chore: update dependencies

This will replace previous used filter and only includes oBDS messages without
information about tumor board information.

.github/workflows/release.yml

@@ -0,0 +1,46 @@
+name: Create release and upload assets
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  linuxbuild:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v4
+      - name: Run tests
+        run: cargo test --verbose
+      - run: make linux-package
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          draft: 'true'
+          make_latest: 'true'
+          generate_release_notes: 'true'
+          files: |
+            *linux.tar.gz
+  windowsbuild:
+    runs-on: windows-latest
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v4
+      - name: Run tests
+        run: cargo test --verbose
+      - run: make win-package
+      - name: Release
+        uses: softprops/action-gh-release@v2
+        if: startsWith(github.ref, 'refs/tags/')
+        with:
+          draft: 'true'
+          make_latest: 'true'
+          generate_release_notes: 'true'
+          files: |
+            *win64.zip

.github/workflows/test.yml

@@ -0,0 +1,22 @@
+name: "Run Tests"
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Build
+        run: cargo build --verbose
+      - name: Run tests
+        run: cargo test --verbose

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "bzkf-rwdp-check"
-version = "0.3.3"
+version = "0.4.0"
 edition = "2021"
 authors = ["Paul-Christian Volkmer <volkmer_p@ukw.de>"]
 description = "Anwendung zur Durchführung einer Plausibilitätsprüfung anhand der Daten für die BZKF Real World Data Platform."
@@ -11,11 +11,11 @@ clap = { version = "4.5", features = ["std", "help", "usage", "derive", "error-c
 console = "0.15"
 csv = "1.3"
 dialoguer = "0.11"
-itertools = "0.13"
+itertools = "0.14"
 mysql = "25.0"
 serde = { version = "1.0", features = ["derive"] }
 urlencoding = "2.1"
-regex = "1.10"
+regex = "1.11"
 
 [profile.release]
 opt-level = "s"

Makefile

@@ -16,7 +16,8 @@ win-package: win-binary-x86_64
 	cp target/x86_64-pc-windows-gnu/release/$(PROG_NAME).exe $(PROG_NAME)/
 	cp README.md $(PROG_NAME)/
 	cp LICENSE $(PROG_NAME)/
-	zip $(PROG_NAME)-$(TAG)_win64.zip $(PROG_NAME)/*
+	# first try (linux) zip command, then powershell sub command to create ZIP file
+	zip $(PROG_NAME)-$(TAG)_win64.zip $(PROG_NAME)/* || powershell Compress-ARCHIVE $(PROG_NAME) $(PROG_NAME)-$(TAG)_win64.zip
 	rm -rf $(PROG_NAME) || true
 
 .PHONY: linux-package

README.md

@@ -2,6 +2,9 @@
 
 Anwendung zur Durchführung einer Plausibilitätsprüfung anhand der Daten für die BZKF Real World Data Platform.
 
+**Hinweis:** Dies ist eine Weiterführung des ursprünglichen
+Projekts [bzkf-rwdp-check](https://github.com/CCC-MF/bzkf-rwdp-check)
+
 ## Aufbau der ETL-Strecke an den Standorten
 
 Die Daten werden aus der Onkostar-Datenbank ausgelesen und in Apache-Kafka eingespeist.
@@ -67,10 +70,14 @@ Dies eignet sich um nachträglich Zahlen zu einem bestimmten Datum zu ermitteln.
 
 Der optionale Parameter `--include-extern` schließt Meldungen mit externer Diagnosestellung ein.
 Diese sind normalerweise nicht enthalten.
+Die Entscheidung, ob eine Meldung intern oder extern gemeldet wird, wird anhand der `Melder_ID` getroffen.
+Enthält diese die Zeichenkette `9999` wird von einer externen Meldung ausgegangen.
 
 Der optionale Parameter `--include-histo-zyto` schließt Meldungen mit Meldeanlass `histologhie_zytologie` ein.
 Diese sind normalerweise ebenfalls nicht enthalten.
 
+Mit dem optionalen Parameter `--schema-versions` werden die Angaben zudem noch oBDS-Schema-Version getrennt ausgegeben.
+
 ## Export aus der Onkostar-Datenbank
 
 Die Anwendung ist in der Lage, mit dem Befehl `export` die Spalten
@@ -99,3 +106,15 @@ Die Anwendung kann auch die Conditions in der CSV-Datei mit der Onkostar-Datenba
 
 Hierzu kann der Befehl `compare` genutzt werden. Dieser verwendet alle Optionen für die Datenbank und die
 Option `--file` für die CSV-Datei und gibt eine Übersicht auf der Konsole aus.
+
+## Vergleich der XML-basierten LKR-Export-Protokolldatei mit der Datenbank
+
+Mithilfe dieser Anwendung kann auch der aktuelle Inhalt der Datenbank gegen die LKR-Export-Protokolldatei für einen
+Export verglichen werden.
+
+Der Befehl `check-export` kann zusammen mit der Angabe der Protokolldatei (`--file`) und der Angabe des
+Exports (`--package=...` bzw. `--export-package=...`) und den Optionen für den Datenbankzugriff ausgeführt werden.
+
+Zur Überprüfung werden irrelevante Leerzeichen und Zeilenumbrüche entfernt und _Self-Closed-Tags_ ersetzt
+(`<Meldeanlass />` => `<Meldeanlass></Meldeanlass>`),
+da in Onkostar in der Datenbank und der LKR-Export-Protokolldatei verschiedene Formatierungen verwendet werden (können).

