gitignore generated pdfs

Typst 0.11 now has the concept of #context's, which can be used with
counters.

.gitignore

@@ -0,0 +1 @@
+*.pdf

CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+
+## 0.2.0 (upcoming)
+
+* renamed `numbered_gloss` to `numbered-gloss`, `gloss_count` to `gloss-count`, in light of the
+Typst style preference for kebab-case. Also renamed their arguments to use snake-case as well.
+* Documented standard abbreviations
+* Removed all default gloss line formatting

README.md

@@ -4,13 +4,15 @@
 creating interlinear morpheme-by-morpheme glosses according to the [Leipzig
 glossing rules](https://www.eva.mpg.de/lingua/pdf/Glossing-Rules.pdf).
 
-Run `typst compile leipzig-gloss-examples.typ` in the root of the repository to
+# Documentation
+
+Run `typst compile documentation.typ` in the root of the repository to
 generate a pdf file with examples and documentation. This command is also
 codified in the accompanying [justfile](https://github.com/casey/just) as `just
-build-example`.
+build-doc`.
 
-The definitions intended for use by end users are the `#gloss` and
-`#numbered_gloss` functions.
+The definitions intended for use by end users are the `gloss` and
+`numbered-gloss` functions, and the `abbreviations` submodule.
 
 
 # Contributing

abbreviations-used-example.typ

@@ -0,0 +1,58 @@
+#import "abbreviations.typ": *
+
+#let custom-abbreviations = (
+  "FMNT": "Present/Future stem formant",
+)
+
+#let fmnt = emit-abbreviation("FMNT")
+
+// An example function that uses `with-used-abbreviations`
+#let print_usage_chart = with-used-abbreviations(final-used-abbreviations => {
+
+    show terms: t => {
+      for t in t.children [
+      #t.term #h(2cm) #t.description\
+      ]
+    }
+
+    let print-abbrevs(abbrv_list) = {
+      for abbrv in abbrv_list {
+        let explanation = if abbrv in standard-abbreviations {
+            standard-abbreviations.at(abbrv)
+          } else {
+            custom-abbreviations.at(abbrv)
+          }
+
+        terms((smallcaps(lower(abbrv)), explanation))
+      }
+    }
+  
+    heading(level: 3)[Abbreviations in order of use]
+    print-abbrevs(final-used-abbreviations.keys())
+
+    heading(level: 3)[Abbreviations in alphabetical order]
+    let sorted-abbreviations = final-used-abbreviations.keys().sorted()
+    print-abbrevs(sorted-abbreviations)
+})
+
+= Some linguistics paper
+
+
+== Abbreviations used in this document
+#print_usage_chart
+
+== The main body of the paper
+
+
+The #p1#sg pronoun in Spanish is _yo_. The #p2#sg pronoun in Spanish is _tu_.
+
+The six cases of Latin are:
+  - Nominative (#nom)
+  - Genitive (#gen)
+  - Dative (#dat)
+  - Accusative (#acc)
+  - Ablative (#abl)
+  - Vocative (#voc)
+
+The Present/Future stem formant (#fmnt) in Georgian disappears in perfective screeves.
+

