Implemented parsing CEF (EU) genericode Code Lists to Kotlin enum classes
This commit is contained in:
parent
b9d75a6423
commit
b47ee96183
|
|
@ -0,0 +1,75 @@
|
|||
|
||||
## Sources
|
||||
|
||||
Sources of Code Lists according to XRechnung specification p. 105, enhanced by information from [EN16931 code lists file](https://ec.europa.eu/digital-building-blocks/sites/display/DIGITAL/Registry+of+supporting+artefacts+to+implement+EN16931)
|
||||
|
||||
| Name | Beschreibung | Version | XRepository Versionskennung und Link | Usage | Using in fields |
|
||||
|--------------|----------------------------------------------------------------------------------------------------|---------|-----------------------------------------------|-----------|-------------------------------------------------------------------------|
|
||||
| ISO 3166-1 | Country codes (kompatibel zu ISO 3166-1) | 2022 | urn:xoev-de:kosit:codeliste:country-codes_8 | extended | BT-40, BT-55, BT-69, BT-80, BT-159 |
|
||||
| ISO 4217 | Currency codes (kompatibel zu ISO 4217) | 2021 | urn:xoev-de:kosit:codeliste:currency-codes_3 | full list | BT-5, BT-6 |
|
||||
| ISO/IEC 6523 | ICD — Identifier scheme code (kompatibel zu ISO 6523) | 2023 | urn:xoev-de:kosit:codeliste:icd_5 | full list | BT-29-1, BT-30-1, BT-46-1, BT-47-1, BT-60-1, BT-61-1, BT-71-1, BT-157-1 |
|
||||
| UNTDID 1001 | Document name coded | 21a | urn:xoev-de:kosit:codeliste:untdid.1001_4 | subset | BT-3 |
|
||||
| UNTDID 1153 | Reference code qualifier | d20a | urn:xoev-de:kosit:codeliste:untdid.1153_3 | full list | BT-18-1, BT-128-1 |
|
||||
| UNTDID 2005 | Date or time or period function code qualifier | d21a | urn:xoev-de:kosit:codeliste:untdid.2005_4 | subset | BT-8 |
|
||||
| UNTDID 4451 | Text subject code qualifier | d21a | urn:xoev-de:kosit:codeliste:untdid.4451_4 | full list | BT-21 |
|
||||
| UNTDID 4461 | Payment means coded | d20a | urn:xoev-de:xrechnung:codeliste:untdid.4461_3 | full list | BT-81 |
|
||||
| UNTDID 5189 | Allowance or charge identification coded | d20a | urn:xoev-de:kosit:codeliste:untdid.5189_3 | subset | BT-98, BT-140 |
|
||||
| UNTDID 5305 | Duty or tax or fee category coded | d20a | urn:xoev-de:kosit:codeliste:untdid.5305_3 | subset | BT-95, BT-102, BT-118, BT-151 |
|
||||
| UNTDID 7143 | Item type identification coded | d21a | urn:xoev-de:kosit:codeliste:untdid.7143_4 | full list | BT-158-1 |
|
||||
| UNTDID 7161 | Special service description coded | d20a | urn:xoev-de:kosit:codeliste:untdid.7161_3 | full list | BT-105, BT-145 |
|
||||
| EAS | Electronic Address Scheme Code list | 9.0 | urn:xoev-de:kosit:codeliste:eas_5 | full list | BT-34-1, BT-49-1 |
|
||||
| VATEX | VAT exemption reason code list | 4.0 | urn:xoev-de:kosit:codeliste:vatex_1 | full list | BT-121 |
|
||||
| Rec 20 | UN/EC Recommendation Nº20 – Codes for Units of Measure Used in International Trade | Rev. 17 | urn:xoev-de:kosit:codeliste:rec20_3 | full list | BT-130, BT-150 |
|
||||
| Rec 21 | UN/EC Recommendation Nº21 – Codes for Passengers, Types of Cargo, Packages and Packaging Materials | Rev. 12 | urn:xoev-de:kosit:codeliste:rec21_3 | full list | BT-130, BT-150 |
|
||||
| VAT ID | VAT Identifier; has only code "VAT" for Value added tax; code list only in EN Excel file | | | subset | BT-31, BT-48, BT-63 |
|
||||
| VAT Cat | VAT Category code; has only code "VAT" for Value added tax; code list only in EN Excel file | | | subset | BT-95, BT-102, BT-118, BT-151 |
|
||||
| MIME | Mime type codes — Mime codes; code list only in EN Excel file | | | subset | BT-125-1 |
|
||||
|
||||
|
||||
## Einschätzung zu Quellen
|
||||
|
||||
### EN / CEF Genericode Code Listen
|
||||
|
||||
URL: https://ec.europa.eu/digital-building-blocks/sites/display/DIGITAL/Registry+of+supporting+artefacts+to+implement+EN16931
|
||||
|
||||
\+ good to parse
|
||||
|
||||
\- no descriptions
|
||||
\- only English names
|
||||
|
||||
|
||||
### UNTDID
|
||||
|
||||
URL e.g.: https://unece.org/fileadmin/DAM/trade/untdid/d16b/tred/tred1001.htm
|
||||
|
||||
\+ incl. Engl. descriptions
|
||||
|
||||
\- difficult to parse, plain text only (on a website!)
