README.md

@@ -24,7 +24,7 @@ Most of the nucleotide based commands and options in USEARCH version 7 are suppo
 
 ## Getting Help
 
-If you can't find an answer in the [VSEARCH documentation](https://github.com/torognes/vsearch/releases/download/v2.8.0/vsearch_manual.pdf), please visit the [VSEARCH Web Forum](https://groups.google.com/forum/#!forum/vsearch-forum) to post a question or start a discussion.
+If you can't find an answer in the [VSEARCH documentation](https://github.com/torognes/vsearch/releases/download/v2.8.5/vsearch_manual.pdf), please visit the [VSEARCH Web Forum](https://groups.google.com/forum/#!forum/vsearch-forum) to post a question or start a discussion.
 
 ## Example
 
@@ -37,9 +37,9 @@ In the example below, VSEARCH will identify sequences in the file database.fsa t
 **Source distribution** To download the source distribution from a [release](https://github.com/torognes/vsearch/releases) and build the executable and the documentation, use the following commands:
 
 ```
-wget https://github.com/torognes/vsearch/archive/v2.8.0.tar.gz
-tar xzf v2.8.0.tar.gz
-cd vsearch-2.8.0
+wget https://github.com/torognes/vsearch/archive/v2.8.5.tar.gz
+tar xzf v2.8.5.tar.gz
+cd vsearch-2.8.5
 ./autogen.sh
 ./configure
 make
@@ -70,36 +70,36 @@ Binary distributions are provided for x86-64 systems running GNU/Linux, macOS (v
 Download the appropriate executable for your system using the following commands if you are using a Linux x86_64 system:
 
 ```sh
-wget https://github.com/torognes/vsearch/releases/download/v2.8.0/vsearch-2.8.0-linux-x86_64.tar.gz
-tar xzf vsearch-2.8.0-linux-x86_64.tar.gz
+wget https://github.com/torognes/vsearch/releases/download/v2.8.5/vsearch-2.8.5-linux-x86_64.tar.gz
+tar xzf vsearch-2.8.5-linux-x86_64.tar.gz
 ```
 
 Or these commands if you are using a Linux ppc64le system:
 
 ```sh
-wget https://github.com/torognes/vsearch/releases/download/v2.8.0/vsearch-2.8.0-linux-ppc64le.tar.gz
-tar xzf vsearch-2.8.0-linux-ppc64le.tar.gz
+wget https://github.com/torognes/vsearch/releases/download/v2.8.5/vsearch-2.8.5-linux-ppc64le.tar.gz
+tar xzf vsearch-2.8.5-linux-ppc64le.tar.gz
 ```
 
 Or these commands if you are using a Mac:
 
 ```sh
-wget https://github.com/torognes/vsearch/releases/download/v2.8.0/vsearch-2.8.0-macos-x86_64.tar.gz
-tar xzf vsearch-2.8.0-macos-x86_64.tar.gz
+wget https://github.com/torognes/vsearch/releases/download/v2.8.5/vsearch-2.8.5-macos-x86_64.tar.gz
+tar xzf vsearch-2.8.5-macos-x86_64.tar.gz
 ```
 
 Or if you are using Windows, download and extract (unzip) the contents of this file:
 
