Add managed writer for Ion 1.1 with basic round-trip testing #830
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,181 @@ | ||
| // Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. | ||
| // SPDX-License-Identifier: Apache-2.0 | ||
| package com.amazon.ion.impl | ||
|
|
||
| import com.amazon.ion.impl.bin.* | ||
| import com.amazon.ion.util.* | ||
| import java.io.OutputStream | ||
|
|
||
| /** | ||
| * A [_Private_FastAppendable] that buffers data to blocks of memory which are managed by a [BlockAllocator]. Only when | ||
| * [flush] is called are the blocks written to the wrapped [OutputStream]. | ||
| * | ||
| * This is necessary for cases where an [IonManagedWriter_1_1] over Ion text needs to emit encoding directives that are | ||
| * not known in advance. The [OutputStreamFastAppendable] class only buffers a fixed amount of data, so it is not safe | ||
| * to use if there are system values to be written. For a sufficiently large user value, an [OutputStreamFastAppendable] | ||
| * can end up flushing partial or whole user values flushing to the [OutputStream] before the [IonManagedWriter_1_1] can | ||
| * write the system value that it depends on. | ||
| * | ||
| * Once [IonManagedWriter_1_1] supports an auto-flush feature, then this class will have very little practical | ||
| * difference from [OutputStreamFastAppendable] for the case where no system values are needed. | ||
| * | ||
| * TODO: | ||
| * - Add proper tests | ||
| */ | ||
| internal class BlockBufferingOutputStreamFastAppendable( | ||
| private val out: OutputStream, | ||
| private val allocator: BlockAllocator, | ||
| /** | ||
| * The minimum utilization of a block before a longer value | ||
| * can skip the end of a block and just start a new block. | ||
| */ | ||
| minBlockUtilization: Double = 1.0, | ||
| ) : OutputStream(), _Private_FastAppendable { | ||
|
|
||
| init { | ||
| // 0.0 would have the possibility of wasting entire blocks. | ||
| // 0.5 is somewhat arbitrary, but at least sensible that you should use at least | ||
| // half of a block before moving on to the next block. | ||
| require(minBlockUtilization in 0.5..1.0) { "minBlockUtilization must be between 0.5 and 1" } | ||
| require(allocator.blockSize > 10) | ||
| } | ||
|
|
||
| private val maxBlockWaste: Int = (allocator.blockSize * (1.0 - minBlockUtilization)).toInt() | ||
|
|
||
| private var index = -1 | ||
| private val blocks = mutableListOf<Block>() | ||
| private var current: Block = nextBlock() | ||
|
|
||
| private fun nextBlock(): Block { | ||
| index++ | ||
| if (index < 0) throw IllegalStateException("This output stream is closed.") | ||
| if (index >= blocks.size) blocks.add(allocator.allocateBlock()) | ||
| return blocks[index] | ||
| } | ||
|
|
||
| override fun close() { | ||
| flush() | ||
| blocks.onEach { it.close() }.clear() | ||
| index = Int.MIN_VALUE | ||
| } | ||
|
|
||
| override fun flush() { | ||
| blocks.forEach { block -> | ||
| out.write(block.data, 0, block.limit) | ||
| block.reset() | ||
| } | ||
| index = 0 | ||
| current = blocks[index] | ||
| } | ||
|
|
||
| override fun write(b: Int) { | ||
| if (current.remaining() < 1) current = nextBlock() | ||
| val block = current | ||
| block.data[block.limit] = b.toByte() | ||
| block.limit++ | ||
| } | ||
|
|
||
| override fun write(b: ByteArray, off: Int, len: Int) { | ||
| if (len > current.remaining()) { | ||
| if (current.remaining() < maxBlockWaste && len < allocator.blockSize) { | ||
| current = nextBlock() | ||
| } else { | ||
| writeBytesSlow(b, off, len) | ||
| return | ||
| } | ||
| } | ||
| val block = current | ||
| System.arraycopy(b, off, block.data, block.limit, len) | ||
| block.limit += len | ||
