human_languages 0.5.0 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 631034119725af61d326b444a85929c504d264d846dd0290cf1ae62baf4f251f
-  data.tar.gz: bafdcaa5a045e7bfa8d99f7107b370908fcb38a558f25c2cd40d5cdf2fc1d3be
+  metadata.gz: 20b8b867dd0dfd832d335d36654c4694f052f3ac27678126a52b8c5a642f84ca
+  data.tar.gz: ec6824a865759f3996fa88b451e08df60f5b0dc5b3b7e7ac65da69b21aa999f6
 SHA512:
-  metadata.gz: c7b52732a22520bf41d360af3c8348049b4ab6c88e9c98acc5a43c4a258c849ba2e529f67631c266b3e537e73a510e8e6dee986998975b7b3732febaff3e7909
-  data.tar.gz: fa8c638cf53b4dc3c8d3b0101deaa430d9b686ed68ec574681c0b9039f73152d66bc262010565c9d35bde558253c95bf9f67c85d310ed966451fe9665d2f7b51
+  metadata.gz: 90e86425845dbc672d8b83f49f47c9d52daefe3cfe19f538297696e76c62e9e79636f7a29c83e7a2db50afdcc07b0af5802ee43114105c30924741bdaf1ea349
+  data.tar.gz: 6a11b163c23981727ee4192663438a5734b15b1af953eeb00841a389a45bca7d3a4e4e858ef384f803b3fe6906ce15c6c2c11fd1f593f5286fb5b297f0b0455f

data/.rubocop.yml

@@ -1,3 +1,8 @@
+---
+require:
+  - rubocop-minitest
+  - rubocop-rake
+
 AllCops:
   TargetRubyVersion: 2.7
   NewCops: enable

data/CHANGELOG.md

@@ -7,6 +7,30 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.7.0] - 2023-03-08
+
+### Added
+
+- Add `macrolanguage` reference for languages of scope `individual` that belong to a macrolanguage.
+- Add overview table in README about related and similar gems.
+- Add option to search language by name case insensitively.
+
+### Fixed
+
+- Installation instruction in README: wrong gem name, correct is `human_languages`
+
+### Changed
+
+- Update ISO 639 data incorporating approved [2022 changes](https://iso639-3.sil.org/sites/iso639-3/files/reports/639-3_ChangeRequests_2022_Summary.pdf).
+
+## [0.6.0] - 2022-06-08
+
+### Changed
+
+- Name of gem `languages` -> `human_languages`
+- Language's attribute `scope` is now a Symbol (previously String)
+- Language's attribute `type` is now a Symbol (previously String)
+
 ## [0.5.0] - 2022-06-06
 
 ### Changed

data/Gemfile

@@ -5,8 +5,8 @@ source 'https://rubygems.org'
 # Specify your gem's dependencies in languages.gemspec
 gemspec
 
-gem 'minitest', '~> 5.0'
+gem 'minitest', '~> 5.18'
 gem 'rake', '~> 13.0'
-gem 'rubocop', '~> 1.21'
-gem 'rubocop-minitest', '~> 0.20.0'
+gem 'rubocop', '~> 1.48'
+gem 'rubocop-minitest', '~> 0.29.0'
 gem 'rubocop-rake', '~> 0.6.0'

data/Gemfile.lock

@@ -1,47 +1,49 @@
 PATH
   remote: .
   specs:
-    languages (0.5.0)
+    human_languages (0.7.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
     ast (2.4.2)
-    minitest (5.15.0)
+    json (2.6.3)
+    minitest (5.18.0)
     parallel (1.22.1)
-    parser (3.1.2.0)
+    parser (3.2.1.0)
       ast (~> 2.4.1)
     rainbow (3.1.1)
     rake (13.0.6)
-    regexp_parser (2.5.0)
+    regexp_parser (2.7.0)
     rexml (3.2.5)
-    rubocop (1.30.0)
+    rubocop (1.48.0)
+      json (~> 2.3)
       parallel (~> 1.10)
-      parser (>= 3.1.0.0)
+      parser (>= 3.2.0.0)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.18.0, < 2.0)
+      rubocop-ast (>= 1.26.0, < 2.0)
       ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.18.0)
-      parser (>= 3.1.1.0)
-    rubocop-minitest (0.20.0)
-      rubocop (>= 0.90, < 2.0)
+      unicode-display_width (>= 2.4.0, < 3.0)
+    rubocop-ast (1.27.0)
+      parser (>= 3.2.1.0)
+    rubocop-minitest (0.29.0)
+      rubocop (>= 1.39, < 2.0)
     rubocop-rake (0.6.0)
       rubocop (~> 1.0)
-    ruby-progressbar (1.11.0)
-    unicode-display_width (2.1.0)
+    ruby-progressbar (1.13.0)
+    unicode-display_width (2.4.2)
 
 PLATFORMS
   x86_64-linux
 
 DEPENDENCIES
-  languages!
-  minitest (~> 5.0)
+  human_languages!
+  minitest (~> 5.18)
   rake (~> 13.0)
-  rubocop (~> 1.21)
-  rubocop-minitest (~> 0.20.0)
+  rubocop (~> 1.48)
+  rubocop-minitest (~> 0.29.0)
   rubocop-rake (~> 0.6.0)
 
 BUNDLED WITH

data/README.adoc

@@ -3,9 +3,9 @@ Benno Bielmeier
 :source-language: ruby
 
 image:https://api.reuse.software/badge/github.com/bbenno/languages[link="https://api.reuse.software/info/github.com/bbenno/languages", alt="REUSE status"]
-image:https://img.shields.io/github/v/tag/bbenno/languages[GitHub tag (latest SemVer)]
+image:https://badge.fury.io/rb/human_languages.svg["Gem Version", link="https://badge.fury.io/rb/human_languages"]
 
