#! /bin/bash -ue # Last edited on 2025-05-04 22:49:18 by stolfi # Creates files "descr.wik" for each language, book, and section. function defcap() { subdir="$1"; shift # Either "{lang}", "{lang}/{book}", or "{lang}/{book}/{sec}" cap="$1"; shift echo "${subdir}" 1>&2 dir="dat/${subdir}" # Ensure that ${cap} ends with ".": pat="[.]$" # Pattern must be in a variable. Bash is a crock! if [[ ! ( "${cap}" =~ $pat ) ]]; then cap="${cap}."; fi lang="${subdir%%/*}" book=""; sec=""; if [[ "${subdir}" != "${lang}" ]]; then bs="${subdir#*/}"; 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 } defcap arab "[[Arabic language|Arabic]]" 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 "Whole text." 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 "Whole text." 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 "Whole text." 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 "Whole text." 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 "Whole text." defcap chin "[[Chinese language|Chinese (Mandarin)]]" 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/deu.1 "Book 5, ''Deuteronomium''" defcap chin/ptn/exo.1 "Book 2, ''Exodus''" defcap chin/ptn/gen.1 "Book 1, ''Genesis''" defcap chin/ptn/lev.1 "Book 3, ''Leviticus''" defcap chin/ptn/num.1 "Book 4, ''Numeri''" defcap chin/ptn/tot.1 "Whole text" 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/deu.1 "Book 5, ''Deuteronomium''" defcap chin/ptt/exo.1 "Book 2, ''Exodus''" defcap chin/ptt/gen.1 "Book 1, ''Genesis''" defcap chin/ptt/lev.1 "Book 3, ''Leviticus''" defcap chin/ptt/num.1 "Book 4, ''Numeri''" defcap chin/ptt/tot.1 "Whole text." 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 "Whole text." 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 character is treated as a separate token." defcap chin/voa/tot.1 "Whole text." defcap chip "[[Chinese language|Chinese (Mandarin)]] in [[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 characters." defcap chip/voa/tot.1 "Whole text." defcap chrc "[[Chinese language|Chinese (Mandarin)]]" 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 "Whole text." 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 "Whole list." 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 "Herbal section." defcap engl/cul/pre.1 "Preamble section." defcap engl/cul/rec.1 "Recipes section." defcap engl/cul/tot.1 "Whole text." 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 "Whole text (minus Latin insertions)." 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 "Whole list." 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 "Whole text." defcap enrc "[[English language|English]], encrypted by replacing each distinct 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), mapped to lowercase, excluding numbers" defcap enrc/wow/tot.1 "Whole text." defcap envg "[[English language|English]], encrypted with a [[Vigenère cypher]] with 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." defcap envg/wow/tot.1 "Whole text." defcap envt "[[English language|English]]" defcap envt/wow "Text of [[H. G. Wells]]'s novel ''[[The War of the Worlds]]'' (1898), excluding numbers, mapped to lowercase, encrypted by replacing each distinct lexeme, in order of decreasing frequency, with a distinct Vietnamese syllable or two-syllable compound from the Vietnamese Bible, also in order of decreasing frequency: like 'the' ⟶ 'ngu+o+i', 'and' ⟶ 'va\`', 'dead' ⟶ 'le^~-chuo^.c', etc.." defcap envt/wow/tot.1 "Whole text." 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 "Whole text." 