First commit.

.github/workflows/python-package.yml

@@ -0,0 +1,29 @@
+name: CLDF-validation
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.6]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pytest-cldf
+    - name: Test with pytest
+      run: |
+        pytest --cldf-metadata=cldf/cldf-metadata.json test.py 

.gitignore

@@ -0,0 +1,102 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+

cldf/.gitattributes

@@ -0,0 +1 @@
+*.csv text eol=crlf

cldf/README.md

@@ -0,0 +1,3 @@
+# CLDF directory
+
+This directory contains the dataset formatted as [CLDF dataset](https://cldf.clld.org).

cldfbench_vrosenberg1853.py

@@ -0,0 +1,26 @@
+import pathlib
+
+from cldfbench import Dataset as BaseDataset
+
+
+class Dataset(BaseDataset):
+    dir = pathlib.Path(__file__).parent
+    id = "vrosenberg1853"
+
+    def cldf_specs(self):  # A dataset must declare all CLDF sets it creates.
+        return super().cldf_specs()
+
+    def cmd_download(self, args):
+        """
+        Download files to the raw/ directory. You can use helpers methods of `self.raw_dir`, e.g.
+
+        >>> self.raw_dir.download(url, fname)
+        """
+        pass
+
+    def cmd_makecldf(self, args):
+        """
+        Convert the raw data to a CLDF dataset.
+
+        >>> args.writer.objects['LanguageTable'].append(...)
+        """

etc/00-steps-on-terminal.sh

@@ -0,0 +1,16 @@
+source /Users/Primahadi/Documents/cldf_project/myenv/bin/activate
+
+cldfbench new
+# id: vrosenberg1853
+# title: CLDF dataset derived from von Rosenberg's "De Mentawei-Eilanden en Hunne Bewoners" from 1853 for comparative numeral data
+# license: https://creativecommons.org/licenses/by-nc-sa/4.0/
+# url: 
+# citation: Rosenberg, Carl Benjamin Hermann von. 1853. De Mentawei-Eilanden en Hunne Bewoners. Tijdschrift voor Indische Taal-, Land- en Volkenkunde 1. 403–440.
+
+cd vrosenberg1853
+
+# pre-process the raw data in `01-raw-data-pre-processing.R`
+
+# run pyconcepticon
+concepticon --repos "/Users/Primahadi/Documents/cldf_project/concepticon/concepticon-data" \
+map_concepts "etc/gloss-to-map.tsv" --language en --output "etc/concepts.tsv"

