com.googler.python 1.0.7 → 1.0.9

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/chardet/charsetprober.py

@@ -0,0 +1,145 @@
+######################## 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 #########################
+
+import logging
+import re
+
+from .enums import ProbingState
+
+
+class CharSetProber(object):
+
+    SHORTCUT_THRESHOLD = 0.95
+
+    def __init__(self, lang_filter=None):
+        self._state = None
+        self.lang_filter = lang_filter
+        self.logger = logging.getLogger(__name__)
+
+    def reset(self):
+        self._state = ProbingState.DETECTING
+
+    @property
+    def charset_name(self):
+        return None
+
+    def feed(self, buf):
+        pass
+
+    @property
+    def state(self):
+        return self._state
+
+    def get_confidence(self):
+        return 0.0
+
+    @staticmethod
+    def filter_high_byte_only(buf):
+        buf = re.sub(b'([\x00-\x7F])+', b' ', buf)
+        return buf
+
+    @staticmethod
+    def filter_international_words(buf):
+        """
+        We define three types of bytes:
+        alphabet: english alphabets [a-zA-Z]
+        international: international characters [\x80-\xFF]
+        marker: everything else [^a-zA-Z\x80-\xFF]
+
+        The input buffer can be thought to contain a series of words delimited
+        by markers. This function works to filter all words that contain at
+        least one international character. All contiguous sequences of markers
+        are replaced by a single space ascii character.
+
+        This filter applies to all scripts which do not use English characters.
+        """
+        filtered = bytearray()
+
+        # This regex expression filters out only words that have at-least one
+        # international character. The word may include one marker character at
+        # the end.
+        words = re.findall(b'[a-zA-Z]*[\x80-\xFF]+[a-zA-Z]*[^a-zA-Z\x80-\xFF]?',
+                           buf)
+
+        for word in words:
+            filtered.extend(word[:-1])
+
+            # If the last character in the word is a marker, replace it with a
+            # space as markers shouldn't affect our analysis (they are used
+            # similarly across all languages and may thus have similar
+            # frequencies).
+            last_char = word[-1:]
+            if not last_char.isalpha() and last_char < b'\x80':
+                last_char = b' '
+            filtered.extend(last_char)
+
+        return filtered
+
+    @staticmethod
+    def filter_with_english_letters(buf):
+        """
+        Returns a copy of ``buf`` that retains only the sequences of English
+        alphabet and high byte characters that are not between <> characters.
+        Also retains English alphabet and high byte characters immediately
+        before occurrences of >.
+
+        This filter can be applied to all scripts which contain both English
+        characters and extended ASCII characters, but is currently only used by
+        ``Latin1Prober``.
+        """
+        filtered = bytearray()
+        in_tag = False
+        prev = 0
+
+        for curr in range(len(buf)):
+            # Slice here to get bytes instead of an int with Python 3
+            buf_char = buf[curr:curr + 1]
+            # Check if we're coming out of or entering an HTML tag
+            if buf_char == b'>':
+                in_tag = False
+            elif buf_char == b'<':
+                in_tag = True
+
+            # If current character is not extended-ASCII and not alphabetic...
+            if buf_char < b'\x80' and not buf_char.isalpha():
+                # ...and we're not in a tag
+                if curr > prev and not in_tag:
+                    # Keep everything after last non-extended-ASCII,
+                    # non-alphabetic character
+                    filtered.extend(buf[prev:curr])
+                    # Output a space to delimit stretch we kept
+                    filtered.extend(b' ')
+                prev = curr + 1
+
+        # If we're not in a tag...
+        if not in_tag:
+            # Keep everything after last non-extended-ASCII, non-alphabetic
+            # character
+            filtered.extend(buf[prev:])
+
+        return filtered

