interscript-maps 3.2.3 → 3.2.4

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.
@@ -50,6 +50,94 @@ metadata {
50
50
  tests {
51
51
  "Билјана" -> "Biljana"
52
52
  "Душко" -> "Dushko"
53
+ # Exhaustive per-row tests for odni-mkd-Cyrl-Latn-2015, generated from the source
54
+ # document's table.
55
+ # Source: ICS 630-01 Annex H (ANNEX H - Macedonian_Personal_Names_FLTS
56
+ # (U).pdf), p. 2 (letter table); held source
57
+ # interscript-private-references/ics-630-01/ANNEX H -
58
+ # Macedonian_Personal_Names_FLTS (U).pdf. Extraction: annex text layer,
59
+ # every value cell cross-checked against the rendered page image. Each
60
+ # printed cell gives both cases (e.g. "А а | A a"); transcribed as two rows
61
+ # per cell (upper -> upper value, lower -> lower value). The dze row’s
62
+ # letter cell prints "S s" — a substitute-glyph rendering of Cyrillic Ѕ ѕ in
63
+ # this annex (verified visually; the Macedonian alphabet has no Latin S
64
+ # between З and И, and the value Dz dz is the standard dze romanization) —
65
+ # the row is transcribed as Ѕ -> Dz / ѕ -> dz and, failing end-to-end,
66
+ # recorded as a finding. The text layer for the same cell stores "Ss"/"Dz
67
+ # dz". Skipped printed rows: ’ (apostrophe sign) — printed value cell "[Not
68
+ # represented]" — instruction cell, no romanization value. | Ѕ/ѕ (dze) —
69
+ # printed value cell "Dz dz" FAILS end-to-end on the Cyrillic key: the map
70
+ # encodes the annex’s substitute glyphs literally (Latin S/s, U+0053/U+0073
71
+ # -> Dz/dz) while the actual Cyrillic dze letters Ѕ/ѕ (U+0405/U+0455) carry
72
+ # no rule and pass through unchanged ("Ѕ" -> "Ѕ"). Finding, never forced
73
+ # green. Findings (map-vs-source, map untouched): Ѕ/ѕ (U+0405/U+0455):
74
+ # printed row Dz/dz untestable — the map has no rule for the Cyrillic dze
75
+ # letters; it instead maps Latin S/s -> Dz/dz (the annex’s substituted
76
+ # letter cell taken literally), so Cyrillic dze passes through unencoded AND
77
+ # Latin-letter input is silently rewritten to Dz/dz, against the annex’s own
78
+ # convention of spelling Latin-letter names as-is.
79
+ # Provenance artifact: scripts/row-sources/odni-mkd-Cyrl-Latn-2015.json (60 rows).
80
+ # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
81
+ "А" -> "A"
82
+ "а" -> "a"
83
+ "Б" -> "B"
84
+ "б" -> "b"
85
+ "В" -> "V"
86
+ "в" -> "v"
87
+ "Г" -> "G"
88
+ "г" -> "g"
89
+ "Д" -> "D"
90
+ "д" -> "d"
91
+ "Ѓ" -> "Gj"
92
+ "ѓ" -> "gj"
93
+ "Е" -> "E"
94
+ "е" -> "e"
95
+ "Ж" -> "Zh"
96
+ "ж" -> "zh"
97
+ "З" -> "Z"
98
+ "з" -> "z"
99
+ "И" -> "I"
100
+ "и" -> "i"
101
+ "Ј" -> "J"
102
+ "ј" -> "j"
103
+ "К" -> "K"
104
+ "к" -> "k"
105
+ "Л" -> "L"
106
+ "л" -> "l"
107
+ "Љ" -> "Lj"
108
+ "љ" -> "lj"
109
+ "М" -> "M"
110
+ "м" -> "m"
111
+ "Н" -> "N"
112
+ "н" -> "n"
113
+ "Њ" -> "Nj"
114
+ "њ" -> "nj"
115
+ "О" -> "O"
116
+ "о" -> "o"
117
+ "П" -> "P"
118
+ "п" -> "p"
119
+ "Р" -> "R"
120
+ "р" -> "r"
121
+ "С" -> "S"
122
+ "с" -> "s"
123
+ "Т" -> "T"
124
+ "т" -> "t"
125
+ "Ќ" -> "Kj"
126
+ "ќ" -> "kj"
127
+ "У" -> "U"
128
+ "у" -> "u"
129
+ "Ф" -> "F"
130
+ "ф" -> "f"
131
+ "Х" -> "H"
132
+ "х" -> "h"
133
+ "Ц" -> "Ts"
134
+ "ц" -> "ts"
135
+ "Ч" -> "Ch"
136
+ "ч" -> "ch"
137
+ "Џ" -> "Dzh"
138
+ "џ" -> "dzh"
139
+ "Ш" -> "Sh"
140
+ "ш" -> "sh"
53
141
  }
54
142
 