abbreviations.typ

@@ -0,0 +1,205 @@
+// See https://www.eva.mpg.de/lingua/resources/glossing-rules.php
+#let 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",
+  "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",
+  "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",
+  "IRR": "irrealis",
+  "LOC": "locative",
+  "M": "masculine",
+  "N": "neuter",
+  "N-": [non- (e.g. #smallcaps[nsg] nonsingular, #smallcaps[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",
+  "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",
+  "REL": "relative",
+  "RES": "resultative",
+  "S": "single argument of canonical intransitive verb",
+  "SBJ": "subject",
+  "SBJV": "subjunctive",
+  "SG": "singular",
+  "TOP": "topic",
+  "TR": "transitive",
+  "VOC": "vocative",
+)
+
+// A dictionary used as a set to mark which abbreviations have been used by a call to
+// `emit-abbreviation`. Each key in the dictionary is the string symbol of that abbreviation,
+// and the value is always `true`.
+#let used-abbreviations = state("leipzig-gloss-used-abbreviations", (:))
+
+// Accepts a callback that accepts the state of the `used-abbreviations`
+// dictionary at the end of the document. Also an additional debug parameter
+#let with-used-abbreviations(callback) = {
+locate(loc => {
+    let final_used-abbreviations = used-abbreviations.final(loc)
+    callback(final_used-abbreviations)
+  })
+}
+
+#let render-abbreviation(symbol) = smallcaps(lower(symbol))
+
+// Public function. Given a symbol that is a string, emits
+// the lowercase version of that string in smallcaps format, and adds
+// its use to the `used-abbreviations` table
+#let emit-abbreviation(symbol) = {
+  let mark_used(symbol) = {
+    used-abbreviations.update(cur => {
+      cur.insert(symbol, true)
+      cur
+    })
+  }
+
+  mark_used(symbol)
+  render-abbreviation(symbol)
+}
+
+
+#let p1 = emit-abbreviation("1")
+#let p2 = emit-abbreviation("2")
+#let p3 = emit-abbreviation("3")
+#let A = emit-abbreviation("A")
+#let abl = emit-abbreviation("ABL")
+#let abs = emit-abbreviation("ABS")
+#let acc = emit-abbreviation("ACC")
+#let adj = emit-abbreviation("ADJ")
+#let adv = emit-abbreviation("ADV")
+#let agr = emit-abbreviation("AGR")
+#let all = emit-abbreviation("ALL")
+#let antip = emit-abbreviation("ANTIP")
+#let appl = emit-abbreviation("APPL")
+#let art = emit-abbreviation("ART")
+#let aux = emit-abbreviation("AUX")
+#let ben = emit-abbreviation("BEN")
+#let caus = emit-abbreviation("CAUS")
+#let clf = emit-abbreviation("CLF")
+#let com = emit-abbreviation("COM")
+#let comp = emit-abbreviation("COMP")
+#let compl = emit-abbreviation("COMPL")
+#let cond = emit-abbreviation("COND")
+#let cop = emit-abbreviation("COP")
+#let cvb = emit-abbreviation("CVB")
+#let dat = emit-abbreviation("DAT")
+#let decl = emit-abbreviation("DECL")
+#let def = emit-abbreviation("DEF")
+#let dem = emit-abbreviation("DEM")
+#let det = emit-abbreviation("DET")
+#let dist = emit-abbreviation("DIST")
+#let distr = emit-abbreviation("DISTR")
+#let du = emit-abbreviation("DU")
+#let dur = emit-abbreviation("DUR")
+#let erg = emit-abbreviation("ERG")
+#let excl = emit-abbreviation("EXCL")
+#let F = emit-abbreviation("F")
+#let foc = emit-abbreviation("FOC")
+#let fut = emit-abbreviation("FUT")
+#let gen = emit-abbreviation("GEN")
+#let imp = emit-abbreviation("IMP")
+#let incl = emit-abbreviation("INCL")
+#let ind = emit-abbreviation("IND")
+#let indf = emit-abbreviation("INDF")
+#let inf = emit-abbreviation("INF")
+#let ins = emit-abbreviation("INS")
+#let intr = emit-abbreviation("INTR")
+#let ipfv = emit-abbreviation("IPFV")
+#let irr = emit-abbreviation("IRR")
+#let loc = emit-abbreviation("LOC")
+#let M = emit-abbreviation("M")
+#let N = emit-abbreviation("N")
+#let non = emit-abbreviation("N-")
+#let neg = emit-abbreviation("NEG")
+#let nmlz = emit-abbreviation("NMLZ")
+#let nom = emit-abbreviation("NOM")
+#let obj = emit-abbreviation("OBJ")
+#let obl = emit-abbreviation("OBL")
+#let P = emit-abbreviation("P")
+#let pass = emit-abbreviation("PASS")
+#let pfv = emit-abbreviation("PFV")
+#let pl = emit-abbreviation("PL")
+#let poss = emit-abbreviation("POSS")
+#let pred = emit-abbreviation("PRED")
+#let prf = emit-abbreviation("PRF")
+#let prs = emit-abbreviation("PRS")
+#let prog = emit-abbreviation("PROG")
+#let proh = emit-abbreviation("PROH")
+#let prox = emit-abbreviation("PROX")
+#let pst = emit-abbreviation("PST")
+#let ptcp = emit-abbreviation("PTCP")
+#let purp = emit-abbreviation("PURP")
+#let Q = emit-abbreviation("Q")
+#let quot = emit-abbreviation("QUOT")
+#let recp = emit-abbreviation("RECP")
+#let refl = emit-abbreviation("REFL")
+#let rel = emit-abbreviation("REL")
+#let res = emit-abbreviation("RES")
+#let S = emit-abbreviation("S")
+#let sbj = emit-abbreviation("SBJ")
+#let sbjv = emit-abbreviation("SBJV")
+#let sg = emit-abbreviation("SG")
+#let top = emit-abbreviation("TOP")
+#let tr = emit-abbreviation("TR")
+#let voc = emit-abbreviation("VOC")
+

