diff --git a/maps/alalc-chr-Cher-Latn-2012.isc b/maps/alalc-chr-Cher-Latn-2012.isc index 18c54e8..a77ceef 100644 --- a/maps/alalc-chr-Cher-Latn-2012.isc +++ b/maps/alalc-chr-Cher-Latn-2012.isc @@ -47,6 +47,104 @@ tests { "Ꮿ" -> "ya" "ᎣᏏᏲ" -> "osiyo" "ᏣᎳᎩ" -> "tsalagi" + +# Exhaustive per-row tests for alalc-chr-Cher-Latn-2012, generated from the source +# document's table. +# Source: ALA-LC Cherokee Romanization Table (2012 version; no earlier +# versions) (https://www.loc.gov/catdir/cpso/romanization/cherokee.pdf; +# local source interscript-private-references/alalc/alalc-cherokee.pdf). +# Single-page syllabary grid, 85 rows, in printed grid order (left to right, +# top to bottom). Complete: no skipped rows — every printed cell is a single +# one-to-one romanization encodable as a character rule. The v-series values +# (Ꭵ Ꭼ Ꮂ Ꮈ Ꮕ Ꮫ Ꮲ Ꮸ Ꮾ Ᏼ) are the table's rendering of the nasal vowel. Glyph +# codepoints verified against the PDF text layer. +# Provenance artifact: scripts/row-sources/alalc-chr-Cher-Latn-2012.json (85 rows). +# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-14); regenerate from the artifact, do not hand-edit. + "Ꭰ" -> "a" + "Ꭱ" -> "e" + "Ꭲ" -> "i" + "Ꭳ" -> "o" + "Ꭴ" -> "u" + "Ꭵ" -> "v" + "Ꭶ" -> "ga" + "Ꭷ" -> "ka" + "Ꭸ" -> "ge" + "Ꭹ" -> "gi" + "Ꭺ" -> "go" + "Ꭻ" -> "gu" + "Ꭼ" -> "gv" + "Ꭽ" -> "ha" + "Ꭾ" -> "he" + "Ꭿ" -> "hi" + "Ꮀ" -> "ho" + "Ꮁ" -> "hu" + "Ꮂ" -> "hv" + "Ꮃ" -> "la" + "Ꮄ" -> "le" + "Ꮅ" -> "li" + "Ꮆ" -> "lo" + "Ꮇ" -> "lu" + "Ꮈ" -> "lv" + "Ꮉ" -> "ma" + "Ꮊ" -> "me" + "Ꮋ" -> "mi" + "Ꮌ" -> "mo" + "Ꮍ" -> "mu" + "Ꮎ" -> "na" + "Ꮏ" -> "hna" + "Ꮐ" -> "nah" + "Ꮑ" -> "ne" + "Ꮒ" -> "ni" + "Ꮓ" -> "no" + "Ꮔ" -> "nu" + "Ꮕ" -> "nv" + "Ꮖ" -> "qua" + "Ꮗ" -> "que" + "Ꮘ" -> "qui" + "Ꮙ" -> "quo" + "Ꮚ" -> "quu" + "Ꮛ" -> "quv" + "Ꮜ" -> "sa" + "Ꮝ" -> "s" + "Ꮞ" -> "se" + "Ꮟ" -> "si" + "Ꮠ" -> "so" + "Ꮡ" -> "su" + "Ꮢ" -> "sv" + "Ꮣ" -> "da" + "Ꮤ" -> "ta" + "Ꮥ" -> "de" + "Ꮦ" -> "te" + "Ꮧ" -> "di" + "Ꮨ" -> "ti" + "Ꮩ" -> "do" + "Ꮪ" -> "du" + "Ꮫ" -> "dv" + "Ꮬ" -> "dla" + "Ꮭ" -> "tla" + "Ꮮ" -> "tle" + "Ꮯ" -> "tli" + "Ꮰ" -> "tlo" + "Ꮱ" -> "tlu" + "Ꮲ" -> "tlv" + "Ꮳ" -> "tsa" + "Ꮴ" -> "tse" + "Ꮵ" -> "tsi" + "Ꮶ" -> "tso" + "Ꮷ" -> "tsu" + "Ꮸ" -> "tsv" + "Ꮹ" -> "wa" + "Ꮺ" -> "we" + "Ꮻ" -> "wi" + "Ꮼ" -> "wo" + "Ꮽ" -> "wu" + "Ꮾ" -> "wv" + "Ꮿ" -> "ya" + "Ᏸ" -> "ye" + "Ᏹ" -> "yi" + "Ᏺ" -> "yo" + "Ᏻ" -> "yu" + "Ᏼ" -> "yv" } stage main { diff --git a/maps/alalc-hye-Armn-Latn-2022.isc b/maps/alalc-hye-Armn-Latn-2022.isc