 ```
-https://github.com/torognes/vsearch/releases/download/v2.8.0/vsearch-2.8.0-win-x86_64.zip
+https://github.com/torognes/vsearch/releases/download/v2.8.5/vsearch-2.8.5-win-x86_64.zip
 ```
 
-Linux and Mac: You will now have the binary distribution in a folder called `vsearch-2.8.0-linux-x86_64` or `vsearch-2.8.0-macos-x86_64` in which you will find three subfolders `bin`, `man` and `doc`. We recommend making a copy or a symbolic link to the vsearch binary `bin/vsearch` in a folder included in your `$PATH`, and a copy or a symbolic link to the vsearch man page `man/vsearch.1` in a folder included in your `$MANPATH`. The PDF version of the manual is available in `doc/vsearch_manual.pdf`.
+Linux and Mac: You will now have the binary distribution in a folder called `vsearch-2.8.5-linux-x86_64` or `vsearch-2.8.5-macos-x86_64` in which you will find three subfolders `bin`, `man` and `doc`. We recommend making a copy or a symbolic link to the vsearch binary `bin/vsearch` in a folder included in your `$PATH`, and a copy or a symbolic link to the vsearch man page `man/vsearch.1` in a folder included in your `$MANPATH`. The PDF version of the manual is available in `doc/vsearch_manual.pdf`.
 
-Windows: You will now have the binary distribution in a folder called `vsearch-2.8.0-win-x86_64`. The vsearch executable is called `vsearch.exe`. The manual in PDF format is called `vsearch_manual.pdf`.
+Windows: You will now have the binary distribution in a folder called `vsearch-2.8.5-win-x86_64`. The vsearch executable is called `vsearch.exe`. The manual in PDF format is called `vsearch_manual.pdf`.
 
 
-**Documentation** The VSEARCH user's manual is available in the `man` folder in the form of a [man page](https://github.com/torognes/vsearch/blob/master/man/vsearch.1). A pdf version ([vsearch_manual.pdf](https://github.com/torognes/vsearch/releases/download/v2.8.0/vsearch_manual.pdf)) will be generated by `make`. To install the manpage manually, copy the `vsearch.1` file or a create a symbolic link to `vsearch.1` in a folder included in your `$MANPATH`. The manual in both formats is also available with the binary distribution. The manual in PDF form ([vsearch_manual.pdf](https://github.com/torognes/vsearch/releases/download/v2.8.0/vsearch_manual.pdf)) is also attached to the latest [release](https://github.com/torognes/vsearch/releases).
+**Documentation** The VSEARCH user's manual is available in the `man` folder in the form of a [man page](https://github.com/torognes/vsearch/blob/master/man/vsearch.1). A pdf version ([vsearch_manual.pdf](https://github.com/torognes/vsearch/releases/download/v2.8.5/vsearch_manual.pdf)) will be generated by `make`. To install the manpage manually, copy the `vsearch.1` file or a create a symbolic link to `vsearch.1` in a folder included in your `$MANPATH`. The manual in both formats is also available with the binary distribution. The manual in PDF form ([vsearch_manual.pdf](https://github.com/torognes/vsearch/releases/download/v2.8.5/vsearch_manual.pdf)) is also attached to the latest [release](https://github.com/torognes/vsearch/releases).
 
 
 ## Plugins, packages, and wrappers

configure.ac

@@ -2,7 +2,7 @@
 # Process this file with autoconf to produce a configure script.
 
 AC_PREREQ([2.63])
-AC_INIT([vsearch], [2.8.0], [torognes@ifi.uio.no])
+AC_INIT([vsearch], [2.8.5], [torognes@ifi.uio.no])
 AC_CANONICAL_TARGET
 AM_INIT_AUTOMAKE([subdir-objects])
 AC_LANG([C++])
@@ -14,8 +14,8 @@ MACOSX_DEPLOYMENT_TARGET="10.7"
 