documentation.typ

@@ -0,0 +1,373 @@
+#set document(title: "typst leipzig-glossing documentation")
+#import "leipzig-gloss.typ": abbreviations, gloss, numbered-gloss, gloss-count
+
+#show link: x => underline[*#x*]
+
+#let codeblock-old(contents) = block(fill: luma(230), inset: 8pt, radius: 4pt, breakable: false, contents)
+
+#let codeblock(contents, addl-bindings: (:), unevaled-first-line: none) = {
+    let full-contents = if unevaled-first-line != none {
+        unevaled-first-line + "\n" + contents
+    } else {
+        contents
+    }
+
+    eval(contents, mode: "markup", scope: (gloss: gloss, numbered-gloss: numbered-gloss) + addl-bindings)
+    block(fill: luma(230), inset: 8pt, radius: 4pt, breakable: false, raw(full-contents, lang: "typst"))
+}
+
+// Abbreviations used in this document
+
+#import abbreviations: poss, prog, sg, pl, sbj, obj, fut, neg, obl, gen, com, ins, all, pst, inf
+#import abbreviations: art, dat, du, A, P, prf
+
+#let fmnt = abbreviations.emit-abbreviation("FMNT")
+
+#align(center)[#text(17pt)[Typst `leipzig-glossing` Documentation]]
+
+= Introduction
+
+Interlinear morpheme-by-morpheme glosses are common in linguistic texts to give
+information about the meanings of individual words and morphemes in the
+language being studied. A set of conventions called the *Leipzig Glossing Rules*
+was developed to give linguists a general set of standards and principles for
+how to format these glosses. The most recent version of these rules can be
+found in PDF form at
+#link("https://www.eva.mpg.de/lingua/pdf/Glossing-Rules.pdf")[this link],
+provided by the Department of Linguistics at the Max Planck Institute for
+Evolutionary Anthropology.
+
+There is a staggering variety of LaTex packages designed to properly align and
+format glosses (including `gb4e`, `ling-macros`, `linguex`, `expex`, and
+probably even more). These modules vary in the complexity of their syntax and
+the amount of control they give to the user of various aspects of formatting.
+The `typst-leipzig-glossing` module is designed to provide utilities for
+creating aligned Leipzig-style glosses in Typst, while keeping the syntax as
+intuitive as possible and allowing users as much control over how their glosses
+look as is feasible.
+
+This PDF will show examples of the module's functionality and detail relevant
+parameters. For more information or to inform devs of a bug or other issue,
+visit the module's Github repository
+#link("https://github.com/neunenak/typst-leipzig-glossing")
+
+#show raw: x => highlight(fill: luma(230), extent: 1pt)[#x]
+
+= Basic glossing functionality
+
+
+As a first example, here is a gloss of a text in Georgian, along with the Typst code used to generate it:
+
+
+#codeblock(
+"#gloss(
+    header: [from \"Georgian and the Unaccusative Hypothesis\", Alice Harris, 1982],
+    source: ([ბავშვ-ი], [ატირდა]),
+    transliteration: ([bavšv-i], [aṭirda]),
+    morphemes: ([child-#smallcaps[nom]], [3S/cry/#smallcaps[incho]/II]),
+    translation: [The child burst out crying],
+)", unevaled-first-line: "#import \"leipzig-gloss.typ\": gloss")
+
+
+And an example for English which exhibits some additional styling, and uses imports from another file
+for common glossing abbreviations:
+
+#codeblock(
+"#gloss(
+  source: ([I'm], [eat-ing], [your], [head]),
+  source-style: (item) => text(fill: red)[#item],
+  morphemes: ([1#sg.#sbj\=to.be], [eat-#prog], [2#sg.#poss], [head]),
+  morphemes-style: text.with(size: 10pt, fill: blue),
+  translation: text(weight: \"semibold\")[I'm eating your head!],
+  translation-style: (item) => [\"#item\"],
+)
+", addl-bindings: (poss: poss, prog: prog, sg: sg, sbj: sbj))
+
+
+The `#gloss` function has three pre-defined parameters for glossing levels:
+`source`, `transliteration`, and `morphemes`. It also has two parameters
+for unaligned text: `header` for text that precedes the gloss, and
+`translation` for text that follows the gloss.
+
+
+The `morphemes` param can be skipped, if you just want to provide a source
+text and translation, without a gloss:
+
+#codeblock(
+"#gloss(
+    source: ([Trato de entender, debo comprender, qué es lo que ha hecho conmigo],),
+    source-style: emph,
+    translation: [I try to understand, I must comprehend, what she has done with me],
+)
+")
+
+
+Note that it is still necessary to wrap the `source` argument in an array of length one.
+
+Here is an example of a lengthy gloss that forces a line break:
+
+// adapted from https://brill.com/fileasset/downloads_static/static_publishingbooks_formatting_glosses_linguistic_examples.pdf
+#codeblock(
+"#gloss(
+    source:    ([Ich],[arbeite],[ein],[Jahr],[um],[das],[Geld], [zu],[verdienen,],[das], [dein],[Bruder], [an],[einem],[Wochenende],[ausgibt.]),