-image:https://img.shields.io/maintenance/yes/2022[Maintenance]
+image:https://img.shields.io/maintenance/yes/2023[Maintenance]
 image:https://github.com/bbenno/languages/actions/workflows/main.yml/badge.svg[link="https://github.com/bbenno/languages/actions/workflows/main.yml"]
 
 Simple, dependency-less gem providing all known human languagesfootnote:[This includes all individual languages already accounted for in ISO 639-2 as well as extinct, ancient, constructed, and historical languages.] defined in ISO 639-3
@@ -17,7 +17,7 @@ The ISO code set in link:data/[data/] is taken from the official ISO 639-3 regis
 Add this line to your application’s Gemfile:
 [source]
 ----
-gem 'languages'
+gem 'human_languages'
 ----
 
 And then execute:
@@ -27,7 +27,7 @@ $ bundle install
 
 Or install it yourself as:
 ....
-$ gem install languages
+$ gem install human_languages
 ....
 
 == Usage
@@ -65,7 +65,13 @@ Languages.search "^Germ"
 Languages.search /\AJapan/
 ----
 
-CAUTION: `Languages.search` is case-sensitive unless specified explicitly, e.g. using `/search_pattern/i`.
+[CAUTION]
+--
+Passing a string to `Languages.search` results in case-sensitive search.
+If case-insensitive search is intended, use ignorecase regexp like `/search_pattern/i` or pass optional `case_sensitive` parameter.
+[source]
+Languages.search('search_pattern', case_sensitive: false)
+--
 
 .Since ISO 639-3 categorizes the languages by scope and type, one can filter by them
 [source]
@@ -91,6 +97,7 @@ Languages.all.select { |l| %w[ancient historical].include?(l.type) }
 === Data Objects
 
 The `Language` objects have a simple read-only interface:
+
 [source]
 ----
 language = Language[:fr]
@@ -100,14 +107,74 @@ language.alpha2               # => :fr   (alias for #iso639_1)
 language.alpha3               # => :fra  (alias for #iso639_3)
 language.alpha3_bibliographic # => :fre  (alias for #iso_639_2b)
 language.alpha3_terminology   # => :fra  (alias for #iso_639_2t)
-language.type                 # => "living"
-language.scope                # => "individual"
+language.type                 # => :living
+language.scope                # => :individual
 
 language.extinct?             # => false
 language.living?              # => true
 language.individual_language? # => true
 ----
 
+Some languages of scope `individual` have a reference to their macrolanguage (scope `macrolanguage) that they belong to.
+More information on macrolanguages can be found https://iso639-3.sil.org/about/scope#Macrolanguages[here].
+
+[source]
+----
+language = Language[:wuu]
+language.individual_language? # => true
+
+macrolanguage = language.macrolanguage
+
+macrolanguage.alpha3        # => "zho"
+macrolanguage.name          # => "Chinese"
+macrolanguage.scope         # => :macrolanguage
+macrolanguage.macrolanguage # => nil
+----
+
+== Related Gems and Differences
+
+Why to build another gem for ISO 639?
+
+.Overview
+[%header,cols="2,1,2,2,3"]
+|===
+|Gem
+|ISO 639-1/-2
+|ISO 639-3
+|Translations
+|Data Storage
+
+|https://rubygems.org/gems/iso639[iso639]
+|✅
+|❌
+|French
+|Collection of Hashes
+
+|https://rubygems.org/gems/iso-639[iso-639]
+|✅
+|❌
+|French
+|Array of Arrays
+
+|https://rubygems.org/gems/iso-639-data[iso-639-data]
+|✅
+|(✅) only scope individual
+|French for ISO 639-2
+|Hash of Hashes
+
+|https://rubygems.org/gems/language_list[language_list]
+|✅
+|(✅) only scope individual
+|-
+|Array of Language-Objects
+
+|https://rubygems.org/gems/human_languages[human_languages]
+|✅
+|✅
+|-
+|Array of Language-Objects
+|===
+
 == Development
 
 After checking out the repo, run `bin/setup` to install dependencies.

