utcoffset()
+        same_dt = wall_0.replace(tzinfo=None) == wall_1.replace(tzinfo=None)
+
+        return same_dt and not same_offset
+
+    def _fold_status(self, dt_utc, dt_wall):
+        """
+        Determine the fold status of a "wall" datetime, given a representation
+        of the same datetime as a (naive) UTC datetime. This is calculated based
+        on the assumption that ``dt.utcoffset() - dt.dst()`` is constant for all
+        datetimes, and that this offset is the actual number of hours separating
+        ``dt_utc`` and ``dt_wall``.
+
+        :param dt_utc:
+            Representation of the datetime as UTC
+
+        :param dt_wall:
+            Representation of the datetime as "wall time". This parameter must
+            either have a `fold` attribute or have a fold-naive
+            :class:`datetime.tzinfo` attached, otherwise the calculation may
+            fail.
+        """
+        if self.is_ambiguous(dt_wall):
+            delta_wall = dt_wall - dt_utc
+            _fold = int(delta_wall == (dt_utc.utcoffset() - dt_utc.dst()))
+        else:
+            _fold = 0
+
+        return _fold
+
+    def _fold(self, dt):
+        return getattr(dt, 'fold', 0)
+
+    def _fromutc(self, dt):
+        """
+        Given a timezone-aware datetime in a given timezone, calculates a
+        timezone-aware datetime in a new timezone.
+
+        Since this is the one time that we *know* we have an unambiguous
+        datetime object, we take this opportunity to determine whether the
+        datetime is ambiguous and in a "fold" state (e.g. if it's the first
+        occurrence, chronologically, of the ambiguous datetime).
+
+        :param dt:
+            A timezone-aware :class:`datetime.datetime` object.
+        """
+
+        # Re-implement the algorithm from Python's datetime.py
+        dtoff = dt.utcoffset()
+        if dtoff is None:
+            raise ValueError("fromutc() requires a non-None utcoffset() "
+                             "result")
+
+        # The original datetime.py code assumes that `dst()` defaults to
+        # zero during ambiguous times. PEP 495 inverts this presumption, so
+        # for pre-PEP 495 versions of python, we need to tweak the algorithm.
+        dtdst = dt.dst()
+        if dtdst is None:
+            raise ValueError("fromutc() requires a non-None dst() result")
+        delta = dtoff - dtdst
+
+        dt += delta
+        # Set fold=1 so we can default to being in the fold for
+        # ambiguous dates.
+        dtdst = enfold(dt, fold=1).dst()
+        if dtdst is None:
+            raise ValueError("fromutc(): dt.dst gave inconsistent "
+                             "results; cannot convert")
+        return dt + dtdst
+
+    @_validate_fromutc_inputs
+    def fromutc(self, dt):
+        """
+        Given a timezone-aware datetime in a given timezone, calculates a
+        timezone-aware datetime in a new timezone.
+
+        Since this is the one time that we *know* we have an unambiguous
+        datetime object, we take this opportunity to determine whether the
+        datetime is ambiguous and in a "fold" state (e.g. if it's the first
+        occurrence, chronologically, of the ambiguous datetime).
+
+        :param dt:
+            A timezone-aware :class:`datetime.datetime` object.
+        """
+        dt_wall = self._fromutc(dt)
+
+        # Calculate the fold status given the two datetimes.
+        _fold = self._fold_status(dt, dt_wall)
+
+        # Set the default fold value for ambiguous dates
+        return enfold(dt_wall, fold=_fold)
+
+
+class tzrangebase(_tzinfo):
+    """
+    This is an abstract base class for time zones represented by an annual
+    transition into and out of DST. Child classes should implement the following
+    methods:
+
+        * ``__init__(self, *args, **kwargs)``
+        * ``transitions(self, year)`` - this is expected to return a tuple of
+          datetimes representing the DST on and off transitions in standard
+          time.
+
+    A fully initialized ``tzrangebase`` subclass should also provide the
+    following attributes:
+        * ``hasdst``: Boolean whether or not the zone uses DST.
+        * ``_dst_offset`` / ``_std_offset``: :class:`datetime.timedelta` objects
+          representing the respective UTC offsets.
+        * ``_dst_abbr`` / ``_std_abbr``: Strings representing the timezone short
+          abbreviations in DST and STD, respectively.
+        * ``_hasdst``: Whether or not the zone has DST.
+
+    .. versionadded:: 2.6.0
+    """
+    def __init__(self):
+        raise NotImplementedError('tzrangebase is an abstract base class')
+
+    def utcoffset(self, dt):
+        isdst = self._isdst(dt)
+
+        if isdst is None:
+            return None
+        elif isdst:
+            return self._dst_offset
+        else:
+            return self._std_offset
+
+    def dst(self, dt):
+        isdst = self._isdst(dt)
+
+        if isdst is None:
+            return None
+        elif isdst:
+            return self._dst_base_offset
+        else:
+            return ZERO
+
+    @tzname_in_python2
+    def tzname(self, dt):
+        if self._isdst(dt):
+            return self._dst_abbr
+        else:
+            return self._std_abbr
+
+    def fromutc(self, dt):
+        """ Given a datetime in UTC, return local time """
+        if not isinstance(dt, datetime):
+            raise TypeError("fromutc() requires a datetime argument")
+
+        if dt.tzinfo is not self:
+            raise ValueError("dt.tzinfo is not self")
+
+        # Get transitions - if there are none, fixed offset
+        transitions = self.transitions(dt.year)
+        if transitions is None:
+            return dt + self.utcoffset(dt)
+
+        # Get the transition times in UTC
+        dston, dstoff = transitions
+
+        dston -= self._std_offset
+        dstoff -= self._std_offset
+
+        utc_transitions = (dston, dstoff)
+        dt_utc = dt.replace(tzinfo=None)
+
+        isdst = self._naive_isdst(dt_utc, utc_transitions)
+
+        if isdst:
+            dt_wall = dt + self._dst_offset
+        else:
+            dt_wall = dt + self._std_offset
+
+        _fold = int(not isdst and self.is_ambiguous(dt_wall))
+
+        return enfold(dt_wall, fold=_fold)
+
+    def is_ambiguous(self, dt):
+        """
+        Whether or not the "wall time" of a given datetime is ambiguous in this
+        zone.
+
+        :param dt:
+            A :py:class:`datetime.datetime`, naive or time zone aware.
+
+
+        :return:
+            Returns ``True`` if ambiguous, ``False`` otherwise.
+
+        .. versionadded:: 2.6.0
+        """
+        if not self.hasdst:
+            return False
+
+        start, end = self.transitions(dt.year)
+
+        dt = dt.replace(tzinfo=None)
+        return (end <= dt < end + self._dst_base_offset)
+
+    def _isdst(self, dt):
+        if not self.hasdst:
+            return False
+        elif dt is None:
+            return None
+
+        transitions = self.transitions(dt.year)
+
+        if transitions is None:
+            return False
+
+        dt = dt.replace(tzinfo=None)
+
+        isdst = self._naive_isdst(dt, transitions)
+
+        # Handle ambiguous dates
+        if not isdst and self.is_ambiguous(dt):
+            return not self._fold(dt)
+        else:
+            return isdst
+
+    def _naive_isdst(self, dt, transitions):
+        dston, dstoff = transitions
+
+        dt = dt.replace(tzinfo=None)
+
+        if dston < dstoff:
+            isdst = dston <= dt < dstoff
+        else:
+            isdst = not dstoff <= dt < dston
+
+        return isdst
+
+    @property
+    def _dst_base_offset(self):
+        return self._dst_offset - self._std_offset
+
+    __hash__ = None
+
+    def __ne__(self, other):
+        return not (self == other)
+
+    def __repr__(self):
+        return "%s(...)" % self.__class__.__name__
+
+    __reduce__ = object.__reduce__

