xplia 1.0.1__py3-none-any.whl

venv/Lib/site-packages/pip/_vendor/chardet/metadata/languages.py

@@ -0,0 +1,352 @@
+"""
+Metadata about languages used by our model training code for our
+SingleByteCharSetProbers.  Could be used for other things in the future.
+
+This code is based on the language metadata from the uchardet project.
+"""
+
+from string import ascii_letters
+from typing import List, Optional
+
+# TODO: Add Ukrainian (KOI8-U)
+
+
+class Language:
+    """Metadata about a language useful for training models
+
+    :ivar name: The human name for the language, in English.
+    :type name: str
+    :ivar iso_code: 2-letter ISO 639-1 if possible, 3-letter ISO code otherwise,
+                    or use another catalog as a last resort.
+    :type iso_code: str
+    :ivar use_ascii: Whether or not ASCII letters should be included in trained
+                     models.
+    :type use_ascii: bool
+    :ivar charsets: The charsets we want to support and create data for.
+    :type charsets: list of str
+    :ivar alphabet: The characters in the language's alphabet. If `use_ascii` is
+                    `True`, you only need to add those not in the ASCII set.
+    :type alphabet: str
+    :ivar wiki_start_pages: The Wikipedia pages to start from if we're crawling
+                            Wikipedia for training data.
+    :type wiki_start_pages: list of str
+    """
+
+    def __init__(
+        self,
+        name: Optional[str] = None,
+        iso_code: Optional[str] = None,
+        use_ascii: bool = True,
+        charsets: Optional[List[str]] = None,
+        alphabet: Optional[str] = None,
+        wiki_start_pages: Optional[List[str]] = None,
+    ) -> None:
+        super().__init__()
+        self.name = name
+        self.iso_code = iso_code
+        self.use_ascii = use_ascii
+        self.charsets = charsets
+        if self.use_ascii:
+            if alphabet:
+                alphabet += ascii_letters
+            else:
+                alphabet = ascii_letters
+        elif not alphabet:
+            raise ValueError("Must supply alphabet if use_ascii is False")
+        self.alphabet = "".join(sorted(set(alphabet))) if alphabet else None
+        self.wiki_start_pages = wiki_start_pages
+
+    def __repr__(self) -> str:
+        param_str = ", ".join(
+            f"{k}={v!r}" for k, v in self.__dict__.items() if not k.startswith("_")
+        )
+        return f"{self.__class__.__name__}({param_str})"
+
+
+LANGUAGES = {
+    "Arabic": Language(
+        name="Arabic",
+        iso_code="ar",
+        use_ascii=False,
+        # We only support encodings that use isolated
+        # forms, because the current recommendation is
+        # that the rendering system handles presentation
+        # forms. This means we purposefully skip IBM864.
+        charsets=["ISO-8859-6", "WINDOWS-1256", "CP720", "CP864"],
+        alphabet="ءآأؤإئابةتثجحخدذرزسشصضطظعغػؼؽؾؿـفقكلمنهوىيًٌٍَُِّ",
+        wiki_start_pages=["الصفحة_الرئيسية"],
+    ),
+    "Belarusian": Language(
+        name="Belarusian",
+        iso_code="be",
+        use_ascii=False,
+        charsets=["ISO-8859-5", "WINDOWS-1251", "IBM866", "MacCyrillic"],
+        alphabet="АБВГДЕЁЖЗІЙКЛМНОПРСТУЎФХЦЧШЫЬЭЮЯабвгдеёжзійклмнопрстуўфхцчшыьэюяʼ",
+        wiki_start_pages=["Галоўная_старонка"],
+    ),
+    "Bulgarian": Language(
+        name="Bulgarian",
+        iso_code="bg",
+        use_ascii=False,