data/data/iso-639-3-macrolanguages.tsv

@@ -0,0 +1,455 @@
+M_Id	I_Id	I_Status
+aka	fat	A
+aka	twi	A
+ara	aao	A
+ara	abh	A
+ara	abv	A
+ara	acm	A
+ara	acq	A
+ara	acw	A
+ara	acx	A
+ara	acy	A
+ara	adf	A
+ara	aeb	A
+ara	aec	A
+ara	afb	A
+ara	ajp	R
+ara	apc	A
+ara	apd	A
+ara	arb	A
+ara	arq	A
+ara	ars	A
+ara	ary	A
+ara	arz	A
+ara	auz	A
+ara	avl	A
+ara	ayh	A
+ara	ayl	A
+ara	ayn	A
+ara	ayp	A
+ara	bbz	R
+ara	pga	A
+ara	shu	A
+ara	ssh	A
+aym	ayc	A
+aym	ayr	A
+aze	azb	A
+aze	azj	A
+bal	bcc	A
+bal	bgn	A
+bal	bgp	A
+bik	bcl	A
+bik	bhk	R
+bik	bln	A
+bik	bto	A
+bik	cts	A
+bik	fbl	A
+bik	lbl	A
+bik	rbl	A
+bik	ubl	A
+bnc	ebk	A
+bnc	lbk	A
+bnc	obk	A
+bnc	rbk	A
+bnc	vbk	A
+bua	bxm	A
+bua	bxr	A
+bua	bxu	A
+chm	mhr	A
+chm	mrj	A
+cre	crj	A
+cre	crk	A
+cre	crl	A
+cre	crm	A
+cre	csw	A
+cre	cwd	A
+del	umu	A
+del	unm	A
+den	scs	A
+den	xsl	A
+din	dib	A
+din	dik	A
+din	dip	A
+din	diw	A
+din	dks	A
+doi	dgo	A
+doi	xnr	A
+est	ekk	A
+est	vro	A
+fas	pes	A
+fas	prs	A
+ful	ffm	A
+ful	fub	A
+ful	fuc	A
+ful	fue	A
+ful	fuf	A
+ful	fuh	A
+ful	fui	A
+ful	fuq	A
+ful	fuv	A
+gba	bdt	A
+gba	gbp	A
+gba	gbq	A
+gba	gmm	A
+gba	gso	A
+gba	gya	A
+gba	mdo	R
+gon	esg	A
+gon	ggo	R
+gon	gno	A
+gon	wsg	A
+grb	gbo	A
+grb	gec	A
+grb	grj	A
+grb	grv	A
+grb	gry	A
+grn	gnw	A
+grn	gug	A
+grn	gui	A
+grn	gun	A
+grn	nhd	A
+hai	hax	A
+hai	hdn	A
+hbs	bos	A
+hbs	cnr	A
+hbs	hrv	A
+hbs	srp	A
+hmn	blu	R
+hmn	cqd	A
+hmn	hea	A
+hmn	hma	A
+hmn	hmc	A
+hmn	hmd	A
+hmn	hme	A
+hmn	hmg	A
+hmn	hmh	A
+hmn	hmi	A
+hmn	hmj	A
+hmn	hml	A
+hmn	hmm	A
+hmn	hmp	A
+hmn	hmq	A
+hmn	hms	A
+hmn	hmw	A
+hmn	hmy	A
+hmn	hmz	A
+hmn	hnj	A
+hmn	hrm	A
+hmn	huj	A
+hmn	mmr	A
+hmn	muq	A
+hmn	mww	A
+hmn	sfm	A
+iku	ike	A
+iku	ikt	A
+ipk	esi	A
+ipk	esk	A
+jrb	ajt	R
+jrb	aju	A
+jrb	jye	A
+jrb	yhd	A
+jrb	yud	A
+kau	kby	A
+kau	knc	A
+kau	krt	A
+kln	enb	A
+kln	eyo	A
+kln	niq	A
+kln	oki	A
+kln	pko	A
+kln	sgc	A
+kln	spy	A
+kln	tec	A
+kln	tuy	A
+kok	gom	A
+kok	knn	A
+kom	koi	A
+kom	kpv	A
+kon	kng	A
+kon	kwy	A
+kon	ldi	A
+kpe	gkp	A
+kpe	xpe	A
+kur	ckb	A
+kur	kmr	A
+kur	sdh	A
+lah	hnd	A
+lah	hno	A
+lah	jat	A
+lah	phr	A
+lah	pmu	R
+lah	pnb	A
+lah	skr	A
+lah	xhe	A
+lav	ltg	A
+lav	lvs	A
+luy	bxk	A
+luy	ida	A
+luy	lkb	A
+luy	lko	A
+luy	lks	A
+luy	lri	A
+luy	lrm	A
+luy	lsm	A
+luy	lto	A
+luy	lts	A
+luy	lwg	A
+luy	nle	A
+luy	nyd	A
+luy	rag	A
+man	emk	A
+man	mku	A
+man	mlq	A
+man	mnk	A
+man	msc	A
+man	mwk	A
+man	myq	R
+mlg	bhr	A
+mlg	bjq	R
+mlg	bmm	A
+mlg	bzc	A
+mlg	msh	A
+mlg	plt	A
+mlg	skg	A
+mlg	tdx	A
+mlg	tkg	A
+mlg	txy	A
+mlg	xmv	A
+mlg	xmw	A
+mon	khk	A
+mon	mvf	A
+msa	bjn	A
+msa	btj	A
+msa	bve	A
+msa	bvu	A
