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
File without changes
|
@@ -35,7 +35,7 @@ description: |
|
|
35
35
|
time been listed in the Factbook or Chiefs of State directory but who no longer appears in those resources
|
36
36
|
(i.e. is no longer a government official), the IC Standard spelling should appear first, with the spelling, if
|
37
37
|
known, as it previously appeared in those resources listed within parentheses at the first usage.
|
38
|
-
|
38
|
+
|
39
39
|
The primary goal is to produce a consistent Romanized transcription of names that is specifically readable
|
40
40
|
to the English-speaking non-specialist. The system uses the 26 letters of the standard (English) Roman
|
41
41
|
alphabet. Some ambiguities in the Romanized form will occur without the use of diacritics. However,
|
@@ -35,14 +35,14 @@ description: |
|
|
35
35
|
longer appears in those resources (i.e. is no longer a government official), the IC Standard
|
36
36
|
spelling should appear first, with the spelling, if known, as it previously appeared in those
|
37
37
|
resources listed within parentheses at the first usage.
|
38
|
-
|
38
|
+
|
39
39
|
The primary goal is to produce a consistent Romanized transcription of names that is specifically
|
40
40
|
readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
|
41
41
|
(English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
|
42
42
|
of diacritics. However, within the context of a report, where additional information about the
|
43
43
|
individual is provided, the referent will be clearly identified. This system will be used in
|
44
44
|
conjunction with on-line tools, name dictionaries, and lists containing conventional spellings of
|
45
|
-
names of well-known individuals.
|
45
|
+
names of well-known individuals.
|
46
46
|
|
47
47
|
notes:
|
48
48
|
|
@@ -0,0 +1,221 @@
|
|
1
|
+
---
|
2
|
+
authority_id: odni
|
3
|
+
id: 2015
|
4
|
+
language: urd
|
5
|
+
source_script: Arab
|
6
|
+
destination_script: Latn
|
7
|
+
name: Office of the Director Of National Intelligence Hindi Urdu Personal Names 2015 System, ICS-630-01 Annex F
|
8
|
+
#url:
|
9
|
+
creation_date: 2015
|
10
|
+
confirmation_date: 2015
|
11
|
+
description: |
|
12
|
+
This system is the Intelligence Community (IC) standard for the transliteration of names
|
13
|
+
from Hindi and Urdu that will be applied to all final written reports and products for IC
|
14
|
+
consumers. It is not intended to eliminate variations of a name that can contribute
|
15
|
+
forensic information. Rather, it is to provide an IC standard Romanized (English)
|
16
|
+
transliteration from standard Hindi and Urdu that can then be linked to forensic
|
17
|
+
information in ways that will help identify the referent of the name.
|
18
|
+
|
19
|
+
There are typically a number of ways that names can be Romanized from either
|
20
|
+
Devanagari (Hindi) or modified Arabic (Urdu) scripts. Ambiguities can result from the
|
21
|
+
Romanization of Hindi and Urdu names for several reasons, including the fact that some
|
22
|
+
sounds in South Asian languages (e.g., retroflex consonants, voiced aspirates) have no
|
23
|
+
equivalent in English or other European languages. In the case of Urdu, as in the original
|
24
|
+
Arabic source of many Islamic names, short vowel markings, double consonant marks
|
25
|
+
and other diacritics that would clearly distinguish the name are almost always omitted
|
26
|
+
from standard written texts. And many Islamic names of Arabic or Persian origin reflect
|
27
|
+
spelling distinctions from those languages that are lost in modern Urdu pronunciation
|
28
|
+
(e.g., three distinct Arabic letters all represent the identical sound [s] for Urdu speakers);
|
29
|
+
transliterations might either maintain those spelling distinctions or ignore them entirely.
|
30
|
+
And, as in the Arabic source, names containing the Arabic definite article ‘al’ (‘ul’) show
|
31
|
+
anticipatory assimilation in pronunciation (e.g., Shams al Din > Shamsuddin);
|
32
|
+
transliterations may either reflect spelling or pronunciation in such cases.
