quarchpy 2.1.13.dev1__py2.py3-none-any.whl → 2.1.14__py2.py3-none-any.whl

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

@@ -0,0 +1,132 @@
+######################## 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 .charsetprober import CharSetProber
+from .enums import CharacterCategory, ProbingState, SequenceLikelihood
+
+
+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, reversed=False, name_prober=None):
+        super(SingleByteCharSetProber, self).__init__()
+        self._model = model
+        # TRUE if we need to reverse every pair in the model lookup
+        self._reversed = reversed
+        # Optional auxiliary prober for name decision
+        self._name_prober = name_prober
+        self._last_order = None
+        self._seq_counters = None
+        self._total_seqs = None
+        self._total_char = None
+        self._freq_char = None
+        self.reset()
+
+    def reset(self):
+        super(SingleByteCharSetProber, self).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
+        # characters that fall in our sampling range
+        self._freq_char = 0
+
+    @property
+    def charset_name(self):
+        if self._name_prober:
+            return self._name_prober.charset_name
+        else:
+            return self._model['charset_name']
+
+    @property
+    def language(self):
+        if self._name_prober:
+            return self._name_prober.language
+        else:
+            return self._model.get('language')
+
+    def feed(self, byte_str):
+        if not self._model['keep_english_letter']:
+            byte_str = self.filter_international_words(byte_str)
+        if not byte_str:
+            return self.state
+        char_to_order_map = self._model['char_to_order_map']
+        for i, c in enumerate(byte_str):
+            # XXX: Order is in range 1-64, so one would think we want 0-63 here,
+            #      but that leads to 27 more test failures than before.
+            order = char_to_order_map[c]
+            # 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:
+                        i = (self._last_order * self.SAMPLE_SIZE) + order
+                        model = self._model['precedence_matrix'][i]
+                    else:  # reverse the order of the letters in the lookup
+                        i = (order * self.SAMPLE_SIZE) + self._last_order
+                        model = self._model['precedence_matrix'][i]
+                    self._seq_counters[model] += 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 threshhold %s', charset_name,
+                                      confidence,
+                                      self.NEGATIVE_SHORTCUT_THRESHOLD)
+                    self._state = ProbingState.NOT_ME
+
+        return self.state
+
+    def get_confidence(self):
+        r = 0.01
+        if self._total_seqs > 0:
+            r = ((1.0 * self._seq_counters[SequenceLikelihood.POSITIVE]) /
+                 self._total_seqs / self._model['typical_positive_ratio'])
+            r = r * self._freq_char / self._total_char
+            if r >= 1.0:
+                r = 0.99
+        return r

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

@@ -0,0 +1,73 @@
+######################## 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 .sbcharsetprober import SingleByteCharSetProber
+from .langcyrillicmodel import (Win1251CyrillicModel, Koi8rModel,
+                                Latin5CyrillicModel, MacCyrillicModel,
+                                Ibm866Model, Ibm855Model)
+from .langgreekmodel import Latin7GreekModel, Win1253GreekModel
+from .langbulgarianmodel import Latin5BulgarianModel, Win1251BulgarianModel
+# from .langhungarianmodel import Latin2HungarianModel, Win1250HungarianModel
+from .langthaimodel import TIS620ThaiModel
+from .langhebrewmodel import Win1255HebrewModel
+from .hebrewprober import HebrewProber
+from .langturkishmodel import Latin5TurkishModel
+
+
+class SBCSGroupProber(CharSetGroupProber):
+    def __init__(self):
+        super(SBCSGroupProber, self).__init__()
+        self.probers = [
+            SingleByteCharSetProber(Win1251CyrillicModel),
+            SingleByteCharSetProber(Koi8rModel),
+            SingleByteCharSetProber(Latin5CyrillicModel),
+            SingleByteCharSetProber(MacCyrillicModel),
+            SingleByteCharSetProber(Ibm866Model),
+            SingleByteCharSetProber(Ibm855Model),
+            SingleByteCharSetProber(Latin7GreekModel),
+            SingleByteCharSetProber(Win1253GreekModel),
+            SingleByteCharSetProber(Latin5BulgarianModel),
+            SingleByteCharSetProber(Win1251BulgarianModel),
+            # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250)
+            #       after we retrain model.
+            # SingleByteCharSetProber(Latin2HungarianModel),
+            # SingleByteCharSetProber(Win1250HungarianModel),
+            SingleByteCharSetProber(TIS620ThaiModel),
+            SingleByteCharSetProber(Latin5TurkishModel),
+        ]
+        hebrew_prober = HebrewProber()
+        logical_hebrew_prober = SingleByteCharSetProber(Win1255HebrewModel,
+                                                        False, hebrew_prober)
+        visual_hebrew_prober = SingleByteCharSetProber(Win1255HebrewModel, True,
+                                                       hebrew_prober)
+        hebrew_prober.set_model_probers(logical_hebrew_prober, visual_hebrew_prober)
+        self.probers.extend([hebrew_prober, logical_hebrew_prober,
+                             visual_hebrew_prober])
+
+        self.reset()

