libpostal-sys 0.1.1

Low-level wrappers for libpostal address normalization (with locks to support thread-safe initialization)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119


#include "unicode_scripts.h"

typedef struct script_transliteration_rule {
    script_language_t script_language;
    transliterator_index_t index;
} script_transliteration_rule_t;

script_transliteration_rule_t script_transliteration_rules[] = {
    {{SCRIPT_THAANA, ""}, {0, 2}},
    {{SCRIPT_TELUGU, ""}, {2, 1}},
    {{SCRIPT_CYRILLIC, "be"}, {3, 1}},
    {{SCRIPT_CYRILLIC, "bg"}, {4, 1}},
    {{SCRIPT_CYRILLIC, "ru"}, {5, 1}},
    {{SCRIPT_CYRILLIC, ""}, {6, 1}},
    {{SCRIPT_CYRILLIC, "uz"}, {7, 1}},
    {{SCRIPT_CYRILLIC, "kk"}, {8, 1}},
    {{SCRIPT_CYRILLIC, "sr"}, {9, 1}},
    {{SCRIPT_CYRILLIC, "mn"}, {10, 1}},
    {{SCRIPT_CYRILLIC, "mk"}, {11, 1}},
    {{SCRIPT_CYRILLIC, "uk"}, {12, 1}},
    {{SCRIPT_CYRILLIC, "ky"}, {13, 1}},
    {{SCRIPT_HANGUL, ""}, {14, 1}},
    {{SCRIPT_HAN, ""}, {15, 1}},
    {{SCRIPT_ARMENIAN, ""}, {16, 1}},
    {{SCRIPT_TAMIL, ""}, {17, 1}},
    {{SCRIPT_MALAYALAM, ""}, {18, 1}},
    {{SCRIPT_GUJARATI, ""}, {19, 1}},
    {{SCRIPT_LATIN, ""}, {20, 1}},
    {{SCRIPT_LATIN, "nb"}, {21, 2}},
    {{SCRIPT_LATIN, "de"}, {23, 1}},
    {{SCRIPT_LATIN, "sv"}, {24, 2}},
    {{SCRIPT_LATIN, "da"}, {26, 2}},
    {{SCRIPT_LATIN, "et"}, {28, 1}},
    {{SCRIPT_GEORGIAN, ""}, {29, 2}},
    {{SCRIPT_DEVANAGARI, ""}, {31, 1}},
    {{SCRIPT_THAI, ""}, {32, 1}},
    {{SCRIPT_GREEK, ""}, {33, 3}},
    {{SCRIPT_KATAKANA, ""}, {36, 2}},
    {{SCRIPT_ORIYA, ""}, {38, 1}},
    {{SCRIPT_HIRAGANA, ""}, {39, 1}},
    {{SCRIPT_ARABIC, "fa"}, {40, 1}},
    {{SCRIPT_ARABIC, ""}, {41, 2}},
    {{SCRIPT_ARABIC, "ps"}, {43, 1}},
    {{SCRIPT_CANADIAN_ABORIGINAL, ""}, {44, 1}},
    {{SCRIPT_BENGALI, ""}, {45, 1}},
    {{SCRIPT_GURMUKHI, ""}, {46, 1}},
    {{SCRIPT_KANNADA, ""}, {47, 1}},
    {{SCRIPT_COMMON, ""}, {48, 1}},
    {{SCRIPT_COMMON, "nb"}, {49, 2}},
    {{SCRIPT_COMMON, "de"}, {51, 1}},
    {{SCRIPT_COMMON, "sv"}, {52, 2}},
    {{SCRIPT_COMMON, "da"}, {54, 2}},
    {{SCRIPT_COMMON, "et"}, {56, 1}},
    {{SCRIPT_HEBREW, ""}, {57, 2}}
};

char *script_transliterators[] = {
    "thaana-latin",
    "maldivian-latin-bgn",
    "telugu-latin",
    "belarusian-latin-bgn",
    "bulgarian-latin-bgn",
    "russian-latin-bgn",
    "cyrillic-latin",
    "uzbek-latin-bgn",
    "kazakh-latin-bgn",
    "serbian-latin-bgn",
    "mongolian-latin-bgn",
    "macedonian-latin-bgn",
    "ukrainian-latin-bgn",
    "kirghiz-latin-bgn",
    "hangul-latin",
    "han-latin",
    "armenian-latin-bgn",
    "tamil-latin",
    "malayalam-latin",
    "gujarati-latin",
    "latin-ascii",
    "scandinavian-ascii",
    "latin-ascii",
    "german-ascii",
    "scandinavian-ascii",
    "latin-ascii",
    "scandinavian-ascii",
    "latin-ascii",
    "german-ascii",
    "georgian-latin",
    "georgian-latin-bgn",
    "devanagari-latin",
    "thai-latin",
    "greek-latin",
    "greek-latin-bgn",
    "greek-latin-ungegn",
    "katakana-latin",
    "katakana-latin-bgn",
    "oriya-latin",
    "hiragana-latin",
    "persian-latin-bgn",
    "arabic-latin",
    "arabic-latin-bgn",
    "pashto-latin-bgn",
    "canadianaboriginal-latin",
    "bengali-latin",
    "gurmukhi-latin",
    "kannada-latin",
    "latin-ascii",
    "scandinavian-ascii",
    "latin-ascii",
    "german-ascii",
    "scandinavian-ascii",
    "latin-ascii",
    "scandinavian-ascii",
    "latin-ascii",
    "german-ascii",
    "hebrew-latin",
    "hebrew-latin-bgn"
};