Merge pull request #727 from clarin-eric/devel

@TomazErjavec, merging to main

.github/actions/ParlaMintStatus/status.sh

@@ -2,9 +2,9 @@ pwd
 cd ParlaMint
 
 changed_files=$(git diff --name-only HEAD HEAD~1)
-parla_changed=$(echo "$changed_files"|grep 'Data/ParlaMint-.*/'|sed -n 's/^Data\/ParlaMint-\([-A-Z]*\).*.xml$/\1/p'|sort|uniq|tr '\n' ' '|sed 's/ *$//')
+parla_changed=$(echo "$changed_files"|grep 'Sample/ParlaMint-.*/'|sed -n 's/^Sample\/ParlaMint-\([-A-Z]*\).*.xml$/\1/p'|sort|uniq|tr '\n' ' '|sed 's/ *$//')
 scripts_changed=$(echo "$changed_files"|egrep  "^(Schema|Scripts)")
-parla_all=$(echo Data/ParlaMint-*|sed 's/Data\/ParlaMint-\([-A-Z]*\)/\1/g'|sort)
+parla_all=$(echo Sample/ParlaMint-*|sed 's/Sample\/ParlaMint-\([-A-Z]*\)/\1/g'|sort)
 
 
 parla_process=$(test -z "${parla_changed}" && echo "${parla_all}" || echo "${parla_changed}")
@@ -13,8 +13,8 @@ parla_process=$(echo "[\"$parla_process\"]"|sed 's/  */","/g'| sed 's/^\[""\]$/[
 parla_changed_size=0
 for parla in $parla_changed;
 do
-  size=$(find Data/ParlaMint-$parla -type f -name "ParlaMint-$parla*.xml"  -print0 | du -c --block-size=1000000 --files0-from=-|tail -1|cut -f 1)
-  echo "::notice:: Data/ParlaMint-$parla size =${size} MB"
+  size=$(find Sample/ParlaMint-$parla -type f -name "ParlaMint-$parla*.xml"  -print0 | du -c --block-size=1000000 --files0-from=-|tail -1|cut -f 1)
+  echo "::notice:: Sample/ParlaMint-$parla size =${size} MB"
   parla_changed_size=$(echo "$parla_changed_size+$size"|bc)
 done
 

.github/actions/ParlaMintValidate/validate.sh

@@ -3,7 +3,7 @@ cd ParlaMint
 
 FAIL=0
 
-DATADIR=Data
+DATADIR=Sample
 
 TESTDIR="SAMPLE/Parla-CLARIN"
 mkdir -p $TESTDIR

.github/workflows/createSample.yml

@@ -54,27 +54,27 @@ jobs:
             DIR="${{env.SAMPLE_DIR}}/$parla"
             mkdir $DIR
             echo "::notice::New sample files [$parla] TEXT"
-            java -jar $GITHUB_WORKSPACE/Saxon.jar outDir=$DIR revRespPers='GitHub Action' -xsl:${{env.SAMPLE_SCRIPT}} Data/ParlaMint-$parla/ParlaMint-$parla.xml
+            java -jar $GITHUB_WORKSPACE/Saxon.jar outDir=$DIR revRespPers='GitHub Action' -xsl:${{env.SAMPLE_SCRIPT}} Sample/ParlaMint-$parla/ParlaMint-$parla.xml
 