src/cli.rs

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -62,6 +62,8 @@ pub enum SubCommand {
         year: String,
         #[arg(long, value_parser = value_is_date, help = "Ignoriere LKR-Exporte seit Datum")]
         ignore_exports_since: Option<String>,
+        #[arg(long, help = "Ignoriere Meldungen, die nicht im oBDS 2.x Format sind")]
+        ignore_non_obds_2: bool,
         #[arg(long, help = "Meldungen mit externer Diagnose einschließen")]
         include_extern: bool,
         #[arg(
@@ -69,6 +71,8 @@ pub enum SubCommand {
             help = "Meldungen mit Meldeanlass 'histologie_zytologie' einschließen"
         )]
         include_histo_zyto: bool,
+        #[arg(long, help = "Meldungen mit oBDS-Schema-version anzeigen")]
+        schema_versions: bool,
     },
     #[command(
         about = "Erstellt eine (reduzierte) CSV-Datei zum direkten Vergleich mit der OPAL-CSV-Datei"
@@ -101,6 +105,8 @@ pub enum SubCommand {
         year: String,
         #[arg(long, value_parser = value_is_date, help = "Ignoriere LKR-Exporte seit Datum")]
         ignore_exports_since: Option<String>,
+        #[arg(long, help = "Ignoriere Meldungen, die nicht im oBDS 2.x Format sind")]
+        ignore_non_obds_2: bool,
         #[arg(long, help = "Export mit Trennzeichen ';' für Excel")]
         xls_csv: bool,
         #[arg(long, help = "Meldungen mit externer Diagnose einschließen")]
@@ -140,6 +146,8 @@ pub enum SubCommand {
         year: String,
         #[arg(long, value_parser = value_is_date, help = "Ignoriere LKR-Exporte seit Datum")]
         ignore_exports_since: Option<String>,
+        #[arg(long, help = "Ignoriere Meldungen, die nicht im oBDS 2.x Format sind")]
+        ignore_non_obds_2: bool,
         #[arg(long, help = "Meldungen mit externer Diagnose einschließen")]
         include_extern: bool,
         #[arg(
@@ -148,6 +156,37 @@ pub enum SubCommand {
         )]
         include_histo_zyto: bool,
     },
+    #[command(about = "Abgleich zwischen LKR-Export-Protokoll und Onkostar-Datenbank")]
+    CheckExport {
+        #[arg(short = 'D', long, help = "Datenbank-Name", default_value = "onkostar")]
+        database: String,
+        #[arg(
+            short = 'h',
+            long,
+            help = "Datenbank-Host",
+            default_value = "localhost"
+        )]
+        host: String,
+        #[arg(short = 'P', long, help = "Datenbank-Host", default_value = "3306")]
+        port: u16,
+        #[arg(
+            short = 'p',
+            long,
+            help = "Passwort. Wenn nicht angegeben, wird danach gefragt"
+        )]
+        password: Option<String>,
+        #[arg(short = 'u', long, help = "Benutzername")]
+        user: String,
+        #[arg(short, long, help = "LKR-Export-Protokoll-Datei")]
+        file: PathBuf,
+        #[arg(
+            long,
+            alias = "export-package",
+            help = "Exportpaketnummer",
+            default_value = "0"
+        )]
+        package: u16,
+    },
 }
 
 fn value_is_date(value: &str) -> Result<String, String> {

src/common.rs

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -23,6 +23,7 @@ use serde::{Deserialize, Serialize};
 
 pub struct Icd10GroupSize {
     pub name: String,
+    pub schema_version: Option<String>,
     pub size: usize,
 }
 
@@ -68,6 +69,7 @@ impl Check {
             .map(|(icd10, group)| (icd10, group.collect::<Vec<_>>()))
             .map(|record| Icd10GroupSize {
                 name: record.0,
+                schema_version: None,
                 size: record.1.len(),
             })
             .collect::<Vec<_>>();
@@ -116,3 +118,15 @@ impl Check {
         .to_string()
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use crate::common::Check;
+
+    #[test]
+    fn should_map_icd10_code_as_expected() {
+        assert_eq!(Check::map_icd_code("D39.1"), "C56, D39.1");
+        assert_eq!(Check::map_icd_code("C00"), "C00-C14");
+        assert_eq!(Check::map_icd_code("F79.9"), "Other");
+    }
+}

src/database.rs

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -24,7 +24,23 @@ use mysql::prelude::Queryable;
 use mysql::{params, Pool};
 
 use crate::common::{ExportData, Icd10GroupSize};
-use crate::resources::{EXPORT_QUERY, SQL_QUERY};
+use crate::resources::{EXPORTED_TO_LKR, EXPORT_QUERY, SQL_QUERY, SQL_QUERY_WITH_SCHEMA_VERSION};
+
+fn result_mapper() -> fn((String, String, usize)) -> Icd10GroupSize {
+    |(icd10_group, _, count)| Icd10GroupSize {
+        name: icd10_group,
+        schema_version: None,
+        size: count,
+    }
+}
+
+fn result_mapper_with_schema_version() -> fn((String, String, usize)) -> Icd10GroupSize {
+    |(icd10_group, schema_version, count)| Icd10GroupSize {
+        name: icd10_group,
+        schema_version: Some(schema_version),
+        size: count,
+    }
+}
 
 pub struct DatabaseSource(String);
 
@@ -39,27 +55,35 @@ impl DatabaseSource {
         &self,
         year: &str,
         ignore_exports_since: &str,
+        ignore_non_obds_2: bool,
         include_extern: bool,
         include_histo_zyto: bool,
+        schema_versions: bool,
     ) -> Result<Vec<Icd10GroupSize>, ()> {
+        let params = params! {
+            "year" => year,
+            "ignore_exports_since" => ignore_exports_since,
+            "ignore_non_obds_2" => if ignore_non_obds_2 { 1 } else { 0 },
+            "include_extern" => if include_extern { 1 } else { 0 },
+            "include_histo_zyto" => if include_histo_zyto { 1 } else { 0 }
+        };
+
         match Pool::new(self.0.as_str()) {
             Ok(pool) => {
                 if let Ok(mut connection) = pool.try_get_conn(Duration::from_secs(3)) {
-                    return match connection.exec_map(
-                        SQL_QUERY,
-                        params! {
-                            "year" => year,
-                            "ignore_exports_since" => ignore_exports_since,
-                            "include_extern" => if include_extern { 1 } else { 0 },
-                            "include_histo_zyto" => if include_histo_zyto { 1 } else { 0 }
+                    return match schema_versions {
+                        true => match connection.exec_map(
+                            SQL_QUERY_WITH_SCHEMA_VERSION,
+                            params,
+                            result_mapper_with_schema_version(),
+                        ) {
+                            Ok(result) => Ok(result),
+                            Err(_) => Err(()),
                         },
-                        |(icd10_group, count)| Icd10GroupSize {
-                            name: icd10_group,
-                            size: count,
+                        false => match connection.exec_map(SQL_QUERY, params, result_mapper()) {
+                            Ok(result) => Ok(result),
+                            Err(_) => Err(()),
                         },
-                    ) {
-                        Ok(result) => Ok(result),
-                        Err(_) => Err(()),
                     };
                 }
             }
@@ -75,6 +99,7 @@ impl DatabaseSource {
         &self,
         year: &str,
         ignore_exports_since: &str,
+        ignore_non_obds_2: bool,
         use_pat_id: bool,
         include_extern: bool,
         include_histo_zyto: bool,
@@ -87,6 +112,7 @@ impl DatabaseSource {
                         params! {
                             "year" => year,
                             "ignore_exports_since" => ignore_exports_since,
+                            "ignore_non_obds_2" => if ignore_non_obds_2 { 1 } else { 0 },
                             "include_extern" => if include_extern { 1 } else { 0 },
                             "include_histo_zyto" => if include_histo_zyto { 1 } else { 0 }
                         },
@@ -111,4 +137,30 @@ impl DatabaseSource {
 
