interscript 0.1.3 → 0.1.9

data/maps/un-asm-Beng-Latn-1972.yaml

@@ -0,0 +1,223 @@
+---
+authority_id: un
+id: 1972
+language: iso-639-2:ben
+source_script: Beng
+destination_script: Latn
+name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Assamese Romanization, Version 4.0
+url: https://www.eki.ee/wgrs/rom1_as.htm
+creation_date: 1972
+confirmation_date: 2016
+description: |
+  The United Nations recommended system was approved in 1972 (II/11) and amended in 1977 (III/12),
+  based on a report prepared by D. N. Sharma. The tables and their corrections were published in
+  volume II of the conference reports.
+
+  There is no evidence of the use of the system either in India or in international cartographic products.
+
+  Assamese (Asamīyā) uses an alphasyllabic script whereby each character represents a syllable rather
+  than one sound. Vowels and diphthongs are marked in two ways: as independent characters (used syllable-initially)
+  and in an abbreviated form, to denote vowels after consonants. The romanization table is unambiguous but the user
+  would have to recognize many ligatures not given in the original table. The system is mostly reversible but there
+  exist some ambiguities in the romanization of vowels (independent vs. abbreviated characters) and consonants
+  (ligatures vs. character sequences).
+
+  References
+
+  Second United Nations Conference on the Standardization of Geographical Names.
+  London, 10–31 May 1972. Vol. II. Technical papers. United Nations. New York 1974, pp. 141–142.
+
+  Third United Nations Conference on the Standardization of Geographical Names. Athens,
+  17 August – 7 September 1977. Vol. II, Technical papers, pp. 393 etc.
+
+notes:
+   - |
+     ু Exceptions: গু gu; রু ru; শু shu; হু hu; ন্তু ntu; স্তু stu.
+   - |
+     ূ Exceptions: রূ rū.
+   - |
+     ৃ Exceptions: হৃ hṛ.
+   - |
+     ্‌  Pronunciation without a vowel; special form: ৎ t.
+   - |
+     Dotted variants of the characters: ড় ṙa; ঢ় ṙha; য় ya.
+
+tests:
+  - source: "অসমীয়া কবিতা"
+    expected: "asamīyā kabitā"
+  - source: "কবিৰ আজি জন্মদিন"
+    expected: "kabira āji janmadina"
+  - source: "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড"
+    expected: "beruṭata emāhara pāchhate punara bhayaṁkara agnikāṇḍa"
+  - source: "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ"
+    expected: "bhaṅāra biruddhe āvedana dākhila kaṁganāra"
+  - source: "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি"
+    expected: "āpuni paṙhi bhāla pāba parā bātari"
+  - source: "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক"
+    expected: "shrīrāmapurata garubharti ṭrāka jabda, dujanaka āṭaka"
+  - source: "কেনে আছে প্ৰাক্তন"
+    expected: "kene āchhe prāktana"
+  - source: "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ"
+    expected: "kamumbāira meyarara dehata kobhiḍa pajiṭibha"
+  - source: "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা"
+    expected: "ṭuiṭāraj̱oge khoda sadarī kare ei kathā"
+  - source: "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়"
+    expected: "lakhimapura jilāra nārāyaṇapurara barapathārata āji prashānti dhāma nāmere ekhana bṛddhāshramara shubhārambha karā haya"
+
+map:
+  rules:
+    - pattern: ([ক]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'k'
+    - pattern: ([খ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'kh'
+    - pattern: ([গ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'g'
+    - pattern: ([ঘ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'gh'
+    - pattern: ([ঙ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṅ'
+    - pattern: ([চ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ch'
+    - pattern: ([ছ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'chh'