|
||||
\- only English names and descriptions
|
||||
\- partially more codes than XRechnung standard allows
|
||||
|
||||
|
||||
### Factur-X / ZUGFeRD Code Lists .xslx
|
||||
|
||||
Download .zip from: https://www.ferd-net.de/standards/zugferd-2.3.2/zugferd-2.3.2.html?acceptCookie=1
|
||||
|
||||
\+ alle code lists in one file
|
||||
\+ incl. Engl. descriptions and invoice fields in which codes are used
|
||||
|
||||
\- difficult to parse
|
||||
|
||||
|
||||
### UNECE Rec. 20 & 21
|
||||
|
||||
Recommendation 20 Codes for Units of Measure Used in International Trade
|
||||
|
||||
Recommendation 21 Codes for Passengers, Types of Cargo, Packages and Packaging Materials (with Complementary Codes for Package Names)
|
||||
|
||||
URL: https://unece.org/trade/uncefact/cl-recommendations
|
||||
|
||||
\+ good to parse
|
||||
\+ incl. Engl. descriptions
|
||||
\+ incl. unit symbols
|
||||
|
||||
\- only units, no other code lists
|
||||
\- only English names and descriptions
|
||||
|
|
@ -0,0 +1,36 @@
|
|||
plugins {
|
||||
kotlin("jvm")
|
||||
}
|
||||
|
||||
|
||||
kotlin {
|
||||
jvmToolchain(11)
|
||||
}
|
||||
|
||||
|
||||
val phGenericodeVersion: String by project
|
||||
|
||||
val klfVersion: String by project
|
||||
|
||||
val assertKVersion: String by project
|
||||
val logbackVersion: String by project
|
||||
|
||||
dependencies {
|
||||
implementation(project(":e-invoice-domain"))
|
||||
|
||||
implementation("com.helger:ph-genericode:$phGenericodeVersion")
|
||||
|
||||
implementation("net.codinux.log:klf:$klfVersion")
|
||||
|
||||
|
||||
testImplementation(kotlin("test"))
|
||||
|
||||
testImplementation("com.willowtreeapps.assertk:assertk:$assertKVersion")
|
||||
|
||||
testImplementation("ch.qos.logback:logback-classic:$logbackVersion")
|
||||
}
|
||||
|
||||
|
||||
tasks.test {
|
||||
useJUnitPlatform()
|
||||
}
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
package net.codinux.invoicing.app
|
||||
|
||||
import net.codinux.invoicing.parser.CodeGenerator
|
||||
import net.codinux.invoicing.parser.genericode.CefGenericodeCodelistsParser
|
||||
import java.io.File
|
||||
|
||||
fun main() {
|
||||
CefGenericodeCodelistsParserApp().parseCefGenericodeLists()
|
||||
}
|
||||
|
||||
class CefGenericodeCodelistsParserApp {
|
||||
|
||||
fun parseCefGenericodeLists() {
|
||||
val zipFile = File(javaClass.classLoader.getResource("codeLists/cef-genericodes-2024-11-15.zip")!!.toURI())
|
||||
|
||||
val codeLists = CefGenericodeCodelistsParser().parse(zipFile)
|
||||
|
||||
var outputDirectoryBasePath = zipFile.parentFile.parentFile.absolutePath.replace("e-invoice-spec-parser", "e-invoice-domain")
|
||||
if (outputDirectoryBasePath.contains("/build/resources/main")) {
|
||||
outputDirectoryBasePath = outputDirectoryBasePath.replace("/build/resources/main", "/src/main")
|
||||
}
|
||||
val outputDirectory = File(outputDirectoryBasePath, "kotlin/net/codinux/invoicing/model/codes")
|
||||
|
||||
CodeGenerator().generateCodeFiles(codeLists, outputDirectory)
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,54 @@
|
|||
package net.codinux.invoicing.parser
|
||||
|
||||
import net.codinux.invoicing.parser.genericode.CodeList
|
||||
import net.codinux.invoicing.parser.genericode.Column
|
||||
import java.io.File
|
||||
|
||||
class CodeGenerator {
|
||||
|
||||
fun generateCodeFiles(codeLists: List<CodeList>, outputDirectory: File) {