| } | ||
|
|
||
| // slow in the sense that we do all kind of block boundary checking | ||
| private fun writeBytesSlow(bytes: ByteArray, _off: Int, _len: Int) { | ||
| var off = _off | ||
| var len = _len | ||
| while (len > 0) { | ||
| val block = current | ||
| val amount = Math.min(len, block.remaining()) | ||
| System.arraycopy(bytes, off, block.data, block.limit, amount) | ||
| block.limit += amount | ||
| off += amount | ||
| len -= amount | ||
| if (block.remaining() == 0) { | ||
| current = nextBlock() | ||
| } | ||
| } | ||
| } | ||
|
|
||
| override fun append(c: Char): Appendable = apply { if (c.code < 0x80) appendAscii(c) else appendUtf16(c) } | ||
|
|
||
| override fun append(csq: CharSequence): Appendable = apply { append(csq, 0, csq.length) } | ||
|
|
||
| override fun append(csq: CharSequence, start: Int, end: Int): Appendable { | ||
| for (i in start until end) { | ||
| append(csq[i]) | ||
| } | ||
| return this | ||
| } | ||
|
|
||
| override fun appendAscii(c: Char) { | ||
| assert(c.code < 0x80) | ||
| write(c.code) | ||
| } | ||
|
|
||
| override fun appendAscii(csq: CharSequence) = appendAscii(csq, 0, csq.length) | ||
|
|
||
| override fun appendAscii(csq: CharSequence, start: Int, end: Int) { | ||
| if (csq is String) { | ||
| // Using deprecated String.getBytes intentionally, since it is | ||
| // correct behavior in this case, and much faster. | ||
| var pos = start | ||
| val len = end - start | ||
| if (len > current.remaining() && current.remaining() < maxBlockWaste && len < allocator.blockSize) { | ||
| current = nextBlock() | ||
| } | ||
| while (true) { | ||
| val copyAmount = minOf(current.remaining(), end - pos) | ||
| csq.copyBytes(pos, pos + copyAmount, current.data, current.limit) | ||
| current.limit += copyAmount | ||
| pos += copyAmount | ||
| if (pos >= end) return | ||
| current = nextBlock() | ||
| } | ||
| } else { | ||
| append(csq, start, end) | ||
| } | ||
| } | ||
|
|
||
| override fun appendUtf16(c: Char) { | ||
| assert(c.code >= 0x80) | ||
| if (current.remaining() < 3) { | ||
| current = nextBlock() | ||
| } | ||
| if (c.code < 0x800) { | ||
| current.data[current.limit++] = (0xff and (0xC0 or (c.code shr 6))).toByte() | ||
| current.data[current.limit++] = (0xff and (0x80 or (c.code and 0x3F))).toByte() | ||
| } else if (c.code < 0x10000) { | ||
| current.data[current.limit++] = (0xff and (0xE0 or (c.code shr 12))).toByte() | ||
| current.data[current.limit++] = (0xff and (0x80 or (c.code shr 6 and 0x3F))).toByte() | ||
| current.data[current.limit++] = (0xff and (0x80 or (c.code and 0x3F))).toByte() | ||
| } | ||
| } | ||
|
|
||
| override fun appendUtf16Surrogate(leadSurrogate: Char, trailSurrogate: Char) { | ||
| // Here we must convert a UTF-16 surrogate pair to UTF-8 bytes. | ||
| val c = _Private_IonConstants.makeUnicodeScalar(leadSurrogate.code, trailSurrogate.code) | ||
| assert(c >= 0x10000) | ||
| if (current.remaining() < 4) { | ||
| current = nextBlock() | ||
| } | ||
| current.data[current.limit++] = (0xff and (0xF0 or (c shr 18))).toByte() | ||
| current.data[current.limit++] = (0xff and (0x80 or (c shr 12 and 0x3F))).toByte() | ||
| current.data[current.limit++] = (0xff and (0x80 or (c shr 6 and 0x3F))).toByte() | ||
| current.data[current.limit++] = (0xff and (0x80 or (c and 0x3F))).toByte() | ||
| } | ||
|
|
||
| /** Helper function to wrap [java.lang.String.getBytes]. */ | ||
| private fun String.copyBytes(srcBegin: Int, srcEnd: Int, dst: ByteArray, dstBegin: Int) { | ||
| (this as java.lang.String).getBytes(srcBegin, srcEnd, dst, dstBegin) | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🗺️ I think this is something that we can probably live with.