quarchpy/venv/Lib/site-packages/pip/_vendor/chardet/sjisprober.py

@@ -0,0 +1,92 @@
+######################## BEGIN LICENSE BLOCK ########################
+# The Original Code is mozilla.org code.
+#
+# The Initial Developer of the Original Code is
+# Netscape Communications Corporation.
+# Portions created by the Initial Developer are Copyright (C) 1998
+# the Initial Developer. All Rights Reserved.
+#
+# Contributor(s):
+#   Mark Pilgrim - port to Python
+#
+# 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 .mbcharsetprober import MultiByteCharSetProber
+from .codingstatemachine import CodingStateMachine
+from .chardistribution import SJISDistributionAnalysis
+from .jpcntx import SJISContextAnalysis
+from .mbcssm import SJIS_SM_MODEL
+from .enums import ProbingState, MachineState
+
+
+class SJISProber(MultiByteCharSetProber):
+    def __init__(self):
+        super(SJISProber, self).__init__()
+        self.coding_sm = CodingStateMachine(SJIS_SM_MODEL)
+        self.distribution_analyzer = SJISDistributionAnalysis()
+        self.context_analyzer = SJISContextAnalysis()
+        self.reset()
+
+    def reset(self):
+        super(SJISProber, self).reset()
+        self.context_analyzer.reset()
+
+    @property
+    def charset_name(self):
+        return self.context_analyzer.charset_name
+
+    @property
+    def language(self):
+        return "Japanese"
+
+    def feed(self, byte_str):
+        for i in range(len(byte_str)):
+            coding_state = self.coding_sm.next_state(byte_str[i])
+            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
+            elif coding_state == MachineState.ITS_ME:
+                self._state = ProbingState.FOUND_IT
+                break
+            elif coding_state == MachineState.START:
+                char_len = self.coding_sm.get_current_charlen()
+                if i == 0:
+                    self._last_char[1] = byte_str[0]
+                    self.context_analyzer.feed(self._last_char[2 - char_len:],
+                                               char_len)
+                    self.distribution_analyzer.feed(self._last_char, char_len)
+                else:
+                    self.context_analyzer.feed(byte_str[i + 1 - char_len:i + 3
+                                                        - char_len], char_len)
+                    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.context_analyzer.got_enough_data() and
+               (self.get_confidence() > self.SHORTCUT_THRESHOLD)):
+                self._state = ProbingState.FOUND_IT
+
+        return self.state
+
+    def get_confidence(self):
+        context_conf = self.context_analyzer.get_confidence()
+        distrib_conf = self.distribution_analyzer.get_confidence()
+        return max(context_conf, distrib_conf)