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/tz/_factories.py

@@ -0,0 +1,80 @@
+from datetime import timedelta
+import weakref
+from collections import OrderedDict
+
+from six.moves import _thread
+
+
+class _TzSingleton(type):
+    def __init__(cls, *args, **kwargs):
+        cls.__instance = None
+        super(_TzSingleton, cls).__init__(*args, **kwargs)
+
+    def __call__(cls):
+        if cls.__instance is None:
+            cls.__instance = super(_TzSingleton, cls).__call__()
+        return cls.__instance
+
+
+class _TzFactory(type):
+    def instance(cls, *args, **kwargs):
+        """Alternate constructor that returns a fresh instance"""
+        return type.__call__(cls, *args, **kwargs)
+
+
+class _TzOffsetFactory(_TzFactory):
+    def __init__(cls, *args, **kwargs):
+        cls.__instances = weakref.WeakValueDictionary()
+        cls.__strong_cache = OrderedDict()
+        cls.__strong_cache_size = 8
+
+        cls._cache_lock = _thread.allocate_lock()
+
+    def __call__(cls, name, offset):
+        if isinstance(offset, timedelta):
+            key = (name, offset.total_seconds())
+        else:
+            key = (name, offset)
+
+        instance = cls.__instances.get(key, None)
+        if instance is None:
+            instance = cls.__instances.setdefault(key,
+                                                  cls.instance(name, offset))
+
+        # This lock may not be necessary in Python 3. See GH issue #901
+        with cls._cache_lock:
+            cls.__strong_cache[key] = cls.__strong_cache.pop(key, instance)
+
+            # Remove an item if the strong cache is overpopulated
+            if len(cls.__strong_cache) > cls.__strong_cache_size:
+                cls.__strong_cache.popitem(last=False)
+
+        return instance
+
+
+class _TzStrFactory(_TzFactory):
+    def __init__(cls, *args, **kwargs):
+        cls.__instances = weakref.WeakValueDictionary()
+        cls.__strong_cache = OrderedDict()
+        cls.__strong_cache_size = 8
+
+        cls.__cache_lock = _thread.allocate_lock()
+
+    def __call__(cls, s, posix_offset=False):
+        key = (s, posix_offset)
+        instance = cls.__instances.get(key, None)
+
+        if instance is None:
+            instance = cls.__instances.setdefault(key,
+                cls.instance(s, posix_offset))
+
+        # This lock may not be necessary in Python 3. See GH issue #901
+        with cls.__cache_lock:
+            cls.__strong_cache[key] = cls.__strong_cache.pop(key, instance)
+
+            # Remove an item if the strong cache is overpopulated
+            if len(cls.__strong_cache) > cls.__strong_cache_size:
+                cls.__strong_cache.popitem(last=False)
+
+        return instance
+

