interscript 0.1.3 → 0.1.9

data/maps/un-prs-Arab-Latn-1967.yaml

@@ -0,0 +1,236 @@
+---
+authority_id: ungen
+id: 2017
+language: iso-639-3:prs # prs stands for Dari (https://iso639-3.sil.org/code/prs&_ga=GA1.2.2054538372.1574092823)
+source_script: Arab
+destination_script: Latn
+name: Persian UN 1967
+url: http://www.eki.ee/wgrs/v2_2/rom1_fa.htm
+creation_date: 1967
+confirmation_date: 01-2003
+description: |
+  The United Nations recommended system was approved in 1967 (
+  I/13), based on the official system adopted by Iran and
+  published in its English version as Transliteration of
+  Farsi Geographic Names to Latin Alphabet (September 1966).
+  The romanization table was also published as an annex to
+  the Toponymic Guidelines for the Islamic Republic of Iran
+  in 2000 (Toponymic Guidelines for map and other editors –
+  Revised edition 1998. Submitted by the Islamic Republic of
+  Iran. UNGEGN, 20th session. New York, 17-28 January 2000,
+  Working Paper No. 41.).
+
+  The system is used in the Islamic Republic of Iran and in
+  international cartographic products.
+
+  Persian (Farsi) uses the Perso-Arabic script that is
+  written from right to left. The Persian script usually
+  omits vowel points and diacritical marks from writing which
+  makes it difficult to obtain uniform results in the
+  romanization of Persian. The romanization is generally
+  reversible though there are some ambiguous letter
+  sequences (kh, sh, th, zh) which also may represent the
+  romanized values of two Persian characters in addition to
+  the respective single ones.
+
+
+notes:
+  - A Word-initially.
+  - B Not romanized; marks absence of the vowel.
+  - C Doubling of the consonant letter.
+  - D After a consonant (excl. -ah).
+  - E After a vowel (see also note 2).
+  - 1-The adjectival ending of Arabic origin -يه in Persian is
+    romanized -īyeh. In romanizing the definite article the
+    same rules of assimilation of consonants are applied as in
+    Arabic, e.g. زين الدين Zeyn od Dīn.
+
+  - 2-The relational suffix (eẕāfeh) -e is usually not
+    expressed in Persian writing after a consonant. After final
+    ا or و it is written with ى, e.g. پاى آب Pā-ye Āb. After
+    final ى and ه it is expressed by writing hamzeh over the
+    character دهانۀ ممبر Dahāneh-ye Mambar.
+
+  - 3-To point Persian vowels two systems are in use that are
+    separated by a column in the table. The first system is a
+    Persian one while the other adheres to the Arabic
+    tradition. In normal spelling vowel points are not used.
+
+tests:
+  - source: اَنجِيرة
+    expected: Anjīrah
+
+  - source: اِيْوَانِي
+    expected: Eyvānī
+
+  - source: آبَادَان
+    expected: Ābādān
+
+  - source: قُرآن
+    expected: Qor’ān
+
+  - source: مَآب
+    expected: Ma’āb
+
+  - source: مُحَمَّد
+    expected: Moḩammad
+
+  - source: كُوهِ مَرغُوب
+    expected: Kūh-e Marghūb
+
+  - source: پَايِ آب
+    expected: Pā-ye Āb
+
+  - source: جُويِ آس
+    expected: Jū-ye Ās
+
+  - source: دَهَانِهٴ مَمبَر
+    expected: Dahāneh-ye Mambar
+
+  - source: سَلَسِيٴ بُذُرگ
+    expected: Salasī-ye Boz̄org
+
+  - source: ذُو الفَقَار
+    expected: Z̄ū ol Faqār
+
+
+map:
+  postrules:
+    - pattern: (?<=\b)(?<!\b[‘|’|'|-])[\u0061-\uFFFF]
+      result: "upcase"
+
+    - pattern: " Al"
+      result: " al"
+
+    - pattern: " Ol"
+      result: " ol"
+
+  characters:
+
+    '\u064e' : 'a' # َ fatha
+    '\u064e(?=\u0629)' : '' # َ fatha followed by ta' marboota
+    '\u064e(?=a[h|t])' : '' # َ fatha followed by ta' marboota, handling different order of conversion
+    '\u0650' : 'e' # ِ kasra
+    '\u064f' : 'o' # ُ damma
+    '\u0652' : ''  # ْ sokoon, see Note B
+
+    '\u064e\u0627' : 'ā'  # ـَا fatha followed by ا
+    '\u064e\u0649' : 'á'  # ـَى fatha followed by ى which is ا not ي
+    '\b\u0622' : 'ā'  # آ  NOTE A
+    '\u0622' : '’ā' # آ
+    '\u0650\u064a' : 'ī' # ـِي kasra followed by ي
+    '\u064f\u0648' : 'ū'  # ـُو damma followed by و
+    '[\u064e|\u0650]\u064a\u0652' : 'ey'  # ـَيْ
+    '[\u064e|\u064f]\u0648\u0652' : 'ow'  # ـَوْ
+    '\u0621' : '’' # ء
+    '\u2013' : '–'
+    '\u2013[\u0649|\u064a]\u0647' : '-īyeh'
+    '[\u0654|\u0674]' : '-e' # ٴ ezafeh
+    '(?<=[\u064a|\u0647])[\u0654|\u0674]' : '-ye' # ٴ ezafeh
+    '\u0650\b' : '-e' # ِ kasra
+    '[\u064a|\u06cc]\u0650\b' : '-ye' # ِ kasra
+
+    # NOTE C
+    '\u0628\u0651' : 'bb'  # ب
+    '\u062a\u0651' : 'tt'  # ت
+    '\u062b\u0651' : 's̄s̄'  # ث
+    '\u062c\u0651' : 'jj'  # ج
+    '\u062d\u0651' : 'ḩḩ' # ح
+    '\u062e\u0651' : 'kh'  # خ
+    '\u062f\u0651' : 'dd'  # د
+    '\u0630\u0651' : 'z̄z̄'  # ذ
+    '\u0631\u0651' : 'rr'  # ر
+    '\u0632\u0651' : 'zz'  # ز
+    '\u0633\u0651' : 'ss'  # س
+    '\u0634\u0651' : 'sh'  # ش
+    '\u0635\u0651' : 'şş'  # ص
+    '\u0636\u0651' : 'ẕẕ'  # ض
+    '\u0637\u0651' : 'ţţ'  # ط
+    '\u0638\u0651' : 'z̧z̧'  # ظ
+    '\u063a\u0651' : 'gh'  # غ
+    '\u0641\u0651' : 'ff'  # ف
+    '\u0642\u0651' : 'qq'  # ق
+    '\u0643\u0651' : 'kk'  # ك
+    '\u0644\u0651' : 'll'  # ل
+    '\u0645\u0651' : 'mm'  # م
+    '\u0646\u0651' : 'nn'  # ن
+    '\u0647\u0651' : 'hh'  # ه
+    '\u0648\u0651' : 'vv'  # و
+    '\u064a\u0651' : 'yy'  # ي
+
+    # NOTE 1
+    # Sun letters
+    '\b\u0627\u0644\u062a' : 'ot t'  # الت
+    '\b\u0627\u0644\u062b' : 'os̄ s̄'  # الث
+    '\b\u0627\u0644\u062f' : 'od d' # الد
+    '\b\u0627\u0644\u0630' : 'oz̄ z̄'  # الذ
+    '\b\u0627\u0644\u0631' : 'or r' # الر
+    '\b\u0627\u0644\u0632' : 'oz z'  # الز
+    '\b\u0627\u0644\u0633' : 'os s' # الس
+    '\b\u0627\u0644\u0634' : 'osh sh' # الش
+    '\b\u0627\u0644\u0635' : 'oş ş'  # الص
+    '\b\u0627\u0644\u0636' : 'oẕ ẕ'  # الض
+    '\b\u0627\u0644\u0637' : 'oţ ţ'  # الط
+    '\b\u0627\u0644\u0638' : 'oz̧ z̧' # الظ
+    '\b\u0627\u0644\u0644' : 'ol l'  # الل
+    '\b\u0627\u0644\u0646' : 'on n'  # الن
+
+    '\u0650\u064a\u0651' : 'īy' # ـِيَّ
+    '\u0650\u064a(?=\u064e|u064f)' : 'iy' # ـِي kasra followed by ي
+
+    # ta' marboota
+    '\u0629' : 'at' # ة in the middle of the sentence
