Re-generate CLDF with notes.

complexico · Jul 6, 2024 · 5b2e2bd · 5b2e2bd
1 parent 1e036fa
commit 5b2e2bd
Show file tree

Hide file tree

Showing 11 changed files with 343 additions and 335 deletions.
diff --git a/.Rhistory b/.Rhistory
diff --git a/.zenodo.json b/.zenodo.json
@@ -7,20 +7,18 @@
     ],
     "creators": [
         {
-            "name": "Carl Benjamin Hermann von Rosenberg"
-        }
-    ],
-    "contributors": [
-        {
-            "name": "Gede Primahadi W. Rajeg",
-            "type": "Other"
+            "name": "Gede Primahadi W. Rajeg"
         }
     ],
+    "contributors": [],
     "communities": [
         {
             "identifier": "lexibank"
         }
     ],
     "upload_type": "dataset",
-    "description": "<p>Cite the source of the dataset as:</p>\n\n<blockquote>\n<p>Rosenberg, Carl Benjamin Hermann von. 1853. De Mentawei-Eilanden en Hunne Bewoners. Tijdschrift voor Indische Taal-, Land- en Volkenkunde 1. 403\u2013440.</p>\n</blockquote>"
+    "description": "<p>Cite the source of the dataset as:</p>\n\n<blockquote>\n<p>Rosenberg, Carl Benjamin Hermann von. 1853. De Mentawei-Eilanden en Hunne Bewoners. Tijdschrift voor Indische Taal-, Land- en Volkenkunde 1. 403\u2013440.</p>\n</blockquote>",
+    "license": {
+        "id": "CC-BY-NC-SA-4.0"
+    }
 }
diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md
@@ -2,5 +2,4 @@
 
 Name                 | GitHub user     | Description                          | Role
 ---                  | ---             | ---                                  | ---
-Carl Benjamin Hermann von Rosenberg |                 |                                      | Author
-Gede Primahadi W. Rajeg       | @gederajeg       | maintainer, CLDF conversion, Concepticon mapping, Orthography profiling                           | Other
+Gede Primahadi W. Rajeg       | @gederajeg       | digitisation, code, CLDF conversion, Concepticon mapping, Orthography profiling                           | Maintainer
diff --git a/LICENSE b/LICENSE
@@ -33,7 +33,7 @@ exhaustive, and do not form part of our licenses.
      material not subject to the license. This includes other CC-
      licensed material, or material used under an exception or
      limitation to copyright. More considerations for licensors:
-    wiki.creativecommons.org/Considerations_for_licensors
+	wiki.creativecommons.org/Considerations_for_licensors
 
      Considerations for the public: By using one of our public
      licenses, a licensor grants the public permission to use the
@@ -49,8 +49,8 @@ exhaustive, and do not form part of our licenses.
      such as asking that all changes be marked or described.
      Although not required by our licenses, you are encouraged to
      respect those requests where reasonable. More considerations
-     for the public:
-    wiki.creativecommons.org/Considerations_for_licensees
+     for the public: 
+	wiki.creativecommons.org/Considerations_for_licensees
 
 =======================================================================
 
@@ -435,3 +435,4 @@ the avoidance of doubt, this paragraph does not form part of the
 public licenses.
 
 Creative Commons may be contacted at creativecommons.org.
+
diff --git a/README.md b/README.md
@@ -1,5 +1,9 @@
 # CLDF dataset derived from von Rosenberg's "De Mentawei-Eilanden en Hunne Bewoners" from 1853
 
+<!-- badges: start -->
+[![CLDF validation](https://github.com/complexico/mentawai-word-list-1853/workflows/CLDF-validation/badge.svg)](https://github.com/complexico/mentawai-word-list-1853/actions?query=workflow%3ACLDF-validation)
+<!-- badges: end -->
+
 ## How to cite
 
 If you use these data please cite
@@ -10,10 +14,17 @@ If you use these data please cite
 ## Description
 
 
-This dataset is licensed under a CC-BY-NC-SA 4.0 license
+This dataset is licensed under a https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en license
 
 Available online at https://www.digitale-sammlungen.de/en/view/bsb10433845?page=450,451
 
+## Notes
+
+Based on the [Rights Statement](https://www.digitale-sammlungen.de/en/details/bsb10433845) (presented down below in that page), this digitised journal has a [No Copyright-Non-commercial use only](https://rightsstatements.org/page/NoC-NC/1.0/?language=en) condition.
+
+Before the CLDF conversion using Python, the materials in this repository (inside the [data](https://github.com/complexico/mentawai-word-list-1853/tree/main/data) directory) were processed using R as an RStudio project (the R scripts are in the [codes](https://github.com/complexico/mentawai-word-list-1853/tree/main/codes) directory). The English gloss of the Dutch was generated via the DeepL translator using the [`deeplr` R package](https://cran.r-project.org/package=deeplr).
+
+
 ## Statistics
 
