com.googler.python 1.0.8 → 1.1.0

package/python3.4.2/lib/python3.4/site-packages/pip/_vendor/{requests/packages/chardet → chardet}/latin1prober.py

@@ -1,139 +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 #########################
-
-from .charsetprober import CharSetProber
-from .constants import eNotMe
-from .compat import wrap_ord
-
-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
-
-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
-)
-
-
-class Latin1Prober(CharSetProber):
-    def __init__(self):
-        CharSetProber.__init__(self)
-        self.reset()
-
-    def reset(self):
-        self._mLastCharClass = OTH
-        self._mFreqCounter = [0] * FREQ_CAT_NUM
-        CharSetProber.reset(self)
-
-    def get_charset_name(self):
-        return "windows-1252"
-
-    def feed(self, aBuf):
-        aBuf = self.filter_with_english_letters(aBuf)
-        for c in aBuf:
-            charClass = Latin1_CharToClass[wrap_ord(c)]
-            freq = Latin1ClassModel[(self._mLastCharClass * CLASS_NUM)
-                                    + charClass]
-            if freq == 0:
-                self._mState = eNotMe
-                break
-            self._mFreqCounter[freq] += 1
-            self._mLastCharClass = charClass
-
-        return self.get_state()
-
-    def get_confidence(self):
-        if self.get_state() == eNotMe:
-            return 0.01
-
-        total = sum(self._mFreqCounter)
-        if total < 0.01:
-            confidence = 0.0
-        else:
-            confidence = ((self._mFreqCounter[3] / total)
-                          - (self._mFreqCounter[1] * 20.0 / total))
-        if confidence < 0.0:
-            confidence = 0.0
-        # lower the confidence of latin1 so that other more accurate
-        # detector can take priority.
-        confidence = confidence * 0.5
-        return confidence
+######################## 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 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
+
+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
+)
+
+
+class Latin1Prober(CharSetProber):
+    def __init__(self):
+        super(Latin1Prober, self).__init__()
+        self._last_char_class = None
+        self._freq_counter = None
+        self.reset()
+
+    def reset(self):
+        self._last_char_class = OTH
+        self._freq_counter = [0] * FREQ_CAT_NUM
+        CharSetProber.reset(self)
+
+    @property
+    def charset_name(self):
+        return "ISO-8859-1"
+
+    @property
+    def language(self):
+        return ""
+
+    def feed(self, byte_str):
+        byte_str = self.filter_with_english_letters(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):
+        if self.state == ProbingState.NOT_ME:
+            return 0.01
+
+        total = sum(self._freq_counter)
+        if total < 0.01:
+            confidence = 0.0
+        else:
+            confidence = ((self._freq_counter[3] - self._freq_counter[1] * 20.0)
+                          / total)
+        if confidence < 0.0:
+            confidence = 0.0
+        # lower the confidence of latin1 so that other more accurate
+        # detector can take priority.
+        confidence = confidence * 0.73
+        return confidence

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

@@ -0,0 +1,91 @@
+######################## 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 .charsetprober import CharSetProber
+from .enums import ProbingState, MachineState
+
+
+class MultiByteCharSetProber(CharSetProber):
+    """
+    MultiByteCharSetProber
+    """
+
+    def __init__(self, lang_filter=None):
+        super(MultiByteCharSetProber, self).__init__(lang_filter=lang_filter)
+        self.distribution_analyzer = None
+        self.coding_sm = None
+        self._last_char = [0, 0]
+
+    def reset(self):
+        super(MultiByteCharSetProber, self).reset()
+        if self.coding_sm:
+            self.coding_sm.reset()
+        if self.distribution_analyzer:
+            self.distribution_analyzer.reset()
+        self._last_char = [0, 0]
+
+    @property
+    def charset_name(self):
+        raise NotImplementedError
+
+    @property
+    def language(self):
+        raise NotImplementedError
+
+    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.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):
+        return self.distribution_analyzer.get_confidence()

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

@@ -1,54 +1,54 @@
-######################## 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 .charsetgroupprober import CharSetGroupProber
-from .utf8prober import UTF8Prober
-from .sjisprober import SJISProber
-from .eucjpprober import EUCJPProber
-from .gb2312prober import GB2312Prober
-from .euckrprober import EUCKRProber
-from .cp949prober import CP949Prober
-from .big5prober import Big5Prober
-from .euctwprober import EUCTWProber
-
-
-class MBCSGroupProber(CharSetGroupProber):
-    def __init__(self):
-        CharSetGroupProber.__init__(self)
-        self._mProbers = [
-            UTF8Prober(),
-            SJISProber(),
-            EUCJPProber(),
-            GB2312Prober(),
-            EUCKRProber(),
-            CP949Prober(),
-            Big5Prober(),
-            EUCTWProber()
-        ]
-        self.reset()
+######################## 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 .charsetgroupprober import CharSetGroupProber
+from .utf8prober import UTF8Prober
+from .sjisprober import SJISProber
+from .eucjpprober import EUCJPProber
+from .gb2312prober import GB2312Prober
+from .euckrprober import EUCKRProber
+from .cp949prober import CP949Prober
+from .big5prober import Big5Prober
+from .euctwprober import EUCTWProber
+
+
+class MBCSGroupProber(CharSetGroupProber):
+    def __init__(self, lang_filter=None):
+        super(MBCSGroupProber, self).__init__(lang_filter=lang_filter)
+        self.probers = [
+            UTF8Prober(),
+            SJISProber(),
+            EUCJPProber(),
+            GB2312Prober(),
+            EUCKRProber(),
+            CP949Prober(),
+            Big5Prober(),
+            EUCTWProber()
+        ]
+        self.reset()