-
Notifications
You must be signed in to change notification settings - Fork 623
/
IndexableBinaryStringTools.cs
329 lines (314 loc) · 17.7 KB
/
IndexableBinaryStringTools.cs
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
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
using J2N.Numerics;
using Lucene.Net.Diagnostics;
using System;
using System.Runtime.CompilerServices;
namespace Lucene.Net.Util
{
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/// <summary>
/// Provides support for converting byte sequences to <see cref="string"/>s and back again.
/// The resulting <see cref="string"/>s preserve the original byte sequences' sort order.
/// <para/>
/// The <see cref="string"/>s are constructed using a Base 8000h encoding of the original
/// binary data - each char of an encoded <see cref="string"/> represents a 15-bit chunk
/// from the byte sequence. Base 8000h was chosen because it allows for all
/// lower 15 bits of char to be used without restriction; the surrogate range
/// [U+D8000-U+DFFF] does not represent valid chars, and would require
/// complicated handling to avoid them and allow use of char's high bit.
/// <para/>
/// Although unset bits are used as padding in the final char, the original
/// byte sequence could contain trailing bytes with no set bits (null bytes):
/// padding is indistinguishable from valid information. To overcome this
/// problem, a char is appended, indicating the number of encoded bytes in the
/// final content char.
/// <para/>
/// @lucene.experimental
/// </summary>
[Obsolete("Implement Analysis.TokenAttributes.ITermToBytesRefAttribute and store bytes directly instead. this class will be removed in Lucene 5.0")]
public static class IndexableBinaryStringTools // LUCENENET specific - made static
{
private static readonly CodingCase[] CODING_CASES = new CodingCase[] {
// CodingCase(int initialShift, int finalShift)
new CodingCase(7, 1),
// CodingCase(int initialShift, int middleShift, int finalShift)
new CodingCase(14, 6, 2),
new CodingCase(13, 5, 3),
new CodingCase(12, 4, 4),
new CodingCase(11, 3, 5),
new CodingCase(10, 2, 6),
new CodingCase(9, 1, 7),
new CodingCase(8, 0)
};
/// <summary>
/// Returns the number of chars required to encode the given <see cref="byte"/>s.
/// </summary>
/// <param name="inputArray"> Byte sequence to be encoded </param>
/// <param name="inputOffset"> Initial offset into <paramref name="inputArray"/> </param>
/// <param name="inputLength"> Number of bytes in <paramref name="inputArray"/> </param>
/// <returns> The number of chars required to encode the number of <see cref="byte"/>s. </returns>
// LUCENENET specific overload for CLS compliance
[MethodImpl(MethodImplOptions.AggressiveInlining)]
#pragma warning disable IDE0060 // Remove unused parameter
public static int GetEncodedLength(byte[] inputArray, int inputOffset, int inputLength)
#pragma warning restore IDE0060 // Remove unused parameter
{
// Use long for intermediaries to protect against overflow
return (int)((8L * inputLength + 14L) / 15L) + 1;
}
/// <summary>
/// Returns the number of chars required to encode the given <see cref="sbyte"/>s.
/// </summary>
/// <param name="inputArray"> <see cref="sbyte"/> sequence to be encoded </param>
/// <param name="inputOffset"> Initial offset into <paramref name="inputArray"/> </param>
/// <param name="inputLength"> Number of sbytes in <paramref name="inputArray"/> </param>
/// <returns> The number of chars required to encode the number of <see cref="sbyte"/>s. </returns>
[CLSCompliant(false)]
[MethodImpl(MethodImplOptions.AggressiveInlining)]
#pragma warning disable IDE0060 // Remove unused parameter
public static int GetEncodedLength(sbyte[] inputArray, int inputOffset, int inputLength)
#pragma warning restore IDE0060 // Remove unused parameter
{
// Use long for intermediaries to protect against overflow
return (int)((8L * inputLength + 14L) / 15L) + 1;
}
/// <summary>
/// Returns the number of <see cref="byte"/>s required to decode the given char sequence.
/// </summary>
/// <param name="encoded"> Char sequence to be decoded </param>
/// <param name="offset"> Initial offset </param>
/// <param name="length"> Number of characters </param>
/// <returns> The number of <see cref="byte"/>s required to decode the given char sequence </returns>
public static int GetDecodedLength(char[] encoded, int offset, int length)
{
int numChars = length - 1;
if (numChars <= 0)
{
return 0;
}
else
{
// Use long for intermediaries to protect against overflow
long numFullBytesInFinalChar = encoded[offset + length - 1];
long numEncodedChars = numChars - 1;
return (int)((numEncodedChars * 15L + 7L) / 8L + numFullBytesInFinalChar);
}
}
/// <summary>
/// Encodes the input <see cref="byte"/> sequence into the output char sequence. Before
/// calling this method, ensure that the output array has sufficient
/// capacity by calling <see cref="GetEncodedLength(byte[], int, int)"/>.