+msa	coa	A
+msa	dup	A
+msa	hji	A
+msa	ind	A
+msa	jak	A
+msa	jax	A
+msa	kvb	A
+msa	kvr	A
+msa	kxd	A
+msa	lce	A
+msa	lcf	A
+msa	liw	A
+msa	max	A
+msa	meo	A
+msa	mfa	A
+msa	mfb	A
+msa	min	A
+msa	mly	R
+msa	mqg	A
+msa	msi	A
+msa	mui	A
+msa	orn	A
+msa	ors	A
+msa	pel	A
+msa	pse	A
+msa	tmw	A
+msa	urk	A
+msa	vkk	A
+msa	vkt	A
+msa	xmm	A
+msa	zlm	A
+msa	zmi	A
+msa	zsm	A
+mwr	dhd	A
+mwr	mtr	A
+mwr	mve	A
+mwr	rwr	A
+mwr	swv	A
+mwr	wry	A
+nep	dty	A
+nep	npi	A
+nor	nno	A
+nor	nob	A
+oji	ciw	A
+oji	ojb	A
+oji	ojc	A
+oji	ojg	A
+oji	ojs	A
+oji	ojw	A
+oji	otw	A
+ori	ory	A
+ori	spv	A
+orm	gax	A
+orm	gaz	A
+orm	hae	A
+orm	orc	A
+pus	pbt	A
+pus	pbu	A
+pus	pst	A
+que	cqu	R
+que	qub	A
+que	qud	A
+que	quf	A
+que	qug	A
+que	quh	A
+que	quk	A
+que	qul	A
+que	qup	A
+que	qur	A
+que	qus	A
+que	quw	A
+que	qux	A
+que	quy	A
+que	quz	A
+que	qva	A
+que	qvc	A
+que	qve	A
+que	qvh	A
+que	qvi	A
+que	qvj	A
+que	qvl	A
+que	qvm	A
+que	qvn	A
+que	qvo	A
+que	qvp	A
+que	qvs	A
+que	qvw	A
+que	qvz	A
+que	qwa	A
+que	qwc	A
+que	qwh	A
+que	qws	A
+que	qxa	A
+que	qxc	A
+que	qxh	A
+que	qxl	A
+que	qxn	A
+que	qxo	A
+que	qxp	A
+que	qxr	A
+que	qxt	A
+que	qxu	A
+que	qxw	A
+raj	bgq	A
+raj	gda	A
+raj	gju	A
+raj	hoj	A
+raj	mup	A
+raj	wbr	A
+rom	rmc	A
+rom	rmf	A
+rom	rml	A
+rom	rmn	A
+rom	rmo	A
+rom	rmw	A
+rom	rmy	A
+sqi	aae	A
+sqi	aat	A
+sqi	aln	A
+sqi	als	A
+srd	sdc	A
+srd	sdn	A
+srd	src	A
+srd	sro	A
+swa	swc	A
+swa	swh	A
+syr	aii	A
+syr	cld	A
+tmh	taq	A
+tmh	thv	A
+tmh	thz	A
+tmh	ttq	A
+uzb	uzn	A
+uzb	uzs	A
+yid	ydd	A
+yid	yih	A
+zap	zaa	A
+zap	zab	A
+zap	zac	A
+zap	zad	A
+zap	zae	A
+zap	zaf	A
+zap	zai	A
+zap	zam	A
+zap	zao	A
+zap	zaq	A
+zap	zar	A
+zap	zas	A
+zap	zat	A
+zap	zav	A
+zap	zaw	A
+zap	zax	A
+zap	zca	A
+zap	zcd	A
+zap	zoo	A
+zap	zpa	A
+zap	zpb	A
+zap	zpc	A
+zap	zpd	A
+zap	zpe	A
+zap	zpf	A
+zap	zpg	A
+zap	zph	A
+zap	zpi	A
+zap	zpj	A
+zap	zpk	A
+zap	zpl	A
+zap	zpm	A
+zap	zpn	A
+zap	zpo	A
+zap	zpp	A
+zap	zpq	A
+zap	zpr	A
+zap	zps	A
+zap	zpt	A
+zap	zpu	A
+zap	zpv	A
+zap	zpw	A
+zap	zpx	A
+zap	zpy	A
+zap	zpz	A
+zap	zsr	A
+zap	ztc	R
+zap	zte	A
+zap	ztg	A
+zap	ztl	A
+zap	ztm	A
+zap	ztn	A
+zap	ztp	A
+zap	ztq	A
+zap	zts	A
+zap	ztt	A
+zap	ztu	A
+zap	ztx	A
+zap	zty	A
+zha	ccx	R
+zha	ccy	R
+zha	zch	A
+zha	zeh	A
+zha	zgb	A
+zha	zgm	A
+zha	zgn	A
+zha	zhd	A
+zha	zhn	A
+zha	zlj	A
+zha	zln	A
+zha	zlq	A
+zha	zqe	A
+zha	zyb	A
+zha	zyg	A
+zha	zyj	A
+zha	zyn	A
+zha	zzj	A
+zho	cdo	A
+zho	cjy	A
+zho	cmn	A
+zho	cnp	A
+zho	cpx	A
+zho	csp	A
+zho	czh	A
+zho	czo	A
+zho	gan	A
+zho	hak	A
+zho	hsn	A
+zho	lzh	A
+zho	mnp	A
+zho	nan	A
+zho	wuu	A
+zho	yue	A
+zza	diq	A
+zza	kiu	A