 # Set default gcc and g++ options
 
-CFLAGS='-g'
-CXXFLAGS='-g'
+CFLAGS='-g -march=native'
+CXXFLAGS='-g -march=native'
 
 # Checks for programs.
 AC_PROG_CXX

debian/changelog

+vsearch (2.8.5-1) unstable; urgency=medium
+
+  * New upstream version
+  * Standards-Version: 4.2.1
+
+ -- Andreas Tille <tille@debian.org>  Wed, 26 Sep 2018 21:00:00 +0200
+
 vsearch (2.8.0-1) unstable; urgency=medium
 
   * New upstream version

debian/control

@@ -10,7 +10,7 @@ Build-Depends: debhelper (>= 11~),
                python-markdown,
                ghostscript,
                time
-Standards-Version: 4.1.4
+Standards-Version: 4.2.1
 Vcs-Browser: https://salsa.debian.org/med-team/vsearch
 Vcs-Git: https://salsa.debian.org/med-team/vsearch.git
 Homepage: https://github.com/torognes/vsearch/

debian/patches/compilerflags.patch

@@ -6,10 +6,10 @@ Author: Sascha Steinbiss <satta@debian.org>
  
  # Set default gcc and g++ options
  
--CFLAGS='-g'
--CXXFLAGS='-g'
-+#CFLAGS='-g'
-+#CXXFLAGS='-g'
+-CFLAGS='-g -march=native'
+-CXXFLAGS='-g -march=native'
++#CFLAGS='-g -march=native'
++#CXXFLAGS='-g -march=native'
  
  # Checks for programs.
  AC_PROG_CXX

man/vsearch.1

 .\" ============================================================================
-.TH vsearch 1 "April 24, 2018" "version 2.8.0" "USER COMMANDS"
+.TH vsearch 1 "September 26, 2018" "version 2.8.5" "USER COMMANDS"
 .\" ============================================================================
 .SH NAME
 vsearch \(em chimera detection, clustering, dereplication and
@@ -828,7 +828,8 @@ Dereplication and rereplication options:
 Merge strictly identical sequences contained in
 \fIfilename\fR. Identical sequences are defined as having the same
 length and the same string of nucleotides (case insensitive, T and U
-are considered the same).
+are considered the same). See the options \-\-sizein and \-\-sizeout
+to take into account and compute abundance values.
 .TP
 .BI \-\-derep_prefix \0filename
 Merge sequences with identical prefixes contained in \fIfilename\fR.
@@ -3394,6 +3395,29 @@ incorrect FASTA headers of consensus sequences after clustering.
 .TP
 .BR v2.8.0\~ "released April 24th, 2018"
 Added the fastq_maxdiffpct option to the fastq_mergepairs command.
+.TP
+.BR v2.8.1\~ "released June 22nd, 2018"
+Fixes for compilation warnings with GCC 8.
+.TP
+.BR v2.8.2\~ "released August 21st, 2018"
+Fix for wrong placement of semicolons in header lines in some cases
+when using the sizeout or xsize options. Reduced memory requirements
+for full-length dereplication in cases with many duplicate sequences.
+Improved wording of fastq_mergepairs report. Updated manual regarding
+use of sizein and sizeout with dereplication. Changed a compiler
+option.
+.TP
+.BR v2.8.3\~ "released August 31st, 2018"
+Fix for segmentation fault for \-\-derep_fulllength with \-\-uc.
+.TP
+.BR v2.8.4\~ "released September 3rd, 2018"
+Further reduce memory requirements for dereplication when not using
+the uc option. Fix output during subsampling when quiet or log options
+are in effect.
+.TP
+.BR v2.8.5\~ "released September 26th, 2018"
+Fixed a bug in fastq_eestats2 that caused the values for large lengths
+to be much too high when the input sequences had varying lengths.
 .RE
 .LP
 .\" ============================================================================
@@ -3403,7 +3427,3 @@ Added the fastq_maxdiffpct option to the fastq_mergepairs command.
 .\" visualize and output to pdf
 .\" man -l vsearch.1
