xplia 1.0.1__py3-none-any.whl

venv/Lib/site-packages/pip/_vendor/chardet/latin1prober.py

@@ -0,0 +1,147 @@
+######################## 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 List, Union
+
+from .charsetprober import CharSetProber
+from .enums import ProbingState
+
+FREQ_CAT_NUM = 4
+
+UDF = 0  # undefined
+OTH = 1  # other
+ASC = 2  # ascii capital letter
+ASS = 3  # ascii small letter
+ACV = 4  # accent capital vowel
+ACO = 5  # accent capital other
+ASV = 6  # accent small vowel
+ASO = 7  # accent small other
+CLASS_NUM = 8  # total classes
+
+# fmt: off
+Latin1_CharToClass = (
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 00 - 07
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 08 - 0F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 10 - 17
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 18 - 1F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 20 - 27
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 28 - 2F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 30 - 37
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 38 - 3F
+    OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC,   # 40 - 47
+    ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC,   # 48 - 4F
+    ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC,   # 50 - 57
+    ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH,   # 58 - 5F
+    OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS,   # 60 - 67
+    ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS,   # 68 - 6F
+    ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS,   # 70 - 77
+    ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH,   # 78 - 7F
+    OTH, UDF, OTH, ASO, OTH, OTH, OTH, OTH,   # 80 - 87
+    OTH, OTH, ACO, OTH, ACO, UDF, ACO, UDF,   # 88 - 8F
+    UDF, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # 90 - 97
+    OTH, OTH, ASO, OTH, ASO, UDF, ASO, ACO,   # 98 - 9F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # A0 - A7
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # A8 - AF
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # B0 - B7
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,   # B8 - BF
+    ACV, ACV, ACV, ACV, ACV, ACV, ACO, ACO,   # C0 - C7
+    ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV,   # C8 - CF
+    ACO, ACO, ACV, ACV, ACV, ACV, ACV, OTH,   # D0 - D7
+    ACV, ACV, ACV, ACV, ACV, ACO, ACO, ACO,   # D8 - DF
+    ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASO,   # E0 - E7
+    ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV,   # E8 - EF
+    ASO, ASO, ASV, ASV, ASV, ASV, ASV, OTH,   # F0 - F7
+    ASV, ASV, ASV, ASV, ASV, ASO, ASO, ASO,   # F8 - FF
+)
+
+# 0 : illegal
+# 1 : very unlikely
+# 2 : normal
+# 3 : very likely
+Latin1ClassModel = (
+# UDF OTH ASC ASS ACV ACO ASV ASO
+    0,  0,  0,  0,  0,  0,  0,  0,  # UDF
+    0,  3,  3,  3,  3,  3,  3,  3,  # OTH
+    0,  3,  3,  3,  3,  3,  3,  3,  # ASC
+    0,  3,  3,  3,  1,  1,  3,  3,  # ASS
+    0,  3,  3,  3,  1,  2,  1,  2,  # ACV
+    0,  3,  3,  3,  3,  3,  3,  3,  # ACO
+    0,  3,  1,  3,  1,  1,  1,  3,  # ASV
+    0,  3,  1,  3,  1,  1,  3,  3,  # ASO
+)
+# fmt: on
+
+
+class Latin1Prober(CharSetProber):
+    def __init__(self) -> None:
+        super().__init__()
+        self._last_char_class = OTH
+        self._freq_counter: List[int] = []
+        self.reset()
+
+    def reset(self) -> None:
+        self._last_char_class = OTH
+        self._freq_counter = [0] * FREQ_CAT_NUM
+        super().reset()
+
+    @property
+    def charset_name(self) -> str:
+        return "ISO-8859-1"
+
+    @property
+    def language(self) -> str:
+        return ""
+
+    def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
+        byte_str = self.remove_xml_tags(byte_str)
+        for c in byte_str:
+            char_class = Latin1_CharToClass[c]
+            freq = Latin1ClassModel[(self._last_char_class * CLASS_NUM) + char_class]
+            if freq == 0:
+                self._state = ProbingState.NOT_ME
+                break
+            self._freq_counter[freq] += 1
+            self._last_char_class = char_class
+
+        return self.state
+
+    def get_confidence(self) -> float:
+        if self.state == ProbingState.NOT_ME:
+            return 0.01
+
+        total = sum(self._freq_counter)
+        confidence = (
+            0.0
+            if total < 0.01
+            else (self._freq_counter[3] - self._freq_counter[1] * 20.0) / total
+        )
+        confidence = max(confidence, 0.0)
+        # lower the confidence of latin1 so that other more accurate
+        # detector can take priority.
+        confidence *= 0.73
+        return confidence

