Squashed commit of the following:

kosloot · kosloot · commit bdcfd01531c0 · 2025-12-11T13:54:12.000+01:00
commit e9fd679 Author: Ko van der Sloot <Ko.vanderSloot@ziggo.nl> Date: Tue Dec 9 11:26:46 2025 +0100 enter 2026 commit 2825b4b Author: Ko van der Sloot <Ko.vanderSloot@ziggo.nl> Date: Mon Nov 24 10:44:01 2025 +0100 adapted to change in libfolia add_child() API
diff --git a/.github/workflows/foliautils.yml b/.github/workflows/foliautils.yml
@@ -36,7 +36,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest]
-        compiler: [g++-12, clang++ -std=c++17]
+        compiler: [g++ -std=c++17, clang++ -std=c++17]
 
     steps:
       - uses: actions/checkout@v4.1.1
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 # FoliAutils
 
-  (c) CLST/TiCC/CLiPS 2024
+  (c) CLST/TiCC/CLiPS 2026
   https://github.com/LanguageMachines/foliautils
 
     Centre for Language and Speech Technology, Radboud University Nijmegen
diff --git a/codemeta.json b/codemeta.json
@@ -7,7 +7,7 @@
     "@type": "SoftwareSourceCode",
     "identifier": "foliautils",
     "name": "foliautils",
-    "version": "0.23",
+    "version": "0.24",
     "description": "Command-line utilities for working with the Format for Linguistic Annotation (FoLiA).",
     "license": "https://spdx.org/licenses/GPL-3.0-only",
 	"url": "https://github.com/LanguageMachines/foliautils",
diff --git a/configure.ac b/configure.ac
@@ -2,7 +2,7 @@
 # Process this file with autoconf to produce a configure script.
 
 AC_PREREQ([2.69])
-AC_INIT([foliautils],[0.23],[lamasoftware@science.ru.nl]) #adapt version number in codemeta.json as well
+AC_INIT([foliautils],[0.24],[lamasoftware@science.ru.nl]) #adapt version number in codemeta.json as well
 AM_INIT_AUTOMAKE
 AC_CONFIG_SRCDIR([.])
 AC_CONFIG_MACRO_DIR([m4])
diff --git a/include/foliautils/common_code.h b/include/foliautils/common_code.h
@@ -1,6 +1,6 @@
 /* ex: set tabstop=8 expandtab: */
 /*
-  Copyright (c) 2006 - 2024
+  Copyright (c) 2006 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-2text.cxx b/src/FoLiA-2text.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-abby.cxx b/src/FoLiA-abby.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-alto.cxx b/src/FoLiA-alto.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-benchmark.cxx b/src/FoLiA-benchmark.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-clean.cxx b/src/FoLiA-clean.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-collect.cxx b/src/FoLiA-collect.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-correct.cxx b/src/FoLiA-correct.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-hocr.cxx b/src/FoLiA-hocr.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-idf.cxx b/src/FoLiA-idf.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-langcat.cxx b/src/FoLiA-langcat.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-merge.cxx b/src/FoLiA-merge.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-page.cxx b/src/FoLiA-page.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-pm.cxx b/src/FoLiA-pm.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-stats.cxx b/src/FoLiA-stats.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/src/FoLiA-txt.cxx b/src/FoLiA-txt.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
@@ -213,7 +213,6 @@ bool handle_one_file( const string& fileName ){
   if ( par && !par_stack.empty() ){
     // leftovers
     add_paragraph( par, par_stack );
-    par = 0;
     par_stack.clear();
   }
   if ( parCount == 0 ){
diff --git a/src/FoLiA-wordtranslate.cxx b/src/FoLiA-wordtranslate.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
 
   This file is part of foliautils
diff --git a/src/common_code.cxx b/src/common_code.cxx
@@ -1,5 +1,5 @@
 /*
-  Copyright (c) 2014 - 2024
+  Copyright (c) 2014 - 2026
   CLST  - Radboud University
   ILK   - Tilburg University
 