quarchpy/venv/Lib/site-packages/pip/_vendor/chardet/universaldetector.py

@@ -0,0 +1,286 @@
+######################## 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 #########################
+"""
+Module containing the UniversalDetector detector class, which is the primary
+class a user of ``chardet`` should use.
+
+:author: Mark Pilgrim (initial port to Python)
+:author: Shy Shalom (original C code)
+:author: Dan Blanchard (major refactoring for 3.0)
+:author: Ian Cordasco
+"""
+
+
+import codecs
+import logging
+import re
+
+from .charsetgroupprober import CharSetGroupProber
+from .enums import InputState, LanguageFilter, ProbingState
+from .escprober import EscCharSetProber
+from .latin1prober import Latin1Prober
+from .mbcsgroupprober import MBCSGroupProber
+from .sbcsgroupprober import SBCSGroupProber
+
+
+class UniversalDetector(object):
+    """
+    The ``UniversalDetector`` class underlies the ``chardet.detect`` function
+    and coordinates all of the different charset probers.
+
+    To get a ``dict`` containing an encoding and its confidence, you can simply
+    run:
+
+    .. code::
+
+            u = UniversalDetector()
+            u.feed(some_bytes)
+            u.close()
+            detected = u.result
+
+    """
+
+    MINIMUM_THRESHOLD = 0.20
+    HIGH_BYTE_DETECTOR = re.compile(b'[\x80-\xFF]')
+    ESC_DETECTOR = re.compile(b'(\033|~{)')
+    WIN_BYTE_DETECTOR = re.compile(b'[\x80-\x9F]')
+    ISO_WIN_MAP = {'iso-8859-1': 'Windows-1252',
+                   'iso-8859-2': 'Windows-1250',
+                   'iso-8859-5': 'Windows-1251',
+                   'iso-8859-6': 'Windows-1256',
+                   'iso-8859-7': 'Windows-1253',
+                   'iso-8859-8': 'Windows-1255',
+                   'iso-8859-9': 'Windows-1254',
+                   'iso-8859-13': 'Windows-1257'}
+
+    def __init__(self, lang_filter=LanguageFilter.ALL):
+        self._esc_charset_prober = None
+        self._charset_probers = []
+        self.result = None
+        self.done = None
+        self._got_data = None
+        self._input_state = None
+        self._last_char = None
+        self.lang_filter = lang_filter
+        self.logger = logging.getLogger(__name__)
+        self._has_win_bytes = None
+        self.reset()
+
+    def reset(self):
+        """
+        Reset the UniversalDetector and all of its probers back to their
+        initial states.  This is called by ``__init__``, so you only need to
+        call this directly in between analyses of different documents.
+        """
+        self.result = {'encoding': None, 'confidence': 0.0, 'language': None}
+        self.done = False
+        self._got_data = False
+        self._has_win_bytes = False
+        self._input_state = InputState.PURE_ASCII
+        self._last_char = b''
+        if self._esc_charset_prober:
+            self._esc_charset_prober.reset()
+        for prober in self._charset_probers:
+            prober.reset()
+
+    def feed(self, byte_str):
+        """
+        Takes a chunk of a document and feeds it through all of the relevant
+        charset probers.
+
+        After calling ``feed``, you can check the value of the ``done``
+        attribute to see if you need to continue feeding the
+        ``UniversalDetector`` more data, or if it has made a prediction
+        (in the ``result`` attribute).
+
+        .. note::
+           You should always call ``close`` when you're done feeding in your
+           document if ``done`` is not already ``True``.
+        """
+        if self.done:
+            return
+
+        if not len(byte_str):
+            return
+
+        if not isinstance(byte_str, bytearray):
+            byte_str = bytearray(byte_str)
+
+        # First check for known BOMs, since these are guaranteed to be correct
+        if not self._got_data:
+            # If the data starts with BOM, we know it is UTF
+            if byte_str.startswith(codecs.BOM_UTF8):
+                # EF BB BF  UTF-8 with BOM
+                self.result = {'encoding': "UTF-8-SIG",
+                               'confidence': 1.0,
+                               'language': ''}
+            elif byte_str.startswith((codecs.BOM_UTF32_LE,
+                                      codecs.BOM_UTF32_BE)):
+                # FF FE 00 00  UTF-32, little-endian BOM
+                # 00 00 FE FF  UTF-32, big-endian BOM
+                self.result = {'encoding': "UTF-32",
+                               'confidence': 1.0,
+                               'language': ''}
+            elif byte_str.startswith(b'\xFE\xFF\x00\x00'):
+                # FE FF 00 00  UCS-4, unusual octet order BOM (3412)
+                self.result = {'encoding': "X-ISO-10646-UCS-4-3412",
+                               'confidence': 1.0,
+                               'language': ''}
+            elif byte_str.startswith(b'\x00\x00\xFF\xFE'):
+                # 00 00 FF FE  UCS-4, unusual octet order BOM (2143)
+                self.result = {'encoding': "X-ISO-10646-UCS-4-2143",
+                               'confidence': 1.0,
+                               'language': ''}
+            elif byte_str.startswith((codecs.BOM_LE, codecs.BOM_BE)):
+                # FF FE  UTF-16, little endian BOM
+                # FE FF  UTF-16, big endian BOM
+                self.result = {'encoding': "UTF-16",
+                               'confidence': 1.0,
+                               'language': ''}
+
+            self._got_data = True
+            if self.result['encoding'] is not None:
+                self.done = True
+                return
+
+        # If none of those matched and we've only see ASCII so far, check
+        # for high bytes and escape sequences
+        if self._input_state == InputState.PURE_ASCII:
+            if self.HIGH_BYTE_DETECTOR.search(byte_str):