+        charsets=["ISO-8859-5", "WINDOWS-1251", "IBM855"],
+        alphabet="АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯабвгдежзийклмнопрстуфхцчшщъьюя",
+        wiki_start_pages=["Начална_страница"],
+    ),
+    "Czech": Language(
+        name="Czech",
+        iso_code="cz",
+        use_ascii=True,
+        charsets=["ISO-8859-2", "WINDOWS-1250"],
+        alphabet="áčďéěíňóřšťúůýžÁČĎÉĚÍŇÓŘŠŤÚŮÝŽ",
+        wiki_start_pages=["Hlavní_strana"],
+    ),
+    "Danish": Language(
+        name="Danish",
+        iso_code="da",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
+        alphabet="æøåÆØÅ",
+        wiki_start_pages=["Forside"],
+    ),
+    "German": Language(
+        name="German",
+        iso_code="de",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
+        alphabet="äöüßẞÄÖÜ",
+        wiki_start_pages=["Wikipedia:Hauptseite"],
+    ),
+    "Greek": Language(
+        name="Greek",
+        iso_code="el",
+        use_ascii=False,
+        charsets=["ISO-8859-7", "WINDOWS-1253"],
+        alphabet="αβγδεζηθικλμνξοπρσςτυφχψωάέήίόύώΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΣΤΥΦΧΨΩΆΈΉΊΌΎΏ",
+        wiki_start_pages=["Πύλη:Κύρια"],
+    ),
+    "English": Language(
+        name="English",
+        iso_code="en",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "WINDOWS-1252", "MacRoman"],
+        wiki_start_pages=["Main_Page"],
+    ),
+    "Esperanto": Language(
+        name="Esperanto",
+        iso_code="eo",
+        # Q, W, X, and Y not used at all
+        use_ascii=False,
+        charsets=["ISO-8859-3"],
+        alphabet="abcĉdefgĝhĥijĵklmnoprsŝtuŭvzABCĈDEFGĜHĤIJĴKLMNOPRSŜTUŬVZ",
+        wiki_start_pages=["Vikipedio:Ĉefpaĝo"],
+    ),
+    "Spanish": Language(
+        name="Spanish",
+        iso_code="es",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
+        alphabet="ñáéíóúüÑÁÉÍÓÚÜ",
+        wiki_start_pages=["Wikipedia:Portada"],
+    ),
+    "Estonian": Language(
+        name="Estonian",
+        iso_code="et",
+        use_ascii=False,
+        charsets=["ISO-8859-4", "ISO-8859-13", "WINDOWS-1257"],
+        # C, F, Š, Q, W, X, Y, Z, Ž are only for
+        # loanwords
+        alphabet="ABDEGHIJKLMNOPRSTUVÕÄÖÜabdeghijklmnoprstuvõäöü",
+        wiki_start_pages=["Esileht"],
+    ),
+    "Finnish": Language(
+        name="Finnish",
+        iso_code="fi",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
+        alphabet="ÅÄÖŠŽåäöšž",
+        wiki_start_pages=["Wikipedia:Etusivu"],
+    ),
+    "French": Language(
+        name="French",
+        iso_code="fr",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
+        alphabet="œàâçèéîïùûêŒÀÂÇÈÉÎÏÙÛÊ",
+        wiki_start_pages=["Wikipédia:Accueil_principal", "Bœuf (animal)"],
+    ),
+    "Hebrew": Language(
+        name="Hebrew",
+        iso_code="he",
+        use_ascii=False,
+        charsets=["ISO-8859-8", "WINDOWS-1255"],
+        alphabet="אבגדהוזחטיךכלםמןנסעףפץצקרשתװױײ",
+        wiki_start_pages=["עמוד_ראשי"],
+    ),
+    "Croatian": Language(
+        name="Croatian",
+        iso_code="hr",
+        # Q, W, X, Y are only used for foreign words.
+        use_ascii=False,
+        charsets=["ISO-8859-2", "WINDOWS-1250"],
+        alphabet="abcčćdđefghijklmnoprsštuvzžABCČĆDĐEFGHIJKLMNOPRSŠTUVZŽ",
+        wiki_start_pages=["Glavna_stranica"],
+    ),
+    "Hungarian": Language(
+        name="Hungarian",
+        iso_code="hu",
+        # Q, W, X, Y are only used for foreign words.
