diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2018-11-07 12:19:29 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2018-11-07 12:20:17 +0000 |
commit | a64a253794ac64cb40befee54db53bde17dd0d49 (patch) | |
tree | c1024acc5f6e508814b944d99f112259bb28b1be /collectors/python.d.plugin/python_modules/pyyaml2/reader.py | |
parent | New upstream version 1.10.0+dfsg (diff) | |
download | netdata-2dec20452b290c484d509f7ac9a29b38cf690223.tar.xz netdata-2dec20452b290c484d509f7ac9a29b38cf690223.zip |
New upstream version 1.11.0+dfsgupstream/1.11.0+dfsg
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'collectors/python.d.plugin/python_modules/pyyaml2/reader.py')
-rw-r--r-- | collectors/python.d.plugin/python_modules/pyyaml2/reader.py | 191 |
1 files changed, 191 insertions, 0 deletions
diff --git a/collectors/python.d.plugin/python_modules/pyyaml2/reader.py b/collectors/python.d.plugin/python_modules/pyyaml2/reader.py new file mode 100644 index 000000000..8d422954e --- /dev/null +++ b/collectors/python.d.plugin/python_modules/pyyaml2/reader.py @@ -0,0 +1,191 @@ +# SPDX-License-Identifier: MIT +# This module contains abstractions for the input stream. You don't have to +# looks further, there are no pretty code. +# +# We define two classes here. +# +# Mark(source, line, column) +# It's just a record and its only use is producing nice error messages. +# Parser does not use it for any other purposes. +# +# Reader(source, data) +# Reader determines the encoding of `data` and converts it to unicode. +# Reader provides the following methods and attributes: +# reader.peek(length=1) - return the next `length` characters +# reader.forward(length=1) - move the current position to `length` characters. +# reader.index - the number of the current character. +# reader.line, stream.column - the line and the column of the current character. + +__all__ = ['Reader', 'ReaderError'] + +from error import YAMLError, Mark + +import codecs, re + +class ReaderError(YAMLError): + + def __init__(self, name, position, character, encoding, reason): + self.name = name + self.character = character + self.position = position + self.encoding = encoding + self.reason = reason + + def __str__(self): + if isinstance(self.character, str): + return "'%s' codec can't decode byte #x%02x: %s\n" \ + " in \"%s\", position %d" \ + % (self.encoding, ord(self.character), self.reason, + self.name, self.position) + else: + return "unacceptable character #x%04x: %s\n" \ + " in \"%s\", position %d" \ + % (self.character, self.reason, + self.name, self.position) + +class Reader(object): + # Reader: + # - determines the data encoding and converts it to unicode, + # - checks if characters are in allowed range, + # - adds '\0' to the end. + + # Reader accepts + # - a `str` object, + # - a `unicode` object, + # - a file-like object with its `read` method returning `str`, + # - a file-like object with its `read` method returning `unicode`. + + # Yeah, it's ugly and slow. + + def __init__(self, stream): + self.name = None + self.stream = None + self.stream_pointer = 0 + self.eof = True + self.buffer = u'' + self.pointer = 0 + self.raw_buffer = None + self.raw_decode = None + self.encoding = None + self.index = 0 + self.line = 0 + self.column = 0 + if isinstance(stream, unicode): + self.name = "<unicode string>" + self.check_printable(stream) + self.buffer = stream+u'\0' + elif isinstance(stream, str): + self.name = "<string>" + self.raw_buffer = stream + self.determine_encoding() + else: + self.stream = stream + self.name = getattr(stream, 'name', "<file>") + self.eof = False + self.raw_buffer = '' + self.determine_encoding() + + def peek(self, index=0): + try: + return self.buffer[self.pointer+index] + except IndexError: + self.update(index+1) + return self.buffer[self.pointer+index] + + def prefix(self, length=1): + if self.pointer+length >= len(self.buffer): + self.update(length) + return self.buffer[self.pointer:self.pointer+length] + + def forward(self, length=1): + if self.pointer+length+1 >= len(self.buffer): + self.update(length+1) + while length: + ch = self.buffer[self.pointer] + self.pointer += 1 + self.index += 1 + if ch in u'\n\x85\u2028\u2029' \ + or (ch == u'\r' and self.buffer[self.pointer] != u'\n'): + self.line += 1 + self.column = 0 + elif ch != u'\uFEFF': + self.column += 1 + length -= 1 + + def get_mark(self): + if self.stream is None: + return Mark(self.name, self.index, self.line, self.column, + self.buffer, self.pointer) + else: + return Mark(self.name, self.index, self.line, self.column, + None, None) + + def determine_encoding(self): + while not self.eof and len(self.raw_buffer) < 2: + self.update_raw() + if not isinstance(self.raw_buffer, unicode): + if self.raw_buffer.startswith(codecs.BOM_UTF16_LE): + self.raw_decode = codecs.utf_16_le_decode + self.encoding = 'utf-16-le' + elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE): + self.raw_decode = codecs.utf_16_be_decode + self.encoding = 'utf-16-be' + else: + self.raw_decode = codecs.utf_8_decode + self.encoding = 'utf-8' + self.update(1) + + NON_PRINTABLE = re.compile(u'[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD]') + def check_printable(self, data): + match = self.NON_PRINTABLE.search(data) + if match: + character = match.group() + position = self.index+(len(self.buffer)-self.pointer)+match.start() + raise ReaderError(self.name, position, ord(character), + 'unicode', "special characters are not allowed") + + def update(self, length): + if self.raw_buffer is None: + return + self.buffer = self.buffer[self.pointer:] + self.pointer = 0 + while len(self.buffer) < length: + if not self.eof: + self.update_raw() + if self.raw_decode is not None: + try: + data, converted = self.raw_decode(self.raw_buffer, + 'strict', self.eof) + except UnicodeDecodeError, exc: + character = exc.object[exc.start] + if self.stream is not None: + position = self.stream_pointer-len(self.raw_buffer)+exc.start + else: + position = exc.start + raise ReaderError(self.name, position, character, + exc.encoding, exc.reason) + else: + data = self.raw_buffer + converted = len(data) + self.check_printable(data) + self.buffer += data + self.raw_buffer = self.raw_buffer[converted:] + if self.eof: + self.buffer += u'\0' + self.raw_buffer = None + break + + def update_raw(self, size=1024): + data = self.stream.read(size) + if data: + self.raw_buffer += data + self.stream_pointer += len(data) + else: + self.eof = True + +#try: +# import psyco +# psyco.bind(Reader) +#except ImportError: +# pass + |