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 "Whole text." 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 "Whole text." 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 "Whole text." 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 "Book 4 - ''Gospel of John''" defcap grek/nwt/luk.1 "Book 3 - ''Gospel of Luke''" defcap grek/nwt/mat.1 "Book 1 - ''Gospel of Matthew''" defcap grek/nwt/mrk.1 "Book 2 - ''Gospel of Mark''" defcap grek/nwt/tot.1 "Whole text (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 designed to look vaguely phonetic under an ISO-Latin-1 font. '''Without''' vowel points and catillation marks." defcap hebr/tad/tot.1 "Whole text." 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/deu.1 "Book 5, ''Devarim'' (''Deuteronomium'')" defcap hebr/tav/exo.1 "Book 2, ''Shmot'' (''Exodus'')" defcap hebr/tav/gen.1 "Book 1, ''Bereis'' (''Genesis'')" defcap hebr/tav/lev.1 "Book 3, ''Vaykra'' (''Leviticus'')" defcap hebr/tav/num.1 "Book 4, ''Bamidbar'' (''Numeri'')" defcap hebr/tav/tot.1 "Whole text." 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 "Whole text." defcap latn "[[Latin]]" 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/joh.1 "Book 4 - ''Gospel of John''" defcap latn/nwt/luk.1 "Book 3 - ''Gospel of Luke''" defcap latn/nwt/mat.1 "Book 1 - ''Gospel of Matthew''" defcap latn/nwt/mrk.1 "Book 2 - ''Gospel of Mark''" defcap latn/nwt/tot.1 "All four books." 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 "Part III, Tract 1, Books 1--2." 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/deu.1 "Book 5, ''Deuteronomium''" defcap latn/ptt/exo.1 "Book 2, ''Exodus''" defcap latn/ptt/gen.1 "Book 1, ''Genesis''" defcap latn/ptt/lev.1 "Book 3, ''Leviticus''" defcap latn/ptt/num.1 "Book 4, ''Numeri''" defcap latn/ptt/tot.1 "All five books." 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 "Whole text." 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 "Whole text." defcap russ/ptt "The first five books (the ''Pentateuch'') from the [[Synodal Russian Bible]] (1876). Translated from Old Slavonic, with many archaic words. In the KOI8-R encoding, all lowercase." defcap russ/ptt/deu.1 "Book 5, ''Deuteronomium''" defcap russ/ptt/exo.1 "Book 2, ''Exodus''" defcap russ/ptt/gen.1 "Book 1, ''Genesis''" defcap russ/ptt/lev.1 "Book 3, ''Leviticus''" defcap russ/ptt/num.1 "Book 4, ''Numeri''" defcap russ/ptt/tot.1 "All five books." defcap russ/ptr "The first five books (the ''Pentateuch'') from the [[Synodal Russian Bible]] (1876). Translated from Old Slavonic, with many archaic words. Romanized, all lowercase." defcap russ/ptr/deu.1 "Book 5, ''Deuteronomium''" defcap russ/ptr/exo.1 "Book 2, ''Exodus''" defcap russ/ptr/gen.1 "Book 1, ''Genesis''" defcap russ/ptr/lev.1 "Book 3, ''Leviticus''" defcap russ/ptr/num.1 "Book 4, ''Numeri''" defcap russ/ptr/tot.1 "All five books." 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 "Part I (1605)" defcap span/qvi/two.1 "Part II (1615)" defcap span/qvi/tot.1 "Whole text." defcap tibe "[[Tibetan language|Tibetan]]" defcap tibe/ccv "Text of ''[[A Commentary to The Commentary on Valid Perception]]'', By Ravigupta. 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 "Pages 293B-325B and 331A-398A." 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 "Whole text." defcap tibe/vim "Text of the ''[[Sutra of Vimalakirti]]'', from the [[Kangyur]] (core of the Tibetan Buddhist Canon). 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 "Pages 271A-376B." 