From 8c0033d1cd0cea9d09c281b62fc8dedf80810349 Mon Sep 17 00:00:00 2001
From: Veronique Legrand <vlegrand@pasteur.fr>
Date: Thu, 9 Dec 2021 11:39:03 +0100
Subject: [PATCH] fixed bug related to the handling of '+' char in scores; did
some leaning; updated version number
---
configure | 211 ++++++++++++++++++-------------------
configure.ac | 2 +-
src/FqBaseBackend.h | 8 +-
src/FqMainBackend.cpp | 1 +
src/ROCKparams.cpp | 80 ++++++--------
src/unit_test_fqreader.cpp | 2 +-
6 files changed, 147 insertions(+), 157 deletions(-)
diff --git a/configure b/configure
index b2f7a53..6eb122b 100755
--- a/configure
+++ b/configure
@@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.69 for rock 1.9.3.
+# Generated by GNU Autoconf 2.69 for rock 1.9.5.
#
#
# Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -576,8 +576,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='rock'
PACKAGE_TARNAME='rock'
-PACKAGE_VERSION='1.9.3'
-PACKAGE_STRING='rock 1.9.3'
+PACKAGE_VERSION='1.9.5'
+PACKAGE_STRING='rock 1.9.5'
PACKAGE_BUGREPORT=''
PACKAGE_URL=''
@@ -594,6 +594,7 @@ am__nodep
AMDEPBACKSLASH
AMDEP_FALSE
AMDEP_TRUE
+am__quote
am__include
DEPDIR
OBJEXT
@@ -679,8 +680,7 @@ PACKAGE_VERSION
PACKAGE_TARNAME
PACKAGE_NAME
PATH_SEPARATOR
-SHELL
-am__quote'
+SHELL'
ac_subst_files=''
ac_user_opts='
enable_option_checking
@@ -1236,7 +1236,7 @@ if test "$ac_init_help" = "long"; then
# Omit some internal or obsolete options to make the list less imposing.
# This message is too long to be a string in the A/UX 3.1 sh.
cat <<_ACEOF
-\`configure' configures rock 1.9.3 to adapt to many kinds of systems.
+\`configure' configures rock 1.9.5 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@@ -1307,7 +1307,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
- short | recursive ) echo "Configuration of rock 1.9.3:";;
+ short | recursive ) echo "Configuration of rock 1.9.5:";;
esac
cat <<\_ACEOF
@@ -1397,7 +1397,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
-rock configure 1.9.3
+rock configure 1.9.5
generated by GNU Autoconf 2.69
Copyright (C) 2012 Free Software Foundation, Inc.
@@ -1452,7 +1452,7 @@ cat >config.log <<_ACEOF
This file contains any messages produced by compilers while
running configure, to aid debugging if configure makes a mistake.
-It was created by rock $as_me 1.9.3, which was
+It was created by rock $as_me 1.9.5, which was
generated by GNU Autoconf 2.69. Invocation command line was
$ $0 $@
@@ -1942,7 +1942,7 @@ test -n "$target_alias" &&
NONENONEs,x,x, &&
program_prefix=${target_alias}-
-am__api_version='1.16'
+am__api_version='1.15'
# Find a good install program. We prefer a C program (faster),
# so one script is as good as another. But avoid the broken or
@@ -2428,7 +2428,7 @@ fi
# Define the identity of the package.
PACKAGE='rock'
- VERSION='1.9.3'
+ VERSION='1.9.5'
cat >>confdefs.h <<_ACEOF
@@ -2458,8 +2458,8 @@ MAKEINFO=${MAKEINFO-"${am_missing_run}makeinfo"}
# For better backward compatibility. To be removed once Automake 1.9.x
# dies out for good. For more background, see:
-# <https://lists.gnu.org/archive/html/automake/2012-07/msg00001.html>
-# <https://lists.gnu.org/archive/html/automake/2012-07/msg00014.html>
+# <http://lists.gnu.org/archive/html/automake/2012-07/msg00001.html>
+# <http://lists.gnu.org/archive/html/automake/2012-07/msg00014.html>
mkdir_p='$(MKDIR_P)'
# We need awk for the "check" target (and possibly the TAP driver). The
@@ -2510,7 +2510,7 @@ END
Aborting the configuration process, to ensure you take notice of the issue.
You can download and install GNU coreutils to get an 'rm' implementation
-that behaves properly: <https://www.gnu.org/software/coreutils/>.
+that behaves properly: <http://www.gnu.org/software/coreutils/>.