+    '\u0629$' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{2})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{3})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{4})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{5})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{6})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{7})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{8})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{9})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{10})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{11})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{12})\u0629' : 'ah'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{13})\u0629' : 'ah'
+
+    '\b\u0627\u0644' : 'al '  # ال
+    '\s\b\u0627\u0644' : ' ol '  # ال #special Rule 1
+
+    '\b\u0627' : ''  # ا initial
+    '\u0627' : 'ā'  # ا middial
+    '\u0627\b' : 'ā'  # ا final
+
+    '\u0628' : 'b' # ب
+    '\u067E' : 'p' # پ
+    '\u062A' : 't' # ت
+    '\u062B' : 's̄' # ث
+    '\u062C' : 'j' # ج
+    '\u0686' : 'ch' # ‫چ‬
+    '\u062D' : 'ḩ' # ح
+    '\u062E' : 'kh' # خ
+    '\u062F' : 'd' # د
+    '\u0630' : 'z̄' # ذ
+    '\u0631' : 'r' # ر
+    '\u0632' : 'z' # ز
+    '\u0698' : 'zh' # ‫ژ‬
+    '\u0633' : 's' # س
+    '\u0634' : 'sh' # ش
+    '\u0635' : 'ş' # ص
+    '\u0636' : 'ẕ' # ض
+    '\u0637' : 'ţ' # ط
+    '\u0638' : 'z̧' # ظ
+    '\u0639' : '’' # ع
+    '\u063A' : 'gh' # غ
+    '\u0641' : 'f' # ف
+    '\u0642' : 'q' # ق
+    '\u0643' : 'k'  # ك
+    '\u06A9' : 'k' # ک
+    '\u06AF' : 'g' # گ
+    '\u0644' : 'l' # ل‫‬
+    '\u0645' : 'm' # م
+    '\u0646' : 'n' # ن
+    '\u0648' : 'v' # و
+    '\u0647' : 'h' # ه
+    '\u0649' : 'y' # ي
+    '\u064a' : 'y'  # ي

data/maps/un-rus-Cyrl-Latn-1987.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: ungegn
 id: 1987
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
 name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Russian Romanization system
@@ -157,7 +157,7 @@ tests:
 
 
 map:
-  inherit: gost-rus-cyrl-latn-16876-71-1983
+  inherit: gost-rus-Cyrl-Latn-16876-71-1983
 
   characters:
     '\u042A' : '”'  # Ъ

data/maps/un-tam-Taml-Latn-1972.yaml

@@ -0,0 +1,194 @@
+---
+authority_id: un
+id: 1972
+language: iso-639-2:tam
+source_script: Gujr
+destination_script: Taml
+name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Tamil Romanization Version 4.0
+url: https://www.eki.ee/wgrs/rom1_ta.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, Sri Lanka or in international cartographic products.
+
+  Tamil 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. The system is on the whole reversible.
+
+notes:
+
+  - |
+    ஜி Variation: டி ṭi.
+  - |
+    ஜீ Variation: டீ ṭī.
+  - |
+    ஜு Variations: கு ku, ஙு ṅu, சு chu, ஞு ñu, டு ṭu, ணு ṇu, து tu, நு nu, பு pu, மு mu, யு yu, ரு ru, லு lu, etc.
+  - |
+    ஜூ Variations: கூ kū, ஙூ ṅū, சூ chū, ஞூ ñū, டூ ṭū, ணூ ṇū, தூ tū, நூ nū, பூ pū, மூ mū, etc.
+  - |
+    ஃ Absent in the original table.
+  - |
+    ் Pronunciation without a vowel: க் k.
+  - |
+    ஜ, ஶ, ஸ, ன Characters borrowed from the Grantha script.
+  - |
+    ஸ Special syllable character: ஸ்ரீ srī.
+
+tests:
+  - source: "அழிந்து போன நகரத்தில் , தொலைந்து போன நான்"
+    expected: "al̮intu poṉa nakarattil , tŏlaintu poṉa nāṉ"
+  - source: "முதன் முதலாக - மை ஃபர்ஸ்ட் சோலோ ட்ராவல்"
+    expected: "mutaṉ mutalāka - mai ḥparsṭ cholo ṭrāval"
+  - source: "வாழ்க்கையில் அவன் போன முதல் சோலோ டிரிப் அது தான்."
+    expected: "vāl̮kkaiyil avaṉ poṉa mutal cholo ṭirip atu tāṉ."
