release prep

lexibank · Jul 8, 2024 · 2621395 · 2621395
1 parent c8d3bfe
commit 2621395
Show file tree

Hide file tree

Showing 12 changed files with 301 additions and 294 deletions.
diff --git a/.github/workflows/cldf-validation.yml b/.github/workflows/cldf-validation.yml
@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6]
+        python-version: ["3.10", 3.11, 3.12]
 
     steps:
     - uses: actions/checkout@v2

diff --git a/.zenodo.json b/.zenodo.json
@@ -13,7 +13,7 @@
     "contributors": [
         {
             "name": "Johann-Mattis List",
-            "type": "Other"
+            "type": "Editor"
         }
     ],
     "communities": [

diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md
@@ -1,6 +1,6 @@
 # Contributors
 
 Name | GitHub user | Description | Role
---- | --- | --- | --- |
-Beijing University | | data collection | Author 
-Johann-Mattis List | @LinguList | maintainer | Other
+--- | --- | --- | ---
+Beijing University | | data collection | Author
+Johann-Mattis List | @LinguList | maintainer | Editor
diff --git a/README.md b/README.md
@@ -35,22 +35,22 @@ This dataset, which is well-known among Sinologists, comprises 18 dialect variet
 ![BIPA: 100%](https://img.shields.io/badge/BIPA-100%25-brightgreen.svg "BIPA: 100%")
 ![CLTS SoundClass: 100%](https://img.shields.io/badge/CLTS%20SoundClass-100%25-brightgreen.svg "CLTS SoundClass: 100%")
 
-- **Varieties:** 18
-- **Concepts:** 905
+- **Varieties:** 18 (linked to 18 different Glottocodes)
+- **Concepts:** 905 (linked to 738 different Concepticon concept sets)
 - **Lexemes:** 18,059
 - **Sources:** 1
 - **Synonymy:** 1.11
 - **Invalid lexemes:** 0
 - **Tokens:** 120,791
-- **Segments:** 279 (0 BIPA errors, 0 CTLS sound class errors, 279 CLTS modified)
+- **Segments:** 279 (0 BIPA errors, 0 CLTS sound class errors, 279 CLTS modified)
 - **Inventory size (avg):** 62.78
 
 # Contributors
 
 Name | GitHub user | Description | Role
---- | --- | --- | --- |
-Beijing University | | data collection | Author 
-Johann-Mattis List | @LinguList | maintainer | Other
+--- | --- | --- | ---
+Beijing University | | data collection | Author
+Johann-Mattis List | @LinguList | maintainer | Editor
 
 
 

diff --git a/cldf/README.md b/cldf/README.md
@@ -19,8 +19,8 @@ property | value
 [dc:identifier](http://purl.org/dc/terms/identifier) | https://github.com/digling/cddb/
 [dc:license](http://purl.org/dc/terms/license) | https://creativecommons.org/licenses/by/4.0/
 [dcat:accessURL](http://www.w3.org/ns/dcat#accessURL) | https://github.com/lexibank/beidasinitic
-[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="https://github.com/lexibank/beidasinitic/tree/99d9ade">lexibank/beidasinitic v4.0-30-g99d9ade</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v4.4">Glottolog v4.4</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v2.5.0">Concepticon v2.5.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.1.0">CLTS v2.1.0</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>: 3.8.10</li><li><strong>python-packages</strong>: <a href="./requirements.txt">requirements.txt</a></li></ol>
+[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="https://github.com/lexibank/beidasinitic/tree/v5.0.1">lexibank/beidasinitic v5.0.1</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v5.0">Glottolog v5.0</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v3.2.0">Concepticon v3.2.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.3.0">CLTS v2.3.0</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>: 3.12.4</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) | beidasinitic
 [rdf:type](http://www.w3.org/1999/02/22-rdf-syntax-ns#type) | http://www.w3.org/ns/dcat#Distribution
 