|
||||
codeLists.forEach { codeList ->
|
||||
File(outputDirectory, codeList.name + ".kt").bufferedWriter().use { writer ->
|
||||
writer.appendLine("package net.codinux.invoicing.model.codes")
|
||||
writer.newLine()
|
||||
writer.appendLine("enum class ${getClassName(codeList)}(${codeList.columns.joinToString(", ") { "val ${getPropertyName(it)}: ${getDataType(codeList, it)}" } }) {")
|
||||
|
||||
codeList.rows.forEach { row ->
|
||||
writer.appendLine("\t${getEnumName(codeList.columns, row)}(${row.joinToString(", ") { it?.let { "\"${it.replace("\n", "")}\"" } ?: "null" } }),")
|
||||
}
|
||||
writer.appendLine("}")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
private fun getClassName(codeList: CodeList): String {
|
||||
val name = codeList.name
|
||||
return if (name[0].isDigit()) "_" + name
|
||||
else name
|
||||
}
|
||||
|
||||
private fun getPropertyName(column: Column): String = when (column.name) {
|
||||
"Unique code" -> "uniqueCode"
|
||||
"Meaning of the code" -> "meaningOfTheCode"
|
||||
"Optional remark for the usage of this code" -> "optionalRemarkForTheUsageOfTheCode"
|
||||
else -> column.name.replace(" ", "")
|
||||
}
|
||||
|
||||
private fun getDataType(codeList: CodeList, column: Column): String {
|
||||
val index = codeList.columns.indexOf(column)
|
||||
val containsNullValues = codeList.rows.any { it[index] == null }
|
||||
|
||||
return when (column.dataType) {
|
||||
"string" -> "String" + (if (containsNullValues) "?" else "")
|
||||
else -> column.dataType[0].uppercase() + column.dataType.substring(1).replace(" ", "")
|
||||
}
|
||||
}
|
||||
|
||||
private fun getEnumName(columns: List<Column>, row: List<String?>): String {
|
||||
val name = (row[0] ?: "").replace(' ', '_').replace('/', '_').replace('.', '_').replace('-', '_')
|
||||
return if (name[0].isDigit()) "_" + name
|
||||
else name
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,74 @@
|
|||
package net.codinux.invoicing.parser.genericode
|
||||
|
||||
import com.helger.genericode.Genericode10CodeListMarshaller
|
||||
import com.helger.xml.serialize.read.DOMReader
|
||||
import net.codinux.invoicing.parser.model.CodeListType
|
||||
import net.codinux.invoicing.parser.model.Column
|
||||
import net.codinux.log.logger
|
||||
import java.io.File
|
||||
import java.io.InputStream
|
||||
import java.util.zip.ZipFile
|
||||
|
||||
class CefGenericodeCodelistsParser {
|
||||
|
||||
private val log by logger()
|
||||
|
||||
|
||||
fun parse(zipFile: File): List<CodeList> =
|
||||
ZipFile(zipFile).use { zip ->
|
||||
zip.entries().toList().filter { it.isDirectory == false && it.name.endsWith(".gc", true) }
|
||||
.mapNotNull { parse(zip.getInputStream(it), it.name) }
|
||||
}
|
||||
|
||||
private fun parse(genericodeInputStream: InputStream, filename: String): CodeList? {
|
||||
val doc = DOMReader.readXMLDOM(genericodeInputStream)
|
||||
val marshaller = Genericode10CodeListMarshaller()
|
||||
|
||||
if (doc == null) {
|
||||
log.info { "Could not read XML document from file $filename" }
|
||||
return null
|
||||
}
|
||||
|
||||
val codeListDoc = marshaller.read(doc)
|
||||
if (codeListDoc == null) {
|
||||
log.info { "Could not read Code List from file $filename" }
|
||||
return null
|
||||
}
|
||||
|
||||
val columnSet = codeListDoc.columnSet
|
||||
val identification = codeListDoc.identification
|
||||
val simpleCodeList = codeListDoc.simpleCodeList