 
@@ -37,8 +48,7 @@ Available online at https://www.digitale-sammlungen.de/en/view/bsb10433845?page=
 
 Name                 | GitHub user     | Description                          | Role
 ---                  | ---             | ---                                  | ---
-Carl Benjamin Hermann von Rosenberg |                 |                                      | Author
-Gede Primahadi W. Rajeg       | @gederajeg       | maintainer, CLDF conversion, Concepticon mapping, Orthography profiling                           | Other
+Gede Primahadi W. Rajeg       | @gederajeg       | digitisation, code, CLDF conversion, Concepticon mapping, Orthography profiling                           | Maintainer
 
 
 

diff --git a/cldf/.transcription-report.json b/cldf/.transcription-report.json
@@ -2,9 +2,9 @@
     "by_language": {
         "Mentawai": {
             "bipa_errors": [
+                "t\u0361\u0292",
                 "<<\u00eb>>",
-                "<<->>",
-                "t\u0361\u0292"
+                "<<->>"
             ],
             "general_errors": 18,
             "replacements": {
@@ -100,9 +100,9 @@
                 ]
             },
             "sclass_errors": [
+                "t\u0361\u0292",
                 "<<\u00eb>>",
-                "<<->>",
-                "t\u0361\u0292"
+                "<<->>"
             ],
             "segments": {
                 "+": 1,
@@ -251,9 +251,9 @@
         ],
         "bad_words_count": 15,
         "bipa_errors": [
+            "t\u0361\u0292",
             "<<\u00eb>>",
-            "<<->>",
-            "t\u0361\u0292"
+            "<<->>"
         ],
         "general_errors": 18,
         "invalid_words": [],
@@ -352,9 +352,9 @@
             ]
         },
         "sclass_errors": [
+            "t\u0361\u0292",
             "<<\u00eb>>",
-            "<<->>",
-            "t\u0361\u0292"
+            "<<->>"
         ],
         "segments": {
             "+": 1,

diff --git a/cldf/README.md b/cldf/README.md
@@ -11,9 +11,9 @@ property | value
 [dc:bibliographicCitation](http://purl.org/dc/terms/bibliographicCitation) | Rosenberg, Carl Benjamin Hermann von. 1853. De Mentawei-Eilanden en Hunne Bewoners. Tijdschrift voor Indische Taal-, Land- en Volkenkunde 1. 403–440.
 [dc:conformsTo](http://purl.org/dc/terms/conformsTo) | [CLDF Wordlist](http://cldf.clld.org/v1.0/terms.rdf#Wordlist)
 [dc:identifier](http://purl.org/dc/terms/identifier) | https://www.digitale-sammlungen.de/en/view/bsb10433845?page=450,451
-[dc:license](http://purl.org/dc/terms/license) | CC-BY-NC-SA 4.0
+[dc:license](http://purl.org/dc/terms/license) | https://creativecommons.org/licenses/by-nc-sa/4.0/
 [dcat:accessURL](http://www.w3.org/ns/dcat#accessURL) | git@github.com:complexico/mentawai-word-list-1853
-[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="git@github.com:complexico/mentawai-word-list-1853/tree/774ff3f">git@github.com:complexico/mentawai-word-list-1853 774ff3f</a></li><li><a href="glottolog-glottolog-d9da5e2">Glottolog glottolog-glottolog-d9da5e2</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/7c0b6ae3">Concepticon v3.1.0-19-g7c0b6ae3</a></li><li><a href="cldf-clts-clts-6dc73af">CLTS cldf-clts-clts-6dc73af</a></li></ol>
+[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="git@github.com:complexico/mentawai-word-list-1853/tree/1e036fa">git@github.com:complexico/mentawai-word-list-1853 1e036fa</a></li><li><a href="glottolog-glottolog-d9da5e2">Glottolog glottolog-glottolog-d9da5e2</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/7c0b6ae3">Concepticon v3.1.0-19-g7c0b6ae3</a></li><li><a href="cldf-clts-clts-6dc73af">CLTS cldf-clts-clts-6dc73af</a></li></ol>
 [prov:wasGeneratedBy](http://www.w3.org/ns/prov#wasGeneratedBy) | <ol><li><strong>lingpy-rcParams</strong>: <a href="./lingpy-rcParams.json">lingpy-rcParams.json</a></li><li><strong>python</strong>: 3.9.6</li><li><strong>python-packages</strong>: <a href="./requirements.txt">requirements.txt</a></li></ol>
 [rdf:ID](http://www.w3.org/1999/02/22-rdf-syntax-ns#ID) | barrier-islands-mentawai-wlist1853
 [rdf:type](http://www.w3.org/1999/02/22-rdf-syntax-ns#type) | http://www.w3.org/ns/dcat#Distribution