+    - pattern: ([জ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'j'
+    - pattern: ([ঝ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'jh'
+    - pattern: ([ঞ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ñ'
+    - pattern: ([ট]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṭ'
+    - pattern: ([ঠ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṭh'
+    - pattern: ([ড]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ḍ'
+    - pattern: ([ঢ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ḍh'
+    - pattern: ([ণ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṇ'
+    - pattern: ([ত]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   't'
+    - pattern: ([থ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'th'
+    - pattern: ([দ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'd'
+    - pattern: ([ধ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'dh'
+    - pattern: ([ন]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'n'
+    - pattern: ([প]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'p'
+    - pattern: ([ফ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ph'
+    - pattern: ([ব]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'b'
+    - pattern: ([ভ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'bh'
+    - pattern: ([ম]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'm'
+    - pattern: ([য]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'j̱'
+    - pattern: ([ৰ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'r'
+    - pattern: ([ল]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'l'
+    - pattern: ([ৱ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'v'
+    - pattern: ([শ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'sh'
+    - pattern: ([ষ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṣh'
+    - pattern: ([স]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   's'
+    - pattern: ([হ]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'h'
+    - pattern: ([ড়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṙ'
+    - pattern: ([ঢ়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṙh'
+    - pattern: ([য়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'y'
+    - pattern: ([ড়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṙ'
+    - pattern: ([ঢ়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'ṙh'
+    - pattern: ([য়]=?)(?=[\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd])
+      result:   'y'
+
+  characters:
+
+    # I. Independent vowel characters
+    'অ': 'a'
+    'আ': 'ā'
+    'ই': 'i'
+    'ঈ': 'ī'
+    'উ': 'u'
+    'ঊ': 'ū'
+    'ঋ': 'ṛ'
+    'এ': 'e'
+    'ঐ': 'ai'
+    'ও': 'o'
+    'ঔ': 'au'
+
+    # II. Abbreviated vowel characters
+    '\u09be': 'ā'
+    '\u09bf': 'i'
+    '\u09c0': 'ī'
+    '\u09c1': 'u'
+    '\u09c2': 'ū'
+    '\u09c3': 'ṛ'
+    '\u09c7': 'e'
+    '\u09c8': 'ai'
+    '\u09cb': 'o'
+    '\u09cc': 'au'
+
+    # III. Other symbols
+    '\u0982':	'ṁ'
+    '\u0981':	'm̐'
+    '\u0983':	'ḥ'
+    '\u09cd': ''
+
+    # IV. Consonant characters
+    'ক': 'ka'
+    'খ': 'kha'
+    'গ': 'ga'
+    'ঘ': 'gha'
+    'ঙ': 'ṅa'
+    'চ': 'cha'
+    'ছ': 'chha'
+    'জ': 'ja'
+    'ঝ': 'jha'
+    'ঞ': 'ña'
+    'ট': 'ṭa'
+    'ঠ': 'ṭha'
+    'ড': 'ḍa'
+    'ঢ': 'ḍha'
+    'ণ': 'ṇa'
+    'ত': 'ta'
+    'থ': 'tha'
+    'দ': 'da'
+    'ধ': 'dha'
+    'ন': 'na'
+    'প': 'pa'
+    'ফ': 'pha'
+    'ব': 'ba'
+    'ভ': 'bha'
+    'ম': 'ma'
+    'য': 'j̱a'
+    'ৰ': 'ra'
+    'ল': 'la'
+    'ৱ': 'va'
+    'শ': 'sha'
+    'ষ': 'ṣha'
+    'স': 'sa'
+    'হ': 'ha'
+    'ৎ': 't'
+
+    # Note V Dotted variants
+    'ড়': 'ṙa'
+    'ঢ়': 'ṙha'
+    'য়': 'ya'
+    'য়': 'ya'
+    'ড়': 'ṙa'
+    'ঢ়': 'ya'