|
33
|
+
|
34
|
+
Because Hindi and Urdu overlap so extensively, it is desirable to correlate Hindi and
|
35
|
+
Urdu transliterations as much as possible. In the area of names, this can become
|
36
|
+
problematic when the Urdu spelling accurately reflects original Arabic spelling while the
|
37
|
+
Hindi spelling was phonetically-based, in essence, already a transliteration. This would
|
38
|
+
argue for ignoring Arabic/Urdu spelling distinctions not reflected in pronunciation in
|
39
|
+
either Urdu or Hindi (e.g., letter sin versus letter sad) while maintaining Arabic/Urdu
|
40
|
+
spelling distinctions like Hindi also maintains (e.g., qaf as in Qutubbin versus kaf)).
|
41
|
+
However, this is not always possible (see Hindi va versus Urdu wau).
|
42
|
+
|
43
|
+
In cases where an individual’s name has already been transliterated, that is to be indicated
|
44
|
+
– as found – in parentheses immediately following its rendition in the transliteration
|
45
|
+
standard (e.g., Muhammad Khulud (Mohamed Khulood)). In addition, if the original
|
46
|
+
Devanagari or Arabic-script spelling is known, that spelling should also appear in
|
47
|
+
parentheses following the name, if possible, following best practices of the issuing
|
48
|
+
organization and taking into consideration information system capabilities. This
|
49
|
+
convention is designed to ensure that vital forensic information is not lost.
|
50
|
+
|
51
|
+
For names of persons who are known to not be part of the Hindi- or Urdu-speaking
|
52
|
+
community, use the relevant IC transliteration standard for names from that language
|
53
|
+
(e.g., Mikhail, Yitzhak). A translator’s note may be used to clarify the known origin of
|
54
|
+
the person. Spell names of individuals from languages that are written in Roman letters as
|
55
|
+
they are spelled in those languages (e.g., George Clooney, Jorge Garcia, Georges
|
56
|
+
Pompidou).
|
57
|
+
|
58
|
+
In the case of active senior government officials in the on-line CIA World Factbook and
|
59
|
+
the on-line directory of Chiefs of State and Cabinet Members of Foreign Governments,
|
60
|
+
the spellings given in these on-line reference works should be used in place of the IC
|
61
|
+
Standard. For any individual who has at one time been listed in the Factbook or Chiefs of
|
62
|
+
State directory but who no longer appears in those resources (i.e. is no longer a
|
63
|
+
government official), the IC Standard spelling should appear first, with the spelling, if
|
64
|
+
known, as it previously appeared in those resources listed within parentheses at the first
|
65
|
+
usage.
|
66
|
+
|
67
|
+
The primary goal of this system is to produce a consistent Romanized transcription of the
|
68
|
+
name that is readable to the non-specialist. The system uses the 26 letters of the standard
|
69
|
+
(English) Roman alphabet. Some ambiguities in the Romanized form will occur without
|
70
|
+
the use of diacritics. However, within the context of a report, where additional
|
71
|
+
information about the individual is provided, the referent will be clearly identified.
|
72
|
+
Additionally, this system will be used in conjunction with on-line tools, name dictionaries
|
73
|
+
and lists containing conventional spellings of names of well-known individuals
|
74
|
+
|
75
|
+
notes:
|
76
|
+
|
77
|
+
- |
|
78
|
+
Long/Short Vowels: Long and short vowels are not distinguished in the system:
|
79
|
+
The borrowed Arabic name Samir could represent two distinct names, one with a
|
80
|
+
long /a/ (Saamir) and one with a long /i/ (Samiir). One solution would be to use
|
81
|
+
/ee/ to stand for the long /i/, as is often done (Sameer). The IC Standard will not
|
82
|
+
distinguish between these.
