Initial commit

justfile

@@ -0,0 +1,6 @@
+default:
+    just --list
+
+
+build-example:
+    typst leipzig-gloss-examples.typ

leipzig-gloss-examples.typ

@@ -0,0 +1,138 @@
+#import "leipzig-gloss.typ": gloss, numbered_gloss
+#import "linguistic-abbreviations.typ": *
+
+= Leipzig Glossing Examples
+
+This is the classic example of the inflected Georgian verb with an 8-segment consonant cluster:
+
+#gloss(
+    source_text: ([გვ-ფრცქვნ-ი],),
+    source_text_style: none,
+    transliteration: ([gv-prtskvn-i],),
+    morphemes: ([1pl.#obj\-peel-#fmnt],),
+    translation: "You peeled us",
+)
+
+Some more Georgian:
+
+#gloss(
+    header_text: [from "Georgian and the Unaccusative Hypothesis", Harris, 1982],
+    source_text: ([ბავშვ-ი], [ატირდა]),
+    source_text_style: (item) => text(fill: red)[#item],
+    transliteration: ([bavšv-i], [aṭirda]),
+    morphemes: ([child-#smallcaps[nom]], [3S/cry/#smallcaps[incho]/II]),
+    translation: [The child burst out crying],
+)
+
+```typst
+
+#gloss(
+    header_text: [from "Georgian and the Unaccusative Hypothesis", Harris, 1982],
+    source_text: ([ბავშვ-ი], [ატირდა]),
+    source_text_style: (item) => text(fill: red)[#item],
+    transliteration: ([bavšv-i], [aṭirda]),
+    morphemes: ([child-#smallcaps[nom]], [3S/cry/#smallcaps[incho]/II]),
+    translation: [The child burst out crying],
+)
+```
+
+And how about an example in English:
+
+#gloss(
+  source_text: ([I'm], [eat-ing], [your], [head]),
+  morphemes: ([1#sg.#sbj\=to.be], [eat-#prog], [2#sg.#pos], [head]),
+  morphemes_style: text.with(fill: blue),
+  translation: text(weight: "semibold")[I'm eating your head!],
+)
+
+```typst
+#gloss(
+  source_text: ([I'm], [eat-ing], [your], [head]),
+  morphemes: ([1#sg.#subj\=to.be], [eat-#prog], [2#sg.#pos], [head]),
+  morphemes_style: text.with(fill: blue),
+  translation: text(weight: "semibold")[I'm eating your head!],
+)
+```
+
+== Leipzig Glossing Rules PDF examples
+
+See https://www.eva.mpg.de/lingua/pdf/Glossing-Rules.pdf
+
+
+#numbered_gloss(
+    header_text: [Indonesian (Sneddon 1996:237)],
+    source_text: ([Mereka], [di], [Jakarta], [sekarang.]),
+    morphemes: ([they], [in], [Jakarta], [now]),
+    translation: "They are in Jakarta now",
+)
+
+#numbered_gloss(
+    header_text: [Lezgian (Haspelmath 1993:207)],
+    source_text: ([Gila], [abur-u-n], [ferma], [hamišaluǧ], [güǧüna], [amuq’-da-č.]),
+    morphemes: ([now], [they-#obl\-#gen], [farm], [forever], [behind], [stay-#fut\-#neg]),
+    translation: "Now their farm will not stay behind forever.",
+)
+
+#numbered_gloss(
+    header_text: [West Greenlandic (Fortescue 1984:127)],
+    source_text: ([palasi=lu], [niuirtur=lu]),
+    morphemes: ([priest=and], [shopkeeper=and]),
+    translation: "both the priest and the shopkeeper",
+)
+
+#numbered_gloss(
+    header_text: [Hakha Lai],
+    source_text: ([a-nii -láay],),
+    morphemes: ([3#sg\-laugh-#fut],),
+    translation: [s/he will laugh],
+)
+
+#numbered_gloss(
+    header_text: [Russian],
+    source_text: ([My], [s], [Marko], [poexa-l-i], [avtobus-om], [v], [Peredelkino]),
+    morphemes: ([1#pl], [#com], [Marko], [go-#pst\-#pl], [bus-#ins], [#all], [Peredelkino]),
+    additional_gloss_lines: (([we], [with], [Marko], [go-#pst\-#pl], [bus-by], [to], [Peredelkino]),),
+    translation: "Marko and I went to Perdelkino by bus",
+)
+
+#numbered_gloss(
+    header_text: [Turkish],
+    source_text: ([çık-mak],),
+    morphemes: ([come.out-#inf],),
+    translation: "to come out",
+)
+
+#numbered_gloss(
+    header_text: [Latin],
+    source_text: ([insul-arum],),
+    morphemes: ([island-#gen\-#pl],),
+    translation: "of the islands",
+)
+
+#numbered_gloss(
+    header_text: [French],
+    source_text: ([aux], [chevaux]),
+    morphemes: ([to-#art\-#pl],[horse.#pl]),
+    translation: "to the horses",
+)
+
+#numbered_gloss(
+    header_text: [German],
+    source_text: ([unser-n], [Väter-n]),
+    morphemes: ([our-#dat\-#pl],[father.#pl\-#dat.#pl]),
+    translation: "to our fathers",
+)
+
+#numbered_gloss(
+    header_text: [Hittite (Lehmann 1982:211)],
+    source_text: ([n=an], [apedani], [mehuni],[essandu.]),
+    morphemes: ([#smallcaps[conn]=him], [that.#dat.#sg], [time.#dat.#sg], [eat.they.shall]),
+    translation: "They shall celebrate him on that date",
+)
+
+#numbered_gloss(
+    header_text: [Jaminjung (Schultze-Berndt 2000:92)],
+    source_text: ([nanggayan], [guny-bi-yarluga?]),
+    morphemes: ([who], [2#du.#A.3#sg.#P\-#fut\-poke]),
+    translation: "Who do you two want to spear?",
+)