55
143
  stage main {
@@ -56,6 +56,57 @@ metadata {
56
56
 
57
57
  tests {
58
58
  "Рустам Абдрашитов" -> "Rustam Abdrashitov"
59
+ # Exhaustive per-row tests for odni-tat-Cyrl-Latn-2015, generated from the source
60
+ # document's table.
61
+ # Source: ICS 630-01 Annex S (ANNEX S - Tatar_Personal_Names_FLTS (U).pdf),
62
+ # p. 2 (letter table); held source
63
+ # interscript-private-references/ics-630-01/ANNEX S -
64
+ # Tatar_Personal_Names_FLTS (U).pdf. Extraction: annex text layer, every
65
+ # value cell cross-checked against the rendered page image. Cell "у, ү" (one
66
+ # value cell naming two keys) transcribed as two rows. The value cells for е
67
+ # and э print the Latin letter e; the text layer stores the lookalike
68
+ # Cyrillic е (U+0435) — values transcribed from the printed image. General
69
+ # Notes: double digraphs as a single digraph; ъ and ь are not
70
+ # transliterated.
71
+ # Provenance artifact: scripts/row-sources/odni-tat-Cyrl-Latn-2015.json (37 rows).
72
+ # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
73
+ "а" -> "a"
74
+ "ә" -> "a"
75
+ "б" -> "b"
76
+ "в" -> "v"
77
+ "г" -> "g"
78
+ "д" -> "d"
79
+ "е" -> "e"
80
+ "ё" -> "yo"
81
+ "ж" -> "zh"
82
+ "җ" -> "j"
83
+ "з" -> "z"
84
+ "и" -> "i"
85
+ "й" -> "y"
86
+ "к" -> "k"
87
+ "л" -> "l"
88
+ "м" -> "m"
89
+ "н" -> "n"
90
+ "ң" -> "ng"
91
+ "о" -> "o"
92
+ "ө" -> "o"
93
+ "п" -> "p"
94
+ "р" -> "r"
95
+ "с" -> "s"
96
+ "т" -> "t"
97
+ "у" -> "u"
98
+ "ү" -> "u"
99
+ "ф" -> "f"
100
+ "х" -> "kh"
101
+ "һ" -> "h"
102
+ "ц" -> "ts"
103
+ "ч" -> "ch"
104
+ "ш" -> "sh"
105
+ "щ" -> "shch"
106
+ "ы" -> "y"
107
+ "э" -> "e"
108
+ "ю" -> "yu"
109
+ "я" -> "ya"
59
110
  }
60
111
 
61
112
  stage main {
@@ -57,6 +57,68 @@ metadata {
57
57
 
58
58
  tests {
59
59
  "Парвона Ҷамшедов" -> "Parvona Jamshedov"
60
+ # Exhaustive per-row tests for odni-tgk-Cyrl-Latn-2015, generated from the source
61
+ # document's table.
62
+ # Source: ICS 630-01 Annex N (ANNEX N - Tajik_Person-Name_IC_Standard_FLTS
63
+ # (U).pdf), p. 2 (letter table); held source
64
+ # interscript-private-references/ics-630-01/ANNEX N -
65
+ # Tajik_Person-Name_IC_Standard_FLTS (U).pdf. Extraction: annex text layer,
66
+ # every value cell cross-checked against the rendered page image. Two-column
67
+ # table read in document order (left column а..п, right column р..я). The
68
+ # value cell for э prints the Latin letter e; the text layer stores the
69
+ # lookalike Cyrillic е (U+0435) — transcribed from the printed image.
70
+ # General Notes: double digraphs as a single digraph (шш -> sh). Skipped
71
+ # printed rows: е — printed value cell "e, ye¹"; note 1: "Transliterate as
72
+ # ‘ye’ at beginning of words, ‘e’ elsewhere" — the value is
73
+ # position-dependent, un-expressible as a plain row. The map encodes е -> e
74
+ # unconditionally (its word-initial interpretation of the note is not
75
+ # implemented), so a plain-row test would also diverge from the printed
76
+ # semantics. | ъ — printed value cell "<blank>²"; note 2: "Leave out
77
+ # entirely; do not transliterate" — instruction cell, no romanization value.
78
+ # | ц, щ, ь, ы — printed value cells "<see Russian>³"; note 3: "Consult
79
+ # Russian IC standard for this letter" — instruction cells; no Tajik value
80
+ # is printed. (The map carries Ts/Shch/Y values for ц/щ/ы from the Russian
81
+ # standard; not testable against THIS page.) Findings (map-vs-source, map
82
+ # untouched): е: printed note-1 semantics (ye word-initial, e elsewhere) vs
83
+ # map unconditional e — map does not implement the note; row left untested.
84
+ # | ц/щ/ы: map encodes Ts/Shch/Y although the Tajik annex prints no values
85
+ # for them (defers to the Russian IC standard) — map rules exceed this page;
86
+ # rows skipped, map untouched.
87
+ # Provenance artifact: scripts/row-sources/odni-tgk-Cyrl-Latn-2015.json (33 rows).
88
+ # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
89
+ "а" -> "a"
90
+ "б" -> "b"
91
+ "в" -> "v"
92
+ "г" -> "g"
93
+ "ғ" -> "gh"
94
+ "д" -> "d"
95
+ "ё" -> "yo"
96
+ "ж" -> "zh"
97
+ "з" -> "z"
98
+ "и" -> "i"
99
+ "ӣ" -> "i"
100
+ "й" -> "y"
101
+ "к" -> "k"
102
+ "қ" -> "q"
103
+ "л" -> "l"
104
+ "м" -> "m"
105
+ "н" -> "n"
106
+ "о" -> "o"
107
+ "п" -> "p"
108
+ "р" -> "r"
109
+ "с" -> "s"
110
+ "т" -> "t"
111
+ "у" -> "u"
112
+ "ӯ" -> "u"
113
+ "ф" -> "f"
114
+ "х" -> "kh"
115
+ "ҳ" -> "h"
116
+ "ч" -> "ch"
117
+ "ҷ" -> "j"
118
+ "ш" -> "sh"
119
+ "э" -> "e"
120
+ "ю" -> "yu"
121
+ "я" -> "ya"
60
122
  }
61
123
 
