src/Pure/General/bytes.scala
author wenzelm
Tue, 21 Jun 2022 23:27:26 +0200
changeset 75579 3362b6a5d697
parent 75393 87ebf5a50283
child 75586 b2b097624e4c
permissions -rw-r--r--
support XZ compression in Isabelle/ML;
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     1
/*  Title:      Pure/General/bytes.scala
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     2
    Author:     Makarius
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     3
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     4
Immutable byte vectors versus UTF8 strings.
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     5
*/
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     6
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     7
package isabelle
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     8
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
     9
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    10
import java.io.{File => JFile, ByteArrayOutputStream, ByteArrayInputStream,
64229
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
    11
  OutputStream, InputStream, FileInputStream, FileOutputStream}
65070
1222c010bff7 more operations;
wenzelm
parents: 64370
diff changeset
    12
import java.net.URL
68094
0b66aca9c965 more operations;
wenzelm
parents: 68087
diff changeset
    13
import java.util.Base64
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    14
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    15
import org.tukaani.xz.{XZInputStream, XZOutputStream}
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    16
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    17
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
    18
object Bytes {
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
    19
  val empty: Bytes = new Bytes(Array[Byte](), 0, 0)
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
    20
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
    21
  def apply(s: CharSequence): Bytes = {
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
    22
    val str = s.toString
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
    23
    if (str.isEmpty) empty
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
    24
    else {
62527
aae9a2a855e0 tuned signature;
wenzelm
parents: 60833
diff changeset
    25
      val b = UTF8.bytes(str)
54442
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    26
      new Bytes(b, 0, b.length)
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
    27
    }
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
    28
  }
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    29
63779
9da65bc75610 more operations;
wenzelm
parents: 62527
diff changeset
    30
  def apply(a: Array[Byte]): Bytes = apply(a, 0, a.length)
9da65bc75610 more operations;
wenzelm
parents: 62527
diff changeset
    31
54442
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    32
  def apply(a: Array[Byte], offset: Int, length: Int): Bytes =
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    33
    if (length == 0) empty
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    34
    else {
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    35
      val b = new Array[Byte](length)
55618
995162143ef4 tuned imports;
wenzelm
parents: 54512
diff changeset
    36
      System.arraycopy(a, offset, b, 0, length)
54442
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    37
      new Bytes(b, 0, b.length)
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    38
    }
c39972ddd672 more specific Protocol_Output: empty message.body, main content via bytes/text;
wenzelm
parents: 54440
diff changeset
    39
69454
ef051edd4d10 more uniform multi-language operations;
wenzelm
parents: 69448
diff changeset
    40
  val newline: Bytes = apply("\n")
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    41
73576
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    42
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    43
  /* base64 */
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    44
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
    45
  def base64(s: String): Bytes = {
68108
2277fe496d78 more operations;
wenzelm
parents: 68106
diff changeset
    46
    val a = Base64.getDecoder.decode(s)
2277fe496d78 more operations;
wenzelm
parents: 68106
diff changeset
    47
    new Bytes(a, 0, a.length)
2277fe496d78 more operations;
wenzelm
parents: 68106
diff changeset
    48
  }
2277fe496d78 more operations;
wenzelm
parents: 68106
diff changeset
    49
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
    50
  object Decode_Base64 extends Scala.Fun("decode_base64") {
73576
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    51
    val here = Scala_Project.here
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    52
    def invoke(args: List[Bytes]): List[Bytes] =
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    53
      List(base64(Library.the_single(args).text))
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    54
  }
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    55
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
    56
  object Encode_Base64 extends Scala.Fun("encode_base64") {
73576
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    57
    val here = Scala_Project.here
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    58
    def invoke(args: List[Bytes]): List[Bytes] =
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    59
      List(Bytes(Library.the_single(args).base64))
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    60
  }
b50f8cc8c08e support for base64 via Isabelle/Scala/ML;
wenzelm
parents: 73561
diff changeset
    61
68087
dac267cd51fe hexadecimal representation of byte string;
wenzelm
parents: 68018
diff changeset
    62
75579
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    63
  /* XZ compression */
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    64
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    65
  object Compress extends Scala.Fun("compress") {
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    66