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/tz/win.py

@@ -0,0 +1,370 @@
+# -*- coding: utf-8 -*-
+"""
+This module provides an interface to the native time zone data on Windows,
+including :py:class:`datetime.tzinfo` implementations.
+
+Attempting to import this module on a non-Windows platform will raise an
+:py:obj:`ImportError`.
+"""
+# This code was originally contributed by Jeffrey Harris.
+import datetime
+import struct
+
+from six.moves import winreg
+from six import text_type
+
+try:
+    import ctypes
+    from ctypes import wintypes
+except ValueError:
+    # ValueError is raised on non-Windows systems for some horrible reason.
+    raise ImportError("Running tzwin on non-Windows system")
+
+from ._common import tzrangebase
+
+__all__ = ["tzwin", "tzwinlocal", "tzres"]
+
+ONEWEEK = datetime.timedelta(7)
+
+TZKEYNAMENT = r"SOFTWARE\Microsoft\Windows NT\CurrentVersion\Time Zones"
+TZKEYNAME9X = r"SOFTWARE\Microsoft\Windows\CurrentVersion\Time Zones"
+TZLOCALKEYNAME = r"SYSTEM\CurrentControlSet\Control\TimeZoneInformation"
+
+
+def _settzkeyname():
+    handle = winreg.ConnectRegistry(None, winreg.HKEY_LOCAL_MACHINE)
+    try:
+        winreg.OpenKey(handle, TZKEYNAMENT).Close()
+        TZKEYNAME = TZKEYNAMENT
+    except WindowsError:
+        TZKEYNAME = TZKEYNAME9X
+    handle.Close()
+    return TZKEYNAME
+
+
+TZKEYNAME = _settzkeyname()
+
+
+class tzres(object):
+    """
+    Class for accessing ``tzres.dll``, which contains timezone name related
+    resources.
+
+    .. versionadded:: 2.5.0
+    """
+    p_wchar = ctypes.POINTER(wintypes.WCHAR)        # Pointer to a wide char
+
+    def __init__(self, tzres_loc='tzres.dll'):
+        # Load the user32 DLL so we can load strings from tzres
+        user32 = ctypes.WinDLL('user32')
+
+        # Specify the LoadStringW function
+        user32.LoadStringW.argtypes = (wintypes.HINSTANCE,
+                                       wintypes.UINT,
+                                       wintypes.LPWSTR,
+                                       ctypes.c_int)
+
+        self.LoadStringW = user32.LoadStringW
+        self._tzres = ctypes.WinDLL(tzres_loc)
+        self.tzres_loc = tzres_loc
+
+    def load_name(self, offset):
+        """
+        Load a timezone name from a DLL offset (integer).
+
+        >>> from dateutil.tzwin import tzres
+        >>> tzr = tzres()
+        >>> print(tzr.load_name(112))
+        'Eastern Standard Time'
+
+        :param offset:
+            A positive integer value referring to a string from the tzres dll.
+
+        .. note::
+
+            Offsets found in the registry are generally of the form
+            ``@tzres.dll,-114``. The offset in this case is 114, not -114.
+
+        """
+        resource = self.p_wchar()
+        lpBuffer = ctypes.cast(ctypes.byref(resource), wintypes.LPWSTR)
+        nchar = self.LoadStringW(self._tzres._handle, offset, lpBuffer, 0)
+        return resource[:nchar]
+
+    def name_from_string(self, tzname_str):
+        """
+        Parse strings as returned from the Windows registry into the time zone
+        name as defined in the registry.
+
+        >>> from dateutil.tzwin import tzres
+        >>> tzr = tzres()
+        >>> print(tzr.name_from_string('@tzres.dll,-251'))
+        'Dateline Daylight Time'
+        >>> print(tzr.name_from_string('Eastern Standard Time'))
+        'Eastern Standard Time'
+
+        :param tzname_str:
+            A timezone name string as returned from a Windows registry key.
+
+        :return:
+            Returns the localized timezone string from tzres.dll if the string
+            is of the form `@tzres.dll,-offset`, else returns the input string.
+        """
+        if not tzname_str.startswith('@'):
+            return tzname_str
+
+        name_splt = tzname_str.split(',-')
+        try:
+            offset = int(name_splt[1])
+        except:
+            raise ValueError("Malformed timezone string.")
+
+        return self.load_name(offset)
+
+
+class tzwinbase(tzrangebase):
+    """tzinfo class based on win32's timezones available in the registry."""
+    def __init__(self):
+        raise NotImplementedError('tzwinbase is an abstract base class')
+
+    def __eq__(self, other):
+        # Compare on all relevant dimensions, including name.
+        if not isinstance(other, tzwinbase):
+            return NotImplemented
+
+        return  (self._std_offset == other._std_offset and