62
124
  stage main {
@@ -56,6 +56,60 @@ metadata {
56
56
 
57
57
  tests {
58
58
  "Зордун Сабир" -> "Zordun Sabir"
59
+ # Exhaustive per-row tests for odni-uig-Cyrl-Latn-2015, generated from the source
60
+ # document's table.
61
+ # Source: ICS 630-01 Annex U (ANNEX U - Uyghur_Personal_Names_FLTS (U).pdf),
62
+ # p. 2 (letter table); held source
63
+ # interscript-private-references/ics-630-01/ANNEX U -
64
+ # Uyghur_Personal_Names_FLTS (U).pdf. Extraction: annex text layer, every
65
+ # value cell cross-checked against the rendered page image. The printed
66
+ # table has three columns: Cyrillic letter, Uyghur Arabic-script spelling,
67
+ # IC Standard (Latin). The middle column is the Arabic-script equivalent and
68
+ # is not part of this Cyrl->Latn map; documented here, not transcribed as
69
+ # rows. Distinctive values verified visually: ә -> e (not a), в -> w (not
70
+ # v), х -> Latin x (not kh). The value cells for е and ә print the Latin
71
+ # letter e and х the Latin letter x; the text layer stores the lookalike
72
+ # Cyrillic glyphs (U+0435 / U+0445) — values transcribed from the printed
73
+ # image. General Notes: double digraphs as a single digraph (шш -> sh).
74
+ # Skipped printed rows: ъ, ь — not table rows; the General Notes state they
75
+ # are not transliterated (left out).
76
+ # Provenance artifact: scripts/row-sources/odni-uig-Cyrl-Latn-2015.json (35 rows).
77
+ # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
78
+ "а" -> "a"
79
+ "ә" -> "e"
80
+ "б" -> "b"
81
+ "в" -> "w"
82
+ "г" -> "g"
83
+ "ғ" -> "gh"
84
+ "д" -> "d"
85
+ "е" -> "e"
86
+ "ё" -> "yo"
87
+ "ж" -> "j"
88
+ "җ" -> "zh"
89
+ "з" -> "z"
90
+ "и" -> "i"
91
+ "й" -> "y"
92
+ "к" -> "k"
93
+ "қ" -> "q"
94
+ "л" -> "l"
95
+ "м" -> "m"
96
+ "н" -> "n"
97
+ "ң" -> "ng"
98
+ "о" -> "o"
99
+ "ө" -> "o"
100
+ "п" -> "p"
101
+ "р" -> "r"
102
+ "с" -> "s"
103
+ "т" -> "t"
104
+ "у" -> "u"
105
+ "ү" -> "u"
106
+ "ф" -> "f"
107
+ "х" -> "x"
108
+ "һ" -> "h"
109
+ "ч" -> "ch"
110
+ "ш" -> "sh"
111
+ "ю" -> "yu"
112
+ "я" -> "ya"
59
113
  }
60
114
 
61
115
  stage main {
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: interscript-maps
3
3
  version: !ruby/object:Gem::Version
4
- version: 3.2.3
4
+ version: 3.2.4
5
5
  platform: ruby
6
6
  authors:
7
7
  - Ribose Inc.