    val here = Scala_Project.here
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    67
    def invoke(args: List[Bytes]): List[Bytes] =
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    68
      List(Library.the_single(args).compress())
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    69
  }
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    70
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    71
  object Uncompress extends Scala.Fun("uncompress") {
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    72
    val here = Scala_Project.here
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    73
    def invoke(args: List[Bytes]): List[Bytes] =
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    74
      List(Library.the_single(args).uncompress())
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    75
  }
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    76
3362b6a5d697 support XZ compression in Isabelle/ML;
wenzelm
parents: 75393
diff changeset
    77
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    78
  /* read */
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    79
64005
f6e965cf1617 clarified magic values (see also java/io/BufferedInputStream.java);
wenzelm
parents: 64004
diff changeset
    80
  def read_stream(stream: InputStream, limit: Int = Integer.MAX_VALUE, hint: Int = 1024): Bytes =
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    81
    if (limit == 0) empty
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    82
    else {
73414
7411d71b9fb8 more robust;
wenzelm
parents: 73024
diff changeset
    83
      val out_size = (if (limit == Integer.MAX_VALUE) hint else limit) max 1024
7411d71b9fb8 more robust;
wenzelm
parents: 73024
diff changeset
    84
      val out = new ByteArrayOutputStream(out_size)
64005
f6e965cf1617 clarified magic values (see also java/io/BufferedInputStream.java);
wenzelm
parents: 64004
diff changeset
    85
      val buf = new Array[Byte](8192)
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    86
      var m = 0
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    87
75382
81673c441ce3 tuned: eliminted do-while for the sake of scala3;
wenzelm
parents: 73576
diff changeset
    88
      var cont = true
81673c441ce3 tuned: eliminted do-while for the sake of scala3;
wenzelm
parents: 73576
diff changeset
    89
      while (cont) {
73554
wenzelm
parents: 73414
diff changeset
    90
        m = stream.read(buf, 0, buf.length min (limit - out.size))
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    91
        if (m != -1) out.write(buf, 0, m)
75382
81673c441ce3 tuned: eliminted do-while for the sake of scala3;
wenzelm
parents: 73576
diff changeset
    92
        cont = (m != -1 && limit > out.size)
81673c441ce3 tuned: eliminted do-while for the sake of scala3;
wenzelm
parents: 73576
diff changeset
    93
      }
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    94
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
    95
      new Bytes(out.toByteArray, 0, out.size)
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
    96
    }
64001
7ecb22be8f03 more general read_stream: return actual byte count;
wenzelm
parents: 63779
diff changeset
    97
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
    98
  def read(file: JFile): Bytes = {
71152
f2d848a596d1 more robust: file length can be invalid in odd situations;
wenzelm
parents: 71151
diff changeset
    99
    val length = file.length
f2d848a596d1 more robust: file length can be invalid in odd situations;
wenzelm
parents: 71151
diff changeset
   100
    val limit = if (length < 0 || length > Integer.MAX_VALUE) Integer.MAX_VALUE else length.toInt
f2d848a596d1 more robust: file length can be invalid in odd situations;
wenzelm
parents: 71151
diff changeset
   101
    using(new FileInputStream(file))(read_stream(_, limit = limit))
f2d848a596d1 more robust: file length can be invalid in odd situations;
wenzelm
parents: 71151
diff changeset
   102
  }
64229
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   103
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   104
  def read(path: Path): Bytes = read(path.file)
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   105
65070
1222c010bff7 more operations;
wenzelm
parents: 64370
diff changeset
   106
  def read(url: URL): Bytes = using(url.openStream)(read_stream(_))
1222c010bff7 more operations;
wenzelm
parents: 64370
diff changeset
   107
64229
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   108
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   109
  /* write */
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   110
69393
ed0824ef337e static type for Library.using: avoid Java 11 warnings on "Illegal reflective access";
wenzelm
parents: 69365
diff changeset
   111
  def write(file: JFile, bytes: Bytes): Unit =
ed0824ef337e static type for Library.using: avoid Java 11 warnings on "Illegal reflective access";
wenzelm
parents: 69365
diff changeset
   112
    using(new FileOutputStream(file))(bytes.write_stream(_))
64229
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   113
12aa3980f65c more operations;
wenzelm
parents: 64224
diff changeset
   114
  def write(path: Path, bytes: Bytes): Unit = write(path.file, bytes)
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   115
}
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   116
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   117
final class Bytes private(
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   118
  protected val bytes: Array[Byte],
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   119
  protected val offset: Int,
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   120
  val length: Int) extends CharSequence {
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   121
  /* equality */
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   122
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   123
  override def equals(that: Any): Boolean = {
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   124
    that match {
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   125
