[irstlm] 30/146: Removed upstream_revision_487.patch.
Giulio Paci
giuliopaci-guest at moszumanska.debian.org
Tue May 17 07:37:04 UTC 2016
This is an automated email from the git hooks/post-receive script.
giuliopaci-guest pushed a commit to branch master
in repository irstlm.
commit 55a0704ed54cd69233ca4cbc14d539686b273eb9
Author: Giulio Paci <giuliopaci at gmail.com>
Date: Tue Sep 4 03:47:08 2012 +0200
Removed upstream_revision_487.patch.
---
debian/patches/upstream_revision_487.patch | 405 -----------------------------
1 file changed, 405 deletions(-)
diff --git a/debian/patches/upstream_revision_487.patch b/debian/patches/upstream_revision_487.patch
deleted file mode 100644
index bc286d8..0000000
--- a/debian/patches/upstream_revision_487.patch
+++ /dev/null
@@ -1,405 +0,0 @@
-Description: upstream changes since SVN revision 487
-Origin: upstream, https://irstlm.svn.sourceforge.net/svnroot/irstlm/trunk
-Forwarded: not-needed
-Applied-Upstream: revision 487, https://irstlm.svn.sourceforge.net/svnroot/irstlm/trunk
---- a/scripts/add-start-end.sh
-+++ b/scripts/add-start-end.sh
-@@ -1,4 +1,4 @@
--#! /bin/sh
-+#! /bin/bash
-
- #adds sentence start/end symbols to standard input and
- #trims words longer than 80 characters
---- a/scripts/build-lm-qsub.sh
-+++ b/scripts/build-lm-qsub.sh
-@@ -1,4 +1,4 @@
--##! /bin/sh
-+#! /bin/bash
-
- usage()
- {
-@@ -13,7 +13,7 @@
- -o Output gzipped LM, e.g. lm.gz
- -k Number of splits (default 5)
- -n Order of language model (default 3)
-- -t Directory for temporary files (default ./stat)
-+ -t Directory for temporary files (default ./stat_PID)
- -p Prune singleton n-grams (default false)
- -u Use uniform word frequency for dictionary splitting (default false)
- -q parameters for qsub ("-q <queue>", and any other)
-@@ -40,6 +40,8 @@
- #paths to scripts and commands in irstlm
- scr=$IRSTLM/bin
- bin=$IRSTLM/bin
-+gzip=`which gzip 2> /dev/null`;
-+gunzip=`which gunzip 2> /dev/null`;
-
- #check irstlm installation
- if [ ! -e $bin/dict -o ! -e $scr/split-dict.pl ]; then
-@@ -49,7 +51,7 @@
-
- #default parameters
- logfile=/dev/null
--tmpdir=stat$$
-+tmpdir=stat_$$
- order=3
- parts=3
- inpfile="";
-@@ -109,7 +111,7 @@
- ;;
- *)
- echo "wrong smoothing setting";
-- exiti 4;
-+ exit 4;
- esac
- ;;
- p)
-@@ -132,8 +134,8 @@
- done
-
-
--if [ $verbose ];then
--echo inpfile=\"$inpfile\" outfile=$outfile order=$order parts=$parts tmpdir=$tmpdir prune=$prune smoothing=$smoothing dictionary=$dictionary
-+if [ $verbose ]; then
-+echo inpfile=\"$inpfile\" outfile=$outfile order=$order parts=$parts tmpdir=$tmpdir prune=$prune smoothing=$smoothing dictionary=$dictionary verbose=$verbose
- fi
-
- if [ ! "$inpfile" -o ! "$outfile" ]; then
-@@ -152,17 +154,20 @@
- fi
-
- #check tmpdir
-+tmpdir_created=0;
- if [ ! -d $tmpdir ]; then
-- echo "Temporary directory $tmpdir not found";
-+ echo "Temporary directory $tmpdir does not exist";
- echo "creating $tmpdir";
- mkdir -p $tmpdir;
-+ tmpdir_created=1;
- else
-- echo "Cleaning temporary directory $tmpdir";
-- rm $tmpdir/dict* $tmpdir/ngram.dict.* $tmpdir/lm.dict.* $tmpdir/ikn.stat.dict.* 2> /dev/null
-+ echo "Cleaning temporary directory $tmpdir";
-+ rm -r $tmpdir 2> /dev/null
-+ if [ $? != 0 ]; then
-+ echo "Warning: some temporary files could not be removed"
-+ fi
- fi
-
--
--
- workingdir=`pwd | perl -pe 's/\/nfsmnt//g'`
- cd $workingdir
-
-@@ -198,13 +203,16 @@
-
- unset getpids
- echo "Extracting n-gram statistics for each word list"
-+echo "Important: dictionary must be ordered according to order of appearance of words in data"
-+echo "used to generate n-gram blocks, so that sub language model blocks results ordered too"
-+
- for sfx in ${suffix[@]} ; do
-
- (\
- qsub $queueparameters -b no -j yes -sync no -o $qsubout.$sfx -e $qsuberr.$sfx -N $qsubname-$sfx << EOF
- cd $workingdir
- echo exit status $?
