File: reader.py

package info (click to toggle)
ruamel.yaml 0.15.89-3
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 2,508 kB
  • sloc: python: 10,725; ansic: 7,392; makefile: 11
file content (311 lines) | stat: -rw-r--r-- 10,876 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
# coding: utf-8

from __future__ import absolute_import

# 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.

import codecs

from ruamel.yaml.error import YAMLError, FileMark, StringMark, YAMLStreamError
from ruamel.yaml.compat import text_type, binary_type, PY3, UNICODE_SIZE
from ruamel.yaml.util import RegExp

if False:  # MYPY
    from typing import Any, Dict, Optional, List, Union, Text, Tuple, Optional  # NOQA
#    from ruamel.yaml.compat import StreamTextType  # NOQA

__all__ = ['Reader', 'ReaderError']


class ReaderError(YAMLError):
    def __init__(self, name, position, character, encoding, reason):
        # type: (Any, Any, Any, Any, Any) -> None
        self.name = name
        self.character = character
        self.position = position
        self.encoding = encoding
        self.reason = reason

    def __str__(self):
        # type: () -> str
        if isinstance(self.character, binary_type):
            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 a unicode string,
    # - checks if characters are in allowed range,
    # - adds '\0' to the end.

    # Reader accepts
    #  - a `str` object (PY2) / a `bytes` object (PY3),
    #  - a `unicode` object (PY2) / a `str` object (PY3),
    #  - 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, loader=None):
        # type: (Any, Any) -> None
        self.loader = loader
        if self.loader is not None and getattr(self.loader, '_reader', None) is None:
            self.loader._reader = self
        self.reset_reader()
        self.stream = stream  # type: Any  # as .read is called

    def reset_reader(self):
        # type: () -> None
        self.name = None  # type: Any
        self.stream_pointer = 0
        self.eof = True
        self.buffer = ""
        self.pointer = 0
        self.raw_buffer = None  # type: Any
        self.raw_decode = None
        self.encoding = None  # type: Optional[Text]
        self.index = 0
        self.line = 0
        self.column = 0

    @property
    def stream(self):
        # type: () -> Any
        try:
            return self._stream
        except AttributeError:
            raise YAMLStreamError('input stream needs to specified')

    @stream.setter
    def stream(self, val):
        # type: (Any) -> None
        if val is None:
            return
        self._stream = None
        if isinstance(val, text_type):
            self.name = '<unicode string>'
            self.check_printable(val)
            self.buffer = val + u'\0'  # type: ignore
        elif isinstance(val, binary_type):
            self.name = '<byte string>'
            self.raw_buffer = val
            self.determine_encoding()
        else:
            if not hasattr(val, 'read'):
                raise YAMLStreamError('stream argument needs to have a read() method')
            self._stream = val
            self.name = getattr(self.stream, 'name', '<file>')
            self.eof = False
            self.raw_buffer = None
            self.determine_encoding()

    def peek(self, index=0):
        # type: (int) -> Text
        try:
            return self.buffer[self.pointer + index]
        except IndexError:
            self.update(index + 1)
            return self.buffer[self.pointer + index]

    def prefix(self, length=1):
        # type: (int) -> Any
        if self.pointer + length >= len(self.buffer):
            self.update(length)
        return self.buffer[self.pointer : self.pointer + length]

    def forward_1_1(self, length=1):
        # type: (int) -> None
        if self.pointer + length + 1 >= len(self.buffer):
            self.update(length + 1)
        while length != 0:
            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 forward(self, length=1):
        # type: (int) -> None
        if self.pointer + length + 1 >= len(self.buffer):
            self.update(length + 1)
        while length != 0:
            ch = self.buffer[self.pointer]
            self.pointer += 1
            self.index += 1
            if ch == u'\n' 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):
        # type: () -> Any
        if self.stream is None:
            return StringMark(
                self.name, self.index, self.line, self.column, self.buffer, self.pointer
            )
        else:
            return FileMark(self.name, self.index, self.line, self.column)

    def determine_encoding(self):
        # type: () -> None
        while not self.eof and (self.raw_buffer is None or len(self.raw_buffer) < 2):
            self.update_raw()
        if isinstance(self.raw_buffer, binary_type):
            if self.raw_buffer.startswith(codecs.BOM_UTF16_LE):
                self.raw_decode = codecs.utf_16_le_decode  # type: ignore
                self.encoding = 'utf-16-le'
            elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE):
                self.raw_decode = codecs.utf_16_be_decode  # type: ignore
                self.encoding = 'utf-16-be'
            else:
                self.raw_decode = codecs.utf_8_decode  # type: ignore
                self.encoding = 'utf-8'
        self.update(1)

    if UNICODE_SIZE == 2:
        NON_PRINTABLE = RegExp(
            u'[^\x09\x0A\x0D\x20-\x7E\x85' u'\xA0-\uD7FF' u'\uE000-\uFFFD' u']'
        )
    else:
        NON_PRINTABLE = RegExp(
            u'[^\x09\x0A\x0D\x20-\x7E\x85'
            u'\xA0-\uD7FF'
            u'\uE000-\uFFFD'
            u'\U00010000-\U0010FFFF'
            u']'
        )

    _printable_ascii = ('\x09\x0A\x0D' + "".join(map(chr, range(0x20, 0x7F)))).encode('ascii')

    @classmethod
    def _get_non_printable_ascii(cls, data):  # type: ignore
        # type: (Text, bytes) -> Optional[Tuple[int, Text]]
        ascii_bytes = data.encode('ascii')
        non_printables = ascii_bytes.translate(None, cls._printable_ascii)  # type: ignore
        if not non_printables:
            return None
        non_printable = non_printables[:1]
        return ascii_bytes.index(non_printable), non_printable.decode('ascii')

    @classmethod
    def _get_non_printable_regex(cls, data):
        # type: (Text) -> Optional[Tuple[int, Text]]
        match = cls.NON_PRINTABLE.search(data)
        if not bool(match):
            return None
        return match.start(), match.group()

    @classmethod
    def _get_non_printable(cls, data):
        # type: (Text) -> Optional[Tuple[int, Text]]
        try:
            return cls._get_non_printable_ascii(data)  # type: ignore
        except UnicodeEncodeError:
            return cls._get_non_printable_regex(data)

    def check_printable(self, data):
        # type: (Any) -> None
        non_printable_match = self._get_non_printable(data)
        if non_printable_match is not None:
            start, character = non_printable_match
            position = self.index + (len(self.buffer) - self.pointer) + start
            raise ReaderError(
                self.name,
                position,
                ord(character),
                'unicode',
                'special characters are not allowed',
            )

    def update(self, length):
        # type: (int) -> None
        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 as exc:
                    if PY3:
                        character = self.raw_buffer[exc.start]
                    else:
                        character = exc.object[exc.start]
                    if self.stream is not None:
                        position = self.stream_pointer - len(self.raw_buffer) + exc.start
                    elif 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 += '\0'
                self.raw_buffer = None
                break

    def update_raw(self, size=None):
        # type: (Optional[int]) -> None
        if size is None:
            size = 4096 if PY3 else 1024
        data = self.stream.read(size)
        if self.raw_buffer is None:
            self.raw_buffer = data
        else:
            self.raw_buffer += data
        self.stream_pointer += len(data)
        if not data:
            self.eof = True


# try:
#     import psyco
#     psyco.bind(Reader)
# except ImportError:
#     pass