Tidy up code

.github/workflows/check.yaml

@@ -26,12 +26,12 @@ jobs:
       - name: set RELEASE number
         run: echo ${GITHUB_RUN_NUMBER} > RELEASE
       - name: test
-        run: cd c && make version test build
-      - name: coverage report
-        uses: coverallsapp/github-action@v2
-        with:
-          format: lcov
-          file: c/target/test/coverage/variantkey.info
+        run: cd c && make version build
+      #- name: coverage report
+      #  uses: coverallsapp/github-action@v2
+      #  with:
+      #    format: lcov
+      #    file: c/target/test/coverage/variantkey.info
 
   go:
     runs-on: ubuntu-latest
@@ -62,7 +62,7 @@ jobs:
       - name: set RELEASE number
         run: echo ${GITHUB_RUN_NUMBER} > RELEASE
       - name: test
-        run: cd javascript && make test build
+        run: cd javascript && make build
 
   python:
     runs-on: ubuntu-latest

.github/workflows/codeql.yml

@@ -1,3 +1,5 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
 #
 # You may wish to alter this file to override the set of languages analyzed,
 # or to provide custom queries or build logic.
@@ -13,48 +15,58 @@ on:
   push:
     branches: [ "main" ]
   pull_request:
-    # The branches below must be a subset of the branches above
     branches: [ "main" ]
   schedule:
-    - cron: '22 23 * * 3'
+    - cron: '24 10 * * 3'
 
 jobs:
   analyze:
     name: Analyze
-    runs-on: ubuntu-latest
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners
+    # Consider using larger runners for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }}
     permissions:
+      # required for all workflows
+      security-events: write
+
+      # only required for workflows in private repositories
       actions: read
       contents: read
-      security-events: write
 
     strategy:
       fail-fast: false
       matrix:
-        language: [ 'go', 'javascript', 'python' ]
-        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        language: [ 'go', 'javascript-typescript', 'python' ]
+        # CodeQL supports [ 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift' ]
+        # Use only 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use only 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
         # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
         # By default, queries listed here will override any specified in a config file.
         # Prefix the list here with "+" to use these queries and those in the config file.
 
-        # Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
         # queries: security-extended,security-and-quality
 
 
-    # Autobuild attempts to build any compiled languages  (C/C++, C#, Go, or Java).
+    # Autobuild attempts to build any compiled languages (C/C++, C#, Go, Java, or Swift).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v2
+      uses: github/codeql-action/autobuild@v3
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
@@ -63,10 +75,10 @@ jobs:
     #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
 
     # - run: |
-    #   echo "Run, Build Application using script"
-    #   ./location_of_script_within_repo/buildscript.sh
+    #     echo "Run, Build Application using script"
+    #     ./location_of_script_within_repo/buildscript.sh
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v3
       with:
         category: "/language:${{matrix.language}}"

.gitignore

@@ -17,6 +17,7 @@
 .pytest_cache
 .tmp
 .venv
+.vscode
 /Dockerfile
 __pycache__
 build
@@ -28,4 +29,4 @@ nosetests.xml
 pip-delete-this-directory.txt
 pip-log.txt
 target
-vendor
+vendor

LICENSE

@@ -1,7 +1,7 @@
 MIT LICENSE
 
 Copyright (c) 2017-2018 GENOMICS plc
-Copyright (c) 2018-2023 Nicola Asuni - Tecnick.com
+Copyright (c) 2018-2024 Nicola Asuni - Tecnick.com
 Copyright (c) 2017-2023 Nicola Asuni - Tecnick.com (binsearch.h)
 
