Convert some perl scripts to python

aymara · Jun 3, 2024 · 381aafa · 381aafa
1 parent 2b41f24
commit 381aafa
Show file tree

Hide file tree

Showing 22 changed files with 908 additions and 145 deletions.
diff --git a/gbuild.sh b/gbuild.sh
@@ -142,7 +142,7 @@ else
 fi
 current_project=`basename $PWD`
 current_project_name="$(head -n2 CMakeLists.txt | tail -n1)"
-build_prefix=$LIMA_BUILD_DIR/$current_branch
+build_prefix="${LIMA_BUILD_DIR}/${current_branch}"
 source_dir=$PWD
 
 if [[ $version = "rev" ]]; then

diff --git a/lima_linguisticdata/analysisDictionary/eng/wordnet/flex.sh b/lima_linguisticdata/analysisDictionary/eng/wordnet/flex.sh
@@ -23,7 +23,7 @@
 #reformat wordnet entries and remove numeric forms
 awk '($1 !~ /^[0-9]*$/) {print}' wn_*.txt | awk '{print "^W;;" $1 ";" $3 ";;" }' > mots-simples.txt
 
-../../../scripts/flex.pl def.txt mots-simples.txt . formes-eng.txt exclude.txt
+python3 ../../../scripts/flex.py def.txt mots-simples.txt . formes-eng.txt exclude.txt
 
 awk -F";" 'BEGIN {OFS="\t"} ($4) {print $1, $5, "" , $4} ($3) {print $1, $5, "", $3}' formes-eng.txt | sort -u --ignore-case > formes-eng.dic.1
 

diff --git a/lima_linguisticdata/cmake/LinguisticData.cmake b/lima_linguisticdata/cmake/LinguisticData.cmake
@@ -91,119 +91,6 @@ macro (FLEXION _lang)
 
 endmacro (FLEXION _lang)
 
