Python codecs 模块,BOM_UTF32_LE 实例源码

我们从Python开源项目中,提取了以下50个代码示例,用于说明如何使用codecs.BOM_UTF32_LE

项目:scm-workbench    作者:barry-scott    | 项目源码 | 文件源码
def encodingFromContents( contents ):
    if( len(contents) > len(codecs.BOM_UTF8)
    and contents[0:len(codecs.BOM_UTF8)] == codecs.BOM_UTF8 ):
        encoding = 'utf-8'

    elif( len(contents) > len(codecs.BOM_UTF16_LE)
    and contents[0:len(codecs.BOM_UTF16_LE)] in [codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE]):
        encoding = 'utf-16'

    elif( len(contents) > len(codecs.BOM_UTF32_LE)
    and contents[0:len(codecs.BOM_UTF32_LE)] in [codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE]):
        encoding = 'utf-32'

    else:
        encoding = locale.getdefaultlocale()[1]

        # Mac says mac-roman when utf-8 is what is required
        if encoding == 'mac-roman':
            encoding = 'utf-8'

    if encoding is None:
        encoding = 'iso8859-1'

    return encoding
项目:Price-Comparator    作者:Thejas-1    | 项目源码 | 文件源码
def _detect_encoding(self, fileid):
        if isinstance(fileid, PathPointer):
            s = fileid.open().readline()
        else:
            with open(fileid, 'rb') as infile:
                s = infile.readline()
        if s.startswith(codecs.BOM_UTF16_BE):
            return 'utf-16-be'
        if s.startswith(codecs.BOM_UTF16_LE):
            return 'utf-16-le'
        if s.startswith(codecs.BOM_UTF32_BE):
            return 'utf-32-be'
        if s.startswith(codecs.BOM_UTF32_LE):
            return 'utf-32-le'
        if s.startswith(codecs.BOM_UTF8):
            return 'utf-8'
        m = re.match(br'\s*<\?xml\b.*\bencoding="([^"]+)"', s)
        if m:
            return m.group(1).decode()
        m = re.match(br"\s*<\?xml\b.*\bencoding='([^']+)'", s)
        if m:
            return m.group(1).decode()
        # No encoding found -- what should the default be?
        return 'utf-8'
项目:python-    作者:secondtonone1    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        if encoding:
            self.rawStream.seek(seek)
            return lookupEncoding(encoding)
        else:
            self.rawStream.seek(0)
            return None
项目:python-    作者:secondtonone1    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:my-first-blog    作者:AnkurBegining    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        if encoding:
            self.rawStream.seek(seek)
            return lookupEncoding(encoding)
        else:
            self.rawStream.seek(0)
            return None
项目:my-first-blog    作者:AnkurBegining    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:my-first-blog    作者:AnkurBegining    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:googletranslate.popclipext    作者:wizyoung    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:Flask_Blog    作者:sugarguo    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:Flask_Blog    作者:sugarguo    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:pip-update-requirements    作者:alanhamlett    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        if encoding:
            self.rawStream.seek(seek)
            return lookupEncoding(encoding)
        else:
            self.rawStream.seek(0)
            return None
项目:pip-update-requirements    作者:alanhamlett    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:aws-waf-security-automation    作者:cerbo    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:v2ex-tornado-2    作者:coderyy    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2]) # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:swjtu-pyscraper    作者:Desgard    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:swjtu-pyscraper    作者:Desgard    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:noc-orchestrator    作者:DirceuSilvaLabs    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:jira_worklog_scanner    作者:pgarneau    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        if encoding:
            self.rawStream.seek(seek)
            return lookupEncoding(encoding)
        else:
            self.rawStream.seek(0)
            return None
项目:jira_worklog_scanner    作者:pgarneau    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:jira_worklog_scanner    作者:pgarneau    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:pykit    作者:baishancloud    | 项目源码 | 文件源码
def detect_encoding(b):
    bstartswith = b.startswith
    if bstartswith((codecs.BOM_UTF32_BE, codecs.BOM_UTF32_LE)):
        return 'utf-32'
    if bstartswith((codecs.BOM_UTF16_BE, codecs.BOM_UTF16_LE)):
        return 'utf-16'
    if bstartswith(codecs.BOM_UTF8):
        return 'utf-8-sig'

    if len(b) >= 4:
        if not b[0]:
            # 00 00 -- -- - utf-32-be
            # 00 XX -- -- - utf-16-be
            return 'utf-16-be' if b[1] else 'utf-32-be'
        if not b[1]:
            # XX 00 00 00 - utf-32-le
            # XX 00 00 XX - utf-16-le
            # XX 00 XX -- - utf-16-le
            return 'utf-16-le' if b[2] or b[3] else 'utf-32-le'
    elif len(b) == 2:
        if not b[0]:
            # 00 XX - utf-16-be
            return 'utf-16-be'
        if not b[1]:
            # XX 00 - utf-16-le
            return 'utf-16-le'
    # default
    return 'utf-8'
项目:workflows.kyoyue    作者:wizyoung    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:zanph    作者:zanph    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:zanph    作者:zanph    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:zanph    作者:zanph    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:hostapd-mana    作者:adde88    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:hostapd-mana    作者:adde88    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:hostapd-mana    作者:adde88    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        self.rawStream.seek(encoding and seek or 0)

        return encoding
项目:hostapd-mana    作者:adde88    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:YoWhenReady    作者:jnsdrtlf    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:Sci-Finder    作者:snverse    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        if encoding:
            self.rawStream.seek(seek)
            return lookupEncoding(encoding)
        else:
            self.rawStream.seek(0)
            return None
项目:Sci-Finder    作者:snverse    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:Sci-Finder    作者:snverse    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        if encoding:
            self.rawStream.seek(seek)
            return lookupEncoding(encoding)
        else:
            self.rawStream.seek(0)
            return None
项目:Sci-Finder    作者:snverse    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:purelove    作者:hucmosin    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:alexa-stackoverflow    作者:benvand    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:devsecops-example-helloworld    作者:boozallen    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:harbour-sailfinder    作者:DylanVanAssche    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:harbour-sailfinder    作者:DylanVanAssche    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:QXSConsolas    作者:qxsch    | 项目源码 | 文件源码
def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None
项目:ascii-art-py    作者:blinglnav    | 项目源码 | 文件源码
def detectBOM(self):
        """Attempts to detect at BOM at the start of the stream. If
        an encoding can be determined from the BOM return the name of the
        encoding otherwise return None"""
        bomDict = {
            codecs.BOM_UTF8: 'utf-8',
            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
        }

        # Go to beginning of file and read in 4 bytes
        string = self.rawStream.read(4)
        assert isinstance(string, bytes)

        # Try detecting the BOM using bytes from the string
        encoding = bomDict.get(string[:3])         # UTF-8
        seek = 3
        if not encoding:
            # Need to detect UTF-32 before UTF-16
            encoding = bomDict.get(string)         # UTF-32
            seek = 4
            if not encoding:
                encoding = bomDict.get(string[:2])  # UTF-16
                seek = 2

        # Set the read position past the BOM if one was found, otherwise
        # set it to the start of the stream
        if encoding:
            self.rawStream.seek(seek)
            return lookupEncoding(encoding)
        else:
            self.rawStream.seek(0)
            return None
项目:ascii-art-py    作者:blinglnav    | 项目源码 | 文件源码
def guess_json_utf(data):
    """
    :rtype: str
    """
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None