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/chardet/cli/__init__.py

@@ -0,0 +1 @@
+

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/chardet/cli/chardetect.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python
+"""
+Script which takes one or more file paths and reports on their detected
+encodings
+
+Example::
+
+    % chardetect somefile someotherfile
+    somefile: windows-1252 with confidence 0.5
+    someotherfile: ascii with confidence 1.0
+
+If no paths are provided, it takes its input from stdin.
+
+"""
+
+from __future__ import absolute_import, print_function, unicode_literals
+
+import argparse
+import sys
+
+from pip._vendor.chardet import __version__
+from pip._vendor.chardet.compat import PY2
+from pip._vendor.chardet.universaldetector import UniversalDetector
+
+
+def description_of(lines, name='stdin'):
+    """
+    Return a string describing the probable encoding of a file or
+    list of strings.
+
+    :param lines: The lines to get the encoding of.
+    :type lines: Iterable of bytes
+    :param name: Name of file or collection of lines
+    :type name: str
+    """
+    u = UniversalDetector()
+    for line in lines:
+        line = bytearray(line)
+        u.feed(line)
+        # shortcut out of the loop to save reading further - particularly useful if we read a BOM.
+        if u.done:
+            break
+    u.close()
+    result = u.result
+    if PY2:
+        name = name.decode(sys.getfilesystemencoding(), 'ignore')
+    if result['encoding']:
+        return '{0}: {1} with confidence {2}'.format(name, result['encoding'],
+                                                     result['confidence'])
+    else:
+        return '{0}: no result'.format(name)
+
+
+def main(argv=None):
+    """
+    Handles command line arguments and gets things started.
+
+    :param argv: List of arguments, as if specified on the command-line.
+                 If None, ``sys.argv[1:]`` is used instead.
+    :type argv: list of str
+    """
+    # Get command line arguments
+    parser = argparse.ArgumentParser(
+        description="Takes one or more file paths and reports their detected \
+                     encodings")
+    parser.add_argument('input',
+                        help='File whose encoding we would like to determine. \
+                              (default: stdin)',
+                        type=argparse.FileType('rb'), nargs='*',
+                        default=[sys.stdin if PY2 else sys.stdin.buffer])
+    parser.add_argument('--version', action='version',
+                        version='%(prog)s {0}'.format(__version__))
+    args = parser.parse_args(argv)
+
+    for f in args.input:
+        if f.isatty():
+            print("You are running chardetect interactively. Press " +
+                  "CTRL-D twice at the start of a blank line to signal the " +
+                  "end of your input. If you want help, run chardetect " +
+                  "--help\n", file=sys.stderr)
+        print(description_of(f, f.name))
+
+
+if __name__ == '__main__':
+    main()

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/chardet/codingstatemachine.py

@@ -0,0 +1,88 @@
+######################## 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 #########################
+
+import logging
+
+from .enums import MachineState
+
+
+class CodingStateMachine(object):
+    """
+    A state machine to verify a byte sequence for a particular encoding. For
+    each byte the detector receives, it will feed that byte to every active
+    state machine available, one byte at a time. The state machine changes its
+    state based on its previous state and the byte it receives. There are 3
+    states in a state machine that are of interest to an auto-detector:
+
+    START state: This is the state to start with, or a legal byte sequence
+                 (i.e. a valid code point) for character has been identified.
+
+    ME state:  This indicates that the state machine identified a byte sequence
+               that is specific to the charset it is designed for and that
+               there is no other possible encoding which can contain this byte
+               sequence. This will to lead to an immediate positive answer for
+               the detector.
+
+    ERROR state: This indicates the state machine identified an illegal byte
+                 sequence for that encoding. This will lead to an immediate
+                 negative answer for this encoding. Detector will exclude this
+                 encoding from consideration from here on.
+    """
+    def __init__(self, sm):
+        self._model = sm
+        self._curr_byte_pos = 0
+        self._curr_char_len = 0
+        self._curr_state = None
+        self.logger = logging.getLogger(__name__)
+        self.reset()
+
+    def reset(self):
+        self._curr_state = MachineState.START
+
+    def next_state(self, c):
+        # for each byte we get its class
+        # if it is first byte, we also get byte length
+        byte_class = self._model['class_table'][c]
+        if self._curr_state == MachineState.START:
+            self._curr_byte_pos = 0
+            self._curr_char_len = self._model['char_len_table'][byte_class]
+        # from byte's class and state_table, we get its next state
+        curr_state = (self._curr_state * self._model['class_factor']
+                      + byte_class)
+        self._curr_state = self._model['state_table'][curr_state]
+        self._curr_byte_pos += 1
+        return self._curr_state
+
+    def get_current_charlen(self):
+        return self._curr_char_len
+
+    def get_coding_state_machine(self):
+        return self._model['name']
+
+    @property
+    def language(self):
+        return self._model['language']

