interscript 0.1.5 → 0.1.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/__pycache__/g2pwrapper.cpython-38.pyc +0 -0
- data/lib/interscript.rb +5 -1
- data/lib/interscript/fs.rb +3 -1
- data/lib/interscript/mapping.rb +2 -2
- data/lib/interscript/opal.rb +5 -1
- data/lib/interscript/opal/maps.js.erb +7 -4
- data/lib/interscript/version.rb +1 -1
- data/maps/acadsin-zho-Hani-Latn-2002.yaml +1 -1
- data/maps/alalc-amh-Ethi-Latn-1997.yaml +509 -0
- data/maps/alalc-amh-Ethi-Latn-2011.yaml +138 -0
- data/maps/alalc-ara-Arab-Latn-1997.yaml +1283 -0
- data/maps/alalc-asm-Deva-Latn-1997.yaml +159 -0
- data/maps/alalc-aze-Cyrl-Latn-1997.yaml +1 -1
- data/maps/{alalc-bel-cyrl-latn-1997.yaml → alalc-bel-Cyrl-Latn-1997.yaml} +2 -2
- data/maps/alalc-ell-Grek-Latn-1997.yaml +2 -3
- data/maps/alalc-ell-Grek-Latn-2010.yaml +2 -3
- data/maps/alalc-hin-Deva-Latn-2020.yaml +159 -0
- data/maps/alalc-kat-Geok-Latn-1997.yaml +1 -2
- data/maps/alalc-kor-Hang-Latn-1997.yaml +1 -1
- data/maps/alalc-mar-Deva-Latn-1997.yaml +170 -0
- data/maps/{alalc-mkd-cyrl-latn-1997.yaml → alalc-mkd-Cyrl-Latn-1997.yaml} +0 -0
- data/maps/alalc-pan-Deva-Latn-1997.yaml +237 -0
- data/maps/alalc-rus-Cyrl-Latn-1997.yaml +1 -2
- data/maps/alalc-rus-Cyrl-Latn-2012.yaml +2 -2
- data/maps/{alalc-srp-cyrl-latn-2013.yaml → alalc-srp-Cyrl-Latn-2013.yaml} +0 -0
- data/maps/bas-rus-Cyrl-Latn-2017-bss.yaml +0 -1
- data/maps/bgn-jpn-Hrkt-Latn-1962.yaml +0 -2
- data/maps/bgn-kor-Hang-Latn-1943.yaml +1 -1
- data/maps/bgn-kor-Kore-Latn-1943.yaml +1 -1
- data/maps/bgnpcgn-amh-Ethi-Latn-1967.yaml +528 -0
- data/maps/bgnpcgn-ara-Arab-Latn-1956.yaml +592 -0
- data/maps/bgnpcgn-bak-Cyrl-Latn-2007.yaml +5 -5
- data/maps/{bgnpcgn-bel-cyrl-latn-1979.yaml → bgnpcgn-bel-Cyrl-Latn-1979.yaml} +0 -0
- data/maps/bgnpcgn-ell-Grek-Latn-1962.yaml +3 -4
- data/maps/bgnpcgn-ell-Grek-Latn-1996.yaml +0 -1
- data/maps/bgnpcgn-kat-Geor-Latn-2009.yaml +0 -1
- data/maps/bgnpcgn-kor-Hang-Latn-kn-1945.yaml +17 -17
- data/maps/bgnpcgn-kor-Hang-Latn-rok-2011.yaml +2 -2
- data/maps/bgnpcgn-kor-Kore-Latn-rok-2011.yaml +2 -2
- data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.yaml +1 -1
- data/maps/bgnpcgn-nep-Deva-Latn-2011.yaml +200 -0
- data/maps/bgnpcgn-per-Arab-Latn-1956.yaml +0 -1
- data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.yaml +0 -1
- data/maps/bis-asm-Beng-Latn-13194-1991.yaml +159 -0
- data/maps/bis-ben-Beng-Latn-13194-1991.yaml +156 -0
- data/maps/bis-dev-Deva-Latn-13194-1991.yaml +184 -0
- data/maps/bis-gjr-Gujr-Latn-13194-1991.yaml +166 -0
- data/maps/bis-knd-Knda-Latn-13194-1991.yaml +173 -0
- data/maps/bis-mlm-Mlym-Latn-13194-1991.yaml +176 -0
- data/maps/bis-ori-Orya-Latn-13194-1991.yaml +160 -0