             echo "::notice::New sample files [$parla] ANNOTATED"
-            if [ -f "Data/ParlaMint-$parla/ParlaMint-$parla.ana.xml" ] ; then
-              java -jar $GITHUB_WORKSPACE/Saxon.jar outDir=$DIR revRespPers='GitHub Action' -xsl:${{env.SAMPLE_SCRIPT}} Data/ParlaMint-$parla/ParlaMint-$parla.ana.xml
+            if [ -f "Sample/ParlaMint-$parla/ParlaMint-$parla.ana.xml" ] ; then
+              java -jar $GITHUB_WORKSPACE/Saxon.jar outDir=$DIR revRespPers='GitHub Action' -xsl:${{env.SAMPLE_SCRIPT}} Sample/ParlaMint-$parla/ParlaMint-$parla.ana.xml
             else
               echo "::warning::skipping annotated conversion - missing corpus root file"
             fi
-            echo "::notice::Move new sample files to Data/ParlaMint-$parla"
-            ls $DIR|grep "ParlaMint-$parla[\.\_]"|xargs -I {} mv $DIR/{} Data/ParlaMint-$parla/
+            echo "::notice::Move new sample files to Sample/ParlaMint-$parla"
+            ls $DIR|grep "ParlaMint-$parla[\.\_]"|xargs -I {} mv $DIR/{} Sample/ParlaMint-$parla/
             echo "::endgroup::"
           done
       - name: Remove unused data from repository
         run: |
           cd $GITHUB_WORKSPACE/ParlaMint
           shopt -s globstar
           for parla in $(jq -r '.[]' <<< '${{needs.Changes.outputs.parla_changed}}' ); do
-            for file in $(echo Data/ParlaMint-$parla/**/ParlaMint-$parla\_*) ; do
+            for file in $(echo Sample/ParlaMint-$parla/**/ParlaMint-$parla\_*) ; do
               echo "testing $file"
-              xmlfile=$(echo $file|sed -E 's/(-meta\.tsv|\.conllu|\.txt|\.vert)$/.xml/;s/^Data\/ParlaMint-[^\/]*\///')
-              cat Data/ParlaMint-$parla/ParlaMint-$parla{,.ana}.xml | grep -Fq "$xmlfile" || git rm "$file"
+              xmlfile=$(echo $file|sed -E 's/(-meta\.tsv|\.conllu|\.txt|\.vert)$/.xml/;s/^Sample\/ParlaMint-[^\/]*\///')
+              cat Sample/ParlaMint-$parla/ParlaMint-$parla{,.ana}.xml | grep -Fq "$xmlfile" || git rm "$file"
             done
           done
       - name: Create Derived files and Validate ${{needs.Changes.outputs.parla_changed}}
@@ -87,8 +87,8 @@ jobs:
         run: |
           cd $GITHUB_WORKSPACE/ParlaMint
           for parla in $(jq -r '.[]' <<< '${{needs.Changes.outputs.parla_changed}}' ); do
-            git add Data/ParlaMint-$parla/ParlaMint-*.{txt,tsv,conllu,vert,xml} || echo "::warning:: $parla suppress fatal: pathspec '<FILE>' did not match any files"
-            git diff --name-only Data/ParlaMint-$parla
+            git add Sample/ParlaMint-$parla/ParlaMint-*.{txt,tsv,conllu,vert,xml} || echo "::warning:: $parla suppress fatal: pathspec '<FILE>' did not match any files"
+            git diff --name-only Sample/ParlaMint-$parla
           done
           git status
           git commit -a -m "action: generating ParlaMint-${{needs.Changes.outputs.parla_changed}} sample files with #${{github.event.number}}"

.gitignore

@@ -4,5 +4,3 @@ nohup.*
 *.zip
 *.tar
 *.tgz
-validation*
-Data/TMP

CONTRIBUTING.md

@@ -2,7 +2,8 @@
 
 ## Git and GitHub
 
-Sample data should be pushed to the Data branch of the ParlaMint repository directly into the parliament folder (*`Data/ParlaMint-XX`*) in a flat structure of files.
+Sample data should be pushed to the Data branch of the ParlaMint repository directly into the samples folder
+(*`Samples/ParlaMint-XX`*) in a flat structure of files.
 