         Err(())
     }
+
+    pub fn exported(&self, package: u16) -> Result<Vec<(String, String)>, ()> {
+        match Pool::new(self.0.as_str()) {
+            Ok(pool) => {
+                if let Ok(mut connection) = pool.try_get_conn(Duration::from_secs(3)) {
+                    return match connection.exec_map(
+                        EXPORTED_TO_LKR,
+                        params! {
+                            "export_id" => package,
+                        },
+                        |(id, xml_data)| (id, xml_data),
+                    ) {
+                        Ok(result) => Ok(result),
+                        Err(_) => {
+                            return Err(());
+                        }
+                    };
+                }
+            }
+            Err(_) => {
+                return Err(());
+            }
+        }
+
+        Err(())
+    }
 }

src/lkrexport.rs

@@ -0,0 +1,270 @@
+/*
+ * This file is part of bzkf-rwdp-check
+ *
+ * Copyright (C) 2024 the original author or authors.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+use std::fs;
+use std::path::Path;
+use std::str::FromStr;
+
+use itertools::Itertools;
+use regex::Regex;
+
+pub struct LkrExportProtocolFile {
+    pub patients: Vec<Patient>,
+}
+
+impl LkrExportProtocolFile {
+    pub fn parse_file(path: &Path) -> Result<LkrExportProtocolFile, ()> {
+        let xml_file_content = fs::read_to_string(path).map_err(|_| ())?;
+        Self::parse(&xml_file_content)
+    }
+
+    pub fn parse(content: &str) -> Result<LkrExportProtocolFile, ()> {
+        let re = Regex::new(r"(?s)(?<patient><Patient>(.*?)</Patient>)").unwrap();
+
+        if re.is_match(content) {
+            let patients = re
+                .find_iter(content)
+                .map(|m| Patient {
+                    raw_value: m.as_str().to_string(),
+                })
+                .collect_vec();
+            return Ok(LkrExportProtocolFile { patients });
+        }
+
+        Err(())
+    }
+
+    pub fn meldungen(&self) -> Vec<Meldung> {
+        self.patients
+            .iter()
+            .flat_map(|patient| patient.meldungen())
+            .collect_vec()
+    }
+}
+
+pub struct Patient {
+    pub raw_value: String,
+}
+
+impl Patient {
+    pub fn meldungen(&self) -> Vec<Meldung> {
+        let re = Regex::new(r"(?s)(?<meldung><Meldung(.*?)</Meldung>)").unwrap();
+
+        if re.is_match(&self.raw_value) {
+            return re
+                .find_iter(&self.raw_value)
+                .map(|m| Meldung {
+                    raw_value: m.as_str().to_string(),
+                })
+                .collect_vec();
+        }
+        vec![]
+    }
+}
+
+pub struct Meldung {
+    pub raw_value: String,
+}
+
+impl FromStr for Meldung {
+    type Err = ();
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        Ok(Meldung {
+            raw_value: s.to_string(),
+        })
+    }
+}
+
+#[allow(unused)]
+impl Meldung {
+    pub fn id(&self) -> Option<String> {
+        let re = Regex::new(r#"Meldung_ID="(?<meldung_id>(.*?))""#).unwrap();
+
+        if re.is_match(&self.raw_value) {
+            let caps = re.captures(&self.raw_value).unwrap();
+            return Some(caps["meldung_id"].to_string());
+        }
+
+        None
+    }
+
+    pub fn icd10(&self) -> Option<String> {
+        let re = Regex::new(r"(?s)<Primaertumor_ICD_Code>(?<icd10>(.*?))</Primaertumor_ICD_Code>")
+            .unwrap();
+
+        if re.is_match(&self.raw_value) {
+            let caps = re.captures(&self.raw_value).unwrap();
+            return Some(caps["icd10"].to_string());
+        }
+
+        None
+    }
+
+    pub fn database_id(&self) -> Option<String> {
+        match self.id() {
+            Some(id) => to_database_id(&id),
+            _ => None,
+        }
+    }
+
+    pub fn sanitized_xml_string(&self) -> String {
+        let re = Regex::new(r"[\r|\n]+\s*").unwrap();
+        let content = re.replace_all(&self.raw_value, "").trim().to_string();
+
+        let re = Regex::new(r"<[^>]+/>").unwrap();
+        if re.is_match(&content) {
+            let mut c = content.to_string();
+            re.find_iter(&content)
+                .map(|m| m.as_str().to_string().replace('<', "").replace("/>", ""))
+                .for_each(|tag| {
+                    c = c.replace(&format!("<{}/>", tag), &format!("<{}></{}>", tag, tag));
+                });
+            return c;
+        }
+
+        content
+    }
+}
+
+pub fn to_database_id(id: &str) -> Option<String> {
+    let re1 = Regex::new(r"^(?<id>[0-9A-F]+)").unwrap();
+    let re2 = Regex::new(r"(?<id>[0-9]+)$").unwrap();
+
+    if re1.is_match(id) {
+        match re1.find(id).map(|m| m.as_str().to_string()) {
+            Some(val) => match u64::from_str_radix(&val, 16) {
+                Ok(val) => Some(val.to_string()),
+                _ => None,
+            },
+            _ => None,
+        }
+    } else if re2.is_match(id) {
+        re2.find(id).map(|m| m.as_str().to_string())
+    } else {
+        None
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::lkrexport::{LkrExportProtocolFile, Meldung};
+
+    #[test]
+    fn should_read_xml_file_content() {
+        let actual = LkrExportProtocolFile::parse(include_str!("../testdaten/testdaten_1.xml"));
+
+        assert!(actual.is_ok());
+        assert_eq!(actual.unwrap().patients.len(), 2);
+    }
+
+    #[test]
+    fn should_get_meldungen() {
+        let actual = LkrExportProtocolFile::parse(include_str!("../testdaten/testdaten_1.xml"));
+
+        assert!(actual.is_ok());
+
+        let patients = actual.unwrap().patients;
+
+        assert_eq!(patients[0].meldungen().len(), 1);
+        assert_eq!(patients[1].meldungen().len(), 1);
+    }
+
+    #[test]
+    fn should_get_meldung_id() {
+        let actual = LkrExportProtocolFile::parse(include_str!("../testdaten/testdaten_1.xml"));
+
+        assert!(actual.is_ok());
+
+        let patients = actual.unwrap().patients;
+
+        assert_eq!(
+            patients[0].meldungen()[0].id(),
+            Some("TEST1727528".to_string())
+        );
+        assert_eq!(
+            patients[1].meldungen()[0].id(),
+            Some("001A5D50-TEST".to_string())
+        );
+    }
+
+    #[test]
+    fn should_get_meldung_database_id() {
+        let actual = LkrExportProtocolFile::parse(include_str!("../testdaten/testdaten_1.xml"));
+
+        assert!(actual.is_ok());
+
+        let patients = actual.unwrap().patients;
+
+        assert_eq!(
+            patients[0].meldungen()[0].database_id(),
+            Some("1727528".to_string())
+        );
+        assert_eq!(
+            patients[1].meldungen()[0].database_id(),
+            Some("1727824".to_string())
+        );
+    }
+
+    #[test]
+    fn should_get_meldung_icd10() {
+        let actual = LkrExportProtocolFile::parse(include_str!("../testdaten/testdaten_1.xml"));
+
+        assert!(actual.is_ok());
+
+        let patients = actual.unwrap().patients;
+
+        assert_eq!(
+            patients[0].meldungen()[0].icd10(),
+            Some("C17.1".to_string())
+        );
+        assert_eq!(
+            patients[1].meldungen()[0].icd10(),
+            Some("C17.2".to_string())
+        );
+    }
+
+    #[test]
+    fn should_get_meldung_with_trimmed_margin() {
+        let meldung = Meldung {
+            raw_value: "  <Test>\n  <Test2>TestInhalt 3</Test2>\n</Test>\n".into(),
+        };
+
+        assert_eq!(
+            meldung.sanitized_xml_string(),
+            "<Test><Test2>TestInhalt 3</Test2></Test>".to_string()
+        );
+    }
+
+    #[test]
+    fn should_get_meldung_without_self_closing_tags() {
+        let meldung = Meldung {
+            raw_value:
+                "  <Test>\n  <Test2/>\n  <Content>Test</Content>\n  <Test3/>\n  <Test2/>\n</Test>\n"
+                    .into(),
+        };
+
+        assert_eq!(
+            meldung.sanitized_xml_string(),
+            "<Test><Test2></Test2><Content>Test</Content><Test3></Test3><Test2></Test2></Test>"
+                .to_string()
+        );
+    }
+}

