#! /bin/bash -ue
# Last edited on 2026-07-24 19:23:55 by stolfi
# Creates files "descr.wik" for each language, book, and section.
function defcap() {
division="$1"; shift # Either "{lang}", "{lang}/{book}", or "{lang}/{book}/{sec}"
source="$1"; shift # Either "-" or the "{lang}/{book}" folder langbank with the "main.src".
gudnum="$1"; shift # Either "-" or the number of good words to take in this section.
key="$1"; shift # A short id for plot legends.
cap="$1"; shift # The caption, in wikipedia markup.
echo "${division}" 1>&2
dir="dat/${division}"
# Ensure that ${cap} ends with ".":
pat="[.]$" # Pattern must be in a variable. Bash is a crock!
if [[ ! ( "${cap}" =~ $pat ) ]]; then cap="${cap}."; fi
lang="${division%%/*}"
book="";
sec="";
if [[ "${division}" != "${lang}" ]]; then
bs="${division#*/}"; book="${bs%%/*}";
if [[ "${book}" != "${bs}" ]]; then
sec="${bs#*/}";
fi;
fi
echo " lang = '${lang}'" "book = '${book}'" "sec = '${sec}'" 1>&2
if [[ ! ( -d "${dir}" ) ]]; then echo "** ${dir} not a directory" 1>&2; exit 1; fi
capfile="${dir}/caption.wik"
rm -fv ${capfile} 2>&1 | sed -e 's:^: :g' 1>&2
printf "%s\n" "${cap}" > ${capfile}
if [[ "${sec}" != '' ]]; then
# Section directory. There must be token files:
gudfile="${dir}/gud.wdf"
if [[ ! ( -s "${gudfile}" ) ]]; then
echo "** ${gudfile} not not found" 1>&2;
else
# Append a sample of good text to the caption:
printf "Sample: ''" >> ${capfile}
cat ${gudfile} | head -n 1 | tr -d '\012' >> ${capfile}
printf "'' [...] ''" >> ${capfile}
cat ${gudfile} | tail -n 1 | tr -d '\012' >> ${capfile}
printf "''.\n" >> ${capfile}
fi
fi
cat ${capfile} | sed -e 's:^: :g' 1>&2
}
@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
# ######################################################################
# Classical Arabic in JSAR
defcap arab - - - "[[Arabic language|Arabic]]"
# ......................................................................
defcap arab/quf - - - "The ''[[Quran]]'' (~650 CE). Based on the ''Unicode Quran'' document from the ''Sacred Texts'' site, maintained by John B. Hare, with several corrections. Arabic Unicode characters were mapped into [[ISO 8859-1|ISO latin-1]] characters in a vaguely phonetic way, with joined articles. Version '''with''' short vowel marks, sukuns, hamza, and madda."
defcap arab/quf/tot.1 arab/quv 35027 Qur-F Holy_Quran_-_Vowels_Sukuns
# ......................................................................
defcap arab/quv - - - "The ''[[Quran]]'' (~650 CE). Based on the ''Unicode Quran'' document from the Sacred Texts site, maintained by John B. Hare, with several corrections. Arabic Unicode characters were mapped into [[ISO 8859-1|ISO latin-1]] characters in a vaguely phonetic way. '''With''' vowel marks, hamza, madda but '''without''' sukuns."
defcap arab/quv/tot.1 arab/quv 35027 Qur-V Holy_Quran_-_Vowels
# ......................................................................
defcap arab/qud - - - "The ''[[Quran]]'' (~650 CE). Based on the ''Unicode Quran'' document from the ''Sacred Texts'' site, maintained by John B. Hare, with several corrections. Arabic Unicode characters were mapped into [[ISO 8859-1|ISO latin-1]] characters in a vaguely phonetic way, with joined articles. Version '''without''' short vowel marks, sukuns, hamza, madda."
defcap arab/qud/tot.1 arab/quv 35027 Qur-D Holy_Quran_-_Devowelled
# ......................................................................
defcap arab/qph - - - "The ''[[Quran]]'' (~650 CE). Electronic phonetic transliteration from [[University of Southern California|USC]]'s Muslim Student Union, transliterated again into [[ISO 8859-1|ISO latin-1]] characters. The result, particularly short vowel marks, is partly guessed. The subtler phonetic marks (sukuns, hamzas, maddas, alef-maksura, teh-marbuta etc.) were lost."
