GA4GHTT-270: Merge changes from master (241, 247, 248) and porting 248 for 4.4

.github/workflows/build.yml

@@ -59,8 +59,8 @@ jobs:
         path: vcf_assembly_checker_linux
 
 
-  ### Mac OS build
-  macos_build:
+  ### Mac OS build intel
+  macos_build_intel:
     runs-on: macos-12
     strategy:
       matrix:
@@ -84,33 +84,80 @@ jobs:
     - name: Rename release files
       if: ${{ matrix.config.cc == 'clang' }}
       run: |
-        mv build/bin/vcf_validator vcf_validator_macos
-        mv build/bin/vcf_debugulator vcf_debugulator_macos
-        mv build/bin/vcf_assembly_checker vcf_assembly_checker_macos
+        mv build/bin/vcf_validator vcf_validator_macos_x64
+        mv build/bin/vcf_debugulator vcf_debugulator_macos_x64
+        mv build/bin/vcf_assembly_checker vcf_assembly_checker_macos_x64
     - name: Upload vcf-validator
       uses: actions/upload-artifact@v3
       if: ${{ matrix.config.cc == 'clang' }}
       with:
-        name: vcf_validator_macos
-        path: vcf_validator_macos
+        name: vcf_validator_macos_x64
+        path: vcf_validator_macos_x64
     - name: Upload vcf-debugulator
       uses: actions/upload-artifact@v3
       if: ${{ matrix.config.cc == 'clang' }}
       with:
-        name: vcf_debugulator_macos
-        path: vcf_debugulator_macos
+        name: vcf_debugulator_macos_x64
+        path: vcf_debugulator_macos_x64
     - name: Upload vcf-assembly-checker
       uses: actions/upload-artifact@v3
       if: ${{ matrix.config.cc == 'clang' }}
       with:
-        name: vcf_assembly_checker_macos
-        path: vcf_assembly_checker_macos
+        name: vcf_assembly_checker_macos_x64
+        path: vcf_assembly_checker_macos_x64
+
+  ### Mac OS build arm
+  macos_build_arm:
+    runs-on: macos-14
+    strategy:
+      matrix:
+        config:
+          - {cc: "gcc", cxx: "g++"}
+          - {cc: "clang", cxx: "clang++"}
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Install dependencies
+      run: |
+        #brew update
+        HOMEBREW_NO_AUTO_UPDATE=1 brew install boost sqlite3 automake libtool
+        ./install_dependencies.sh osx
+    - name: Compile and test
+      run: |
+        mkdir build && cd build && cmake -G "Unix Makefiles" -DCMAKE_CXX_COMPILER=${{ matrix.config.cxx }} -DCMAKE_C_COMPILER=${{ matrix.config.cc }} ..
+        export LIBRARY_PATH=${LIBRARY_PATH}:/opt/homebrew/opt/icu4c/lib:/opt/homebrew/lib
+        make -j2
+        cd .. && ./build/bin/test_validation_suite
+    - name: Rename release files
+      if: ${{ matrix.config.cc == 'clang' }}
+      run: |
+        mv build/bin/vcf_validator vcf_validator_macos_arm64
+        mv build/bin/vcf_debugulator vcf_debugulator_macos_arm64
+        mv build/bin/vcf_assembly_checker vcf_assembly_checker_macos_arm64
+    - name: Upload vcf-validator
+      uses: actions/upload-artifact@v3
+      if: ${{ matrix.config.cc == 'clang' }}
+      with:
+        name: vcf_validator_macos_arm64
+        path: vcf_validator_macos_arm64
+    - name: Upload vcf-debugulator
+      uses: actions/upload-artifact@v3
+      if: ${{ matrix.config.cc == 'clang' }}
+      with:
+        name: vcf_debugulator_macos_arm64
+        path: vcf_debugulator_macos_arm64
+    - name: Upload vcf-assembly-checker
+      uses: actions/upload-artifact@v3
+      if: ${{ matrix.config.cc == 'clang' }}
+      with:
+        name: vcf_assembly_checker_macos_arm64
+        path: vcf_assembly_checker_macos_arm64
 
 
   ### Release job (tags only)
   create_release:
     if: startsWith(github.ref, 'refs/tags/')
-    needs: [ linux_build, macos_build ]
+    needs: [ linux_build, macos_build_intel, macos_build_arm ]
     runs-on: ubuntu-latest
     steps:
       - name: Download artifacts