- data/maps/bis-pnj-Guru-Latn-13194-1991.yaml +175 -0
- data/maps/bis-tel-Telu-Latn-13194-1991.yaml +170 -0
- data/maps/bis-tml-Taml-Latn-13194-1991.yaml +155 -0
- data/maps/by-bel-Cyrl-Latn-1998.yaml +4 -4
- data/maps/by-bel-Cyrl-Latn-2007.yaml +3 -3
- data/maps/dos-nep-Deva-Latn-1997.yaml +33 -0
- data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml +4 -5
- data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml +4 -5
- data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml +0 -1
- data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml +0 -1
- data/maps/ggg-kat-Geor-Latn-2002.yaml +0 -1
- data/maps/{gki-bel-cyrl-latn-1992.yaml → gki-bel-Cyrl-Latn-1992.yaml} +1 -1
- data/maps/{gki-bel-cyrl-latn-2000.yaml → gki-bel-Cyrl-Latn-2000.yaml} +1 -1
- data/maps/{gost-rus-cyrl-latn-16876-71-1983.yaml → gost-rus-Cyrl-Latn-16876-71-1983.yaml} +1 -1
- data/maps/icao-bel-Cyrl-Latn-9303.yaml +0 -5
- data/maps/icao-bul-Cyrl-Latn-9303.yaml +0 -4
- data/maps/icao-per-Arab-Latn-9303.yaml +0 -1
- data/maps/icao-rus-Cyrl-Latn-9303.yaml +0 -1
- data/maps/icao-ukr-Cyrl-Latn-9303.yaml +0 -1
- data/maps/iso-ara-Arab-Latn-233-1984.yaml +323 -0
- data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml +4 -5
- data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml +1 -2
- data/maps/iso-rus-Cyrl-Latn-9-1995.yaml +0 -1
- data/maps/iso-tha-Thai-Latn-11940-1998.yaml +1 -1
- data/maps/kp-kor-Hang-Latn-2002.yaml +4 -4
- data/maps/lshk-yue-Hani-Latn-jyutping-1993.yaml +2 -2
- data/maps/mvd-bel-Cyrl-Latn-2008.yaml +4 -4
- data/maps/mvd-bel-Cyrl-Latn-2010.yaml +4 -4
- data/maps/mvd-rus-Cyrl-Latn-2008.yaml +1 -2
- data/maps/mvd-rus-Cyrl-Latn-2010.yaml +4 -4
- data/maps/nil-kor-Hang-Hang-jamo.yaml +3 -3
- data/maps/odni-aze-Cyrl-Latn-2015.yaml +1 -1
- data/maps/odni-bel-Cyrl-Latn-2015.yaml +1 -1
- data/maps/odni-bul-Cyrl-Latn-2015.yaml +3 -3
- data/maps/odni-hin-Deva-Latn-2015.yaml +258 -0
- data/maps/odni-kat-Geor-Latn-2015.yaml +0 -1
- data/maps/{odni-mkd-cyrl-latn-2015.yaml → odni-mkd-Cyrl-Latn-2015.yaml} +0 -0
- data/maps/odni-rus-Cyrl-Latn-2015.yaml +1 -1
- data/maps/odni-srp-Cyrl-Latn-2015.yaml +2 -2
- data/maps/odni-urd-Arab-Latn-2015.yaml +221 -0
- data/maps/odni-uzb-Cyrl-Latn-2015.yaml +1 -2
- data/maps/royin-tha-Thai-Latn-1939-generic.yaml +4 -4
- data/maps/royin-tha-Thai-Latn-1968.yaml +4 -4
- data/maps/royin-tha-Thai-Latn-1999-chained.yaml +4 -4
- data/maps/royin-tha-Thai-Latn-1999.yaml +3 -3
- data/maps/{ses-ara-arab-latn-1930.yaml → ses-ara-Arab-Latn-1930.yaml} +7 -3
- data/maps/un-ara-Arab-Latn-1971.yaml +16 -4
- data/maps/un-ara-Arab-Latn-1972.yaml +14 -7
- data/maps/un-ara-Arab-Latn-2017.yaml +56 -19