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 "Whole generated text." defcap viep/mky "Text created by a [[Markov chain]] of order 3, trained on the Cadman Vietnamese Pentateuch." defcap viep/mky/tot.1 "Whole generated text." 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/jhn.1 "Book 4 - ''Gospel of John''" defcap viet/nwt/luk.1 "Book 3 - ''Gospel of Luke''" defcap viet/nwt/mat.1 "Book 1 - ''Gospel of Matthew''" defcap viet/nwt/mrk.1 "Book 2 - ''Gospel of Mark''" defcap viet/nwt/tot.1 "All four books." 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/deu.1 "Book 5, ''Deuteronomium''" defcap viet/ptt/exo.1 "Book 2, ''Exodus''" defcap viet/ptt/gen.1 "Book 1, ''Genesis''" defcap viet/ptt/lev.1 "Book 3, ''Leviticus''" defcap viet/ptt/num.1 "Book 4, ''Numeri''" defcap viet/ptt/tot.1 "All five books." defcap voyn "Voynichese, the language of the ''[[Voynich Manuscript]]''." defcap voyn/fin "Last token after each paragraph break in prose (non-'label') text." defcap voyn/fin/tot.1 "Whole list." defcap voyn/ini "First token after each paragraph break in prose (non-'label') text." defcap voyn/ini/tot.1 "Whole list." defcap voyn/mid "The prose text minus the first and last tokens of each paragraph." defcap voyn/mid/tot.1 "Whole text." defcap voyn/lab "Labels, titles, word lists, and other isolated tokens from the Majority Vote version extracted from the Landini/Zandbergen Interlinear Transcription 1.6e6." defcap voyn/lab/bio.1 "'Biology' section" defcap voyn/lab/cos.1 "'Cosmological' section, part 1 (page f57v)" defcap voyn/lab/cos.2 "'Cosmological' section, part 2 (pages f67r1-f70r2)" defcap voyn/lab/cos.3 "'Cosmological' section, part 3 (pages f85r2,f85v2,f86v3,f86v4)" defcap voyn/lab/hea.1 "'Herbal' section, language A, part 1 (pages f1v-f11v,f13r-f25v,f27r-f30v,f32r,f32v,f35r-f38v,f42r,f42v,f44r-f45v,f47r,f47v,f51r-f54v,f56r,f56v)" defcap voyn/lab/hea.2 "'Herbal' section, language A, part 2 (pages f87r,f87v,f90r1-f90v2,f93r,f93v,f96r,f96v)" defcap voyn/lab/heb.1 "'Herbal' section, language B, part 1 (pages f26r,f26v,f31r,f31v,f33r-f34v,f39r-f41v,f43r,f43v,f46r,f46v,f48r,f48v,f50r,f50v,f55r,f55v,f57r,f66v)" defcap voyn/lab/heb.2 "'Herbal' section, language B, part 2 (pages f94r-f95v2)" defcap voyn/lab/pha.1 "'Pharma' section, part 1 (pages f88r-f89v2)" defcap voyn/lab/pha.2 "'Pharma' section, part 2 (pages f99r-f102v2)" defcap voyn/lab/str.1 "'Stars' section, part 1 (folio f58r)" defcap voyn/lab/str.2 "'Stars' section, part 2 (pages f103r-f108v,f111r-f115v,f116r)" defcap voyn/lab/unk.1 "Page f1r, unknown text type" defcap voyn/lab/unk.2 "Page f49v, unknown text type" defcap voyn/lab/unk.3 "Pages f65r and f65v, unknown text type" defcap voyn/lab/unk.4 "Page f66r, unknown text type" defcap voyn/lab/unk.5 "Page f85r1, unknown text type" defcap voyn/lab/unk.6 "Page f86v6, unknown text type" defcap voyn/lab/unk.7 "Page f86v5, unknown text type" defcap voyn/lab/unk.8 "Page 116v, unknown text type" defcap voyn/lab/zod.1 "'Zodiac' section (pages f70v1,f70v2,f71r-f73v)" defcap voyn/lab/tot.1 "Whole list." defcap voyn/maj "The Majority Vote version of the text, including 'labels'. Extracted from the Landini/Zandbergen Interlinear Transcription 1.6e6." defcap voyn/maj/bio.1 "'Biology' section" defcap voyn/maj/cos.1 "'Cosmological' section, part 1 (page f57v)" defcap voyn/maj/cos.2 "'Cosmological' section, part 2 (pages f67r1-f70r2)" defcap voyn/maj/cos.3 "'Cosmological' section, part 3 (pages f85r2,f85v2,f86v3,f86v4)" defcap voyn/maj/hea.1 "'Herbal' section, language