@@ -69,8 +69,8 @@ Name/Property | Datatype | Description
 [Glottocode](http://cldf.clld.org/v1.0/terms.rdf#glottocode) | `string` | 
 `Glottolog_Name` | `string` | 
 [Macroarea](http://cldf.clld.org/v1.0/terms.rdf#macroarea) | `string` | 
-[Latitude](http://cldf.clld.org/v1.0/terms.rdf#latitude) | `decimal` | 
-[Longitude](http://cldf.clld.org/v1.0/terms.rdf#longitude) | `decimal` | 
+[Latitude](http://cldf.clld.org/v1.0/terms.rdf#latitude) | `decimal`<br>&ge; -90<br>&le; 90 | 
+[Longitude](http://cldf.clld.org/v1.0/terms.rdf#longitude) | `decimal`<br>&ge; -180<br>&le; 180 | 
 `Family` | `string` | 
 `ChineseName` | `string` | 
 `SubGroup` | `string` | 
@@ -112,8 +112,8 @@ property | value
 [dc:identifier](http://purl.org/dc/terms/identifier) | https://github.com/digling/cddb/
 [dc:license](http://purl.org/dc/terms/license) | https://creativecommons.org/licenses/by/4.0/
 [dcat:accessURL](http://www.w3.org/ns/dcat#accessURL) | https://github.com/lexibank/beidasinitic
-[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="https://github.com/lexibank/beidasinitic/tree/99d9ade">lexibank/beidasinitic v4.0-30-g99d9ade</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v4.4">Glottolog v4.4</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v2.5.0">Concepticon v2.5.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.1.0">CLTS v2.1.0</a></li></ol>
-[prov:wasGeneratedBy](http://www.w3.org/ns/prov#wasGeneratedBy) | <ol><li><strong>python</strong>: 3.8.10</li><li><strong>python-packages</strong>: <a href="./requirements.txt">requirements.txt</a></li></ol>
+[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="https://github.com/lexibank/beidasinitic/tree/v5.0.1">lexibank/beidasinitic v5.0.1</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v5.0">Glottolog v5.0</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v3.2.0">Concepticon v3.2.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.3.0">CLTS v2.3.0</a></li></ol>
+[prov:wasGeneratedBy](http://www.w3.org/ns/prov#wasGeneratedBy) | <ol><li><strong>python</strong>: 3.12.4</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) | beidasinitic
 [rdf:type](http://www.w3.org/1999/02/22-rdf-syntax-ns#type) | http://www.w3.org/ns/dcat#Distribution
 
@@ -130,7 +130,7 @@ property | value
 
 Name/Property | Datatype | Description
  --- | --- | --- 
-[ID](http://cldf.clld.org/v1.0/terms.rdf#id) | `string` | Primary key
+[ID](http://cldf.clld.org/v1.0/terms.rdf#id) | `string`<br>Regex: `[a-zA-Z0-9_\-]+` | Primary key
 [Language_ID](http://cldf.clld.org/v1.0/terms.rdf#languageReference) | `string` | References [languages.csv::ID](#table-languagescsv)
 [Parameter_ID](http://cldf.clld.org/v1.0/terms.rdf#parameterReference) | `string` | References [features.csv::ID](#table-featurescsv)
 [Value](http://cldf.clld.org/v1.0/terms.rdf#value) | `string` | 
@@ -151,9 +151,10 @@ property | value
 
 Name/Property | Datatype | Description
  --- | --- | --- 
-[ID](http://cldf.clld.org/v1.0/terms.rdf#id) | `string` | Primary key
+[ID](http://cldf.clld.org/v1.0/terms.rdf#id) | `string`<br>Regex: `[a-zA-Z0-9_\-]+` | Primary key
 [Name](http://cldf.clld.org/v1.0/terms.rdf#name) | `string` | 
 [Description](http://cldf.clld.org/v1.0/terms.rdf#description) | `string` | 
+[ColumnSpec](http://cldf.clld.org/v1.0/terms.rdf#columnSpec) | `json` | 
 `CLTS_BIPA` | `string` | 
 `CLTS_Name` | `string` | 
 `Lexibank_BIPA` | `string` | 
@@ -176,8 +177,8 @@ Name/Property | Datatype | Description
 [Glottocode](http://cldf.clld.org/v1.0/terms.rdf#glottocode) | `string` | 
 `Glottolog_Name` | `string` | 
 [Macroarea](http://cldf.clld.org/v1.0/terms.rdf#macroarea) | `string` | 
-[Latitude](http://cldf.clld.org/v1.0/terms.rdf#latitude) | `decimal` | 
-[Longitude](http://cldf.clld.org/v1.0/terms.rdf#longitude) | `decimal` | 
+[Latitude](http://cldf.clld.org/v1.0/terms.rdf#latitude) | `decimal`<br>&ge; -90<br>&le; 90 | 
+[Longitude](http://cldf.clld.org/v1.0/terms.rdf#longitude) | `decimal`<br>&ge; -180<br>&le; 180 | 
 `Family` | `string` | 
 `ChineseName` | `string` | 
 `SubGroup` | `string` | 