data/maps/un-bel-Cyrl-Latn-2007.yaml

@@ -1,18 +1,18 @@
 ---
 authority_id: un
 id: 2007
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: National System of Geographic Names Transmission into Roman Alphabet in Belarus
 url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/9th-uncsgn-docs/crp/9th_UNCSGN_e-conf-98-crp-21.pdf
 creation_date: 2007
 description: |
-  RESOLUTION OF THE STATE COMMITTEE 
+  RESOLUTION OF THE STATE COMMITTEE
   ON PROPERTY OF THE REPUBLIC OF BELARUS June 11, 2007 No. 38
 
-  8/16668 (06/18/2007) On amendments and additions to the Instructions 
-  for the transliteration of geographical names of the 
+  8/16668 (06/18/2007) On amendments and additions to the Instructions
+  for the transliteration of geographical names of the
   Republic of Belarus in letters of the Latin alphabet
 
   Based on the Regulation on the State Property Committee of the Republic of Belarus,

data/maps/un-ben-Beng-Latn-2016.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: un
 id: 2016
-language: ben
+language: iso-639-2:ben
 source_script: Beng
 destination_script: Latn
 name: Bengali Romanization, Version 4.0

data/maps/{un-ell-Grek-Latn-phonetic-1987.yaml → un-ell-Grek-Latn-1987-phonetic.yaml}

@@ -1,7 +1,7 @@
 ---
 authority_id: un
-id: 1987
-language: ell
+id: 1987-phonetic
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: UNGEGN Greek v1.0, Fifth United Nations Conference on the Standardization of Geographical Names. Writing Systems and Guides to Pronunciation Romanization > Conversion of the Greek alphabet into Latin characters. Paper submitted by Greece and Cyprus.
@@ -11,7 +11,7 @@ description: |
   UNGEGN Romanization table for Greek: Phonetic transcription
 
 
-note: 
+note:
   - Also included in ISO 843:1997, Annex B, Column 5, and ELOT 743:1982, column 5.
   - Corrected obvious errors, which occur every time the table has reappeared: χ > x, x > ks, oï > oi.
   - The vowels are taken from the specification, but some are controversial: /ɑ ɛ/ but /o/.
@@ -23,37 +23,37 @@ note:
 tests:
 
   - source: |
-        Ένα πράμα μόνον με παρακίνησε κι εμένα να γράψω ότι τούτην την πατρίδα την έχομεν όλοι μαζί, 
-        
-        και σοφοί κι αμαθείς και πλούσιοι και φτωχοί και πολιτικοί και στρατιωτικοί και οι πλέον μικρότεροι άνθρωποι· 
-        
-        όσοι αγωνιστήκαμεν, αναλόγως ο καθείς, έχομεν να ζήσομεν εδώ. 
-        
-        Το λοιπόν δουλέψαμεν όλοι μαζί, να την φυλάμεν κι όλοι μαζί και να μην λέγει ούτε ο δυνατός «εγώ» ούτε ο αδύνατος. 
-        
-        Ξέρετε πότε να λέγει ο καθείς «εγώ»; Όταν αγωνιστεί μόνος του και φκιάσει ή χαλάσει, να λέγει «εγώ»· 
-        
-        όταν όμως αγωνίζονται πολλοί και φκιάνουν, τότε να λένε «εμείς». Είμαστε εις το «εμείς» κι όχι εις το «εγώ». 
-        
+        Ένα πράμα μόνον με παρακίνησε κι εμένα να γράψω ότι τούτην την πατρίδα την έχομεν όλοι μαζί,
+
+        και σοφοί κι αμαθείς και πλούσιοι και φτωχοί και πολιτικοί και στρατιωτικοί και οι πλέον μικρότεροι άνθρωποι·
+
+        όσοι αγωνιστήκαμεν, αναλόγως ο καθείς, έχομεν να ζήσομεν εδώ.
+
+        Το λοιπόν δουλέψαμεν όλοι μαζί, να την φυλάμεν κι όλοι μαζί και να μην λέγει ούτε ο δυνατός «εγώ» ούτε ο αδύνατος.
+
+        Ξέρετε πότε να λέγει ο καθείς «εγώ»; Όταν αγωνιστεί μόνος του και φκιάσει ή χαλάσει, να λέγει «εγώ»·
+
+        όταν όμως αγωνίζονται πολλοί και φκιάνουν, τότε να λένε «εμείς». Είμαστε εις το «εμείς» κι όχι εις το «εγώ».
+
         Και εις το εξής να μάθομεν γνώση, αν θέλομεν να φκιάσομεν χωριόν, να ζήσομεν όλοι μαζί.
 
