Fixing single Glottocode and CLDF conversion (#2)

Fix Glottocode
lexibank · Mar 1, 2024 · 29d67a9 · 29d67a9
1 parent cb351ce
commit 29d67a9
Show file tree

Hide file tree

Showing 8 changed files with 67 additions and 60 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: [3.9]
 
     steps:
     - uses: actions/checkout@v2

diff --git a/README.md b/README.md
@@ -48,7 +48,7 @@ This dataset by Sidwell (2015) was used as a gold standard benchmark in the stud
 - **Cognate Diversity:** 0.20
 - **Invalid lexemes:** 0
 - **Tokens:** 17,314
-- **Segments:** 133 (0 BIPA errors, 0 CTLS sound class errors, 133 CLTS modified)
+- **Segments:** 133 (0 BIPA errors, 0 CLTS sound class errors, 133 CLTS modified)
 - **Inventory size (avg):** 47.12
 
 # Contributors

diff --git a/cldf/README.md b/cldf/README.md
@@ -13,8 +13,8 @@ property | value
 [dc:format](http://purl.org/dc/terms/format) | <ol><li>http://concepticon.clld.org/contributions/Sidwell-2015-200</li></ol>
 [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/sidwellbahnaric
-[prov:wasDerivedFrom](http://www.w3.org/ns/prov#wasDerivedFrom) | <ol><li><a href="https://github.com/lexibank/sidwellbahnaric/tree/dbc3d27">lexibank/sidwellbahnaric dbc3d27</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/sidwellbahnaric/tree/v1.0">lexibank/sidwellbahnaric v1.0</a></li><li><a href="https://github.com/glottolog/glottolog/tree/v4.8">Glottolog v4.8</a></li><li><a href="https://github.com/concepticon/concepticon-data/tree/v3.1.0">Concepticon v3.1.0</a></li><li><a href="https://github.com/cldf-clts/clts/tree/v2.2.0">CLTS v2.2.0</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>: 3.9.6</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) | sidwellbahnaric
 [rdf:type](http://www.w3.org/1999/02/22-rdf-syntax-ns#type) | http://www.w3.org/ns/dcat#Distribution
 
@@ -72,8 +72,8 @@ Name/Property | Datatype | Description
 `Glottolog_Name` | `string` | 
 [ISO639P3code](http://cldf.clld.org/v1.0/terms.rdf#iso639P3code) | `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` | 
 
 ## <a name="table-parameterscsv"></a>Table [parameters.csv](./parameters.csv)

diff --git a/cldf/cldf-metadata.json b/cldf/cldf-metadata.json
@@ -16,25 +16,25 @@
         {
             "rdf:about": "https://github.com/lexibank/sidwellbahnaric",
             "rdf:type": "prov:Entity",
-            "dc:created": "dbc3d27",
+            "dc:created": "v1.0",
             "dc:title": "Repository"
         },
         {
             "rdf:about": "https://github.com/glottolog/glottolog",
             "rdf:type": "prov:Entity",
-            "dc:created": "v4.4",
+            "dc:created": "v4.8",
             "dc:title": "Glottolog"
         },
         {
             "rdf:about": "https://github.com/concepticon/concepticon-data",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.5.0",
+            "dc:created": "v3.1.0",
             "dc:title": "Concepticon"
         },
         {
             "rdf:about": "https://github.com/cldf-clts/clts",
             "rdf:type": "prov:Entity",
-            "dc:created": "v2.1.0",
+            "dc:created": "v2.2.0",
             "dc:title": "CLTS"
         }
     ],
@@ -45,7 +45,7 @@
         },
         {
             "dc:title": "python",
-            "dc:description": "3.8.10"
+            "dc:description": "3.9.6"
         },
         {
             "dc:title": "python-packages",
@@ -54,9 +54,6 @@
     ],
     "rdf:ID": "sidwellbahnaric",
     "rdf:type": "http://www.w3.org/ns/dcat#Distribution",
-    "dialect": {
-        "commentPrefix": null
-    },
     "tables": [
         {
             "dc:conformsTo": "http://cldf.clld.org/v1.0/terms.rdf#FormTable",
@@ -180,7 +177,7 @@
                     {
                         "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"
                     },
                     {
@@ -246,7 +243,7 @@
                     {
                         "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"
                     },
                     {