 .\" man -t ./doc/vsearch.1 | ps2pdf - > ./doc/vsearch_manual.pdf
-.\"
-.\" INSTALL (sysadmin)
-.\" gzip -c vsearch.1 > vsearch.1.gz
-.\" mv vsearch.1.gz /usr/share/man/man1/

src/abundance.cc

@@ -149,12 +149,12 @@ void abundance_fprint_header_strip_size(FILE * fp,
     {
       if (start <= 1)
         {
-          if (end < header_length)
+          if (end < header_length - 1)
             fprintf(fp, "%s", header + end + 1);
         }
       else
         {
-          if (end == header_length)
+          if (end >= header_length - 1)
             fprintf(fp, "%.*s", start - 1, header);
           else
             fprintf(fp, "%.*s;%.*s",

src/align.cc

@@ -85,7 +85,7 @@ inline void pushop(char newop, char ** cigarendp, char * op, int * count)
       char buf[25];
       int len = sprintf(buf, "%d", *count);
       *cigarendp -= len;
-      strncpy(*cigarendp, buf, (size_t)len);
+      memcpy(*cigarendp, buf, (size_t)len);
     }
     *op = newop;
     *count = 1;
@@ -102,7 +102,7 @@ inline void finishop(char ** cigarendp, char * op, int * count)
       char buf[25];
       int len = sprintf(buf, "%d", *count);
       *cigarendp -= len;
-      strncpy(*cigarendp, buf, (size_t)len);
+      memcpy(*cigarendp, buf, (size_t)len);
     }
     *op = 0;
     *count = 0;

src/eestats.cc

@@ -465,15 +465,6 @@ void fastq_eestats2()
             }
         }
 
-      for (int x = 0; x < len_steps; x++)
-        {
-          uint64_t len_cutoff = opt_length_cutoffs_shortest + x * opt_length_cutoffs_increment;
-          if (len < len_cutoff)
-            for (int y = 0; y < opt_ee_cutoffs_count; y++)
-              if (ee <= opt_ee_cutoffs_values[y])
-                count_table[x * opt_ee_cutoffs_count + y]++;
-        }
-
       progress_update(fastq_get_position(h));
     }
   progress_done();

src/mergepairs.cc

@@ -1366,7 +1366,7 @@ void fastq_mergepairs()
 
   if (failed_repeat)
     fprintf(stderr,
-            "%10" PRIu64 "  potential tandem repeat\n",
+            "%10" PRIu64 "  multiple potential alignments\n",
             failed_repeat);
 
   if (failed_maxdiffs)

src/subsample.cc

@@ -111,9 +111,14 @@ void subsample()
     for(int i=0; i<dbsequencecount; i++)
       mass_total += db_getabundance(i);
 
+  if (! opt_quiet)
     fprintf(stderr, "Got %" PRIu64 " reads from %d amplicons\n",
             mass_total, dbsequencecount);
 
+  if (opt_log)
+    fprintf(fp_log, "Got %" PRIu64 " reads from %d amplicons\n",
+            mass_total, dbsequencecount);
+
 
   int * abundance = (int*) xmalloc(dbsequencecount * sizeof(int));
 
@@ -229,7 +234,10 @@ void subsample()
 
   xfree(abundance);
 
+  if (! opt_quiet)
     fprintf(stderr, "Subsampled %" PRIu64 " reads from %d amplicons\n", n, samples);
+  if (opt_log)
+    fprintf(fp_log, "Subsampled %" PRIu64 " reads from %d amplicons\n", n, samples);
 
   db_free();
 

src/util.cc

@@ -60,6 +60,8 @@
 
 #include "vsearch.h"
 
+//#define SHOW_RUSAGE
+
 static const char * progress_prompt;
 static uint64_t progress_next;
 static uint64_t progress_size;
@@ -186,7 +188,7 @@ int64_t getusec(void)
 
 void show_rusage()
 {
-#if 0
+#ifdef SHOW_RUSAGE
   double user_time = 0.0;
   double system_time = 0.0;
 

src/vsearch.h

@@ -58,7 +58,9 @@
 
 */
 
+#define __STDC_CONSTANT_MACROS 1
 #define __STDC_FORMAT_MACROS 1
+#define __STDC_LIMIT_MACROS 1
 #define __restrict
 
 #ifdef HAVE_CONFIG_H
@@ -87,6 +89,7 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <float.h>
+#include <stdint.h>
 #include <inttypes.h>
 #include <stdarg.h>