+  - source: "ஸ்கூல் ப்ரெண்ட் கார்த்திக் வீட்டுக்கு போய்ட்டு"
+    expected: "skūl prĕṇṭ kārttik vīṭṭukku poyṭṭu"
+  - source: "நாசா வெளியிட்ட வெடிக்கும் நட்சத்திரத்தின் வீடியோ"
+    expected: "nāchā vĕḷiyiṭṭa vĕṭikkum naṭchattirattiṉ vīṭiyo"
+  - source: "டார்பிடோவை ஏவ உதவும் சூப்பர்சானிக் ஏவுகணையான ஸ்மார்ட் சோதனை வெற்றி"
+    expected: "ṭārpiṭovai eva utavum chūpparchāṉik evukaṇaiyāṉa smārṭ chotaṉai vĕṟṟi"
+  - source: "இந்த ஆண்டு மருத்துவத்துக்கான நோபல் பரிசு பெறுபவர்களின் பெயர்கள் அறிவிப்பு"
+    expected: "inta āṇṭu maruttuvattukkāṉa nopal parichu pĕṟupavarkaḷiṉ pĕyarkaḷ aṟivippu"
+  - source: "மல்லையா விவகாரம்: பிரிட்டன் அரசின் நடவடிக்கைகள் தங்களுக்கு தெரியவில்லை - மத்திய அரசு தகவல்"
+    expected: "mallaiyā vivakāram: piriṭṭaṉ arachiṉ naṭavaṭikkaikaḷ taṅkaḷukku tĕriyavillai - mattiya arachu takaval"
+  - source: "ஆலோசனைக்குப் பிறகு தேனியில் இருந்து சென்னை புறப்பட்டார் துணை முதலமைச்சர் பன்னீர்செல்வம்"
+    expected: "ālochaṉaikkup piṟaku teṉiyil iruntu chĕṉṉai puṟappaṭṭār tuṇai mutalamaichchar paṉṉīrchĕlvam"
+  - source: "இன்று தான் பேரன் பிறந்தநாள் முடிந்து ஃப்ரீ ஆகி இருக்கிறேன்"
+    expected: "iṉṟu tāṉ peraṉ piṟantanāḷ muṭintu ḥprī āki irukkiṟeṉ"
+
+map:
+
+  rules:
+    - pattern: ([க]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'k'
+    - pattern: ([ங]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ṅ'
+    - pattern: ([ச]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ch'
+    - pattern: ([ஞ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ñ'
+    - pattern: ([ட]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ṭ'
+    - pattern: ([ண]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ṇ'
+    - pattern: ([த]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  't'
+    - pattern: ([ந]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'n'
+    - pattern: ([ப]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'p'
+    - pattern: ([ம]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'm'
+    - pattern: ([ய]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'y'
+    - pattern: ([ர]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'r'
+    - pattern: ([ல]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'l'
+    - pattern: ([வ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'v'
+    - pattern: ([ழ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'l̮'
+    - pattern: ([ள]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ḷ'
+    - pattern: ([ற]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ṟ'
+    - pattern: ([ன]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ṉ'
+    - pattern: ([ஜ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'j'
+    - pattern: ([ஶ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'sh'
+    - pattern: ([ஷ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'ṣh'
+    - pattern: ([ஸ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  's'
+    - pattern: ([ஹ]=?)(?=[\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd])
+      result:  'h'
+
+
+  characters:
+    'அ': 'a'
+    'ஆ': 'ā'
+    'ா': 'ā'
+
+    'இ': 'i'
+    'ி': 'i'
+
+    'ஈ': 'ī'
+    'ீ': 'ī'
+
+    'உ': 'u'
+    'ு': 'u'
+
+    'ஊ': 'ū'
+    'ூ': 'ū'
+
+    'ெ': "ĕ"
+    'எ': 'ĕ'
+
+    'ே': "e"
+    'ஏ': 'e'
+
+    'ஐ': 'ai'
+    'ை': "ai"
+
+    'ஒ': 'ŏ'
+    'ொ': 'ŏ'
+
+    'ோ': 'o'
+    'ஓ': 'o'
+
+    'ஔ': 'au'
+    'ௌ': 'au'
+
+    'ஃ': 'ḥ'
+    '்': ''
+
+    'க': 'ka'
+    'ங': 'ṅa'
+    'ச': 'cha'
+    'ஞ': 'ña'
+    'ட': 'ṭa'
+    'ண': 'ṇa'
+    'த': 'ta'
+    'ந': 'na'
+    'ப': 'pa'
+    'ம': 'ma'
+    'ய': 'ya'
+    'ர': 'ra'
+    'ல': 'la'
+    'வ': 'va'
+    'ழ': 'l̮a'
+    'ள': 'ḷa'
+    'ற': 'ṟa'
+    'ன': 'ṉa'
+    'ஜ': 'ja'
+    'ஶ': 'sha'
+    'ஷ': 'ṣha'
+    'ஸ': 'sa'
+    'ஹ': 'ha'
+    'க்ஷ': 'kṣha'
+    'ற்ற': 'ṟṟa'
+    'ன்ற': 'ṉṟa'
+
+    # Digits
+    '௧': '1'
+    '௨': '2'
+    '௩': '3'
+    '௪': '4'
+    '௫': '5'
+    '௬': '6'
+    '௭': '7'
+    '௮': '8'
+    '௯': '9'
+    '௦': '0'
+    '௰': '10'
+    '௱': '100'
+    '௲': '1000'
+
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner

data/maps/un-tel-Telu-Latn-1972.yaml

@@ -0,0 +1,270 @@
+---
+authority_id: un
+id: 1972
+language: iso-639-2:tel
+source_script: Telu
+destination_script: Latn
+name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Telugu Romanization, 1972
+url: https://www.eki.ee/wgrs/rom1_te.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.