-# Convert
-macro(CONVERT _lang)
-
-  add_custom_command(
-    OUTPUT dicotabs.txt
-    COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/pointvirgules2tabs.py ${CMAKE_CURRENT_BINARY_DIR}/../flex/formes-${_lang}.txt dicotabs.txt
-    DEPENDS ${CMAKE_CURRENT_BINARY_DIR}/../flex/formes-${_lang}.txt
-    COMMENT "python3 ${PROJECT_SOURCE_DIR}/scripts/pointvirgules2tabs.py ${CMAKE_CURRENT_BINARY_DIR}/../flex/formes-${_lang}.txt dicotabs.txt"
-    VERBATIM
-  )
-  add_custom_target(
-    dicotabs${_lang}
-    ALL
-    DEPENDS dicotabs.txt
-  )
-  add_dependencies(dicotabs${_lang} flex${_lang})
-
-  add_custom_command(
-    OUTPUT dicostd.txt
-    COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/cmakeconvertstd.pl dicotabs.txt ${CMAKE_CURRENT_SOURCE_DIR}/convstd.txt dicostd.txt
-    DEPENDS dicotabs.txt ${CMAKE_CURRENT_SOURCE_DIR}/convstd.txt
-    COMMENT "perl ${PROJECT_SOURCE_DIR}/scripts/cmakeconvertstd.pl dicotabs.txt ${CMAKE_CURRENT_SOURCE_DIR}/convstd.txt dicostd.txt"
-    VERBATIM
-  )
-  add_custom_target(
-    dicostd${_lang}
-    ALL
-    DEPENDS dicostd.txt
-  )
-  add_dependencies(dicostd${_lang} dicotabs${_lang})
-
-  set (ADDED_LIST_FILES_RESULT)
-  foreach(ADDED_LIST_FILE ${ADDED_LIST_FILES})
-    add_custom_command(
-      OUTPUT ${ADDED_LIST_FILE}.add
-      COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/addnormfield.pl ${CMAKE_CURRENT_SOURCE_DIR}/${ADDED_LIST_FILE} > ${ADDED_LIST_FILE}.add
-      DEPENDS dicostd.txt ${ADDED_LIST_FILE}
-      COMMENT "perl ${PROJECT_SOURCE_DIR}/scripts/addnormfield.pl ${CMAKE_CURRENT_SOURCE_DIR}/${ADDED_LIST_FILE} > ${ADDED_LIST_FILE}.add"
-    )
-    set (ADDED_LIST_FILES_RESULT ${ADDED_LIST_FILES_RESULT} ${ADDED_LIST_FILE}.add)
-  endforeach(ADDED_LIST_FILE ${ADDED_LIST_FILES})
-  add_custom_target(
-    dicoadd${_lang}
-    ALL
-    DEPENDS ${ADDED_LIST_FILES_RESULT}
-  )
-  add_dependencies(dicoadd${_lang} dicostd${_lang})
-
-  set(ENV{LC_ALL} "C")
-
-    add_custom_command(
-      OUTPUT dicocompletstd.txt
-      COMMAND ${SORTPREFIX} sort -u dicostd.txt ${ADDED_LIST_FILES_RESULT} > dicocompletstd.txt
-      DEPENDS dicostd.txt ${ADDED_LIST_FILES_RESULT}
-      COMMENT "sort -u dicostd.txt ${ADDED_LIST_FILES_RESULT} > dicocompletstd.txt"
-      VERBATIM
-    )
-    add_custom_target(
-      dicocomplet${_lang}
-      ALL
-      DEPENDS dicocompletstd.txt
-    )
-    add_dependencies(dicocomplet${_lang} dicoadd${_lang})
-
-  if (NOT (${CMAKE_SYSTEM_NAME} STREQUAL "Windows"))
-    add_custom_command(
-      OUTPUT dico.xml
-      COMMAND echo "<dictionary>" > dico.xml.tmp
-      COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/xmlforms.py dicocompletstd.txt dico.xml.tmp
-      COMMAND bash -c "if [ -n \"${ARGN}\" ]; then cat ${ARGN} >> dico.xml.tmp; fi"
-      COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/addnormfield.pl ${CMAKE_CURRENT_SOURCE_DIR}/dicoponctu.txt > dicoponctu.norm.txt
-      COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/xmlforms.py -desacc=no dicoponctu.norm.txt dico.xml.tmp
-      COMMAND echo "</dictionary>" >> dico.xml.tmp
-      COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/cmakeconvertdefautjys.py ${CMAKE_CURRENT_SOURCE_DIR}/default-${_lang}.txt ../code/convjys.txt default-${_lang}.dat
-      COMMAND mv dico.xml.tmp dico.xml
-      DEPENDS dicocompletstd.txt ${CMAKE_CURRENT_SOURCE_DIR}/dicoponctu.txt ${CMAKE_CURRENT_SOURCE_DIR}/default-${_lang}.txt
-      COMMENT "CONVERT ${_lang} produce XML dico"
-      VERBATIM
-    )
-  else (NOT (${CMAKE_SYSTEM_NAME} STREQUAL "Windows"))
-    # WARNING: VERBATIM option add unintentional double quotes symbols in XML file
-    add_custom_command(
-      OUTPUT dico.xml
-      COMMAND echo ^<dictionary^> > dico.xml.tmp
-      COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/xmlforms.py dicocompletstd.txt dico.xml.tmp
-      COMMAND bash -c "if [ -n \"${ARGN}\" ]; then cat ${ARGN} >> dico.xml.tmp; fi"
-      COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/addnormfield.pl ${CMAKE_CURRENT_SOURCE_DIR}/dicoponctu.txt > dicoponctu.norm.txt
-      COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/xmlforms.py -desacc=no dicoponctu.norm.txt dico.xml.tmp
-      COMMAND echo ^</dictionary^> >> dico.xml.tmp
-      COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/cmakeconvertdefautjys.py ${CMAKE_CURRENT_SOURCE_DIR}/default-${_lang}.txt ../code/convjys.txt default-${_lang}.dat
-      COMMAND mv dico.xml.tmp dico.xml
-      DEPENDS dicocompletstd.txt ${CMAKE_CURRENT_SOURCE_DIR}/dicoponctu.txt ${CMAKE_CURRENT_SOURCE_DIR}/default-${_lang}.txt
-      COMMENT "produce XML dico"
-    )
-  endif (NOT (${CMAKE_SYSTEM_NAME} STREQUAL "Windows"))
-
-  add_custom_target(
-    dicoxml${_lang}
-    ALL
-    DEPENDS dico.xml
-  )
-  add_dependencies(dicoxml${_lang} dicocomplet${_lang})
-
-  add_custom_target(
-    convert${_lang}
-    ALL
-  )
-  add_dependencies(convert${_lang} dicoxml${_lang} ${ARGN} )
-
-  install(FILES ${CMAKE_CURRENT_BINARY_DIR}/default-${_lang}.dat COMPONENT ${_lang} DESTINATION share/apps/lima/resources/LinguisticProcessings/${_lang})
-
-endmacro(CONVERT _lang)
-
 # Compile XML dictionary
 macro(COMPILEXMLDIC _lang _dico _subdir)
   message( "${C_BoldYellow}COMPILEXMLDIC(${_lang} ${_dico} ${_subdir})${C_Norm}" )
@@ -247,11 +134,11 @@ macro(DISAMBMATRICES _lang _succession_categs _codesymbol _priorscript _tablecon
 
