Merge branch 'release/v2.3.1'

.github/workflows/c-cpp.yml

@@ -0,0 +1,27 @@
+name: C/C++ CI
+
+on:
+  push:
+    branches: [ master, develop ]
+  pull_request:
+    branches: [ master, develop ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: dependencies
+      run: sudo DEBIAN_FRONTEND=noninteractive apt-get install -y yaggo gettext swig python3-dev ruby-dev libperl-dev
+    - name: autotools
+      run: autoreconf -fi
+    - name: configure
+      run: ./configure --enable-all-binding --enable-swig
+    - name: make
+      run: make -j2
+    - name: make check
+      run: make -j2 check
+    - name: make distcheck
+      run: make -j2 distcheck

.gitignore

@@ -14,3 +14,5 @@ ltmain.sh
 *_cmdline.hpp
 test-driver
 build-*
+*~
+compile_commands.json

Makefile.am

@@ -1,7 +1,7 @@
 ACLOCAL_AMFLAGS = -I m4
 DISTCHECK_CONFIGURE_FLAGS=--enable-swig --enable-all-binding
 
-EXTRA_DIST = doc/jellyfish.pdf doc/jellyfish.man README LICENSE # jellyfish.spec
+EXTRA_DIST = doc/jellyfish.pdf doc/jellyfish.man README LICENSE-BSD-3-Clause LICENSE-GPL-3.0 # jellyfish.spec
 man1_MANS = doc/jellyfish.man
 
 pkgconfigdir = $(libdir)/pkgconfig
@@ -228,3 +228,6 @@ include gtest.mk
 # Print the value of a variable
 print-%:
 	@echo -n $($*)
+
+# Only compile the the check, don't run
+check-programs: $(BUILT_SOURCES) $(check_PROGRAMS) $(check_LTLIBRARIES)

README.md

@@ -1,3 +1,5 @@
+![CI workflow](https://github.com/gmarcais/Jellyfish/actions/workflows/c-cpp.yml/badge.svg)
+
 # Jellyfish
 
 ## Overview

configure.ac

@@ -1,11 +1,11 @@
-AC_INIT([jellyfish], [2.3.0], [gmarcais@umd.edu])
+AC_INIT([jellyfish],[2.3.1],[gmarcais@cs.cmu.edu])
 AC_CANONICAL_HOST
 AC_CONFIG_MACRO_DIR([m4])
 AM_INIT_AUTOMAKE([subdir-objects foreign parallel-tests color-tests])
 AM_SILENT_RULES([yes])
 AC_CONFIG_SRCDIR([jellyfish])
 AC_CONFIG_HEADERS([config.h])
-AC_PROG_LIBTOOL
+LT_INIT
 AC_LIB_RPATH
 PKG_PROG_PKG_CONFIG
 
@@ -41,9 +41,9 @@ AS_IF([test "x$UNIX2DOS" = "x"],
 
 # Check for md5 or md5sum
 AC_ARG_VAR([MD5], [Path to md5 hashing program])
-AS_IF([test "x$MD5" = "x"], AC_CHECK_PROG([MD5], [md5sum], [md5sum]), [])
-AS_IF([test "x$MD5" = "x"], AC_CHECK_PROG([MD5], [md5], [md5 -r]), [])
-AS_IF([test "x$MD5" = "x"], AC_MSG_ERROR([Could not find md5 hashing program in your path]), [])
+AS_IF([test "x$MD5" = "x"], [AC_CHECK_PROG([MD5], [md5sum], [md5sum])], [])
+AS_IF([test "x$MD5" = "x"], [AC_CHECK_PROG([MD5], [md5], [md5 -r])], [])
+AS_IF([test "x$MD5" = "x"], [AC_MSG_ERROR([Could not find md5 hashing program in your path])], [])
 
 # Check for yaggo
 AC_ARG_VAR([YAGGO], [Yaggo switch parser generator])
@@ -97,15 +97,15 @@ AC_LINK_IFELSE([AC_LANG_PROGRAM([[#include <mach-o/dyld.h>]],
                   [AC_DEFINE([HAVE_NSGETEXECUTABLEPATH], [1], [Used to find executable path on MacOS X])],
                   [AC_MSG_RESULT([no])])
 