|
||||
|
||||
val name = File(filename).nameWithoutExtension
|
||||
val (version, canonicalUri, canonicalVersionUri) = Triple(identification?.version, identification?.canonicalUri, identification?.canonicalVersionUri)
|
||||
val columns = columnSet?.columnChoice.orEmpty().filterIsInstance<com.helger.genericode.v10.Column>().mapIndexed { index, col -> Column(index, col.id!!, col.data?.type!!, col.shortNameValue!!) }
|
||||
val rows = simpleCodeList?.row.orEmpty().map { row -> columns.map { column -> row.value.firstOrNull { (it.columnRef as? com.helger.genericode.v10.Column)?.id == column.id }?.simpleValueValue } }
|
||||
|
||||
return CodeList(getType(name), name, version, canonicalUri, canonicalVersionUri, columns, rows)
|
||||
}
|
||||
|
||||
private fun getType(name: String): CodeListType = when (name) {
|
||||
"Country" -> CodeListType.IsoCountryCodes
|
||||
"Currency" -> CodeListType.IsoCurrencyCodes
|
||||
"ICD" -> CodeListType.Iso_6523_IdentificationSchemeIdentifier
|
||||
|
||||
"1001" -> CodeListType.UN_1001_InvoiceType
|
||||
"1153" -> CodeListType.UN_1153_ReferenceCode
|
||||
|
||||
"Text" -> CodeListType.UN_4451_TextSubjectCodeQualifier
|
||||
"Payment" -> CodeListType.UN_4461_PaymentCodes
|
||||
"5305" -> CodeListType.UN_5305_DutyOrTaxOrFeeCategory
|
||||
"Allowance" -> CodeListType.UN_5189_AllowanceIdentificationCode
|
||||
"Item" -> CodeListType.UN_7143_ItemTypeIdentificationCode
|
||||
"Charge" -> CodeListType.UN_7161_SpecialServiceDescriptionCodes
|
||||
|
||||
"Unit" -> CodeListType.Units
|
||||
|
||||
"EAS" -> CodeListType.EAS
|
||||
"VATEX" -> CodeListType.VATEX
|
||||
"MIME" -> CodeListType.Mime
|
||||
|
||||
else -> throw IllegalArgumentException("No known Code List of name '$name' found")
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
package net.codinux.invoicing.parser.genericode
|
||||
|
||||
import net.codinux.invoicing.parser.model.CodeListType
|
||||
import net.codinux.invoicing.parser.model.Column
|
||||
|
||||
class CodeList(
|
||||
val type: CodeListType,
|
||||
val name: String,
|
||||
val version: String?,
|
||||
val canonicalUri: String?,
|
||||
val canonicalVersionUri: String?,
|
||||
val columns: List<Column>,
|
||||
val rows: List<List<String?>>
|
||||
) {
|
||||
override fun toString() = "$name ${columns.joinToString { it.name }}, ${rows.size} rows"
|
||||
}
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
package net.codinux.invoicing.parser.model
|
||||
|
||||
enum class CodeListType(val filename: String, val usesFullList: Boolean, val usedInFields: List<String>) {
|
||||
IsoCountryCodes("Country", true, listOf("BT-40", "BT-48", "BT-55", "BT-63", "BT-69", "BT-80", "BT-159")), // actually it's not only the full list, it's "extended"
|
||||
IsoCurrencyCodes("Currency", true, listOf("BT-5", "BT-6")),
|
||||
Iso_6523_IdentificationSchemeIdentifier("IdentifierSchemeCode", true, listOf("BT-29-1", "BT-30-1", "BT-46-1", "BT-47-1", "BT-60-1", "BT-61-1", "BT-71-1", "BT-157-1")), // = ICD
|
||||
|
||||
UN_1001_InvoiceType("InvoiceType", false, listOf("BT-3")), // original name: Document type,
|
||||
UN_1153_ReferenceCode("ReferenceCode", true, listOf("BT-18-1", "BT-128-1")),
|
||||
UN_2005_2475_EventTimeCode("TimeReferenceCode", false, listOf("BT-8")), // code list only in EN Excel file
|
||||
|
||||
UN_4451_TextSubjectCodeQualifier("TextSubjectQualifier", true, listOf("BT-21")), // Text subject qualifier, tab Text