defcap arab/qph/tot.1 arab/qph 35027 Qur-P Holy_Quran_-_Semi-Phonetic - whole
# ......................................................................
defcap arab/qcs - - - "The ''[[Quran]]'' (~650 CE). Electronic version of unknown provenance, without short vowel marks or sukuns, in a vaguely phonetic transliteration into [[ISO 8859-1|ISO latin-1]] characters."
defcap arab/qcs/tot.1 arab/qcs 35027 Qur "Holy Quran - Consonants only"
# ######################################################################
defcap chin - - - "[[Chinese language|Chinese (Mandarin)]]"
# ......................................................................
defcap chin/ptt - - - "A Chinese translation of the first five books (''[[Pentateuch]]'') of the Old Testament Bible, from the [[Chinese Union Version|Union Version]] (1919). Chinese characters were mapped 1:1 from GB (Guo Biao) to pinyn with tone marks and disambiguating suffixes, e.g. 'zuo4', 'zuo4.1', 'zuo4.2', so as to distinguish characters with the same pinyin. Each character is treated as a separate token."
defcap chin/ptt/gen.1 - 35027 UOT-1 "OT-UniV, Book 1, ''Genesis''"
defcap chin/ptt/exo.1 - 35027 UOT-2 "OT-UniV, Book 2, ''Exodus''"
defcap chin/ptt/num.1 - 35027 UOT-3 "OT-UniV, Book 3, ''Leviticus''"
defcap chin/ptt/lev.1 - 35027 UOT-4 "OT-UniV, Book 4, ''Numeri''"
defcap chin/ptt/deu.1 - 35027 UOT-5 "OT-UniV, Book 5, ''Deuteronomium''"
defcap chin/ptt/tot.1 chin/ptt 35027 UOT-P "Chinese OT-UniV, Books 1-5, ''Pentateuch''"
# ......................................................................
defcap chin/ptn - - - "A Chinese translation of the first five books (''[[Pentateuch]]'') of the Old Testament Bible, possibly the [[New Chinese Version]] (1992). Chinese characters were mapped 1:1 from GB (Guo Biao) to pinyn with tone marks and disambiguating suffixes, e.g, 'zuo4', 'zuo4.1', 'zuo4.2', so as to distinguish characters with the same pinyin. Each character is treated as a separate token."
defcap chin/ptn/gen.1 - 35027 NOT-1 "OT-NewV, Book 1 (''Genesis'')"
defcap chin/ptn/exo.1 - 35027 NOT-2 "OT-NewV, Book 2 (''Exodus'')"
defcap chin/ptn/num.1 - 35027 NOT-3 "OT-NewV, Book 3 (''Leviticus'')"
defcap chin/ptn/lev.1 - 35027 NOT-4 "OT-NewV, Book 4 (''Numeri'')"
defcap chin/ptn/deu.1 - 35027 NOT-5 "OT-NewV, Book 5 (''Deuteronomium'')"
defcap chin/ptn/tot.1 chin/ptn 35027 NOT-P "Chinese OT-NewV, Books 1-5 (''Pentateuch'')"
# ......................................................................
defcap chin/red - - - "The classical Chinese novel ''[[Dream of the Red Chamber]]'' or ''Dream of the Red Mansion'' (''Hong2 Lou2 Meng4'') by Cao2 Xue3 Qin2 and Gao E (~1750); with some errors and omissions. Chinese characters were mapped 1:1 from GB (Guo Biao) to pinyn with tone marks and disambiguating suffixes, e.g. 'zuo4', 'zuo4.1', 'zuo4.2', so as to distinguish characters with the same pinyin. Each character is treated as a separate token."
defcap chin/red/tot.1 chin/red 35027 Red "Dream of Red Mansion - pinyin - disamb"
# ......................................................................
defcap chin/voa - - - "Transcripts of 92 selected [[Voice of America]] broadcasts in Chinese (1996-1998). Chinese characters were mapped 1:1 from GB (Guo Biao) to pinyn with tone marks and disambiguating suffixes, e.g. 'zuo4', 'zuo4.1', 'zuo4.2'. Each Chinese character is a separate token."
defcap chin/voa/tot.1 chin/voa 35027 VoA-D "Voice of America News - pinyin - disamb."