+    source-style: text.with(weight: \"bold\"),
+    morphemes: ([I],  [work],[  one], [year],[to],[the],[money],[to],[earn,],     [that],[your],[brother],[on],[one],  [weekend],   [spends.]),
+    translation: [\"I work one year to earn the money that your brother spends in one weekend\"]
+)", addl-bindings: (poss: poss, prog: prog, sg: sg, sbj: sbj))
+
+
+To add more than three glossing lines, there is an additional parameter
+`additional-lines` that can take a list of arbitrarily many more glossing
+lines, which will appear below those specified in the aforementioned
+parameters:
+
+#codeblock(
+"#gloss(
+    header: [Hunzib (van den Berg 1995:46)],
+    source: ([ождиг],[хо#super[н]хе],[мукъер]),
+    transliteration: ([oʒdig],[χõχe],[muqʼer]),
+    morphemes: ([ož-di-g],[xõxe],[m-uq'e-r]),
+    additional-lines: (
+        ([boy-#smallcaps[obl]-#smallcaps[ad]], [tree(#smallcaps[g4])], [#smallcaps[g4]-bend-#smallcaps[pret]]),
+        ([at boy], [tree], [bent]),
+    ),
+    translation: [\"Because of the boy, the tree bent.\"]
+)
+")
+
+//TODO add a custom numbering system that can handle example 18a-c of Kartvelian Morphosyntax and Number Agreement
+== Numbering Glosses
+
+The `gloss` function takes a boolean parameter `numbering` which will add an incrementing
+count to each gloss. A function `numbered-gloss` is exported for convenience; this is
+defined as simply `#let numbered-gloss = gloss.with(numbering: true)`, and is called with the
+same arguments as `gloss`:
+
+
+#codeblock(
+"#gloss(
+    source: ([გვ-ფრცქვნ-ი],),
+    transliteration: ([gv-prtskvn-i],),
+    morphemes: ([1#pl.#obj\-peel-#fmnt],),
+    translation: \"You peeled us\",
+    numbering: true,
+)
+
+#numbered-gloss(
+    source: ([მ-ფრცქვნ-ი],),
+    transliteration: ([m-prtskvn-i],),
+    morphemes: ([1#sg.#obj\-peel-#fmnt],),
+    translation: \"You peeled me\",
+)
+
+", addl-bindings: (pl: pl, obj: obj, sg: sg, fmnt: fmnt))
+
+The displayed number for numbered glosses is iterated for each numbered gloss
+that appears throughout the document. Unnumbered glosses do not increment the
+counter for the numbered glosses.
+
+The gloss count is controlled by the Typst counter variable `gloss-count`. This
+variable can be imported from the `leipzig-gloss` package and manipulated using the
+standard Typst counter functions to control gloss numbering:
+
+#codeblock(
+"#gloss-count.update(20)
+
+#numbered-gloss(
+    header: [from _Standard Basque: A Progressive Grammar_ by Rudolf de Rijk, quoting P. Charriton],
+    source: ([Bada beti guregan zorion handi baten nahia.],),
+    translation: [There always is in us a will for a great happiness.],
+)", addl-bindings: (gloss-count: gloss-count))
+
+
+== Styling lines of a gloss
+
+Each of the aforementioned text parameters has a corresponding style parameter,
+formed by adding `-style` to its name: `header-style`, `source-style`,
+`transliteration-style`, `morphemes-style`, and `translation-style`. These parameters
+allow you to specify formatting that should be applied to each entire line of
+the gloss. This is particularly useful for the aligned gloss itself, since
+otherwise one would have to modify each content item in the list individually.
+
+In addition to these parameters, Typst’s usual content formatting can be applied
+to or within any given content block in the gloss. Formatting applied in this
+way will override any contradictory line-level formatting.
+
+#codeblock(
+"#gloss(
+    header: [This text is about eating your head.],
+    header-style: text.with(weight: \"bold\", fill: green),
+    source: (text(fill:black)[I'm], [eat-ing], [your], [head]),
+    source-style: text.with(style: \"italic\", fill: red),
+    morphemes: ([1#sg.#sbj\=to.be], text(fill:black)[eat-#prog], [2#sg.#poss], [head]),
+    morphemes-style: text.with(fill: blue),
+    translation: text(weight: \"bold\")[I'm eating your head!],
+)", addl-bindings: (prog: prog, sbj: sbj, poss: poss, sg: sg))
+
+//TODO add `line_styles` param
+
+= Standard Abbreviations
+
+The Leipzig Glossing Rules define a commonly-used set of short abbreviations
+for grammatical terms used in glosses, such as #abbreviations.acc for
+"accusative (case)", or #abbreviations.ptcp for "participle" (see "Appendix:
+List of Standard Abbreviations in the Leipzig Glossing Rules document)
+
+
+By convention, these are typeset using #smallcaps[smallcaps]. This package
+contains a module value `abbreviations`. Individual abbreviations may be
+accessed either with Typst field access notation or by importing them from
+`abbreviations`:
+
+
+#codeblock(
+"#import abbreviations: obl, sg, prf
+
+#gloss(
+    header: [(from _Why Caucasian Languages?_, by Bernard Comrie, in _Endangered Languages of the Caucasus and Beyond_)],