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/{requests/packages/chardet → chardet}/compat.py

@@ -1,34 +1,34 @@
-######################## BEGIN LICENSE BLOCK ########################
-# Contributor(s):
-#   Ian Cordasco - 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 #########################
-
-import sys
-
-
-if sys.version_info < (3, 0):
-    base_str = (str, unicode)
-else:
-    base_str = (bytes, str)
-
-
-def wrap_ord(a):
-    if sys.version_info < (3, 0) and isinstance(a, base_str):
-        return ord(a)
-    else:
-        return a
+######################## BEGIN LICENSE BLOCK ########################
+# Contributor(s):
+#   Dan Blanchard
+#   Ian Cordasco
+#
+# 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 #########################
+
+import sys
+
+
+if sys.version_info < (3, 0):
+    PY2 = True
+    PY3 = False
+    base_str = (str, unicode)
+    text_type = unicode
+else:
+    PY2 = False
+    PY3 = True
+    base_str = (bytes, str)
+    text_type = str

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/{requests/packages/chardet → chardet}/cp949prober.py

@@ -1,44 +1,49 @@
-######################## 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 EUCKRDistributionAnalysis
-from .mbcssm import CP949SMModel
-
-
-class CP949Prober(MultiByteCharSetProber):
-    def __init__(self):
-        MultiByteCharSetProber.__init__(self)
-        self._mCodingSM = CodingStateMachine(CP949SMModel)
-        # NOTE: CP949 is a superset of EUC-KR, so the distribution should be
-        #       not different.
-        self._mDistributionAnalyzer = EUCKRDistributionAnalysis()
-        self.reset()
-
-    def get_charset_name(self):
-        return "CP949"
+######################## 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 .chardistribution import EUCKRDistributionAnalysis
+from .codingstatemachine import CodingStateMachine
+from .mbcharsetprober import MultiByteCharSetProber
+from .mbcssm import CP949_SM_MODEL
+
+
+class CP949Prober(MultiByteCharSetProber):
+    def __init__(self):
+        super(CP949Prober, self).__init__()
+        self.coding_sm = CodingStateMachine(CP949_SM_MODEL)
+        # NOTE: CP949 is a superset of EUC-KR, so the distribution should be
+        #       not different.
+        self.distribution_analyzer = EUCKRDistributionAnalysis()
+        self.reset()
+
+    @property
+    def charset_name(self):
+        return "CP949"
+
+    @property
+    def language(self):
+        return "Korean"