# ######################################################################
defcap chip - - - "[[Chinese language|Chinese (Mandarin)]] - phonetic - [[pinyin]]"
defcap chip/voa - - - "Transcripts of 92 selected Voice of America broadcasts in Chinese (1996-1998). Chinese characters were converted to pinyin with tone marks, e.g. 'qing2', by Ocrat.com. Note that the same pinyin lexeme may represent two or more different Chinese characters. Each Chinese character is a separate token."
defcap chip/voa/tot.1 chip/voa 35027 VoA-H "Voice of America - pinyin - phonetic."
# ######################################################################
defcap chrc - - - "[[Chinese language|Chinese (Mandarin)]] - Roman-coded"
defcap chrc/red - - - "The classical Chinese novel ''[[Dream of the Red Chamber]]'' (''Hong2 Lou2 Meng4'') by Cao2 Xue3 Qin2 and Gao E, ~1750; with some errors and omissions. Chinese characters were mapped 1:1 from GB (Guo Biao) to a fancy number scheme similar to Roman numerals but with the structure of Voynichese lexemes, like 'ÓÖ' (= 'you4') ⟶ 'yrkso'. Each Chinese character is treated as a separate token."
defcap chrc/red/tot.1 chin/red 35027 Red-X "Dream of Red Mansion - Roman-coded"
# ######################################################################
defcap engl - - - "[[English language|English]]"
defcap engl/cpn - - - "Plant names from [[Nicholas Culpeper]]'s herbal medicine handbook ''The English Physitian'' (1652), from Richard Siderits's transcription, in the original spelling."
defcap engl/cpn/tot.1 engl/cul 35027 CpH-N "Culpeper - plant names."
defcap engl/cul - - - "Text from [[Nicholas Culpeper]]'s herbal medicine handbook ''The English Physitian'' (1652), from Richard Siderits's transcription, in the original spelling; excluding numerals, Latin insertions, marginal notes, verses, titles, etc.."
defcap engl/cul/her.1 - 35027 CpH-H "Culpeper - Herbal section."
defcap engl/cul/pre.1 - 35027 CpH-P "Culpeper - Preamble section."
defcap engl/cul/rec.1 - 35027 CpH-R "Culpeper - Recipes section."
defcap engl/cul/tot.1 engl/cul 35027 CpH "Culpeper - Preamble+Herbal+Recipes."
defcap engl/twp - - - "Text of the ''[[Wakefield Mystery Plays]]'' aka ''Towneley Mystery Plays'', popular plays on religious themes (1460). From the 1897 edition by George England, in the original spelling. The language is [[Middle English]] with archaic characters replaced."
defcap engl/twp/tot.1 engl/twp 35027 TwP "Towneley plays - English parts only."
defcap engl/wnm - - - "Proper nouns from [[H. G. Wells]]'a novel ''[[The War of the Worlds]]'' (1898), from Project Gutenberg, mapped to lowercase."
defcap engl/wnm/tot.1 engl/wow 35027 WoW-N "War of the Worlds - proper nouns."
defcap engl/wow - - - "Text of [[H. G. Wells]]'s novel ''[[The War of the Worlds]]'' (1898), from Project Gutenberg; excluding numbers, mapped to lowercase."
defcap engl/wow/tot.1 engl/wow 35027 WoW "War of the Worlds."
??? more engl texts
# ######################################################################
defcap engp - - - "Pseudo-English texts generated by [[Markov chain]]s of various orders, using English transition frequencies."
defcap engp/mkw - - - "Output of a [[Markov chain]] of order 3 - using English lowercase letter frequencies."
defcap engp/mkw/tot.1 engp/mkw 35027 MKE-3 "English Markov-3."
defcap engp/mkx - - - "Output of a [[Markov chain]] of order 2 - using English lowercase letter frequencies."
defcap engp/mkx/tot.1 engp/mkx 35027 MKE-2 "English Markov-2."
defcap engp/mky - - - "Output of a [[Markov chain]] of order 1 - using English lowercase letter frequencies."
defcap engp/mky/tot.1 engp/mky 35027 MKE-1 "English Markov-1."
defcap engp/mkz
"Output of a [[Markov chain]] of order 0 using English lowercase letter frequencies."
defcap engp/mkz/tot.1 engp/mkz 35027 MKE-0 "English Markov-0."
