Merge pull request #163 from GenSpectrum/staticAnalysis

Reenable linter and code style standardization

.clang-format

@@ -13,6 +13,4 @@ ContinuationIndentWidth: 3
 AlwaysBreakAfterDefinitionReturnType: None
 AlwaysBreakAfterReturnType: None
 PenaltyReturnTypeOnItsOwnLine: 1000
-ReferenceAlignment: Left
-PointerAlignment: Left
-DerivePointerAlignment: false
+QualifierAlignment: Left

.clang-tidy

@@ -15,8 +15,10 @@ Checks: >
   clang-analyzer-cplusplus.NewDeleteLeaks,
   -modernize-use-trailing-return-type,
   -misc-non-private-member-variables-in-classes,
+  -misc-include-cleaner,
   -google-readability-avoid-underscore-in-googletest-name,
   -abseil-string-find-str-contains
+  -bugprone-easily-swappable-parameters
 #  TODO(someone): clean up misc-non-private-member-variables-in-classes and add option back in
 # Not using google-readability-avoid-underscore-in-googletest-name because it also fails for test_name
 # Not using abseil-string-find-str-contains because we don't want to include more libraries
@@ -34,6 +36,6 @@ CheckOptions:
   - { key: readability-identifier-naming.TypeTemplateParameterIgnoredRegexp, value: expr-type }
   - { key: readability-implicit-bool-conversion.AllowIntegerConditions,  value: 1 }
   - { key: readability-implicit-bool-conversion.AllowPointerConditions,  value: 1 }
-  - { key: bugprone-easily-swappable-parameters.MinimumLength, value: 3 }
+  - { key: bugprone-easily-swappable-parameters.MinimumLength, value: 2 }
 
 # readability-identifier-naming.TypeTemplateParameterIgnoredRegexp is workaround for error of clang-tidy with ubuntu (https://github.com/llvm/llvm-project/issues/46097)

.dockerignore

@@ -2,6 +2,7 @@
 !CMakeLists.txt
 !build_with_conan.py
 !conanprofile.docker
+!conanprofile.ARMdocker
 !conanfile.py
 !.clang-tidy
 !src/

build_with_conan.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
+import argparse
 import os
 import shutil
-import argparse
+import subprocess
 
 
 def clean_build_folder(build_folder: str):
@@ -37,21 +38,26 @@ def main(args):
         + " ".join(conan_options))
     print("----------------------------------")
 
-    os.system(
-        "conan install . --build=missing --profile ./conanprofile --profile:build ./conanprofile --output-folder=build "
-        + " ".join(conan_options))
+    conan_install_cmd = "conan install . --build=missing --profile ./conanprofile --profile:build ./conanprofile --output-folder=build " + " ".join(
+        conan_options)
+    if subprocess.call(conan_install_cmd, shell=True) != 0:
+        raise Exception("Conan install command failed.")
 
     print("----------------------------------")
     print("cmake " + " ".join(cmake_options) + " -B build")
     print("----------------------------------")
 
-    os.system("cmake " + " ".join(cmake_options) + " -B build")
+    cmake_cmd = "cmake " + " ".join(cmake_options) + " -B build"
+    if subprocess.call(cmake_cmd, shell=True) != 0:
+        raise Exception("CMake command failed.")
 
     print("----------------------------------")
     print(f"cmake --build build --parallel {args.parallel}")
     print("----------------------------------")
 
-    os.system(f"cmake --build build --parallel {args.parallel}")
+    cmake_build_cmd = f"cmake --build build --parallel {args.parallel}"
+    if subprocess.call(cmake_build_cmd, shell=True) != 0:
+        raise Exception("CMake build command failed.")
 