|
83
|
+
|
84
|
+
- |
|
85
|
+
No distinction is made between: retroflex and non-retroflex consonants; and
|
86
|
+
nasalized vowels and vowels followed by /n/.
|
87
|
+
- |
|
88
|
+
No distinction is made between the several Arabic letters with the same phonetic
|
89
|
+
value in Urdu: e.g., letters sin/svad, zal/ze/zoe.
|
90
|
+
- |
|
91
|
+
A distinction is drawn between Urdu letters qaf and kaf (and correspondingly,
|
92
|
+
Hindi qa and ka).
|
93
|
+
- |
|
94
|
+
A distinction is drawn between aspirated (e.g., /d/) and nonaspirated consonants
|
95
|
+
(e.g., /dh/), with the exception of ch/chh, both represented by /ch/.
|
96
|
+
- |
|
97
|
+
Double consonants: Double consonants represented by the tashdid (shaddah) are
|
98
|
+
shown in most cases (e.g., Hassan, Muhammad). Exceptions: consonants
|
99
|
+
represented by digraphs are not doubled (e.g., Mubashir [not Mubashshir]).
|
100
|
+
- |
|
101
|
+
Hamzah (glottal stop) and ayn: Unlike in the Arabic IC Standard, these are not
|
102
|
+
represented in the IC standard.
|
103
|
+
- |
|
104
|
+
Digraphs: No distinction is made between digraphs such as /sh/ and single
|
105
|
+
contiguous letters such as /s/ followed by /h/.
|
106
|
+
- |
|
107
|
+
Arabic definite article “al” (‘the’): Shows sun letter assimilation in the
|
108
|
+
Romanized form (e.g., Abdur Rahman rather than Abdal Rahman, rather than
|
109
|
+
Arabic IC standard 'Abd al-Rahman).
|
110
|
+
- |
|
111
|
+
Special Rules
|
112
|
+
- |
|
113
|
+
Hyphens: Hyphens (-) are NOT used to connect name elements within a name:
|
114
|
+
Abdur Rahman. The single exception to this is the izafat (i.e., linking vowel in
|
115
|
+
noun-link-modifier construction of Persian origin), which does show a hyphen
|
116
|
+
before the /e/ and a following space: Koh-e Nur (‘mountain of light’), “Jaish-e
|
117
|
+
xx” (‘Army of xx’ construction).
|
118
|
+
- |
|
119
|
+
Names incorporating “din” are written as one unit: Azermuddin, Badruddin,
|
120
|
+
Faizuddin, Salahuddin.
|
121
|
+
- |
|
122
|
+
Names that incorporate Allah as part of the name show the Arabic grammatical
|
123
|
+
marker /u/ rather than the /a/ of Allah: Abdullah (not Abdallah).
|
124
|
+
- |
|
125
|
+
Inherent short vowel /a/ in Devanagari is represented with an /a/ in Roman. Final
|
126
|
+
consonants are assumed not to have a short /a/ (e.g., masc. name Ram Lal, not
|
127
|
+
Rama Lala).
|
128
|
+
- |
|
129
|
+
As a general rule, Devanagari va is transcribed as a /v/: Vijay, Vishal, etc.
|
130
|
+
Exception: /sw/ combination: Saraswati, Krishnaswami. Urdu wau, however, is
|
131
|
+
transcribed as /w/: Wasim, Walid.