data/data/iso-639-3.tsv

@@ -186,7 +186,6 @@ aja				I	L	Aja (South Sudan)
 ajg				I	L	Aja (Benin)	
 aji				I	L	Ajië	
 ajn				I	L	Andajin	
-ajp				I	L	South Levantine Arabic	
 ajs				I	L	Algerian Jewish Sign Language	
 aju				I	L	Judeo-Moroccan Arabic	
 ajw				I	E	Ajawa	
@@ -310,7 +309,7 @@ aou				I	L	A'ou
 aox				I	L	Atorada	
 aoz				I	L	Uab Meto	
 apb				I	L	Sa'a	
-apc				I	L	North Levantine Arabic	
+apc				I	L	Levantine Arabic	
 apd				I	L	Sudanese Arabic	
 ape				I	L	Bukiyip	
 apf				I	L	Pahanan Agta	
@@ -1459,6 +1458,7 @@ cwd				I	L	Woods Cree
 cwe				I	L	Kwere	
 cwg				I	L	Chewong	
 cwt				I	L	Kuwaataay	
+cxh				I	L	Cha'ari	
 cya				I	L	Nopala Chatino	
 cyb				I	E	Cayubaba	
 cym	wel	cym	cy	I	L	Welsh	
@@ -1693,6 +1693,7 @@ dsb	dsb	dsb		I	L	Lower Sorbian
 dse				I	L	Dutch Sign Language	
 dsh				I	L	Daasanach	
 dsi				I	L	Disa	
+dsk				I	L	Dokshi	
 dsl				I	L	Danish Sign Language	
 dsn				I	E	Dusner	
 dso				I	L	Desiya	
@@ -1753,9 +1754,11 @@ dyi				I	L	Djimini Senoufo
 dym				I	L	Yanda Dom Dogon	
 dyn				I	L	Dyangadi	
 dyo				I	L	Jola-Fonyi	
+dyr				I	L	Dyarim	
 dyu	dyu	dyu		I	L	Dyula	
 dyy				I	L	Djabugay	
 dza				I	L	Tunzu	
+dzd				I	L	Daza	
 dze				I	E	Djiwarli	
 dzg				I	L	Dazaga	
 dzl				I	L	Dzalakha	
@@ -1877,6 +1880,7 @@ ett				I	A	Etruscan
 etu				I	L	Ejagham	
 etx				I	L	Eten	
 etz				I	L	Semimi	
+eud				I	L	Eudeve	
 eus	baq	eus	eu	I	L	Basque	
 eve				I	L	Even	
 evh				I	L	Uvbie	
@@ -2576,6 +2580,7 @@ ijj				I	L	Ede Ije
 ijn				I	L	Kalabari	
 ijs				I	L	Southeast Ijo	
 ike				I	L	Eastern Canadian Inuktitut	
+ikh				I	L	Ikhin-Arokho	
 iki				I	L	Iko	
 ikk				I	L	Ika	
 ikl				I	L	Ikulu	
@@ -2686,6 +2691,7 @@ iya				I	L	Iyayu
 iyo				I	L	Mesaka	
 iyx				I	L	Yaka (Congo)	
 izh				I	L	Ingrian	
+izm				I	L	Kizamani	
 izr				I	L	Izere	
 izz				I	L	Izii	
 jaa				I	L	Jamamadí	
@@ -2804,7 +2810,7 @@ jru				I	L	Japrería
 jsl				I	L	Japanese Sign Language	
 jua				I	L	Júma	
 jub				I	L	Wannu	
-juc				I	E	Jurchen	
+juc				I	H	Jurchen	
 jud				I	L	Worodougou	
 juh				I	L	Hõne	
 jui				I	E	Ngadjuri	
@@ -2985,7 +2991,6 @@ kgi				I	L	Selangor Sign Language
 kgj				I	L	Gamale Kham	
 kgk				I	L	Kaiwá	
 kgl				I	E	Kunggari	
-kgm				I	E	Karipúna	
 kgn				I	L	Karingani	
 kgo				I	L	Krongo	
 kgp				I	L	Kaingang	
@@ -3262,7 +3267,7 @@ krj				I	L	Kinaray-A
 krk				I	E	Kerek	
 krl	krl	krl		I	L	Karelian	
 krn				I	L	Sapo	
-krp				I	L	Korop	
+krp				I	L	Durop	
 krr				I	L	Krung	
 krs				I	L	Gbaya (Sudan)	
 krt				I	L	Tumari Kanuri	
@@ -3272,7 +3277,6 @@ krw				I	L	Western Krahn
 krx				I	L	Karon	
 kry				I	L	Kryts	
 krz				I	L	Sota Kanum	
-ksa				I	L	Shuwa-Zamani	
 ksb				I	L	Shambala	
 ksc				I	L	Southern Kalinga	
 ksd				I	L	Kuanua	
@@ -3476,7 +3480,7 @@ lac				I	L	Lacandon
 lad	lad	lad		I	L	Ladino	
 lae				I	L	Pattani	
 laf				I	L	Lafofa	
-lag				I	L	Langi	
+lag				I	L	Rangi	
 lah	lah	lah		M	L	Lahnda	
 lai				I	L	Lambya	
 laj				I	L	Lango (Uganda)	
@@ -3580,6 +3584,7 @@ lgn				I	L	T'apo
 lgo				I	L	Lango (South Sudan)	
 lgq				I	L	Logba	
 lgr				I	L	Lengo	
+lgs				I	L	Guinea-Bissau Sign Language	
 lgt				I	L	Pahi	
 lgu				I	L	Longgu	
 lgz				I	L	Ligenza	
@@ -3703,7 +3708,7 @@ loc				I	L	Inonhan
 loe				I	L	Saluan	
 lof				I	L	Logol	
 log				I	L	Logo	
-loh				I	L	Narim	
+loh				I	L	Laarim	
 loi				I	L	Loma (Côte d'Ivoire)	
 loj				I	L	Lou	
 lok				I	L	Loko	
@@ -3796,6 +3801,7 @@ luz				I	L	Southern Luri
 lva				I	L	Maku'a	
 lvi				I	L	Lavi	
 lvk				I	L	Lavukaleve	
+lvl				I	L	Lwel	
 lvs				I	L	Standard Latvian	
 lvu				I	L	Levuka	
 lwa				I	L	Lwalu	
@@ -4766,7 +4772,6 @@ noi				I	L	Noiri
 noj				I	L	Nonuya	
 nok				I	E	Nooksack	
 nol				I	E	Nomlaki	
-nom				I	E	Nocamán	
 non	non	non		I	H	Old Norse	
 nop				I	L	Numanggang	
 noq				I	L	Ngongo	
@@ -4940,6 +4945,7 @@ nzd				I	L	Nzadi
 nzi	nzi	nzi		I	L	Nzima	
 nzk				I	L	Nzakara	
 nzm				I	L	Zeme Naga	
+nzr				I	L	Dir-Nyamzak-Mbarimi	
 nzs				I	L	New Zealand Sign Language	
 nzu				I	L	Teke-Nzikou	
 nzy				I	L	Nzakambay	
@@ -5276,7 +5282,6 @@ ple				I	L	Palu'e
 plg				I	L	Pilagá	
 plh				I	L	Paulohi	
 pli	pli	pli	pi	I	A	Pali	
-plj				I	L	Polci	
 plk				I	L	Kohistani Shina	
 pll				I	L	Shwe Palaung	
 pln				I	L	Palenquero	
@@ -5298,7 +5303,6 @@ pmf				I	L	Pamona
 pmh				I	H	Māhārāṣṭri Prākrit	
 pmi				I	L	Northern Pumi	
 pmj				I	L	Southern Pumi	