--$bin/ngt -i="$inpfile" -n=$order -gooout=y -o="gzip -c > $tmpdir/ngram.dict.${sfx}.gz" -fd="$tmpdir/dict.${sfx}" $dictionary -iknstat="$tmpdir/ikn.stat.dict.${sfx}"
-+$bin/ngt -i="$inpfile" -n=$order -gooout=y -o="$gzip -c > $tmpdir/ngram.dict.${sfx}.gz" -fd="$tmpdir/dict.${sfx}" $dictionary -iknstat="$tmpdir/ikn.stat.dict.${sfx}"
- echo exit status $?
- echo
- EOF
-@@ -237,7 +245,7 @@
- cd $workingdir
- echo exit status $?
-
--$scr/build-sublm.pl $verbose $prune $smoothing "cat $tmpdir/ikn.stat.dict*" --size $order --ngrams "gunzip -c $tmpdir/ngram.dict.${sfx}.gz" -sublm $tmpdir/lm.dict.${sfx}
-+$scr/build-sublm.pl $verbose $prune $smoothing "cat $tmpdir/ikn.stat.dict*" --size $order --ngrams "$gunzip -c $tmpdir/ngram.dict.${sfx}.gz" -sublm $tmpdir/lm.dict.${sfx}
- echo exit status $?
-
- echo
-@@ -258,7 +266,7 @@
- cd $workingdir
- echo exit status $?
-
--$scr/build-sublm.pl $verbose $prune $smoothing --size $order --ngrams "gunzip -c $tmpdir/ngram.dict.${sfx}.gz" -sublm $tmpdir/lm.dict.${sfx}
-+$scr/build-sublm.pl $verbose $prune $smoothing --size $order --ngrams "$gunzip -c $tmpdir/ngram.dict.${sfx}.gz" -sublm $tmpdir/lm.dict.${sfx}
-
- echo
- EOF
-@@ -292,9 +300,16 @@
- ) 2>&1 > $qsublog
-
- echo "Cleaning temporary directory $tmpdir";
--rm -r $tmpdir 2> /dev/null
-+rm $tmpdir/* 2> /dev/null
- rm $qsubout* $qsuberr* $qsublog* 2> /dev/null
-
--exit
-+if [ $tmpdir_created -eq 1 ]; then
-+ echo "Removing temporary directory $tmpdir";
-+ rmdir $tmpdir 2> /dev/null
-+ if [ $? != 0 ]; then
-+ echo "Warning: the temporary directory could not be removed."
-+ fi
-+fi
-
-+exit 0
-
---- a/scripts/build-lm.sh
-+++ b/scripts/build-lm.sh
-@@ -1,4 +1,6 @@
--#! /bin/sh
-+#! /bin/bash
-+
-+set -m # Enable Job Control
-
- usage()
- {
-@@ -13,7 +15,7 @@
- -o Output gzipped LM, e.g. lm.gz
- -k Number of splits (default 5)
- -n Order of language model (default 3)
-- -t Directory for temporary files (default ./stat)
-+ -t Directory for temporary files (default ./stat_PID)
- -p Prune singleton n-grams (default false)
- -u Use uniform word frequency for dictionary splitting (default false)
- -s Smoothing methods: witten-bell (default), kneser-ney, improved-kneser-ney
-@@ -30,7 +32,7 @@
- fi
-
- #paths to scripts and commands in irstlm
--scr=$IRSTLM/bin/
-+scr=$IRSTLM/bin
- bin=$IRSTLM/bin
- gzip=`which gzip 2> /dev/null`;
- gunzip=`which gunzip 2> /dev/null`;
-@@ -43,7 +45,7 @@
-
- #default parameters
- logfile=/dev/null
--tmpdir=stat
-+tmpdir=stat_$$
- order=3
- parts=3
- inpfile="";
-@@ -143,13 +145,18 @@
- fi
-
- #check tmpdir
-+tmpdir_created=0;
- if [ ! -d $tmpdir ]; then