src/main.rs

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -18,6 +18,7 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+use std::collections::HashMap;
 use std::error::Error;
 
 use clap::Parser;
@@ -28,10 +29,12 @@ use itertools::Itertools;
 use crate::cli::{Cli, SubCommand};
 use crate::common::{Check, DiffRecord, Icd10GroupSize};
 use crate::database::DatabaseSource;
+use crate::lkrexport::{to_database_id, LkrExportProtocolFile, Meldung};
 
 mod cli;
 mod common;
 mod database;
+mod lkrexport;
 mod opal;
 mod resources;
 
@@ -48,9 +51,9 @@ fn request_password_if_none(password: Option<String>) -> String {
     }
 }
 
-fn sanitize_year(year: String) -> String {
+fn sanitize_year(year: &str) -> String {
     if year.len() == 4 {
-        year
+        year.to_string()
     } else {
         format!("2{:0>3}", year)
     }
@@ -64,26 +67,34 @@ fn print_items(items: &[Icd10GroupSize]) {
             .to_string(),
     );
     items.iter().for_each(|item| {
-        let _ = term.write_line(&format!("{:<20}={:>6}", item.name, item.size));
+        let _ = term.write_line(&format!(
+            "{:<20} {:<6} ={:>6}",
+            item.name,
+            item.schema_version.as_ref().unwrap_or(&String::new()),
+            item.size
+        ));
     });
     let sum: usize = items
         .iter()
         .filter(|item| item.name != "Other")
         .map(|item| item.size)
         .sum();
-    let _ = term.write_line(&style("─".repeat(27)).dim().to_string());
+    let _ = term.write_line(&style("─".repeat(35)).dim().to_string());
     let _ = term.write_line(
-        &style(format!("{:<20}={:>6}", "Summe (C**.*/D**.*)", sum))
-            .dim()
-            .to_string(),
+        &style(format!(
+            "{:<20} {:<6} ={:>6}",
+            "Summe (C**.*/D**.*)", "", sum
+        ))
+        .dim()
+        .to_string(),
     );
     let sum: usize = items.iter().map(|item| item.size).sum();
     let _ = term.write_line(
-        &style(format!("{:<20}={:>6}", "Gesamtsumme", sum))
+        &style(format!("{:<20} {:<6} ={:>6}", "Gesamtsumme", "", sum))
             .dim()
             .to_string(),
     );
-    let _ = term.write_line(&style("─".repeat(27)).dim().to_string());
+    let _ = term.write_line(&style("─".repeat(35)).dim().to_string());
 }
 
 fn print_extern_notice(include_extern: bool) {
@@ -118,15 +129,18 @@ fn main() -> Result<(), Box<dyn Error>> {
             user,
             year,
             ignore_exports_since,
+            ignore_non_obds_2,
             include_extern,
             include_histo_zyto,
+            schema_versions,
         } => {
             let password = request_password_if_none(password);
-            let year = sanitize_year(year);
+            let year = sanitize_year(&year);
 
             let _ = term.write_line(
                 &style(format!("Warte auf Daten für das Diagnosejahr {}...", year))
                     .blue()
+                    .bright()
                     .to_string(),
             );
 
@@ -135,8 +149,10 @@ fn main() -> Result<(), Box<dyn Error>> {
                 .check(
                     &year,
                     &ignore_exports_since.unwrap_or("9999-12-31".into()),
+                    ignore_non_obds_2,
                     include_extern,
                     include_histo_zyto,
+                    schema_versions,
                 )
                 .map_err(|_e| "Fehler bei Zugriff auf die Datenbank")?;
 
@@ -155,16 +171,18 @@ fn main() -> Result<(), Box<dyn Error>> {
             output,
             year,
             ignore_exports_since,
+            ignore_non_obds_2,
             xls_csv,
             include_extern,
             include_histo_zyto,
         } => {
             let password = request_password_if_none(password);
-            let year = sanitize_year(year);
+            let year = sanitize_year(&year);
 
             let _ = term.write_line(
                 &style(format!("Warte auf Daten für das Diagnosejahr {}...", year))
                     .blue()
+                    .bright()
                     .to_string(),
             );
 
@@ -173,6 +191,7 @@ fn main() -> Result<(), Box<dyn Error>> {
                 .export(
                     &year,
                     &ignore_exports_since.unwrap_or("9999-12-31".into()),
+                    ignore_non_obds_2,
                     pat_id,
                     include_extern,
                     include_histo_zyto,
@@ -217,15 +236,17 @@ fn main() -> Result<(), Box<dyn Error>> {
             file,
             year,
             ignore_exports_since,
+            ignore_non_obds_2,
             include_extern,
             include_histo_zyto,
         } => {
             let password = request_password_if_none(password);
-            let year = sanitize_year(year);
+            let year = sanitize_year(&year);
 
             let _ = term.write_line(
                 &style(format!("Warte auf Daten für das Diagnosejahr {}...", year))
                     .blue()
+                    .bright()
                     .to_string(),
             );
 