CMakeLists.txt

@@ -3,7 +3,7 @@ project (vcf-validator CXX C)
 
 set (vcf-validator_VERSION_MAJOR 0)
 set (vcf-validator_VERSION_MINOR 9)
-set (vcf-validator_VERSION_PATCH 6)
+set (vcf-validator_VERSION_PATCH 7)
 
 configure_file (
   "${PROJECT_SOURCE_DIR}/inc/cmake_config.hpp.in"

inc/assembly_report/assembly_report.hpp

@@ -61,7 +61,11 @@ namespace ebi
 
         void add_synonym(std::string synonym)
         {
-            synonyms.push_back(synonym);
+            // Only add the synonym if there isn't one already
+            if (std::find(synonyms.begin(), synonyms.end(), synonym) == synonyms.end())
+            {
+                synonyms.push_back(synonym);
+            }
         }
 
       private:

inc/util/string_utils.hpp

@@ -32,6 +32,7 @@ namespace ebi
     /**
      * Splits `s` using `delims` as separator and fills the container `ret` with the parts.
      * An empty string results in an empty container `ret`.
+     * Expects a string without leading separators and when one is present, it would be part of 1st string.
      * @param s input string to split
      * @param delims any character here acts as a separator
      * @param ret return by reference the container filled with the string split.

inc/vcf/error.hpp

@@ -225,7 +225,7 @@ namespace ebi
         using BodySectionError::BodySectionError;
         ChromosomeBodyError() : ChromosomeBodyError{0} {}
         ChromosomeBodyError(size_t line) : ChromosomeBodyError{line,
-            "Chromosome is not a string without colons or whitespaces, optionally wrapped with angle brackets (<>)"} { }
+            "Chromosome is not a string without whitespaces, optionally wrapped with angle brackets (<>)"} { }
         virtual ~ChromosomeBodyError() override { }
         virtual void apply_visitor(ErrorVisitor &visitor) override { visitor.visit(*this); }
     };

inc/vcf/file_structure.hpp

@@ -205,7 +205,15 @@ namespace ebi
             { SVTYPE, { STRING, "1" } },
             { VALIDATED, { FLAG, "0" } },
             { THOUSAND_G, { FLAG, "0" } },
-            { SVCLAIM, { STRING, "A" } }
+            { SVCLAIM, { STRING, "A" } },
+            { RN, { INTEGER, "A" } },
+            { RUS, { STRING, UNKNOWN_CARDINALITY } },
+            { RUL, { INTEGER, UNKNOWN_CARDINALITY } },
+            { RUC, { FLOAT, UNKNOWN_CARDINALITY } },
+            { RB, { INTEGER, UNKNOWN_CARDINALITY } },
+            { CIRUC, { FLOAT, UNKNOWN_CARDINALITY } },
+            { CIRB, { INTEGER, UNKNOWN_CARDINALITY } },
+            { RUB, { INTEGER, UNKNOWN_CARDINALITY } }
     };
 
     const std::map<std::string, std::pair<std::string, std::string>> format_v41_v42 = {
@@ -422,19 +430,12 @@ namespace ebi
         void set_types();
 
         /**
-         * Checks that chromosome does not contain colons or white-spaces
+         * Checks that chromosome does not contain white-spaces
          *
          * @throw ChromosomeBodyError
          */
         void check_chromosome() const;
 
-        /**
-         * Checks that chromosome does not contain any colons
-         *
-         * @throw ChromosomeBodyError
-         */
-        void check_chromosome_no_colons() const;
-
         /**
          * Checks that chromosome does not contain any white-spaces
          *
@@ -724,6 +725,11 @@ namespace ebi
          * @throw InfoBodyError
          */
         void check_info_have_mandatory() const;
+
+        /**
+         * gets total RN count
+         */
+        int getRNvalue() const;
     };
 
     std::ostream &operator<<(std::ostream &os, const Record &record);

inc/vcf/optional_policy.hpp

@@ -61,6 +61,8 @@ namespace ebi
         void check_body_entry_info_svlen(ParsingState & state, Record const & record) const;
         void check_body_entry_info_svclaim(ParsingState & state, Record const & record) const;
         void check_body_entry_info_confidence_interval(ParsingState & state, Record const & record) const;
+        void check_body_entry_info_rb_ruc(ParsingState & state, Record const & record) const;
+        void check_body_entry_info_rul_rus(ParsingState & state, Record const & record) const;
         void check_contig_meta(ParsingState & state, Record const & record) const;
         void check_alternate_allele_meta(ParsingState & state, Record const & record) const;
         void check_filter_meta(ParsingState & state, Record const & record) const;

inc/vcf/string_constants.hpp

@@ -164,6 +164,14 @@ namespace ebi
     const std::string VALIDATED = "VALIDATED";
     const std::string THOUSAND_G = "1000G";
     const std::string SVCLAIM = "SVCLAIM";
+    const std::string RN = "RN";
+    const std::string RUS = "RUS";
+    const std::string RUL = "RUL";
+    const std::string RUC = "RUC";
+    const std::string RB = "RB";
+    const std::string CIRUC = "CIRUC";
+    const std::string CIRB = "CIRB";
+    const std::string RUB = "RUB";
 
     // FORMAT predefined tags
     const std::string AHAP = "AHAP";