-pmk				I	E	Pamlico	
 pml				I	E	Lingua Franca	
 pmm				I	L	Pomo	
 pmn				I	L	Pam	
@@ -5382,7 +5386,6 @@ prl				I	L	Peruvian Sign Language
 prm				I	L	Kibiri	
 prn				I	L	Prasuni	
 pro	pro	pro		I	H	Old Provençal (to 1500)	
-prp				I	L	Parsi	
 prq				I	L	Ashéninka Perené	
 prr				I	E	Puri	
 prs				I	L	Dari	
@@ -5460,6 +5463,7 @@ pys				I	L	Paraguayan Sign Language
 pyu				I	L	Puyuma	
 pyx				I	A	Pyu (Myanmar)	
 pyy				I	L	Pyen	
+pze				I	L	Pesse	
 pzh				I	L	Pazeh	
 pzn				I	L	Jejara Naga	
 qua				I	L	Quapaw	
@@ -5649,6 +5653,7 @@ rsk				I	L	Ruthenian
 rsl				I	L	Russian Sign Language	
 rsm				I	L	Miriwoong Sign Language	
 rsn				I	L	Rwandan Sign Language	
+rsw				I	L	Rishiwa	
 rtc				I	L	Rungtu Chin	
 rth				I	L	Ratahan	
 rtm				I	L	Rotuman	
@@ -5920,7 +5925,6 @@ sll				I	L	Salt-Yui
 slm				I	L	Pangutaran Sama	
 sln				I	E	Salinan	
 slp				I	L	Lamaholot	
-slq				I	E	Salchuq	
 slr				I	L	Salar	
 sls				I	L	Singapore Sign Language	
 slt				I	L	Sila	
@@ -6189,7 +6193,6 @@ syy				I	L	Al-Sayyid Bedouin Sign Language
 sza				I	L	Semelai	
 szb				I	L	Ngalum	
 szc				I	L	Semaq Beri	
-szd				I	E	Seru	
 sze				I	L	Seze	
 szg				I	L	Sengele	
 szl				I	L	Silesian	
@@ -6453,7 +6456,6 @@ tmg				I	E	Ternateño
 tmh	tmh	tmh		M	L	Tamashek	
 tmi				I	L	Tutuba	
 tmj				I	L	Samarokena	
-tmk				I	L	Northwestern Tamang	
 tml				I	L	Tamnim Citak	
 tmm				I	L	Tai Thanh	
 tmn				I	L	Taman (Indonesia)	
@@ -6531,7 +6533,6 @@ tpr				I	L	Tuparí
 tpt				I	L	Tlachichilco Tepehua	
 tpu				I	L	Tampuan	
 tpv				I	L	Tanapag	
-tpw				I	E	Tupí	
 tpx				I	L	Acatepec Me'phaa	
 tpy				I	L	Trumai	
 tpz				I	L	Tinputz	
@@ -6647,6 +6648,7 @@ tuz				I	L	Turka
 tva				I	L	Vaghua	
 tvd				I	L	Tsuvadi	
 tve				I	L	Te'un	
+tvi				I	L	Tulai	
 tvk				I	L	Southeast Ambrym	
 tvl	tvl	tvl		I	L	Tuvalu	
 tvm				I	L	Tela-Masbuar	
@@ -6779,6 +6781,7 @@ ulm				I	L	Ulumanda'
 uln				I	L	Unserdeutsch	
 ulu				I	L	Uma' Lung	
 ulw				I	L	Ulwa	
+uly				I	L	Buli	
 uma				I	L	Umatilla	
 umb	umb	umb		I	L	Umbundu	
 umc				I	A	Marrucinian	
@@ -6893,6 +6896,7 @@ vin				I	L	Vinza
 vis				I	L	Vishavan	
 vit				I	L	Viti	
 viv				I	L	Iduna	
+vjk				I	L	Bajjika	
 vka				I	E	Kariyarra	
 vkj				I	L	Kujarge	
 vkk				I	L	Kaur	
@@ -7083,7 +7087,7 @@ wms				I	L	Wambon
 wmt				I	L	Walmajarri	
 wmw				I	L	Mwani	
 wmx				I	L	Womo	
-wnb				I	L	Wanambre	
+wnb				I	L	Mokati	
 wnc				I	L	Wantoat	
 wnd				I	E	Wandarang	
 wne				I	L	Waneci	
@@ -7141,6 +7145,7 @@ wsr				I	L	Owenia
 wss				I	L	Wasa	
 wsu				I	E	Wasu	
 wsv				I	E	Wotapuri-Katarqalai	
+wtb				I	L	Matambwe	
 wtf				I	L	Watiwa	
 wth				I	E	Wathawurrung	
 wti				I	L	Berta	
@@ -7418,7 +7423,6 @@ xso				I	E	Solano
 xsp				I	L	Silopi	
 xsq				I	L	Makhuwa-Saka	
 xsr				I	L	Sherpa	
-xss				I	E	Assan	
 xsu				I	L	Sanumá	
 xsv				I	E	Sudovian	
 xsy				I	L	Saisiyat	
@@ -7532,6 +7536,7 @@ ych				I	L	Chesu
 ycl				I	L	Lolopo	
 ycn				I	L	Yucuna	
 ycp				I	L	Chepya	
+ycr				I	L	Yilan Creole	
 yda				I	E	Yanda	
 ydd				I	L	Eastern Yiddish	
 yde				I	L	Yangum Dey	
@@ -7584,6 +7589,7 @@ yix				I	L	Axi Yi
 yiz				I	L	Azhe	
 yka				I	L	Yakan	
 ykg				I	L	Northern Yukaghir	
+ykh				I	L	Khamnigan Mongol	
 yki				I	L	Yoke	
 ykk				I	L	Yakaikeke	
 ykl				I	L	Khlula	
@@ -7758,12 +7764,13 @@ zbt				I	L	Batui
 zbu				I	L	Bu (Bauchi State)	
 zbw				I	L	West Berawan	
 zca				I	L	Coatecas Altas Zapotec	
-zcd	zcd	zcd		I	L	Las Delicias Zapotec	
+zcd				I	L	Las Delicias Zapotec	
 zch				I	L	Central Hongshuihe Zhuang	
 zdj				I	L	Ngazidja Comorian	
 zea				I	L	Zeeuws	
 zeg				I	L	Zenag	
 zeh				I	L	Eastern Hongshuihe Zhuang	
+zem				I	L	Zeem	
 zen	zen	zen		I	L	Zenaga	
 zga				I	L	Kinga	
 zgb				I	L	Guibei Zhuang	
@@ -7787,7 +7794,6 @@ zin				I	L	Zinza
 ziw				I	L	Zigula	
 ziz				I	L	Zizilivakan	
 zka				I	L	Kaimbulawa	
-zkb				I	E	Koibal	
 zkd				I	L	Kadu	
 zkg				I	A	Koguryo	
 zkh				I	H	Khorezmian	
@@ -7805,6 +7811,7 @@ zlj				I	L	Liujiang Zhuang
 zlm				I	L	Malay (individual language)	
 zln				I	L	Lianshan Zhuang	
 zlq				I	L	Liuqian Zhuang	
+zlu				I	L	Zul	
 zma				I	L	Manda (Australia)	
 zmb				I	L	Zimba	
 zmc				I	E	Margany	
@@ -7894,7 +7901,6 @@ ztt				I	L	Tejalapan Zapotec
 ztu				I	L	Güilá Zapotec	
 ztx				I	L	Zaachila Zapotec	
 zty				I	L	Yatee Zapotec	
-zua				I	L	Zeem	
 zuh				I	L	Tokano	
 zul	zul	zul	zu	I	L	Zulu	
 zum				I	L	Kumzari	