   add_custom_command(
     OUTPUT trigramMatrix-${_lang}.dat
-    COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_extract.pl ${_succession_categs}
+    COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_extract.py ${_succession_categs}
     COMMAND cat ${_succession_categs} | sort | uniq -c | gawk -F" " "{print $2\"\t\"$1}" > unigramMatrix-${_lang}.dat
-    COMMAND perl ${_priorscript} corpus_${_lang}_merge.txt priorUnigramMatrix-${_lang}.dat ${_codesymbol} ${_tableconvert}
+    COMMAND python3 ${_priorscript} corpus_${_lang}_merge.txt priorUnigramMatrix-${_lang}.dat ${_codesymbol} ${_tableconvert}
     COMMAND cp bigramsend.txt bigramMatrix-${_lang}.dat
-    COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_normalize.pl trigramsend.txt trigramMatrix-${_lang}.dat
+    COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_normalize.py trigramsend.txt trigramMatrix-${_lang}.dat
 
     DEPENDS ${_codesymbol} ${_succession_categs}
     COMMENT "compile ${_lang} trigram matrix"
@@ -283,11 +170,11 @@ macro (DISAMBMATRICES_EXECENV _lang _succession_categs _codesymbol _priorscript
       ${CMAKE_BINARY_DIR}/execEnv/resources/Disambiguation/bigramMatrix-${_lang}.dat
       ${CMAKE_BINARY_DIR}/execEnv/resources/Disambiguation/trigramMatrix-${_lang}.dat
     COMMAND ${CMAKE_COMMAND} -E make_directory ${CMAKE_BINARY_DIR}/execEnv/resources/Disambiguation
-    COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_extract.pl ${_succession_categs}
+    COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_extract.py ${_succession_categs}
     COMMAND cat ${_succession_categs} | sort | uniq -c | gawk -F" " "{print $2\"\t\"$1}" > unigramMatrix-${_lang}.dat
-    COMMAND perl ${_priorscript} corpus_${_lang}_merge.txt priorUnigramMatrix-${_lang}.dat ${_codesymbol} ${_tableconvert}
+    COMMAND python3 ${_priorscript} corpus_${_lang}_merge.txt priorUnigramMatrix-${_lang}.dat ${_codesymbol} ${_tableconvert}
     COMMAND cp bigramsend.txt bigramMatrix-${_lang}.dat
-    COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_normalize.pl trigramsend.txt trigramMatrix-${_lang}.dat
+    COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_normalize.py trigramsend.txt trigramMatrix-${_lang}.dat
 