+                 self._dst_offset == other._dst_offset and
+                 self._stddayofweek == other._stddayofweek and
+                 self._dstdayofweek == other._dstdayofweek and
+                 self._stdweeknumber == other._stdweeknumber and
+                 self._dstweeknumber == other._dstweeknumber and
+                 self._stdhour == other._stdhour and
+                 self._dsthour == other._dsthour and
+                 self._stdminute == other._stdminute and
+                 self._dstminute == other._dstminute and
+                 self._std_abbr == other._std_abbr and
+                 self._dst_abbr == other._dst_abbr)
+
+    @staticmethod
+    def list():
+        """Return a list of all time zones known to the system."""
+        with winreg.ConnectRegistry(None, winreg.HKEY_LOCAL_MACHINE) as handle:
+            with winreg.OpenKey(handle, TZKEYNAME) as tzkey:
+                result = [winreg.EnumKey(tzkey, i)
+                          for i in range(winreg.QueryInfoKey(tzkey)[0])]
+        return result
+
+    def display(self):
+        """
+        Return the display name of the time zone.
+        """
+        return self._display
+
+    def transitions(self, year):
+        """
+        For a given year, get the DST on and off transition times, expressed
+        always on the standard time side. For zones with no transitions, this
+        function returns ``None``.
+
+        :param year:
+            The year whose transitions you would like to query.
+
+        :return:
+            Returns a :class:`tuple` of :class:`datetime.datetime` objects,
+            ``(dston, dstoff)`` for zones with an annual DST transition, or
+            ``None`` for fixed offset zones.
+        """
+
+        if not self.hasdst:
+            return None
+
+        dston = picknthweekday(year, self._dstmonth, self._dstdayofweek,
+                               self._dsthour, self._dstminute,
+                               self._dstweeknumber)
+
+        dstoff = picknthweekday(year, self._stdmonth, self._stddayofweek,
+                                self._stdhour, self._stdminute,
+                                self._stdweeknumber)
+
+        # Ambiguous dates default to the STD side
+        dstoff -= self._dst_base_offset
+
+        return dston, dstoff
+
+    def _get_hasdst(self):
+        return self._dstmonth != 0
+
+    @property
+    def _dst_base_offset(self):
+        return self._dst_base_offset_
+
+
+class tzwin(tzwinbase):
+    """
+    Time zone object created from the zone info in the Windows registry
+
+    These are similar to :py:class:`dateutil.tz.tzrange` objects in that
+    the time zone data is provided in the format of a single offset rule
+    for either 0 or 2 time zone transitions per year.
+
+    :param: name
+        The name of a Windows time zone key, e.g. "Eastern Standard Time".
+        The full list of keys can be retrieved with :func:`tzwin.list`.
+    """
+
+    def __init__(self, name):
+        self._name = name
+
+        with winreg.ConnectRegistry(None, winreg.HKEY_LOCAL_MACHINE) as handle:
+            tzkeyname = text_type("{kn}\\{name}").format(kn=TZKEYNAME, name=name)
+            with winreg.OpenKey(handle, tzkeyname) as tzkey:
+                keydict = valuestodict(tzkey)
+
+        self._std_abbr = keydict["Std"]
+        self._dst_abbr = keydict["Dlt"]
+
+        self._display = keydict["Display"]
+
+        # See http://ww_winreg.jsiinc.com/SUBA/tip0300/rh0398.htm
+        tup = struct.unpack("=3l16h", keydict["TZI"])
+        stdoffset = -tup[0]-tup[1]          # Bias + StandardBias * -1
+        dstoffset = stdoffset-tup[2]        # + DaylightBias * -1
+        self._std_offset = datetime.timedelta(minutes=stdoffset)
+        self._dst_offset = datetime.timedelta(minutes=dstoffset)
+
+        # for the meaning see the win32 TIME_ZONE_INFORMATION structure docs
+        # http://msdn.microsoft.com/en-us/library/windows/desktop/ms725481(v=vs.85).aspx
+        (self._stdmonth,
+         self._stddayofweek,   # Sunday = 0
+         self._stdweeknumber,  # Last = 5
+         self._stdhour,
+         self._stdminute) = tup[4:9]
+
+        (self._dstmonth,
+         self._dstdayofweek,   # Sunday = 0
+         self._dstweeknumber,  # Last = 5
+         self._dsthour,
+         self._dstminute) = tup[12:17]
+
+        self._dst_base_offset_ = self._dst_offset - self._std_offset
+        self.hasdst = self._get_hasdst()
+
