mirror of
https://git.pumpin.online/funkpower/catena.git
synced 2026-10-23 11:17:13 +00:00
funkpower
6f39b75d94
`Unger, Dutch Shipbuilding, 33-4` — a surname, a short title, and where in it. No year, no publisher, nothing but commas. It is how a humanities book cites a work it has already given in full, which is most of what its notes are: one book in the corpus has 2,229 such chunks and this read almost none of them. The locators trailing a short note are not part of its title — `Sjoerds, Algemene Beschryvinge, i, f I, 501-2` cites the Beschryvinge, not the Beschryvinge-comma-i-comma-f-I. An entry ending on a year is an imprint and goes on being read as one. Also: a work after a semicolon may open on a quotation mark, and the marks a style puts round a short title belong to the style. 626 more references over the 202 reference sections sampled from the corpus.
247 lines
8.2 KiB
Rust
247 lines
8.2 KiB
Rust
//! Reading a block of references end to end.
|
|
|
|
use citefind::{Kind, read};
|
|
|
|
/// A page of endnotes as conversion leaves it: numbers, anchors, and a
|
|
/// discursive note in among the citations.
|
|
const NOTES: &str = "\
|
|
[1.](part0011.html#ke_00001_00003) John MacGowan, *The Imperial History of China* (London: Curzon, 1897), p. 154.
|
|
2. I am grateful to the seminar at Leiden for pressing me on this.
|
|
[3](text0007.xhtml#en3). Johanna Bockman, *Markets in the Name of Socialism* (Stanford, CA: Stanford University Press, 2011), 40-42.
|
|
4. Ibid., p. 44.
|
|
";
|
|
|
|
#[test]
|
|
fn a_page_of_notes_keeps_its_numbering_and_drops_its_asides() {
|
|
let found = read(NOTES);
|
|
assert_eq!(found.len(), 3, "{found:#?}");
|
|
assert_eq!(
|
|
found
|
|
.iter()
|
|
.map(|one| one.marker.as_deref())
|
|
.collect::<Vec<_>>(),
|
|
[Some("1"), Some("3"), Some("4")]
|
|
);
|
|
// Numbered from zero in the order they appeared, whatever the markers say.
|
|
assert_eq!(
|
|
found.iter().map(|one| one.idx).collect::<Vec<_>>(),
|
|
[0, 1, 2]
|
|
);
|
|
assert_eq!(found[0].authors, ["John MacGowan"]);
|
|
assert_eq!(found[0].container.as_deref(), Some("Curzon"));
|
|
assert_eq!(found[1].year, Some(2011));
|
|
assert_eq!(found[1].kind, Kind::Book);
|
|
assert!(found[2].continuation);
|
|
}
|
|
|
|
#[test]
|
|
fn a_rule_of_dashes_means_the_author_above() {
|
|
let block = "\
|
|
Smith, John. *The First Book*. Oxford: Clarendon Press, 1998.
|
|
|
|
———. *The Second Book*. Oxford: Clarendon Press, 2001.
|
|
|
|
——— *The Third Book*. Oxford: Clarendon Press, 2004.
|
|
|
|
Doe, Jane. *Something Else*. Cambridge: University Press, 2005.
|
|
|
|
———. *And Another*. Cambridge: University Press, 2007.";
|
|
let found = read(block);
|
|
assert_eq!(found.len(), 5, "{found:#?}");
|
|
assert_eq!(
|
|
found
|
|
.iter()
|
|
.map(|one| one.authors.clone())
|
|
.collect::<Vec<_>>(),
|
|
[
|
|
vec!["Smith, John"],
|
|
vec!["Smith, John"],
|
|
vec!["Smith, John"],
|
|
vec!["Doe, Jane"],
|
|
vec!["Doe, Jane"],
|
|
]
|
|
);
|
|
assert_eq!(found[2].title.as_deref(), Some("The Third Book"));
|
|
}
|
|
|
|
#[test]
|
|
fn an_ibid_does_not_inherit_an_author_the_way_a_dash_does() {
|
|
let block = "\
|
|
Smith, John. *The First Book*. Oxford: Clarendon Press, 1998.