etc/01-raw-data-pre-processing.R

@@ -0,0 +1,53 @@
+library(tidyverse)
+library(deeplr)
+
+df <- read_tsv("https://raw.githubusercontent.com/complexico/mentawai-word-list-1853/main/data/vrosenberg1853p434.tsv")
+
+df <- df |>
+	mutate(ID = row_number()) |>
+	select(ID, everything()) |>
+	pivot_longer(cols = -c(Dutch, ID), names_to = "Doculect", values_to = "Forms")
+
+# prepare a translation data (run one time then save it)
+# source("etc/00-deeplr.R")
+# dutch <- df |>
+#	select(ID, Dutch) |>
+#	distinct()
+
+# dutch_w_english <- dutch |>
+#	mutate(English = translate2(text = Dutch, target_lang = "EN", source_lang = "NL", preserve_formatting = TRUE, auth_key = mydeepl))
+
+# dutch_w_english <- dutch_w_english |>
+# 	mutate(English = replace(English, English == "a", "one"))
+# write_tsv(dutch_w_english, file = "etc/dutch_w_english.tsv")
+
+dutch_w_english <- read_tsv("etc/dutch_w_english.tsv")
+
+doculect <- tribble(
+	~Doculect, ~Doculect_Eng, ~Glottocode, ~Glottolog_name,
+	"Maleisch", "Central Malay", "mala1479", "Central Malay",
+	"Lampongsch", "Lampungic", "lamp1241", "Lampungic",
+	"Redjangsch", "Rejang", "reja1240", "Rejang",
+	"Battasch", "Batakic", "toba1265", "Batakic",
+	"Atjinesch", "Acehnese", "achi1257", "Acehnese",
+	"Niasch", "Nias", "nias1242", "Nias",
+	"Mentaweijsch", "Mentawai", "ment1249", "Mentawai",
+	"Engganoosch", "Enggano", "engg1245", "Enggano"
+)
+# I choose Glottolog's Central Malay because I am not really sure the specific Malay variety referred to by von Rosenberg. Glottolog describes Central Malay as the primary source of the variety of Malay spoken throughout the South East Asia: "Malay (zlm-zlm) = 3 (Wider communication). Originated in Sumatra; spoken throughout southeast Asia. With the advent of Islam, Malay became widespread in the 15th and 16th centuries. Lingua franca for Malaysia’s multiethnic population. Used in trade, literature, and story telling."
+
+df <- df |>
+	left_join(dutch_w_english) |>
+	select(ID, Forms, Dutch, English, Doculect) |>
+	left_join(doculect) |>
+	rename(Doculect_orig = Doculect,
+		   Doculect = Doculect_Eng)
+
+df |> write_tsv("raw/raw-dat.tsv")
+
+# Prepare the concept for Concepticon mapping
+# df |>
+# 	select(ENGLISH = English, ID) |>
+# 	distinct() |>
+# 	write_tsv("etc/gloss-to-map.tsv")
+

etc/README.md

@@ -0,0 +1,4 @@
+# Configuration directory
+
+This directory contains "configuration" data, i.e. data which helps with and
+guides the conversion of the raw data to CLDF.

etc/concepts.tsv

@@ -0,0 +1,15 @@
+ENGLISH	ID	CONCEPTICON_ID	CONCEPTICON_GLOSS	SIMILARITY
+one	1	1493	ONE	2
+#<<<				
+two	2	1498	TWO	2
+two	2	1384	SECOND	2
+#>>>				
+three	3	492	THREE	2
+four	4	1500	FOUR	2
+five	5	493	FIVE	2
+six	6	1703	SIX	2
+seven	7	1704	SEVEN	2
+eight	8	1705	EIGHT	2
+nine	9	1483	NINE	2
+ten	10	1515	TEN	2
+#	10/10	100%	

etc/dutch_w_english.tsv

@@ -0,0 +1,11 @@
+ID	Dutch	English
+1	een	one
+2	twee	two
+3	drie	three
+4	vier	four
+5	vijf	five
+6	zes	six
+7	zeven	seven
+8	acht	eight
+9	negen	nine
+10	tien	ten

etc/gloss-to-map.tsv

@@ -0,0 +1,11 @@
+ENGLISH	ID
+one	1
+two	2
+three	3
+four	4
+five	5
+six	6
+seven	7
+eight	8
+nine	9
+ten	10

etc/languages.tsv

@@ -0,0 +1,9 @@
+ID	Doculect_Dutch	Name	Glottocode	Glottolog_Name	Sources
+1	Maleisch	Central Malay	mala1479	Central Malay	VonRosenberg1853
+2	Lampongsch	Lampungic	lamp1241	Lampungic	VonRosenberg1853
+3	Redjangsch	Rejang	reja1240	Rejang	VonRosenberg1853
+4	Battasch	Batakic	toba1265	Batakic	VonRosenberg1853
+5	Atjinesch	Acehnese	achi1257	Acehnese	VonRosenberg1853
+6	Niasch	Nias	nias1242	Nias	VonRosenberg1853
+7	Mentaweijsch	Mentawai	ment1249	Mentawai	VonRosenberg1853
+8	Engganoosch	Enggano	engg1245	Enggano	VonRosenberg1853