 
 if __name__ == "__main__":

conanfile.py

@@ -6,12 +6,12 @@ class SiloRecipe(ConanFile):
     settings = "os", "compiler", "build_type", "arch"
 
     requires = [
-        "boost/1.81.0",
+        "boost/1.82.0",
         "poco/1.12.4",
-        "onetbb/2021.7.0",
+        "onetbb/2021.9.0",
         "nlohmann_json/3.11.2",
         "gtest/cci.20210126",
-        "roaring/0.9.9",
+        "roaring/1.3.0",
         "spdlog/1.11.0",
         "vincentlaucsb-csv-parser/2.1.3",
         "yaml-cpp/0.7.0",

endToEndTests/test/queries/HasAAMutation.json

@@ -12,7 +12,7 @@
   },
   "expectedQueryResult": [
     {
-      "count": 3
+      "count": 1
     }
   ]
 }

include/silo/common/aa_symbol_map.h

@@ -0,0 +1,33 @@
+#ifndef SILO_AA_SYMBOL_MAP_H
+#define SILO_AA_SYMBOL_MAP_H
+
+#include <vector>
+
+#include <boost/serialization/access.hpp>
+
+#include "silo/common/aa_symbols.h"
+
+namespace silo {
+
+template <typename T>
+class AASymbolMap {
+   friend class boost::serialization::access;
+
+  private:
+   template <class Archive>
+   [[maybe_unused]] void serialize(Archive& archive, const uint32_t /* version */) {
+      // clang-format off
+      archive& data;
+      // clang-format on
+   }
+
+   std::array<T, AA_SYMBOL_COUNT> data;
+
+  public:
+   inline T& operator[](AA_SYMBOL symbol) { return data.at(static_cast<uint8_t>(symbol)); }
+   inline const T& at(AA_SYMBOL symbol) const { return data.at(static_cast<uint8_t>(symbol)); }
+};
+
+}  // namespace silo
+
+#endif  // SILO_AA_SYMBOL_MAP_H

include/silo/common/aa_symbols.h

@@ -4,53 +4,115 @@
 #include <array>
 #include <iostream>
 #include <optional>
-#include <vector>
 
 namespace silo {
 
 /// https://www.bioinformatics.org/sms2/iupac.html
-enum class AA_SYMBOL {
-   A,  // Alanine
-   C,  // Cysteine
-   D,  // Aspartic Acid
-   E,  // Glutamic Acid
-   F,  // Phenylalanine
-   G,  // Glycine
-   H,  // Histidine
-   I,  // Isoleucine
-   K,  // Lysine
-   L,  // Leucine
-   M,  // Methionine
-   N,  // Asparagine
-   P,  // Proline
-   Q,  // Glutamine
-   R,  // Arginine
-   S,  // Serine
-   T,  // Threonine
-   V,  // Valine
-   W,  // Tryptophan
-   Y,  // Tyrosine
-   B,  // Aspartic acid or Asparagine
-   Z,  // Glutamine or Glutamic acid
-   X,  // Any amino acid
+enum class AA_SYMBOL : char {
+   GAP,   // - Gap in sequence
+   A,     // Alanine
+   C,     // Cysteine
+   D,     // Aspartic Acid
+   E,     // Glutamic Acid
+   F,     // Phenylalanine
+   G,     // Glycine
+   H,     // Histidine
+   I,     // Isoleucine
+   K,     // Lysine
+   L,     // Leucine
+   M,     // Methionine
+   N,     // Asparagine
+   P,     // Proline
+   Q,     // Glutamine
+   R,     // Arginine
+   S,     // Serine
+   T,     // Threonine
+   V,     // Valine
+   W,     // Tryptophan
+   Y,     // Tyrosine
+   B,     // Aspartic acid or Asparagine
+   Z,     // Glutamine or Glutamic acid
+   STOP,  // Stop codon
+   X,     // Any amino acid
 };
 
-static constexpr unsigned AA_SYMBOL_COUNT = static_cast<unsigned>(AA_SYMBOL::X) + 1;
+static constexpr uint32_t AA_SYMBOL_COUNT = 25;
+static constexpr uint32_t CODING_AA_SYMBOL_COUNT = 21;
 