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/chardet/enums.py

@@ -0,0 +1,76 @@
+"""
+All of the Enums that are used throughout the chardet package.
+
+:author: Dan Blanchard (dan.blanchard@gmail.com)
+"""
+
+
+class InputState(object):
+    """
+    This enum represents the different states a universal detector can be in.
+    """
+    PURE_ASCII = 0
+    ESC_ASCII = 1
+    HIGH_BYTE = 2
+
+
+class LanguageFilter(object):
+    """
+    This enum represents the different language filters we can apply to a
+    ``UniversalDetector``.
+    """
+    CHINESE_SIMPLIFIED = 0x01
+    CHINESE_TRADITIONAL = 0x02
+    JAPANESE = 0x04
+    KOREAN = 0x08
+    NON_CJK = 0x10
+    ALL = 0x1F
+    CHINESE = CHINESE_SIMPLIFIED | CHINESE_TRADITIONAL
+    CJK = CHINESE | JAPANESE | KOREAN
+
+
+class ProbingState(object):
+    """
+    This enum represents the different states a prober can be in.
+    """
+    DETECTING = 0
+    FOUND_IT = 1
+    NOT_ME = 2
+
+
+class MachineState(object):
+    """
+    This enum represents the different states a state machine can be in.
+    """
+    START = 0
+    ERROR = 1
+    ITS_ME = 2
+
+
+class SequenceLikelihood(object):
+    """
+    This enum represents the likelihood of a character following the previous one.
+    """
+    NEGATIVE = 0
+    UNLIKELY = 1
+    LIKELY = 2
+    POSITIVE = 3
+
+    @classmethod
+    def get_num_categories(cls):
+        """:returns: The number of likelihood categories in the enum."""
+        return 4
+
+
+class CharacterCategory(object):
+    """
+    This enum represents the different categories language models for
+    ``SingleByteCharsetProber`` put characters into.
+
+    Anything less than CONTROL is considered a letter.
+    """
+    UNDEFINED = 255
+    LINE_BREAK = 254
+    SYMBOL = 253
+    DIGIT = 252
+    CONTROL = 251

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/chardet/escprober.py

@@ -0,0 +1,101 @@
+######################## 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 .codingstatemachine import CodingStateMachine
+from .enums import LanguageFilter, ProbingState, MachineState
+from .escsm import (HZ_SM_MODEL, ISO2022CN_SM_MODEL, ISO2022JP_SM_MODEL,
+                    ISO2022KR_SM_MODEL)
+
+
+class EscCharSetProber(CharSetProber):
+    """
+    This CharSetProber uses a "code scheme" approach for detecting encodings,
+    whereby easily recognizable escape or shift sequences are relied on to
+    identify these encodings.
+    """
+
+    def __init__(self, lang_filter=None):
+        super(EscCharSetProber, self).__init__(lang_filter=lang_filter)
+        self.coding_sm = []
+        if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED:
+            self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL))
+            self.coding_sm.append(CodingStateMachine(ISO2022CN_SM_MODEL))
+        if self.lang_filter & LanguageFilter.JAPANESE:
+            self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL))
+        if self.lang_filter & LanguageFilter.KOREAN:
+            self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL))
+        self.active_sm_count = None
+        self._detected_charset = None
+        self._detected_language = None
+        self._state = None
+        self.reset()
+
+    def reset(self):
+        super(EscCharSetProber, self).reset()
+        for coding_sm in self.coding_sm:
+            if not coding_sm:
+                continue
+            coding_sm.active = True
+            coding_sm.reset()
+        self.active_sm_count = len(self.coding_sm)
+        self._detected_charset = None
+        self._detected_language = None
+
+    @property
+    def charset_name(self):
+        return self._detected_charset
+
+    @property
+    def language(self):
+        return self._detected_language
+
+    def get_confidence(self):
+        if self._detected_charset:
+            return 0.99
+        else:
+            return 0.00
+
+    def feed(self, byte_str):
+        for c in byte_str:
+            for coding_sm in self.coding_sm:
+                if not coding_sm or not coding_sm.active:
+                    continue
+                coding_state = coding_sm.next_state(c)
+                if coding_state == MachineState.ERROR:
+                    coding_sm.active = False
+                    self.active_sm_count -= 1
+                    if self.active_sm_count <= 0:
+                        self._state = ProbingState.NOT_ME
+                        return self.state
+                elif coding_state == MachineState.ITS_ME:
+                    self._state = ProbingState.FOUND_IT
+                    self._detected_charset = coding_sm.get_coding_state_machine()
+                    self._detected_language = coding_sm.language
+                    return self.state
+
+        return self.state