+    source: ([\[qálɐ-m], [∅-kw’-á\]], [ɬ’ə́-r]),
+    morphemes: ([city-#obl], [3#sg\-go-#prf], [man-#abbreviations.abs]),
+    translation: \"The man who went to the city.\"
+)", addl-bindings: (abbreviations: abbreviations), unevaled-first-line: "#import \"leipzig-gloss.typ\": abbreviations")
+
+
+The full list of abbreviations is as follows:
+
+== Full list of abbreviations
+
+#{
+for (abbreviation, description) in abbreviations.standard-abbreviations {
+        [#abbreviations.render-abbreviation(abbreviation) - #raw(lower(abbreviation)) - #description ]
+        linebreak()
+    }
+}
+
+== Custom abbreviations
+
+Custom abbreviations may be defined using the `abbreviations.emit-abbreviation` function:
+
+#codeblock(
+"#import abbreviations: obl, sg, prf, fut, emit-abbreviation
+
+#let ts = emit-abbreviation(\"TS\")
+
+#gloss(
+    header: [(from _Georgian: A Structural Reference Grammar_, by George Hewitt)],
+    source: ([g-nax-av-en],),
+    morphemes: ([you#sub[2]-see(#fut)#sub[4]-#ts#sub[7]-they#sub[11]],),
+    translation: \"they will see you\",
+)", addl-bindings: (abbreviations: abbreviations), unevaled-first-line: "#import \"leipzig-gloss.typ\": abbreviations")
+
+== Building used-abbreviations pages
+
+A user of `leipzig-glossing` might wish to generate an introductory page
+displaying which abbreviations were actually used in the document. The
+`abbreviations.with-used-abbreviations` function may be used for this purpose;
+see the `abbreviations-used-example.typ` file in `leipzig-glossing` source for an example.
+
+= Further Example Glosses
+
+These are the first twelve example glosses given in #link("https://www.eva.mpg.de/lingua/pdf/Glossing-Rules.pdf").
+along with the Typst markup needed to generate them:
+
+#{
+    gloss-count.update(0)
+}
+
+#codeblock(
+"#numbered-gloss(
+    header: [Indonesian (Sneddon 1996:237)],
+    source: ([Mereka], [di], [Jakarta], [sekarang.]),
+    morphemes: ([they], [in], [Jakarta], [now]),
+    translation: \"They are in Jakarta now\",
+)")
+
+#codeblock(
+"#numbered-gloss(
+    header: [Lezgian (Haspelmath 1993:207)],
+    source: ([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.\",
+)", addl-bindings: (fut: fut, neg: neg, obl: obl, gen:gen))
+
+#codeblock(
+"#numbered-gloss(
+    header: [West Greenlandic (Fortescue 1984:127)],
+    source: ([palasi=lu], [niuirtur=lu]),
+    morphemes: ([priest=and], [shopkeeper=and]),
+    translation: \"both the priest and the shopkeeper\",
+)")
+
+#codeblock(
+"#numbered-gloss(
+    header: [Hakha Lai],
+    source: ([a-nii -láay],),
+    morphemes: ([3#sg\-laugh-#fut],),
+    translation: [s/he will laugh],
+)", addl-bindings: (sg: sg, fut: fut))
+
+#codeblock(
+"#numbered-gloss(
+    header: [Russian],
+    source: ([My], [s], [Marko], [poexa-l-i], [avtobus-om], [v], [Peredelkino]),
+    morphemes: ([1#pl], [#com], [Marko], [go-#pst\-#pl], [bus-#ins], [#all], [Peredelkino]),
+    additional-lines: (([we], [with], [Marko], [go-#pst\-#pl], [bus-by], [to], [Peredelkino]),),
+    translation: \"Marko and I went to Perdelkino by bus\",
+)", addl-bindings: (com: com, pl: pl, ins: ins, all: all, pst:pst))
+
+#codeblock(
+"#numbered-gloss(
+    header: [Turkish],
+    source: ([çık-mak],),
+    morphemes: ([come.out-#inf],),
+    translation: \"to come out\",
+)", addl-bindings: (inf: inf))
+
+#codeblock(
+"#numbered-gloss(
+    header: [Latin],
+    source: ([insul-arum],),
+    morphemes: ([island-#gen\-#pl],),
+    translation: \"of the islands\",
+)", addl-bindings: (gen:gen, pl: pl))
+
+#codeblock(
+"#numbered-gloss(
+    header: [French],
+    source: ([aux], [chevaux]),
+    morphemes: ([to-#art\-#pl],[horse.#pl]),
+    translation: \"to the horses\",
+)",addl-bindings: (art:art, pl:pl))
+
+#codeblock(
+"#numbered-gloss(
+    header: [German],
+    source: ([unser-n], [Väter-n]),
+    morphemes: ([our-#dat\-#pl],[father.#pl\-#dat.#pl]),
+    translation: \"to our fathers\",
+)", addl-bindings: (dat:dat, pl:pl))
+
+#codeblock(
+"#numbered-gloss(
+    header: [Hittite (Lehmann 1982:211)],
+    source: ([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\",
+)", addl-bindings: (pl:pl, sg:sg, dat:dat))
+
+#codeblock(
+"#numbered-gloss(
+    header: [Jaminjung (Schultze-Berndt 2000:92)],
+    source: ([nanggayan], [guny-bi-yarluga?]),
+    morphemes: ([who], [2#du.#A.3#sg.#P\-#fut\-poke]),
+    translation: \"Who do you two want to spear?\",
+)", addl-bindings: (du:du, sg:sg, fut:fut, A:A, P:P))
+
+
+#codeblock("
+#numbered-gloss(
+    header: [Turkish (cf. 6)],
+    source: ([çık-mak],),
+    morphemes: ([come_out-#inf],),
+    translation: ['to come out'],
+)", addl-bindings: (inf: inf))