+    def __repr__(self):
+        return "tzwin(%s)" % repr(self._name)
+
+    def __reduce__(self):
+        return (self.__class__, (self._name,))
+
+
+class tzwinlocal(tzwinbase):
+    """
+    Class representing the local time zone information in the Windows registry
+
+    While :class:`dateutil.tz.tzlocal` makes system calls (via the :mod:`time`
+    module) to retrieve time zone information, ``tzwinlocal`` retrieves the
+    rules directly from the Windows registry and creates an object like
+    :class:`dateutil.tz.tzwin`.
+
+    Because Windows does not have an equivalent of :func:`time.tzset`, on
+    Windows, :class:`dateutil.tz.tzlocal` instances will always reflect the
+    time zone settings *at the time that the process was started*, meaning
+    changes to the machine's time zone settings during the run of a program
+    on Windows will **not** be reflected by :class:`dateutil.tz.tzlocal`.
+    Because ``tzwinlocal`` reads the registry directly, it is unaffected by
+    this issue.
+    """
+    def __init__(self):
+        with winreg.ConnectRegistry(None, winreg.HKEY_LOCAL_MACHINE) as handle:
+            with winreg.OpenKey(handle, TZLOCALKEYNAME) as tzlocalkey:
+                keydict = valuestodict(tzlocalkey)
+
+            self._std_abbr = keydict["StandardName"]
+            self._dst_abbr = keydict["DaylightName"]
+
+            try:
+                tzkeyname = text_type('{kn}\\{sn}').format(kn=TZKEYNAME,
+                                                          sn=self._std_abbr)
+                with winreg.OpenKey(handle, tzkeyname) as tzkey:
+                    _keydict = valuestodict(tzkey)
+                    self._display = _keydict["Display"]
+            except OSError:
+                self._display = None
+
+        stdoffset = -keydict["Bias"]-keydict["StandardBias"]
+        dstoffset = stdoffset-keydict["DaylightBias"]
+
+        self._std_offset = datetime.timedelta(minutes=stdoffset)
+        self._dst_offset = datetime.timedelta(minutes=dstoffset)
+
+        # For reasons unclear, in this particular key, the day of week has been
+        # moved to the END of the SYSTEMTIME structure.
+        tup = struct.unpack("=8h", keydict["StandardStart"])
+
+        (self._stdmonth,
+         self._stdweeknumber,  # Last = 5
+         self._stdhour,
+         self._stdminute) = tup[1:5]
+
+        self._stddayofweek = tup[7]
+
+        tup = struct.unpack("=8h", keydict["DaylightStart"])
+
+        (self._dstmonth,
+         self._dstweeknumber,  # Last = 5
+         self._dsthour,
+         self._dstminute) = tup[1:5]
+
+        self._dstdayofweek = tup[7]
+
+        self._dst_base_offset_ = self._dst_offset - self._std_offset
+        self.hasdst = self._get_hasdst()
+
+    def __repr__(self):
+        return "tzwinlocal()"
+
+    def __str__(self):
+        # str will return the standard name, not the daylight name.
+        return "tzwinlocal(%s)" % repr(self._std_abbr)
+
+    def __reduce__(self):
+        return (self.__class__, ())
+
+
+def picknthweekday(year, month, dayofweek, hour, minute, whichweek):
+    """ dayofweek == 0 means Sunday, whichweek 5 means last instance """
+    first = datetime.datetime(year, month, 1, hour, minute)
+
+    # This will work if dayofweek is ISO weekday (1-7) or Microsoft-style (0-6),
+    # Because 7 % 7 = 0
+    weekdayone = first.replace(day=((dayofweek - first.isoweekday()) % 7) + 1)
+    wd = weekdayone + ((whichweek - 1) * ONEWEEK)
+    if (wd.month != month):
+        wd -= ONEWEEK
+
+    return wd
+
+
+def valuestodict(key):
+    """Convert a registry key's values to a dictionary."""
+    dout = {}
+    size = winreg.QueryInfoKey(key)[1]
+    tz_res = None
+
+    for i in range(size):
+        key_name, value, dtype = winreg.EnumValue(key, i)
+        if dtype == winreg.REG_DWORD or dtype == winreg.REG_DWORD_LITTLE_ENDIAN:
+            # If it's a DWORD (32-bit integer), it's stored as unsigned - convert
+            # that to a proper signed integer
+            if value & (1 << 31):
+                value = value - (1 << 32)
+        elif dtype == winreg.REG_SZ:
+            # If it's a reference to the tzres DLL, load the actual string
+            if value.startswith('@tzres'):
+                tz_res = tz_res or tzres()
+                value = tz_res.name_from_string(value)
+
+            value = value.rstrip('\x00')    # Remove trailing nulls
+
+        dout[key_name] = value
+
+    return dout