|
|
|
|
Ibid., p. 44.";
|
|
let found = read(block);
|
|
assert_eq!(found.len(), 2);
|
|
assert!(found[1].authors.is_empty(), "{:#?}", found[1]);
|
|
assert!(found[1].continuation);
|
|
}
|
|
|
|
#[test]
|
|
fn every_record_says_what_it_could_not_settle() {
|
|
let found = read(
|
|
"Marron, Kevin Ritual Abuse, Seal Books, 1988\n\nAnother, Line. Of nothing much, 1990.",
|
|
);
|
|
for one in &found {
|
|
assert_eq!(
|
|
one.unsettled,
|
|
one.missing()
|
|
.iter()
|
|
.map(|s| s.to_string())
|
|
.collect::<Vec<_>>()
|
|
);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn the_same_block_reads_the_same_way_every_time() {
|
|
assert_eq!(read(NOTES), read(NOTES));
|
|
}
|
|
|
|
/// A block mixing one entry that reads cleanly, one that gives up nothing
|
|
/// but a title, and a continuation.
|
|
const MIXED: &str = "\
|
|
1. John MacGowan, *The Imperial History of China* (London: Curzon, 1897), p. 154.
|
|
2. Marron, Kevin Ritual Abuse, Seal Books, 1988.
|
|
3. Ibid., p. 44.
|
|
";
|
|
|
|
#[test]
|
|
fn a_prompt_asks_about_the_entries_that_did_not_settle_and_no_others() {
|
|
let found = read(MIXED);
|
|
assert_eq!(found.len(), 3, "{found:#?}");
|
|
let prompt = citefind::prompt::compose(&found).expect("something unsettled");
|
|
|
|
// The entry that read cleanly is not in the question, and neither is the
|
|
// continuation — it has nothing of its own to give.
|
|
assert!(!prompt.contains("MacGowan"), "{prompt}");
|
|
assert!(!prompt.contains("Ibid"), "{prompt}");
|
|
assert!(prompt.contains("Ritual Abuse"), "{prompt}");
|
|
assert!(prompt.contains("wanted:"), "{prompt}");
|
|
}
|
|
|
|
#[test]
|
|
fn a_prompt_is_only_composed_where_there_is_something_to_ask() {
|
|
let settled = read(
|
|
"1. John MacGowan, *The Imperial History of China* (London: Curzon, 1897), p. 154.\n2. Johanna Bockman, *Markets in the Name of Socialism* (Stanford, CA: Stanford University Press, 2011), 40.",
|
|
);
|
|
assert!(
|
|
settled.iter().all(|one| one.unsettled.is_empty()),
|
|
"{settled:#?}"
|
|
);
|
|
assert_eq!(citefind::prompt::compose(&settled), None);
|
|
}
|
|
|
|
#[test]
|
|
fn a_reply_about_an_entry_that_settled_does_not_overrule_the_page() {
|
|
let mut found = read(MIXED);
|
|
let before = found[0].clone();
|
|
let filled = citefind::prompt::merge(
|
|
&mut found,
|
|
r#"{"0": {"title": "Invented", "container": "Invented"}, "2": {"title": "Invented"}}"#,
|
|
)
|
|
.expect("a reply");
|
|
assert_eq!(filled, 0);
|
|
assert_eq!(found[0], before);
|
|
assert_eq!(found[2].title, None);
|
|
}
|
|
|
|
#[test]
|
|
fn a_reply_fills_in_only_what_was_asked_about() {
|
|
let mut found = read("Marron, Kevin Ritual Abuse, Seal Books, 1988");
|
|
assert_eq!(found.len(), 1);
|
|
assert!(found[0].unsettled.contains(&"authors".to_string()));
|
|
|
|
let filled = citefind::prompt::merge(
|
|
&mut found,
|
|
"Sure!\n```json\n{\"0\": {\"authors\": [\"Marron, Kevin\"], \"year\": 1066}}\n```",
|
|
)
|
|
.expect("a reply");
|
|
assert_eq!(filled, 1);
|
|
assert_eq!(found[0].authors, ["Marron, Kevin"]);
|
|
// The year was read off the page, so the model's does not replace it.