 ### Setup
 
@@ -43,16 +44,16 @@ git pull
 
 ```bash
 # replace XX with your country code
-git add Data/ParlaMint-XX/*.xml
-git commit -m 'XX' Data/ParlaMint-XX/ParlaMint-XX*.xml
+git add Samples/ParlaMint-XX/*.xml
+git commit -m 'XX' Samples/ParlaMint-XX/ParlaMint-XX*.xml
 ```
 
 - Add common content (tagUsages, word extents, version):
 
-  - edit files and save in `Data/ParlaMint-XX/add-common-content/ParlaMint-XX/` folder: `make add-common-content-XX`
+  - edit files and save in `Samples/ParlaMint-XX/add-common-content/ParlaMint-XX/` folder: `make add-common-content-XX`
   - check if modified files are ok
-  - replace `Data/ParlaMint-XX/*.xml` files with `Data/ParlaMint-XX/add-common-content/ParlaMint-XX/` content
-  - commit changes `git commit -m 'XX add common content' Data/ParlaMint-XX/ParlaMint-XX*.xml`
+  - replace `Samples/ParlaMint-XX/*.xml` files with `Samples/ParlaMint-XX/add-common-content/ParlaMint-XX/` content
+  - commit changes `git commit -m 'XX add common content' Samples/ParlaMint-XX/ParlaMint-XX*.xml`
 
 - Push data to your Fork:
 

Corpora/Logs/README.md

@@ -0,0 +1,10 @@
+# ParlaMint Corpora Log files
+
+This directory contains the log files made by the release pipeline.
+For each corpus there are 3 files:
+* `ParlaMint-XX.log`: the complete log for ParlaMint-XX
+* `ParlaMint-XX.warn.log`: warnings only
+* `ParlaMint-XX.error.log`: errors only
+
+The logs above are also present with the -en suffix (e.g. `ParlaMint-XX-en.log`) which are the logs for corpora
+which have been machine translated to English.

Distro/Makefile → Corpora/Makefile

@@ -1,55 +1,87 @@
+## Transliteration tests
+test-translit4:
+	$s tsv=0.tsv -xsl:bin/trans-tsv2tei.xsl Sources-TEI/ParlaMint-BG.TEI/ParlaMint-BG-listPerson.xml > ParlaMint-BG-listPerson.xml
+test-translit3:
+	bin/trans-execute.pl Sources-TEI/ParlaMint-BG.TEI/ParlaMint-BG-listPerson.xml
+test-translit2:
+	$s -xsl:bin/trans-tei2tsv.xsl Sources-TEI/ParlaMint-BG.TEI/ParlaMint-BG-listOrg.xml > ParlaMint-BG-listOrg.tsv
+test-translit1:
+	$s -xsl:bin/trans-tei2tsv.xsl Sources-TEI/ParlaMint-BG.TEI/ParlaMint-BG-listPerson.xml > ParlaMint-BG-listPerson.tsv
+	$s -xsl:bin/trans-tei2tsv.xsl Sources-TEI/ParlaMint-GR.TEI/ParlaMint-GR-listPerson.xml > ParlaMint-GR-listPerson.tsv
+	$s -xsl:bin/trans-tei2tsv.xsl Sources-TEI/ParlaMint-UA.TEI/ParlaMint-UA-listPerson.xml > ParlaMint-UA-listPerson.tsv
+
+######## Merging taxonomies
+
+TAXONOMIES-TEI = subcorpus speaker_types parla.legislature
+TAXONOMIES-ANA = NER
+
+merge-taxos-nohup:
+	nohup time make merge-taxos 2> Taxonomies/ParlaMint-taxonomy-merge.log > Logs/ParlaMint-taxonomy.log &
+
+merge-taxos:
+	for TAXONOMY in ${TAXONOMIES-TEI}; do \
+	$s template=../Corpora/Taxonomies/ParlaMint-taxonomy-$${TAXONOMY}.template.xml \
+	-xsl:../Scripts/parlamint-merge-taxonomy.xsl Master/ParlaMint.xml \
+	> Taxonomies/ParlaMint-taxonomy-$${TAXONOMY}.xml; \
+	done;
+	for TAXONOMY in ${TAXONOMIES-ANA}; do \
+	$s template=../Corpora/Taxonomies/ParlaMint-taxonomy-$${TAXONOMY}.ana.template.xml \
+	-xsl:../Scripts/parlamint-merge-taxonomy.xsl Master/ParlaMint.ana.xml \
+	> Taxonomies/ParlaMint-taxonomy-$${TAXONOMY}.ana.xml; \
+	done;
+	${vta} Taxonomies/ParlaMint-taxonomy-*.xml
+
 ############### Makefile for making a distributable version of the ParlaMint and ParlaMint-en corpora
 