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/tzwin.py

@@ -0,0 +1,2 @@
+# tzwin has moved to dateutil.tz.win
+from .tz.win import *

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/utils.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+"""
+This module offers general convenience and utility functions for dealing with
+datetimes.
+
+.. versionadded:: 2.7.0
+"""
+from __future__ import unicode_literals
+
+from datetime import datetime, time
+
+
+def today(tzinfo=None):
+    """
+    Returns a :py:class:`datetime` representing the current day at midnight
+
+    :param tzinfo:
+        The time zone to attach (also used to determine the current day).
+
+    :return:
+        A :py:class:`datetime.datetime` object representing the current day
+        at midnight.
+    """
+
+    dt = datetime.now(tzinfo)
+    return datetime.combine(dt.date(), time(0, tzinfo=tzinfo))
+
+
+def default_tzinfo(dt, tzinfo):
+    """
+    Sets the ``tzinfo`` parameter on naive datetimes only
+
+    This is useful for example when you are provided a datetime that may have
+    either an implicit or explicit time zone, such as when parsing a time zone
+    string.
+
+    .. doctest::
+
+        >>> from dateutil.tz import tzoffset
+        >>> from dateutil.parser import parse
+        >>> from dateutil.utils import default_tzinfo
+        >>> dflt_tz = tzoffset("EST", -18000)
+        >>> print(default_tzinfo(parse('2014-01-01 12:30 UTC'), dflt_tz))
+        2014-01-01 12:30:00+00:00
+        >>> print(default_tzinfo(parse('2014-01-01 12:30'), dflt_tz))
+        2014-01-01 12:30:00-05:00
+
+    :param dt:
+        The datetime on which to replace the time zone
+
+    :param tzinfo:
+        The :py:class:`datetime.tzinfo` subclass instance to assign to
+        ``dt`` if (and only if) it is naive.
+
+    :return:
+        Returns an aware :py:class:`datetime.datetime`.
+    """
+    if dt.tzinfo is not None:
+        return dt
+    else:
+        return dt.replace(tzinfo=tzinfo)
+
+
+def within_delta(dt1, dt2, delta):
+    """
+    Useful for comparing two datetimes that may have a negligible difference
+    to be considered equal.
+    """
+    delta = abs(delta)
+    difference = dt1 - dt2
+    return -delta <= difference <= delta

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/zoneinfo/__init__.py

@@ -0,0 +1,167 @@
+# -*- coding: utf-8 -*-
+import warnings
+import json
+
+from tarfile import TarFile
+from pkgutil import get_data
+from io import BytesIO
+
+from dateutil.tz import tzfile as _tzfile
+
+__all__ = ["get_zonefile_instance", "gettz", "gettz_db_metadata"]
+
+ZONEFILENAME = "dateutil-zoneinfo.tar.gz"
+METADATA_FN = 'METADATA'
+
+
+class tzfile(_tzfile):
+    def __reduce__(self):
+        return (gettz, (self._filename,))
+
+
+def getzoneinfofile_stream():
+    try:
+        return BytesIO(get_data(__name__, ZONEFILENAME))
+    except IOError as e:  # TODO  switch to FileNotFoundError?
+        warnings.warn("I/O error({0}): {1}".format(e.errno, e.strerror))
+        return None
+
+
+class ZoneInfoFile(object):
+    def __init__(self, zonefile_stream=None):
+        if zonefile_stream is not None:
+            with TarFile.open(fileobj=zonefile_stream) as tf:
+                self.zones = {zf.name: tzfile(tf.extractfile(zf), filename=zf.name)
+                              for zf in tf.getmembers()
+                              if zf.isfile() and zf.name != METADATA_FN}
+                # deal with links: They'll point to their parent object. Less
+                # waste of memory
+                links = {zl.name: self.zones[zl.linkname]
+                         for zl in tf.getmembers() if
+                         zl.islnk() or zl.issym()}
+                self.zones.update(links)
+                try:
+                    metadata_json = tf.extractfile(tf.getmember(METADATA_FN))
+                    metadata_str = metadata_json.read().decode('UTF-8')
+                    self.metadata = json.loads(metadata_str)
+                except KeyError:
+                    # no metadata in tar file
+                    self.metadata = None
+        else:
+            self.zones = {}
+            self.metadata = None
+
+    def get(self, name, default=None):
+        """
+        Wrapper for :func:`ZoneInfoFile.zones.get`. This is a convenience method
+        for retrieving zones from the zone dictionary.
+
+        :param name:
+            The name of the zone to retrieve. (Generally IANA zone names)
+
+        :param default:
+            The value to return in the event of a missing key.
+
+        .. versionadded:: 2.6.0
+
+        """
+        return self.zones.get(name, default)
+
+
+# The current API has gettz as a module function, although in fact it taps into
+# a stateful class. So as a workaround for now, without changing the API, we
+# will create a new "global" class instance the first time a user requests a
+# timezone. Ugly, but adheres to the api.
+#
+# TODO: Remove after deprecation period.
+_CLASS_ZONE_INSTANCE = []
+
+
+def get_zonefile_instance(new_instance=False):
+    """
+    This is a convenience function which provides a :class:`ZoneInfoFile`
+    instance using the data provided by the ``dateutil`` package. By default, it
+    caches a single instance of the ZoneInfoFile object and returns that.
+
+    :param new_instance:
+        If ``True``, a new instance of :class:`ZoneInfoFile` is instantiated and
+        used as the cached instance for the next call. Otherwise, new instances
+        are created only as necessary.
+
+    :return:
+        Returns a :class:`ZoneInfoFile` object.
+
+    .. versionadded:: 2.6
+    """
+    if new_instance:
+        zif = None
+    else:
+        zif = getattr(get_zonefile_instance, '_cached_instance', None)
+
+    if zif is None:
+        zif = ZoneInfoFile(getzoneinfofile_stream())
+
+        get_zonefile_instance._cached_instance = zif
+
+    return zif
+
+
+def gettz(name):
+    """
+    This retrieves a time zone from the local zoneinfo tarball that is packaged
+    with dateutil.
+
+    :param name:
+        An IANA-style time zone name, as found in the zoneinfo file.
+
+    :return:
+        Returns a :class:`dateutil.tz.tzfile` time zone object.
+
+    .. warning::
+        It is generally inadvisable to use this function, and it is only
+        provided for API compatibility with earlier versions. This is *not*
+        equivalent to ``dateutil.tz.gettz()``, which selects an appropriate
+        time zone based on the inputs, favoring system zoneinfo. This is ONLY
+        for accessing the dateutil-specific zoneinfo (which may be out of
+        date compared to the system zoneinfo).
+
+    .. deprecated:: 2.6
+        If you need to use a specific zoneinfofile over the system zoneinfo,
+        instantiate a :class:`dateutil.zoneinfo.ZoneInfoFile` object and call
+        :func:`dateutil.zoneinfo.ZoneInfoFile.get(name)` instead.
+
+        Use :func:`get_zonefile_instance` to retrieve an instance of the
+        dateutil-provided zoneinfo.
+    """
+    warnings.warn("zoneinfo.gettz() will be removed in future versions, "
+                  "to use the dateutil-provided zoneinfo files, instantiate a "
+                  "ZoneInfoFile object and use ZoneInfoFile.zones.get() "
+                  "instead. See the documentation for details.",
+                  DeprecationWarning)
+
+    if len(_CLASS_ZONE_INSTANCE) == 0:
+        _CLASS_ZONE_INSTANCE.append(ZoneInfoFile(getzoneinfofile_stream()))
+    return _CLASS_ZONE_INSTANCE[0].zones.get(name)
+
+
+def gettz_db_metadata():
+    """ Get the zonefile metadata
+
+    See `zonefile_metadata`_
+
+    :returns:
+        A dictionary with the database metadata
+
+    .. deprecated:: 2.6
+        See deprecation warning in :func:`zoneinfo.gettz`. To get metadata,
+        query the attribute ``zoneinfo.ZoneInfoFile.metadata``.
+    """
+    warnings.warn("zoneinfo.gettz_db_metadata() will be removed in future "
+                  "versions, to use the dateutil-provided zoneinfo files, "
+                  "ZoneInfoFile object and query the 'metadata' attribute "
+                  "instead. See the documentation for details.",
+                  DeprecationWarning)
+
+    if len(_CLASS_ZONE_INSTANCE) == 0:
+        _CLASS_ZONE_INSTANCE.append(ZoneInfoFile(getzoneinfofile_stream()))
+    return _CLASS_ZONE_INSTANCE[0].metadata