- data/maps/un-bel-Cyrl-Latn-2007.yaml +3 -3
- data/maps/un-ell-Grek-Latn-1987-tl.yaml +1 -2
- data/maps/un-ell-Grek-Latn-1987-ts.yaml +0 -1
- data/maps/un-ell-Grek-Latn-phonetic-1987.yaml +42 -42
- data/maps/un-mon-Mong-Latn-2013.yaml +9 -3
- data/maps/un-nep-Deva-Latn-1972.yaml +163 -0
- data/maps/un-rus-Cyrl-Latn-1987.yaml +1 -1
- data/maps/{un-ukr-cyrl-latn-1998.yaml → un-ukr-Cyrl-Latn-1998.yaml} +1 -1
- data/maps/ungegn-amh-Ethi-Latn-2016.yaml +575 -0
- data/maps/var-kor-Hang-Latn-mr-1939.yaml +2 -2
- data/maps/var-kor-Kore-Hang-2013.yaml +1 -1
- data/maps/var-kor-Kore-Latn-mr-1939.yaml +1 -2
- data/maps/var-tha-Thai-Thai-phonemic.yaml +5 -5
- data/maps/var-tha-Thai-Zsym-ipa.yaml +12 -12
- data/maps/var-zho-Hani-Latn-1979.yaml +7 -7
- metadata +41 -15
@@ -0,0 +1,156 @@
|
|
1
|
+
---
|
2
|
+
authority_id: bis
|
3
|
+
id: 1991
|
4
|
+
language: ben
|
5
|
+
source_script: Beng
|
6
|
+
destination_script: Latn
|
7
|
+
name: Indian script code for information interchange - ISCII - Bengali Romanization
|
8
|
+
#url:
|
9
|
+
creation_date: 1991
|
10
|
+
description: |
|
11
|
+
IS 13194 (1991): Indian script code for information
|
12
|
+
interchange - ISCII [LITD 20: Indian Language Technologies
|
13
|
+
and Products]
|
14
|
+
|
15
|
+
notes:
|
16
|
+
- |
|
17
|
+
Exception: Anusvāra is transliterated by:
|
18
|
+
|
19
|
+
a) ṅ before gutturals,
|
20
|
+
b) ñ before palatals,
|
21
|
+
c) ṇ before cerebrals,
|
22
|
+
d) n before dentals, and
|
23
|
+
e) m before labials.
|
24
|
+
|
25
|
+
tests:
|
26
|
+
- source: "টিকা"
|
27
|
+
expected: "ṭikā"
|
28
|
+
- source: "শুরু"
|
29
|
+
expected: "śuru"
|
30
|
+
- source: "করোনাভাইরাসের উপসর্গ রয়েছে এমন ভ্রমণকারীদের শনাক্ত করতেই এ ব্যবস্থা নেওয়া হয়"
|
31
|
+
expected: "krŏnābhāirāsēr upsrg rẏēchē ēmn bhrmṇkārīdēr śnākt krtēi ē bybsthā nēŏẏā hẏ"
|
32
|
+
- source: "চীন এ ভাইরাসের সংক্রমণ ছড়িয়ে পড়ার বিষয়টি নিশ্চিত করার পর এ অঞ্চলের দেশগুলো নিজেদের বন্দরগুলোতে নজরদারি শুরু করে"
|
33
|
+
expected: "cīn ē bhāirāsēr sṅkrmṇ chd̂iẏē pd̂ār biṣẏṭi niścit krār pr ē añclēr dēśgulŏ nijēdēr bndrgulŏtē njrdāri śuru krē"
|
34
|
+
- source: "আপনার কি মনে হয়, দক্ষিণ এশিয়ার দেশগুলো সফলভাবে এ সুযোগের সদ্ব্যবহার করতে পেরেছে?"
|
35
|
+
expected: "āpnār ki mnē hẏ, dkṣiṇ ēśiẏār dēśgulŏ sphlbhābē ē suyŏgēr sdbybhār krtē pērēchē?"
|
36
|
+
- source: "এরপর এ ভাইরাসের সংক্রমণ দক্ষিণ এশিয়ায় ছড়িয়ে পড়ার আগে এ অঞ্চলের দেশগুলো চলতি বছরের শুরুর দিকে মহামারি মোকাবিলায় কয়েক মাস সময় পেয়েছিল"
|
37
|
+
expected: "ērpr ē bhāirāsēr sṅkrmṇ dkṣiṇ ēśiẏāẏ chd̂iẏē pd̂ār āgē ē añclēr dēśgulŏ clti bchrēr śurur dikē mhāmāri mŏkābilāẏ kẏēk mās smẏ pēẏēchil"
|
38
|
+
- source: "ন্যূনতম শেয়ার না থাকলে ছাড়তেই হবে পরিচালক পদ"