     COMMAND ${CMAKE_COMMAND} -E copy unigramMatrix-${_lang}.dat ${CMAKE_BINARY_DIR}/execEnv/resources/Disambiguation/unigramMatrix-${_lang}.dat
     COMMAND   ${CMAKE_COMMAND} -E copy priorUnigramMatrix-${_lang}.dat ${CMAKE_BINARY_DIR}/execEnv/resources/Disambiguation/priorUnigramMatrix-${_lang}.dat

diff --git a/lima_linguisticdata/disambiguisationMatrices/eng/CMakeLists.txt b/lima_linguisticdata/disambiguisationMatrices/eng/CMakeLists.txt
@@ -33,9 +33,9 @@ add_custom_target(
   DEPENDS succession_categs_retag.txt corpus_eng_merge.txt
 )
 
-DISAMBMATRICES(eng succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.pl X,SYM,UNK,PROPN,CONJ,NUM)
+DISAMBMATRICES(eng succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.py X,SYM,UNK,PROPN,CONJ,NUM)
 
-DISAMBMATRICES_EXECENV(eng succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.pl X,SYM,UNK,PROPN,CONJ,NUM)
+DISAMBMATRICES_EXECENV(eng succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.py X,SYM,UNK,PROPN,CONJ,NUM)
 
 add_dependencies(trigrammatrix-eng categs-eng)
 

diff --git a/lima_linguisticdata/disambiguisationMatrices/fre/CMakeLists.txt b/lima_linguisticdata/disambiguisationMatrices/fre/CMakeLists.txt
@@ -20,9 +20,9 @@ add_custom_target(
   DEPENDS succession_categs_retag.txt
 )
 
-DISAMBMATRICES(fre succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.pl U,ET,PREF,NPP,PONCT,CC,CS)
+DISAMBMATRICES(fre succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.py U,ET,PREF,NPP,PONCT,CC,CS)
 
-DISAMBMATRICES_EXECENV(fre succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.pl U,ET,PREF,NPP,PONCT,CC,CS)
+DISAMBMATRICES_EXECENV(fre succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.py U,ET,PREF,NPP,PONCT,CC,CS)
 
 add_dependencies(trigrammatrix-fre categs-fre)
 

diff --git a/lima_linguisticdata/disambiguisationMatrices/por/CMakeLists.txt b/lima_linguisticdata/disambiguisationMatrices/por/CMakeLists.txt
@@ -21,9 +21,9 @@ add_custom_target(
   DEPENDS succession_categs_retag.txt
 )
 
-DISAMBMATRICES(por succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.pl DIVERS_*,NOM_PROPRE*,CONJ_*,NOMBRE*)
+DISAMBMATRICES(por succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.py DIVERS_*,NOM_PROPRE*,CONJ_*,NOMBRE*)
 
-DISAMBMATRICES_EXECENV(por succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.pl DIVERS_*,NOM_PROPRE*,CONJ_*,NOMBRE*)
+DISAMBMATRICES_EXECENV(por succession_categs_retag.txt ${CMAKE_CURRENT_SOURCE_DIR}/code_symbolic2lima.txt ${PROJECT_SOURCE_DIR}/scripts/disamb_matrices_prior-convert.py DIVERS_*,NOM_PROPRE*,CONJ_*,NOMBRE*)
 
 add_dependencies(trigrammatrix-por categs-por)
 

diff --git a/lima_linguisticdata/rules-idiom/eng/src/CMakeLists.txt b/lima_linguisticdata/rules-idiom/eng/src/CMakeLists.txt
@@ -7,8 +7,8 @@ file (GLOB SYMBOLICCODESENG ${PROJECT_SOURCE_DIR}/analysisDictionary/eng/code/sy
 