index a4ebad2..14439fe 100644 --- a/maps/alalc-hye-Armn-Latn-2022.isc +++ b/maps/alalc-hye-Armn-Latn-2022.isc @@ -77,6 +77,166 @@ tests { "Ռ․" -> "1000" "Կարդա՛, գրի՛ր տարին բոլոր" -> "Karda, grir tarin bolor" "Բարձրանում է աշխարհ մի անեզր, որ քոնն է անշուշտ և իմը." -> "Bardzranum ē ashkharh mi anezr, or kʻonn ē anshusht ev imě." + +# Exhaustive per-row tests for alalc-hye-Armn-Latn-2022, generated from the source +# document's table. +# Source: ALA-LC Armenian Romanization Table (2022 version; earlier +# versions: 2011, 1997) +# (https://www.loc.gov/catdir/cpso/romanization/armenian.pdf; local source +# interscript-private-references/alalc/alalc-armenian.pdf). Rows in document +# order: the letter table pp. 1-2 line by line (upper then lower per printed +# line), the Note 3 soft-sign combination table (p. 2), then the +# letter-numeral table (p. 7) as printed column streams (left column +# top-down, then right). Primary values only: the bracketed West Armenian +# alternates are excluded per the map's encoding scope. Skipped +# un-expressible rows: the Ե/ե Y/y alternates (Note 2: initial position of a +# name followed by a vowel, Classical) and the Յ/յ Ḥ/ḥ alternates (Note 4: +# initial position of a word or stem in a compound, Classical) are +# position-dependent; the composite numerals ԺԱ․ ԺԲ․ ԻԱ․ ԻԲ․ ԼԱ․ ԼԲ․ are +# multi-letter values and the map encodes single-letter numeral rules only; +# the ․․․ continuation placeholders are not romanization rows. The +# punctuation section (pp. 5-6) is instruction prose, not a table: «» and ։ +# are encoded as map rules but are not row-transcribed here; ՞ and ՜ require +# sentence-end repositioning and are un-encodable as character rules; ՛ has +# empty output, which the generator contract (non-empty to) excludes — it is +# already encoded as a map rule. The diacritics page (p. 4) repeats +# letter-table rows and adds none. The Ev row's printed lower-case +# vernacular cell is the ech-yiwn ligature և; եվ is not a printed table row +# (the map encodes it additionally). The printed rows for Զ/զ and Ս/ս carry +# a '(see Note 3)' reference marker; transcribed as plain Z/S values. The +# aspiration mark is U+02BB, the soft sign U+02B9, the numeral leader +# U+2024; tilded/macroned/dotted Latin letters are the printed precomposed +# forms. +# Provenance artifact: scripts/row-sources/alalc-hye-Armn-Latn-2022.json (128 rows). +# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-14); regenerate