leipzig-gloss.typ

@@ -0,0 +1,104 @@
+#let gloss_count = counter("gloss_count")
+
+#let gloss_lines(spacing_between_items, formatters, gloss_line_lists) = {
+    assert(gloss_line_lists.len() > 0, message: "Gloss line lists cannot be empty")
+
+    let len = gloss_line_lists.at(0).len()
+
+    for line in gloss_line_lists {
+        assert(line.len() == len)
+    }
+
+    assert(formatters.len() == gloss_line_lists.len(), message: "The number of formatters and the number of gloss line lists should be equal")
+
+    let make_item_box(..args) = {
+        box(stack(dir: ttb, spacing: 0.5em, ..args))
+    }
+
+    for item_index in range(0, len) {
+        let args = ()
+        for line_idx, formatter in formatters {
+            let formatter_fn = if formatter == none {
+                (x) => x
+            } else {
+                formatter
+            }
+
+            let item = gloss_line_lists.at(line_idx).at(item_index)
+            args.push(formatter_fn(item))
+        }
+        make_item_box(..args)
+        h(spacing_between_items)
+    }
+}
+
+
+#let gloss(
+    header_text: none,
+    source_text: (),
+    source_text_style: emph,
+    transliteration: none,
+    transliteration_style: none,
+    morphemes: (),
+    morphemes_style: none,
+    additional_gloss_lines: (), //List of list of content
+    translation: none,
+    spacing_between_items: 1em,
+    numbering: false,
+) = {
+
+    assert(type(source_text) == "array", message: "source_text needs to be an array; perhaps you forgot to type `(` and `)`, or a trailing comma?")
+    assert(type(morphemes) == "array", message: "morphemes needs to be an array; perhaps you forgot to type `(` and `)`, or a trailing comma?")
+
+    assert(source_text.len() == morphemes.len(), message: "source_text and morphemes have different lengths")
+
+    if transliteration != none {
+        assert(transliteration.len() == source_text.len(), message: "source_text and transliteration have different lengths")
+    }
+
+    let gloss_items = {
+
+        if header_text != none {
+            header_text
+            linebreak()
+        }
+
+        let formatters = (source_text_style,)
+        let gloss_line_lists = (source_text,)
+
+        if transliteration != none {
+            formatters.push(transliteration_style)
+            gloss_line_lists.push(transliteration)
+        }
+
+        formatters.push(morphemes_style)
+        gloss_line_lists.push(morphemes)
+
+        for additional in additional_gloss_lines {
+            formatters.push(none) //TODO fix this
+            gloss_line_lists.push(additional)
+        }
+
+
+        gloss_lines(spacing_between_items, formatters, gloss_line_lists)
+
+        if translation != none {
+            linebreak()
+            ["#translation"]
+        }
+    }
+
+    let gloss_number = if numbering {
+        [(#gloss_count.display())]
+    } else {
+        none
+    }
+
+    [#gloss_number #pad(left: 1em)[#gloss_items]]
+
+    if numbering {
+        gloss_count.step()
+    }
+}
+
+#let numbered_gloss = gloss.with(numbering: true)