If you want to complete the configuration process using your problematic
'rm' anyway, export the environment variable ACCEPT_INFERIOR_RM_PROGRAM
@@ -3033,45 +3033,45 @@ DEPDIR="${am__leading_dot}deps"
ac_config_commands="$ac_config_commands depfiles"
-{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether ${MAKE-make} supports the include directive" >&5
-$as_echo_n "checking whether ${MAKE-make} supports the include directive... " >&6; }
-cat > confinc.mk << 'END'
+
+am_make=${MAKE-make}
+cat > confinc << 'END'
am__doit:
- @echo this is the am__doit target >confinc.out
+ @echo this is the am__doit target
.PHONY: am__doit
END
+# If we don't find an include directive, just comment out the code.
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for style of include used by $am_make" >&5
+$as_echo_n "checking for style of include used by $am_make... " >&6; }
am__include="#"
am__quote=
-# BSD make does it like this.
-echo '.include "confinc.mk" # ignored' > confmf.BSD
-# Other make implementations (GNU, Solaris 10, AIX) do it like this.
-echo 'include confinc.mk # ignored' > confmf.GNU
-_am_result=no
-for s in GNU BSD; do
- { echo "$as_me:$LINENO: ${MAKE-make} -f confmf.$s && cat confinc.out" >&5
- (${MAKE-make} -f confmf.$s && cat confinc.out) >&5 2>&5
- ac_status=$?
- echo "$as_me:$LINENO: \$? = $ac_status" >&5
- (exit $ac_status); }
- case $?:`cat confinc.out 2>/dev/null` in #(
- '0:this is the am__doit target') :
- case $s in #(
- BSD) :
- am__include='.include' am__quote='"' ;; #(
- *) :
- am__include='include' am__quote='' ;;
-esac ;; #(
- *) :
- ;;
+_am_result=none
+# First try GNU make style include.
+echo "include confinc" > confmf
+# Ignore all kinds of additional output from 'make'.
+case `$am_make -s -f confmf 2> /dev/null` in #(
+*the\ am__doit\ target*)
+ am__include=include
+ am__quote=
+ _am_result=GNU
+ ;;
esac
- if test "$am__include" != "#"; then
- _am_result="yes ($s style)"
- break
- fi
-done
-rm -f confinc.* confmf.*
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: ${_am_result}" >&5
-$as_echo "${_am_result}" >&6; }
+# Now try BSD make style include.
+if test "$am__include" = "#"; then
+ echo '.include "confinc"' > confmf
+ case `$am_make -s -f confmf 2> /dev/null` in #(
+ *the\ am__doit\ target*)
+ am__include=.include
+ am__quote="\""
+ _am_result=BSD
+ ;;
+ esac
+fi
+
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $_am_result" >&5
+$as_echo "$_am_result" >&6; }
+rm -f confinc confmf
# Check whether --enable-dependency-tracking was given.
if test "${enable_dependency_tracking+set}" = set; then :
@@ -3921,7 +3921,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
# report actual input values of CONFIG_FILES etc. instead of their
# values after options handling.
ac_log="
-This file was extended by rock $as_me 1.9.3, which was
+This file was extended by rock $as_me 1.9.5, which was
generated by GNU Autoconf 2.69. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@@ -3978,7 +3978,7 @@ _ACEOF
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
ac_cs_version="\\
-rock config.status 1.9.3
+rock config.status 1.9.5
configured by $0, generated by GNU Autoconf 2.69,
with options \\"\$ac_cs_config\\"
@@ -4086,7 +4086,7 @@ cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
#
# INIT-COMMANDS
#
-AMDEP_TRUE="$AMDEP_TRUE" MAKE="${MAKE-make}"
+AMDEP_TRUE="$AMDEP_TRUE" ac_aux_dir="$ac_aux_dir"
_ACEOF
@@ -4534,35 +4534,29 @@ $as_echo "$as_me: executing $ac_file commands" >&6;}
# Older Autoconf quotes --file arguments for eval, but not when files
# are listed without --file. Let's play safe and only enable the eval
# if we detect the quoting.
- # TODO: see whether this extra hack can be removed once we start
- # requiring Autoconf 2.70 or later.
- case $CONFIG_FILES in #(
- *\'*) :
- eval set x "$CONFIG_FILES" ;; #(
- *) :
- set x $CONFIG_FILES ;; #(
- *) :
- ;;
-esac
+ case $CONFIG_FILES in
+ *\'*) eval set x "$CONFIG_FILES" ;;
+ *) set x $CONFIG_FILES ;;
+ esac
shift
- # Used to flag and report bootstrapping failures.