|
39
|
+
expected: "nyūntm śēẏār nā thāklē chād̂tēi hbē pricālk pd"
|
40
|
+
- source: "বিজন কুমার শীলের ‘ওয়ার্ক পারমিট’ পেতে অনিশ্চয়তা"
|
41
|
+
expected: "bijn kumār śīlēr ‘ŏẏārk pārmiṭ’ pētē aniścẏtā"
|
42
|
+
- source: "বাংলাদেশে হার্ড ইমিউনিটি তৈরি হওয়ার তথ্য–প্রমাণ মেলেনি"
|
43
|
+
expected: "bāṃlādēśē hārḍ imiuniṭi tairi hŏẏār tthy–prmāṇ mēlēni"
|
44
|
+
- source: "চীনে গত বছর করোনাভাইরাসের মহামারির সূত্রপাত হয়"
|
45
|
+
expected: "cīnē gt bchr krŏnābhāirāsēr mhāmārir sūtrpāt hẏ"
|
46
|
+
map:
|
47
|
+
|
48
|
+
rules:
|
49
|
+
# note
|
50
|
+
- pattern: \u0982(?=[কখগঘঙ])
|
51
|
+
result: ṅ
|
52
|
+
- pattern: \u0982(?=[চছজঝঞ])
|
53
|
+
result: ñ
|
54
|
+
- pattern: \u0982(?=[টঠডড়ঢঢ়ণ])
|
55
|
+
result: ṇ
|
56
|
+
- pattern: \u0982(?=[তৎথদধন])
|
57
|
+
result: n
|
58
|
+
- pattern: \u0982(?=[পফবভম])
|
59
|
+
result: m
|
60
|
+
|
61
|
+
|
62
|
+
characters:
|
63
|
+
'অ': 'a'
|
64
|
+
'আ': 'ā'
|
65
|
+
'ই': 'i'
|
66
|
+
'ঈ': 'ī'
|
67
|
+
'উ': 'u'
|
68
|
+
'ঊ': 'ū'
|
69
|
+
'ৠ': 'ṛ'
|
70
|
+
'ঌ': 'ḻ'
|
71
|
+
'এ': 'ē'
|
72
|
+
'ঐ': 'ai'
|
73
|
+
'ও': 'ŏ'
|
74
|
+
'ঔ': 'au'
|
75
|
+
|
76
|
+
# II. Consonants (see Note 2)
|
77
|
+
# Gutturals
|
78
|
+
'ক': 'k'
|
79
|
+
'খ': 'kh'
|
80
|
+
'গ': 'g'
|
81
|
+
'ঘ': 'gh'
|
82
|
+
'ঙ': 'ṅ'
|
83
|
+
|
84
|
+
# Palatals
|
85
|
+
'চ': 'c'
|
86
|
+
'ছ': 'ch'
|
87
|
+
'জ': 'j'
|
88
|
+
'ঝ': 'jh'
|
89
|
+
'ঞ': 'ñ'
|
90
|
+
|
91
|
+
# Cerebrals
|
92
|
+
'ট': 'ṭ'
|
93
|
+
'ঠ': 'ṭh'
|
94
|
+
'ড': 'ḍ'
|
95
|
+
'ড়': 'd̂'
|
96
|
+
'ঢ': 'ḍh'
|
97
|
+
'ঢ়': 'd̂h'
|
98
|
+
'ণ': 'ṇ'
|
99
|
+
|
100
|
+
# Dentals
|
101
|
+
'ত': 't'
|
102
|
+
'ৎ': 't'
|
103
|
+
'থ': 'th'
|
104
|
+
'দ': 'd'
|
105
|
+
'ধ': 'dh'
|
106
|
+
'ন': 'n'
|
107
|
+
|
108
|
+
# Labials
|
109
|
+
'প': 'p'
|
110
|
+
'ফ': 'ph'
|
111
|
+
'ব': 'b'
|
112
|
+
'ভ': 'bh'
|
113
|
+
'ম': 'm'
|
114
|
+
|
115
|
+
# Semivowels
|
116
|
+
'য': 'y'
|
117
|
+
'য়': 'ẏ'
|
118
|
+
'য়': 'ẏ'
|
119
|
+
'র': 'r'
|
120
|
+
'ল': 'l'
|
121
|
+
|
122
|
+
# Sibilants
|
123
|
+
'শ': 'ś'
|
124
|
+
'ষ': 'ṣ'
|
125
|
+
'স': 's'
|
126
|
+
|
127
|
+
|
128
|
+
# Aspirate
|
129
|
+
'হ': 'h'
|
130
|
+
|
131
|
+
# Chandrabindu
|
132
|
+
'ঁ': 'm'
|
133
|
+
|
134
|
+
# Bisarga
|
135
|
+
'ঃ ': 'ḥ'
|
136
|
+
|
137
|
+
# Anusvāra
|
138
|
+
'ং': 'ṃ'
|
139
|
+
|
140
|
+
# Medials # Needed for connecting constants
|
141
|
+
|
142
|
+
'\u09be': 'ā'
|
143
|
+
'\u09bf': 'i'
|
144
|
+
'\u09c0': 'ī'
|
145
|
+
'\u09c1': 'u'
|
146
|
+
'\u09c2': 'ū'
|
147
|
+
'\u09c3': 'ṛ'
|
148
|
+
'\u09c7': 'ē'
|
149
|
+
'\u09c8': 'ai'
|
150
|
+
'\u09cb': 'ŏ'
|
151
|
+
'\u09cc': 'au'
|
152
|
+
'\u09CD': '' # Used for joining
|
153
|
+
'्': ''
|
154
|
+
'़': ''
|
155
|
+
'।': '.'