+        use_ascii=False,
+        charsets=["ISO-8859-2", "WINDOWS-1250"],
+        alphabet="abcdefghijklmnoprstuvzáéíóöőúüűABCDEFGHIJKLMNOPRSTUVZÁÉÍÓÖŐÚÜŰ",
+        wiki_start_pages=["Kezdőlap"],
+    ),
+    "Italian": Language(
+        name="Italian",
+        iso_code="it",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
+        alphabet="ÀÈÉÌÒÓÙàèéìòóù",
+        wiki_start_pages=["Pagina_principale"],
+    ),
+    "Lithuanian": Language(
+        name="Lithuanian",
+        iso_code="lt",
+        use_ascii=False,
+        charsets=["ISO-8859-13", "WINDOWS-1257", "ISO-8859-4"],
+        # Q, W, and X not used at all
+        alphabet="AĄBCČDEĘĖFGHIĮYJKLMNOPRSŠTUŲŪVZŽaąbcčdeęėfghiįyjklmnoprsštuųūvzž",
+        wiki_start_pages=["Pagrindinis_puslapis"],
+    ),
+    "Latvian": Language(
+        name="Latvian",
+        iso_code="lv",
+        use_ascii=False,
+        charsets=["ISO-8859-13", "WINDOWS-1257", "ISO-8859-4"],
+        # Q, W, X, Y are only for loanwords
+        alphabet="AĀBCČDEĒFGĢHIĪJKĶLĻMNŅOPRSŠTUŪVZŽaābcčdeēfgģhiījkķlļmnņoprsštuūvzž",
+        wiki_start_pages=["Sākumlapa"],
+    ),
+    "Macedonian": Language(
+        name="Macedonian",
+        iso_code="mk",
+        use_ascii=False,
+        charsets=["ISO-8859-5", "WINDOWS-1251", "MacCyrillic", "IBM855"],
+        alphabet="АБВГДЃЕЖЗЅИЈКЛЉМНЊОПРСТЌУФХЦЧЏШабвгдѓежзѕијклљмнњопрстќуфхцчџш",
+        wiki_start_pages=["Главна_страница"],
+    ),
+    "Dutch": Language(
+        name="Dutch",
+        iso_code="nl",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "WINDOWS-1252", "MacRoman"],
+        wiki_start_pages=["Hoofdpagina"],
+    ),
+    "Polish": Language(
+        name="Polish",
+        iso_code="pl",
+        # Q and X are only used for foreign words.
+        use_ascii=False,
+        charsets=["ISO-8859-2", "WINDOWS-1250"],
+        alphabet="AĄBCĆDEĘFGHIJKLŁMNŃOÓPRSŚTUWYZŹŻaąbcćdeęfghijklłmnńoóprsśtuwyzźż",
+        wiki_start_pages=["Wikipedia:Strona_główna"],
+    ),
+    "Portuguese": Language(
+        name="Portuguese",
+        iso_code="pt",
+        use_ascii=True,
+        charsets=["ISO-8859-1", "ISO-8859-15", "WINDOWS-1252", "MacRoman"],
+        alphabet="ÁÂÃÀÇÉÊÍÓÔÕÚáâãàçéêíóôõú",
+        wiki_start_pages=["Wikipédia:Página_principal"],
+    ),
+    "Romanian": Language(
+        name="Romanian",
+        iso_code="ro",
+        use_ascii=True,
+        charsets=["ISO-8859-2", "WINDOWS-1250"],
+        alphabet="ăâîșțĂÂÎȘȚ",
+        wiki_start_pages=["Pagina_principală"],
+    ),
+    "Russian": Language(
+        name="Russian",
+        iso_code="ru",
+        use_ascii=False,
+        charsets=[
+            "ISO-8859-5",
+            "WINDOWS-1251",
+            "KOI8-R",
+            "MacCyrillic",
+            "IBM866",
+            "IBM855",
+        ],
+        alphabet="абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ",
+        wiki_start_pages=["Заглавная_страница"],
+    ),
+    "Slovak": Language(
+        name="Slovak",
+        iso_code="sk",
+        use_ascii=True,
+        charsets=["ISO-8859-2", "WINDOWS-1250"],
+        alphabet="áäčďéíĺľňóôŕšťúýžÁÄČĎÉÍĹĽŇÓÔŔŠŤÚÝŽ",
+        wiki_start_pages=["Hlavná_stránka"],
+    ),
+    "Slovene": Language(
+        name="Slovene",
+        iso_code="sl",
+        # Q, W, X, Y are only used for foreign words.
+        use_ascii=False,
+        charsets=["ISO-8859-2", "WINDOWS-1250"],
+        alphabet="abcčdefghijklmnoprsštuvzžABCČDEFGHIJKLMNOPRSŠTUVZŽ",
+        wiki_start_pages=["Glavna_stran"],
+    ),
+    # Serbian can be written in both Latin and Cyrillic, but there's no
+    # simple way to get the Latin alphabet pages from Wikipedia through
+    # the API, so for now we just support Cyrillic.