- am_rc=0
- for am_mf
+ for mf
do
# Strip MF so we end up with the name of the file.
- am_mf=`$as_echo "$am_mf" | sed -e 's/:.*$//'`
- # Check whether this is an Automake generated Makefile which includes
- # dependency-tracking related rules and includes.
- # Grep'ing the whole file directly is not great: AIX grep has a line
+ mf=`echo "$mf" | sed -e 's/:.*$//'`
+ # Check whether this is an Automake generated Makefile or not.
+ # We used to match only the files named 'Makefile.in', but
+ # some people rename them; so instead we look at the file content.
+ # Grep'ing the first line is not enough: some people post-process
+ # each Makefile.in and add a new line on top of each file to say so.
+ # Grep'ing the whole file is not good either: AIX grep has a line
# limit of 2048, but all sed's we know have understand at least 4000.
- sed -n 's,^am--depfiles:.*,X,p' "$am_mf" | grep X >/dev/null 2>&1 \
- || continue
- am_dirpart=`$as_dirname -- "$am_mf" ||
-$as_expr X"$am_mf" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \
- X"$am_mf" : 'X\(//\)[^/]' \| \
- X"$am_mf" : 'X\(//\)$' \| \
- X"$am_mf" : 'X\(/\)' \| . 2>/dev/null ||
-$as_echo X"$am_mf" |
+ if sed -n 's,^#.*generated by automake.*,X,p' "$mf" | grep X >/dev/null 2>&1; then
+ dirpart=`$as_dirname -- "$mf" ||
+$as_expr X"$mf" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \
+ X"$mf" : 'X\(//\)[^/]' \| \
+ X"$mf" : 'X\(//\)$' \| \
+ X"$mf" : 'X\(/\)' \| . 2>/dev/null ||
+$as_echo X"$mf" |
sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{
s//\1/
q
@@ -4580,48 +4574,53 @@ $as_echo X"$am_mf" |
q
}
s/.*/./; q'`
- am_filepart=`$as_basename -- "$am_mf" ||
-$as_expr X/"$am_mf" : '.*/\([^/][^/]*\)/*$' \| \
- X"$am_mf" : 'X\(//\)$' \| \
- X"$am_mf" : 'X\(/\)' \| . 2>/dev/null ||
-$as_echo X/"$am_mf" |
- sed '/^.*\/\([^/][^/]*\)\/*$/{
+ else
+ continue
+ fi
+ # Extract the definition of DEPDIR, am__include, and am__quote
+ # from the Makefile without running 'make'.
+ DEPDIR=`sed -n 's/^DEPDIR = //p' < "$mf"`
+ test -z "$DEPDIR" && continue
+ am__include=`sed -n 's/^am__include = //p' < "$mf"`
+ test -z "$am__include" && continue
+ am__quote=`sed -n 's/^am__quote = //p' < "$mf"`
+ # Find all dependency output files, they are included files with
+ # $(DEPDIR) in their names. We invoke sed twice because it is the
+ # simplest approach to changing $(DEPDIR) to its actual value in the
+ # expansion.
+ for file in `sed -n "
+ s/^$am__include $am__quote\(.*(DEPDIR).*\)$am__quote"'$/\1/p' <"$mf" | \
+ sed -e 's/\$(DEPDIR)/'"$DEPDIR"'/g'`; do
+ # Make sure the directory exists.
+ test -f "$dirpart/$file" && continue
+ fdir=`$as_dirname -- "$file" ||
+$as_expr X"$file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \
+ X"$file" : 'X\(//\)[^/]' \| \
+ X"$file" : 'X\(//\)$' \| \
+ X"$file" : 'X\(/\)' \| . 2>/dev/null ||
+$as_echo X"$file" |
+ sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{
s//\1/
q
}
- /^X\/\(\/\/\)$/{
+ /^X\(\/\/\)[^/].*/{
s//\1/
q
}
- /^X\/\(\/\).*/{
+ /^X\(\/\/\)$/{
+ s//\1/
+ q
+ }
+ /^X\(\/\).*/{
s//\1/
q
}
s/.*/./; q'`
- { echo "$as_me:$LINENO: cd "$am_dirpart" \
- && sed -e '/# am--include-marker/d' "$am_filepart" \
- | $MAKE -f - am--depfiles" >&5
- (cd "$am_dirpart" \
- && sed -e '/# am--include-marker/d' "$am_filepart" \
- | $MAKE -f - am--depfiles) >&5 2>&5
- ac_status=$?
- echo "$as_me:$LINENO: \$? = $ac_status" >&5
- (exit $ac_status); } || am_rc=$?