from the artifact, do not hand-edit. + "Ա" -> "A" + "ա" -> "a" + "Բ" -> "B" + "բ" -> "b" + "Գ" -> "G" + "գ" -> "g" + "Դ" -> "D" + "դ" -> "d" + "Ե" -> "E" + "ե" -> "e" + "Զ" -> "Z" + "զ" -> "z" + "Է" -> "Ē" + "է" -> "ē" + "Ը" -> "Ě" + "ը" -> "ě" + "Թ" -> "Tʻ" + "թ" -> "tʻ" + "Ժ" -> "Zh" + "ժ" -> "zh" + "Ի" -> "I" + "ի" -> "i" + "Լ" -> "L" + "լ" -> "l" + "Խ" -> "Kh" + "խ" -> "kh" + "Ծ" -> "Ts" + "ծ" -> "ts" + "Կ" -> "K" + "կ" -> "k" + "Հ" -> "H" + "հ" -> "h" + "Ձ" -> "Dz" + "ձ" -> "dz" + "Ղ" -> "Gh" + "ղ" -> "gh" + "Ճ" -> "Ch" + "ճ" -> "ch" + "Մ" -> "M" + "մ" -> "m" + "Յ" -> "Y" + "յ" -> "y" + "Ն" -> "N" + "ն" -> "n" + "Շ" -> "Sh" + "շ" -> "sh" + "Ո" -> "O" + "ո" -> "o" + "Չ" -> "Chʻ" + "չ" -> "chʻ" + "Պ" -> "P" + "պ" -> "p" + "Ջ" -> "J" + "ջ" -> "j" + "Ռ" -> "Ṛ" + "ռ" -> "ṛ" + "Ս" -> "S" + "ս" -> "s" + "Վ" -> "V" + "վ" -> "v" + "Տ" -> "T" + "տ" -> "t" + "Ր" -> "R" + "ր" -> "r" + "Ց" -> "Tsʻ" + "ց" -> "tsʻ" + "Ւ" -> "W" + "ւ" -> "w" + "Ու" -> "U" + "ու" -> "u" + "Փ" -> "Pʻ" + "փ" -> "pʻ" + "Ք" -> "Kʻ" + "ք" -> "kʻ" + "Եւ" -> "Ew" + "եւ" -> "ew" + "Եվ" -> "Ev" + "և" -> "ev" + "Օ" -> "Ō" + "օ" -> "ō" + "Ֆ" -> "F" + "ֆ" -> "f" + "Գհ" -> "Gʹh" + "գհ" -> "gʹh" + "Դզ" -> "Dʹz" + "դզ" -> "dʹz" + "Կհ" -> "Kʹh" + "կհ" -> "kʹh" + "Սհ" -> "Sʹh" + "սհ" -> "sʹh" + "Տս" -> "Tʹs" + "տս" -> "tʹs" + "Ա․" -> "1" + "Բ․" -> "2" + "Գ․" -> "3" + "Դ․" -> "4" + "Ե․" -> "5" + "Զ․" -> "6" + "Է․" -> "7" + "Ը․" -> "8" + "Թ․" -> "9" + "Ժ․" -> "10" + "Ի․" -> "20" + "Լ․" -> "30" + "Խ․" -> "40" + "Ծ․" -> "50" + "Կ․" -> "60" + "Հ․" -> "70" + "Ձ․" -> "80" + "Ղ․" -> "90" + "Ճ․" -> "100" + "Մ․" -> "200" + "Յ․" -> "300" + "Ն․" -> "400" + "Շ․" -> "500" + "Ո․" -> "600" + "Չ․" -> "700" + "Պ․" -> "800" + "Ջ․" -> "900" + "Ռ․" -> "1000" + "Ս․" -> "2000" + "Վ․" -> "3000" + "Տ․" -> "4000" + "Ր․" -> "5000" + "Ց․" -> "6000" + "Ւ․" -> "7000" + "Փ․" -> "8000" + "Ք․" -> "9000" } stage main { diff --git a/maps/alalc-zgh-Tfng-Latn-2012.isc b/maps/alalc-zgh-Tfng-Latn-2012.isc index 6ad0c1f..8c3f109 100644 --- a/maps/alalc-zgh-Tfng-Latn-2012.isc +++ b/maps/alalc-zgh-Tfng-Latn-2012.isc @@ -56,6 +56,69 @@ tests { "ⵥ" -> "ẓ" "ⴳⵯ" -> "g°" "ⵯ" -> "°" + +# Exhaustive per-row tests for alalc-zgh-Tfng-Latn-2012, generated from the source +# document's table. +# Source: ALA-LC Moroccan Tamazight Romanization Table (2012; no version +# year printed on the document, approval date CC:AAM 2012-01-22 from PDF +# metadata) (https://www.loc.gov/catdir/cpso/romanization/tamazight.pdf; +# local