|
156
|
+
"": ''# Used for joining
|
@@ -0,0 +1,184 @@
|
|
1
|
+
---
|
2
|
+
authority_id: bis
|
3
|
+
id: 1991
|
4
|
+
language: dev
|
5
|
+
source_script: Deva
|
6
|
+
destination_script: Latn
|
7
|
+
name: Indian script code for information interchange - ISCII - Devanagri Romanization
|
8
|
+
#url:
|
9
|
+
creation_date: 1991
|
10
|
+
description: |
|
11
|
+
IS 13194 (1991): Indian script code for information
|
12
|
+
interchange - ISCII [LITD 20: Indian Language Technologies
|
13
|
+
and Products]
|
14
|
+
|
15
|
+
notes:
|
16
|
+
- |
|
17
|
+
Exception: Anusvāra is transliterated by:
|
18
|
+
|
19
|
+
a) ṅ before gutturals,
|
20
|
+
b) ñ before palatals,
|
21
|
+
c) ṇ before cerebrals,
|
22
|
+
d) n before dentals, and
|
23
|
+
e) m before labials.
|
24
|
+
|
25
|
+
tests:
|
26
|
+
- source: "हम"
|
27
|
+
expected: "hm"
|
28
|
+
- source: "मीन"
|
29
|
+
expected: "mīn"
|
30
|
+
- source: "औसत"
|
31
|
+
expected: "aust"
|
32
|
+
- source: "माँ"
|
33
|
+
expected: "mām"
|
34
|
+
- source: "ट्रंप बोले, चीन को देश बेच देगा बिडेन परिवार, वैक्सीन लाने की कोशिशों में अड़ंगा डालने का लगाया आरोप"
|
35
|
+
expected: "ṭrmp bōlē, cīn kō dēś bēc dēgā biḍēn privār, vaiksīn lānē kī kōśiśōṃ mēṃ aḍṅgā ḍālnē kā lgāyā ārōp"
|
36
|
+
- source: "चालबाज चीन से तनातनी के बीच पश्चिमी मोर्चे को लगातार मजबूत कर रही वायुसेना"
|
37
|
+
expected: "cālbāj cīn sē tnātnī kē bīc pścimī mōrcē kō lgātār mjbūt kr rhī vāyusēnā"
|
38
|
+
- source: "चीन ने पांचों भारतीय नागरिकों को रिहा किया, PLA ने किया था अगवा"
|
39
|
+
expected: "cīn nē pāñcōṃ bhārtīy nāgrikōṃ kō rihā kiyā, PLA nē kiyā thā agvā"
|
40
|
+
- source: "पूर्व नौसेना अधिकारी मदन शर्मा से रक्षा मंत्री राजनाथ सिंह ने की बात, कहा- ऐसे हमले हैं अस्वीकार्य"
|
41
|
+
expected: "pūrv nausēnā adhikārī mdn śrmā sē rkṣā mntrī rājnāth siṃh nē kī bāt, khā- aisē hmlē haiṃ asvīkāry"
|
42
|
+
- source: "सात दिन बाद ही छोड़ दिया ससुराल"
|
43
|
+
expected: "sāt din bād hī chōd̂ diyā ssurāl"
|
44
|
+
- source: "राजस्थान में फिर खींचतान, पायलट ने गहलोत को लिखा पत्र, याद दिलाया घोषणा-पत्र, कहा- नाखुश है गुर्जर समाज"
|
45
|
+
expected: "rājsthān mēṃ phir khīñctān, pāylṭ nē ghlōt kō likhā ptr, yād dilāyā ghōṣṇā-ptr, khā- nākhuś hai gurjr smāj"
|
46
|
+
|
47
|
+
map:
|
48
|
+
|
49
|
+
rules:
|
50
|
+
# note
|
51
|
+
- pattern: \u0902(?=[कखगघङ])
|
52
|
+
result: ṅ
|
53
|
+
- pattern: \u0902(?=[चछजझञ])
|
54
|
+