metadata.json

@@ -0,0 +1,8 @@
+{
+    "id": "vrosenberg1853",
+    "title": "CLDF dataset derived from von Rosenberg's \"De Mentawei-Eilanden en Hunne Bewoners\" from 1853 for comparative numeral data",
+    "description": null,
+    "license": "https://creativecommons.org/licenses/by-nc-sa/4.0/",
+    "url": null,
+    "citation": "Rosenberg, Carl Benjamin Hermann von. 1853. De Mentawei-Eilanden en Hunne Bewoners. Tijdschrift voor Indische Taal-, Land- en Volkenkunde 1. 403\u2013440."
+}

raw/README.md

@@ -0,0 +1,4 @@
+# Source directory
+
+This directory contains the "raw" source data of the dataset from which the
+CLDF dataset in [`cldf/`](../cldf) is derived.

raw/raw-dat.tsv

@@ -0,0 +1,81 @@
+ID	Forms	Dutch	English	Doculect_orig	Doculect	Glottocode	Glottolog_name
+1	satoe	een	one	Maleisch	Central Malay	mala1479	Central Malay
+1	sije	een	one	Lampongsch	Lampungic	lamp1241	Lampungic
+1	do	een	one	Redjangsch	Rejang	reja1240	Rejang
+1	sada	een	one	Battasch	Batakic	toba1265	Batakic
+1	sa	een	one	Atjinesch	Acehnese	achi1257	Acehnese
+1	sara	een	one	Niasch	Nias	nias1242	Nias
+1	sara	een	one	Mentaweijsch	Mentawai	ment1249	Mentawai
+1	daheij	een	one	Engganoosch	Enggano	engg1245	Enggano
+2	doea	twee	two	Maleisch	Central Malay	mala1479	Central Malay
+2	rowa	twee	two	Lampongsch	Lampungic	lamp1241	Lampungic
+2	dooij	twee	two	Redjangsch	Rejang	reja1240	Rejang
+2	doeo	twee	two	Battasch	Batakic	toba1265	Batakic
+2	doea	twee	two	Atjinesch	Acehnese	achi1257	Acehnese
+2	doea	twee	two	Niasch	Nias	nias1242	Nias
+2	doea	twee	two	Mentaweijsch	Mentawai	ment1249	Mentawai
+2	adoea	twee	two	Engganoosch	Enggano	engg1245	Enggano
+3	tiga	drie	three	Maleisch	Central Malay	mala1479	Central Malay
+3	pullo	drie	three	Lampongsch	Lampungic	lamp1241	Lampungic
+3	tellau	drie	three	Redjangsch	Rejang	reja1240	Rejang
+3	tolo	drie	three	Battasch	Batakic	toba1265	Batakic
+3	tlo	drie	three	Atjinesch	Acehnese	achi1257	Acehnese
+3	feloe	drie	three	Niasch	Nias	nias1242	Nias
+3	teloe	drie	three	Mentaweijsch	Mentawai	ment1249	Mentawai
+3	agoloe	drie	three	Engganoosch	Enggano	engg1245	Enggano
+4	ampat	vier	four	Maleisch	Central Malay	mala1479	Central Malay
+4	ampa	vier	four	Lampongsch	Lampungic	lamp1241	Lampungic
+4	mpat	vier	four	Redjangsch	Rejang	reja1240	Rejang
+4	opat	vier	four	Battasch	Batakic	toba1265	Batakic
+4	pat	vier	four	Atjinesch	Acehnese	achi1257	Acehnese
+4	effa	vier	four	Niasch	Nias	nias1242	Nias
+4	eppat	vier	four	Mentaweijsch	Mentawai	ment1249	Mentawai
+4	aöpa	vier	four	Engganoosch	Enggano	engg1245	Enggano
+5	lima	vijf	five	Maleisch	Central Malay	mala1479	Central Malay
+5	lema	vijf	five	Lampongsch	Lampungic	lamp1241	Lampungic