-static constexpr std::array<char, AA_SYMBOL_COUNT> AA_SYMBOL_REPRESENTATION{
-   'A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N',
-   'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y', 'B', 'Z', 'X',
+static constexpr std::array<AA_SYMBOL, AA_SYMBOL_COUNT> AA_SYMBOLS{
+   AA_SYMBOL::GAP, AA_SYMBOL::A, AA_SYMBOL::C, AA_SYMBOL::D, AA_SYMBOL::E,
+   AA_SYMBOL::F,   AA_SYMBOL::G, AA_SYMBOL::H, AA_SYMBOL::I, AA_SYMBOL::K,
+   AA_SYMBOL::L,   AA_SYMBOL::M, AA_SYMBOL::N, AA_SYMBOL::P, AA_SYMBOL::Q,
+   AA_SYMBOL::R,   AA_SYMBOL::S, AA_SYMBOL::T, AA_SYMBOL::V, AA_SYMBOL::W,
+   AA_SYMBOL::Y,   AA_SYMBOL::B, AA_SYMBOL::Z, AA_SYMBOL::X, AA_SYMBOL::STOP,
 };
 
-static constexpr std::array<AA_SYMBOL, AA_SYMBOL_COUNT> AA_SYMBOLS{
-   AA_SYMBOL::A, AA_SYMBOL::C, AA_SYMBOL::D, AA_SYMBOL::E, AA_SYMBOL::F, AA_SYMBOL::G,
-   AA_SYMBOL::H, AA_SYMBOL::I, AA_SYMBOL::K, AA_SYMBOL::L, AA_SYMBOL::M, AA_SYMBOL::N,
-   AA_SYMBOL::P, AA_SYMBOL::Q, AA_SYMBOL::R, AA_SYMBOL::S, AA_SYMBOL::T, AA_SYMBOL::V,
-   AA_SYMBOL::W, AA_SYMBOL::Y, AA_SYMBOL::B, AA_SYMBOL::Z, AA_SYMBOL::X,
+static constexpr std::array<AA_SYMBOL, CODING_AA_SYMBOL_COUNT> VALID_AA_SYMBOL_READS{
+   AA_SYMBOL::GAP, AA_SYMBOL::A, AA_SYMBOL::C, AA_SYMBOL::D, AA_SYMBOL::E, AA_SYMBOL::F,
+   AA_SYMBOL::G,   AA_SYMBOL::H, AA_SYMBOL::I, AA_SYMBOL::K, AA_SYMBOL::L, AA_SYMBOL::M,
+   AA_SYMBOL::N,   AA_SYMBOL::P, AA_SYMBOL::Q, AA_SYMBOL::R, AA_SYMBOL::S, AA_SYMBOL::T,
+   AA_SYMBOL::V,   AA_SYMBOL::W, AA_SYMBOL::Y,
 };
 