result: ñ
|
55
|
+
- pattern: \u0902(?=[टठडढण])
|
56
|
+
result: ṇ
|
57
|
+
- pattern: \u0902(?=[तथदधन])
|
58
|
+
result: n
|
59
|
+
- pattern: \u0902(?=[पफबभम])
|
60
|
+
result: m
|
61
|
+
|
62
|
+
|
63
|
+
characters:
|
64
|
+
'अ': 'a'
|
65
|
+
'आ': 'ā'
|
66
|
+
'इ': 'i'
|
67
|
+
'ई': 'ī'
|
68
|
+
'उ': 'u'
|
69
|
+
'ऊ': 'ū'
|
70
|
+
'ऋ': 'ṛ'
|
71
|
+
'ॠ': 'ṝ'
|
72
|
+
'ऌ': 'ḻ'
|
73
|
+
'ॡ': 'ḹ'
|
74
|
+
|
75
|
+
'ए': 'ē'
|
76
|
+
'ऐ': 'ai'
|
77
|
+
'ऍ': 'ê'
|
78
|
+
|
79
|
+
'ऒ': 'o'
|
80
|
+
'ओ': 'ŏ'
|
81
|
+
'औ': 'au'
|
82
|
+
'ऑ': 'ô'
|
83
|
+
|
84
|
+
# II. Consonants (see Note 2)
|
85
|
+
# Gutturals
|
86
|
+
'क': 'k'
|
87
|
+
'ख': 'kh'
|
88
|
+
'ग': 'g'
|
89
|
+
'घ': 'gh'
|
90
|
+
'ङ': 'ṅ'
|
91
|
+
|
92
|
+
# Palatals
|
93
|
+
'च': 'c'
|
94
|
+
'छ': 'ch'
|
95
|
+
'ज': 'j'
|
96
|
+
'झ': 'jh'
|
97
|
+
'ञ': 'ñ'
|
98
|
+
|
99
|
+
# Cerebrals
|
100
|
+
'ट': 'ṭ'
|
101
|
+
'ठ': 'ṭh'
|
102
|
+
'ड': 'ḍ'
|
103
|
+
'ढ': 'ḍh'
|
104
|
+
'ण': 'ṇ'
|
105
|
+
|
106
|
+
# Dentals
|
107
|
+
'त': 't'
|
108
|
+
'थ': 'th'
|
109
|
+
'द': 'd'
|
110
|
+
'ध': 'dh'
|
111
|
+
'न': 'n'
|
112
|
+
'ऩ': 'ṉ'
|
113
|
+
|
114
|
+
# Labials
|
115
|
+
'प': 'p'
|
116
|
+
'फ': 'ph'
|
117
|
+
'ब': 'b'
|
118
|
+
'भ': 'bh'
|
119
|
+
'म': 'm'
|
120
|
+
|
121
|
+
# Semivowels
|
122
|
+
'य': 'y'
|
123
|
+
'य़': 'ẏ'
|
124
|
+
'र': 'r'
|
125
|
+
'ऱ': 'ṟ'
|
126
|
+
'ल': 'l'
|
127
|
+
'ळ': 'ḷ'
|
128
|
+
'ऴ': 'ẕ'
|
129
|
+
|
130
|
+
|
131
|
+
'व': 'v'
|
132
|
+
|
133
|
+
# Sibilants
|
134
|
+
'श': 'ś'
|
135
|
+
'ष': 'ṣ'
|
136
|
+
'स': 's'
|
137
|
+
|
138
|
+
|
139
|
+
# Aspirate
|
140
|
+
'ह': 'h'
|
141
|
+
|
142
|
+
|
143
|
+
#Nukta Constants
|
144
|
+
|
145
|
+
'क़': 'q'
|
146
|
+
'ख़': 'ḵẖ'
|
147
|
+
'ग़': 'gẖ'
|
148
|
+
'ज़': 'z'
|
149
|
+
'ड़': 'd̂'
|
150
|
+
'ढ़': 'd̂h'
|
151
|
+
'फ़': 'f'
|
152
|
+
|
153
|
+
# Chandrabindu
|
154
|
+
'ँ': 'm'
|
155
|
+
|
156
|
+
# Bisarga
|
157
|
+
'ः ': 'ḥ'
|
158
|
+
|
159
|
+
# Anusvāra
|
160
|
+
'ं': 'ṃ'
|
161
|
+
|
162
|
+
# Medials # Needed for connecting constants
|
163
|
+
'ा': "ā"
|
164
|
+
'ि': "i"
|
165
|
+
'ी': "ī"
|
166
|
+
'ु': "u"
|
167
|
+
'ू': "ū"
|
168
|
+
'ृ': "ṛ"
|
169
|
+
|
170
|
+
|
171
|
+
'ॆ': "e"
|
172
|
+
'े': "ē"
|
173
|
+
'ै': "ai"
|
174
|
+
'ॅ': "ê"
|
175
|
+
|
176
|
+
|
177
|
+
'ॊ': 'o'
|
178
|
+
'ो': 'ō'
|
179
|
+
'ौ': 'au'
|
180
|
+
'ॉ': 'ô'
|
181
|
+
'्': ''
|
182
|
+
'़': ''
|
183
|
+
'।': '.'