diff --git a/cldf/cldf-metadata.json b/cldf/cldf-metadata.json
@@ -5,7 +5,7 @@
     "dc:conformsTo": "http://cldf.clld.org/v1.0/terms.rdf#Wordlist",
     "dc:identifier": "https://www.digitale-sammlungen.de/en/view/bsb10433845?page=450,451",
     "dc:isVersionOf": null,
-    "dc:license": "CC-BY-NC-SA 4.0",
+    "dc:license": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
     "dc:related": null,
     "dc:source": "sources.bib",
     "dc:title": "CLDF dataset derived from von Rosenberg's \"De Mentawei-Eilanden en Hunne Bewoners\" from 1853",
@@ -14,7 +14,7 @@
         {
             "rdf:about": "git@github.com:complexico/mentawai-word-list-1853",
             "rdf:type": "prov:Entity",
-            "dc:created": "774ff3f",
+            "dc:created": "1e036fa",
             "dc:title": "Repository"
         },
         {

diff --git a/cldf/lingpy-rcParams.json b/cldf/lingpy-rcParams.json
@@ -123,7 +123,7 @@
     "scorer": {},
     "sonar": true,
     "stress": "\u02c8\u02cc'",
-    "timestamp": "2024-07-06 11:25",
+    "timestamp": "2024-07-06 14:58",
     "tones": "\u00b9\u00b2\u00b3\u2074\u2075\u2076\u2077\u2078\u2079\u2070\u2081\u2082\u2083\u2084\u2085\u2086\u2087\u2088\u2089\u20800123456789\u02e5\u02e6\u02e7\u02e8\u02e9\u02ea\u02eb-\ua708-\ua709-\ua70a-\ua70b-\ua70c-\ua70d-\ua70e-\ua70f-\ua710-\ua711-\ua712-\ua713-\ua714-\ua715-\ua716-\ua717-\ua718-\ua719-\ua71a-\ua700-\ua701-\ua702-\ua703-\ua704-\ua705-\ua706-\ua707",
     "tree_calc": "neighbor",
     "unique_sequences": true,

diff --git a/metadata.json b/metadata.json
@@ -2,7 +2,7 @@
     "id": "barrier-islands-mentawai-wlist1853",
     "title": "CLDF dataset derived from von Rosenberg's \"De Mentawei-Eilanden en Hunne Bewoners\" from 1853",
     "description": null,
-    "license": "CC-BY-NC-SA 4.0",
+    "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en",
     "url": "https://www.digitale-sammlungen.de/en/view/bsb10433845?page=450,451",
     "citation": "Rosenberg, Carl Benjamin Hermann von. 1853. De Mentawei-Eilanden en Hunne Bewoners. Tijdschrift voor Indische Taal-, Land- en Volkenkunde 1. 403\u2013440."
 }
diff --git a/tutorial-step-notes-to-create-the-cldf.sh b/tutorial-step-notes-to-create-the-cldf.sh
@@ -59,7 +59,7 @@ tree -v --charset utf-8
 cldfbench lexibank.makecldf cldfbench_barrier-islands-mentawai-wlist1853.py --glottolog "/Users/Primahadi/Documents/cldf_project/glottolog-glottolog-d9da5e2" --concepticon "/Users/Primahadi/Documents/cldf_project/concepticon/concepticon-data" --clts "/Users/Primahadi/Documents/cldf_project/cldf-clts-clts-6dc73af"
 
 # to create an orthography profile (with a guess to possible IPA form/phoneme) from the Form col. in cldf/forms.csv using pylexibank (cf. List (2021: section 6)): https://calc.hypotheses.org/2954
-cldfbench lexibank.init_profile cldfbench_barrier-islands-mentawai-wlist1853.py --clts "/Users/Primahadi/Documents/cldf_project/cldf-clts-clts-6dc73af"
+# cldfbench lexibank.init_profile cldfbench_barrier-islands-mentawai-wlist1853.py --clts "/Users/Primahadi/Documents/cldf_project/cldf-clts-clts-6dc73af"
 
 ## note on orthography workflow
 - # we could add an orthography profile file (orthography.tsv) in `etc` directory that we previously created using qlcData and manually edited (## ensure we already have the IPA match of the grapheme as well!)