+                self._input_state = InputState.HIGH_BYTE
+            elif self._input_state == InputState.PURE_ASCII and \
+                    self.ESC_DETECTOR.search(self._last_char + byte_str):
+                self._input_state = InputState.ESC_ASCII
+
+        self._last_char = byte_str[-1:]
+
+        # If we've seen escape sequences, use the EscCharSetProber, which
+        # uses a simple state machine to check for known escape sequences in
+        # HZ and ISO-2022 encodings, since those are the only encodings that
+        # use such sequences.
+        if self._input_state == InputState.ESC_ASCII:
+            if not self._esc_charset_prober:
+                self._esc_charset_prober = EscCharSetProber(self.lang_filter)
+            if self._esc_charset_prober.feed(byte_str) == ProbingState.FOUND_IT:
+                self.result = {'encoding':
+                               self._esc_charset_prober.charset_name,
+                               'confidence':
+                               self._esc_charset_prober.get_confidence(),
+                               'language':
+                               self._esc_charset_prober.language}
+                self.done = True
+        # If we've seen high bytes (i.e., those with values greater than 127),
+        # we need to do more complicated checks using all our multi-byte and
+        # single-byte probers that are left.  The single-byte probers
+        # use character bigram distributions to determine the encoding, whereas
+        # the multi-byte probers use a combination of character unigram and
+        # bigram distributions.
+        elif self._input_state == InputState.HIGH_BYTE:
+            if not self._charset_probers:
+                self._charset_probers = [MBCSGroupProber(self.lang_filter)]
+                # If we're checking non-CJK encodings, use single-byte prober
+                if self.lang_filter & LanguageFilter.NON_CJK:
+                    self._charset_probers.append(SBCSGroupProber())
+                self._charset_probers.append(Latin1Prober())
+            for prober in self._charset_probers:
+                if prober.feed(byte_str) == ProbingState.FOUND_IT:
+                    self.result = {'encoding': prober.charset_name,
+                                   'confidence': prober.get_confidence(),
+                                   'language': prober.language}
+                    self.done = True
+                    break
+            if self.WIN_BYTE_DETECTOR.search(byte_str):
+                self._has_win_bytes = True
+
+    def close(self):
+        """
+        Stop analyzing the current document and come up with a final
+        prediction.
+
+        :returns:  The ``result`` attribute, a ``dict`` with the keys
+                   `encoding`, `confidence`, and `language`.
+        """
+        # Don't bother with checks if we're already done
+        if self.done:
+            return self.result
+        self.done = True
+
+        if not self._got_data:
+            self.logger.debug('no data received!')
+
+        # Default to ASCII if it is all we've seen so far
+        elif self._input_state == InputState.PURE_ASCII:
+            self.result = {'encoding': 'ascii',
+                           'confidence': 1.0,
+                           'language': ''}
+
+        # If we have seen non-ASCII, return the best that met MINIMUM_THRESHOLD
+        elif self._input_state == InputState.HIGH_BYTE:
+            prober_confidence = None
+            max_prober_confidence = 0.0
+            max_prober = None
+            for prober in self._charset_probers:
+                if not prober:
+                    continue
+                prober_confidence = prober.get_confidence()
+                if prober_confidence > max_prober_confidence:
+                    max_prober_confidence = prober_confidence
+                    max_prober = prober
+            if max_prober and (max_prober_confidence > self.MINIMUM_THRESHOLD):
+                charset_name = max_prober.charset_name
+                lower_charset_name = max_prober.charset_name.lower()
+                confidence = max_prober.get_confidence()
+                # Use Windows encoding name instead of ISO-8859 if we saw any
+                # extra Windows-specific bytes
+                if lower_charset_name.startswith('iso-8859'):
+                    if self._has_win_bytes:
+                        charset_name = self.ISO_WIN_MAP.get(lower_charset_name,
+                                                            charset_name)
+                self.result = {'encoding': charset_name,
+                               'confidence': confidence,
+                               'language': max_prober.language}
+
+        # Log all prober confidences if none met MINIMUM_THRESHOLD
+        if self.logger.getEffectiveLevel() == logging.DEBUG:
+            if self.result['encoding'] is None:
+                self.logger.debug('no probers hit minimum threshold')
+                for group_prober in self._charset_probers:
+                    if not group_prober:
+                        continue
+                    if isinstance(group_prober, CharSetGroupProber):
+                        for prober in group_prober.probers:
+                            self.logger.debug('%s %s confidence = %s',
+                                              prober.charset_name,
+                                              prober.language,
+                                              prober.get_confidence())
+                    else:
+                        self.logger.debug('%s %s confidence = %s',
+                                          prober.charset_name,
+                                          prober.language,
+                                          prober.get_confidence())
+        return self.result