justfile

@@ -2,5 +2,10 @@ default:
     just --list
 
 
-build-example:
-    typst compile leipzig-gloss-examples.typ
+# Build the leipzig-glossing documentation PDF
+build-doc:
+    typst compile documentation.typ
+
+# Build the abbbreviations-used example
+build-abbreviations-example:
+    typst compile abbreviations-used-example.typ

leipzig-gloss-examples.typ

@@ -1,282 +0,0 @@
-#import "leipzig-gloss.typ": gloss, numbered_gloss, gloss_count
-#import "linguistic-abbreviations.typ": *
-
-#show link: x => underline[*#x*]
-//#show raw: x => text(fill: rgb("#43464b"))[#x]
-
-#let codeblock(contents) = block(fill: luma(230), inset: 8pt, radius: 4pt, breakable: false, contents)
-
-
-= Introduction
-
-Interlinear morpheme-by-morpheme glosses are common in linguistic texts to give
-information about the meanings of individual words and morphemes in the
-language being studied. A set of conventions called the *Leipzig Glossing Rules*
-was developed to give linguists a general set of standards and principles for
-how to format these glosses. The most recent version of these rules can be
-found in PDF form at
-#link("https://www.eva.mpg.de/lingua/pdf/Glossing-Rules.pdf")[this link],
-provided by the Department of Linguistics at the Max Planck Institute for
-Evolutionary Anthropology.
-
-There is a staggering variety of LaTex packages designed to properly align and
-format glosses (including `gb4e`, `ling-macros`, `linguex`, `expex`, and
-probably even more). These modules vary in the complexity of their syntax and
-the amount of control they give to the user of various aspects of formatting.
-The `typst-leipzig-glossing` module is designed to provide utilities for
-creating aligned Leipzig-style glosses in Typst, while keeping the syntax as
-intuitive as possible and allowing users as much control over how their glosses
-look as is feasible.
-
-This PDF will show examples of the module's functionality and detail relevant
-parameters. For more information or to inform devs of a bug or other issue,
-visit the module's Github repository
-#link("https://github.com/neunenak/typst-leipzig-glossing")[neunenak/typst-leipzig-glossing].
-
-= Basic glossing functionality
-
-
-As a first example, here is a gloss of a text in Georgian, along with the Typst code used to generate it:
-
-
-#gloss(
-    header_text: [from "Georgian and the Unaccusative Hypothesis", Alice Harris, 1982],
-    source_text: ([ბავშვ-ი], [ატირდა]),
-    transliteration: ([bavšv-i], [aṭirda]),
-    morphemes: ([child-#smallcaps[nom]], [3S/cry/#smallcaps[incho]/II]),
-    translation: [The child burst out crying],
-)
-
-#codeblock[
-```typst
-#gloss(
-    header_text: [from "Georgian and the Unaccusative Hypothesis", Alice Harris, 1982],
-    source_text: ([ბავშვ-ი], [ატირდა]),
-    transliteration: ([bavšv-i], [aṭirda]),
-    morphemes: ([child-#smallcaps[nom]], [3S/cry/#smallcaps[incho]/II]),
-    translation: [The child burst out crying],
-)
-```
-]
-
-And an example for English which exhibits some additional styling, and uses imports from another file
-for common glossing abbreviations:
-
-#gloss(
-  source_text: ([I'm], [eat-ing], [your], [head]),
-  source_text_style: (item) => text(fill: red)[#item],
-  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!],
-)
-
-#codeblock[
-```typst
-#import "linguistic-abbreviations.typ": *
-
-#gloss(
-  source_text: ([I'm], [eat-ing], [your], [head]),
-  source_text_style: (item) => text(fill: red)[#item],
-  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!],
-)
-```
-]
-
-
-The `#gloss` function has three pre-defined parameters for glossing levels:
-`source_text`, `transliteration`, and `morphemes`. It also has two parameters
-for unaligned text: `header_text` for text that precedes the gloss, and
-`translation` for text that follows the gloss.
-
-If one wishes to add more than three glossing lines, there is an additional
-parameter `additional_gloss_lines` that can take a list of arbitrarily many more glossing