@@ -234,6 +255,7 @@ fn main() -> Result<(), Box<dyn Error>> {
                 .export(
                     &year,
                     &ignore_exports_since.unwrap_or("9999-12-31".into()),
+                    ignore_non_obds_2,
                     pat_id,
                     include_extern,
                     include_histo_zyto,
@@ -247,7 +269,7 @@ fn main() -> Result<(), Box<dyn Error>> {
 
             let mut not_in_csv = db_items
                 .iter()
-                .filter(|db_item| {
+                .filter(|&db_item| {
                     !csv_items
                         .iter()
                         .map(|csv_item| &csv_item.condition_id)
@@ -277,7 +299,7 @@ fn main() -> Result<(), Box<dyn Error>> {
 
             not_in_csv
                 .iter()
-                .for_each(|item| match Check::is_relevant(&item.icd_10_code) {
+                .for_each(|&item| match Check::is_relevant(&item.icd_10_code) {
                     true => {
                         let _ = term.write_line(&format!(
                             "{:<64}   {:<10}   {:<5}   {:<5}   {}",
@@ -308,7 +330,7 @@ fn main() -> Result<(), Box<dyn Error>> {
 
             let mut not_in_db = csv_items
                 .iter()
-                .filter(|csv_item| {
+                .filter(|&csv_item| {
                     !db_items
                         .iter()
                         .map(|db_item| &db_item.condition_id)
@@ -421,6 +443,185 @@ fn main() -> Result<(), Box<dyn Error>> {
                 ));
             });
         }
+        SubCommand::CheckExport {
+            database,
+            host,
+            password,
+            port,
+            user,
+            file,
+            package,
+        } => {
+            let password = request_password_if_none(password);
+
+            let _ = term.write_line(
+                &style(format!(
+                    "Warte auf Daten für den LKR-Export '{}'...",
+                    package
+                ))
+                .blue()
+                .bright()
+                .to_string(),
+            );
+
+            let db = DatabaseSource::new(&database, &host, &password, port, &user);
+
+            let db_entries = db
+                .exported(package)
+                .map_err(|_e| "Fehler bei Zugriff auf die Datenbank")?;
+
+            let db_meldungen = db_entries
+                .iter()
+                .map(|entry| LkrExportProtocolFile::parse(&entry.1))
+                .filter(|entry| entry.is_ok())
+                .flat_map(|entry| entry.unwrap().meldungen())
+                .filter(|meldung| meldung.id().is_some())
+                .map(|meldung| (meldung.id().unwrap(), meldung))
+                .collect::<HashMap<_, _>>();
+
+            let xml_meldungen = LkrExportProtocolFile::parse_file(file.as_path())
+                .map_err(|_e| "Fehler bei Zugriff auf die Protokolldatei")?
+                .meldungen()
+                .into_iter()
+                .filter(|meldung| meldung.id().is_some())
+                .map(|meldung| (meldung.id().unwrap(), meldung))
+                .collect::<HashMap<_, _>>();
+
+            let missing_xml_ids = db_meldungen
+                .keys()
+                .filter(|&key| !xml_meldungen.contains_key(key))
+                .collect_vec();
+
+            let _ = term.clear_last_lines(1);
+
+            let _ = term.write_line(
+                &style(format!(
+                    "{} Datenbankeinträge mit {} Meldungen abgerufen",
+                    db_entries.len(),
+                    db_meldungen.len()
+                ))
+                .green()
+                .to_string(),
+            );
+
+            fn print_missing_ids(missing_ids: &[&String], term: &Term) {
+                missing_ids.iter().sorted().for_each(|&item| {
+                    let _ = term.write_line(&format!(
+                        "{} ({})",
+                        item,
+                        to_database_id(item).unwrap_or("?".into())
+                    ));
+                });
+            }
+
+            if db_meldungen.len() != xml_meldungen.len() {
+                let _ = term.write_line(
+                    &style("\nNicht übereinstimmende Anzahl an Meldungen:")
+                        .yellow()
+                        .to_string(),
+                );
+                let _ = term.write_line(&format!(
+                    "Datenbank:      {:>10}\nProtokolldatei: {:>10}",
+                    db_meldungen.len(),
+                    xml_meldungen.len()
+                ));
+
+                let missing_db_ids = xml_meldungen
+                    .keys()
+                    .filter(|&key| !db_meldungen.contains_key(key))
+                    .collect_vec();
+
+                if !missing_db_ids.is_empty() {
+                    let _ = term.write_line(
+                        &style("\nIn der Datenbank fehlende Meldungen:")
+                            .yellow()
+                            .to_string(),
+                    );
+
+                    print_missing_ids(&missing_db_ids, &term);
+                }
+
+                if !missing_xml_ids.is_empty() {
+                    let _ = term.write_line(
+                        &style("\nIn der Protokolldatei fehlende Meldungen:")
+                            .yellow()
+                            .to_string(),
+                    );
+
+                    print_missing_ids(&missing_xml_ids, &term);
+                }
+            }
+
+            let multiple_meldung_entries = db_entries
+                .iter()
+                .map(|(lkr_meldung, meldung)| (lkr_meldung, LkrExportProtocolFile::parse(meldung)))
+                .filter_map(|(lkr_meldung, meldung)| {
+                    if meldung.unwrap().meldungen().len() > 1 {
+                        Some(lkr_meldung)
+                    } else {
+                        None
+                    }
+                })
+                .sorted()
+                .collect_vec();
+
+            if !multiple_meldung_entries.is_empty() {
+                let _ = term.write_line(
+                    &style("\nFolgende Einträge in `lkr_meldung_export` haben mehrere Meldungsinhalte in `xml_daten`:")
+                        .yellow()
+                        .to_string(),
+                );
+
+                multiple_meldung_entries.iter().for_each(|&item| {
+                    let _ = term.write_line(&item.to_string());
+                });
+            }
+
+            let different_content = db_meldungen
+                .iter()
+                .filter(|(id, _)| !missing_xml_ids.contains(id))
+                .filter(|(id, meldung)| {
+                    xml_meldungen
+                        .get(&id.to_string())
+                        .unwrap_or(&Meldung {
+                            raw_value: String::new(),
+                        })
+                        .sanitized_xml_string()
+                        != meldung.sanitized_xml_string()
+                })
+                .map(|(_, meldung)| meldung.id().unwrap_or("?".into()))
+                .collect_vec();
+
+            if !different_content.is_empty() {
+                let _ = term.write_line(
+                    &style(&format!(
+                        "\nFolgende {} Meldungen unterscheiden sich in der Datenbank und der Protokolldatei:",
+                        different_content.len()
+                    ))
+                    .yellow()
+                    .to_string(),
+                );
+
+                let _ = term.write_line(
+                    "Dies kann auch aufgrund der verwendeten XML-Encodierung auftreten und bedeutet nicht immer eine inhaltliche Abweichung."
+                );
+
+                different_content
+                    .iter()
+                    .sorted_by(|&id1, &id2| {
+                        to_database_id(id1)
+                            .unwrap_or_default()
+                            .cmp(&to_database_id(id2).unwrap_or_default())
+                    })
+                    .for_each(|id| {
+                        let _ = term.write_line(&format!(
+                            "{} ({})",
+                            id,
+                            to_database_id(id).unwrap_or("?".into())
+                        ));
+                    });
+            }
+        }
     }
 