# ######################################################################
defcap enrc - - - "[[English language|English]], encrypted with a codebook cypher that replaces each distinct word (lexeme) with a Roman numeral, in order of decreasing frequency: like 'that' ⟶ 'xiii', 'his' ⟶ 'lxiv'. The letter 'p' is used for 5000."
defcap enrc/wow - - - "Text of [[H. G. Wells]]'s novel ''[[The War of the Worlds]]'' (1898), excluding numbers, mapped to lowercase, Roman-coded"
defcap enrc/wow/tot.1 engl/wow 35027 WoW-Rom "War of the Worlds - Roman-coded."
# ######################################################################
defcap envg - - - "[[English language|English]], encrypted with a [[Vigenère cypher]] using a 27-character alphabet (letters plus apostrophe), preserving spaces, with key 'ferrocyanide': like 'no one would have believed ...' ⟶ 'ss eds yluyl ke'i svzkbvrl ...'."
defcap envg/wow - - - "Text of [[H. G. Wells]]'s novel ''[[The War of the Worlds]]'' (1898), excluding numbers, mapped to lowercase, Vigenere-encrypted."
defcap envg/wow/tot.1 engl/wow 35027 WoW-Vig "War of the Worlds - Vigenere."
# ######################################################################
defcap envt - - - "[[English language|English]], encrypted with a codebook cypher that replaces each distinct word (lexeme) with a distinct Vietnamses syllable or syllable pair, in order of decreasing frequency."
defcap envt/wow - - - "Text of [[H. G. Wells]]'s novel ''[[The War of the Worlds]]'' (1898), excluding numbers, mapped to lowercase, with Vietnamese syllables from the Bible: like 'the' ⟶ 'ngu+o+i', 'and' ⟶ 'va\`', 'dead' ⟶ 'le^~-chuo^.c', etc. "
defcap envt/wow/tot.1 engl/wow 35027 WoW-Vie "War of the Worlds - Viet-coded."
# ######################################################################
defcap fran - - - "[[French language|French]]"
defcap fran/tal - - - "[[Jules Verne]]'s novel ''[[De la Terre à la Lune]]'' = ''From the Earth to the Moon'' (1865). Unabridged transcription by John Walker, in original spelling; excluding numbers and footnotes, mapped to lowercase."
defcap fran/tal/tot.1 fran/tal 35027 TrLn "De la Terre a la lune."
# ######################################################################
defcap geez - - - "[[Ge'ez]] (Classical Ethiopian)"
defcap geez/eno - - - "Text of the ''[[Book of Enoch]]'' (''1 Enoch''), originally in the Hebrew Bible, translated from Aramaic and/or Hebrew before 100 BCE. Published by Michal Jerabek. In the SERA encoding, with numerals excluded."
defcap geez/eno/tot.1 geez/eno 35027 Eno "First Book of Enoch."
defcap geez/gok - - - "Text of the ''[[Glory of the Kings]]'' (''Kebra Nagast''), a 14th century chronicle of Ethiopian kings, part of the Coptic Bible. Published by Michal Jerabek. In the SERA encoding, with numerals excluded."
defcap geez/gok/tot.1 geez/gok 35027 GoK "Glory of the Kings."
# ######################################################################
defcap germ - - - "[[German language|German]]"
defcap germ/sim - - - "Text of ''[[The Adventures of Simplicius Simplicissimus]]'' (''Der Abenteuerliche Simplicissimus Teutsch''), a novel by Hans von Grimmelshausen (~1669). Recast in modern spelling, excluding numerals, poems, and foreign laguage insertions. Mapped to lowercase."
defcap germ/sim/tot.1 germ/sim 35027 Simp "Simplicissimus Teutsch."