|
132
|
+
|
133
|
+
tests:
|
134
|
+
- source: "وشال ٹھاکر"
|
135
|
+
expected: "ishal tsakr"
|
136
|
+
- source: "حسن محمود"
|
137
|
+
expected: "hasn mhamid"
|
138
|
+
- source: "یوسف خان"
|
139
|
+
expected: "iisf khan"
|
140
|
+
- source: "معین خان"
|
141
|
+
expected: "mein khan"
|
142
|
+
- source: "سعید اجمل"
|
143
|
+
expected: "seid ajml"
|
144
|
+
- source: "انضمام الحق"
|
145
|
+
expected: "anzmam alhaq"
|
146
|
+
- source: "فرہاد رضا"
|
147
|
+
expected: "frahad rza"
|
148
|
+
- source: "وسیم اکرام"
|
149
|
+
expected: "isim akram"
|
150
|
+
- source: "شکیب الحسن"
|
151
|
+
expected: "shkib alhasn"
|
152
|
+
- source: "حسن عبد اللہ"
|
153
|
+
expected: "hasn ebd allah"
|
154
|
+
|
155
|
+
map:
|
156
|
+
|
157
|
+
characters:
|
158
|
+
|
159
|
+
|
160
|
+
'\u0622': 'a' # ARABIC ALEF W/MADDA ABOVE
|
161
|
+
'\u0627': 'a' # or u ARABIC ALEF
|
162
|
+
'\u06cc': 'i' # or ai or u ARABIC LETTER WAW
|
163
|
+
'\u0648': 'i' # or o,au ARABIC LETTER FARSI YEH
|
164
|
+
'\u06d2': 'e' # ARABIC LETTER YEH BARREE
|
165
|
+
'\u0650': 'e' # ARABIC ARABIC KASRA
|
166
|
+
'\u0639': 'e' # ARABIC LETTER AIN
|
167
|
+
'\u06c1': 'ah' # ARABIC LETTER HEH GOAL
|
168
|
+
'\u062d': 'ha' # ARABIC LETTER HAH
|
169
|
+
'\u0648\u0670': 'a' # ARABIC LETTER FARSI YEH + ARABIC LETTER SUPERSCRIPT ALEF
|
170
|
+
'\u0670': 'a' # ARABIC LETTER SUPERSCRIPT ALEF
|
171
|
+
'\u0627\u0650': 'i' # ARABIC ALEF + ARABIC KASRA
|
172
|
+
'\u0639\u0650': 'i' # ARABIC LETTER AIN + ARABIC KASRA
|
173
|
+
'\u064f': 'i' # ARABIC DAMMA
|
174
|
+
'\u06d3': 'i' # ARABIC LETTER YEH BARREE WITH HAMZA ABOVE
|
175
|
+
'\u06c2': '-e' # ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
|
176
|
+
'\u06c1\u0650': 'o' # ARABIC LETTER YEH WITH HAMZA ABOVE
|
177
|
+
'\u0624': 'au' # ARABIC LETTER WAW WITH HAMZA ABOVE
|
178
|
+
|
179
|
+
|
180
|
+
|
181
|
+
'\u06a9': 'k' # ARABIC LETTER KEHEH
|
182
|
+
'\u0642': 'q' # ARABIC LETTER QAF
|
183
|
+
'\u062e': 'kh' # ARABIC LETTER KHAH
|
184
|
+
'\u06af': 'g' # ARABIC LETTER GAF
|
185
|
+
'\u063a': 'gh' # ARABIC LETTER GHAIN
|
186
|
+
'\u0686': 'ch' # ARABIC LETTER TCHEH
|
187
|
+
'\u062c': 'j' # Arabic Letter Jeem
|
188
|
+
|
189
|
+
'\u0632': 'z' # Arabic Letter ZAIN
|
190
|
+
'\u0630': 'z' # Arabic Letter THAL
|
191
|
+
'\u0636': 'z' # Arabic Letter DAD
|
192
|
+
'\u0638': 'z' # Arabic Letter ZAH
|
193
|
+
'\u0698': 'zh' # Arabic Letter JEH
|
194
|
+
|
195
|
+
|
196
|
+
'\u0679': 't' # ARABIC LETTER TTEH
|
197
|
+
'\u0688': 'd' # Arabic Letter DDAL
|
198
|
+
'\u062f': 'd' # Arabic Letter DAL
|
199
|
+
'\u0691': 'r' # Arabic Letter RREH
|
200
|
+
'\u062a': 't' # Arabic Letter TEH
|
201
|
+
'\u0637': 't' # Arabic Letter TAH
|
202
|
+
'\u0646': 'n' # Arabic Letter NOON
|
203
|
+
'\u06ba': 'n' # Arabic Letter NOON GHUNNA
|
204
|
+
|
205
|
+
|
206
|
+
'\u067e': 'p' # Arabic Letter PE
|
207
|
+
'\u0641': 'f' # Arabic Letter FEH
|
208
|
+
'\u0628': 'b' # Arabic Letter BEH