+
+  Telugu 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. The system is
+  mostly reversible but there may exist some ambiguities in the romanization of vowels (independent vs. abbreviated characters)
+  and consonants (combinations with subscript consonants vs. character sequences).
+
+notes:
+
+  - |
+    Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+    a) when another vowel is indicated by its appropriate sign; and
+    b) when the absence of any vowel is indicated by the superscript sign ( ౬ ) called valapalagilaka.
+  - |
+    Exception: Sunna is transliterated by:
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+  - |
+    Ardhasunna before gutturals and palatal, cerebral, and dental occlusives is transliterated n̐.
+    Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
+    transliterated m
+
+tests:
+  - source: "తమిళనాడు"
+    expected: "tamiḷanāḍu"
+  - source: "తంటికొండ ఘటన: ఆగని మృత్యుఘోష"
+    expected: "taṃṭikŏṃḍa ghaṭana: āgani mṛtyughoṣha"
+  - source: "మళ్లీ వివాదం: అమితాబ్‌పై కేసు"
+    expected: "maḷlī vivādaṃ: amitābpai kesu"
+  - source: "వరద సాయం పేరుతో వైట్ కాలర్ దోపిడీ"
+    expected: "varada sāyaṃ peruto vaiṭ kālar dopiḍī"
+  - source: "రెండో విడత జీఎస్టీ పరిహారం"
+    expected: "rĕṃḍo viḍata jīĕsṭī parihāraṃ"
+  - source: "నితీష్‌ కుమార్‌ అధ్యాయం ముగిసినట్లేనా?!"
+    expected: "nitīṣh kumār adhyāyaṃ mugisinaṭlenā?!"
+  - source: "వారిపై జీవితాంతం నిషేధం విధించండి!"
+    expected: "vāripai jīvitāṃtaṃ niṣhedhaṃ vidhiṃchaṃḍi!"
+  - source: "మరో లాక్‌డౌన్‌ వల్ల అన్నీ అనర్థాలే!"
+    expected: "maro lākḍaun valla annī anarthāle!"
+  - source: "జెసిండా మరో సంచలనం"
+    expected: "jĕsiṃḍā maro saṃchalanaṃ"
+  - source: "స్వీయ నిర్బంధంలోకి డబ్ల్యూహెచ్‌ఓ డైరెక్టర్‌"
+    expected: "svīya nirbaṃdhaṃloki ḍablyūhĕcho ḍairĕkṭar"
+  - source: "కరోనాపై యుద్ధంలో సమిధలు"
+    expected: "karonāpai yuddhaṃlo samidhalu"
+  - source: "అమెరికా ఎన్నికలు: ‘పెద్దన్న’ ఎవరో?!"
+    expected: "amĕrikā ĕnnikalu: ‘pĕddanna’ ĕvaro?!"