# ######################################################################
defcap grek - - - "[[Greek language|Greek]]"
defcap grek/nwt - - - "Text ''[[Byzantine text-type]]'' or ''Majority Text'' version of the ''[[New Testament]]'' in vulgar Byzantine Greek (''koiné''), from 300 CE or earlier, in a had-hoc enconding of the Greek alphabet into ISO Latin-1."
defcap grek/nwt/joh.1 - 35027 BNT-Jhn "Greek NT - Book 4 ('John'')"
defcap grek/nwt/luk.1 - 35027 BNT-Luk "Greek NT - Book 3 ('Luke'')"
defcap grek/nwt/mat.1 - 35027 BNT-Mat "Greek NT - Book 1 ('Matthew'')"
defcap grek/nwt/mrk.1 - 35027 BNT-Mrk "Greek NT - Book 2 ('Mark'')"
defcap grek/nwt/tot.1 grek/nwt 35027 BNT-G "Greek NT - 27 books."
# ######################################################################
defcap hebr - - - "[[Hebrew language|Hebrew]]"
defcap hebr/tad - - - "The first five books (''[[Torah]]'', ''Pentateuch'') of the Hebrew Bible (''Tanak''). From the 10th century version (the [[Masoretic text]]) of the original, composed mainly around ~500 BCE from earlier texts. From the ''Sacred Texts'' site, maintained by John B. Hare. In an ad-hoc single-byte encoding (JSHB) designed to look vaguely phonetic under an ISO-Latin-1 font. '''Without''' vowel points and catillation marks."
defcap hebr/tad/tot.1 hebr/tan 35027 HBD "Hebrew Bible - no vowels - Books 1-5 ''Torah'' (''Pentateuch'')."
defcap hebr/tav - - - "The first five books (''[[Torah]]'', ''Pentateuch'') of the Hebrew Bible (''Tanak''). From the 10th century version (the [[Masoretic text]]) of the original, probably composed mainly around ~500 BCE from earlier texts. From the ''Sacred Texts'' site, maintained by John B. Hare. In an ad-hoc single-byte encoding designed to look vaguely phonetic under an ISO-Latin-1 font. '''With''' vowel points but '''without''' cantillation marks."
defcap hebr/tav/gen.1 - 35027 HBV-1 "Book 1 (''Bereis'' = ''Genesis'')"
defcap hebr/tav/exo.1 - 35027 HBV-2 "Book 2 (''Shmot'' = ''Exodus'')"
defcap hebr/tav/lev.1 - 35027 HBV-3 "Book 3 (''Vaykra'' = ''Leviticus'')"
defcap hebr/tav/num.1 - 35027 HBV-4 "Book 4 (''Bamidbar'' = ''Numeri'')"
defcap hebr/tav/deu.1 - 35027 HBV-5 "Book 5 (''Devarim'' = ''Deuteronomium'')"
defcap hebr/tav/tot.1 hebr/tan 35027 HBV "Hebrew Bible - with vowels - Books 1-5 (''Torah'')."
# ######################################################################
defcap ital - - - "[[Italian language|Italian]]"
defcap ital/psp - - - "Text of [[Alessandro Manzoni]]'s novel ''I Promessi Sposi'' (''[[The Betrothed (Manzoni novel)|The Bethrothed]]'' (second writing, 1840), excluding numerals and foreign insertions, mapped to lowercase."
defcap ital/psp/tot.1 ital/psp 35027 PrSp "Promessi Sposi."
# ######################################################################
defcap latn - - - "[[Latin]]"
defcap latn/ahl - - - "Latin text of the [[Alchemists' Herbal]], compiled by [[Marco Ponzi]]."
defcap latn/ahl/tot.1 latn/ahl 35027 AHL "Alchemists' Herbal"
defcap latn/nwt - - - "The first four books (the ''Gospels'') from the Latin version (''[[Vulgate]]'') of the ''[[New Testament]]'', edited by [[St. Jerome]] around 400 CE. Converted to lowercase."
defcap latn/nwt/mat.1 - 35027 VNT-1 "Vulgate NT, Book 1 (''Matthew'')"
defcap latn/nwt/mrk.1 - 35027 VNT-2 "Vulgate NT, Book 2 (''Mark'')"
defcap latn/nwt/luk.1 - 35027 VNT-3 "Vulgate NT, Book 3 (''Luke'')"
defcap latn/nwt/joh.1 - 35027 VNT-4 "Vulgate NT, Book 4 (''John'')"
defcap latn/nwt/tot.1 latn/nwt 35027 VNT-G "Vulgate NT, Books 1-5."