diff --git a/cldf/StructureDataset-metadata.json b/cldf/StructureDataset-metadata.json
@@ -22,32 +22,32 @@
         {
             "rdf:about": "https://github.com/lexibank/beidasinitic",
             "rdf:type": "prov:Entity",
-            "dc:created": "v4.0-30-g99d9ade",
+            "dc:created": "v5.0.1",
             "dc:title": "Repository"
         },
         {
             "rdf:about": "https://github.com/glottolog/glottolog",
             "rdf:type": "prov:Entity",
-            "dc:created": "v4.4",
+            "dc:created": "v5.0",
             "dc:title": "Glottolog"
         },
         {
             "rdf:about": "https://github.com/concepticon/concepticon-data",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.5.0",
+            "dc:created": "v3.2.0",
             "dc:title": "Concepticon"
         },
         {
             "rdf:about": "https://github.com/cldf-clts/clts",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.1.0",
+            "dc:created": "v2.3.0",
             "dc:title": "CLTS"
         }
     ],
     "prov:wasGeneratedBy": [
         {
             "dc:title": "python",
-            "dc:description": "3.8.10"
+            "dc:description": "3.12.4"
         },
         {
             "dc:title": "python-packages",
@@ -56,9 +56,6 @@
     ],
     "rdf:ID": "beidasinitic",
     "rdf:type": "http://www.w3.org/ns/dcat#Distribution",
-    "dialect": {
-        "commentPrefix": null
-    },
     "tables": [
         {
             "dc:conformsTo": "http://cldf.clld.org/v1.0/terms.rdf#ValueTable",
@@ -180,6 +177,12 @@
                         "required": false,
                         "name": "Description"
                     },
+                    {
+                        "datatype": "json",
+                        "propertyUrl": "http://cldf.clld.org/v1.0/terms.rdf#columnSpec",
+                        "required": false,
+                        "name": "ColumnSpec"
+                    },
                     {
                         "datatype": "string",
                         "name": "CLTS_BIPA"
@@ -221,7 +224,7 @@
                     {
                         "datatype": "string",
                         "propertyUrl": "http://cldf.clld.org/v1.0/terms.rdf#glottocode",
-                        "valueUrl": "http://glottolog.org/resource/languoid/id/{glottolog_id}",
+                        "valueUrl": "http://glottolog.org/resource/languoid/id/{Glottocode}",
                         "name": "Glottocode"
                     },
                     {

diff --git a/cldf/cldf-metadata.json b/cldf/cldf-metadata.json
@@ -17,25 +17,25 @@
         {
             "rdf:about": "https://github.com/lexibank/beidasinitic",
             "rdf:type": "prov:Entity",
-            "dc:created": "v4.0-30-g99d9ade",
+            "dc:created": "v5.0.1",
             "dc:title": "Repository"
         },
         {
             "rdf:about": "https://github.com/glottolog/glottolog",
             "rdf:type": "prov:Entity",
-            "dc:created": "v4.4",
+            "dc:created": "v5.0",
             "dc:title": "Glottolog"
         },
         {
             "rdf:about": "https://github.com/concepticon/concepticon-data",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.5.0",
+            "dc:created": "v3.2.0",
             "dc:title": "Concepticon"
         },
         {
             "rdf:about": "https://github.com/cldf-clts/clts",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.1.0",
+            "dc:created": "v2.3.0",
             "dc:title": "CLTS"
         }
     ],
@@ -46,7 +46,7 @@
         },
         {
             "dc:title": "python",
-            "dc:description": "3.8.10"
+            "dc:description": "3.12.4"
         },
         {
             "dc:title": "python-packages",
@@ -55,9 +55,6 @@
     ],
     "rdf:ID": "beidasinitic",
     "rdf:type": "http://www.w3.org/ns/dcat#Distribution",
-    "dialect": {
-        "commentPrefix": null
-    },
     "tables": [
         {
             "dc:conformsTo": "http://cldf.clld.org/v1.0/terms.rdf#FormTable",
@@ -184,7 +181,7 @@
                     {
                         "datatype": "string",
                         "propertyUrl": "http://cldf.clld.org/v1.0/terms.rdf#glottocode",
-                        "valueUrl": "http://glottolog.org/resource/languoid/id/{glottolog_id}",
+                        "valueUrl": "http://glottolog.org/resource/languoid/id/{Glottocode}",
                         "name": "Glottocode"
                     },
                     {
@@ -257,7 +254,7 @@
                     {
                         "datatype": "string",
                         "propertyUrl": "http://cldf.clld.org/v1.0/terms.rdf#concepticonReference",
-                        "valueUrl": "http://concepticon.clld.org/parameters/{concepticon_id}",
+                        "valueUrl": "http://concepticon.clld.org/parameters/{Concepticon_ID}",
                         "name": "Concepticon_ID"
                     },
                     {