+  - source: "౪౬౨౬౯"
+    expected: "46269"
+  - source: "రంగపూర్"
+    expected: "raṃgapūr"
+  # subscript consonant characters
+  - source: "ట్ట"
+    expected: "ṭṭa"
+  - source: "ప్ప"
+    expected: "ppa"
+  - source: "చ్చ"
+    expected: "chcha"
+
+
+map:
+
+  rules:
+    - pattern: ([క]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'k'
+    - pattern: ([ఖ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'kh'
+    - pattern: ([గ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'g'
+    - pattern: ([ఘ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'gh'
+    - pattern: ([ఙ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'ṅ'
+    - pattern: ([చ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'ch'
+    - pattern: ([ఛ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'chh'
+    - pattern: ([జ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'j'
+    - pattern: ([ఝ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'jh'
+    - pattern: ([ఞ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'ñ'
+    - pattern: ([ట]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:   'ṭ'
+    - pattern: ([ఠ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:   'ṭh'
+    - pattern: ([డ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:   'ḍ'
+    - pattern: ([ఢ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:   'ḍh'
+    - pattern: ([ణ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:   'ṇ'
+    - pattern: ([త]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  't'
+    - pattern: ([థ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'th'
+    - pattern: ([ద]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'd'
+    - pattern: ([ధ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'dh'
+    - pattern: ([న]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'n'
+    - pattern: ([ప]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'p'
+    - pattern: ([ఫ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'ph'
+    - pattern: ([బ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'b'
+    - pattern: ([భ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'bh'
+    - pattern: ([మ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'm'
+    - pattern: ([య]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'y'
+    - pattern: ([ర]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'r'
+    - pattern: ([ఱ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'r'
+    - pattern: ([ల]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'l'
+    - pattern: ([వ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'v'
+    - pattern: ([శ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'sh'
+    - pattern: ([ష]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'ṣh'
+    - pattern: ([స]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  's'
+    - pattern: ([హ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:  'h'
+    - pattern: ([ళ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d])
+      result:   'ḷ'
+
+  characters:
+
+    # I. Independent vowel characters
+
+    'అ': 'a'
+    'ఆ': 'ā'
+    'ఇ': 'i'
+    'ఈ': 'ī'
+    'ఉ': 'u'
+    'ఊ': 'ū'
+    'ఋ': 'ṛ'
+    'ౠ': 'ṝ'
+    'ఎ': 'ĕ'
+    'ఏ': 'e'
+    'ఐ': 'ai'
+    'ఒ': 'ŏ'
+    'ఓ': 'o'
+    'ఔ': 'au'
+
+    # II. Abbreviated vowel characters and other symbols
+
+    'ా': 'ā'
+    'ి': 'i' # Variations: చి chi, ని ni, యి yi, లి li, etc.
+    'ీ': 'ī'
+    'ు': 'u' # Variations: జు ju, పు pu, వు vu, etc.
+    'ూ': 'ū'
+    'ృ': 'ṛ'
+    'ె': 'ĕ'
+    'ే': 'e'
+    'ై': 'ai'
+    'ొ': 'ŏ' # Variations: మొ mŏ, యొ yŏ.
+    'ో': 'o' # Variations: మో mo, యో yo.
+    'ౌ': 'au'
+    'ঁ': 'ṁ'
+    'ఁ': 'm̐' # Signified historic nasal sound, now obsolete.
+    'ః': 'ḥ'
+    'ం': 'ṃ'
+    '\u0c4d': '' # End-of-syllable mark (i.e., a consonant without a vowel): రంగపూర్ Raṁgapūr.
+
+    # III. Consonant characters
+
+    # Gutturals
+    'క': 'ka'
+    'ఖ': 'kha'
+    'గ': 'ga'
+    'ఘ': 'gha'
+    'ఙ': 'ṅa'
+
+    # Palatals
+    'చ': 'cha'
+    'ఛ': 'chha'
+    'జ': 'ja'
+    'ఝ': 'jha'
+    'ఞ': 'ña'
+
+    # Cerebrals
+    'ట':  'ṭa'
+    'ఠ':  'ṭha'
+    'డ':  'ḍa'
+    'ఢ':  'ḍha'
+    'ణ':  'ṇa'
+
+    # Dentals
+    'త': 'ta'
+    'థ': 'tha'
+    'ద': 'da'
+    'ధ': 'dha'
+    'న': 'na'
+
+    # Labials
+    'ప': 'pa'
+    'ఫ': 'pha'
+    'బ': 'ba'
+    'భ': 'bha'
+    'మ': 'ma'
+
+    # Semivowels
+    'య': 'ya'
+    'ర': 'ra' #Variant: ఱ.
+    'ఱ': 'ra'
+    'ల': 'la'
+    'వ': 'va'
+
+    # Sibilants
+    'శ': 'sha'
+    'ష': 'ṣha'
+    'స': 'sa'
+
+    # Aspirate
+    'హ': 'ha'
+    'ళ' : 'ḷa'
+
+    '\u09CD': '' # Used for joining
+    'ౕ	': ''
+    'ౖ	': ''
+    '्': ''
+    '़': ''
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining
+
+    # numbers
+
+    '౦': '0'
+    '౧': '1'
+    '౨': '2'
+    '౩': '3'
+    '౪': '4'
+    '౫': '5'
+    '౬': '6'
+    '౭': '7'
+    '౮': '8'
+    '౯': '9'