 add_custom_command(
   OUTPUT idiomaticExpressions-eng.rules
-  COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/reformat_idioms.pl ${CMAKE_CURRENT_SOURCE_DIR}/idioms-eng.txt > idioms-eng.grace
-  COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/transcodeIdiomatic.pl ${CMAKE_BINARY_DIR}/lima_linguisticprocessing/tools/common/convertSymbolicCodes --configDir=${PROJECT_SOURCE_DIR}/../lima_common/conf/ ${PROJECT_SOURCE_DIR}/analysisDictionary/eng/code/code-eng.xml ${SYMBOLICCODESENG} idioms-eng.grace > idiomaticExpressions-eng.rules
+  COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/reformat_idioms.py ${CMAKE_CURRENT_SOURCE_DIR}/idioms-eng.txt > idioms-eng.grace
+  COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/transcode_idiomatic.py ${CMAKE_BINARY_DIR}/lima_linguisticprocessing/tools/common/convertSymbolicCodes ${PROJECT_SOURCE_DIR}/analysisDictionary/eng/code/code-eng.xml ${SYMBOLICCODESENG} idioms-eng.grace > idiomaticExpressions-eng.rules
   DEPENDS
     ${CMAKE_CURRENT_SOURCE_DIR}/idioms-eng.txt
     ${SYMBOLICCODESENG}

diff --git a/lima_linguisticdata/rules-idiom/fre/examples/test-example.sh b/lima_linguisticdata/rules-idiom/fre/examples/test-example.sh
@@ -27,7 +27,6 @@ for example in $*; do
 
         python -c "import os, re; open('conf/lima-lp-tva-fre-example.xml', 'w', encoding='utf-8').write(re.sub(r'LinguisticProcessings/fre/idiomaticExpressions-fre.rules', f'idiom-examples/{os.getenv('exampleFile')}', open(os.path.join(os.getenv('LIMA_CONF'), 'lima-lp-tva-fre.xml'), 'r', encoding='utf-8').read()))"
 
-#         perl -pe 's%LinguisticProcessings/fre/idiomaticExpressions-fre.rules%idiom-examples/$ENV{"exampleFile"}%' $LIMA_CONF/lima-lp-tva-fre.xml > conf/lima-lp-tva-fre-example.xml;
         echo "running test on $exampleFile";
         tva --language=fre --resources-dir=resources --config-dir=conf --lp-config-file=lima-lp-tva-example.xml idiom-example-fre-test.xml >& tva-$example.log;
         egrep "(TestReport|total)" tva-$example.log

diff --git a/lima_linguisticdata/rules-idiom/fre/src/CMakeLists.txt b/lima_linguisticdata/rules-idiom/fre/src/CMakeLists.txt
@@ -7,15 +7,15 @@ file (GLOB SYMBOLICCODESFRE ${PROJECT_SOURCE_DIR}/analysisDictionary/fre/code/sy
 