-AC_CHECK_HEADERS_ONCE([execinfo.h ext/stdio_filebuf.h sys/syscall.h])
+AC_CHECK_HEADERS_ONCE([execinfo.h ext/stdio_filebuf.h sys/syscall.h sys/prctl.h])
 AC_CHECK_MEMBER([siginfo_t.si_int],
                 [AC_DEFINE([HAVE_SI_INT], [1], [Define if siginfo_t.si_int exists])],
                 [], [[#include <signal.h>]])
 
 # --enable-all-static
 # Do not use libtool if building all static
 AC_ARG_ENABLE([all-static],
-              [AC_HELP_STRING([--enable-all-static], [create statically linked executable])])
+              [AS_HELP_STRING([--enable-all-static],[create statically linked executable])])
 STATIC_FLAGS=
 AS_IF([test x$enable_all_static = xyes],
       [AC_SUBST([STATIC_FLAGS], [-all-static])])
@@ -116,24 +116,24 @@ AS_IF([test x$enable_all_static = xyes],
 maybe_swig=
 # --enable-python-binding
 AC_ARG_ENABLE([python-binding],
-              [AC_HELP_STRING([--enable-python-binding@<:@=PATH@:>@], [create SWIG python module and install in PATH])])
+              [AS_HELP_STRING([--enable-python-binding@<:@=PATH@:>@],[create SWIG python module and install in PATH (user or system site-packages if PATH=user|sys)])])
 # --enable-ruby-binding
 AC_ARG_ENABLE([ruby-binding],
-              [AC_HELP_STRING([--enable-ruby-binding@<:@=PATH@:>@], [create SWIG ruby module and install in PATH])])
+              [AS_HELP_STRING([--enable-ruby-binding@<:@=PATH@:>@],[create SWIG ruby module and install in PATH])])
 # --enable-perl-binding
 AC_ARG_ENABLE([perl-binding],
-              [AC_HELP_STRING([--enable-perl-binding@<:@=PATH@:>@], [create SWIG perl module and install in PATH])])
+              [AS_HELP_STRING([--enable-perl-binding@<:@=PATH@:>@],[create SWIG perl module and install in PATH])])
 # --enable-all-binding
 AC_ARG_ENABLE([all-binding],
-              [AC_HELP_STRING([--enable-all-binding@<:@=PATH@:>@], [create SWIG module for all languages and install in PATH])])
+              [AS_HELP_STRING([--enable-all-binding@<:@=PATH@:>@],[create SWIG module for all languages and install in PATH])])
 
 # --enable-swig
 AC_ARG_ENABLE([swig],
-              [AC_HELP_STRING([--enable-swig], [enable development of swig binding])])
+              [AS_HELP_STRING([--enable-swig],[enable development of swig binding])])
 AS_IF([test x$enable_swig = xyes],
       [AX_PKG_SWIG([3.0.0], [], [AC_MSG_ERROR([SWIG version 3 is required])])])
 AS_IF([test -n "$SWIG"],
-      [SWIG_ENABLE_CXX])
+      [AX_SWIG_ENABLE_CXX])
 AM_CONDITIONAL([HAVE_SWIG], [test -n "$SWIG"])
 
 # Python binding setup
@@ -143,7 +143,7 @@ AM_COND_IF([PYTHON_BINDING],
            [AS_IF([test x$enable_python_binding != xyes], [PYTHON_SITE_PKG=$enable_python_binding])]
            [AX_PYTHON_DEVEL([], [$prefix])])
 AC_ARG_ENABLE([python-deprecated],
-              [AC_HELP_STRING([--enable-python-deprecated], [enable the deprecated 'jellyfish' module (in addition to 'dna_jellyfish')])])
+              [AS_HELP_STRING([--enable-python-deprecated],[enable the deprecated 'jellyfish' module (in addition to 'dna_jellyfish')])])
 AM_CONDITIONAL([PYTHON_DEPRECATED], [test -z "$enable_python_deprecated" -o x$enable_python_deprecated != xno])
 
 # Ruby binding setup

doc/jellyfish.man

@@ -12,11 +12,8 @@
 ..
 .TH "JELLYFISH" "1" "2010/10/1" "k\-mer counter " "k\-mer counter "
 .SH NAME
+jellyfish - software to count k\-mers in DNA sequences
 