|
184
|
+
"": '' # no need for zero with joiner
|
@@ -0,0 +1,166 @@
|
|
1
|
+
---
|
2
|
+
authority_id: bis
|
3
|
+
id: 1991
|
4
|
+
language: gjr
|
5
|
+
source_script: Gujr
|
6
|
+
destination_script: Latn
|
7
|
+
name: Indian script code for information interchange - ISCII - Gujrati Romanization
|
8
|
+
#url:
|
9
|
+
creation_date: 1991
|
10
|
+
description: |
|
11
|
+
IS 13194 (1991): Indian script code for information
|
12
|
+
interchange - ISCII [LITD 20: Indian Language Technologies
|
13
|
+
and Products]
|
14
|
+
|
15
|
+
notes:
|
16
|
+
- |
|
17
|
+
Exception: Anusvāra is transliterated by:
|
18
|
+
|
19
|
+
a) ṅ before gutturals,
|
20
|
+
b) ñ before palatals,
|
21
|
+
c) ṇ before cerebrals,
|
22
|
+
d) n before dentals, and
|
23
|
+
e) m before labials.
|
24
|
+
|
25
|
+
tests:
|
26
|
+
- source: "અમિત શાહનો કોરોના રિપોર્ટ 2 ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી"
|
27
|
+
expected: "amit śāhnŏ kŏrŏnā ripŏrṭ 2 ŏgsṭē pŏjhiṭiv āvyŏ htŏ, tyārthī tēmnuṃ svāsthy sāruṃ nthī"
|
28
|
+
- source: "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો"
|
29
|
+
expected: "mēdāntā hŏspiṭlmāṃ tēmnŏ ilāj cālī rhyŏ htŏ"
|
30
|
+
- source: "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો"
|
31
|
+
expected: "bhārtnā viśvnāthn ānndē śēnyānmāṃ phēlŏ phiḍē śtrñj viśv kp jītyŏ"
|
32
|
+
- source: "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ 40 લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું"
|
33
|
+
expected: "bhārtīy vḍā prdhān jvāhrlāl nēhruē 40 lākh hinduŏ anē muslmānŏnā pārsprik sthānāntrṇnuṃ sūcn āpyuṃ"
|
34
|
+
- source: "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન 58 ડિગ્રી સેલ્સિયસ હતું."
|
35
|
+
expected: "libiyānā ēl ajijiyāmāṃ dhrtī pr sauthī vdhu tāpmān nŏndhāyuṃ. ē vkhtē chāyāmāṃ nŏndhvāmāṃ āvēluṃ tāpmān 58 ḍigrī sēlsiys htuṃ."
|
36
|
+
- source: "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી"
|
37
|
+
expected: "prthm viśvyuddhḥ jrmnī anē phrāns vccē ēsnēnī lḍāī śrū thī htī"
|
38
|
+
- source: "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું."
|
39
|
+
expected: "ēnglŏ-mistr yuddhḥ tēl al kēbirnuṃ yuddh lḍvāmāṃ āvyuṃ htuṃ."