AWS Lambda Layer/python/lib/python3.9/site-packages/dateutil/zoneinfo/rebuild.py

@@ -0,0 +1,75 @@
+import logging
+import os
+import tempfile
+import shutil
+import json
+from subprocess import check_call, check_output
+from tarfile import TarFile
+
+from dateutil.zoneinfo import METADATA_FN, ZONEFILENAME
+
+
+def rebuild(filename, tag=None, format="gz", zonegroups=[], metadata=None):
+    """Rebuild the internal timezone info in dateutil/zoneinfo/zoneinfo*tar*
+
+    filename is the timezone tarball from ``ftp.iana.org/tz``.
+
+    """
+    tmpdir = tempfile.mkdtemp()
+    zonedir = os.path.join(tmpdir, "zoneinfo")
+    moduledir = os.path.dirname(__file__)
+    try:
+        with TarFile.open(filename) as tf:
+            for name in zonegroups:
+                tf.extract(name, tmpdir)
+            filepaths = [os.path.join(tmpdir, n) for n in zonegroups]
+
+            _run_zic(zonedir, filepaths)
+
+        # write metadata file
+        with open(os.path.join(zonedir, METADATA_FN), 'w') as f:
+            json.dump(metadata, f, indent=4, sort_keys=True)
+        target = os.path.join(moduledir, ZONEFILENAME)
+        with TarFile.open(target, "w:%s" % format) as tf:
+            for entry in os.listdir(zonedir):
+                entrypath = os.path.join(zonedir, entry)
+                tf.add(entrypath, entry)
+    finally:
+        shutil.rmtree(tmpdir)
+
+
+def _run_zic(zonedir, filepaths):
+    """Calls the ``zic`` compiler in a compatible way to get a "fat" binary.
+
+    Recent versions of ``zic`` default to ``-b slim``, while older versions
+    don't even have the ``-b`` option (but default to "fat" binaries). The
+    current version of dateutil does not support Version 2+ TZif files, which
+    causes problems when used in conjunction with "slim" binaries, so this
+    function is used to ensure that we always get a "fat" binary.
+    """
+
+    try:
+        help_text = check_output(["zic", "--help"])
+    except OSError as e:
+        _print_on_nosuchfile(e)
+        raise
+
+    if b"-b " in help_text:
+        bloat_args = ["-b", "fat"]
+    else:
+        bloat_args = []
+
+    check_call(["zic"] + bloat_args + ["-d", zonedir] + filepaths)
+
+
+def _print_on_nosuchfile(e):
+    """Print helpful troubleshooting message
+
+    e is an exception raised by subprocess.check_call()
+
+    """
+    if e.errno == 2:
+        logging.error(
+            "Could not find zic. Perhaps you need to install "
+            "libc-bin or some other package that provides it, "
+            "or it's not in your PATH?")

