#10: testum/de-extraneum/, testum/de-hxl/, testum/de-csv/

EticaAI · Nov 28, 2021 · 2ee571d · 2ee571d
1 parent 4a0d186
commit 2ee571d
Show file tree

Hide file tree

Showing 12 changed files with 119 additions and 9 deletions.
diff --git a/bin/hxltmcli.py b/bin/hxltmcli.py
@@ -5716,7 +5716,8 @@ def initialle(self, strictum: bool):  # pylint: disable=too-many-branches
         #     ValueError: not enough values to unpack (expected 2, got 1)
         if self.linguam.find('-') == -1:
             raise ValueError(
-                'HXLTMLinguam zzz-Zzzz? [{0}]'.format(str(self.linguam)))
+                'HXLTMLinguam zzz-Zzzz? [{0}] Archivum est HXLTM?'.format(
+                    str(self.linguam)))
 
         self.iso6393, self.iso115924 = \
             list(self.linguam.split('-'))

diff --git a/testum/csv-3-exemplum.csv b/testum/csv-3-exemplum.csv
diff --git a/testum/de-csv/csv-non-hxltm-exemplum.csv b/testum/de-csv/csv-non-hxltm-exemplum.csv
@@ -0,0 +1,7 @@
+id,en,pt
+1,UN,ONU
+2,United Nations,Organização das Nações Unidas
+3,IFRC,FICV/CV
+4,International Federation of Red Cross and Red Crescent Societies ,Federação Internacional das Sociedades da Cruz Vermelha e do Crescente Vermelho
+5,AI,AI
+6,Amnesty International,Amnistia Internacional
diff --git a/testum/de-extraneum/hxltm-bi-linguam-in-columnam.csv b/testum/de-extraneum/hxltm-bi-linguam-in-columnam.csv
@@ -0,0 +1,8 @@
+id,source language,target language,source term,target term
+#item+conceptum+codicem,#item+terminum+est_linguam_fontem,#item+terminum+est_linguam_objectivum,#item+terminum+de_linguam_fontem,#item+terminum+de_linguam_objectivum
+1,eng-Latn,por-Latn,UN,ONU
+2,eng-Latn,por-Latn,United Nations,Organização das Nações Unidas
+3,eng-Latn,por-Latn,IFRC,FICV/CV
+4,eng-Latn,por-Latn,International Federation of Red Cross and Red Crescent Societies ,Federação Internacional das Sociedades da Cruz Vermelha e do Crescente Vermelho
+5,eng-Latn,por-Latn,AI,AI
+6,eng-Latn,por-Latn,Amnesty International,Amnistia Internacional
diff --git a/testum/de-extraneum/hxltm-multi-linguam-in-columnam.csv b/testum/de-extraneum/hxltm-multi-linguam-in-columnam.csv
@@ -0,0 +1,14 @@
+id,lang,term
+#item+conceptum+codicem,#item+terminum+est_linguam,#item+terminum+de_linguam
+1,eng-Latn,UN
+2,eng-Latn,United Nations
+3,eng-Latn,IFRC
+4,eng-Latn,International Federation of Red Cross and Red Crescent Societies
+5,eng-Latn,AI
+6,por-Latn,Amnistia Internacional
+1,por-Latn,ONU
+2,por-Latn,Organização das Nações Unidas
+3,por-Latn,FICV/CV
+4,por-Latn,Federação Internacional das Sociedades da Cruz Vermelha e do Crescente Vermelho
+5,por-Latn,AI
+6,por-Latn,Amnistia Internacional
diff --git a/testum/de-extraneum/hxltm-solum-id.tm.hxl.csv b/testum/de-extraneum/hxltm-solum-id.tm.hxl.csv
@@ -0,0 +1,8 @@
+id
+#item+conceptum+codicem
+1
+2
+3
+4
+5
+6
diff --git a/testum/de-extraneum/hxltm-solum-linguam.tm.hxl.csv b/testum/de-extraneum/hxltm-solum-linguam.tm.hxl.csv
@@ -0,0 +1,8 @@
+en,pt
+#item+terminum+i_en+i_eng+is_latn+rem,#item+terminum+i_pt+i_por+is_latn+rem
+UN,ONU
+United Nations,Organização das Nações Unidas
+IFRC,FICV/CV
+International Federation of Red Cross and Red Crescent Societies ,Federação Internacional das Sociedades da Cruz Vermelha e do Crescente Vermelho
+AI,AI
+Amnesty International,Amnistia Internacional
diff --git a/testum/hxl-non-hxltm-exemplum.hxl.csv → testum/de-hxl/hxl-non-hxltm-exemplum.hxl.csv b/testum/hxl-non-hxltm-exemplum.hxl.csv → testum/de-hxl/hxl-non-hxltm-exemplum.hxl.csv
@@ -1,3 +1,4 @@
+id,en,pt
 #vocab+id,#vocab+term+i_en,#vocab+term+i_pt
 1,UN,ONU
 2,United Nations,Organização das Nações Unidas

diff --git a/testum/disciplinam-manuale-anglicum.sh b/testum/disciplinam-manuale-anglicum.sh
@@ -54,6 +54,60 @@ hxltmdexml --help > "hxltmdexml--help_eng-Latn.txt"
 # fi
 ### TODO: implement some way to also validate all CSVs on folder
 