+    "Serbian": Language(
+        name="Serbian",
+        iso_code="sr",
+        alphabet="АБВГДЂЕЖЗИЈКЛЉМНЊОПРСТЋУФХЦЧЏШабвгдђежзијклљмнњопрстћуфхцчџш",
+        charsets=["ISO-8859-5", "WINDOWS-1251", "MacCyrillic", "IBM855"],
+        wiki_start_pages=["Главна_страна"],
+    ),
+    "Thai": Language(
+        name="Thai",
+        iso_code="th",
+        use_ascii=False,
+        charsets=["ISO-8859-11", "TIS-620", "CP874"],
+        alphabet="กขฃคฅฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลฦวศษสหฬอฮฯะัาำิีึืฺุู฿เแโใไๅๆ็่้๊๋์ํ๎๏๐๑๒๓๔๕๖๗๘๙๚๛",
+        wiki_start_pages=["หน้าหลัก"],
+    ),
+    "Turkish": Language(
+        name="Turkish",
+        iso_code="tr",
+        # Q, W, and X are not used by Turkish
+        use_ascii=False,
+        charsets=["ISO-8859-3", "ISO-8859-9", "WINDOWS-1254"],
+        alphabet="abcçdefgğhıijklmnoöprsştuüvyzâîûABCÇDEFGĞHIİJKLMNOÖPRSŞTUÜVYZÂÎÛ",
+        wiki_start_pages=["Ana_Sayfa"],
+    ),
+    "Vietnamese": Language(
+        name="Vietnamese",
+        iso_code="vi",
+        use_ascii=False,
+        # Windows-1258 is the only common 8-bit
+        # Vietnamese encoding supported by Python.
+        # From Wikipedia:
+        # For systems that lack support for Unicode,
+        # dozens of 8-bit Vietnamese code pages are
+        # available.[1] The most common are VISCII
+        # (TCVN 5712:1993), VPS, and Windows-1258.[3]
+        # Where ASCII is required, such as when
+        # ensuring readability in plain text e-mail,
+        # Vietnamese letters are often encoded
+        # according to Vietnamese Quoted-Readable
+        # (VIQR) or VSCII Mnemonic (VSCII-MNEM),[4]
+        # though usage of either variable-width
+        # scheme has declined dramatically following
+        # the adoption of Unicode on the World Wide
+        # Web.
+        charsets=["WINDOWS-1258"],
+        alphabet="aăâbcdđeêghiklmnoôơpqrstuưvxyAĂÂBCDĐEÊGHIKLMNOÔƠPQRSTUƯVXY",
+        wiki_start_pages=["Chữ_Quốc_ngữ"],
+    ),
+}

venv/Lib/site-packages/pip/_vendor/chardet/resultdict.py

@@ -0,0 +1,16 @@
+from typing import TYPE_CHECKING, Optional
+
+if TYPE_CHECKING:
+    # TypedDict was introduced in Python 3.8.
+    #
+    # TODO: Remove the else block and TYPE_CHECKING check when dropping support
+    # for Python 3.7.
+    from typing import TypedDict
+
+    class ResultDict(TypedDict):
+        encoding: Optional[str]
+        confidence: float
+        language: Optional[str]
+
+else:
+    ResultDict = dict

venv/Lib/site-packages/pip/_vendor/chardet/sbcharsetprober.py

@@ -0,0 +1,162 @@
+######################## BEGIN LICENSE BLOCK ########################
+# The Original Code is Mozilla Universal charset detector code.
+#
+# The Initial Developer of the Original Code is
+# Netscape Communications Corporation.
+# Portions created by the Initial Developer are Copyright (C) 2001
+# the Initial Developer. All Rights Reserved.
+#
+# Contributor(s):
+#   Mark Pilgrim - port to Python
+#   Shy Shalom - original C code
+#
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2.1 of the License, or (at your option) any later version.