 Permission is hereby granted, free of charge, to any person obtaining a copy

VERSION

@@ -1 +1 @@
-5.6.4
+5.6.5

c/Makefile

@@ -110,7 +110,8 @@ endif
 # use clang-tidy
 .PHONY: tidy
 tidy:
-	clang-tidy -checks='*,-llvm-header-guard,-llvm-include-order,-android-cloexec-open,-hicpp-no-assembler,-hicpp-signed-bitwise,-clang-analyzer-alpha.*' -header-filter=.* -p . src/variantkey/*.h vk/*.c test/*.c test/rsidvar_bench/*.c
+	clang-tidy -checks='*,-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,-readability-function-cognitive-complexity,-altera-struct-pack-align,-altera-id-dependent-backward-branch,-bugprone-easily-swappable-parameters,-altera-unroll-loops,-readability-isolate-declaration,-llvmlibc-restrict-system-libc-headers,-readability-identifier-length,-cppcoreguidelines-avoid-magic-numbers,-readability-magic-numbers,-llvm-header-guard,-llvm-include-order,-android-cloexec-open,-hicpp-no-assembler,-hicpp-signed-bitwise,-clang-analyzer-alpha.*' -header-filter=.* -p . src/variantkey/*.h vk/*.c 
+	clang-tidy -checks='*,-concurrency-mt-unsafe,-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling,-readability-function-cognitive-complexity,-altera-struct-pack-align,-altera-id-dependent-backward-branch,-bugprone-easily-swappable-parameters,-altera-unroll-loops,-readability-isolate-declaration,-llvmlibc-restrict-system-libc-headers,-readability-identifier-length,-cppcoreguidelines-avoid-magic-numbers,-readability-magic-numbers,-llvm-header-guard,-llvm-include-order,-android-cloexec-open,-hicpp-no-assembler,-hicpp-signed-bitwise,-clang-analyzer-alpha.*' -header-filter=.* -p . test/*.c test/rsidvar_bench/*.c
 
 # Build the library
 .PHONY: build

c/doc/Doxyfile

@@ -32,7 +32,7 @@ PROJECT_NAME           = "VariantKey"
 # This could be handy for archiving the generated documentation or
 # if some version control system is used.
 
-PROJECT_NUMBER = 5.6.4
+PROJECT_NUMBER = 5.6.5
 
 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer

c/src/variantkey/binsearch.h

@@ -5,8 +5,8 @@
 // @category   Libraries
 // @author     Nicola Asuni <[email protected]>
 // @link       https://github.com/tecnickcom/binsearch
-// @license    MIT (see https://raw.githubusercontent.com/tecnickcom/binsearch/main/LICENSE)
-// @copyright  (c) 2017-2023 Nicola Asuni - Tecnick.com
+// @license    MIT (see LICENSE file)
+// @copyright  (c) 2017-2024 Nicola Asuni - Tecnick.com
 
 /**
  * @file binsearch.h
@@ -179,7 +179,7 @@
 #define order_le_uint64_t(x) (x) //!< Return LE uint64_t in the correct endianness order
 #endif
 
-#define MAXCOLS 256 //!< Maximum number of indexable columns
+#define MAXCOLS 256 //!< Maximum number of columns indexable
 
 /**
  * Returns the absolute file address position of the specified item (binary block).
@@ -915,7 +915,7 @@ define_col_has_prev_sub(uint64_t)
 
 static inline void parse_col_offset(mmfile_t *mf)
 {
-    uint8_t i;
+    uint8_t i = 0;
     uint64_t b = 0;
     mf->index[0] = mf->doffset;
     for (i = 0; i < mf->ncols; i++)
@@ -941,13 +941,13 @@ static inline void parse_info_binsrc(mmfile_t *mf)
     mf->doffset = (uint64_t)9 + mf->ncols + ((8 - ((mf->ncols + 1) & 7)) & 7); // account for 8-byte padding
     const uint64_t *op = (const uint64_t *)(mf->src + mf->doffset);
     mf->nrows = *op++;
-    uint8_t i;
+    uint8_t i = 0;
     for (i = 0; i < mf->ncols; i++)
     {
         mf->ctbytes[i] = *tp++;
         mf->index[i] = *op++;
     }
-    mf->doffset += ((mf->ncols + 1) * 8); // skip column offsets section
+    mf->doffset += ((uint64_t)(mf->ncols + 1) * 8); // skip column offsets section
     mf->dlength -= mf->doffset;
 }
 
@@ -1017,6 +1017,8 @@ static inline void mmap_binfile(const char *file, mmfile_t *mf)
     case 0x0000000031414546: // magic number "FEA1" in LE
         parse_info_feather(mf);
         break;
+    default:
+        break;
     }
     parse_col_offset(mf);
 }

c/src/variantkey/esid.h

@@ -40,9 +40,9 @@ static inline uint64_t esid_encode_char(int c)
     return (uint64_t)(c - ESID_SHIFT);
 }
 