|
40
|
+
- source: "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા"
|
41
|
+
expected: "purāvā n htā, ē j kārṇē kēs cālyŏ nhīṃ, pṇ tēmnē njrkēd rākhvāmāṃ āvyā"
|
42
|
+
- source: "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; 91 વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ"
|
43
|
+
expected: "srdār pṭēlē nkkī kryuṃ htuṃ kē kāśmīr bhārtnŏ hissŏ bnśē; 91 vrṣ phēlāṃ lāhŏr jēlmāṃ bhūkhhḍtāḷ drmiyān śhīd thyā htā jtīn dās"
|
44
|
+
- source: "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે"
|
45
|
+
expected: "kŏrŏnā prŏṭŏkŏl vccē ājē mēḍikl prvēś prīkṣā lēvāśēḥ ēnṭrī ṭc phrī rhēśē, ēḍmiṭ kārḍ bār kŏḍthī cēk thśē"
|
46
|
+
|
47
|
+
|
48
|
+
|
49
|
+
map:
|
50
|
+
|
51
|
+
rules:
|
52
|
+
# note
|
53
|
+
- pattern: \u0A82(?=[કખગઘઙ])
|
54
|
+
result: ṅ
|
55
|
+
- pattern: \u0A82(?=[ચછજઝઞ])
|
56
|
+
result: ñ
|
57
|
+
- pattern: \u0A82(?=[ટઠડઢણ])
|
58
|
+
result: ṇ
|
59
|
+
- pattern: \u0A82(?=[તથદધન])
|
60
|
+
result: n
|
61
|
+
- pattern: \u0A82(?=[પફબભમ])
|
62
|
+
result: m
|
63
|
+
|
64
|
+
|
65
|
+
characters:
|
66
|
+
'અ': 'a'
|
67
|
+
'આ': 'ā'
|
68
|
+
'ઇ': 'i'
|
69
|
+
'ઈ': 'ī'
|
70
|
+
'ઉ': 'u'
|
71
|
+
'ઊ': 'ū'
|
72
|
+
# 'ઋ': 'ṛ'
|
73
|
+
'ઌ': 'ḻ'
|
74
|
+
|
75
|
+
'ઍ': 'e'
|
76
|
+
'એ': 'ē'
|
77
|
+
'ઐ': 'ai'
|
78
|
+
|
79
|
+
'ઑ': 'o'
|
80
|
+
'ઓ': 'ŏ'
|
81
|
+
'ઔ': 'au'
|
82
|
+
|
83
|
+
# II. Consonants (see Note 2)
|
84
|
+
# Gutturals
|
85
|
+
'ક': 'k'
|
86
|
+
'ખ': 'kh'
|
87
|
+
'ગ': 'g'
|
88
|
+
'ઘ': 'gh'
|
89
|
+
'ઙ': 'ṅ'
|
90
|
+
|
91
|
+
# Palatals
|
92
|
+
'ચ': 'c'
|
93
|
+
'છ': 'ch'
|
94
|
+
'જ': 'j'
|
95
|
+
'ઝ': 'jh'
|
96
|
+
'ઞ': 'ñ'
|
97
|
+
|
98
|
+
# Cerebrals
|
99
|
+
'ટ': 'ṭ'
|
100
|
+
'ઠ': 'ṭh'
|
101
|
+
'ડ': 'ḍ'
|
102
|
+
'ઢ': 'ḍh'
|
103
|
+
'ણ': 'ṇ'
|
104
|
+
|
105
|
+
# Dentals
|
106
|
+
'ત': 't'
|
107
|
+
'થ': 'th'
|
108
|
+
'દ': 'd'
|
109
|
+
'ધ': 'dh'
|
110
|
+
'ન': 'n'
|
111
|
+
|
112
|
+
# Labials
|
113
|
+
'પ': 'p'
|
114
|
+
'ફ': 'ph'
|
115
|
+
'બ': 'b'
|
116
|
+
'ભ': 'bh'
|
117
|
+
'મ': 'm'
|
118
|
+
|
119
|
+
# Semivowels
|
120
|
+
'ય': 'y'
|
121
|
+
'ર': 'r'
|
122
|
+
'લ': 'l'
|
123
|
+
'ળ': 'ḷ'
|
124
|
+
'વ': 'v'
|
125
|
+
|
126
|
+
# Sibilants
|
127
|
+
'શ': 'ś'
|
128
|
+
'ષ': 'ṣ'
|
129
|
+
'સ': 's'
|
130
|
+
|
131
|
+
|
132
|
+
# Aspirate
|
133
|
+
'હ': 'h'
|
134
|
+
|
135
|
+
# Chandrabindu
|
136
|
+
'ઁ': 'm'
|
137
|
+
|
138
|
+
# Bisarga
|
139
|
+
'ઃ': 'ḥ'
|
140
|
+
|
141
|
+
# Anusvāra
|
142
|
+
'ં': 'ṃ'
|
143
|
+
|
144
|
+
# Medials # Needed for connecting constants
|
145
|
+
|
146
|
+
'ા': 'ā'
|
147
|
+
'િ': 'i'
|
148
|
+
'ી': 'ī'
|
149
|
+
'ુ': 'u'
|
150
|
+
'ૂ': 'ū'
|
151
|
+
'ૃ': 'ṛ'
|
152
|
+
#'ૄ': 'ṛr'
|
153
|
+
'ૅ': 'e'
|
154
|
+
'ે': 'ē'
|
155
|
+
'ૈ': 'ai'
|
156
|
+
'ૉ': 'o'
|
157
|
+
'ો': 'ŏ'
|
158
|
+
'ૌ': 'au'
|
159
|
+
|
160
|
+
|
161
|
+
|
162
|
+
'\u09CD': '' # Used for joining
|
163
|
+
'્': ''
|
164
|
+
'઼': ''
|
165
|
+
'।': '.'
|
166
|
+
"": ''# Used for joining
|