defcap latn/ptt - - - "The first five books (the ''[[Pentateuch]]'') from the Latin version (''[[Vulgate]]'') of the ''Old Testament'', edited by [[St. Jerome]] around 400 CE. Converted to lowercase."
defcap latn/ptt/gen.1 - 35027 VOT-1 "Vulgate OT, Book 1 (''Genesis'')"
defcap latn/ptt/exo.1 - 35027 VOT-2 "Vulgate OT, Book 2 (''Exodus'')"
defcap latn/ptt/lev.1 - 35027 VOT-3 "Vulgate OT, Book 3 (''Leviticus'')"
defcap latn/ptt/num.1 - 35027 VOT-4 "Vulgate OT, Book 4 (''Numeri'')"
defcap latn/ptt/deu.1 - 35027 VOT-5 "Vulgate OT, Book 5 (''Deuteronomium'')"
defcap latn/ptt/tot.1 latn/ptt 35027 VOT-P "Vulgate OT, Books 1-5 (''Pentateuch'')."
defcap latn/ock - - - "The ''[[Dialogus]]'', a political treatise on by Friar [[William of Ockham]] (ca. 1340). In Medieval Latin, converted to lowercase, excluding ordinal and cardinal numerals like '3' or '3us'. "
defcap latn/ock/tot.1 latn/ock 35027 Ock "Ockam's_Dialogus, Part III.1, Books 1--2."
# ######################################################################
defcap port - - - "[[Portuguese language|Portuguese]]"
defcap port/csm - - - "Text of the novel ''[[Dom Casmurro]]'' by ''[[Machado de Assis]]'' (1899). The spelling was updated to Brazilian usage as of ~2000, incuing umlaut on 'u' after 'q', accent in 'éia' endings, differential accents 'tem'/'têm', etc. Mapped to lowercase, with numerals excluded."
defcap port/csm/tot.1 port/csm 35027 DCsm "Dom Casmurro (PT)."
# ######################################################################
defcap russ - - - "[[Russian language|Russian]]"
defcap russ/pic - - - "Text of novel ''[[Roadside Picnic]]'' (''Piknik na obochine'') by [[Arkady Strugatsky|Arkady]] and [[Boris Strugatsky]]. Transliterated from Russian to Latin letters, e.g. 'ю' ⟶ 'yu', 'щ' ⟶ 'shch', with numerals excluded."
defcap russ/pic/tot.1 russ/pic 35027 RPic "Roadside Picnic, Latin translit."
defcap russ/ptt - - - "The first five books (the ''Pentateuch'') from the [[Synodal Russian Bible]] (1876). Translated from Old Slavonic to Russian, with many archaic words. In the KOI8-R encoding, all lowercase."
defcap russ/ptt/deu.1 - 35027 SOTL-5 "Syn OT, Cyr., Book 5 (''Deuteronomium'')"
defcap russ/ptt/exo.1 - 35027 SOTL-2 "Syn OT, Cyr., Book 2 (''Exodus'')"
defcap russ/ptt/gen.1 - 35027 SOTL-1 "Syn OT, Cyr., Book 1 (''Genesis'')"
defcap russ/ptt/lev.1 - 35027 SOTL-3 "Syn OT, Cyr., Book 3 (''Leviticus'')"
defcap russ/ptt/num.1 - 35027 SOTL-4 "Syn OT, Cyr., Book 4 (''Numeri'')"
defcap russ/ptt/tot.1 russ/ptt 35027 SOTL-P "Syn OT, Cyr., Books 1-5 (''Pentateuch'')."
defcap russ/ptr - - - "The first five books (the ''Pentateuch'') from the [[Synodal Russian Bible]] (1876). Translated from Old Slavonic to Russian, with many archaic words. In Latin transliteration with digraphs and trigraphs, all lowercase."
defcap russ/ptr/deu.1 - 35027 SOTR-5 "Syn OT, trlit., Book 5 (''Deuteronomium'')"
defcap russ/ptr/exo.1 - 35027 SOTR-2 "Syn OT, trlit., Book 2 (''Exodus'')"
defcap russ/ptr/gen.1 - 35027 SOTR-1 "Syn OT, trlit., Book 1 (''Genesis'')"
defcap russ/ptr/lev.1 - 35027 SOTR-3 "Syn OT, trlit., Book 3 (''Leviticus'')"
defcap russ/ptr/num.1 - 35027 SOTR-4 "Syn OT, trlit., Book 4 (''Numeri'')"
defcap russ/ptr/tot.1 russ/ptt 35027 SOTR-P "Syn OT, trlit., Books 1-5 (''Pentateuch'')."