 add_custom_command(
   OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/idiomaticExpressions-fre.rules
-  COMMAND perl ${CMAKE_CURRENT_SOURCE_DIR}/buildSeparableVerbList.pl -list=${CMAKE_CURRENT_BINARY_DIR}/separableVerbs.lst -rules=${CMAKE_CURRENT_BINARY_DIR}/separableVerbsSecond.rules ${CMAKE_CURRENT_SOURCE_DIR}/idioms-fre.txt > ${CMAKE_CURRENT_BINARY_DIR}/idioms-fre.withoutVerbs.txt
+  COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/buildSeparableVerbList.pl -list=${CMAKE_CURRENT_BINARY_DIR}/separableVerbs.lst -rules=${CMAKE_CURRENT_BINARY_DIR}/separableVerbsSecond.rules ${CMAKE_CURRENT_SOURCE_DIR}/idioms-fre.txt > ${CMAKE_CURRENT_BINARY_DIR}/idioms-fre.withoutVerbs.txt
   COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/reformat_idioms.pl ${CMAKE_CURRENT_SOURCE_DIR}/idioms-fre.txt > ${CMAKE_CURRENT_BINARY_DIR}/idioms-fre.grace
   COMMAND cat ${CMAKE_CURRENT_SOURCE_DIR}/separableVerbs.rules ${CMAKE_CURRENT_BINARY_DIR}/separableVerbsSecond.rules >> ${CMAKE_CURRENT_BINARY_DIR}/idioms-fre.grace
-  COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/transcodeIdiomatic.pl ${CMAKE_BINARY_DIR}/lima_linguisticprocessing/tools/common/convertSymbolicCodes --configDir=${PROJECT_SOURCE_DIR}/../lima_common/conf/ ${PROJECT_SOURCE_DIR}/analysisDictionary/fre/code/code-fre.xml ${SYMBOLICCODESFRE} ${CMAKE_CURRENT_BINARY_DIR}/idioms-fre.grace > ${CMAKE_CURRENT_BINARY_DIR}/idiomaticExpressions-fre.rules
+  COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/transcodeIdiomatic.pl ${CMAKE_BINARY_DIR}/lima_linguisticprocessing/tools/common/convertSymbolicCodes ${PROJECT_SOURCE_DIR}/analysisDictionary/fre/code/code-fre.xml ${SYMBOLICCODESFRE} ${CMAKE_CURRENT_BINARY_DIR}/idioms-fre.grace > ${CMAKE_CURRENT_BINARY_DIR}/idiomaticExpressions-fre.rules
   DEPENDS
-    ${CMAKE_CURRENT_SOURCE_DIR}/buildSeparableVerbList.pl
+    ${PROJECT_SOURCE_DIR}/scripts/build_separable_verb_list.py
     ${CMAKE_CURRENT_SOURCE_DIR}/categories_convert
-    ${PROJECT_SOURCE_DIR}/scripts/reformat_idioms.pl
-    ${PROJECT_SOURCE_DIR}/scripts/transcodeIdiomatic.pl
+    ${PROJECT_SOURCE_DIR}/scripts/reformat_idioms.py
+    ${PROJECT_SOURCE_DIR}/scripts/transcode_idiomatic.py
     ${CMAKE_CURRENT_SOURCE_DIR}/idioms-fre.txt
     ${CMAKE_CURRENT_SOURCE_DIR}/separableVerbs.rules
     ${SYMBOLICCODESFRE}

diff --git a/lima_linguisticdata/rules-idiom/por/src/CMakeLists.txt b/lima_linguisticdata/rules-idiom/por/src/CMakeLists.txt
@@ -7,8 +7,8 @@ file (GLOB SYMBOLICCODESPOR ${PROJECT_SOURCE_DIR}/analysisDictionary/por/code/sy
 
 add_custom_command(
  OUTPUT idiomaticExpressions-por.rules
- COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/reformat_idioms.pl ${CMAKE_CURRENT_SOURCE_DIR}/idioms-por.txt > idioms-por.grace
- COMMAND perl ${PROJECT_SOURCE_DIR}/scripts/transcodeIdiomatic.pl ${CMAKE_BINARY_DIR}/lima_linguisticprocessing/tools/common/convertSymbolicCodes --configDir=${PROJECT_SOURCE_DIR}/../lima_common/conf/ ${PROJECT_SOURCE_DIR}/analysisDictionary/por/code/code-por.xml ${SYMBOLICCODESPOR} idioms-por.grace > idiomaticExpressions-por.rules
+ COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/reformat_idioms.py ${CMAKE_CURRENT_SOURCE_DIR}/idioms-por.txt > idioms-por.grace
+ COMMAND python3 ${PROJECT_SOURCE_DIR}/scripts/transcode_idiomatic.py ${CMAKE_BINARY_DIR}/lima_linguisticprocessing/tools/common/convertSymbolicCodes ${PROJECT_SOURCE_DIR}/analysisDictionary/por/code/code-por.xml ${SYMBOLICCODESPOR} idioms-por.grace > idiomaticExpressions-por.rules
  DEPENDS
     ${CMAKE_CURRENT_SOURCE_DIR}/idioms-por.txt
     ${SYMBOLICCODESPOR}