         Γιάννης Μακρυγιάννης.
 
     expected: |
-        ɛnɑ prɑmɑ monon mɛ pɑrɑkinisɛ ki ɛmɛnɑ nɑ ɣrɑpso oti tutin tin pɑtriðɑ tin ɛxomɛn oli mɑzi, 
-        
-        kɛ sofi ki ɑmɑθis kɛ plusii kɛ ftoxi kɛ politiki kɛ strɑtiotiki kɛ i plɛon mikrotɛri ɑnθropi; 
-        
-        osi ɑɣonistikɑmɛn, ɑnɑloɣos o kɑθis, ɛxomɛn nɑ zisomɛn ɛðo. 
-        
-        to lipon ðulɛpsɑmɛn oli mɑzi, nɑ tin filɑmɛn ki oli mɑzi kɛ nɑ min lɛɣi utɛ o ðinɑtos «ɛɣo» utɛ o ɑðinɑtos. 
-        
-        ksɛrɛtɛ potɛ nɑ lɛɣi o kɑθis «ɛɣo»? otɑn ɑɣonisti monos tu kɛ fkiɑsi i xɑlɑsi, nɑ lɛɣi «ɛɣo»; 
-        
-        otɑn omos ɑɣonizondɛ poli kɛ fkiɑnun, totɛ nɑ lɛnɛ «ɛmis». imɑstɛ is to «ɛmis» ki oxi is to «ɛɣo». 
-        
+        ɛnɑ prɑmɑ monon mɛ pɑrɑkinisɛ ki ɛmɛnɑ nɑ ɣrɑpso oti tutin tin pɑtriðɑ tin ɛxomɛn oli mɑzi,
+
+        kɛ sofi ki ɑmɑθis kɛ plusii kɛ ftoxi kɛ politiki kɛ strɑtiotiki kɛ i plɛon mikrotɛri ɑnθropi;
+
+        osi ɑɣonistikɑmɛn, ɑnɑloɣos o kɑθis, ɛxomɛn nɑ zisomɛn ɛðo.
+
+        to lipon ðulɛpsɑmɛn oli mɑzi, nɑ tin filɑmɛn ki oli mɑzi kɛ nɑ min lɛɣi utɛ o ðinɑtos «ɛɣo» utɛ o ɑðinɑtos.
+
+        ksɛrɛtɛ potɛ nɑ lɛɣi o kɑθis «ɛɣo»? otɑn ɑɣonisti monos tu kɛ fkiɑsi i xɑlɑsi, nɑ lɛɣi «ɛɣo»;
+
+        otɑn omos ɑɣonizondɛ poli kɛ fkiɑnun, totɛ nɑ lɛnɛ «ɛmis». imɑstɛ is to «ɛmis» ki oxi is to «ɛɣo».
+
         kɛ is to ɛksis nɑ mɑθomɛn ɣnosi, ɑn θɛlomɛn nɑ fkiɑsomɛn xorion, nɑ zisomɛn oli mɑzi.
-       
+
         ɣiɑnis mɑkriɣiɑnis.
 
 
@@ -101,7 +101,7 @@ tests:
     expected: tɑiɣɛtos
   - source: σπρέυ
     expected: sprɛi
-    
+
   - source: Αθήνα
     expected: ɑθinɑ
   - source: Άγιον Όρος
@@ -748,33 +748,33 @@ map:
 