/// </summary>
/// <param name="inputArray"> <see cref="byte"/> sequence to be encoded </param>
/// <param name="inputOffset"> Initial offset into <paramref name="inputArray"/> </param>
/// <param name="inputLength"> Number of bytes in <paramref name="inputArray"/> </param>
/// <param name="outputArray"> <see cref="char"/> sequence to store encoded result </param>
/// <param name="outputOffset"> Initial offset into outputArray </param>
/// <param name="outputLength"> Length of output, must be GetEncodedLength(inputArray, inputOffset, inputLength) </param>
// LUCENENET specific overload for CLS compliance
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static void Encode(byte[] inputArray, int inputOffset, int inputLength, char[] outputArray, int outputOffset, int outputLength)
{
Encode((sbyte[])(Array)inputArray, inputOffset, inputLength, outputArray, outputOffset, outputLength);
}
/// <summary>
/// Encodes the input <see cref="sbyte"/> sequence into the output char sequence. Before
/// calling this method, ensure that the output array has sufficient
/// capacity by calling <see cref="GetEncodedLength(sbyte[], int, int)"/>.
/// </summary>
/// <param name="inputArray"> <see cref="sbyte"/> sequence to be encoded </param>
/// <param name="inputOffset"> Initial offset into <paramref name="inputArray"/> </param>
/// <param name="inputLength"> Number of bytes in <paramref name="inputArray"/> </param>
/// <param name="outputArray"> <see cref="char"/> sequence to store encoded result </param>
/// <param name="outputOffset"> Initial offset into outputArray </param>
/// <param name="outputLength"> Length of output, must be getEncodedLength </param>
[CLSCompliant(false)]
public static void Encode(sbyte[] inputArray, int inputOffset, int inputLength, char[] outputArray, int outputOffset, int outputLength)
{
if (Debugging.AssertsEnabled) Debugging.Assert(outputLength == GetEncodedLength(inputArray, inputOffset, inputLength));
if (inputLength > 0)
{
int inputByteNum = inputOffset;
int caseNum = 0;
int outputCharNum = outputOffset;
CodingCase codingCase;
for (; inputByteNum + CODING_CASES[caseNum].numBytes <= inputLength; ++outputCharNum)
{
codingCase = CODING_CASES[caseNum];
if (2 == codingCase.numBytes)
{
outputArray[outputCharNum] = (char)(((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift)
+ (((inputArray[inputByteNum + 1] & 0xFF).TripleShift(codingCase.finalShift)) & codingCase.finalMask) & /*(short)*/0x7FFF); // LUCENENET: Removed unnecessary cast
} // numBytes is 3
else
{
outputArray[outputCharNum] = (char)(((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift)
+ ((inputArray[inputByteNum + 1] & 0xFF) << codingCase.middleShift)
+ (((inputArray[inputByteNum + 2] & 0xFF).TripleShift(codingCase.finalShift)) & codingCase.finalMask) & /*(short)*/0x7FFF); // LUCENENET: Removed unnecessary cast
}
inputByteNum += codingCase.advanceBytes;
if (++caseNum == CODING_CASES.Length)
{
caseNum = 0;
}
}
// Produce final char (if any) and trailing count chars.
codingCase = CODING_CASES[caseNum];
if (inputByteNum + 1 < inputLength) // codingCase.numBytes must be 3
{
outputArray[outputCharNum++] = (char)((((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift) + ((inputArray[inputByteNum + 1] & 0xFF) <<
codingCase.middleShift)) & /*(short)*/0x7FFF); // LUCENENET: Removed unnecessary cast
// Add trailing char containing the number of full bytes in final char
outputArray[outputCharNum++] = (char)1;
}
else if (inputByteNum < inputLength)
{
outputArray[outputCharNum++] = (char)(((inputArray[inputByteNum] & 0xFF) << codingCase.initialShift) & /*(short)*/0x7FFF); // LUCENENET: Removed unnecessary cast
// Add trailing char containing the number of full bytes in final char
outputArray[outputCharNum++] = caseNum == 0 ? (char)1 : (char)0;
} // No left over bits - last char is completely filled.
else
{
// Add trailing char containing the number of full bytes in final char
outputArray[outputCharNum++] = (char)1;
}
}
}
/// <summary>
/// Decodes the input <see cref="char"/> sequence into the output <see cref="byte"/> sequence. Before
/// calling this method, ensure that the output array has sufficient capacity
/// by calling <see cref="GetDecodedLength(char[], int, int)"/>.