diff --git a/cldf/languages.csv b/cldf/languages.csv
@@ -14,7 +14,7 @@ sre,Sre,koho1244,Koho,kpm,Eurasia,11.6444,108.057,Austroasiatic
 alak,Alak,alak1253,Alak,alk,Eurasia,15.5565,106.597,Austroasiatic
 bunong,Bunong,cent1992,Central Mnong,cmo,Eurasia,12.6313,107.301,Austroasiatic
 bahnargolar,BahnarGolar,bahn1262,Bahnar,bdq,Eurasia,14.0476,108.471,Austroasiatic
-kasseng,Kasseng,kass1248,,,,,,
+kasseng,Kasseng,tali1257,Talieng,tdf,Eurasia,16.5287,106.102,Austroasiatic
 sedang,Sedang,seda1262,Sedang,sed,Eurasia,14.7793,108.027,Austroasiatic
 ramam,Ramam,roma1331,Romam,rmx,Eurasia,14.34,107.447,Austroasiatic
 mnongrlm,MnongRlm,east2333,Eastern Mnong,mng,Eurasia,12.3939,108.354,Austroasiatic

diff --git a/cldf/lingpy-rcParams.json b/cldf/lingpy-rcParams.json
@@ -64,7 +64,7 @@
         10,
         10
     ],
-    "filename": "lingpy-2021-07-26",
+    "filename": "lingpy-2024-02-29",
     "gap_symbol": "-",
     "gap_weight": 0.5,
     "gop": -2,
@@ -123,7 +123,7 @@
     "scorer": {},
     "sonar": true,
     "stress": "\u02c8\u02cc'",
-    "timestamp": "2021-07-26 10:40",
+    "timestamp": "2024-02-29 13:05",
     "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/cldf/requirements.txt b/cldf/requirements.txt
@@ -1,47 +1,57 @@
 appdirs==1.4.4
-bs4==0.0.1
-certifi==2021.5.30
-cldfbench==1.7.1
-cldfcatalog==1.3.2
-clldutils==3.9.0
-colorlog==5.0.1
-csvw==1.11.0
-decorator==4.4.2
-gitdb==4.0.7
-greenlet==1.1.0
-idna==3.2
-iniconfig==1.1.1
-isodate==0.6.0
-lingpy==2.6.8
-Markdown==3.3.4
-networkx==2.5.1
-newick==1.3.0
-numpy==1.21.1
-openpyxl==3.0.7
-packaging==21.0
-pluggy==0.13.1
+attrs==23.2.0
+Babel==2.14.0
+bibtexparser==2.0.0b7
+bs4==0.0.2
+certifi==2024.2.2
+cldfbench==1.14.0
+cldfcatalog==1.5.1
+cldfzenodo==2.1.0
+clldutils==3.22.1
+colorama==0.4.6
+colorlog==6.8.2
+csvw==3.3.0
+exceptiongroup==1.2.0
+gitdb==4.0.11
+idna==3.6
+iniconfig==2.0.0
+isodate==0.6.1
+jsonschema==4.21.1
+lingpy==2.6.13
+lxml==5.1.0
+Markdown==3.5.2
+nameparser==1.1.3
+networkx==3.2.1
+newick==1.9.0
+numpy==1.26.4
+openpyxl==3.1.2
+packaging==23.2
+pluggy==1.4.0
 purl==1.6
-py==1.10.0
 pybtex==0.24.0
-pycldf==1.22.0
+pycldf==1.37.0
 pyclts==3.1.1
-pyconcepticon==2.8.0
-pycountry==20.7.3
-pyglottolog==3.6.0
-pylexibank==3.2.0
-pytest==6.2.4
-regex==2021.7.6
-requests==2.26.0
+pyconcepticon==3.0.0
+pycountry==23.12.11
+pyglottolog==3.12.0
+pylatexenc==2.10
+pylexibank==3.4.0
+pytest==8.0.2
+python-dateutil==2.8.2
+rdflib==7.0.0
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
 rfc3986==1.5.0
-segments==2.2.0
+segments==2.2.1
 six==1.16.0
-smmap==4.0.0
-soupsieve==2.2.1
-SQLAlchemy==1.4.22
-tabulate==0.8.9
-termcolor==1.1.0
-tqdm==4.61.2
-uritemplate==3.0.1
-urllib3==1.26.6
+smmap==5.0.1
+soupsieve==2.5
+SQLAlchemy==1.4.51
+tabulate==0.9.0
+termcolor==2.4.0
+tqdm==4.66.2
+uritemplate==4.1.1
+urllib3==2.2.1
 xlrd==2.0.1
-zenodoclient==0.4.1
+zenodoclient==0.5.1
diff --git a/etc/languages.tsv b/etc/languages.tsv
@@ -14,7 +14,7 @@ Sre	Sre	koho1244
 Alak	Alak	alak1253
 Bunong	Bunong	cent1992
 BahnarGolar	BahnarGolar	bahn1262
-Kasseng	Kasseng	kass1248
+Kasseng	Kasseng	tali1257
 Sedang	Sedang	seda1262
 Ramam	Ramam	roma1331
 MnongRlm	MnongRlm	east2333