source interscript-private-references/alalc/alalc-tamazight.pdf). +# Single-page table, 43 rows, read as printed column streams (left column +# top-down, then right). Complete: no skipped rows — the table includes the +# labialized digraphs ⴳⵯ/ⴽⵯ and the tamatart ⵯ, all encodable. The PDF text +# layer drops the macron-below marks (U+0331) on the ⴲ ⴴ ⴸ ⵝ values and the +# entire value cells for ⵕ ⵟ ⴺ; those values are transcribed from the +# printed page image. Decomposed text-layer forms are NFC-normalized +# (h+U+0323 → ḥ U+1E25, s+U+0323 → ṣ, z+U+0323 → ẓ, d+U+0323 → ḍ). The ⴺ +# value (d with dot below and macron below) follows the printed glyph with +# the map's documented mark order (U+0323 then U+0331). The printed ⵄ ⵖ rows +# carry '(See note 1)' and ⵯ '(See note 2)' reference markers; transcribed +# as plain values. +# Provenance artifact: scripts/row-sources/alalc-zgh-Tfng-Latn-2012.json (43 rows). +# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-14); regenerate from the artifact, do not hand-edit. + "ⴰ" -> "a" + "ⴱ" -> "b" + "ⴲ" -> "ḇ" + "ⴳ" -> "g" + "ⴳⵯ" -> "g°" + "ⴴ" -> "g̱" + "ⴵ" -> "ğ" + "ⴷ" -> "d" + "ⴸ" -> "ḏ" + "ⴹ" -> "ḍ" + "ⴺ" -> "ḍ̱" + "ⴻ" -> "e" + "ⴼ" -> "f" + "ⴽ" -> "k" + "ⴽⵯ" -> "k°" + "ⴿ" -> "k" + "ⵀ" -> "h" + "ⵃ" -> "ḥ" + "ⵄ" -> "ɛ" + "ⵅ" -> "x" + "ⵇ" -> "q" + "ⵉ" -> "i" + "ⵊ" -> "j" + "ⵍ" -> "l" + "ⵎ" -> "m" + "ⵏ" -> "n" + "ⵓ" -> "u" + "ⵔ" -> "r" + "ⵕ" -> "ṛ" + "ⵖ" -> "ɣ" + "ⵙ" -> "s" + "ⵚ" -> "ṣ" + "ⵛ" -> "c" + "ⵜ" -> "t" + "ⵝ" -> "ṯ" + "ⵞ" -> "č" + "ⵟ" -> "ṭ" + "ⵠ" -> "v" + "ⵡ" -> "w" + "ⵢ" -> "y" + "ⵣ" -> "z" + "ⵥ" -> "ẓ" + "ⵯ" -> "°" } stage main { diff --git a/scripts/row-sources/alalc-chr-Cher-Latn-2012.json b/scripts/row-sources/alalc-chr-Cher-Latn-2012.json new file mode 100644 index 0000000..3e5f44d --- /dev/null +++ b/scripts/row-sources/alalc-chr-Cher-Latn-2012.json @@ -0,0 +1,91 @@ +{ + "system": "alalc-chr-Cher-Latn-2012", + "rows": [ + ["Ꭰ", "a"], + ["Ꭱ", "e"], + ["Ꭲ", "i"], + ["Ꭳ", "o"], + ["Ꭴ", "u"], + ["Ꭵ", "v"], + ["Ꭶ", "ga"], + ["Ꭷ", "ka"], + ["Ꭸ", "ge"], + ["Ꭹ", "gi"], + ["Ꭺ", "go"], + ["Ꭻ", "gu"], + ["Ꭼ", "gv"], + ["Ꭽ", "ha"], + ["Ꭾ", "he"], + ["Ꭿ", "hi"], + ["Ꮀ", "ho"], + ["Ꮁ", "hu"], + ["Ꮂ", "hv"], + ["Ꮃ", "la"], + ["Ꮄ", "le"], + ["Ꮅ", "li"], + ["Ꮆ", "lo"], + ["Ꮇ", "lu"], + ["Ꮈ", "lv"], + ["Ꮉ", "ma"], + ["Ꮊ", "me"], + ["Ꮋ", "mi"], + ["Ꮌ", "mo"], + ["Ꮍ", "mu"], + ["Ꮎ", "na"], + ["Ꮏ", "hna"], + ["Ꮐ", "nah"], + ["Ꮑ", "ne