+#
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+# 02110-1301  USA
+######################### END LICENSE BLOCK #########################
+
+from typing import Dict, List, NamedTuple, Optional, Union
+
+from .charsetprober import CharSetProber
+from .enums import CharacterCategory, ProbingState, SequenceLikelihood
+
+
+class SingleByteCharSetModel(NamedTuple):
+    charset_name: str
+    language: str
+    char_to_order_map: Dict[int, int]
+    language_model: Dict[int, Dict[int, int]]
+    typical_positive_ratio: float
+    keep_ascii_letters: bool
+    alphabet: str
+
+
+class SingleByteCharSetProber(CharSetProber):
+    SAMPLE_SIZE = 64
+    SB_ENOUGH_REL_THRESHOLD = 1024  # 0.25 * SAMPLE_SIZE^2
+    POSITIVE_SHORTCUT_THRESHOLD = 0.95
+    NEGATIVE_SHORTCUT_THRESHOLD = 0.05
+
+    def __init__(
+        self,
+        model: SingleByteCharSetModel,
+        is_reversed: bool = False,
+        name_prober: Optional[CharSetProber] = None,
+    ) -> None:
+        super().__init__()
+        self._model = model
+        # TRUE if we need to reverse every pair in the model lookup
+        self._reversed = is_reversed
+        # Optional auxiliary prober for name decision
+        self._name_prober = name_prober
+        self._last_order = 255
+        self._seq_counters: List[int] = []
+        self._total_seqs = 0
+        self._total_char = 0
+        self._control_char = 0
+        self._freq_char = 0
+        self.reset()
+
+    def reset(self) -> None:
+        super().reset()
+        # char order of last character
+        self._last_order = 255
+        self._seq_counters = [0] * SequenceLikelihood.get_num_categories()
+        self._total_seqs = 0
+        self._total_char = 0
+        self._control_char = 0
+        # characters that fall in our sampling range
+        self._freq_char = 0
+
+    @property
+    def charset_name(self) -> Optional[str]:
+        if self._name_prober:
+            return self._name_prober.charset_name
+        return self._model.charset_name
+
+    @property
+    def language(self) -> Optional[str]:
+        if self._name_prober:
+            return self._name_prober.language
+        return self._model.language
+
+    def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
+        # TODO: Make filter_international_words keep things in self.alphabet
+        if not self._model.keep_ascii_letters:
+            byte_str = self.filter_international_words(byte_str)
+        else:
+            byte_str = self.remove_xml_tags(byte_str)
+        if not byte_str:
+            return self.state
+        char_to_order_map = self._model.char_to_order_map
+        language_model = self._model.language_model
+        for char in byte_str:
+            order = char_to_order_map.get(char, CharacterCategory.UNDEFINED)
+            # XXX: This was SYMBOL_CAT_ORDER before, with a value of 250, but
+            #      CharacterCategory.SYMBOL is actually 253, so we use CONTROL
+            #      to make it closer to the original intent. The only difference
+            #      is whether or not we count digits and control characters for
+            #      _total_char purposes.
+            if order < CharacterCategory.CONTROL:
+                self._total_char += 1
+            if order < self.SAMPLE_SIZE:
+                self._freq_char += 1
+                if self._last_order < self.SAMPLE_SIZE:
+                    self._total_seqs += 1
+                    if not self._reversed:
+                        lm_cat = language_model[self._last_order][order]
+                    else:
+                        lm_cat = language_model[order][self._last_order]
+                    self._seq_counters[lm_cat] += 1
+            self._last_order = order
+
+        charset_name = self._model.charset_name
+        if self.state == ProbingState.DETECTING:
+            if self._total_seqs > self.SB_ENOUGH_REL_THRESHOLD:
+                confidence = self.get_confidence()
+                if confidence > self.POSITIVE_SHORTCUT_THRESHOLD:
+                    self.logger.debug(
+                        "%s confidence = %s, we have a winner", charset_name, confidence
+                    )
+                    self._state = ProbingState.FOUND_IT
+                elif confidence < self.NEGATIVE_SHORTCUT_THRESHOLD:
+                    self.logger.debug(
+                        "%s confidence = %s, below negative shortcut threshold %s",
+                        charset_name,
+                        confidence,
+                        self.NEGATIVE_SHORTCUT_THRESHOLD,
+                    )
+                    self._state = ProbingState.NOT_ME
+
+        return self.state
+
+    def get_confidence(self) -> float:
+        r = 0.01
+        if self._total_seqs > 0:
+            r = (
+                (
+                    self._seq_counters[SequenceLikelihood.POSITIVE]
+                    + 0.25 * self._seq_counters[SequenceLikelihood.LIKELY]
+                )
+                / self._total_seqs
+                / self._model.typical_positive_ratio
+            )
+            # The more control characters (proportionnaly to the size
+            # of the text), the less confident we become in the current
+            # charset.
+            r = r * (self._total_char - self._control_char) / self._total_char
+            r = r * self._freq_char / self._total_char
+            if r >= 1.0:
+                r = 0.99
+        return r

venv/Lib/site-packages/pip/_vendor/chardet/sbcsgroupprober.py

@@ -0,0 +1,88 @@
+######################## BEGIN LICENSE BLOCK ########################
+# The Original Code is Mozilla Universal charset detector code.