     "\u0387": ";"   # ·
     "\u00B7": ";"   # ·
- 
+
   postrules:
     - pattern: vv
-      result: "v"  
+      result: "v"
     - pattern: ðð
-      result: "ð"  
+      result: "ð"
     - pattern: zz
-      result: "z"  
+      result: "z"
     - pattern: θθ
-      result: "θ"  
+      result: "θ"
     - pattern: kk
-      result: "k"  
+      result: "k"
     - pattern: ll
-      result: "l"  
+      result: "l"
     - pattern: mm
-      result: "m"  
+      result: "m"
     - pattern: nn
-      result: "n"  
+      result: "n"
     - pattern: pp
-      result: "p"  
+      result: "p"
     - pattern: rr
-      result: "r"  
+      result: "r"
     - pattern: ss
-      result: "s"  
+      result: "s"
     - pattern: tt
-      result: "t"  
+      result: "t"
     - pattern: ff
-      result: "f"  
+      result: "f"
     - pattern: xx
-      result: "x"  
+      result: "x"

data/maps/un-ell-Grek-Latn-1987-tl.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: un
-id: 1987
-language: ell
+id: 1987-tl
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: UNGEGN Greek v4.0
@@ -22,11 +22,10 @@ tests:
 
     expected: |
         Éna práma mónon me parakíni̱se ki eména na grápso̱ óti toúti̱n ti̱n patrída ti̱n échomen óloi mazí, kai sofoí ki amatheís kai ploúsioi kai fto̱choí kai politikoí kai stratio̱tikoí kai oi pléon mikróteroi ánthro̱poi; ósoi ago̱nistí̱kamen, analógo̱s o katheís, échomen na zí̱somen edó̱. To loipón doulépsamen óloi mazí, na ti̱n fylámen ki óloi mazí kai na mi̱n légei oúte o dynatós «egó̱» oúte o adýnatos. Xérete póte na légei o katheís «egó̱»? Ótan ago̱nisteí mónos tou kai fkiásei í̱ chalásei, na légei «egó̱»; ótan ómo̱s ago̱nízontai polloí kai fkiánoun, tóte na léne «emeís». Eímaste eis to «emeís» ki óchi eis to «egó̱». Kai eis to exí̱s na máthomen gnó̱si̱, an thélomen na fkiásomen cho̱rión, na zí̱somen óloi mazí.
-       
+
         Giánni̱s Makrygiánni̱s.
 
 map:
   character_separator: ""
   word_separator: " "
   inherit: "elot-ell-Grek-Latn-743-1982-tl"
-

data/maps/un-ell-Grek-Latn-1987-ts.yaml

@@ -1,12 +1,12 @@
 ---
 authority_id: un
-id: 2016
-language: ell
+id: 1987-tl
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: UNGEGN Greek v4.0
 url: http://www.eki.ee/wgrs/rom1_el.htm
-creation_date: 2016
+creation_date: 1987
 description: |
   UNGEGN Romanization table for Greek
 
@@ -17,4 +17,3 @@ map:
   character_separator: ""
   word_separator: " "
   inherit: "elot-ell-Grek-Latn-743-1982-ts"
-