     Ok(())

src/opal.rs

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

src/resources/export.sql

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -29,15 +29,17 @@ FROM (
         EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID') AS pid,
         lme.versionsnummer,
         SHA2(CONCAT('https://fhir.diz.uk-erlangen.de/identifiers/onkostar-xml-condition-id|', EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID'), 'condition', EXTRACTVALUE(lme.xml_daten, '//Diagnose/@Tumor_ID')), 256) AS cond_id,
-        SUBSTRING_INDEX(EXTRACTVALUE(lm.xml_daten, '//Primaertumor_ICD_Code'), ' ', 1) AS condcodingcode,
-        SUBSTRING_INDEX(EXTRACTVALUE(lm.xml_daten, '//Diagnosedatum'), ' ', 1) AS diagnosedatum,
-        SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lm.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) AS diagnosejahr
+        SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Primaertumor_ICD_Code'), ' ', 1) AS condcodingcode,
+        SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1) AS diagnosedatum,
+        SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) AS diagnosejahr
     FROM lkr_meldung_export lme
-    JOIN lkr_meldung lm ON (lm.id = lme.lkr_meldung AND lme.typ <> '-1' AND lm.extern <= :include_extern)
-    WHERE lm.xml_daten LIKE '%ICD_Version%'
-        AND SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lm.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) = :year
-        AND (lm.xml_daten LIKE '%<cTNM%' OR lm.xml_daten LIKE '%<pTNM%' OR lm.xml_daten LIKE '%<Menge_Histologie>%' OR lm.xml_daten LIKE '%<Menge_Weitere_Klassifikation>%')
-        AND (lm.xml_daten NOT LIKE '%histologie_zytologie%' OR 1 = :include_histo_zyto)
+    WHERE lme.xml_daten LIKE '%ICD_Version%'
+        AND lme.typ <> -1
+        AND lme.xml_daten NOT LIKE '%<Menge_Tumorkonferenz%'
+        AND SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) = :year
+        AND (lme.xml_daten NOT LIKE '%histologie_zytologie%' OR 1 = :include_histo_zyto)
+        AND (EXTRACTVALUE(lme.xml_daten, '//Meldende_Stelle') NOT LIKE '%9999%' OR 1 <= :include_extern)
+        AND (EXTRACTVALUE(lme.xml_daten, '//ADT_GEKID/@Schema_Version') LIKE '2.%' OR 1 = :ignore_non_obds_2)
     ) o1
     LEFT OUTER JOIN (
 

src/resources/exported-to-lkr.sql

@@ -0,0 +1,26 @@
+/*
+ * This file is part of bzkf-rwdp-check
+ *
+ * Copyright (C) 2024 the original author or authors.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+SELECT
+    CONVERT(id,char) AS id,
+    xml_daten
+FROM lkr_meldung_export
+WHERE typ <> -1
+    AND (lkr_export = :export_id OR (0 = :export_id AND lkr_export IN (SELECT MAX(lkr_export) FROM lkr_meldung_export)));

src/resources/mod.rs

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -20,4 +20,8 @@
 
 pub const SQL_QUERY: &str = include_str!("query.sql");
 
+pub const SQL_QUERY_WITH_SCHEMA_VERSION: &str = include_str!("query_with_schema_version.sql");
+
 pub const EXPORT_QUERY: &str = include_str!("export.sql");
+
+pub const EXPORTED_TO_LKR: &str = include_str!("exported-to-lkr.sql");

src/resources/query.sql

@@ -1,7 +1,7 @@
 /*
  * This file is part of bzkf-rwdp-check
  *
- * Copyright (C) 2024 Comprehensive Cancer Center Mainfranken and contributors.
+ * Copyright (C) 2024 the original author or authors.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -107,34 +107,35 @@ SELECT CASE
 
            ELSE 'Other'
            END AS ICD10_GROUP,
-
+       '' AS schema_version,
        COUNT(*) as COUNT
 FROM (
-
     SELECT DISTINCT
+        lme.lkr_meldung,
         EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID') AS pid,
+        EXTRACTVALUE(lme.xml_daten, '//ADT_GEKID/@Schema_Version') AS schema_version,
         lme.versionsnummer,
         SHA2(CONCAT('https://fhir.diz.uk-erlangen.de/identifiers/onkostar-xml-condition-id|', EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID'), 'condition', EXTRACTVALUE(lme.xml_daten, '//Diagnose/@Tumor_ID')), 256) AS cond_id,
-        SUBSTRING_INDEX(EXTRACTVALUE(lm.xml_daten, '//Primaertumor_ICD_Code'), ' ', 1) AS condcodingcode,
-        SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lm.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) AS diagnosejahr
+        SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Primaertumor_ICD_Code'), ' ', 1) AS condcodingcode,
+        SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) AS diagnosejahr
     FROM lkr_meldung_export lme
-    JOIN lkr_meldung lm ON (lm.id = lme.lkr_meldung AND lme.typ <> '-1' AND lm.extern <= :include_extern)
     WHERE lme.xml_daten LIKE '%ICD_Version%'
-        AND SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lm.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) = :year
-        AND (lm.xml_daten LIKE '%<cTNM%' OR lm.xml_daten LIKE '%<pTNM%' OR lm.xml_daten LIKE '%<Menge_Histologie>%' OR lm.xml_daten LIKE '%<Menge_Weitere_Klassifikation>%')
-        AND (lm.xml_daten NOT LIKE '%histologie_zytologie%' OR 1 = :include_histo_zyto)
-    ) o1
-    LEFT OUTER JOIN (
-
+        AND lme.typ <> -1
+        AND lme.xml_daten NOT LIKE '%<Menge_Tumorkonferenz%'
+        AND SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) = :year
+        AND (lme.xml_daten NOT LIKE '%histologie_zytologie%' OR 1 = :include_histo_zyto)
+        AND (EXTRACTVALUE(lme.xml_daten, '//Meldende_Stelle') NOT LIKE '%9999%' OR 1 <= :include_extern)
+        AND (EXTRACTVALUE(lme.xml_daten, '//ADT_GEKID/@Schema_Version') LIKE '2.%' OR 1 = :ignore_non_obds_2)
+ ) o1
+LEFT OUTER JOIN (
     SELECT DISTINCT
+        lme.lkr_meldung,
         SHA2(CONCAT('https://fhir.diz.uk-erlangen.de/identifiers/onkostar-xml-condition-id|', EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID'), 'condition', EXTRACTVALUE(lme.xml_daten, '//Diagnose/@Tumor_ID')), 256) AS cond_id,
-        CASE WHEN le.exportiert_am < :ignore_exports_since THEN MAX(versionsnummer) ELSE ~0 END AS max_version
+        CASE WHEN STR_TO_DATE(EXTRACTVALUE(lme.xml_daten, '//Meldedatum'), '%d.%c.%Y') < :ignore_exports_since THEN MAX(versionsnummer) ELSE ~0 END AS max_version
     FROM lkr_meldung_export lme
-        JOIN lkr_export le ON (lme.lkr_export = le.id)
     WHERE SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) = :year
     GROUP BY cond_id ORDER BY cond_id
-
-    ) o2
+) o2
 ON (o1.cond_id = o2.cond_id AND o1.versionsnummer < max_version)
 WHERE diagnosejahr = :year AND o2.cond_id IS NULL
 GROUP BY ICD10_GROUP;