-lines, which will appear below those specified in the aforementioned
-parameters:
-
-#gloss(
-    header_text: [Hunzib (van den Berg 1995:46)],
-    source_text: ([ождиг],[хо#super[н]хе],[мукъер]),
-    transliteration: ([oʒdig],[χõχe],[muqʼer]),
-    morphemes: ([ož-di-g],[xõxe],[m-uq'e-r]),
-    additional_gloss_lines: (
-        ([boy-#smallcaps[obl]-#smallcaps[ad]], [tree(#smallcaps[g4])], [#smallcaps[g4]-bend-#smallcaps[pret]]),
-        ([at boy], [tree], [bent]),
-    ),
-    translation: ["Because of the boy, the tree bent."]
-)
-
-#codeblock[
-```typst
-#gloss(
-    header_text: [Hunzib (van den Berg 1995:46)],
-    source_text: ([ождиг],[хо#super[н]хе],[мукъер]),
-    transliteration: ([oʒdig],[χõχe],[muqʼer]),
-    morphemes: ([ož-di-g],[xõxe],[m-uq'e-r]),
-    additional_gloss_lines: (
-        ([boy-#smallcaps[obl]-#smallcaps[ad]], [tree(#smallcaps[g4])], [#smallcaps[g4]-bend-#smallcaps[pret]]),
-        ([at boy], [tree], [bent]),
-    ),
-    translation: ["Because of the boy, the tree bent."]
-)
-```
-]
-
-To number gloss examples, use `#numbered_gloss` in place of `gloss`. All other parameters remain the same.
-
-#numbered_gloss(
-    source_text: ([გვ-ფრცქვნ-ი],),
-    source_text_style: none,
-    transliteration: ([gv-prtskvn-i],),
-    morphemes: ([1#pl.#obj\-peel-#fmnt],),
-    translation: "You peeled us",
-)
-
-#codeblock[
-```typst
-#import "linguistic-abbreviations.typ": *
-
-#gloss(
-    source_text: ([გვ-ფრცქვნ-ი],),
-    source_text_style: none,
-    transliteration: ([gv-prtskvn-i],),
-    morphemes: ([1#pl.#obj\-peel-#fmnt],),
-    translation: "You peeled us",
-```)]
-
-The displayed number for numbered glosses is iterated for each numbered gloss
-that appears throughout the document. Unnumbered glosses do not increment the
-counter for the numbered glosses.
-
-The gloss count is controlled by the Typst counter variable `gloss_count`. This
-variable can be imported from the `leipzig-gloss` package and reset using the
-standard Typst counter functions to control gloss numbering.
-
-//TODO add examples here
-
-
-== Styling lines of a gloss
-
-Each of the aforementioned text parameters has a corresponding style parameter,
-formed by adding `_style` to its name: `header_text_style`, `source_text_style`,
-`transliteration_style`, `morphemes_style`, and `translation_style`. These parameters
-allow you to specify formatting that should be applied to each entire line of
-the gloss. This is particularly useful for the aligned gloss itself, since
-otherwise one would have to modify each content item in the list individually.
-
-In addition to these parameters, Typst’s usual content formatting can be applied
-to or within any given content block in the gloss. Formatting applied in this
-way will override any contradictory line-level formatting.
-
-#gloss(
-    header_text: [This text is about eating your head.],
-    header_text_style: text.with(weight: "bold", fill: green),
-    source_text: (text(fill:black)[I'm], [eat-ing], [your], [head]),
-    source_text_style: text.with(style: "italic", fill: red),
-    morphemes: ([1#sg.#sbj\=to.be], text(fill:black)[eat-#prog], [2#sg.#pos], [head]),
-    morphemes_style: text.with(fill: blue),
-    translation: text(weight: "bold")[I'm eating your head!],
-)
-#codeblock[
-```typst
-#gloss(
-    header_text: [This text is about eating your head.],
-    header_text_style: text.with(weight: "bold", fill: green),
-    source_text: (text(fill:black)[I'm], [eat-ing], [your], [head]),
-    source_text_style: text.with(style: "italic", fill: red),
-    morphemes: ([1#sg.#sbj\=to.be], text(fill:black)[eat-#prog], [2#sg.#pos], [head]),
-    morphemes_style: text.with(fill: blue),
-    translation: text(weight: "bold")[I'm eating your head!],
-)
-```
-]
-//TODO add `line_styles` param
-
-
-== Further Example Glosses
-
-These example glosses replicate the ones given in
-#link("https://www.eva.mpg.de/lingua/pdf/Glossing-Rules.pdf").
-
-#{
-    gloss_count.update(0)
-}
-
-#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