data/human_languages.gemspec

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+require_relative 'lib/languages/version'
+
+Gem::Specification.new do |spec|
+  spec.name = 'human_languages'
+  spec.version = Languages::VERSION
+  spec.authors = ['Benno Bielmeier']
+  spec.email = ['git@bbenno.com']
+
+  spec.summary = 'ISO 639-3 languages'
+  spec.description = 'ISO 639-3 is a set of codes that defines three-letter identifiers for all known human languages.'
+  spec.homepage = 'https://github.com/bbenno/languages'
+  spec.license = 'MIT'
+  spec.required_ruby_version = '>= 2.7.0'
+
+  # spec.metadata["allowed_push_host"] = "TODO: Set to your gem server 'https://example.com'"
+
+  spec.metadata['homepage_uri'] = spec.homepage
+  spec.metadata['source_code_uri'] = spec.homepage
+  spec.metadata['changelog_uri'] = "#{spec.metadata['source_code_uri']}/blob/HEAD/CHANGELOG.md"
+  spec.metadata['rubygems_mfa_required'] = 'true'
+  spec.metadata['github_repo'] = 'git@github.com:bbenno/languages.git'
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (f == __FILE__) || f.match(%r{\A(?:(?:bin|test|spec|features)/|\.(?:git|travis|circleci)|appveyor)})
+    end
+  end
+  spec.bindir = 'exe'
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  # Uncomment to register a new dependency of your gem
+  # spec.add_dependency "example-gem", "~> 1.0"
+
+  # For more information and examples about making a new gem, check out our
+  # guide at: https://bundler.io/guides/creating_gem.html
+end

data/lib/languages/language.rb

@@ -5,15 +5,15 @@ module Languages
   class Language
     include Comparable
 
-    attr_reader :iso639_1, :iso639_2b, :iso639_2t, :iso639_3, :scope, :type, :name # , :comment
+    attr_reader :iso639_1, :iso639_2b, :iso639_2t, :iso639_3, :scope, :type, :name, :macrolanguage # , :comment
 
-    def initialize(csv_attributes) # rubocop:disable Metrics/AbcSize
+    def initialize(csv_attributes) # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity
       @iso639_3 = csv_attributes.fetch(:id).to_sym
       @iso639_2b = csv_attributes.fetch(:part2b)&.to_sym
       @iso639_2t = csv_attributes.fetch(:part2t)&.to_sym
       @iso639_1 = csv_attributes.fetch(:part1)&.to_sym
-      @scope = SCOPES.detect { |s| s.chr.upcase == csv_attributes.fetch(:scope) }
-      @type = TYPES.detect { |t| t.chr.upcase == csv_attributes.fetch(:language_type) }
+      @scope = SCOPES.detect { |s| s.chr.upcase == csv_attributes.fetch(:scope) }&.to_sym
+      @type = TYPES.detect { |t| t.chr.upcase == csv_attributes.fetch(:language_type) }&.to_sym
       @name = csv_attributes.fetch(:ref_name)
       # @comment = csv_attributes.fetch(:comment)
     end
@@ -32,7 +32,7 @@ module Languages
 
     TYPES.each do |type|
       define_method "#{type}?" do
-        self.type == type
+        self.type == type.to_sym
       end
     end
 
@@ -41,7 +41,7 @@ module Languages
       method_name = scope.end_with?('language') ? scope : "#{scope}_language"
 
       define_method "#{method_name}?" do
-        self.scope == scope
+        self.scope == scope.to_sym
       end
     end
 

data/lib/languages/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Languages
-  VERSION = '0.5.0'
+  VERSION = '0.7.0'
 end

data/lib/languages.rb

@@ -8,15 +8,10 @@ require_relative 'languages/language'
 