+ as_dir=$dirpart/$fdir; as_fn_mkdir_p
+ # echo "creating $dirpart/$file"
+ echo '# dummy' > "$dirpart/$file"
+ done
done
- if test $am_rc -ne 0; then
- { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5
-$as_echo "$as_me: error: in \`$ac_pwd':" >&2;}
-as_fn_error $? "Something went wrong bootstrapping makefile fragments
- for automatic dependency tracking. Try re-running configure with the
- '--disable-dependency-tracking' option to at least be able to build
- the package (albeit without support for automatic dependency tracking).
-See \`config.log' for more details" "$LINENO" 5; }
- fi
- { am_dirpart=; unset am_dirpart;}
- { am_filepart=; unset am_filepart;}
- { am_mf=; unset am_mf;}
- { am_rc=; unset am_rc;}
- rm -f conftest-deps.mk
}
;;
diff --git a/configure.ac b/configure.ac
index 4455482..fdf809f 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1,7 +1,7 @@
dnl Process this file with autoconf to produce a configure script.
AC_PREREQ(2.59)
-AC_INIT(rock, 1.9.3)
+AC_INIT(rock, 1.9.5)
AC_CANONICAL_SYSTEM
diff --git a/src/FqBaseBackend.h b/src/FqBaseBackend.h
index a91a8ac..5e73247 100644
--- a/src/FqBaseBackend.h
+++ b/src/FqBaseBackend.h
@@ -89,8 +89,8 @@ protected:
// for writing undefined (reads that don't contain a sufficient number of correct k-mers)
// correct k-mers are k-mers that contain only nucleotides with a quality score greater than a given threshold (default is 0).
// expected minimum number of correct k-mers is provided by the user. Default is 1
- char * undef_filename;
- int undef_f_desc;
+ //char * undef_filename;
+ //int undef_f_desc;
static FasqQualThreshold qual_thres;
@@ -121,8 +121,8 @@ public:
f_id=0;
o_f_desc=-1;
o_filename=NULL;
- undef_f_desc=-1;
- undef_filename=NULL;
+ //undef_f_desc=-1;
+ // undef_filename=NULL;
o_buf=NULL;
pos_in_w_buf=NULL;
diff --git a/src/FqMainBackend.cpp b/src/FqMainBackend.cpp
index fe85cff..bb37e78 100644
--- a/src/FqMainBackend.cpp
+++ b/src/FqMainBackend.cpp
@@ -158,6 +158,7 @@ void FqMainBackend::processBuf(T_buf_info& buf_info,unsigned char f_id,unsigned
}
break;
case k_read_qual_start:
+ if (qual_score) goto inc_score; // In this case we are already processing the read score. The + char is simply phred score 43-33=10 if phred33.
qual_score=1;
fq_rec_info.nb_k_mers_in_error=0;
fq_rec_info.nb_k_mers_in_error_in_PE2=0;
diff --git a/src/ROCKparams.cpp b/src/ROCKparams.cpp
index 634642d..38a066f 100755
--- a/src/ROCKparams.cpp
+++ b/src/ROCKparams.cpp
@@ -37,51 +37,41 @@ const int ROCKparams::output_ext;
const int ROCKparams::undef_ext;
-/*
-void ROCKparams::computeLambda() {
- unsigned long tmp=parms.filter_size;
- tmp*=1073741824; // this is in fact 1024*1024*1024.