 ### VARIABLES
 
 # All ParlaMint II corpora
 # CORPORA = AT BA BE BG CZ DK EE ES ES-CT ES-GA ES-PV FI FR GB GR HR HU IS IT LT LV NL NO PL PT RS RO SE SI TR UA
-# Missing corpora: ES ES-PV FI LT RO
+# Missing corpora: FI LT RO ES-PV
 
-######## SUBMITTED CORPORA FOR V 3.0
-# CORPORA = AT BA BE BG CZ DK EE ES-CT ES-GA FR GB GR HR HU IS IT LV NL NO PL PT RS SE SI TR UA
+######## SUBMITTED CORPORA FOR V 3.1
+# CORPORA = AT BA BE BG CZ DK EE ES ES-CT ES-GA FR GB GR HR HU IS IT LV NL NO PL PT RS SE SI TR UA
 
 # Partial runs:
 CORPORA = AT
 
-######## MTed CORPORA FOR V 3.0
-MT-CORPORA = AT-en BA-en BE-en BG-en CZ-en DK-en EE-en ES-CT-en ES-GA-en FR-en GR-en HR-en HU-en IS-en IT-en LV-en NL-en NO-en PL-en PT-en RS-en SE-en SI-en TR-en UA-en
+######## MTed CORPORA FOR V 3.1
+MT-CORPORA = AT-en BA-en BE-en BG-en CZ-en DK-en EE-en ES-en ES-CT-en ES-GA-en FR-en GR-en HR-en HU-en IS-en IT-en LV-en NL-en NO-en PL-en PT-en RS-en SE-en SI-en TR-en UA-en
 
 # Used in test targets:
 CORPUS = UA
 
 #Where things are, as we use several branches: this one (most likely dev), and documentation
-PARLAMINT = /project/corpora/Parla/ParlaMint
-HERE = ${PARLAMINT}/ParlaMint-V3/Distro
-DOC = ${PARLAMINT}/ParlaMint-documentation
-SCH = ${DOC}/Schema
+PARLAMINT = /project/corpora/Parla/ParlaMint/ParlaMint
+SCH = ${PARLAMINT}/Schema
+HERE = ${PARLAMINT}/Corpora
 TEMP = ${HERE}/Temp
 
 #Where the submitted corpora are found (ParlaMint- .TEI/ and .TEI.ana/
-SOURCE = ${HERE}/Source
-SOURCE-MT = ${HERE}/Source-MT
+SOURCES = ${HERE}/Sources-TEI
+SOURCES-MT = ${HERE}/Sources-MT
 
 # Version number and PID of next(!) TEI and TEI.ana ParlaMint release
 VERSION = 3.1
 HANDLE-TEI = http://hdl.handle.net/11356/1859
 HANDLE-ANA = http://hdl.handle.net/11356/1860
 
-# Version number and PID of future(!) MTed ParlaMint-en.ana release
-VERSION-MT = 3.0
-HANDLE-MT = http://hdl.handle.net/11356/1810
+# Version number and PID of next MTed ParlaMint-en.ana release
+VERSION-MT = 3.1
+HANDLE-MT = http://hdl.handle.net/11356/1864
 
 #Where the produced corpora are put for inspection
 WEB = [email protected]:/home/tomaz/www/tmp/ParlaMint/
 
 ###### Targets
 
-### Fixes for 3.0-en:
+### Fixes for 3.1-en:
 