data/maps/un-guj-Gujr-Latn-1972.yaml

@@ -0,0 +1,229 @@
+---
+authority_id: un
+id: 1972
+language: iso-639-2:guj
+source_script: Gujr
+destination_script: Latn
+name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Gujarati Romanization Version 4.0
+url: https://www.eki.ee/wgrs/rom1_gu.htm
+creation_date: 1972
+confirmation_date: 2016
+description: |
+  The United Nations recommended system was approved in 1972 (II/11) and amended in 1977 (III/12),
+  based on a report prepared by D. N. Sharma. The tables and their corrections were published in
+  volume II of the conference reports.
+
+  There is no evidence of the use of the system either in India or in international cartographic products.
+
+  Gujarati (Gujarātī) uses an alphasyllabic script whereby each character represents a syllable
+  rather than one sound. Vowels and diphthongs are marked in two ways: as independent characters
+  (used syllable-initially) and in an abbreviated form, to denote vowels after consonants.
+  The romanization table is unambiguous but the user would have to recognize many ligatures not
+  given in the original table. For two vowel letters (e/ĕ, o/ŏ) there is uncertainty as to the
+  conditions in which either of the two variants is to be used. The system is mostly reversible
+  but there exist some ambiguities in the romanization of vowels (independent vs. abbreviated characters)
+  and consonants (ligatures vs. character sequences).
+
+  References
+
+  Second United Nations Conference on the Standardization of Geographical Names. London, 10–31 May 1972.
+  Vol. II. Technical papers. United Nations. New York 1974, pp. 134–135.
+
+  Third United Nations Conference on the Standardization of Geographical Names.
+  Athens, 17 August – 7 September 1977. Vol. II, Technical papers, pp. 393 etc.
+
+notes:
+
+  - |
+    Exception of ી : જી jī.
+  - |
+    Exception of ૂ : રૂ rū.
+  - |
+    ્‌ indicates pronunciation without a vowel.
+
+tests:
+  - source: "અમિત શાહનો કોરોના રિપોર્ટ ૨ ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી"
+    expected: "amita shāhanŏ kŏrŏnā ripŏrṭa 2 ŏgasṭĕ pŏjhiṭiva āvyŏ hatŏ, tyārathī tĕmanuṁ svāsthya sāruṁ nathī"
+  - source: "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો"
+    expected: "mĕdāṁtā hŏspiṭalamāṁ tĕmanŏ ilāja chālī rahyŏ hatŏ"
+  - source: "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો"
+    expected: "bhāratanā vishvanāthana ānaṁdĕ shĕnayānamāṁ pahĕlŏ fiḍĕ shataraṁja vishva kapa jītyŏ"
+  - source: "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ ૪૦ લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું"
+    expected: "bhāratīya vaḍā pradhāna javāharalāla nĕharuĕ 40 lākha hinduŏ anĕ musalamānŏnā pārasparika sthānāṁtaraṇanuṁ sūchana āpyuṁ"
+  - source: "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન ૫૮ ડિગ્રી સેલ્સિયસ હતું."
+    expected: "libiyānā ĕla ajijiyāmāṁ dharatī para sauthī vadhu tāpamāna nŏṁdhāyuṁ. ĕ vakhatĕ chhāyāmāṁ nŏṁdhavāmāṁ āvĕluṁ tāpamāna 58 ḍigrī sĕlsiyasa hatuṁ."
+  - source: "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી"
+    expected: "prathama vishvayuddhaḥ jarmanī anĕ frānsa vachchĕ ĕsnĕnī laḍāī sharū thaī hatī"
+  - source: "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું."
+    expected: "ĕnglŏ-mistra yuddhaḥ tĕla ala kĕbiranuṁ yuddha laḍavāmāṁ āvyuṁ hatuṁ."
+  - source: "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા"
+    expected: "purāvā na hatā, ĕ ja kāraṇĕ kĕsa chālyŏ nahīṁ, paṇa tĕmanĕ najarakĕda rākhavāmāṁ āvyā"
+  - source: "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; ૯૧ વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ"
+    expected: "saradāra paṭĕlĕ nakkī karyuṁ hatuṁ kĕ kāshmīra bhāratanŏ hissŏ banashĕ; 91 varṣha pahĕlāṁ lāhŏra jĕlamāṁ bhūkhahaḍatāḷa daramiyāna shahīda thayā hatā jatīna dāsa"
+  - source: "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે"
+    expected: "kŏrŏnā prŏṭŏkŏla vachchĕ ājĕ mĕḍikala pravĕsha parīkṣhā lĕvāshĕḥ ĕnṭrī ṭacha frī rahĕshĕ, ĕḍamiṭa kārḍa bāra kŏḍathī chĕka thashĕ"
+  - source: "અલ્ ક઼`ઇદ્ માં હવામાન"
+    expected: "al ka`id māṁ havāmāna"