-.PP
-Jellyfish
-is a software to count k\-mers in DNA sequences. 
-.PP
 .SH SYNOPSIS
 
 jellyfish count
@@ -157,7 +154,7 @@ occurring many times will used multiple entries in the hash.
 Important: the size of the couting field does NOT change the result, 
 it only impacts the amount of memory used. In particular, there is no 
 maximum value in the hash. Even if the counting field uses 5 bits, a 
-k\-mer occuring 2 million times will have a value reported of 2 
+k\-mer occurring 2 million times will have a value reported of 2 
 million (i.e., it is not capped at 2^5). 
 .PP
 The \fB\-c\fP
@@ -459,7 +456,7 @@ Options (default value in (), *required):
 .SS QHISTO
 Usage: jellyfish qhisto [options] db:string 
 .PP
-Create an histogram of k\-mer occurences 
+Create an histogram of k\-mer occurrences 
 .PP
 Options (default value in (), *required): 
 .TP

examples/count_in_file/Makefile

@@ -1,6 +1,6 @@
 CC = g++
 CXXFLAGS = $(shell pkg-config --cflags jellyfish-2.0) -std=c++0x -Wall -O3
-LDFLAGS = -Wl,--rpath=$(shell pkg-config --libs-only-L jellyfish-2.0 | sed -e 's/-L//g')
+LDFLAGS = -Wl,--rpath=$(shell pkg-config --libs-only-L jellyfish-2.0 | sed -e 's/ -L/ /g')
 LDLIBS = $(shell pkg-config --libs jellyfish-2.0)
 
 all: count_in_file

examples/jf_count_dump/Makefile

@@ -1,6 +1,6 @@
 CC = g++
 CXXFLAGS = $(shell pkg-config --cflags jellyfish-2.0) -std=c++0x -Wall -O3
-LDFLAGS = -Wl,--rpath=$(shell pkg-config --libs-only-L jellyfish-2.0 | sed -e 's/-L//g')
+LDFLAGS = -Wl,--rpath=$(shell pkg-config --libs-only-L jellyfish-2.0 | sed -e 's/ -L/ /g')
 LDLIBS = $(shell pkg-config --libs jellyfish-2.0)
 
 all: jf_count_dump

examples/query_per_sequence/Makefile

@@ -1,6 +1,6 @@
 CC = g++
 CXXFLAGS = $(shell pkg-config --cflags jellyfish-2.0) -std=c++0x -Wall -O3
-LDFLAGS = -Wl,--rpath=$(shell pkg-config --libs-only-L jellyfish-2.0 | sed -e 's/-L//g')
+LDFLAGS = -Wl,--rpath=$(shell pkg-config --libs-only-L jellyfish-2.0 | sed -e 's/ -L/ /g')
 LDLIBS = $(shell pkg-config --libs jellyfish-2.0)
 
 all: query_per_sequence

include/jellyfish/generic_file_header.hpp

@@ -172,13 +172,17 @@ class generic_file_header {
 
 protected:
   std::string get_hostname() const {
+    if(std::getenv("SOURCE_DATE_EPOCH"))
+      return "hostname";
     struct utsname buf;
     if(uname(&buf) == -1)
       return "";
     return buf.nodename;
   }
 
   std::string get_pwd() const {
+    if(std::getenv("SOURCE_DATE_EPOCH"))
+      return ".";
 #ifdef PATH_MAX
     size_t len = PATH_MAX;
 #else
@@ -194,6 +198,16 @@ class generic_file_header {
   std::string get_localtime() const {
     time_t t = time(0);
     std::string res(ctime(&t));
+    char *source_date_epoch = std::getenv("SOURCE_DATE_EPOCH");
+    if(source_date_epoch) {
+      std::istringstream iss(source_date_epoch);
+      iss >> t;
+      if(iss.fail() || !iss.eof()) {
+        std::cerr << "Error: Cannot parse SOURCE_DATE_EPOCH as integer\n";
+        exit(27);
+      }
+      res = asctime(gmtime(&t));
+    }
     chomp(res);
     return res;
   }