-- echo "Temporary directory $tmpdir not found";
-+ echo "Temporary directory $tmpdir does not exist";
- echo "creating $tmpdir";
- mkdir -p $tmpdir;
-+ tmpdir_created=1;
- else
-- echo "Cleaning temporary directory $tmpdir";
-- rm $tmpdir/dict* $tmpdir/ngram.dict.* $tmpdir/lm.dict.* $tmpdir/ikn.stat.* 2> /dev/null
-+ echo "Cleaning temporary directory $tmpdir";
-+ rm $tmpdir/* 2> /dev/null
-+ if [ $? != 0 ]; then
-+ echo "Warning: some temporary files could not be removed"
-+ fi
- fi
-
-
-@@ -166,9 +173,11 @@
- for sdict in $tmpdir/dict.*;do
- sdict=`basename $sdict`
- echo $sdict;
--$bin/ngt -i="$inpfile" -n=$order -gooout=y -o="$gzip -c > $tmpdir/ngram.${sdict}.gz" -fd="$tmpdir/$sdict" $dictionary -iknstat="$tmpdir/ikn.stat.$sdict" >> $logfile 2>&1
-+$bin/ngt -i="$inpfile" -n=$order -gooout=y -o="$gzip -c > $tmpdir/ngram.${sdict}.gz" -fd="$tmpdir/$sdict" $dictionary -iknstat="$tmpdir/ikn.stat.$sdict" >> $logfile 2>&1 &
- done
-
-+# Wait for all parallel jobs to finish
-+while [ 1 ]; do fg 2> /dev/null; [ $? == 1 ] && break; done
-
- echo "Estimating language models for each word list"
- for sdict in `ls $tmpdir/dict.*` ; do
-@@ -176,20 +185,32 @@
- echo $sdict;
-
- if [ $smoothing = "--kneser-ney" -o $smoothing = "--improved-kneser-ney" ]; then
--$scr/build-sublm.pl $verbose $prune $smoothing "cat $tmpdir/ikn.stat.dict.*" --size $order --ngrams "$gunzip -c $tmpdir/ngram.${sdict}.gz" -sublm $tmpdir/lm.$sdict >> $logfile #2>&1
-+$scr/build-sublm.pl $verbose $prune $smoothing "cat $tmpdir/ikn.stat.dict.*" --size $order --ngrams "$gunzip -c $tmpdir/ngram.${sdict}.gz" -sublm $tmpdir/lm.$sdict >> $logfile 2>&1 &
- else
--$scr/build-sublm.pl $verbose $prune $smoothing --size $order --ngrams "$gunzip -c $tmpdir/ngram.${sdict}.gz" -sublm $tmpdir/lm.$sdict >> $logfile #2>&1
-+$scr/build-sublm.pl $verbose $prune $smoothing --size $order --ngrams "$gunzip -c $tmpdir/ngram.${sdict}.gz" -sublm $tmpdir/lm.$sdict >> $logfile 2>&1 &
- fi
-
- done
-
-+# Wait for all parallel jobs to finish
-+while [ 1 ]; do fg 2> /dev/null; [ $? == 1 ] && break; done
-+
- echo "Merging language models into $outfile"
- $scr/merge-sublm.pl --size $order --sublm $tmpdir/lm.dict -lm $outfile >> $logfile 2>&1
-
- echo "Cleaning temporary directory $tmpdir";
--rm $tmpdir/dict* $tmpdir/ngram.dict.* $tmpdir/lm.dict.* $tmpdir/ikn.stat.dict.* 2> /dev/null
-+rm $tmpdir/* 2> /dev/null
-+
-+if [ $tmpdir_created -eq 1 ]; then
-+ echo "Removing temporary directory $tmpdir";
-+ rmdir $tmpdir 2> /dev/null
-+ if [ $? != 0 ]; then
-+ echo "Warning: the temporary directory could not be removed."