+  - source: "મંત્રાલય તથા ખ઼.ય ના વિ૨ષ્ઠ અધિકા૨ીઓ ઉપસ્થિત ૨હ્યા હતા"
+    expected: "maṁtrālaya tathā kha.ya nā vi2ṣhṭha adhikā2īŏ upasthita 2hyā hatā"
+
+map:
+
+  rules:
+    - pattern: ([ક]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'k'
+    - pattern: ([ખ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'kh'
+    - pattern: ([ગ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'g'
+    - pattern: ([ઘ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'gh'
+    - pattern: ([ઙ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ṅ'
+    - pattern: ([ચ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ch'
+    - pattern: ([છ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'chh'
+    - pattern: ([જ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'j'
+    - pattern: ([ઝ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'jh'
+    - pattern: ([ઞ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ñ'
+    - pattern: ([ટ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ṭ'
+    - pattern: ([ઠ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ṭh'
+    - pattern: ([ડ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ḍ'
+    - pattern: ([ઢ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ḍh'
+    - pattern: ([ણ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ṇ'
+    - pattern: ([ત]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 't'
+    - pattern: ([થ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'th'
+    - pattern: ([દ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'd'
+    - pattern: ([ધ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'dh'
+    - pattern: ([ન]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'n'
+    - pattern: ([પ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'p'
+    - pattern: ([ફ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'f'
+    - pattern: ([બ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'b'
+    - pattern: ([ભ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'bh'
+    - pattern: ([મ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'm'
+    - pattern: ([ય]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'y'
+    - pattern: ([ર]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'r'
+    - pattern: ([લ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'l'
+    - pattern: ([વ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'v'
+    - pattern: ([શ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'sh'
+    - pattern: ([ષ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ṣh'
+    - pattern: ([સ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 's'
+    - pattern: ([હ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'h'
+    - pattern: ([ળ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])
+      result: 'ḷ'
+
+  characters:
+    # I. Independent vowel characters
+    'અ': 'a'
+    'આ': 'ā'
+    'ઇ': 'i'
+    'ઈ': 'ī'
+    'ઉ': 'u'
+    'ઊ': 'ū'
+    'ઋ': 'ṛ'
+    'ઍ': 'e'
+    'એ': 'ĕ'
+    'ઐ': 'ai'
+    'ઑ': 'o'
+    'ઓ': 'ŏ'
+    'ઔ': 'au'
+
+    # II. Abbreviated vowel characters
+    'ા': 'ā'
+    'િ': 'i'
+    'ી': 'ī'
+    'ુ': 'u'
+    'ૂ': 'ū'
+    'ૃ': 'ṛ'
+    'ૅ': 'e'
+    'ે': 'ĕ'
+    'ૈ': 'ai'
+    'ૉ': 'o'
+    'ો': 'ŏ'
+    'ૌ': 'au'
+
+    # III. Other symbols
+    'ઃ': 'ḥ'
+    'ં': 'ṁ'
+    'ઁ': 'm̐'
+    '્': ''
+
+    # IV. Consonant characters
+    'ક': 'ka'
+    'ખ': 'kha'
+    'ગ': 'ga'
+    'ઘ': 'gha'
+    'ઙ': 'ṅa'
+    'ચ': 'cha'
+    'છ': 'chha'
+    'જ': 'ja'
+    'ઝ': 'jha'
+    'ઞ': 'ña'
+    'ટ': 'ṭa'
+    'ઠ': 'ṭha'
+    'ડ': 'ḍa'
+    'ઢ': 'ḍha'
+    'ણ': 'ṇa'
+    'ત': 'ta'
+    'થ': 'tha'
+    'દ': 'da'
+    'ધ': 'dha'
+    'ન': 'na'
+    'પ': 'pa'
+    'ફ': 'fa'
+    'બ': 'ba'
+    'ભ': 'bha'
+    'મ': 'ma'
+    'ય': 'ya'
+    'ર': 'ra'
+    'લ': 'la'
+    'વ': 'va'
+    'શ': 'sha'
+    'ષ': 'ṣha'
+    'સ': 'sa'
+    'હ': 'ha'
+    'ળ': 'ḷa'
+
+    # digits
+    '૦': '0'
+    '૧': '1'
+    '૨': '2'
+    '૩': '3'
+    '૪': '4'
+    '૫': '5'
+    '૬': '6'
+    '૭': '7'
+    '૮': '8'
+    '૯': '9'
+
+    '઼': ''
+    '।': '.'
+    '\u09CD': '' # Used for joining
+    "‍": ''# Used for joining