"], + ["Ꮒ", "ni"], + ["Ꮓ", "no"], + ["Ꮔ", "nu"], + ["Ꮕ", "nv"], + ["Ꮖ", "qua"], + ["Ꮗ", "que"], + ["Ꮘ", "qui"], + ["Ꮙ", "quo"], + ["Ꮚ", "quu"], + ["Ꮛ", "quv"], + ["Ꮜ", "sa"], + ["Ꮝ", "s"], + ["Ꮞ", "se"], + ["Ꮟ", "si"], + ["Ꮠ", "so"], + ["Ꮡ", "su"], + ["Ꮢ", "sv"], + ["Ꮣ", "da"], + ["Ꮤ", "ta"], + ["Ꮥ", "de"], + ["Ꮦ", "te"], + ["Ꮧ", "di"], + ["Ꮨ", "ti"], + ["Ꮩ", "do"], + ["Ꮪ", "du"], + ["Ꮫ", "dv"], + ["Ꮬ", "dla"], + ["Ꮭ", "tla"], + ["Ꮮ", "tle"], + ["Ꮯ", "tli"], + ["Ꮰ", "tlo"], + ["Ꮱ", "tlu"], + ["Ꮲ", "tlv"], + ["Ꮳ", "tsa"], + ["Ꮴ", "tse"], + ["Ꮵ", "tsi"], + ["Ꮶ", "tso"], + ["Ꮷ", "tsu"], + ["Ꮸ", "tsv"], + ["Ꮹ", "wa"], + ["Ꮺ", "we"], + ["Ꮻ", "wi"], + ["Ꮼ", "wo"], + ["Ꮽ", "wu"], + ["Ꮾ", "wv"], + ["Ꮿ", "ya"], + ["Ᏸ", "ye"], + ["Ᏹ", "yi"], + ["Ᏺ", "yo"], + ["Ᏻ", "yu"], + ["Ᏼ", "yv"] + ], + "note": "ALA-LC Cherokee Romanization Table (2012 version; no earlier versions) (https://www.loc.gov/catdir/cpso/romanization/cherokee.pdf; local source interscript-private-references/alalc/alalc-cherokee.pdf). Single-page syllabary grid, 85 rows, in printed grid order (left to right, top to bottom). Complete: no skipped rows — every printed cell is a single one-to-one romanization encodable as a character rule. The v-series values (Ꭵ Ꭼ Ꮂ Ꮈ Ꮕ Ꮫ Ꮲ Ꮸ Ꮾ Ᏼ) are the table's rendering of the nasal vowel. Glyph codepoints verified against the PDF text layer." +} diff --git a/scripts/row-sources/alalc-hye-Armn-Latn-2022.json b/scripts/row-sources/alalc-hye-Armn-Latn-2022.json new file mode 100644 index 0000000..0d6a8d1 --- /dev/null +++ b/scripts/row-sources/alalc-hye-Armn-Latn-2022.json @@ -0,0 +1,134 @@ +{ + "system": "alalc-hye-Armn-Latn-2022", + "rows": [ + ["Ա", "A"], + ["ա", "a"], + ["Բ", "B"], + ["բ", "b"], + ["Գ", "G"], + ["գ", "g"], + ["Դ", "D"], + ["դ", "d"], + ["Ե", "E"], + ["ե", "e"], + ["Զ", "Z"], + ["զ", "z"], + ["Է", "Ē"], + ["է", "ē"], + ["Ը", "Ě"], + ["ը", "ě"], + ["Թ", "Tʻ"], + ["թ", "tʻ"], + ["Ժ", "Zh"], + ["ժ", "zh"], + ["Ի", "I"], + ["ի", "i"], + ["Լ", "L"], + ["լ", "l"], + ["Խ", "Kh"], + ["խ", "kh"], + ["Ծ", "Ts"], + ["ծ", "ts"], + ["Կ", "K"], + ["կ", "k"], + ["Հ", "H"], + ["հ", "h"], + ["Ձ", "Dz"], + ["ձ", "dz"], + ["Ղ", "Gh"], + ["ղ", "gh"], + ["Ճ", "Ch"], + ["ճ", "ch"], + ["Մ", "M"], + ["մ", "m"], + ["Յ", "Y"], + ["յ", "y"], + ["Ն", "N"], + ["ն", "n"], + ["Շ", "Sh"], + ["շ", "sh"], + ["Ո", "O"], + ["ո", "o"], + ["Չ", "Chʻ"], + ["չ", "chʻ"], + ["Պ", "P"], + ["պ", "p"], + ["Ջ", "J"], + ["ջ", "j"], + ["Ռ", "Ṛ"], + ["