@@ -1,6 +1,8 @@
-#let gloss_count = counter("gloss_count")
+#import "abbreviations.typ"
 
-#let build_gloss(spacing_between_items, formatters, gloss_line_lists) = {
+#let gloss-count = counter("gloss_count")
+
+#let build_gloss(item-spacing, 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()
@@ -28,86 +30,91 @@
             args.push(formatter_fn(item))
         }
         make_item_box(..args)
-        h(spacing_between_items)
+        h(item-spacing)
     }
 }
 
 
 #let gloss(
-    header_text: none,
-    header_text_style: none,
-    source_text: (),
-    source_text_style: emph,
+    header: none,
+    header-style: none,
+    source: (),
+    source-style: none,
     transliteration: none,
-    transliteration_style: none,
-    morphemes: (),
-    morphemes_style: none,
-    additional_gloss_lines: (), //List of list of content
+    transliteration-style: none,
+    morphemes: none,
+    morphemes-style: none,
+    additional-lines: (), //List of list of content
     translation: none,
-    translation_style: none,
-    spacing_between_items: 1em,
-    gloss_padding: 2.0em, //TODO document these
+    translation-style: none,
+
+    item-spacing: 1em,
+    gloss-padding: 2.0em, //TODO document these
     left_padding: 0.5em,
     numbering: false,
     breakable: 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(type(source) == "array", message: "source 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 morphemes != none {
+        assert(type(morphemes) == "array", message: "morphemes needs to be an array; perhaps you forgot to type `(` and `)`, or a trailing comma?")
+        assert(source.len() == morphemes.len(), message: "source and morphemes have different lengths")
+    }
 
     if transliteration != none {
-        assert(transliteration.len() == source_text.len(), message: "source_text and transliteration have different lengths")
+        assert(transliteration.len() == source.len(), message: "source and transliteration have different lengths")
     }
 
     let gloss_items = {
 
-        if header_text != none {
-            if header_text_style != none {
-                header_text_style(header_text)
+        if header != none {
+            if header-style != none {
+                header-style(header)
             } else {
-                header_text
+                header
             }
             linebreak()
         }
 
-        let formatters = (source_text_style,)
-        let gloss_line_lists = (source_text,)
+        let formatters = (source-style,)
+        let gloss_line_lists = (source,)
 
         if transliteration != none {
-            formatters.push(transliteration_style)
+            formatters.push(transliteration-style)
             gloss_line_lists.push(transliteration)
         }
 
-        formatters.push(morphemes_style)
-        gloss_line_lists.push(morphemes)
+        if morphemes != none {
+            formatters.push(morphemes-style)
+            gloss_line_lists.push(morphemes)
+        }
 
-        for additional in additional_gloss_lines {
+        for additional in additional-lines {
             formatters.push(none) //TODO fix this
             gloss_line_lists.push(additional)
         }
 
 
-        build_gloss(spacing_between_items, formatters, gloss_line_lists)
+        build_gloss(item-spacing, formatters, gloss_line_lists)
 
         if translation != none {
             linebreak()
 
-            if translation_style == none {
-                ["#translation"]
+            if translation-style == none {
+                translation
             } else {
-                translation_style(translation)
+                translation-style(translation)
             }
         }
     }
 
     if numbering {
-        gloss_count.step()
+        gloss-count.step()
     }
 
     let gloss_number = if numbering {
-        [(#gloss_count.display())]
+        [(#context gloss-count.display())]
     } else {
         none
     }
@@ -118,7 +125,7 @@
             dir:ltr, //TODO this needs to be more flexible
             left_padding,
             [#gloss_number],
-            gloss_padding - left_padding - measure([#gloss_number],styles).width,
+            gloss-padding - left_padding - measure([#gloss_number],styles).width,
             [#gloss_items]
             )
         ]
@@ -126,4 +133,4 @@
     )
 }
 
-#let numbered_gloss = gloss.with(numbering: true)
+#let numbered-gloss = gloss.with(numbering: true)

linguistic-abbreviations.typ

@@ -1,128 +0,0 @@
-#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])

typst.toml

@@ -1,6 +1,6 @@
 [package]
 name = "leipzig-glossing"
-version = "0.1.0"
+version = "0.2.0"
 entrypoint = "leipzig-gloss.typ"
 authors = ["Greg Shuflin", "Other open-source contributors"]
 license = "MIT"