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

@@ -0,0 +1,162 @@
+######################## BEGIN LICENSE BLOCK ########################
+# This code was modified from latin1prober.py by Rob Speer <rob@lumino.so>.
+# 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):
+#   Rob Speer - adapt to MacRoman encoding
+#   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 List, Union
+
+from .charsetprober import CharSetProber
+from .enums import ProbingState
+
+FREQ_CAT_NUM = 4
+
+UDF = 0  # undefined
+OTH = 1  # other
+ASC = 2  # ascii capital letter
+ASS = 3  # ascii small letter
+ACV = 4  # accent capital vowel
+ACO = 5  # accent capital other
+ASV = 6  # accent small vowel
+ASO = 7  # accent small other
+ODD = 8  # character that is unlikely to appear
+CLASS_NUM = 9  # total classes
+
+# The change from Latin1 is that we explicitly look for extended characters
+# that are infrequently-occurring symbols, and consider them to always be
+# improbable. This should let MacRoman get out of the way of more likely
+# encodings in most situations.
+
+# fmt: off
+MacRoman_CharToClass = (
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 00 - 07
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 08 - 0F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 10 - 17
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 18 - 1F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 20 - 27
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 28 - 2F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 30 - 37
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # 38 - 3F
+    OTH, ASC, ASC, ASC, ASC, ASC, ASC, ASC,  # 40 - 47
+    ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC,  # 48 - 4F
+    ASC, ASC, ASC, ASC, ASC, ASC, ASC, ASC,  # 50 - 57
+    ASC, ASC, ASC, OTH, OTH, OTH, OTH, OTH,  # 58 - 5F
+    OTH, ASS, ASS, ASS, ASS, ASS, ASS, ASS,  # 60 - 67
+    ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS,  # 68 - 6F
+    ASS, ASS, ASS, ASS, ASS, ASS, ASS, ASS,  # 70 - 77
+    ASS, ASS, ASS, OTH, OTH, OTH, OTH, OTH,  # 78 - 7F
+    ACV, ACV, ACO, ACV, ACO, ACV, ACV, ASV,  # 80 - 87
+    ASV, ASV, ASV, ASV, ASV, ASO, ASV, ASV,  # 88 - 8F
+    ASV, ASV, ASV, ASV, ASV, ASV, ASO, ASV,  # 90 - 97
+    ASV, ASV, ASV, ASV, ASV, ASV, ASV, ASV,  # 98 - 9F
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, ASO,  # A0 - A7
+    OTH, OTH, ODD, ODD, OTH, OTH, ACV, ACV,  # A8 - AF
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, OTH,  # B0 - B7
+    OTH, OTH, OTH, OTH, OTH, OTH, ASV, ASV,  # B8 - BF
+    OTH, OTH, ODD, OTH, ODD, OTH, OTH, OTH,  # C0 - C7
+    OTH, OTH, OTH, ACV, ACV, ACV, ACV, ASV,  # C8 - CF
+    OTH, OTH, OTH, OTH, OTH, OTH, OTH, ODD,  # D0 - D7
+    ASV, ACV, ODD, OTH, OTH, OTH, OTH, OTH,  # D8 - DF
+    OTH, OTH, OTH, OTH, OTH, ACV, ACV, ACV,  # E0 - E7
+    ACV, ACV, ACV, ACV, ACV, ACV, ACV, ACV,  # E8 - EF
+    ODD, ACV, ACV, ACV, ACV, ASV, ODD, ODD,  # F0 - F7
+    ODD, ODD, ODD, ODD, ODD, ODD, ODD, ODD,  # F8 - FF
+)
+
+# 0 : illegal
+# 1 : very unlikely
+# 2 : normal
+# 3 : very likely
+MacRomanClassModel = (
+# UDF OTH ASC ASS ACV ACO ASV ASO ODD
+    0,  0,  0,  0,  0,  0,  0,  0,  0,  # UDF
+    0,  3,  3,  3,  3,  3,  3,  3,  1,  # OTH
+    0,  3,  3,  3,  3,  3,  3,  3,  1,  # ASC
+    0,  3,  3,  3,  1,  1,  3,  3,  1,  # ASS
+    0,  3,  3,  3,  1,  2,  1,  2,  1,  # ACV
+    0,  3,  3,  3,  3,  3,  3,  3,  1,  # ACO
+    0,  3,  1,  3,  1,  1,  1,  3,  1,  # ASV
+    0,  3,  1,  3,  1,  1,  3,  3,  1,  # ASO
+    0,  1,  1,  1,  1,  1,  1,  1,  1,  # ODD
+)
+# fmt: on
+
+
+class MacRomanProber(CharSetProber):
+    def __init__(self) -> None:
+        super().__init__()
+        self._last_char_class = OTH
+        self._freq_counter: List[int] = []
+        self.reset()
+
+    def reset(self) -> None:
+        self._last_char_class = OTH
+        self._freq_counter = [0] * FREQ_CAT_NUM
+
+        # express the prior that MacRoman is a somewhat rare encoding;
+        # this can be done by starting out in a slightly improbable state
+        # that must be overcome
+        self._freq_counter[2] = 10
+
+        super().reset()
+
+    @property
+    def charset_name(self) -> str:
+        return "MacRoman"
+
+    @property
+    def language(self) -> str:
+        return ""
+
+    def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
+        byte_str = self.remove_xml_tags(byte_str)
+        for c in byte_str:
+            char_class = MacRoman_CharToClass[c]
+            freq = MacRomanClassModel[(self._last_char_class * CLASS_NUM) + char_class]
+            if freq == 0:
+                self._state = ProbingState.NOT_ME
+                break
+            self._freq_counter[freq] += 1
+            self._last_char_class = char_class
+
+        return self.state
+
+    def get_confidence(self) -> float:
+        if self.state == ProbingState.NOT_ME:
+            return 0.01
+
+        total = sum(self._freq_counter)
+        confidence = (
+            0.0
+            if total < 0.01
+            else (self._freq_counter[3] - self._freq_counter[1] * 20.0) / total
+        )
+        confidence = max(confidence, 0.0)
+        # lower the confidence of MacRoman so that other more accurate
+        # detector can take priority.
+        confidence *= 0.73
+        return confidence