src/resources/query_with_schema_version.sql

@@ -0,0 +1,141 @@
+/*
+ * This file is part of bzkf-rwdp-check
+ *
+ * Copyright (C) 2024 the original author or authors.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+SELECT CASE
+           WHEN condcodingcode LIKE 'C00%'
+               OR condcodingcode LIKE 'C01%'
+               OR condcodingcode LIKE 'C02%'
+               OR condcodingcode LIKE 'C03%'
+               OR condcodingcode LIKE 'C04%'
+               OR condcodingcode LIKE 'C05%'
+               OR condcodingcode LIKE 'C06%'
+               OR condcodingcode LIKE 'C07%'
+               OR condcodingcode LIKE 'C08%'
+               OR condcodingcode LIKE 'C09%'
+               OR condcodingcode LIKE 'C10%'
+               OR condcodingcode LIKE 'C11%'
+               OR condcodingcode LIKE 'C12%'
+               OR condcodingcode LIKE 'C13%'
+               OR condcodingcode LIKE 'C14%' THEN 'C00-C14'
+
+           WHEN condcodingcode LIKE 'C15%' THEN 'C15'
+
+           WHEN condcodingcode LIKE 'C16%' THEN 'C16'
+
+           WHEN condcodingcode LIKE 'C18%'
+               OR condcodingcode LIKE 'C19%'
+               OR condcodingcode LIKE 'C20%'
+               OR condcodingcode LIKE 'C21%' THEN 'C18-C21'
+
+           WHEN condcodingcode LIKE 'C22%' THEN 'C22'
+
+           WHEN condcodingcode LIKE 'C23%'
+               OR condcodingcode LIKE 'C24%' THEN 'C23-C24'
+
+           WHEN condcodingcode LIKE 'C25%' THEN 'C25'
+
+           WHEN condcodingcode LIKE 'C32%' THEN 'C32'
+
+           WHEN condcodingcode LIKE 'C33%'
+               OR condcodingcode LIKE 'C34%' THEN 'C33-C34'
+
+           WHEN condcodingcode LIKE 'C43%' THEN 'C43'
+
+           WHEN condcodingcode LIKE 'C50%'
+               OR condcodingcode LIKE 'D05%' THEN 'C50, D05'
+
+           WHEN condcodingcode LIKE 'C53%'
+               OR condcodingcode LIKE 'D06%' THEN 'C53, D06'
+
+           WHEN condcodingcode LIKE 'C54%'
+               OR condcodingcode LIKE 'C55%' THEN 'C54-C55'
+
+           WHEN condcodingcode LIKE 'C56%'
+               OR condcodingcode = 'D39.1' THEN 'C56, D39.1'
+
+           WHEN condcodingcode LIKE 'C61%' THEN 'C61'
+
+           WHEN condcodingcode LIKE 'C62%' THEN 'C62'
+
+           WHEN condcodingcode LIKE 'C64%' THEN 'C64'
+
+           WHEN condcodingcode LIKE 'C67%'
+               OR condcodingcode = 'D09.0'
+               OR condcodingcode = 'D41.4' THEN 'C67, D09.0, D41.4'
+
+           WHEN condcodingcode LIKE 'C70%'
+               OR condcodingcode LIKE 'C71%'
+               OR condcodingcode LIKE 'C72%' THEN 'C70-C72'
+
+           WHEN condcodingcode LIKE 'C73%' THEN 'C73'
+
+           WHEN condcodingcode LIKE 'C81%' THEN 'C81'
+
+           WHEN condcodingcode LIKE 'C82%'
+               OR condcodingcode LIKE 'C83%'
+               OR condcodingcode LIKE 'C84%'
+               OR condcodingcode LIKE 'C85%'
+               OR condcodingcode LIKE 'C86%'
+               OR condcodingcode LIKE 'C87%'
+               OR condcodingcode LIKE 'C88%'
+               OR condcodingcode LIKE 'C96%' THEN 'C82-C88, C96'
+
+           WHEN condcodingcode LIKE 'C90%' THEN 'C90'
+
+           WHEN condcodingcode LIKE 'C91%'
+               OR condcodingcode LIKE 'C92%'
+               OR condcodingcode LIKE 'C93%'
+               OR condcodingcode LIKE 'C94%'
+               OR condcodingcode LIKE 'C95%' THEN 'C91-C95'
+
+           ELSE 'Other'
+           END AS ICD10_GROUP,
+       schema_version,
+       COUNT(*) as COUNT
+FROM (
+    SELECT DISTINCT
+        lme.lkr_meldung,
+        EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID') AS pid,
+        EXTRACTVALUE(lme.xml_daten, '//ADT_GEKID/@Schema_Version') AS schema_version,
+        lme.versionsnummer,
+        SHA2(CONCAT('https://fhir.diz.uk-erlangen.de/identifiers/onkostar-xml-condition-id|', EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID'), 'condition', EXTRACTVALUE(lme.xml_daten, '//Diagnose/@Tumor_ID')), 256) AS cond_id,
+        SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Primaertumor_ICD_Code'), ' ', 1) AS condcodingcode,
+        SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) AS diagnosejahr
+    FROM lkr_meldung_export lme
+    WHERE lme.xml_daten LIKE '%ICD_Version%'
+        AND lme.typ <> -1
+        AND lme.xml_daten NOT LIKE '%<Menge_Tumorkonferenz%'
+        AND SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) = :year
+        AND (lme.xml_daten NOT LIKE '%histologie_zytologie%' OR 1 = :include_histo_zyto)
+        AND (EXTRACTVALUE(lme.xml_daten, '//Meldende_Stelle') NOT LIKE '%9999%' OR 1 <= :include_extern)
+        AND (EXTRACTVALUE(lme.xml_daten, '//ADT_GEKID/@Schema_Version') LIKE '2.%' OR 1 = :ignore_non_obds_2)
+ ) o1
+LEFT OUTER JOIN (
+    SELECT DISTINCT
+        lme.lkr_meldung,
+        SHA2(CONCAT('https://fhir.diz.uk-erlangen.de/identifiers/onkostar-xml-condition-id|', EXTRACTVALUE(lme.xml_daten, '//Patienten_Stammdaten/@Patient_ID'), 'condition', EXTRACTVALUE(lme.xml_daten, '//Diagnose/@Tumor_ID')), 256) AS cond_id,
+        CASE WHEN STR_TO_DATE(EXTRACTVALUE(lme.xml_daten, '//Meldedatum'), '%d.%c.%Y') < :ignore_exports_since THEN MAX(versionsnummer) ELSE ~0 END AS max_version
+    FROM lkr_meldung_export lme
+    WHERE SUBSTRING_INDEX(SUBSTRING_INDEX(EXTRACTVALUE(lme.xml_daten, '//Diagnosedatum'), ' ', 1), '.', -1) = :year
+    GROUP BY cond_id ORDER BY cond_id
+) o2
+ON (o1.cond_id = o2.cond_id AND o1.versionsnummer < max_version)
+WHERE diagnosejahr = :year AND o2.cond_id IS NULL
+GROUP BY ICD10_GROUP, schema_version;