quarchpy/venv/Lib/site-packages/pip/_vendor/chardet/utf8prober.py

@@ -0,0 +1,82 @@
+######################## BEGIN LICENSE BLOCK ########################
+# The Original Code is mozilla.org code.
+#
+# The Initial Developer of the Original Code is
+# Netscape Communications Corporation.
+# Portions created by the Initial Developer are Copyright (C) 1998
+# the Initial Developer. All Rights Reserved.
+#
+# Contributor(s):
+#   Mark Pilgrim - port to Python
+#
+# 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 .charsetprober import CharSetProber
+from .enums import ProbingState, MachineState
+from .codingstatemachine import CodingStateMachine
+from .mbcssm import UTF8_SM_MODEL
+
+
+
+class UTF8Prober(CharSetProber):
+    ONE_CHAR_PROB = 0.5
+
+    def __init__(self):
+        super(UTF8Prober, self).__init__()
+        self.coding_sm = CodingStateMachine(UTF8_SM_MODEL)
+        self._num_mb_chars = None
+        self.reset()
+
+    def reset(self):
+        super(UTF8Prober, self).reset()
+        self.coding_sm.reset()
+        self._num_mb_chars = 0
+
+    @property
+    def charset_name(self):
+        return "utf-8"
+
+    @property
+    def language(self):
+        return ""
+
+    def feed(self, byte_str):
+        for c in byte_str:
+            coding_state = self.coding_sm.next_state(c)
+            if coding_state == MachineState.ERROR:
+                self._state = ProbingState.NOT_ME
+                break
+            elif coding_state == MachineState.ITS_ME:
+                self._state = ProbingState.FOUND_IT
+                break
+            elif coding_state == MachineState.START:
+                if self.coding_sm.get_current_charlen() >= 2:
+                    self._num_mb_chars += 1
+
+        if self.state == ProbingState.DETECTING:
+            if self.get_confidence() > self.SHORTCUT_THRESHOLD:
+                self._state = ProbingState.FOUND_IT
+
+        return self.state
+
+    def get_confidence(self):
+        unlike = 0.99
+        if self._num_mb_chars < 6:
+            unlike *= self.ONE_CHAR_PROB ** self._num_mb_chars
+            return 1.0 - unlike
+        else:
+            return unlike

quarchpy/venv/Lib/site-packages/pip/_vendor/chardet/version.py

@@ -0,0 +1,9 @@
+"""
+This module exists only to simplify retrieving the version number of chardet
+from within setup.py and from chardet subpackages.
+
+:author: Dan Blanchard (dan.blanchard@gmail.com)
+"""
+
+__version__ = "3.0.4"
+VERSION = __version__.split('.')

quarchpy/venv/Lib/site-packages/pip/_vendor/colorama/__init__.py

@@ -0,0 +1,6 @@
+# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
+from .initialise import init, deinit, reinit, colorama_text
+from .ansi import Fore, Back, Style, Cursor
+from .ansitowin32 import AnsiToWin32
+
+__version__ = '0.4.4'