+#
+# The Initial Developer of the Original Code is
+# Netscape Communications Corporation.
+# Portions created by the Initial Developer are Copyright (C) 2001
+# the Initial Developer. All Rights Reserved.
+#
+# Contributor(s):
+#   Mark Pilgrim - port to Python
+#   Shy Shalom - original C code
+#
+# This library is free software; you can redistribute it and/or
+# modify it under the terms of the GNU Lesser General Public
+# License as published by the Free Software Foundation; either
+# version 2.1 of the License, or (at your option) any later version.
+#
+# This library is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+# Lesser General Public License for more details.
+#
+# You should have received a copy of the GNU Lesser General Public
+# License along with this library; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+# 02110-1301  USA
+######################### END LICENSE BLOCK #########################
+
+from .charsetgroupprober import CharSetGroupProber
+from .hebrewprober import HebrewProber
+from .langbulgarianmodel import ISO_8859_5_BULGARIAN_MODEL, WINDOWS_1251_BULGARIAN_MODEL
+from .langgreekmodel import ISO_8859_7_GREEK_MODEL, WINDOWS_1253_GREEK_MODEL
+from .langhebrewmodel import WINDOWS_1255_HEBREW_MODEL
+
+# from .langhungarianmodel import (ISO_8859_2_HUNGARIAN_MODEL,
+#                                  WINDOWS_1250_HUNGARIAN_MODEL)
+from .langrussianmodel import (
+    IBM855_RUSSIAN_MODEL,
+    IBM866_RUSSIAN_MODEL,
+    ISO_8859_5_RUSSIAN_MODEL,
+    KOI8_R_RUSSIAN_MODEL,
+    MACCYRILLIC_RUSSIAN_MODEL,
+    WINDOWS_1251_RUSSIAN_MODEL,
+)
+from .langthaimodel import TIS_620_THAI_MODEL
+from .langturkishmodel import ISO_8859_9_TURKISH_MODEL
+from .sbcharsetprober import SingleByteCharSetProber
+
+
+class SBCSGroupProber(CharSetGroupProber):
+    def __init__(self) -> None:
+        super().__init__()
+        hebrew_prober = HebrewProber()
+        logical_hebrew_prober = SingleByteCharSetProber(
+            WINDOWS_1255_HEBREW_MODEL, is_reversed=False, name_prober=hebrew_prober
+        )
+        # TODO: See if using ISO-8859-8 Hebrew model works better here, since
+        #       it's actually the visual one
+        visual_hebrew_prober = SingleByteCharSetProber(
+            WINDOWS_1255_HEBREW_MODEL, is_reversed=True, name_prober=hebrew_prober
+        )
+        hebrew_prober.set_model_probers(logical_hebrew_prober, visual_hebrew_prober)
+        # TODO: ORDER MATTERS HERE. I changed the order vs what was in master
+        #       and several tests failed that did not before. Some thought
+        #       should be put into the ordering, and we should consider making
+        #       order not matter here, because that is very counter-intuitive.
+        self.probers = [
+            SingleByteCharSetProber(WINDOWS_1251_RUSSIAN_MODEL),
+            SingleByteCharSetProber(KOI8_R_RUSSIAN_MODEL),
+            SingleByteCharSetProber(ISO_8859_5_RUSSIAN_MODEL),
+            SingleByteCharSetProber(MACCYRILLIC_RUSSIAN_MODEL),
+            SingleByteCharSetProber(IBM866_RUSSIAN_MODEL),
+            SingleByteCharSetProber(IBM855_RUSSIAN_MODEL),
+            SingleByteCharSetProber(ISO_8859_7_GREEK_MODEL),
+            SingleByteCharSetProber(WINDOWS_1253_GREEK_MODEL),
+            SingleByteCharSetProber(ISO_8859_5_BULGARIAN_MODEL),
+            SingleByteCharSetProber(WINDOWS_1251_BULGARIAN_MODEL),
+            # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250)
+            #       after we retrain model.
+            # SingleByteCharSetProber(ISO_8859_2_HUNGARIAN_MODEL),
+            # SingleByteCharSetProber(WINDOWS_1250_HUNGARIAN_MODEL),
+            SingleByteCharSetProber(TIS_620_THAI_MODEL),
+            SingleByteCharSetProber(ISO_8859_9_TURKISH_MODEL),
+            hebrew_prober,
+            logical_hebrew_prober,
+            visual_hebrew_prober,
+        ]
+        self.reset()