+5	lema	vijf	five	Redjangsch	Rejang	reja1240	Rejang
+5	lema	vijf	five	Battasch	Batakic	toba1265	Batakic
+5	lemoeng	vijf	five	Atjinesch	Acehnese	achi1257	Acehnese
+5	limang	vijf	five	Niasch	Nias	nias1242	Nias
+5	liman	vijf	five	Mentaweijsch	Mentawai	ment1249	Mentawai
+5	alima	vijf	five	Engganoosch	Enggano	engg1245	Enggano
+6	anam	zes	six	Maleisch	Central Malay	mala1479	Central Malay
+6	anam	zes	six	Lampongsch	Lampungic	lamp1241	Lampungic
+6	noom	zes	six	Redjangsch	Rejang	reja1240	Rejang
+6	onam	zes	six	Battasch	Batakic	toba1265	Batakic
+6	nam	zes	six	Atjinesch	Acehnese	achi1257	Acehnese
+6	e nem	zes	six	Niasch	Nias	nias1242	Nias
+6	ennem	zes	six	Mentaweijsch	Mentawai	ment1249	Mentawai
+6	akiakoio	zes	six	Engganoosch	Enggano	engg1245	Enggano
+7	toedjoe	zeven	seven	Maleisch	Central Malay	mala1479	Central Malay
+7	peto	zeven	seven	Lampongsch	Lampungic	lamp1241	Lampungic
+7	tojoa	zeven	seven	Redjangsch	Rejang	reja1240	Rejang
+7	paito	zeven	seven	Battasch	Batakic	toba1265	Batakic
+7	tojo	zeven	seven	Atjinesch	Acehnese	achi1257	Acehnese
+7	fitoe	zeven	seven	Niasch	Nias	nias1242	Nias
+7	pitoe	zeven	seven	Mentaweijsch	Mentawai	ment1249	Mentawai
+7	alima-adoea	zeven	seven	Engganoosch	Enggano	engg1245	Enggano
+8	delapan	acht	eight	Maleisch	Central Malay	mala1479	Central Malay
+8	oallo	acht	eight	Lampongsch	Lampungic	lamp1241	Lampungic
+8	delapon	acht	eight	Redjangsch	Rejang	reja1240	Rejang
+8	oallo	acht	eight	Battasch	Batakic	toba1265	Batakic
+8	dlappang	acht	eight	Atjinesch	Acehnese	achi1257	Acehnese
+8	walloe	acht	eight	Niasch	Nias	nias1242	Nias
+8	walloe	acht	eight	Mentaweijsch	Mentawai	ment1249	Mentawai
+8	alima-agoloe	acht	eight	Engganoosch	Enggano	engg1245	Enggano
+9	sembilan	negen	nine	Maleisch	Central Malay	mala1479	Central Malay
+9	sewa	negen	nine	Lampongsch	Lampungic	lamp1241	Lampungic
+9	sempilan	negen	nine	Redjangsch	Rejang	reja1240	Rejang
+9	sea	negen	nine	Battasch	Batakic	toba1265	Batakic
+9	sakorang	negen	nine	Atjinesch	Acehnese	achi1257	Acehnese
+9	siwa	negen	nine	Niasch	Nias	nias1242	Nias
+9	siwa	negen	nine	Mentaweijsch	Mentawai	ment1249	Mentawai
+9	alima-aöpa	negen	nine	Engganoosch	Enggano	engg1245	Enggano
+10	sapoeloe	tien	ten	Maleisch	Central Malay	mala1479	Central Malay
+10	polo	tien	ten	Lampongsch	Lampungic	lamp1241	Lampungic
+10	depoolo	tien	ten	Redjangsch	Rejang	reja1240	Rejang
+10	sapolo	tien	ten	Battasch	Batakic	toba1265	Batakic
+10	sapolo	tien	ten	Atjinesch	Acehnese	achi1257	Acehnese
+10	foeloe	tien	ten	Niasch	Nias	nias1242	Nias
+10	poeloe	tien	ten	Mentaweijsch	Mentawai	ment1249	Mentawai
+10	tahapoeloe	tien	ten	Engganoosch	Enggano	engg1245	Enggano