- parms.lambda=tmp/UINT_MAX;
- if (parms.kappa>get_mask<unsigned char>::value) parms.lambda=parms.lambda/sizeof(unsigned short);
-}*/
-/*
-int ROCKparams::getfilterPEMode() {
- return parms.filter_PE_separately;
-}*/
+
void usage(int status) {
-cout<<"ROCK 1.9.3 Copyright (C) 2016-2021 Institut Pasteur"<<endl;
-cout<<endl;
-cout<<"Reducing Over-Covering K-mers within FASTQ file(s)"<<endl;
-cout<<endl;
-cout<<"USAGE: rock [options] [files]"<<endl;
-cout<<endl;
-cout<<"OPTIONS:"<<endl;
-cout<<" -i <file> file containing the name(s) of the input FASTQ file(s) to"<<endl;
-cout<<" process; single-end: one file name per line; paired-end:"<<endl;
-cout<<" two file names per line separated by a comma; up to 15"<<endl;
-cout<<" FASTQ file names can be specified; of note, input file"<<endl;
-cout<<" name(s) can also be specified as program argument(s)"<<endl;
-cout<<" -o <file> file containing the name(s) of the output FASTQ file(s);"<<endl;
-cout<<" FASTQ file name(s) should be structured in the same way as"<<endl;
-cout<<" the file specified in option -i."<<endl;
-cout<<" -k <int> k-mer length (default 25)"<<endl;
-cout<<" -c <int> lower-bound k-mer coverage depth threshold (default: 0)"<<endl;
-cout<<" -C <int> upper-bound k-mer coverage depth threshold (default: 70)"<<endl;
-cout<<" -l <int> number of hashing function(s) (default: 4)"<<endl;
-cout<<" -n <int> expected total number of distinct k-mers within the input"<<endl;
-cout<<" read sequences; not compatible with option -l."<<endl;
-cout<<" -f <float> maximum expected false positive probability when computing"<<endl;
-cout<<" the optimal number of hashing functions from the number of"<<endl;
-cout<<" distinct k-mers specified with option -n (default: 0.05)."<<endl;
-cout<<" -q <int> sets as valid only k-mers made up of nucleotides with"<<endl;
-cout<<" Phred score (+33 offset) above this cutoff (default: 0)"<<endl;
-cout<<" -m <int> minimum number of valid k-mer(s) to consider a read; all"<<endl;
-cout<<" non-considered reads are written into output file(s) with"<<endl;
-cout<<" extension undefined.fastq (default: 1)"<<endl;
-cout<<" -v verbose mode"<<endl;
-cout<<" -h prints this message and exit"<<endl;
-exit(status);
+ cout<<endl;
+ cout<<"ROCK 1.9.5 Copyright (C) 2016-2021 Institut Pasteur"<<endl;
+ cout<<endl;
+ cout<<"Reducing Over-Covering K-mers within FASTQ file(s)"<<endl;
+ cout<<endl;
+ cout<<"USAGE: rock [options] [files]"<<endl;
+ cout<<endl;
+ cout<<"OPTIONS:"<<endl;
+ cout<<" -i <file> file containing the name(s) of the input FASTQ file(s) to"<<endl;
+ cout<<" process; single-end: one file name per line; paired-end:"<<endl;
+ cout<<" two file names per line separated by a comma; up to 15"<<endl;
+ cout<<" FASTQ file names can be specified; of note, input file"<<endl;
+ cout<<" name(s) can also be specified as program argument(s)"<<endl;
+ cout<<" -o <file> file containing the name(s) of the output FASTQ file(s);"<<endl;
+ cout<<" FASTQ file name(s) should be structured in the same way as"<<endl;
+ cout<<" the file specified in option -i."<<endl;
+ cout<<" -k <int> k-mer length (default 25)"<<endl;
+ cout<<" -c <int> lower-bound k-mer coverage depth threshold (default: 0)"<<endl;
+ cout<<" -C <int> upper-bound k-mer coverage depth threshold (default: 70)"<<endl;
+ cout<<" -l <int> number of hashing function(s) (default: 4)"<<endl;
+ cout<<" -n <int> expected total number of distinct k-mers within the input"<<endl;
+ cout<<" read sequences; not compatible with option -l."<<endl;
+ cout<<" -f <float> maximum expected false positive probability when computing"<<endl;
+ cout<<" the optimal number of hashing functions from the number of"<<endl;
+ cout<<" distinct k-mers specified with option -n (default: 0.05)."<<endl;
+ cout<<" -q <int> sets as valid only k-mers made up of nucleotides with"<<endl;
+ cout<<" Phred score (+33 offset) above this cutoff (default: 0)"<<endl;
+ cout<<" -m <int> minimum number of valid k-mer(s) to consider a read;"<<endl;
+ cout<<" -v verbose mode"<<endl;
+ cout<<" -h prints this message and exit"<<endl;
+ cout<<endl;
+ exit(status);
}
@@ -223,10 +213,10 @@ void ROCKparams::changeExtension(string& FName,const int& extension_type) { // c
if (o_found!=std::string::npos) FName.replace(o_found,1,".rock.");
else FName.append(".rock.fq");
}
- else {
+/* else {
if (o_found!=std::string::npos) FName.replace(o_found,1,".undefined.");
else FName.append(".undefined.fq");
- }
+ }*/
}
string ROCKparams::genUndefFilename(const string& fname,const string& dname) {
diff --git a/src/unit_test_fqreader.cpp b/src/unit_test_fqreader.cpp
index 22e1104..bb72773 100644
--- a/src/unit_test_fqreader.cpp
+++ b/src/unit_test_fqreader.cpp
@@ -89,7 +89,7 @@ void test_processSingleFile() {
}
/*
- * Expects a given minimum of k_mers to be present in the read or else it is dumped as undefined
+ * Expects a given minimum of k_mers to be present in the read.
*/
void test_processSingleFileWithMQOption() {
srp sr;
--
GitLab