|
209
|
+
'\u0645': 'm' # Arabic Letter MEEM
|
210
|
+
'\u0631': 'r' # Arabic Letter REH
|
211
|
+
'\u0644': 'l' # Arabic Letter LAM
|
212
|
+
'\u0634': 'sh' # Arabic Letter SHEEN
|
213
|
+
'\u0633': 's' # Arabic Letter SHEEN
|
214
|
+
'\u062b': 's' # Arabic Letter THEH
|
215
|
+
'\u0635': 's' # Arabic Letter SAD
|
216
|
+
'\u0621': '' # Arabic Letter HAMZA
|
217
|
+
'\u06be': 's' # Arabic Letter HEH DOACHASHMEE
|
218
|
+
'\u064b': 'n' # Arabic Letter FATHATAN
|
219
|
+
'\u064e': 'n' # Arabic sign FATHATAN
|
220
|
+
'\u0652': '' # Arabic Letter SUKUN
|
221
|
+
'\u0651': '' # Arabic Letter SHADDA
|
@@ -36,7 +36,7 @@ description: |
|
|
36
36
|
longer appears in those resources (i.e. is no longer a government official), the IC Standard
|
37
37
|
spelling should appear first, with the spelling, if known, as it previously appeared in those
|
38
38
|
resources listed within parentheses at the first usage.
|
39
|
-
|
39
|
+
|
40
40
|
The primary goal is to produce a consistent Romanized transcription of names that is specifically
|
41
41
|
readable to the English-speaking non-specialist. The system uses the 26 letters of the standard
|
42
42
|
(English) Roman alphabet. Some ambiguities in the Romanized form will occur without the use
|
@@ -164,4 +164,3 @@ map:
|
|
164
164
|
'\u042c': '' # Ь
|
165
165
|
'\u044a': '' # ъ
|
166
166
|
'\u044c': '' # ь
|
167
|
-
|
@@ -7,11 +7,11 @@ destination_script: Latn
|
|
7
7
|
name: Royal Thai General System of Transcription (1939) Generic
|
8
8
|
url: http://www.siamese-heritage.org/jsspdf/1941/JSS_033_1d_RoyalInstituteTranscriptionOfThaiIntoRomanCharacters.pdf
|
9
9
|
creation_date: 1939
|
10
|
-
adoption_date:
|
10
|
+
adoption_date:
|
11
11
|
description: |
|
12
12
|
This map loads two external maps to convert Thai text first into phonemic Thai,
|
13
13
|
and then into IPA transcription.
|
14
|
-
|
14
|
+
|
15
15
|
The IPA transcription will then be handled by this map, and converted into
|
16
16
|
Royal Thai General System of Transcription (1939)
|
17
17
|
|
@@ -37,7 +37,7 @@ chain: ["var-tha-Thai-Thai-phonemic" ,"var-tha-Thai-Zsym-ipa"]
|
|
37
37
|
|
38
38
|
map:
|
39
39
|
title-case: false
|
40
|
-
word_separator: " "
|
40
|
+
word_separator: " "
|
41
41
|
|
42
42
|
rules:
|
43
43
|
- pattern: '[˩˨˧˦˥]'
|
@@ -62,7 +62,7 @@ map:
|
|
62
62
|
'ŋ': 'ng'
|
63
63
|
'j': 'y'
|
64
64
|
'ɔ': 'o̦'
|
65
|
-
'ɤ': 'œ'
|
65
|
+
'ɤ': 'œ'
|
66
66
|
'ɛ': 'æ'
|
67
67
|
'ɯ': 'ư'
|
68
68
|
'ʰ': 'h'
|
@@ -7,11 +7,11 @@ destination_script: Latn
|
|
7
7
|
name: Royal Thai General System of Transcription (1968)
|
8
8
|
url: http://www.royin.go.th/wp-content/uploads/royin-ebook/276/FileUpload/758_6484.pdf
|
9
9
|
creation_date: 1968
|
10
|
-
adoption_date:
|
10
|
+
adoption_date:
|
11
11
|
description: |
|
12
12
|
This map loads two external maps to convert Thai text first into phonemic Thai,
|
13
13
|
and then into IPA transcription.