testdaten/testdaten_1.xml

@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ADT_GEKID xmlns="http://www.gekid.de/namespace" Schema_Version="2.2.3">
+    <Absender Absender_ID="TEST" Software_ID="ONKOSTAR" Installations_ID="2011">
+        <Absender_Bezeichnung>TEST</Absender_Bezeichnung>
+        <Absender_Anschrift>Musterstraße 1, 012345 Musterhausen</Absender_Anschrift>
+    </Absender>
+    <Menge_Patient>
+        <Patient>
+            <Patienten_Stammdaten Patient_ID="20001234">
+                <KrankenversichertenNr>E123456789</KrankenversichertenNr>
+                <KrankenkassenNr>123456789</KrankenkassenNr>
+                <Patienten_Nachname>Tester</Patienten_Nachname>
+                <Patienten_Titel></Patienten_Titel>
+                <Patienten_Vornamen>Patrick</Patienten_Vornamen>
+                <Patienten_Geburtsname>Tester</Patienten_Geburtsname>
+                <Patienten_Geschlecht>M</Patienten_Geschlecht>
+                <Patienten_Geburtsdatum>01.01.1980</Patienten_Geburtsdatum>
+                <Menge_Adresse>
+                    <Adresse>
+                        <Patienten_Strasse>Testweg</Patienten_Strasse>
+                        <Patienten_Hausnummer>1</Patienten_Hausnummer>
+                        <Patienten_Land>DE</Patienten_Land>
+                        <Patienten_PLZ>01234</Patienten_PLZ>
+                        <Patienten_Ort>Musterhausen</Patienten_Ort>
+                    </Adresse>
+                </Menge_Adresse>
+            </Patienten_Stammdaten>
+            <Menge_Meldung>
+                <Meldung Meldung_ID="TEST1727528" Melder_ID="TEST">
+                    <Meldedatum>11.06.2024</Meldedatum>
+                    <Meldebegruendung>I</Meldebegruendung>
+                    <Meldeanlass>statusaenderung</Meldeanlass>
+                    <Tumorzuordnung Tumor_ID="1">
+                        <Primaertumor_ICD_Code>C17.1</Primaertumor_ICD_Code>
+                        <Primaertumor_ICD_Version>10 2015 GM</Primaertumor_ICD_Version>
+                        <Diagnosedatum>10.06.2024</Diagnosedatum>
+                        <Seitenlokalisation>T</Seitenlokalisation>
+                    </Tumorzuordnung>
+                    <Menge_Tumorkonferenz>
+                        <Tumorkonferenz Tumorkonferenz_ID="1234567">
+                            <Tumorkonferenz_Datum>11.06.2024</Tumorkonferenz_Datum>
+                            <Tumorkonferenz_Typ>praeth</Tumorkonferenz_Typ>
+                        </Tumorkonferenz>
+                    </Menge_Tumorkonferenz>
+                </Meldung>
+            </Menge_Meldung>
+        </Patient>
+        <Patient>
+            <Patienten_Stammdaten Patient_ID="20004321">
+                <KrankenversichertenNr>E123456789</KrankenversichertenNr>
+                <KrankenkassenNr>123456789</KrankenkassenNr>
+                <Patienten_Nachname>Tester</Patienten_Nachname>
+                <Patienten_Titel></Patienten_Titel>
+                <Patienten_Vornamen>Patricia</Patienten_Vornamen>
+                <Patienten_Geburtsname>Tester</Patienten_Geburtsname>
+                <Patienten_Geschlecht>W</Patienten_Geschlecht>
+                <Patienten_Geburtsdatum>01.01.1980</Patienten_Geburtsdatum>
+                <Menge_Adresse>
+                    <Adresse>
+                        <Patienten_Strasse>Testweg</Patienten_Strasse>
+                        <Patienten_Hausnummer>1</Patienten_Hausnummer>
+                        <Patienten_Land>DE</Patienten_Land>
+                        <Patienten_PLZ>01234</Patienten_PLZ>
+                        <Patienten_Ort>Musterhausen</Patienten_Ort>
+                    </Adresse>
+                </Menge_Adresse>
+            </Patienten_Stammdaten>
+            <Menge_Meldung>
+                <Meldung Meldung_ID="001A5D50-TEST" Melder_ID="TEST">
+                    <Meldedatum>11.06.2024</Meldedatum>
+                    <Meldebegruendung>I</Meldebegruendung>
+                    <Meldeanlass>statusaenderung</Meldeanlass>
+                    <Tumorzuordnung Tumor_ID="1">
+                        <Primaertumor_ICD_Code>C17.2</Primaertumor_ICD_Code>
+                        <Primaertumor_ICD_Version>10 2015 GM</Primaertumor_ICD_Version>
+                        <Diagnosedatum>01.01.2024</Diagnosedatum>
+                        <Seitenlokalisation>T</Seitenlokalisation>
+                    </Tumorzuordnung>
+                    <Menge_Tumorkonferenz>
+                        <Tumorkonferenz Tumorkonferenz_ID="1234568">
+                            <Tumorkonferenz_Datum>10.01.2024</Tumorkonferenz_Datum>
+                            <Tumorkonferenz_Typ>praeth</Tumorkonferenz_Typ>
+                        </Tumorkonferenz>
+                    </Menge_Tumorkonferenz>
+                </Meldung>
+            </Menge_Meldung>
+        </Patient>
+    </Menge_Patient>
+</ADT_GEKID>