 # Provides living, extinct, ancient, historic, and constructed languages, specified in ISO 639-3
 module Languages
-  @@data = CSV.read(File.join(File.dirname(__FILE__), '../data/iso-639-3.tsv'), headers: true, col_sep: "\t") # rubocop:disable Style/ClassVars
-              .map { |row| row.to_h.transform_keys { |k| k.downcase.to_sym } }
-              .map { |h| Language.new(h) }
-              .freeze
-
   class << self
     TYPES.each do |type|
       define_method type do
-        @@data.select { |l| l.public_send("#{type}?") }
+        all.select { |l| l.public_send("#{type}?") }
       end
     end
 
@@ -25,7 +20,7 @@ module Languages
       scope = "#{scope}_language" unless scope.end_with? 'language'
 
       define_method "#{scope}s" do
-        @@data.select { |l| l.public_send("#{scope}?") }
+        all.select { |l| l.public_send("#{scope}?") }
       end
     end
 
@@ -38,25 +33,26 @@ module Languages
       end
     end
 
-    def search(pattern)
-      @@data.select { |l| l.name.match? pattern }
+    def search(pattern, case_sensitive: true)
+      pattern = Regexp.new(pattern, Regexp::IGNORECASE).freeze unless case_sensitive
+      all.select { |l| l.name.match? pattern }
     end
 
     # Returns all human known languages, specified in ISO 639-3
     def all
-      @@data
+      data.values
     end
 
     def names
-      @@data.map(&:name)
+      all.map(&:name)
     end
 
     def alpha2_codes
-      @@data.map(&:alpha2).compact
+      all.map(&:alpha2).compact
     end
 
     def alpha3_codes
-      @@data.map(&:alpha3)
+      all.map(&:alpha3)
     end
 
     private
@@ -65,21 +61,40 @@ module Languages
     # @param [Symbol] key ISO 639-1 identifier
     # @return [Language,NilClass] language with associated with the identifier; otherwise +nil+
     def get_by_alpha2(key)
-      @@data.detect { |l| l.iso639_1 == key }
+      all.detect { |l| l.iso639_1 == key }
     end
 
     # Returns language associated with ISO 639-2 or ISO 639-3 identifier
     # @param [Symbol] key ISO 639-2 or ISO 639-3 identifier
     # @return [Language,NilClass] language with associated with the identifier; otherwise +nil+
     def get_by_alpha3(key)
-      @@data.detect { |l| l.iso639_3 == key || l.iso639_2b == key || l.iso639_2t == key }
+      data[key] || all.detect { |l| l.iso639_2b == key || l.iso639_2t == key }
     end
 
     # Returns language associated with ISO 639-3 reference name
     # @param [String] name reference name (english)
     # @return [Language,NilClass] language with associated with the name; otherwise +nil+
     def get_by_name(name)
-      @@data.detect { |l| l.name.downcase == name.downcase }
+      all.detect { |l| l.name.downcase == name.downcase }
+    end
+
+    private # rubocop:disable Lint/UselessAccessModifier
+
+    def data
+      @@data
+    end
+
+    def load_tsv_data(filename)
+      CSV.read(File.join(File.dirname(__FILE__), "../data/#{filename}"), headers: true, col_sep: "\t")
     end
   end
+
+  @@data = load_tsv_data('iso-639-3.tsv') # rubocop:disable Style/ClassVars
+           .map { |row| row.to_h.transform_keys { |k| k.downcase.to_sym } }
+           .each_with_object({}) { |l, h| h[l[:id].to_sym] = Language.new(l) }
+           .freeze
+
+  load_tsv_data('iso-639-3-macrolanguages.tsv')
+    # Ignore deprecated mappings (i.e. row[2] = 'R')
+    .each { |row| data[row[1].to_sym].instance_variable_set(:@macrolanguage, data[row[0].to_sym]) if row[2] == 'A' }
 end

data/sig/languages.rbs

@@ -8,7 +8,7 @@ module Languages
   @@data: Array[Language]
 
   def self?.[]: (String | Symbol) -> Language?
-  def self?.search: (String|Regexp) -> Array[Language]
+  def self?.search: (String|Regexp pattern, ?bool case_sensitive) -> Array[Language]
 
   def self?.all: () -> Array[Language]
   def self?.names: () -> Array[String]
@@ -34,6 +34,7 @@ module Languages
     attr_reader scope: String
     attr_reader type: String
     attr_reader name: String
+    attr_reader macrolanguage: Language?
 
     alias iso639_2 iso639_2t
     alias iso639_5 iso639_2

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: human_languages
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.7.0
 platform: ruby
 authors:
 - Benno Bielmeier
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-06-06 00:00:00.000000000 Z
+date: 2023-03-08 00:00:00.000000000 Z
 dependencies: []
 description: ISO 639-3 is a set of codes that defines three-letter identifiers for
   all known human languages.
@@ -27,7 +27,9 @@ files:
 - LICENSES/MIT.txt
 - README.adoc
 - Rakefile
+- data/iso-639-3-macrolanguages.tsv
 - data/iso-639-3.tsv
+- human_languages.gemspec
 - lib/languages.rb
 - lib/languages/constants.rb
 - lib/languages/language.rb
@@ -41,6 +43,7 @@ metadata:
   source_code_uri: https://github.com/bbenno/languages
   changelog_uri: https://github.com/bbenno/languages/blob/HEAD/CHANGELOG.md
   rubygems_mfa_required: 'true'
+  github_repo: git@github.com:bbenno/languages.git
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -56,7 +59,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.4.7
 signing_key:
 specification_version: 4
 summary: ISO 639-3 languages