ռ", "ṛ"], + ["Ս", "S"], + ["ս", "s"], + ["Վ", "V"], + ["վ", "v"], + ["Տ", "T"], + ["տ", "t"], + ["Ր", "R"], + ["ր", "r"], + ["Ց", "Tsʻ"], + ["ց", "tsʻ"], + ["Ւ", "W"], + ["ւ", "w"], + ["Ու", "U"], + ["ու", "u"], + ["Փ", "Pʻ"], + ["փ", "pʻ"], + ["Ք", "Kʻ"], + ["ք", "kʻ"], + ["Եւ", "Ew"], + ["եւ", "ew"], + ["Եվ", "Ev"], + ["և", "ev"], + ["Օ", "Ō"], + ["օ", "ō"], + ["Ֆ", "F"], + ["ֆ", "f"], + ["Գհ", "Gʹh"], + ["գհ", "gʹh"], + ["Դզ", "Dʹz"], + ["դզ", "dʹz"], + ["Կհ", "Kʹh"], + ["կհ", "kʹh"], + ["Սհ", "Sʹh"], + ["սհ", "sʹh"], + ["Տս", "Tʹs"], + ["տս", "tʹs"], + ["Ա․", "1"], + ["Բ․", "2"], + ["Գ․", "3"], + ["Դ․", "4"], + ["Ե․", "5"], + ["Զ․", "6"], + ["Է․", "7"], + ["Ը․", "8"], + ["Թ․", "9"], + ["Ժ․", "10"], + ["Ի․", "20"], + ["Լ․", "30"], + ["Խ․", "40"], + ["Ծ․", "50"], + ["Կ․", "60"], + ["Հ․", "70"], + ["Ձ․", "80"], + ["Ղ․", "90"], + ["Ճ․", "100"], + ["Մ․", "200"], + ["Յ․", "300"], + ["Ն․", "400"], + ["Շ․", "500"], + ["Ո․", "600"], + ["Չ․", "700"], + ["Պ․", "800"], + ["Ջ․", "900"], + ["Ռ․", "1000"], + ["Ս․", "2000"], + ["Վ․", "3000"], + ["Տ․", "4000"], + ["Ր․", "5000"], + ["Ց․", "6000"], + ["Ւ․", "7000"], + ["Փ․", "8000"], + ["Ք․", "9000"] + ], + "note": "ALA-LC Armenian Romanization Table (2022 version; earlier versions: 2011, 1997) (https://www.loc.gov/catdir/cpso/romanization/armenian.pdf; local source interscript-private-references/alalc/alalc-armenian.pdf). Rows in document order: the letter table pp. 1-2 line by line (upper then lower per printed line), the Note 3 soft-sign combination table (p. 2), then the letter-numeral table (p. 7) as printed column streams (left column top-down, then right). Primary values only: the bracketed West Armenian alternates are excluded per the map's encoding scope. Skipped un-expressible rows: the Ե/ե Y/y alternates (Note 2: initial position of a name followed by a vowel, Classical) and the Յ/յ Ḥ/ḥ alternates (Note 4: initial position of a word or stem in a compound, Classical) are position-dependent; the composite numerals ԺԱ․ ԺԲ․ ԻԱ․ ԻԲ․ ԼԱ․ ԼԲ․ are multi-letter values and the map encodes single-letter numeral rules only; the ․․․ continuation placeholders are not romanization rows. The punctuation section (pp. 5-6) is instruction prose, not a table: «» and ։ are encoded as map rules but are not row-transcribed here; ՞ and ՜ require sentence-end repositioning and are un-encodable as character rules; ՛ has empty output, which the generator contract (non-empty to) excludes — it is already encoded as a map rule. The diacritics page (p. 4) repeats letter-table rows and adds none. The Ev row's printed lower-case vernacular cell is the ech-yiwn ligature և; եվ is not a printed table row (the map encodes it additionally). The printed rows for Զ/զ and Ս/ս carry a '(see Note 3)' reference marker; transcribed as plain Z/S values. The aspiration mark is U+02BB, the soft sign U+02B9, the numeral leader U+2024; tilded/macroned/dotted Latin letters are the printed precomposed forms." +} diff --git a/scripts/row-sources/alalc-zgh-Tfng-Latn-2012.json b/scripts/row-sources/alalc-zgh-Tfng-Latn-2012.json new file mode 100644 index 0000000..95b402e --- /dev/null +++ b/scripts/row-sources/alalc-zgh-Tfng-Latn-2012.json @@ -0,0 +1,49 @@ +{ + "system": "alalc-zgh-Tfng-Latn-2012", + "rows": [ + ["ⴰ", "a"], + ["ⴱ", "b"], + ["ⴲ", "ḇ"], + ["ⴳ", "g"], + ["ⴳⵯ", "g°"], + ["ⴴ", "g̱"], + ["ⴵ", "ğ"], + ["ⴷ", "d"], + ["ⴸ", "ḏ"], + ["ⴹ", "ḍ"], + ["ⴺ", "ḍ̱"], + ["ⴻ", "e"], + ["ⴼ", "f"], + ["ⴽ", "k"], + ["ⴽⵯ", "k°"], + ["ⴿ", "k"], + ["ⵀ", "h"], + ["ⵃ", "ḥ"], + ["ⵄ", "ɛ"], + ["ⵅ", "x"], + ["ⵇ", "q"], + ["ⵉ", "i"], + ["ⵊ", "j"], + ["ⵍ", "l"], + ["ⵎ", "m"], + ["ⵏ", "n"], + ["ⵓ", "u"], + ["ⵔ", "r"], + ["ⵕ", "ṛ"], + ["ⵖ", "ɣ"], + ["ⵙ", "s"], + ["ⵚ", "ṣ"], + ["ⵛ", "c"], + ["ⵜ", "t"], + ["ⵝ", "ṯ"], + ["ⵞ", "č"], + ["ⵟ", "ṭ"], + ["ⵠ", "v"], + ["ⵡ", "w"], + ["ⵢ", "y"], + ["ⵣ", "z"], + ["ⵥ", "ẓ"], + ["ⵯ", "°"] + ], + "note": "ALA-LC Moroccan Tamazight Romanization Table (2012; no version year printed on the document, approval date CC:AAM 2012-01-22 from PDF metadata) (https://www.loc.gov/catdir/cpso/romanization/tamazight.pdf; local source interscript-private-references/alalc/alalc-tamazight.pdf). Single-page table, 43 rows, read as printed column streams (left column top-down, then right). Complete: no skipped rows — the table includes the labialized digraphs ⴳⵯ/ⴽⵯ and the tamatart ⵯ, all encodable. The PDF text layer drops the macron-below marks (U+0331) on the ⴲ ⴴ ⴸ ⵝ values and the entire value cells for ⵕ ⵟ ⴺ; those values are transcribed from the printed page image. Decomposed text-layer forms are NFC-normalized (h+U+0323 → ḥ U+1E25, s+U+0323 → ṣ, z+U+0323 → ẓ, d+U+0323 → ḍ). The ⴺ value (d with dot below and macron below) follows the printed glyph with the map's documented mark order (U+0323 then U+0331). The printed ⵄ ⵖ rows carry '(See note 1)' and ⵯ '(See note 2)' reference markers; transcribed as plain values." +}