-inline std::optional<AA_SYMBOL> toAASymbol(char character) {
+inline char aaSymbolToChar(AA_SYMBOL symbol) {
+   switch (symbol) {
+      case AA_SYMBOL::GAP:
+         return '-';
+      case AA_SYMBOL::A:
+         return 'A';
+      case AA_SYMBOL::C:
+         return 'C';
+      case AA_SYMBOL::D:
+         return 'D';
+      case AA_SYMBOL::E:
+         return 'E';
+      case AA_SYMBOL::F:
+         return 'F';
+      case AA_SYMBOL::G:
+         return 'G';
+      case AA_SYMBOL::H:
+         return 'H';
+      case AA_SYMBOL::I:
+         return 'I';
+      case AA_SYMBOL::K:
+         return 'K';
+      case AA_SYMBOL::L:
+         return 'L';
+      case AA_SYMBOL::N:
+         return 'N';
+      case AA_SYMBOL::M:
+         return 'M';
+      case AA_SYMBOL::P:
+         return 'P';
+      case AA_SYMBOL::Q:
+         return 'Q';
+      case AA_SYMBOL::R:
+         return 'R';
+      case AA_SYMBOL::S:
+         return 'S';
+      case AA_SYMBOL::T:
+         return 'T';
+      case AA_SYMBOL::V:
+         return 'V';
+      case AA_SYMBOL::W:
+         return 'W';
+      case AA_SYMBOL::Y:
+         return 'Y';
+      case AA_SYMBOL::B:
+         return 'B';
+      case AA_SYMBOL::Z:
+         return 'Z';
+      case AA_SYMBOL::X:
+         return 'X';
+      case AA_SYMBOL::STOP:
+         return '*';
+   }
+}
+
+inline std::optional<AA_SYMBOL> charToAASymbol(char character) {
    switch (character) {
+      case '-':
+         return AA_SYMBOL::GAP;
       case 'A':
          return AA_SYMBOL::A;
       case 'C':
@@ -71,10 +133,10 @@ inline std::optional<AA_SYMBOL> toAASymbol(char character) {
          return AA_SYMBOL::K;
       case 'L':
          return AA_SYMBOL::L;
-      case 'M':
-         return AA_SYMBOL::M;
       case 'N':
          return AA_SYMBOL::N;
+      case 'M':
+         return AA_SYMBOL::M;
       case 'P':
          return AA_SYMBOL::P;
       case 'Q':
@@ -97,6 +159,8 @@ inline std::optional<AA_SYMBOL> toAASymbol(char character) {
          return AA_SYMBOL::Z;
       case 'X':
          return AA_SYMBOL::X;
+      case '*':
+         return AA_SYMBOL::STOP;
       default:
          return std::nullopt;
    }

include/silo/common/bidirectional_map.h

@@ -1,16 +1,21 @@
 #ifndef SILO_BIDIRECTIONAL_MAP_H
 #define SILO_BIDIRECTIONAL_MAP_H
 
-#include <mutex>
+#include <cstdint>
 #include <optional>
 #include <string>
 #include <unordered_map>
 #include <vector>
 
 #include <boost/serialization/access.hpp>
 
+#include "silo/common/pango_lineage.h"
 #include "silo/common/types.h"
 
+namespace boost::serialization {
+class access;
+}  // namespace boost::serialization
+
 namespace silo::common {
 
 template <typename V>
@@ -19,7 +24,7 @@ class BidirectionalMap {
 
   private:
    template <class Archive>
-   [[maybe_unused]] void serialize(Archive& archive, const unsigned int /* version */) {
+   [[maybe_unused]] void serialize(Archive& archive, const uint32_t /* version */) {
       // clang-format off
       archive& value_to_id;
       archive& id_to_value;
@@ -35,7 +40,7 @@ class BidirectionalMap {
 
    [[nodiscard]] V getValue(Idx idx) const;
 
-   [[nodiscard]] std::optional<Idx> getId(V value) const;
+   [[maybe_unused]] [[nodiscard]] std::optional<Idx> getId(V value) const;
 
    [[nodiscard]] Idx getOrCreateId(V value);
 };

include/silo/common/date.h

@@ -1,6 +1,7 @@
 #ifndef SILO_DATE_H
 #define SILO_DATE_H
 
+#include <cstdint>
 #include <optional>
 #include <string>
 

include/silo/common/fasta_reader.h

@@ -3,6 +3,8 @@
 
 #include <filesystem>
 #include <iostream>
+#include <optional>
+#include <string>
 
 #include "silo/common/input_stream_wrapper.h"
 
@@ -11,14 +13,14 @@ class FastaReader {
   private:
    silo::InputStreamWrapper in_file;
 
-   bool populateKey(std::string& key);
+   std::optional<std::string> nextKey();
 
   public:
    explicit FastaReader(const std::filesystem::path& in_file_name);
 
-   bool nextKey(std::string& key);
+   std::optional<std::string> nextSkipGenome();
 
-   bool next(std::string& key, std::string& genome);
+   std::optional<std::string> next(std::string& genome_buffer);
 
    void reset();
 };

include/silo/common/format_number.h

@@ -1,6 +1,7 @@
 #ifndef SILO_FORMAT_NUMBER_H
 #define SILO_FORMAT_NUMBER_H
 
+#include <cstdint>
 #include <string>
 
 namespace silo {