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

@@ -0,0 +1,95 @@
+######################## 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
+#   Proofpoint, Inc.
+#
+# 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 Optional, Union
+
+from .chardistribution import CharDistributionAnalysis
+from .charsetprober import CharSetProber
+from .codingstatemachine import CodingStateMachine
+from .enums import LanguageFilter, MachineState, ProbingState
+
+
+class MultiByteCharSetProber(CharSetProber):
+    """
+    MultiByteCharSetProber
+    """
+
+    def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
+        super().__init__(lang_filter=lang_filter)
+        self.distribution_analyzer: Optional[CharDistributionAnalysis] = None
+        self.coding_sm: Optional[CodingStateMachine] = None
+        self._last_char = bytearray(b"\0\0")
+
+    def reset(self) -> None:
+        super().reset()
+        if self.coding_sm:
+            self.coding_sm.reset()
+        if self.distribution_analyzer:
+            self.distribution_analyzer.reset()
+        self._last_char = bytearray(b"\0\0")
+
+    def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
+        assert self.coding_sm is not None
+        assert self.distribution_analyzer is not None
+
+        for i, byte in enumerate(byte_str):
+            coding_state = self.coding_sm.next_state(byte)
+            if coding_state == MachineState.ERROR:
+                self.logger.debug(
+                    "%s %s prober hit error at byte %s",
+                    self.charset_name,
+                    self.language,
+                    i,
+                )
+                self._state = ProbingState.NOT_ME
+                break
+            if coding_state == MachineState.ITS_ME:
+                self._state = ProbingState.FOUND_IT
+                break
+            if coding_state == MachineState.START:
+                char_len = self.coding_sm.get_current_charlen()
+                if i == 0:
+                    self._last_char[1] = byte
+                    self.distribution_analyzer.feed(self._last_char, char_len)
+                else:
+                    self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len)
+
+        self._last_char[0] = byte_str[-1]
+
+        if self.state == ProbingState.DETECTING:
+            if self.distribution_analyzer.got_enough_data() and (
+                self.get_confidence() > self.SHORTCUT_THRESHOLD
+            ):
+                self._state = ProbingState.FOUND_IT
+
+        return self.state
+
+    def get_confidence(self) -> float:
+        assert self.distribution_analyzer is not None
+        return self.distribution_analyzer.get_confidence()

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

@@ -0,0 +1,57 @@
+######################## 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
+#   Proofpoint, Inc.
+#
+# 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 .big5prober import Big5Prober
+from .charsetgroupprober import CharSetGroupProber
+from .cp949prober import CP949Prober
+from .enums import LanguageFilter
+from .eucjpprober import EUCJPProber
+from .euckrprober import EUCKRProber
+from .euctwprober import EUCTWProber
+from .gb2312prober import GB2312Prober
+from .johabprober import JOHABProber
+from .sjisprober import SJISProber
+from .utf8prober import UTF8Prober
+
+
+class MBCSGroupProber(CharSetGroupProber):
+    def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
+        super().__init__(lang_filter=lang_filter)
+        self.probers = [
+            UTF8Prober(),
+            SJISProber(),
+            EUCJPProber(),
+            GB2312Prober(),
+            EUCKRProber(),
+            CP949Prober(),
+            Big5Prober(),
+            EUCTWProber(),
+            JOHABProber(),
+        ]
+        self.reset()