 # Instead of TEI-derived CoNLL-U files we release original MTed CoNLL-U
-# because it contains word alignments 
+# because they also contain word alignments 
 # Script also adds -en suffix to filesnames + readme.
 mt-cp-conllu:
-	bin/cp-conllu.pl 'Source-MT/ParlaMint-*-en.conllu' 'Master'
+	bin/cp-conllu.pl validate '${SOURCES-MT}/ParlaMint-*-en.conllu' 'Master'
 
 # Make txt and tsv files with tsvs
 mt-convert-txt:
@@ -62,9 +94,9 @@ mt-convert-txt:
 mrg-conll-nohup:
 	nohup time make mrg-conll > Logs/ParlaMint_Merge_CoNLL-U.log &
 mrg-conll:
-	bin/merge-conllu.pl Master/ParlaMint-BE.conllu Source-MT/ParlaMint-BE-en.conllu
-	bin/merge-conllu.pl Master/ParlaMint-ES-CT.conllu Source-MT/ParlaMint-ES-CT-en.conllu
-	bin/merge-conllu.pl Master/ParlaMint-UA.conllu Source-MT/ParlaMint-UA-en.conllu
+	bin/merge-conllu.pl Master/ParlaMint-BE.conllu ${SOURCES-MT}/ParlaMint-BE-en.conllu
+	bin/merge-conllu.pl Master/ParlaMint-ES-CT.conllu ${SOURCES-MT}/ParlaMint-ES-CT-en.conllu
+	bin/merge-conllu.pl Master/ParlaMint-UA.conllu ${SOURCES-MT}/ParlaMint-UA-en.conllu
 
 # Fix a mistake with handle in corpora
 fix-handle:
@@ -81,15 +113,15 @@ cp-readmes:
 # Make samples only
 samples:
 	for CORPUS in ${CORPORA}; do \
-	${FINALIZE} -sample -codes $${CORPUS} -in ${SOURCE} -out ${HERE}/Master 2> Logs/ParlaMint-$${CORPUS}.log; \
+	${FINALIZE} -sample -codes $${CORPUS} -in ${SOURCES} -out ${HERE}/Master 2> Logs/ParlaMint-$${CORPUS}.log; \
 	grep -a -i 'error' Logs/ParlaMint-$${CORPUS}.log > Logs/ParlaMint-$${CORPUS}.error.log;  \
 	grep -a -i 'warn'  Logs/ParlaMint-$${CORPUS}.log > Logs/ParlaMint-$${CORPUS}.warn.log;  \
 	done;
 
 # Make vertical files only
 make-verts:
 	for CORPUS in ${CORPORA}; do \
-	${FINALIZE} -vert -codes $${CORPUS} -in ${SOURCE} -out ${HERE}/Master \
+	${FINALIZE} -vert -codes $${CORPUS} -in ${SOURCES} -out ${HERE}/Master; \
 	done;
 	make verts
 
@@ -106,7 +138,7 @@ mt-make-root:
 
 cp-samples:
 	# bin/cp-samples.pl 'Master/Sample-ParlaMint-*-en' Test
-	bin/cp-samples.pl 'Master/Sample-ParlaMint-*-en' ../Data
+	bin/cp-samples.pl 'Master/Sample-ParlaMint-*-en' ../Samples
 
 mt-logs:
 	for CORPUS in ${CORPORA}; do \
@@ -120,10 +152,6 @@ web:
 	rsync -av Logs/*.log ${WEB}/Logs
 	rsync -av Packed/*.tgz ${WEB}/Repo
 
-###### Factorisation of source corpora; needs to be run only once
-factor-all:
-	../Scripts/parlamint-factorize-corpora.pl ${SOURCE}
-
 ###### Targets for producing releasable version of ParlaMint corpora
 FINALIZE = perl ../Scripts/parlamint2distro.pl -version ${VERSION} -teihandle ${HANDLE-TEI} -anahandle ${HANDLE-ANA} -schema ../Schema -docs Docs
 
@@ -136,16 +164,16 @@ nohup:
 nohup2:
 	nice nohup time make all > Logs/ParlaMint.2.log &
 