      case other: Bytes =>
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   126
        if (this eq other) true
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   127
        else if (length != other.length) false
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   128
        else (0 until length).forall(i => bytes(offset + i) == other.bytes(other.offset + i))
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   129
      case _ => false
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   130
    }
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   131
  }
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   132
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   133
  private lazy val hash: Int = {
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   134
    var h = 0
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   135
    for (i <- offset until offset + length) {
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   136
      val b = bytes(i).asInstanceOf[Int] & 0xFF
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   137
      h = 31 * h + b
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   138
    }
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   139
    h
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   140
  }
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   141
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   142
  override def hashCode(): Int = hash
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   143
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   144
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   145
  /* content */
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   146
54512
7a92ed889da4 persistent value;
wenzelm
parents: 54444
diff changeset
   147
  lazy val sha1_digest: SHA1.Digest = SHA1.digest(bytes)
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   148
69448
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   149
  def is_empty: Boolean = length == 0
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   150
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   151
  def iterator: Iterator[Byte] =
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   152
    for (i <- (offset until (offset + length)).iterator)
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   153
      yield bytes(i)
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   154
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   155
  def array: Array[Byte] = {
69365
c5b3860d29ef avoid loading of font file, to eliminate "Illegal reflective access by com.lowagie.text.pdf.MappedRandomAccessFile$1 (iText-2.1.5.jar) to method java.nio.DirectByteBuffer.cleaner()" -- due to com.lowagie.text.pdf.TrueTypeFont.process() / RandomAccessFileOrArray;
wenzelm
parents: 68167
diff changeset
   156
    val a = new Array[Byte](length)
c5b3860d29ef avoid loading of font file, to eliminate "Illegal reflective access by com.lowagie.text.pdf.MappedRandomAccessFile$1 (iText-2.1.5.jar) to method java.nio.DirectByteBuffer.cleaner()" -- due to com.lowagie.text.pdf.TrueTypeFont.process() / RandomAccessFileOrArray;
wenzelm
parents: 68167
diff changeset
   157
    System.arraycopy(bytes, offset, a, 0, length)
c5b3860d29ef avoid loading of font file, to eliminate "Illegal reflective access by com.lowagie.text.pdf.MappedRandomAccessFile$1 (iText-2.1.5.jar) to method java.nio.DirectByteBuffer.cleaner()" -- due to com.lowagie.text.pdf.TrueTypeFont.process() / RandomAccessFileOrArray;
wenzelm
parents: 68167
diff changeset
   158
    a
c5b3860d29ef avoid loading of font file, to eliminate "Illegal reflective access by com.lowagie.text.pdf.MappedRandomAccessFile$1 (iText-2.1.5.jar) to method java.nio.DirectByteBuffer.cleaner()" -- due to com.lowagie.text.pdf.TrueTypeFont.process() / RandomAccessFileOrArray;
wenzelm
parents: 68167
diff changeset
   159
  }
c5b3860d29ef avoid loading of font file, to eliminate "Illegal reflective access by com.lowagie.text.pdf.MappedRandomAccessFile$1 (iText-2.1.5.jar) to method java.nio.DirectByteBuffer.cleaner()" -- due to com.lowagie.text.pdf.TrueTypeFont.process() / RandomAccessFileOrArray;
wenzelm
parents: 68167
diff changeset
   160
73561
c83152933579 clarified signature: Bytes extends CharSequence already (see d201996f72a8);
wenzelm
parents: 73559
diff changeset
   161
  def text: String = UTF8.decode_permissive(this)
65279
fa62e095d8f1 clarified signature (again, see also 3ed43cfc8b14);
wenzelm
parents: 65070
diff changeset
   162
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   163
  def base64: String = {
68094
0b66aca9c965 more operations;
wenzelm
parents: 68087
diff changeset
   164
    val b =
0b66aca9c965 more operations;
wenzelm
parents: 68087
diff changeset
   165
      if (offset == 0 && length == bytes.length) bytes
0b66aca9c965 more operations;
wenzelm
parents: 68087
diff changeset
   166
      else Bytes(bytes, offset, length).bytes
0b66aca9c965 more operations;
wenzelm
parents: 68087
diff changeset
   167
    Base64.getEncoder.encodeToString(b)
0b66aca9c965 more operations;
wenzelm
parents: 68087
diff changeset
   168
  }
0b66aca9c965 more operations;
wenzelm
parents: 68087
diff changeset
   169
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   170
  def maybe_base64: (Boolean, String) = {
68106
a514e29db980 return exports as result for Isabelle server;
wenzelm
parents: 68094
diff changeset
   171
    val s = text
a514e29db980 return exports as result for Isabelle server;
wenzelm
parents: 68094
diff changeset
   172
    if (this == Bytes(s)) (false, s) else (true, base64)
a514e29db980 return exports as result for Isabelle server;
wenzelm
parents: 68094
diff changeset
   173
  }
a514e29db980 return exports as result for Isabelle server;
wenzelm
parents: 68094
diff changeset
   174
68150
f0f34cbed539 clarified output: avoid costly operations on huge blobs;
wenzelm
parents: 68149
diff changeset
   175
  override def toString: String = "Bytes(" + length + ")"
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   176
72885
1b0f81e556a2 accommodate OpenJDK 15;