include/jellyfish/mer_dna.hpp

@@ -81,7 +81,7 @@ struct cmask<U, len, 0> {
 
 // Fast reverse complement of one word through bit tweedling.
 inline uint32_t word_reverse_complement(uint32_t w) {
-  typedef uint64_t U;
+  typedef uint32_t U;
   w = ((w >> 2)  & cmask<U, 2 >::v) | ((w & cmask<U, 2 >::v) << 2);
   w = ((w >> 4)  & cmask<U, 4 >::v) | ((w & cmask<U, 4 >::v) << 4);
   w = ((w >> 8)  & cmask<U, 8 >::v) | ((w & cmask<U, 8 >::v) << 8);

include/jellyfish/sorted_dumper.hpp

@@ -73,7 +73,6 @@ class sorted_dumper : public dumper_t<storage_t>, public thread_exec {
     std::ostringstream           buffer;
     heap_type                    heap(ary_->max_reprobe_offset());
     token_type&                  token = ring_[i];
-    size_t                       count = 0;
     typename storage_t::key_type key;
 
     for(size_t id = i; id * block_info.second < ary_->size(); id += nb_threads_) {
@@ -85,7 +84,6 @@ class sorted_dumper : public dumper_t<storage_t>, public thread_exec {
         heap_item item = heap.head();
         if(item->val_ >= this->min() && item->val_ <= this->max())
           static_cast<D*>(this)->write_key_value_pair(buffer, item);
-        ++count;
         heap.pop();
         if(it.next())
           heap.push(it);

lib/generator_manager.cc

@@ -9,6 +9,9 @@
 #include <config.h>
 
 #include <unistd.h>
+#ifdef HAVE_SYS_PRCTL_H
+#include <sys/prctl.h>
+#endif
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
@@ -119,6 +122,9 @@ void generator_manager_base::start()  {
 
 
   // In child
+#ifdef PR_SET_PDEATHSIG
+  prctl(PR_SET_PDEATHSIG, SIGHUP);
+#endif
   if(setup_signal_handlers() == -1)
     exit(EXIT_FAILURE);
   start_commands(); // child start commands
@@ -190,6 +196,9 @@ void generator_manager_base::start_one_command(const std::string& command, int p
   }
 
   // In child
+#ifdef PR_SET_PDEATHSIG
+  prctl(PR_SET_PDEATHSIG, SIGHUP);
+#endif
   int dev_null = open_cloexec("/dev/null", O_RDONLY);
   if(dev_null != -1)
     dup2(dev_null, 0);

lib/jsoncpp.cpp

@@ -1733,7 +1733,7 @@ Value::CZString::operator<( const CZString &other ) const
 bool 
 Value::CZString::operator==( const CZString &other ) const 
 {
-   if ( cstr_ )
+   if ( cstr_ && other.cstr_ )
       return strcmp( cstr_, other.cstr_ ) == 0;
    return index_ == other.index_;
 }

m4/m4-ax_ext.m4

@@ -44,7 +44,7 @@
 #   and this notice are preserved. This file is offered as-is, without any
 #   warranty.
 
-#serial 17
+#serial 19
 
 AC_DEFUN([AX_EXT],
 [
@@ -160,22 +160,22 @@ AC_DEFUN([AX_EXT],
         ax_cv_have_sse_os_support_ext=no,
         if test "$((0x$edx_cpuid1>>25&0x01))" = 1; then
           AC_LANG_PUSH([C])
-          AC_TRY_RUN([
+          AC_RUN_IFELSE([AC_LANG_SOURCE([[
 #include <signal.h>
 #include <stdlib.h>
             /* No way at ring1 to ring3 in protected mode to check the CR0 and CR4
                control registers directly. Execute an SSE instruction.
                If it raises SIGILL then OS doesn't support SSE based instructions */
             void sig_handler(int signum){ exit(1); }
-            int main(){
+            int main(void){
               signal(SIGILL, sig_handler);
               /* SSE instruction xorps  %xmm0,%xmm0 */
               __asm__ __volatile__ (".byte 0x0f, 0x57, 0xc0");
               return 0;
-            }],
-            ax_cv_have_sse_os_support_ext=yes,
-            ax_cv_have_sse_os_support_ext=no,
-            ax_cv_have_sse_os_support_ext=no)
+            }]])],
+            [ax_cv_have_sse_os_support_ext=yes],
+            [ax_cv_have_sse_os_support_ext=no],
+            [ax_cv_have_sse_os_support_ext=no])
           AC_LANG_POP([C])
         fi
       ])