linguistic-abbreviations.typ

@@ -0,0 +1,128 @@
+#let fmnt = smallcaps([fmnt])
+
+
+/*
+Appendix: List of Standard Abbreviations
+
+1 first person
+2 second person
+3 third person
+A agent-like argument of canonical transitive verb
+ABL ablative
+ABS absolutive
+ACC accusative
+ADJ adjective
+ADV adverb(ial)
+AGR agreement
+ALL allative
+ANTIP antipassive
+APPL applicative
+ART article
+AUX auxiliary
+BEN benefactive
+*/
+#let A = smallcaps([a])
+#let all = smallcaps([all])
+#let art = smallcaps([art])
+
+/*
+CAUS causative
+CLF classifier
+COM comitative
+COMP complementizer
+COMPL completive
+COND conditional
+COP copula
+CVB converb
+DAT dative
+DECL declarative
+DEF definite
+DEM demonstrative
+DET determiner
+DIST distal
+*/
+#let com = smallcaps([com])
+#let dat = smallcaps([dat])
+
+/*
+DISTR distributive
+DU dual
+DUR durative
+ERG ergative
+EXCL exclusive
+F feminine
+FOC focus
+FUT future
+GEN genitive
+IMP imperative
+INCL inclusive
+IND indicative
+INDF indefinite
+INF infinitive
+INS instrumental
+INTR intransitive
+IPFV imperfective
+*/
+
+#let du = smallcaps([du])
+#let fut = smallcaps([fut])
+#let gen = smallcaps([gen])
+#let inf = smallcaps([inf])
+#let ins = smallcaps([ins])
+
+/*
+IRR irrealis
+LOC locative
+M masculine
+N neuter
+N- non- (e.g. NSG nonsingular, NPST nonpast)
+NEG negation, negative
+NMLZ nominalizer/nominalization
+NOM nominative
+OBJ object
+OBL oblique
+P patient-like argument of canonical transitive verb
+PASS passive
+PFV perfective
+PL plural
+*/
+
+#let obl = smallcaps([obl])
+#let neg = smallcaps([neg])
+#let obj = smallcaps([obj])
+#let pl = smallcaps([pl])
+/*
+POSS possessive
+PRED predicative
+PRF perfect
+PRS present
+PROG progressive
+PROH prohibitive
+PROX proximal/proximate
+PST past
+PTCP participle
+PURP purposive
+Q question particle/marker
+QUOT quotative
+RECP reciprocal
+REFL reflexive
+*/
+#let P = smallcaps([p])
+#let pos = smallcaps([pos])
+#let prog = smallcaps([prog])
+#let pst = smallcaps([pst])
+
+/*
+REL relative
+RES resultative
+S single argument of canonical intransitive verb
+SBJ subject
+SBJV subjunctive
+SG singular
+TOP topic
+TR transitive
+VOC vocative
+*/
+
+#let sg = smallcaps([sg])
+#let sbj = smallcaps([sbj])