# ######################################################################
defcap span - - - "[[Spanish language|Spanish]]"
defcap span/qvi - - - "Text of [[Miguel de Cervantes]]'s novel ''[[Don Quixote]]''. In original spelling of early 1600s, including variable use of 'v', 'u', and 'b' for the same sound. Mapped to lowercase, excluding foreign language insertions and poems."
defcap span/qvi/one.1 span/qvi 3 35027 DQux-1 "Part I (1605)"
defcap span/qvi/two.1 span/qvi 3 35027 DQux-2 "Part II (1615)"
defcap span/qvi/tot.1 span/qvi 3 35027 DQux "Don Quixote, Parts I+II."
??? span/cas
# ######################################################################
defcap tibe - - - "[[Tibetan language|Tibetan]]"
defcap tibe/ccv - - - "Text of pages 293B--325B and 331A--398A of ''[[A Commentary to The Commentary on Valid Perception]]'', by Devendrabuddhi, translated to Tibetan by Subhutishrishanti and Ma Geway Lodro (~1050 CE). Part of the classical commentaries (''[[Tengyur]]'') on the Tibetan Buddhist Canon. Item TD4224 from the the Asian Classics Input Project (ACIP) collection, in their encoding."
defcap tibe/ccv/tot.1 tibe/ccv 35027 CVR "Comm. Comm. Valid Reasoning (part)"
defcap tibe/pmi - - - "Text of the ''[[Play of Mistaken Illusion]]'' by [[Kyabje Trijang Rinpoche]] (mid 1900s). Item 95306 from the Asian Classics Input Project (ACIP) collection."
defcap tibe/pmi/tot.1 tibe/pmi 35027 PMI "Mistaken Illusion."
defcap tibe/vim - - - "Text of pages 271A--376B of the ''[[Sutra of Vimalakirti]]'', from the [[Kangyur]], the core of the Tibetan Buddhist Canon (~600 CE). A translation from a ~100 CE Sanskrit original. Item KL0176 from the Asian Classics Input Project (ACIP) collection, in their encoding."
defcap tibe/vim/tot.1 tibe/vim 35027 Vim "Vimalakirti (part)"
# ######################################################################
defcap viep - - - "Synthetic text imitating [[Vietnamese language|Vietnamese]]."
defcap viep/grs - - - "Text created by a software implementation of the 'grille' method proposed by Gordon Rugg for the Voynich Manuscript. The three columns of his table are obtained from 520 actual Vietnamese words, split into initial consonants, vowels, and final consonants."
defcap viep/grs/tot.1 viep/grs 35027 Rugg-Vt "Pseudo-vietnamese (Rugg's grille)."
defcap viep/mky - - - "Text created by a [[Markov chain]] of order 3, trained on the Cadman Vietnamese Pentateuch."
defcap viep/mky/tot.1 viep/mky 35027 Mky3-Vt "Pseudo-vietnamese (Markov-3)."
# ######################################################################
defcap viet - - - "[[Vietnamese language|Vietnamese]]"
defcap viet/nwt - - - "The first four books (the ''Gospels'') of the [[Catholic Vietnamese New Testament]], translated by Father [[Nguye^n The^' Thua^'n]]. In the ASCII VIQR encoding, mapped to lowercase."
defcap viet/nwt/mat.1 - 35027 CatNT-1 "Catholic NT, Book 1 - (''Matthew'')"
defcap viet/nwt/mrk.1 - 35027 CatNT-2 "Catholic NT, Book 2 - (''Mark'')"
defcap viet/nwt/luk.1 - 35027 CatNT-3 "Catholic NT, Book 3 - (''Luke'')"
defcap viet/nwt/jhn.1 - 35027 CatNT-4 "Catholic NT, Book 4 - (''John'')"
defcap viet/nwt/tot.1 viet/nwt 35027 CatNT-G "Catholic NT, Books 1-4 (''Gospels'')"
defcap viet/ptt - - - "The first five books (the ''Pentateuch'') from the [[Cadman Vietnamese Bible]] (1934). Probably translated from the English [[King James Bible]]. In the ASCII VIQR encoding, mapped to lowercase, without hyphens."