|
14
|
-
|
14
|
+
|
15
15
|
The IPA transcription will then be handled by this map, and converted into
|
16
16
|
Royal Thai General System of Transcription (1968).
|
17
17
|
|
@@ -124,7 +124,7 @@ chain: ["var-tha-Thai-Thai-phonemic" ,"var-tha-Thai-Zsym-ipa"]
|
|
124
124
|
|
125
125
|
map:
|
126
126
|
title-case: false
|
127
|
-
word_separator: " "
|
127
|
+
word_separator: " "
|
128
128
|
|
129
129
|
rules:
|
130
130
|
- pattern: '[˩˨˧˦˥]'
|
@@ -151,7 +151,7 @@ map:
|
|
151
151
|
'ŋ': 'ng'
|
152
152
|
'j': 'y'
|
153
153
|
'ɔ': 'o'
|
154
|
-
'ɤ': 'oe'
|
154
|
+
'ɤ': 'oe'
|
155
155
|
'ɛ': 'ae'
|
156
156
|
'ɯ': 'u'
|
157
157
|
'ʰ': 'h'
|
@@ -7,11 +7,11 @@ destination_script: Latn
|
|
7
7
|
name: Royal Thai General System of Transcription (1999)
|
8
8
|
url: http://www.royin.go.th/wp-content/uploads/royin-ebook/276/FileUpload/758_6484.pdf
|
9
9
|
creation_date: 1999
|
10
|
-
adoption_date:
|
10
|
+
adoption_date:
|
11
11
|
description: |
|
12
12
|
This map loads two external maps to convert Thai text first into phonemic Thai,
|
13
13
|
and then into IPA transcription.
|
14
|
-
|
14
|
+
|
15
15
|
The IPA transcription will then be handled by this map, and converted into
|
16
16
|
Royal Thai General System of Transcription (1999)
|
17
17
|
|
@@ -125,7 +125,7 @@ chain: ["var-tha-Thai-Thai-phonemic" ,"var-tha-Thai-Zsym-ipa"]
|
|
125
125
|
|
126
126
|
map:
|
127
127
|
title-case: false
|
128
|
-
word_separator: " "
|
128
|
+
word_separator: " "
|
129
129
|
|
130
130
|
rules:
|
131
131
|
- pattern: '[˩˨˧˦˥]'
|
@@ -152,7 +152,7 @@ map:
|
|
152
152
|
'ŋ': 'ng'
|
153
153
|
'j': 'y'
|
154
154
|
'ɔ': 'o'
|
155
|
-
'ɤ': 'oe'
|
155
|
+
'ɤ': 'oe'
|
156
156
|
'ɛ': 'ae'
|
157
157
|
'ɯ': 'ue' # New spelling, was u in 1968
|
158
158
|
'ʰ': 'h'
|
@@ -7,7 +7,7 @@ destination_script: Latn
|
|
7
7
|
name: Royal Thai General System of Transcription (1999)
|
8
8
|
url: http://www.royin.go.th/wp-content/uploads/royin-ebook/276/FileUpload/758_6484.pdf
|
9
9
|
creation_date: 1999
|
10
|
-
adoption_date:
|
10
|
+
adoption_date:
|
11
11
|
description:
|
12
12
|
|
13
13
|
notes: |
|
@@ -48,7 +48,7 @@ tests:
|
|
48
48
|