A, part 1 (pages f1v-f11v,f13r-f25v,f27r-f30v,f32r,f32v,f35r-f38v,f42r,f42v,f44r-f45v,f47r,f47v,f51r-f54v,f56r,f56v)" defcap voyn/maj/hea.2 "'Herbal' section, language A, part 2 (pages f87r,f87v,f90r1-f90v2,f93r,f93v,f96r,f96v)" defcap voyn/maj/heb.1 "'Herbal' section, language B, part 1 (pages f26r,f26v,f31r,f31v,f33r-f34v,f39r-f41v,f43r,f43v,f46r,f46v,f48r,f48v,f50r,f50v,f55r,f55v,f57r,f66v)" defcap voyn/maj/heb.2 "'Herbal' section, language B, part 2 (pages f94r-f95v2)" defcap voyn/maj/pha.1 "'Pharma' section, part 1 (pages f88r-f89v2)" defcap voyn/maj/pha.2 "'Pharma' section, part 2 (pages f99r-f102v2)" defcap voyn/maj/str.1 "'Stars' section, part 1 (folio f58r)" defcap voyn/maj/str.2 "'Stars' section, part 2 (pages f103r-f108v,f111r-f115v,f116r)" defcap voyn/maj/unk.1 "Page f1r, unknown text type" defcap voyn/maj/unk.2 "Page f49v, unknown text type" defcap voyn/maj/unk.3 "Pages f65r and f65v, unknown text type" defcap voyn/maj/unk.4 "Page f66r, unknown text type" defcap voyn/maj/unk.5 "Page f85r1, unknown text type" defcap voyn/maj/unk.6 "Page f86v6, unknown text type" defcap voyn/maj/unk.7 "Page f86v5, unknown text type" defcap voyn/maj/unk.8 "Page 116v, unknown text type" defcap voyn/maj/zod.1 "'Zodiac' section (pages f70v1,f70v2,f71r-f73v)" defcap voyn/maj/tot.1 "Whole text." defcap voyn/prs "Prose-like parts from Majority Vote version of the text, excluding 'labels'. Extracted from the Landini/Zandbergen Interlinear Transcription 1.6e6." defcap voyn/prs/bio.1 "'Biology' section" defcap voyn/prs/cos.1 "'Cosmological' section, part 1 (page f57v)" defcap voyn/prs/cos.2 "'Cosmological' section, part 2 (pages f67r1-f70r2)" defcap voyn/prs/cos.3 "'Cosmological' section, part 3 (pages f85r2,f85v2,f86v3,f86v4)" defcap voyn/prs/hea.1 "'Herbal' section, language A, part 1 (pages f1v-f11v,f13r-f25v,f27r-f30v,f32r,f32v,f35r-f38v,f42r,f42v,f44r-f45v,f47r,f47v,f51r-f54v,f56r,f56v)" defcap voyn/prs/hea.2 "'Herbal' section, language A, part 2 (pages f87r,f87v,f90r1-f90v2,f93r,f93v,f96r,f96v)" defcap voyn/prs/heb.1 "'Herbal' section, language B, part 1 (pages f26r,f26v,f31r,f31v,f33r-f34v,f39r-f41v,f43r,f43v,f46r,f46v,f48r,f48v,f50r,f50v,f55r,f55v,f57r,f66v)" defcap voyn/prs/heb.2 "'Herbal' section, language B, part 2 (pages f94r-f95v2)" defcap voyn/prs/pha.1 "'Pharma' section, part 1 (pages f88r-f89v2)" defcap voyn/prs/pha.2 "'Pharma' section, part 2 (pages f99r-f102v2)" defcap voyn/prs/str.1 "'Stars' section, part 1 (folio f58r)" defcap voyn/prs/str.2 "'Stars' section, part 2 (pages f103r-f108v,f111r-f115v,f116r)" defcap voyn/prs/unk.1 "Page f1r, unknown text type" defcap voyn/prs/unk.2 "Page f49v, unknown text type" defcap voyn/prs/unk.3 "Pages f65r and f65v, unknown text type" defcap voyn/prs/unk.4 "Page f66r, unknown text type" defcap voyn/prs/unk.5 "Page f85r1, unknown text type" defcap voyn/prs/unk.6 "Page f86v6, unknown text type" defcap voyn/prs/unk.7 "Page f86v5, unknown text type" defcap voyn/prs/unk.8 "Page 116v, unknown text type" defcap voyn/prs/zod.1 "'Zodiac' section (pages f70v1,f70v2,f71r-f73v)" defcap voyn/prs/tot.1 "Whole prose text." defcap voyn/tak "Takeshi Takahasi's transcription of the text, including 'labels', extracted from the Landini/Zandbergen Interlinear Transcription 1.6e6." defcap voyn/tak/tot.1 "Whole text." 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 "Whole text." defcap voyp/grs "Text generated by Gordon Rugg with a software implementation of his proposed 'table-and-grille' method." defcap voyp/grs/tot.1 "Whole text."