|
|
assert_eq!(found[0].year, Some(1988));
|
|
assert!(!found[0].unsettled.contains(&"authors".to_string()));
|
|
}
|
|
|
|
#[test]
|
|
fn a_reply_that_is_not_json_is_refused_rather_than_half_applied() {
|
|
let mut found = read(NOTES);
|
|
let before = found.clone();
|
|
assert!(citefind::prompt::merge(&mut found, "I could not tell.").is_err());
|
|
assert_eq!(found, before);
|
|
}
|
|
|
|
#[test]
|
|
fn a_note_that_cites_two_works_gives_two_records() {
|
|
let found = read(
|
|
"12. Theodor W. Adorno, *Negative Dialectics*, trans. E. B. Ashton (London, 1973), 365; \
|
|
Jeffrey C. Alexander, \"On the Social Construction of Moral Universals,\" *Cultural Trauma* 5 (2002), 196.\n\
|
|
13. Smith, John. Thinking, Fast and Slow. New York: Farrar, Straus and Giroux, 2011.",
|
|
);
|
|
assert_eq!(found.len(), 3, "{found:#?}");
|
|
// Both halves of note 12 are note 12.
|
|
assert_eq!(
|
|
found
|
|
.iter()
|
|
.map(|one| one.marker.as_deref())
|
|
.collect::<Vec<_>>(),
|
|
[Some("12"), Some("12"), Some("13")]
|
|
);
|
|
assert_eq!(found[0].title.as_deref(), Some("Negative Dialectics"));
|
|
assert_eq!(
|
|
found[1].title.as_deref(),
|
|
Some("On the Social Construction of Moral Universals")
|
|
);
|
|
// The full stop between an author and a title is not a separator, or
|
|
// every bibliography entry ever written would come apart at it.
|
|
assert_eq!(found[2].title.as_deref(), Some("Thinking, Fast and Slow"));
|
|
}
|
|
|
|
#[test]
|
|
fn the_body_of_a_page_is_not_the_first_of_the_notes_at_its_foot() {
|
|
let page = format!(
|
|
"{}\n\n1. John MacGowan, *The Imperial History of China* (London: Curzon, 1897), p. 154.\n\
|
|
2. Johanna Bockman, *Markets in the Name of Socialism* (Stanford, CA: Stanford University Press, 2011), 40.",
|
|
"The obligation ran both ways, and contemporaries said so plainly whenever they were asked. ".repeat(8)
|
|
);
|
|
let found = read(&page);
|
|
assert_eq!(found.len(), 2, "{found:#?}");
|
|
assert!(
|
|
found.iter().all(|one| !one.text.contains("obligation")),
|
|
"{found:#?}"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn a_short_note_citing_two_works_gives_two_records() {
|
|
let found = read(
|
|
"12 Unger, Dutch Shipbuilding, 33-4; Unger, 'Dutch herring', 256-9.\n\
|
|
13 Van Gelder, The Two Reformations, 213, 312; Herwaarden, 'Geloof en geloofsuitingen', 403-4.",
|
|
);
|
|
assert_eq!(found.len(), 4, "{found:#?}");
|
|
assert_eq!(
|
|
found
|
|
.iter()
|
|
.map(|one| one.title.as_deref())
|
|
.collect::<Vec<_>>(),
|
|
[
|
|
Some("Dutch Shipbuilding"),
|
|
Some("Dutch herring"),
|
|
Some("The Two Reformations"),
|
|
Some("Geloof en geloofsuitingen"),
|
|
]
|
|
);
|
|
assert_eq!(
|
|
found
|
|
.iter()
|
|
.map(|one| one.marker.as_deref())
|
|
.collect::<Vec<_>>(),
|
|
[Some("12"), Some("12"), Some("13"), Some("13")]
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn nothing_citation_shaped_gives_nothing() {
|
|
assert!(read("Bibliography\n\nSee below.\n\n233\n").is_empty());
|
|
}
|