-all:	final
+all:	final verts
 xall:	final verts pack
 
 pack:
 	perl ../Scripts/pack-parlamint.pl -codes '${CORPORA}' -in Master -out Packed
 verts:
-	perl ../Scripts/join-verts.pl -codes '${CORPORA}' -in Master -out Verts
+	perl ../Scripts/join-verts.pl -version ${VERSION} -codes '${CORPORA}' -in Master -out Verts
 final:
 	for CORPUS in ${CORPORA}; do \
-	${FINALIZE} -all -codes $${CORPUS} -in ${SOURCE} -out ${HERE}/Master 2> Logs/ParlaMint-$${CORPUS}.log; \
+	${FINALIZE} -all -codes $${CORPUS} -in ${SOURCES} -out ${HERE}/Master 2> Logs/ParlaMint-$${CORPUS}.log; \
 	grep -a -i 'error' Logs/ParlaMint-$${CORPUS}.log > Logs/ParlaMint-$${CORPUS}.error.log;  \
 	grep -a -i 'warn'  Logs/ParlaMint-$${CORPUS}.log > Logs/ParlaMint-$${CORPUS}.warn.log;  \
 	echo "$${CORPUS}.warn"; \
@@ -162,13 +190,13 @@ final:
 ### Make MTed corpora
 
 # Make distribution with:
-FINALIZE-MT = perl ../Scripts/parlamint2distro.pl -version ${VERSION-MT} -anahandle ${HANDLE-MT} -schema ${DOC}/Schema -docs ${HERE}/Docs
+FINALIZE-MT = perl ../Scripts/parlamint2distro.pl -version ${VERSION-MT} -anahandle ${HANDLE-MT} -schema ${PARLAMINT}/Schema -docs ${HERE}/Docs
 
 # Targets
 mt-nohup:
-	nice nohup time make mt-all-final > Logs/ParlaMint-en.3.log &
-mt-all-final:	mt-pack mt-web
-mt-xall-final:	mt-convert mt-verts mt-pack mt-web
+	nice nohup time make mt-all-final > Logs/ParlaMint-en.log &
+mt-all-final:	mt-convert
+mt-xall-final:	mt-init mt-convert mt-verts mt-pack mt-web
 
 mt-web:
 	rsync -av Logs/*-en*.log ${WEB}/Logs
@@ -198,8 +226,8 @@ mt-convert:
 	for CORPUS in ${CORPORA}; do \
 	perl ../Scripts/mt-conllu2tei.pl \
 	${HERE}/Master/ParlaMint-$${CORPUS}.TEI.ana/ParlaMint-$${CORPUS}.ana.xml \
-	${SOURCE-MT}/ParlaMint-$${CORPUS}-en-notes.tsv \
-	${SOURCE-MT}/ParlaMint-$${CORPUS}-en.conllu \
+	${SOURCES-MT}/ParlaMint-$${CORPUS}-en-notes.tsv \
+	${SOURCES-MT}/ParlaMint-$${CORPUS}-en.conllu \
 	${TEMP}/ParlaMint-$${CORPUS}-en.TEI.ana 2> Logs/ParlaMint-$${CORPUS}-en.log; \
 	${FINALIZE-MT} -all -notei -noconll -codes $${CORPUS}-en -in ${TEMP} -out ${HERE}/Master \
 	2>> Logs/ParlaMint-$${CORPUS}-en.log; \
@@ -208,6 +236,15 @@ mt-convert:
 	done;
 