/// </summary>
/// <param name="inputArray"> <see cref="char"/> sequence to be decoded </param>
/// <param name="inputOffset"> Initial offset into <paramref name="inputArray"/> </param>
/// <param name="inputLength"> Number of chars in <paramref name="inputArray"/> </param>
/// <param name="outputArray"> <see cref="byte"/> sequence to store encoded result </param>
/// <param name="outputOffset"> Initial offset into outputArray </param>
/// <param name="outputLength"> Length of output, must be
/// GetDecodedLength(inputArray, inputOffset, inputLength) </param>
// LUCENENET specific overload for CLS compliance
[MethodImpl(MethodImplOptions.AggressiveInlining)]
public static void Decode(char[] inputArray, int inputOffset, int inputLength, byte[] outputArray, int outputOffset, int outputLength)
{
Decode(inputArray, inputOffset, inputLength, (sbyte[])(Array)outputArray, outputOffset, outputLength);
}
/// <summary>
/// Decodes the input char sequence into the output sbyte sequence. Before
/// calling this method, ensure that the output array has sufficient capacity
/// by calling <see cref="GetDecodedLength(char[], int, int)"/>.
/// </summary>
/// <param name="inputArray"> <see cref="char"/> sequence to be decoded </param>
/// <param name="inputOffset"> Initial offset into <paramref name="inputArray"/> </param>
/// <param name="inputLength"> Number of chars in <paramref name="inputArray"/> </param>
/// <param name="outputArray"> <see cref="byte"/> sequence to store encoded result </param>
/// <param name="outputOffset"> Initial offset into outputArray </param>
/// <param name="outputLength"> Length of output, must be
/// GetDecodedLength(inputArray, inputOffset, inputLength) </param>
[CLSCompliant(false)]
public static void Decode(char[] inputArray, int inputOffset, int inputLength, sbyte[] outputArray, int outputOffset, int outputLength)
{
if (Debugging.AssertsEnabled) Debugging.Assert(outputLength == GetDecodedLength(inputArray, inputOffset, inputLength));
int numInputChars = inputLength - 1;
int numOutputBytes = outputLength;
if (numOutputBytes > 0)
{
int caseNum = 0;
int outputByteNum = outputOffset;
int inputCharNum = inputOffset;
short inputChar;
CodingCase codingCase;
for (; inputCharNum < numInputChars - 1; ++inputCharNum)
{
codingCase = CODING_CASES[caseNum];
inputChar = (short)inputArray[inputCharNum];
if (2 == codingCase.numBytes)
{
if (0 == caseNum)
{
outputArray[outputByteNum] = (sbyte)(inputChar.TripleShift(codingCase.initialShift));
}
else
{
outputArray[outputByteNum] += (sbyte)(inputChar.TripleShift(codingCase.initialShift));
}
outputArray[outputByteNum + 1] = (sbyte)((inputChar & codingCase.finalMask) << codingCase.finalShift);
} // numBytes is 3
else
{
outputArray[outputByteNum] += (sbyte)(inputChar.TripleShift(codingCase.initialShift));
outputArray[outputByteNum + 1] = (sbyte)((inputChar & codingCase.middleMask).TripleShift(codingCase.middleShift));
outputArray[outputByteNum + 2] = (sbyte)((inputChar & codingCase.finalMask) << codingCase.finalShift);
}
outputByteNum += codingCase.advanceBytes;
if (++caseNum == CODING_CASES.Length)
{
caseNum = 0;
}
}
// Handle final char
inputChar = (short)inputArray[inputCharNum];
codingCase = CODING_CASES[caseNum];
if (0 == caseNum)
{
outputArray[outputByteNum] = 0;
}
outputArray[outputByteNum] += (sbyte)(inputChar.TripleShift(codingCase.initialShift));
int bytesLeft = numOutputBytes - outputByteNum;
if (bytesLeft > 1)
{
if (2 == codingCase.numBytes)
{
outputArray[outputByteNum + 1] = (sbyte)((inputChar & codingCase.finalMask).TripleShift(codingCase.finalShift));
} // numBytes is 3
else
{
outputArray[outputByteNum + 1] = (sbyte)((inputChar & codingCase.middleMask).TripleShift(codingCase.middleShift));
if (bytesLeft > 2)
{
outputArray[outputByteNum + 2] = (sbyte)((inputChar & codingCase.finalMask) << codingCase.finalShift);
}
}
}
}
}
internal class CodingCase
{
internal int numBytes, initialShift, middleShift, finalShift, advanceBytes = 2;
internal short middleMask, finalMask;
internal CodingCase(int initialShift, int middleShift, int finalShift)
{
this.numBytes = 3;
this.initialShift = initialShift;
this.middleShift = middleShift;
this.finalShift = finalShift;
this.finalMask = /*(short)*/((short)0xFF.TripleShift(finalShift)); // LUCENENET: Removed unnecessary cast
this.middleMask = (short)(/*(short)*/0xFF << middleShift); // LUCENENET: Removed unnecessary cast
}
internal CodingCase(int initialShift, int finalShift)
{
this.numBytes = 2;
this.initialShift = initialShift;
this.finalShift = finalShift;
this.finalMask = /*(short)*/((short)0xFF.TripleShift(finalShift)); // LUCENENET: Removed unnecessary cast
if (finalShift != 0)
{
advanceBytes = 1;
}
}
}
}
}