Commonize text encoding

The library now performs its own text encoding, removing the dependency on platform utilities.

README.md

@@ -38,12 +38,12 @@ suspend fun awaitPrint(): MyError? {
   val libraryError: PrintError? = connection.print(configuration) {       // (2)
     // MULTIPLE TEXT ALIGNMENTS PER LINE
     line("Famous bridges:")
-    charset(Charset.CP865) // Can encode Ø, but not ů
+    charset(IBM865) // Can encode Ø, but not ů
     segmentedLine(
       LineSegment("Øresundsbroen", TextAlignment.LEFT),
       LineSegment("7845m", TextAlignment.RIGHT),
     )
-    charset(Charset.CP852) // Can encode ů, but not Ø
+    charset(IBM852) // Can encode ů, but not Ø
     segmentedLine(
       LineSegment("Karlův most", TextAlignment.LEFT),
       LineSegment("515m", TextAlignment.RIGHT),

escpos4k/src/commonMain/kotlin/cz/multiplatform/escpos4k/core/Command.kt

@@ -16,11 +16,14 @@
 
 package cz.multiplatform.escpos4k.core
 
+import cz.multiplatform.escpos4k.core.encoding.charset.Charset
+import cz.multiplatform.escpos4k.core.encoding.encode
+
 internal sealed class Command {
   abstract fun bytes(): ByteArray
 
   class Text(private val text: String, charset: Charset) : Command() {
-    private val encodedBytes: ByteArray by lazy { encode(text, charset) }
+    private val encodedBytes: ByteArray by lazy { text.encode(charset) }
 
     override fun bytes(): ByteArray = encodedBytes.copyOf()
 

escpos4k/src/commonMain/kotlin/cz/multiplatform/escpos4k/core/CommandBuilder.kt

@@ -20,6 +20,7 @@ import arrow.core.Nel
 import arrow.core.nonEmptyListOf
 import arrow.core.toNonEmptyListOrNull
 import cz.multiplatform.escpos4k.core.LineDistributionStrategy.Companion.SpaceEvenly
+import cz.multiplatform.escpos4k.core.encoding.charset.Charset
 
 /**
  * The central class for building the content to send to the printer. The class provides a variety
@@ -43,9 +44,9 @@ import cz.multiplatform.escpos4k.core.LineDistributionStrategy.Companion.SpaceEv
  * val builder = CommandBuilder(defaultConfig) {
  *   // Charsets
  *   line("Famous bridges:")
- *   charset(Charset.CP865) // Can encode Ø, but not ů
+ *   charset(IBM865) // Can encode Ø, but not ů
  *   line("Øresundsbroen: 7845m")
- *   charset(Charset.CP852) // Can encode ů, but not Ø
+ *   charset(IBM852) // Can encode ů, but not Ø
  *   line("Karlův most: 515m")
  *
  *   // Text style - temporary style builder
@@ -162,10 +163,10 @@ public class CommandBuilder(
    * printer.print {
    *   line("Famous bridges:")
    *
-   *   charset(Charset.CP865) // Can encode Ø, but not ů
+   *   charset(IBM865) // Can encode Ø, but not ů
    *   line("Øresundsbroen: 7845m")
    *
-   *   charset(Charset.CP852) // Can encode ů, but not Ø
+   *   charset(IBM852) // Can encode ů, but not Ø
    *   line("Karlův most: 515m")
    * }
    * ```
@@ -192,10 +193,10 @@ public class CommandBuilder(
    *   line("Famous bridges")
    *
    *   // 865 can encode Ø, but not ů
-   *   charset(Charset.CP865)
+   *   charset(IBM865)
    *   line("Øresundsbroen: 7845m")
    *
-   *   withCharset(Charset.CP852) {
+   *   withCharset(IBM852) {
    *     // 852 can encode ů, but not Ø
    *     line("Karlův most: 515m")
    *   }

escpos4k/src/commonMain/kotlin/cz/multiplatform/escpos4k/core/encoding/Encoder.kt

@@ -0,0 +1,63 @@
+/*
+ *    Copyright 2024 Ondřej Karmazín
+ *
+ *    Licensed 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.
+ */
+
+package cz.multiplatform.escpos4k.core.encoding
+
+import cz.multiplatform.escpos4k.core.encoding.charset.Charset
+
+private const val replacement = '?'
+private const val replacementByte = replacement.code.toByte()
+
+internal fun String.encode(charset: Charset): ByteArray {
+  val output = ByteArray(length)
+
+  for ((index, char) in this.withIndex()) {
+    val byte: Byte =
+        when {
+          // 0..31 are control characters, always replaced
+          char.code < 32 -> {
+            log("Replacing control character '${char.code}' at index $index with '$replacement'.")
+            replacementByte
+          }
+
+          // Printable ASCII up to 127
+          char.code < 128 -> {
+            char.code.toByte()
+          }
+
+          // Page-specific characters
+          else -> {
+            val byte = charset.mapping[char]?.toByte()
+            if (byte == null) {
+              log(
+                  "[${charset.ianaName}] Replacing unmappable code unit '${char.code}' at index $index with '$replacement'")
+            }
+            byte ?: replacementByte
+          }
+        }
+
+    output[index] = byte
+  }
+
+  return output
+}
+
+private fun log(msg: String) {
+  val debug = false
+  if (debug) {
+    println(msg)
+  }
+}