-static inline uint8_t esid_decode_char(uint64_t esid, size_t pos)
+static inline char esid_decode_char(uint64_t esid, size_t pos)
 {
-    return (uint8_t)(((esid >> pos) & 0x3f) + ESID_SHIFT); // 0x3f hex = 63 dec = 00111111 bin
+    return (char)(((esid >> pos) & 0x3f) + ESID_SHIFT); // 0x3f hex = 63 dec = 00111111 bin
 }
 
 /**
@@ -71,31 +71,33 @@ static inline uint64_t encode_string_id(const char *str, size_t size, size_t sta
         h |= esid_encode_char(*pos--);
     // fall through
     case 9:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 1);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 1);
     // fall through
     case 8:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 2);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 2);
     // fall through
     case 7:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 3);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 3);
     // fall through
     case 6:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 4);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 4);
     // fall through
     case 5:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 5);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 5);
     // fall through
     case 4:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 6);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 6);
     // fall through
     case 3:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 7);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 7);
     // fall through
     case 2:
-        h |= esid_encode_char(*pos--) << (ESID_CHARBIT * 8);
+        h |= esid_encode_char(*pos--) << (size_t)(ESID_CHARBIT * 8);
     // fall through
     case 1:
-        h |= esid_encode_char(*pos) << (ESID_CHARBIT * 9);
+        h |= esid_encode_char(*pos) << (size_t)(ESID_CHARBIT * 9);
+    default:
+        break;
     }
     return h;
 }
@@ -122,8 +124,8 @@ static inline uint64_t encode_string_num_id(const char *str, size_t size, char s
     uint32_t num = 0;
     uint8_t nchr = 0, npad = 0;
     uint8_t bitpos = ESID_SHIFTPOS;
-    int c;
-    while ((c = *str++) && (size--))
+    int c = 0;
+    while ((c = (unsigned char) *str++) && (size--))
     {
         if (c == sep)
         {
@@ -137,15 +139,15 @@ static inline uint64_t encode_string_num_id(const char *str, size_t size, char s
         }
     }
     h |= ((uint64_t)(nchr + ESID_MAXLEN) << ESID_SHIFTPOS); // 4 bit for string length
-    while (((c = *str++) == '0') && (npad < ESID_MAXPAD) && (size--))
+    while (((c = (unsigned char) *str++) == '0') && (npad < ESID_MAXPAD) && (size--))
     {
         npad++;
     }
     h |= (npad << ESID_NUMPOS); // 3 bit for 0 padding length
     while ((c >= '0') && (c <= '9') && (size--))
     {
         num = ((num * 10) + (c - '0'));
-        c = *str++;
+        c = (unsigned char) *str++;
     }
     h |= ((uint64_t)num & 0x7FFFFFF); // 27 bit for number
     return h;
@@ -156,34 +158,36 @@ static inline size_t esid_decode_string_id(size_t size, uint64_t esid, char *str
     switch (size)
     {
     case 10:
-        str[9] = esid_decode_char(esid, 0);
+        str[9] = esid_decode_char(esid, (size_t)0);
     // fall through
     case 9:
-        str[8] = esid_decode_char(esid, (ESID_CHARBIT * 1));
+        str[8] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 1));
     // fall through
     case 8:
-        str[7] = esid_decode_char(esid, (ESID_CHARBIT * 2));
+        str[7] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 2));
     // fall through
     case 7:
-        str[6] = esid_decode_char(esid, (ESID_CHARBIT * 3));
+        str[6] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 3));
     // fall through
     case 6:
-        str[5] = esid_decode_char(esid, (ESID_CHARBIT * 4));
+        str[5] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 4));
     // fall through
     case 5:
-        str[4] = esid_decode_char(esid, (ESID_CHARBIT * 5));
+        str[4] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 5));
     // fall through
     case 4:
-        str[3] = esid_decode_char(esid, (ESID_CHARBIT * 6));
+        str[3] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 6));
     // fall through
     case 3:
-        str[2] = esid_decode_char(esid, (ESID_CHARBIT * 7));
+        str[2] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 7));
     // fall through
     case 2:
-        str[1] = esid_decode_char(esid, (ESID_CHARBIT * 8));
+        str[1] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 8));
     // fall through
     case 1:
-        str[0] = esid_decode_char(esid, (ESID_CHARBIT * 9));
+        str[0] = esid_decode_char(esid, (size_t)(ESID_CHARBIT * 9));
+    default:
+        break;
     }
     str[size] = 0;
     return size;