AWS Lambda Layer/python/lib/python3.9/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",
+]

AWS Lambda Layer/python/lib/python3.9/site-packages/idna/codec.py

@@ -0,0 +1,112 @@
+from .core import encode, decode, alabel, ulabel, IDNAError
+import codecs
+import re
+from typing import 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[str, int]:  # type: ignore
+        if errors != 'strict':
+            raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
+
+        if not data:
+            return "", 0
+
+        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(alabel(label))
+            if size:
+                size += 1
+            size += len(label)
+
+        # Join with U+002E
+        result_str = '.'.join(result) + trailing_dot  # type: ignore
+        size += len(trailing_dot)
+        return result_str, size
+
+class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
+    def _buffer_decode(self, data: str, errors: str, final: bool) -> Tuple[str, int]:  # type: ignore
+        if errors != 'strict':
+            raise IDNAError('Unsupported error handling \"{}\"'.format(errors))
+
+        if not data:
+            return ('', 0)
+
+        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 getregentry() -> codecs.CodecInfo:
+    # Compatibility as a search_function for codecs.register()
+    return codecs.CodecInfo(
+        name='idna',
+        encode=Codec().encode,  # type: ignore
+        decode=Codec().decode,  # type: ignore
+        incrementalencoder=IncrementalEncoder,
+        incrementaldecoder=IncrementalDecoder,
+        streamwriter=StreamWriter,
+        streamreader=StreamReader,
+    )

AWS Lambda Layer/python/lib/python3.9/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')
+

AWS Lambda Layer/python/lib/python3.9/site-packages/idna/core.py

@@ -0,0 +1,397 @@
+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
+            if joining_type in [ord('L'), ord('D')]:
+                ok = True
+                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
+            if joining_type in [ord('R'), ord('D')]:
+                ok = True
+                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
+
+    if not label:
+        raise IDNAError('No Input')
+
+    label = str(label)
+    check_label(label)
+    label_bytes = _punycode(label)
+    label_bytes = _alabel_prefix + label_bytes
+
+    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]  # type: ignore
+            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 isinstance(s, (bytes, bytearray)):
+        s = s.decode('ascii')
+    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 isinstance(s, (bytes, bytearray)):
+            s = s.decode('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)

AWS Lambda Layer/python/lib/python3.9/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

AWS Lambda Layer/python/lib/python3.9/site-packages/idna/package_data.py

@@ -0,0 +1,2 @@
+__version__ = '3.3'
+

AWS Lambda Layer/python/lib/python3.9/site-packages/requests/__init__.py

@@ -0,0 +1,152 @@
+# -*- coding: utf-8 -*-
+
+#   __
+#  /__)  _  _     _   _ _/   _
+# / (   (- (/ (/ (- _)  /  _)
+#          /
+
+"""
+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 urllib3
+import warnings
+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, <= 1.26
+    assert major == 1
+    assert minor >= 21
+    assert minor <= 26
+
+    # 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, < 5.0.0
+        assert (3, 0, 2) <= (major, minor, patch) < (5, 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 < 3.0.0
+        assert (2, 0, 0) <= (major, minor, patch) < (3, 0, 0)
+    else:
+        raise Exception("You need either charset_normalizer or chardet installed")
+
+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)
+
+from .__version__ import __title__, __description__, __url__, __version__
+from .__version__ import __build__, __author__, __author_email__, __license__
+from .__version__ import __copyright__, __cake__
+
+from . import utils
+from . import packages
+from .models import Request, Response, PreparedRequest
+from .api import request, get, head, post, patch, put, delete, options
+from .sessions import session, Session
+from .status_codes import codes
+from .exceptions import (
+    RequestException, Timeout, URLRequired,
+    TooManyRedirects, HTTPError, ConnectionError,
+    FileModeWarning, ConnectTimeout, ReadTimeout, JSONDecodeError
+)
+
+# Set default logging handler to avoid "No handler found" warnings.
+import logging
+from logging import NullHandler
+
+logging.getLogger(__name__).addHandler(NullHandler())
+
+# FileModeWarnings go off per the default.
+warnings.simplefilter('default', FileModeWarning, append=True)