 ### Tests for debugging MT processing
+
+mt-test9:
+	perl ../Scripts/mt-conllu2tei.pl \
+	${HERE}/Master/ParlaMint-LV.TEI.ana/ParlaMint-LV.ana.xml \
+	${SOURCES-MT}/ParlaMint-LV-en-notes.tsv \
+	Sources-Sem/Test/ParlaMint-LV-en.conllu \
+	${TEMP}/ParlaMint-LV-en.TEI.ana
+	${FINALIZE-MT} -all -notei -noconll -codes LV-en -in ${TEMP} -out ${HERE}/Test
+
 mt-test8:
 	$s -xsl:../Scripts/validate-parlamint.xsl \
 	${HERE}/Master/ParlaMint-AT-en.TEI.ana/ParlaMint-AT-en.ana.xml
@@ -237,46 +274,13 @@ mt-test2a:
 	perl ../Scripts/conllu2tei.pl < Test/0.conllu > Test/0.body.xml
 mt-test2:
 	perl ../Scripts/conllu2tei.pl \
-	< Source-MT/ParlaMint-LV-en.conllu/2015/ParlaMint-LV_2015-11-12-PT12-329.conllu \
+	< ${SOURCES-MT}/ParlaMint-LV-en.conllu/2015/ParlaMint-LV_2015-11-12-PT12-329.conllu \
 	> Test/ParlaMint-LV_2015-11-12-PT12-329.body.xml
 	xmllint --noout Test/ParlaMint-LV_2015-11-12-PT12-329.body.xml
 mt-test1:
 	rm -fr Test/ParlaMint-CZ.tmp/*
 	$s outDir=Test/ParlaMint-CZ.tmp -xsl:../Scripts/mt-prepare4mt.xsl ${HERE}/Master/ParlaMint-CZ.TEI.ana/ParlaMint-CZ.ana.xml
 
-# Producing almost XX-en, uses CORPUS variable
-mt-prep-nohup:
-	nohup time make mt-prep-cnv > Logs/ParlaMint-${CORPUS}-mt2tei.log &
-mt-prep-cnv:
-	perl ../Scripts/mt-conllu2tei.pl \
-	${HERE}/Master/ParlaMint-${CORPUS}.TEI.ana/ParlaMint-${CORPUS}.ana.xml \
-	${SOURCE-MT}/ParlaMint-${CORPUS}-en-notes.tsv \
-	${SOURCE-MT}/ParlaMint-${CORPUS}-en.conllu \
-	Test/ParlaMint-${CORPUS}-en.TEI.ana
-
-#Tests for original corpora
-test1:
-	rm -fr Test/Out/ParlaMint-${CORPUS}*
-	perl ../Scripts/parlamint2distro.pl -all -codes ${CORPUS} -in Test/In -out Test/Out \
-	-version 3.0 -teihandle ${HANDLE-TEI} -anahandle ${HANDLE-ANA} -schema ../Schema -docs Docs \
-
-test-factorize:
-	rm -fr Test/Factorized/ParlaMint-${CORPUS}*
-	mkdir Test/Factorized || :
-	$s outDir=Test/Factorized/ParlaMint-${CORPUS}.TEI \
-	   prefix="ParlaMint-${CORPUS}-" \
-	   -xsl:../Scripts/parlamint-factorize-teiHeader.xsl \
-	   ${SOURCE}/ParlaMint-${CORPUS}.TEI/ParlaMint-${CORPUS}.xml || :
-	$s outDir=Test/Factorized/ParlaMint-${CORPUS}.TEI.ana \
-	   prefix="ParlaMint-${CORPUS}-" \
-	   teiRoot=`pwd`"/Test/Factorized/ParlaMint-${CORPUS}.TEI/ParlaMint-${CORPUS}.xml" \
-	   -xsl:../Scripts/parlamint-factorize-teiHeader.xsl \
-	   ${SOURCE}/ParlaMint-${CORPUS}.TEI.ana/ParlaMint-${CORPUS}.ana.xml || :
-
-errs1:
-	grep -i error Logs/*.log | \
-	grep -v '...suppressing' | grep -v 'Format errors' | grep -v 'Syntax errors' | grep -v 'FAILED'
-
 ### Some idea, need to think about it!
 #REGIS=at ba be bg cz dk es_ct fr gb gr hr hu is it lv nl no pl pt rs se si tr ua
 REGIS=ua