+
+# tag::HXLStandard_examples[]
+### I -------------------------------------------------------------------------
+
+### I -------------------------------------------------------------------------
+# _[eng-Latn]
+# Convert a file in CSV to HXLTM (using HXLStandard tools): use hxltag
+# [eng-Latn]_
+
+# head -n 2 de-csv/csv-non-hxltm-exemplum.csv
+#    id,en,pt
+#    1,UN,ONU
+
+hxltag \
+  --map='id #item+conceptum+codicem' \
+  --map='en #item+terminum+i_en+i_eng+is_latn+rem' \
+  --map='pt #item+terminum+i_pt+i_por+is_latn+rem' \
+  de-csv/csv-non-hxltm-exemplum.csv \
+  resultatum/de-csv/csv-non-hxltm-exemplum.tm.hxl.csv
+
+# head -n 2 resultatum/de-csv/csv-non-hxltm-exemplum.tm.hxl.csv
+#    id,en,pt
+#    #item+conceptum+codicem,#item+terminum+i_en+i_eng+is_latn+rem,
+#    #item+terminum+i_pt+i_por+is_latn+rem
+
+### II -------------------------------------------------------------------------
+# _[eng-Latn]
+# Convert a file already in HXL, but not in HXLTM, to HXLTM: use hxlrename
+# [eng-Latn]_
+
+# head -n 2 hxl/hxl-non-hxltm-exemplum.hxl.csv
+#    id,en,pt
+#    #vocab+id,#vocab+term+i_en,#vocab+term+i_pt
+
+hxlrename \
+  --rename='vocab+id:item+conceptum+codicem' \
+  --rename='vocab+term+i_en:item+terminum+i_en+i_eng+is_latn+rem'  \
+  --rename='vocab+term+i_pt:item+terminum+i_pt+i_por+is_latn+rem'  \
+  de-hxl/hxl-non-hxltm-exemplum.hxl.csv \
+  resultatum/de-hxl/hxl-non-hxltm-exemplum.tm.hxl.csv
+
+# head -n 2 resultatum/de-hxl-non-hxltm/hxl-non-hxltm-exemplum.tm.hxl.csv
+#    id,en,pt
+#    #item+conceptum+codicem,#item+terminum+i_en+i_eng+is_latn+rem,
+#    #item+terminum+i_pt+i_por+is_latn+rem
+
+# end::HXLStandard_examples[]
+
+# Temp, remove
+#    hxlcut --include='#item+codicem' resultatum/de-hxl/hxl-non-hxltm-exemplum.tm.hxl.csv > de-extraneum/hxltm-solum-id.tm.hxl.csv
+#    hxlcut --include='#item+terminum' resultatum/de-hxl/hxl-non-hxltm-exemplum.tm.hxl.csv > de-extraneum/hxltm-solum-linguam.tm.hxl.csv
+#    hxltmcli de-extraneum/hxltm-solum-id.tm.hxl.csv
+#    hxltmcli de-extraneum/hxltm-solum-linguam.tm.hxl.csv
+
 # tag::HXLTM_CSV[]
 ### I -------------------------------------------------------------------------
 # _[eng-Latn]

diff --git a/testum/hxltmcli--help_eng-Latn.txt b/testum/hxltmcli--help_eng-Latn.txt
@@ -86,7 +86,7 @@ optional arguments:
                         formats (like TBX) both to avoid scan the source file
                         and to be sure about HXL attributes of the output
                         format. Default: indicem_de_terminum,meta. Options:
-                        [annotationem annotationem_linguam
+                        [accuratum annotationem annotationem_linguam
                         annotationem_terminum codicem codicem_conceptum
                         dominium indicem_de_terminum meta meta_conceptum
                         meta_linguam meta_terminum rem]

diff --git a/testum/resultatum/de-csv/csv-non-hxltm-exemplum.tm.hxl.csv b/testum/resultatum/de-csv/csv-non-hxltm-exemplum.tm.hxl.csv
@@ -0,0 +1,8 @@
+id,en,pt
+#item+conceptum+codicem,#item+terminum+i_en+i_eng+is_latn+rem,#item+terminum+i_pt+i_por+is_latn+rem
+1,UN,ONU
+2,United Nations,Organização das Nações Unidas
+3,IFRC,FICV/CV
+4,International Federation of Red Cross and Red Crescent Societies ,Federação Internacional das Sociedades da Cruz Vermelha e do Crescente Vermelho
+5,AI,AI
+6,Amnesty International,Amnistia Internacional
diff --git a/testum/resultatum/de-hxl/hxl-non-hxltm-exemplum.tm.hxl.csv b/testum/resultatum/de-hxl/hxl-non-hxltm-exemplum.tm.hxl.csv
@@ -0,0 +1,8 @@
+id,en,pt
+#item+conceptum+codicem,#item+terminum+i_en+i_eng+is_latn+rem,#item+terminum+i_pt+i_por+is_latn+rem
+1,UN,ONU
+2,United Nations,Organização das Nações Unidas
+3,IFRC,FICV/CV
+4,International Federation of Red Cross and Red Crescent Societies ,Federação Internacional das Sociedades da Cruz Vermelha e do Crescente Vermelho
+5,AI,AI
+6,Amnesty International,Amnistia Internacional