wenzelm
parents: 71152
diff changeset
   177
  def proper: Option[Bytes] = if (is_empty) None else Some(this)
1b0f81e556a2 accommodate OpenJDK 15;
wenzelm
parents: 71152
diff changeset
   178
  def proper_text: Option[String] = if (is_empty) None else Some(text)
65630
c41bbf657310 more operations;
wenzelm
parents: 65279
diff changeset
   179
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   180
  def +(other: Bytes): Bytes =
72885
1b0f81e556a2 accommodate OpenJDK 15;
wenzelm
parents: 71152
diff changeset
   181
    if (other.is_empty) this
1b0f81e556a2 accommodate OpenJDK 15;
wenzelm
parents: 71152
diff changeset
   182
    else if (is_empty) other
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   183
    else {
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   184
      val new_bytes = new Array[Byte](length + other.length)
55618
995162143ef4 tuned imports;
wenzelm
parents: 54512
diff changeset
   185
      System.arraycopy(bytes, offset, new_bytes, 0, length)
995162143ef4 tuned imports;
wenzelm
parents: 54512
diff changeset
   186
      System.arraycopy(other.bytes, other.offset, new_bytes, length, other.length)
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   187
      new Bytes(new_bytes, 0, new_bytes.length)
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   188
    }
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   189
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   190
60833
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   191
  /* CharSequence operations */
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   192
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   193
  def charAt(i: Int): Char =
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   194
    if (0 <= i && i < length) (bytes(offset + i).asInstanceOf[Int] & 0xFF).asInstanceOf[Char]
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   195
    else throw new IndexOutOfBoundsException
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   196
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   197
  def subSequence(i: Int, j: Int): Bytes = {
60833
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   198
    if (0 <= i && i <= j && j <= length) new Bytes(bytes, offset + i, j - i)
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   199
    else throw new IndexOutOfBoundsException
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   200
  }
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   201
69448
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   202
  def trim_line: Bytes =
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   203
    if (length >= 2 && charAt(length - 2) == 13 && charAt(length - 1) == 10)
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   204
      subSequence(0, length - 2)
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   205
    else if (length >= 1 && (charAt(length - 1) == 13 || charAt(length - 1) == 10))
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   206
      subSequence(0, length - 1)
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   207
    else this
51e696887b81 more uniform multi-language operations;
wenzelm
parents: 69393
diff changeset
   208
60833
d201996f72a8 provide CharSequence operations as well;
wenzelm
parents: 55618
diff changeset
   209
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   210
  /* streams */
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   211
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   212
  def stream(): ByteArrayInputStream = new ByteArrayInputStream(bytes, offset, length)
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   213
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   214
  def write_stream(stream: OutputStream): Unit = stream.write(bytes, offset, length)
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   215
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   216
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   217
  /* XZ data compression */
54440
2c4940d2edf7 tuned signature;
wenzelm
parents: 54439
diff changeset
   218
73024
337e1b135d2f clarified signature --- internal Cache.none;
wenzelm
parents: 72885
diff changeset
   219
  def uncompress(cache: XZ.Cache = XZ.Cache()): Bytes =
68018
3747fe57eb67 support for XZ.Cache;
wenzelm
parents: 67805
diff changeset
   220
    using(new XZInputStream(stream(), cache))(Bytes.read_stream(_, hint = length))
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   221
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   222
  def compress(options: XZ.Options = XZ.options(), cache: XZ.Cache = XZ.Cache()): Bytes = {
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   223
    val result = new ByteArrayOutputStream(length)
68018
3747fe57eb67 support for XZ.Cache;
wenzelm
parents: 67805
diff changeset
   224
    using(new XZOutputStream(result, options, cache))(write_stream(_))
64004
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   225
    new Bytes(result.toByteArray, 0, result.size)
b4ece7a3f2ca clarified stream operations;
wenzelm
parents: 64001
diff changeset
   226
  }
68167
327bb0f5f768 clarified implicit compression;
wenzelm
parents: 68150
diff changeset
   227
75393
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   228
  def maybe_compress(
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   229
    options: XZ.Options = XZ.options(),
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   230
    cache: XZ.Cache = XZ.Cache()
87ebf5a50283 clarified formatting, for the sake of scala3;
wenzelm
parents: 75382
diff changeset
   231
  ) : (Boolean, Bytes) = {
68167
327bb0f5f768 clarified implicit compression;
wenzelm
parents: 68150
diff changeset
   232
    val compressed = compress(options = options, cache = cache)
327bb0f5f768 clarified implicit compression;
wenzelm
parents: 68150
diff changeset
   233
    if (compressed.length < length) (true, compressed) else (false, this)
327bb0f5f768 clarified implicit compression;
wenzelm
parents: 68150
diff changeset
   234
  }
54439
621a155c7715 immutable byte vectors versus UTF8 strings;
wenzelm
parents:
diff changeset
   235
}