diff --git a/tests/test2text.ok b/tests/test2text.ok
@@ -15,7 +15,7 @@ Usage: FoLiA-2text [options] file/dir
 	-V or --version 	 show version 
 	-e		 expr: specify the expression all input files should match with.
 	-o		 name of the output file(s) prefix.
-foliautils 0.23
+foliautils 0.24
 Usage: FoLiA-2text [options] file/dir
 	 FoLiA-2text will produce a text from a FoLiA file, 
 	 or a whole directory of FoLiA files 
diff --git a/tests/testabby.ok b/tests/testabby.ok
@@ -16,7 +16,7 @@ Usage: FoLiA-abby [options] file/dir
 			 with 'c'=g create gzip files (.gz)
 	-v		 verbose output 
 	-V or --version	 show version 
-FoLiA-abby [foliautils 0.23]
+FoLiA-abby [foliautils 0.24]
 Usage: FoLiA-abby [options] file/dir
 	-t <threads>
 	--threads <threads> Number of threads to run on.
diff --git a/tests/testalto.ok b/tests/testalto.ok
@@ -21,7 +21,7 @@ Usage: alto [options] file/dir
 			 'c'=g creates gzip files (.gz)
 	-v		 verbose output 
 	-V or --version	 show version 
-foliautils 0.23
+foliautils 0.24
 Usage: alto [options] file/dir
 	--cache		 alto cache directory 
 	--clear		 clear cached Alto files at start
diff --git a/tests/testclean.ok b/tests/testclean.ok
@@ -16,7 +16,7 @@ Usage: FoLiA-clean [options] file/dir
 	-h or --help	 this message
 	-V or --version show version 
 	-O		 name of the output dir.
-foliautils 0.23
+foliautils 0.24
 Usage: FoLiA-clean [options] file/dir
 	 FoLiA-clean will produce a cleaned up version of a FoLiA file, 
 	 or a whole directory of FoLiA files 
diff --git a/tests/testcorrect.ok b/tests/testcorrect.ok
@@ -1,5 +1,5 @@
 missing '--punct' option
-foliautils 0.23
+foliautils 0.24
 Usage: [options] file/dir
 	 FoLiA-correct will correct FoLiA files 
 	 or a whole directory of FoLiA files 
diff --git a/tests/testhocr.ok b/tests/testhocr.ok
@@ -13,7 +13,7 @@ Usage: FoLiA-hocr [options] file/dir
 			 use 'none' for an empty prefix. (can be dangerous)
 	-v		 verbose output 
 	-V or --version	 show version 
-foliautils 0.23
+foliautils 0.24
 Usage: FoLiA-hocr [options] file/dir
 	-t 'threads' or
 	--threads='threads' Number of threads to run on.
diff --git a/tests/testidf.ok b/tests/testidf.ok
@@ -14,7 +14,7 @@ Usage: [options] file/dir
 	-e		 expr: specify the expression all files should match with.
 	-O		 output prefix
 	-R		 search the dirs recursively (when appropriate).
-foliautils 0.23
+foliautils 0.24
 Usage: [options] file/dir
 	 FoLiA-idf will produce IDF statistics for a directory of FoLiA files 
 	--clip		 clipping factor. 
diff --git a/tests/testlangcat.ok b/tests/testlangcat.ok
@@ -1,5 +1,5 @@
 missing input file(s)
-foliautils 0.23
+foliautils 0.24
 Usage: [options] dir/filename 
   add language information to a file or files in FoLiA XML format
   The files must have extension '.folia.xml' or '.xml'
@@ -22,15 +22,15 @@ Usage: [options] dir/filename
 process data/langcat.test.xml
 document 'data/langcat.test.xml' has 3 p nodes 
 <?xml version="1.0" encoding="UTF-8"?>
-<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.20" version="1.4.987">
+<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.22" version="1.4.987">
   <metadata type="native">
     <annotations>
       <lang-annotation set="http://raw.github.com/proycon/folia/master/setdefinitions/iso639_3.foliaset"/>
       <text-annotation set="https://raw.githubusercontent.com/proycon/folia/master/setdefinitions/text.foliaset.ttl"/>
     </annotations>
     <provenance>
-      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-08-25T23:18:11" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.23">
-        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.20"/>
+      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-12-18T13:34:53" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.24">
+        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.22"/>
       </processor>
     </provenance>
     <meta id="language">nld</meta>
@@ -53,15 +53,15 @@ document 'data/langcat.test.xml' has 3 p nodes
 process data/lc.xml.gz
 document 'data/lc.xml.gz' has 3 p nodes 
 <?xml version="1.0" encoding="UTF-8"?>
-<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.20" version="1.4.987">
+<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.22" version="1.4.987">
   <metadata type="native">
     <annotations>
       <lang-annotation set="http://raw.github.com/proycon/folia/master/setdefinitions/iso639_3.foliaset"/>
       <text-annotation set="https://raw.githubusercontent.com/proycon/folia/master/setdefinitions/text.foliaset.ttl"/>
     </annotations>
     <provenance>
-      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-08-25T23:18:11" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.23">
-        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.20"/>
+      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-12-18T13:34:53" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.24">
+        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.22"/>
       </processor>
     </provenance>
     <meta id="language">nld</meta>
@@ -84,15 +84,15 @@ document 'data/lc.xml.gz' has 3 p nodes
 process data/langcat.test2.xml
 document 'data/langcat.test2.xml' has 1 p nodes 
 <?xml version="1.0" encoding="UTF-8"?>
-<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.20" version="1.4.987">
+<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.22" version="1.4.987">
   <metadata type="native">
     <annotations>