-+ fi
-+fi
-+
-+exit 0
-+
-+
-
--echo "Removing temporary directory $tmpdir";
--rmdir $tmpdir 2> /dev/null
-
--exit
---- a/scripts/rm-start-end.sh
-+++ b/scripts/rm-start-end.sh
-@@ -1,6 +1,6 @@
--#! /bin/sh
-+#! /bin/bash
-
--#rm star-end symbols
-+#rm start-end symbols
-
- sed 's/<s>//g' | sed 's/<\/s>//g' | sed 's/^ *//' | sed 's/ *$//' | sed '/^$/d'
-
---- a/scripts/split-ngt.sh
-+++ b/scripts/split-ngt.sh
-@@ -1,4 +1,4 @@
--#! /bin/sh
-+#! /bin/bash
-
- #usage:
- #ngt-split.sh <input> <output> <size> <parts>
---- a/src/lmtable.h
-+++ b/src/lmtable.h
-@@ -44,7 +44,7 @@
- #define MIN(a,b) (((a)<(b))?(a):(b))
-
- #define LMTMAXLEV 20
--#define MAX_LINE 1024
-+#define MAX_LINE 100000
-
- #ifndef LMTCODESIZE
- #define LMTCODESIZE (int)3
---- a/src/plsa.cpp
-+++ b/src/plsa.cpp
-@@ -54,6 +54,7 @@
- char *featurefile=NULL;
- char *basefile=NULL;
- char *hfile=NULL;
-+ char *tmphfile=NULL;
- char *tfile=NULL;
- char *wfile=NULL;
- char *ctfile=NULL;
-@@ -83,8 +84,8 @@
- "Model", CMDSTRINGTYPE, &basefile,
- "m", CMDSTRINGTYPE, &basefile,
-
-- "HFile", CMDSTRINGTYPE, &hfile,
-- "hf", CMDSTRINGTYPE, &hfile,
-+ "HFile", CMDSTRINGTYPE, &tmphfile,
-+ "hf", CMDSTRINGTYPE, &tmphfile,
-
- "WFile", CMDSTRINGTYPE, &wfile,
- "wf", CMDSTRINGTYPE, &wfile,
-@@ -119,6 +120,7 @@
- (char *)NULL
- );
-
-+
- GetParams(&argc, &argv, (char*) NULL);
-
- if (argc==1 || help){
-@@ -170,9 +172,14 @@
- exit(1);
- }
-
-- if (!hfile){
-+ if (!tmphfile){
- //set default value
-- strcpy(hfile,"hfff");
-+ hfile=new char[4+1];
-+ strcpy(hfile,"hfff");
-+ }else{
-+ //set the value of the parameter
-+ hfile=new char[strlen(tmphfile)+1];
-+ strcpy(hfile,tmphfile);
- }
-
- dictionary dict(dictfile);
-@@ -219,6 +226,7 @@
- tc.train(adafile,it,.0);
- }
- if (strcmp(hfile,"hfff")==0) system("rm -f hfff");
-+ delete hfile;
-
- exit(1);
- }
---- a/src/quantize-lm.cpp
-+++ b/src/quantize-lm.cpp
-@@ -31,7 +31,7 @@
- #include "math.h"
- #include "util.h"
-
--#define MAX_LINE 1024
-+#define MAX_LINE 100000
-
- //----------------------------------------------------------------------
- // Special type and global variable for the BIN CLUSTERING algorithm
---- a/src/util.h
-+++ b/src/util.h
-@@ -27,7 +27,7 @@
-
-
- #define LMTMAXLEV 20
--#define MAX_LINE 1024
-+#define MAX_LINE 100000
-
- std::string gettempfolder();
- void createtempfile(std::ofstream &fileStream, std::string &filePath, std::ios_base::openmode flags);
---- a/config.h.in
-+++ b/config.h.in
-@@ -33,6 +33,10 @@
- /* Define to 1 if you have the <unistd.h> header file. */
- #undef HAVE_UNISTD_H
-
-+/* Define to the sub-directory in which libtool stores uninstalled libraries.
-+ */
-+#undef LT_OBJDIR
-+
- /* Name of package */
- #undef PACKAGE
-
-@@ -48,6 +52,9 @@
- /* Define to the one symbol short name of this package. */
- #undef PACKAGE_TARNAME
-
-+/* Define to the home page for this package. */
-+#undef PACKAGE_URL
-+
- /* Define to the version of this package. */
- #undef PACKAGE_VERSION
-
---- a/regenerate-makefiles.sh
-+++ b/regenerate-makefiles.sh
-@@ -1,4 +1,4 @@
--#!/bin/bash
-+#!/bin/sh
-
- # NOTE:
- # Versions 1.9 (or higher) of aclocal and automake are required.
-@@ -14,7 +14,7 @@
- force=$1;
- # set parameter force to the value "--force" if you want to recreate all links to the autotools
-
--function die () {
-+die () {
- echo "$@" >&2
- exit 1
- }
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-science/packages/irstlm.git
More information about the debian-science-commits
mailing list