|
||||
UN_4461_PaymentCodes("PaymentMeans", true, listOf("BT-81")), // Payment means, tab Payment
|
||||
UN_5189_AllowanceIdentificationCode("AllowanceIdentificationCode", false, listOf("BT-98", "BT-140")), // tab Allowance
|
||||
UN_5305_DutyOrTaxOrFeeCategory("DutyOrTaxOrFreeCategory", false, listOf("BT-95", "BT-102", "BT-118", "BT-151")),
|
||||
UN_7143_ItemTypeIdentificationCode("ItemTypeIdentificationCode", true, listOf("BT-158-1")), // Item type identification code, tab Item, full list
|
||||
UN_7161_SpecialServiceDescriptionCodes("SpecialServiceDescriptionCode", true, listOf("BT-105", "BT-145")), // Charge codes, tab Charge
|
||||
|
||||
Units("Unit", true, listOf("BT-130", "BT-150")), // UN/ECE Recommendation N°20 and UN/ECE Recommendation N°21 — Unit codes
|
||||
|
||||
EAS("ElectronicAddressSchemeIdentifier", true, listOf("BT-34-1", "BT-49-1")), // Electronic address scheme identifier
|
||||
VATEX("VatExemptionReasonCode", true, listOf("BT-121")), // VAT exemption reason code
|
||||
|
||||
VatIdentifier("VatIdentifier", false, listOf("BT-31", "BT-48", "BT-63")), // code list only in EN Excel file
|
||||
VatCategoryCode("VatCategoryCode", false, listOf("BT-95", "BT-102", "BT-118", "BT-151")), // code list only in EN Excel file
|
||||
Mime("Mime", false, listOf("BT-125-1")),
|
||||
}
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
package net.codinux.invoicing.parser.model
|
||||
|
||||
data class Column(
|
||||
val index: Int,
|
||||
val id: String,
|
||||
val dataType: String,
|
||||
val name: String,
|
||||
) {
|
||||
override fun toString() = "$dataType $name ($id)"
|
||||
}
|
||||
Binary file not shown.
|
|
@ -0,0 +1,32 @@
|
|||
<configuration>
|
||||
|
||||
<appender name="STDOUT" class="ch.qos.logback.core.ConsoleAppender">
|
||||
<!-- encoders are assigned the type
|
||||
ch.qos.logback.classic.encoder.PatternLayoutEncoder by default -->
|
||||
<encoder>
|
||||
<pattern>%d{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n</pattern>
|
||||
</encoder>
|
||||
|
||||
<filter class="ch.qos.logback.classic.filter.ThresholdFilter">
|
||||
<level>DEBUG</level>
|
||||
</filter>
|
||||
</appender>
|
||||
|
||||
<!-- Insert the current time formatted as "yyyyMMdd'T'HHmmss" under
|
||||
the key "bySecond" into the logger context. This value will be
|
||||
available to all subsequent configuration elements. -->
|
||||
<timestamp key="bySecond" datePattern="yyyyMMdd'T'HHmmss"/>
|
||||
|
||||
<root level="ALL">
|
||||
<appender-ref ref="STDOUT"/>
|
||||
</root>
|
||||
|
||||
<!-- Apache FOP will flood otherwise the log so that test run crashes -->
|
||||
<logger name="org.apache.fop" level="INFO">
|
||||
<appender-ref ref="STDOUT"/>
|
||||
</logger>
|
||||
<logger name="org.apache.xmlgraphics.image.loader.spi.ImageImplRegistry" level="INFO">
|
||||
<appender-ref ref="STDOUT"/>
|
||||
</logger>
|
||||
|
||||
</configuration>
|
||||
|
|
@ -26,6 +26,8 @@ angusMailVersion=2.0.3
|
|||
openHtmlToPdfVersion=1.1.22
|
||||
jsoupVersion=1.18.1
|
||||
|
||||
phGenericodeVersion=7.1.3
|
||||
|
||||
klfVersion=1.6.2
|
||||
lokiLogAppenderVersion=0.5.5
|
||||
# only used for tests
|
||||
|
|
|
|||
|
|
@ -30,4 +30,6 @@ include("e-invoice-domain")
|
|||
|
||||
include("invoice-creator")
|
||||
|
||||
include("e-invoice-spec-parser")
|
||||
|
||||
include("e-invoice-api")
|
||||
|
|
|
|||
Loading…
Reference in New Issue