|
49
49
|
map:
|
50
50
|
title-case: false
|
51
|
-
word_separator: " "
|
51
|
+
word_separator: " "
|
52
52
|
transcription: "sequitur.pythainlp_lexicon"
|
53
53
|
|
54
54
|
rules:
|
@@ -68,7 +68,7 @@ map:
|
|
68
68
|
'j': 'i'
|
69
69
|
'w': 'o'
|
70
70
|
'ɔ': 'o'
|
71
|
-
'ɤ': 'oe'
|
71
|
+
'ɤ': 'oe'
|
72
72
|
'ɛ': 'ae'
|
73
73
|
'ɯ': 'ue'
|
74
74
|
'ʔ' : ''
|
@@ -85,12 +85,16 @@ tests:
|
|
85
85
|
# https://unstats.un.org/unsd/geoinfo/geonames/
|
86
86
|
|
87
87
|
- source: شَرم الشَيْخ
|
88
|
-
expected:
|
88
|
+
expected: Sharm el-Sheikh
|
89
89
|
|
90
90
|
- source: الكَفر القَدِيم
|
91
|
-
expected:
|
91
|
+
expected: El-Kafr el-Qadîm
|
92
92
|
map:
|
93
93
|
inherit: "un-ara-Arab-Latn-2017"
|
94
|
+
postrules:
|
95
|
+
- pattern : ' El-' # الص
|
96
|
+
result: ' el-'
|
97
|
+
|
94
98
|
characters:
|
95
99
|
|
96
100
|
|
@@ -117,7 +121,7 @@ map:
|
|
117
121
|
- 'â'
|
118
122
|
- 'a'
|
119
123
|
|
120
|
-
# ta' marboota
|
124
|
+
# ta' marboota in iso-233-1984 is all the same `a`
|
121
125
|
'\u0629$' : 'a'
|
122
126
|
'(?<=\b\u0627\u0644[\u0600-\u06ff]{2})\u0629' : 'a'
|
123
127
|
'(?<=\b\u0627\u0644[\u0600-\u06ff]{3})\u0629' : 'a'
|
@@ -72,16 +72,29 @@ tests:
|
|
72
72
|
# page 31 (38 digital)
|
73
73
|
|
74
74
|
- source: خَيبَر
|
75
|
-
expected:
|
75
|
+
expected: K͟haybar
|
76
76
|
|
77
77
|
- source: ظَهران
|
78
|
-
expected:
|
78
|
+
expected: Z͟hahrān
|
79
79
|
|
80
80
|
- source: القُدس
|
81
|
-
expected:
|
81
|
+
expected: Al Quds
|
82
|
+
|
83
|
+
- source: شَرم الشَيْخ
|
84
|
+
expected: S͟harm as͟h S͟hayk͟h
|
82
85
|
|
83
86
|
map:
|
84
87
|
inherit: "un-ara-Arab-Latn-2017"
|
88
|
+
map:
|
89
|
+
postrules:
|
90
|
+
- pattern : ' At͟h T͟h' # الث
|
91
|
+
result: ' at͟h T͟h'
|
92
|
+
- pattern : ' Ad͟h D͟h' # الذ
|
93
|
+
result: ' ad͟h D͟h'
|
94
|
+
- pattern : ' As͟h S͟h' # الش
|
95
|
+
result: ' as͟h S͟h'
|
96
|
+
- pattern : ' Az͟h Z͟h' # الظ
|
97
|
+
result: ' az͟h Z͟h'
|
85
98
|
characters:
|
86
99
|
|
87
100
|
# sun letters
|
@@ -124,4 +137,3 @@ map:
|
|
124
137
|
'\ufec7' : 'z͟h' # ﻇ
|
125
138
|
'\ufec8' : 'z͟h' # ﻈ
|
126
139
|
'\ufec6' : 'z͟h' # ﻆ
|
127
|
-
|