defcap viet/ptt/gen.1 - 35027 CadOT-1 "Cadman OT, Book 1 (''Genesis'')"
defcap viet/ptt/exo.1 - 35027 CadOT-2 "Cadman OT, Book 2 (''Exodus'')"
defcap viet/ptt/lev.1 - 35027 CadOT-3 "Cadman OT, Book 3 (''Leviticus'')"
defcap viet/ptt/num.1 - 35027 CadOT-4 "Cadman OT, Book 4 (''Numeri'')"
defcap viet/ptt/deu.1 - 35027 CadOT-5 "Cadman OT, Book 5 (''Deuteronomium'')"
defcap viet/ptt/tot.1 viet/ptt 35027 CadOT-P "Cadman OT, Books 1-5 (''Pentateuch'')."
# ######################################################################
defcap voyn - - - "Voynichese, the language of the ''[[Voynich Manuscript]]'' - 2026 EVA transcription by R. Zandbergen and J. Stolfi."
defcap voyn/fin - - - "Last token before each paragraph break in prose (non-'label') text."
defcap voyn/fin/tot.1 - 35027 VMS-PF "Last word in parag, all parags."
defcap voyn/ini - - - "First token after each paragraph break in prose (non-'label') text."
defcap voyn/ini/tot.1 - 35027 VMS-PI "First word in parag, all parags."
defcap voyn/mid - - - "The prose text minus the first and last tokens of each paragraph."
defcap voyn/mid/tot.1 - 35027 VMS-PM "All parags minus first and last word."
defcap voyn/lab - - - "Labels, titles, word lists, and other isolated tokens"
defcap voyn/lab/bio.1 - - - "Labels, Bio or Balneo section"
defcap voyn/lab/cos.1 - - - "Labels, Cosmo and Astro section"
defcap voyn/lab/hea.1 - - - "Labels, Herbal section, language A"
defcap voyn/lab/heb.1 - - - "Labels, Herbal section, language B"
defcap voyn/lab/pha.1 - - - "Labels, Pharma section"
defcap voyn/lab/str.1 - - - "Labels, Starred or Recipes section"
defcap voyn/lab/zod.1 - - - "Labels, Zodiac section"
defcap voyn/lab/unk.1 - - - "Labels, Unknow text types ('uka' to 'uki')"
defcap voyn/lab/tot.1 - 35027 VMS-LAB "Labels, all sections."
defcap voyn/prs - - - "Prose-like parts (parags and rings), excluding 'labels'."
defcap voyn/prs/bio.1 - - - "Prose, Bio or Balneo section"
defcap voyn/prs/cos.1 - - - "Prose, Cosmo and Astro section"
defcap voyn/prs/hea.1 - - - "Prose, Herbal section, language A"
defcap voyn/prs/heb.1 - - - "Prose, Herbal section, language B"
defcap voyn/prs/pha.1 - - - "Prose, Pharma section"
defcap voyn/prs/str.1 - - - "Prose, Starred or Recipes section"
defcap voyn/prs/zod.1 - - - "Prose, Zodiac section"
defcap voyn/prs/unk.1 - - - "Prose, Unknow text types ('uka' to 'uki')"
defcap voyn/prs/tot.1 - 35027 VMS-PRS "Prose, all sections."
# ######################################################################
defcap voyp - - - "Synthetic languages imitating Voynichese, the language of the ''[[Voynich Manuscript]]''"
defcap voyp/grm - - - "Text generated manually by Gordon Rugg with his proposed 'table-and-grille method."
defcap voyp/grm/tot.1 voyp/grm 35027 Rug-M "Rugg's Pseudo-Voynichese, manual."
defcap voyp/grs - - - "Text generated by Gordon Rugg with a software implementation of his proposed 'table-and-grille' method."
defcap voyp/grs/tot.1 voyp/grs 35027 Rug-S "Rugg's Pseudo-Voynichese, software."