       <lang-annotation set="http://raw.github.com/proycon/folia/master/setdefinitions/iso639_3.foliaset"/>
       <text-annotation set="https://raw.githubusercontent.com/proycon/folia/master/setdefinitions/text.foliaset.ttl"/>
     </annotations>
     <provenance>
-      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-08-25T23:18:11" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.23">
-        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.20"/>
+      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-12-18T13:34:53" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.24">
+        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.22"/>
       </processor>
     </provenance>
     <meta id="language">nld</meta>
@@ -110,15 +110,15 @@ document 'data/langcat.test2.xml' has 1 p nodes
 process data/langcat.test-str.folia.xml
 document 'data/langcat.test-str.folia.xml' has 2 str nodes 
 <?xml version="1.0" encoding="UTF-8"?>
-<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.20" version="1.4.987">
+<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.22" version="1.4.987">
   <metadata type="native">
     <annotations>
       <lang-annotation set="http://raw.github.com/proycon/folia/master/setdefinitions/iso639_3.foliaset"/>
       <text-annotation set="https://raw.githubusercontent.com/proycon/folia/master/setdefinitions/text.foliaset.ttl"/>
     </annotations>
     <provenance>
-      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-08-25T23:18:11" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.23">
-        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.20"/>
+      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-12-18T13:34:53" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.24">
+        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.22"/>
       </processor>
     </provenance>
     <meta id="language">nld</meta>
@@ -137,15 +137,15 @@ document 'data/langcat.test-str.folia.xml' has 2 str nodes
 process data/langcat.test-str.folia.xml
 document 'data/langcat.test-str.folia.xml' has 2 str nodes 
 <?xml version="1.0" encoding="UTF-8"?>
-<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.20" version="1.4.987">
+<FoLiA xmlns:xlink="http://www.w3.org/1999/xlink" xmlns="http://ilk.uvt.nl/folia" xml:id="test" generator="libfolia-v2.22" version="1.4.987">
   <metadata type="native">
     <annotations>
       <lang-annotation set="http://raw.github.com/proycon/folia/master/setdefinitions/iso639_3.foliaset"/>
       <text-annotation set="https://raw.githubusercontent.com/proycon/folia/master/setdefinitions/text.foliaset.ttl"/>
     </annotations>
     <provenance>
-      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-08-25T23:18:11" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.23">
-        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.20"/>
+      <processor xml:id="FoLiA-langcat.1" begindatetime="2024-12-18T13:34:53" command="FoLiA-langcat " folia_version="2.5.3" host="kobus" name="FoLiA-langcat" user="sloot" version="0.24">
+        <processor xml:id="FoLiA-langcat.1.generator" folia_version="2.5.3" name="libfolia" type="generator" version="2.22"/>
       </processor>
     </provenance>
     <meta id="language">nld</meta>
diff --git a/tests/testmerge.ok b/tests/testmerge.ok
@@ -1,5 +1,5 @@
 missing '-l or --lexicon' option
-foliautils 0.23
+foliautils 0.24
 Usage: [options] file/dir
 	 FoLiA-merge will merge lemmas and POS tags into FoLiA files 
 	-l or --lexicon=<name>	 the lexicon for word/lemma/POS lookup 
diff --git a/tests/testpage.ok b/tests/testpage.ok
@@ -1,5 +1,5 @@
 missing input file(s)
-FoLiA-page [foliautils 0.23]
+FoLiA-page [foliautils 0.24]
 Usage: FoLiA-page [options] file/dir
 	-t <threads>
 	--threads <threads> Number of threads to run on.
diff --git a/tests/testpm.ok b/tests/testpm.ok
@@ -12,7 +12,7 @@ Usage: FoLiA-pm [options] files/dir
 	-v		 verbose output 
 	-V or --version	 show version 
 	-h or --help 	 this messages 
-foliautils 0.23
+foliautils 0.24
 Usage: FoLiA-pm [options] files/dir
 	 convert Political Mashup XML files to FoLiA
 	 when a dir is given, all '.xml' files in that dir are processed
diff --git a/tests/teststats.ok b/tests/teststats.ok
@@ -49,7 +49,7 @@ The output will be a 2 or 4 columned tab separated file, extension: *tsv
 	-e	 expr: specify the expression all input files should match with.
 	-o	 name of the output file(s) prefix.
 	-R	 search the dirs recursively (when appropriate).
-FoLiA-stats from foliautils 0.23
+FoLiA-stats from foliautils 0.24
 Usage: FoLiA-stats [options] file/dir
 
 FoLiA-stats will produce ngram statistics for a FoLiA file, 
diff --git a/tests/testtxt.ok b/tests/testtxt.ok
@@ -14,7 +14,7 @@ Usage: [options] file/dir
 			 And ignored in general.
 	--setname The FoLiA setname of the created nodes. (Default 'FoLiA-txt-set')
 	--class The classname of the <t> nodes that are created. (Default 'FoLiA-txt')
-foliautils 0.23
+foliautils 0.24
 Usage: [options] file/dir
 	 FoLiA-txt will produce FoLiA files from text files 
 	 The output will only contain <p> and <str> nodes.
diff --git a/tests/testwordtranslate.ok b/tests/testwordtranslate.ok
@@ -1,5 +1,5 @@
 missing input file or directory
-foliautils 0.23
+foliautils 0.24
 Usage: FoLiA-wordtranslate [options] file/dir
 Description: Simple word-by-word translator on the basis of a dictionary (or multiple)
 Options:
