public-backup/harper
1
0
Fork 0
mirror of https://github.com/Automattic/harper.git synced 2025-12-05 19:26:55 -06:00
Code Issues Packages Projects Releases Wiki Activity

fix(core): issues with spell check (#2288)

Browse Source 
* fix(core): `SpellCheck` not properly correcting `Generaly`

* refactor(core): move higher up

* chore(core): `just format`

* fix(core): appease Clippy
This commit is contained in:
Elijah Potter
2025-12-02 14:34:36 -07:00
committed by GitHub
parent aa2cdd4029
commit 150656ee42
11 changed files with 705 additions and 590 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
harper-core/src/linting/spell_check.rs
View File

@@ -480,4 +480,12 @@ mod tests {
"'fill' is supposed to be 'fill'",
);
}
#[test]
fn issue_2261() {
assert_top3_suggestion_result(
"Generaly",
SpellCheck::new(FstDictionary::curated(), Dialect::British),
"Generally",
);
}
}

36
harper-core/src/spell/fst_dictionary.rs
View File

@@ -1,5 +1,6 @@
use super::{MutableDictionary, WordId};
use fst::{IntoStreamer, Map as FstMap, Streamer, map::StreamWithState};
use hashbrown::HashMap;
use lazy_static::lazy_static;
use levenshtein_automata::{DFA, LevenshteinAutomatonBuilder};
use std::borrow::Cow;
@@ -150,28 +151,35 @@ impl Dictionary for FstDictionary {
let upper_dists = stream_distances_vec(&mut word_indexes_stream, &dfa);
let lower_dists = stream_distances_vec(&mut word_indexes_lowercase_stream, &dfa_lowercase);
let mut merged = Vec::with_capacity(upper_dists.len());
// Merge the two results, keeping the smallest distance when both DFAs match.
// The uppercase and lowercase searches can return different result counts, so
// we can't simply zip the vectors without losing matches.
let mut merged = Vec::with_capacity(upper_dists.len().max(lower_dists.len()));
let mut best_distances = HashMap::<u64, u8>::new();
// Merge the two results
for ((i_u, dist_u), (i_l, dist_l)) in upper_dists.into_iter().zip(lower_dists.into_iter()) {
let (chosen_index, edit_distance) = if dist_u <= dist_l {
(i_u, dist_u)
} else {
(i_l, dist_l)
};
let (word, metadata) = &self.words[chosen_index as usize];
for (idx, dist) in upper_dists.into_iter().chain(lower_dists.into_iter()) {
best_distances
.entry(idx)
.and_modify(|existing| *existing = (*existing).min(dist))
.or_insert(dist);
}
for (index, edit_distance) in best_distances {
let (word, metadata) = &self.words[index as usize];
merged.push(FuzzyMatchResult {
word,
edit_distance,
metadata: Cow::Borrowed(metadata),
})
});
}
merged.sort_unstable_by_key(|v| v.word);
merged.dedup_by_key(|v| v.word);
merged.sort_unstable_by_key(|v| v.edit_distance);
// Ignore exact matches
merged.retain(|v| v.edit_distance > 0);
merged.sort_unstable_by(|a, b| {
a.edit_distance
.cmp(&b.edit_distance)
.then_with(|| a.word.cmp(b.word))
});
merged.truncate(max_results);
merged

2
harper-core/src/spell/mod.rs
View File

@@ -342,7 +342,7 @@ fn score_suggestion(misspelled_word: &[char], sug: &FuzzyMatchResult) -> i32 {
score -= 6;
}
if sug.edit_distance == 2 {
if sug.edit_distance <= 2 {
if is_ei_ie_misspelling(misspelled_word, sug.word) {
score -= 11;
}

137
harper-core/tests/text/linters/Alice's Adventures in Wonderland.snap.yml
View File

@@ -103,8 +103,8 @@ Message: |
| ^~~~~~ Did you mean to spell `centre` this way?
Suggest:
- Replace with: “center”
- Replace with: “central”
- Replace with: “censure”
- Replace with: “cent”
@@ -171,11 +171,9 @@ Suggest:
Lint: Spelling (63 priority)
Message: |
74 | again. “Dinah’ll miss me very much to-night, I should think!” (Dinah was the
| ^~~~~~~~ Did you mean to spell `Dinah’ll` this way?
| ^~~~~~~~ Did you mean `Dinah's`?
Suggest:
- Replace with: “Dinah's”
- Replace with: “Dina's”
- Replace with: “Dinah”
@@ -668,9 +666,9 @@ Message: |
320 | she began again: “Où est ma chatte?” which was the first sentence in her French
| ^~ Did you mean to spell `Où` this way?
Suggest:
- Replace with: “Os”
- Replace with: “O”
- Replace with: “OD”
- Replace with: “Of”
- Replace with: “Oh”
- Replace with: “Oi”
@@ -699,9 +697,9 @@ Message: |
320 | she began again: “Où est ma chatte?” which was the first sentence in her French
| ^~~~~~ Did you mean to spell `chatte` this way?
Suggest:
- Replace with: “chatty”
- Replace with: “chaste”
- Replace with: “chatted”
- Replace with: “chattel”
@@ -761,9 +759,9 @@ Message: |
| ^~~~ Did you mean to spell `Lory` this way?
363 | Eaglet, and several other curious creatures. Alice led the way, and the whole
Suggest:
- Replace with: “Lori”
- Replace with: “Gory”
- Replace with: “Dory”
- Replace with: “Lord”
- Replace with: “Lore”
- Replace with: “Lorry”
@@ -809,9 +807,9 @@ Message: |
| ^~~~ Did you mean to spell `Lory` this way?
376 | and would only say, “I am older than you, and must know better;” and this Alice
Suggest:
- Replace with: “Lori”
- Replace with: “Gory”
- Replace with: “Dory”
- Replace with: “Lord”
- Replace with: “Lore”
- Replace with: “Lorry”
@@ -821,9 +819,9 @@ Message: |
| ^~~~ Did you mean to spell `Lory` this way?
378 | refused to tell its age, there was no more to be said.
Suggest:
- Replace with: “Lori”
- Replace with: “Gory”
- Replace with: “Dory”
- Replace with: “Lord”
- Replace with: “Lore”
- Replace with: “Lorry”
@@ -845,8 +843,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Morcar` this way?
Suggest:
- Replace with: “Mortar”
- Replace with: “Molnar”
- Replace with: “Mopar”
- Replace with: “Mercer”
- Replace with: “Molar”
@@ -862,9 +860,9 @@ Message: |
392 | “Ugh!” said the Lory, with a shiver.
| ^~~~ Did you mean to spell `Lory` this way?
Suggest:
- Replace with: “Lori”
- Replace with: “Gory”
- Replace with: “Dory”
- Replace with: “Lord”
- Replace with: “Lore”
- Replace with: “Lorry”
@@ -873,9 +871,9 @@ Message: |
397 | “Not I!” said the Lory hastily.
| ^~~~ Did you mean to spell `Lory` this way?
Suggest:
- Replace with: “Lori”
- Replace with: “Gory”
- Replace with: “Dory”
- Replace with: “Lord”
- Replace with: “Lore”
- Replace with: “Lorry”
@@ -886,8 +884,8 @@ Message: |
400 | of Mercia and Northumbria, declared for him: and even Stigand, the patriotic
Suggest:
- Replace with: “Mortar”
- Replace with: “Molnar”
- Replace with: “Mopar”
- Replace with: “Mercer”
- Replace with: “Molar”
@@ -902,10 +900,12 @@ Message: |
Lint: Spelling (63 priority)
Message: |
400 | of Mercia and Northumbria, declared for him: and even Stigand, the patriotic
| ^~~~~~~ Did you mean `Brigand`?
| ^~~~~~~ Did you mean to spell `Stigand` this way?
401 | archbishop of Canterbury, found it advisable—’”
Suggest:
- Replace with: “Brigand”
- Replace with: “Stand”
- Replace with: “Stipend”
- Replace with: “Strand”
@@ -915,8 +915,9 @@ Message: |
412 | advisable to go with Edgar Atheling to meet William and offer him the crown.
| ^~~~~~~~ Did you mean to spell `Atheling` this way?
Suggest:
- Replace with: “Theming”
- Replace with: “Steeling”
- Replace with: “Gathering”
- Replace with: “Adhering”
- Replace with: “Fathering”
@@ -967,9 +968,9 @@ Message: |
| ^~~~ Did you mean to spell `Lory` this way?
528 | sight; and an old Crab took the opportunity of saying to her daughter “Ah, my
Suggest:
- Replace with: “Lori”
- Replace with: “Gory”
- Replace with: “Dory”
- Replace with: “Lord”
- Replace with: “Lore”
- Replace with: “Lorry”
@@ -978,9 +979,9 @@ Message: |
536 | “And who is Dinah, if I might venture to ask the question?” said the Lory.
| ^~~~ Did you mean to spell `Lory` this way?
Suggest:
- Replace with: “Lori”
- Replace with: “Gory”
- Replace with: “Dory”
- Replace with: “Lord”
- Replace with: “Lore”
- Replace with: “Lorry”
@@ -1035,11 +1036,9 @@ Suggest:
Lint: Spelling (63 priority)
Message: |
585 | I suppose Dinah’ll be sending me on messages next!” And she began fancying the
| ^~~~~~~~ Did you mean to spell `Dinah’ll` this way?
| ^~~~~~~~ Did you mean `Dinah's`?
Suggest:
- Replace with: “Dinah's”
- Replace with: “Dina's”
- Replace with: “Dinah”
@@ -1152,8 +1151,8 @@ Message: |
| ^~~~~ Did you mean to spell `arrum` this way?
Suggest:
- Replace with: “arum”
- Replace with: “atrium”
- Replace with: “argue”
- Replace with: “album”
- Replace with: “alum”
@@ -1968,7 +1967,7 @@ Message: |
Suggest:
- Replace with: “Lace”
- Replace with: “Lacier”
- Replace with: “Lacey”
- Replace with: “Lac”
@@ -1977,9 +1976,9 @@ Message: |
1555 | great hurry; “and their names were Elsie, Lacie, and Tillie; and they lived at
| ^~~~~~ Did you mean to spell `Tillie` this way?
Suggest:
- Replace with: “Billie”
- Replace with: “Lillie”
- Replace with: “Millie”
- Replace with: “Tile”
- Replace with: “Till”
- Replace with: “Till's”
@@ -2558,7 +2557,7 @@ Message: |
| ^~~~~~~ Did you mean to spell `Hjckrrh` this way?
Suggest:
- Replace with: “Hacker”
- Replace with: “Hackish”
- Replace with: “Hickory”
- Replace with: “Hackers”
@@ -2691,9 +2690,9 @@ Message: |
2206 | his flappers, “—Mystery, ancient and modern, with Seaography: then Drawling—the
| ^~~~~~~~~~ Did you mean to spell `Seaography` this way?
Suggest:
- Replace with: “Scenography”
- Replace with: “Stenography”
- Replace with: “Demography”
- Replace with: “Geography”
- Replace with: “Xerography”
@@ -3207,9 +3206,9 @@ Message: |
2477 | eagerly that the Gryphon said, in a rather offended tone, “Hm! No accounting for
| ^~ Did you mean to spell `Hm` this way?
Suggest:
- Replace with: “Him”
- Replace with: “Ho”
- Replace with: “Am”
- Replace with: “Ha”
- Replace with: “Ham”
- Replace with: “He”
@@ -3237,8 +3236,8 @@ Message: |
| ^~~ Did you mean to spell `Soo` this way?
Suggest:
- Replace with: “So”
- Replace with: “Solo”
- Replace with: “Son”
- Replace with: “Soc”
- Replace with: “Sod”
@@ -3279,8 +3278,8 @@ Message: |
| ^~~ Did you mean to spell `Soo` this way?
Suggest:
- Replace with: “So”
- Replace with: “Solo”
- Replace with: “Son”
- Replace with: “Soc”
- Replace with: “Sod”
@@ -3311,8 +3310,8 @@ Message: |
2486 | > of the e—e—evening, Beautiful, beautiful Soup!
Suggest:
- Replace with: “So”
- Replace with: “Solo”
- Replace with: “Son”
- Replace with: “Soc”
- Replace with: “Sod”
@@ -3375,8 +3374,8 @@ Message: |
| ^~~ Did you mean to spell `Soo` this way?
Suggest:
- Replace with: “So”
- Replace with: “Solo”
- Replace with: “Son”
- Replace with: “Soc”
- Replace with: “Sod”
@@ -3417,8 +3416,8 @@ Message: |
| ^~~ Did you mean to spell `Soo` this way?
Suggest:
- Replace with: “So”
- Replace with: “Solo”
- Replace with: “Son”
- Replace with: “Soc”
- Replace with: “Sod”
@@ -3449,8 +3448,8 @@ Message: |
2491 | > e—e—evening, Beautiful, beauti—FUL SOUP!”
Suggest:
- Replace with: “So”
- Replace with: “Solo”
- Replace with: “Son”
- Replace with: “Soc”
- Replace with: “Sod”
@@ -3504,9 +3503,9 @@ Message: |
2491 | > e—e—evening, Beautiful, beauti—FUL SOUP!”
| ^~~ Did you mean to spell `FUL` this way?
Suggest:
- Replace with: “FUD”
- Replace with: “F's”
- Replace with: “UL”
- Replace with: “Full”
- Replace with: “Flu”
- Replace with: “Fol”
@@ -3544,8 +3543,8 @@ Message: |
| ^~~ Did you mean to spell `Soo` this way?
Suggest:
- Replace with: “So”
- Replace with: “Solo”
- Replace with: “Son”
- Replace with: “Soc”
- Replace with: “Sod”

142
harper-core/tests/text/linters/Computer science.snap.yml
View File

@@ -11,8 +11,10 @@ Suggest:
Lint: Spelling (63 priority)
Message: |
45 | Wilhelm Schickard designed and constructed the first working mechanical
| ^~~~~~~~~ Did you mean `Schick`?
| ^~~~~~~~~ Did you mean to spell `Schickard` this way?
Suggest:
- Replace with: “Schick's”
- Replace with: “Shipyard”
- Replace with: “Schick”
@@ -22,9 +24,9 @@ Message: |
46 | calculator in 1623. In 1673, Gottfried Leibniz demonstrated a digital mechanical
| ^~~~~~~~~ Did you mean to spell `Gottfried` this way?
Suggest:
- Replace with: “Guttered”
- Replace with: “Lotteries”
- Replace with: “Notified”
- Replace with: “Pottered”
@@ -34,9 +36,9 @@ Message: |
47 | calculator, called the Stepped Reckoner. Leibniz may be considered the first
| ^~~~~~~~ Did you mean to spell `Reckoner` this way?
Suggest:
- Replace with: “Rickover”
- Replace with: “Reckoned”
- Replace with: “Beckoned”
- Replace with: “Recover”
- Replace with: “Rickover”
@@ -56,9 +58,9 @@ Message: |
50 | de Colmar launched the mechanical calculator industry[note 1] when he invented
| ^~ Did you mean to spell `de` this way?
Suggest:
- Replace with: “den”
- Replace with: “db”
- Replace with: “dc”
- Replace with: “dd”
@@ -69,8 +71,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Colmar` this way?
Suggest:
- Replace with: “Collar”
- Replace with: “Colemak”
- Replace with: “Coleman”
- Replace with: “Cellar”
- Replace with: “Clear”
@@ -104,17 +106,19 @@ Message: |
| ^~~~~~~ Did you mean to spell `Ludgate` this way?
66 | published the 2nd of the only two designs for mechanical analytical engines in
Suggest:
- Replace with: “Legate”
- Replace with: “Luggage”
- Replace with: “Luddite”
- Replace with: “Vulgate”
Lint: Spelling (63 priority)
Message: |
67 | history. In 1914, the Spanish engineer Leonardo Torres Quevedo published his
| ^~~~~~~ Did you mean `Acevedo`?
| ^~~~~~~ Did you mean to spell `Quevedo` this way?
68 | Essays on Automatics, and designed, inspired by Babbage, a theoretical
Suggest:
- Replace with: “Queued”
- Replace with: “Acevedo”
@@ -135,6 +139,9 @@ Message: |
72 | Torres presented in Paris the Electromechanical Arithmometer, a prototype that
| ^~~~~~~~~~~~ Did you mean to spell `Arithmometer` this way?
73 | demonstrated the feasibility of an electromechanical analytical engine, on which
Suggest:
- Replace with: “Arithmetic”
- Replace with: “Anemometer”
@@ -161,9 +168,9 @@ Message: |
78 | ASCC/Harvard Mark I, based on Babbage's Analytical Engine, which itself used
| ^~~~ Did you mean to spell `ASCC` this way?
Suggest:
- Replace with: “AAC”
- Replace with: “ABC”
- Replace with: “ABCs”
- Replace with: “Ac”
- Replace with: “Ace”
- Replace with: “Act”
@@ -184,9 +191,9 @@ Message: |
| ^~~~~ Did you mean to spell `ENIAC` this way?
84 | to refer to the machines rather than their human predecessors. As it became
Suggest:
- Replace with: “ENE's”
- Replace with: “Anzac”
- Replace with: “Fenian”
- Replace with: “Enact”
- Replace with: “Epic”
- Replace with: “Enc”
@@ -231,20 +238,18 @@ Message: |
| ^~~~ Did you mean to spell `Fein` this way?
106 | creation of a Graduate School in Computer Sciences analogous to the creation of
Suggest:
- Replace with: “Fen”
- Replace with: “Fern”
- Replace with: “Vein”
- Replace with: “Rein”
- Replace with: “Fin”
Lint: Spelling (63 priority)
Message: |
110 | and those of others such as numerical analyst George Forsythe, were rewarded:
| ^~~~~~~~ Did you mean to spell `Forsythe` this way?
| ^~~~~~~~ Did you mean `Forsythia`?
Suggest:
- Replace with: “Forsythia”
- Replace with: “Forster”
- Replace with: “Porsche”
@@ -254,8 +259,8 @@ Message: |
116 | Peter Naur suggested the term datalogy, to reflect the fact that the scientific
| ^~~~ Did you mean to spell `Naur` this way?
Suggest:
- Replace with: “Nauru”
- Replace with: “Nair”
- Replace with: “Nauru”
- Replace with: “Na's”
@@ -290,8 +295,8 @@ Message: |
120 | Peter Naur being the first professor in datalogy. The term is used mainly in the
| ^~~~ Did you mean to spell `Naur` this way?
Suggest:
- Replace with: “Nauru”
- Replace with: “Nair”
- Replace with: “Nauru”
- Replace with: “Na's”
@@ -314,8 +319,8 @@ Message: |
| ^~~~ Did you mean to spell `Naur` this way?
122 | science; this is now used for a multi-disciplinary field of data analysis,
Suggest:
- Replace with: “Nauru”
- Replace with: “Nair”
- Replace with: “Nauru”
- Replace with: “Na's”
@@ -498,8 +503,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Edsger` this way?
Suggest:
- Replace with: “Edger”
- Replace with: “Easter”
- Replace with: “Edgar”
- Replace with: “Eager”
- Replace with: “Edge”
@@ -534,11 +539,9 @@ Lint: Spelling (63 priority)
Message: |
155 | influenced by the work of mathematicians such as Kurt Gödel, Alan Turing, John
156 | von Neumann, Rózsa Péter and Alonzo Church and there continues to be a useful
| ^~~~~~~ Did you mean to spell `Neumann` this way?
| ^~~~~~~ Did you mean `Newman`?
Suggest:
- Replace with: “Newman”
- Replace with: “Newman's”
- Replace with: “Normans”
@@ -546,11 +549,9 @@ Lint: Spelling (63 priority)
Message: |
155 | influenced by the work of mathematicians such as Kurt Gödel, Alan Turing, John
156 | von Neumann, Rózsa Péter and Alonzo Church and there continues to be a useful
| ^~~~~ Did you mean to spell `Rózsa` this way?
| ^~~~~ Did you mean `Rosa`?
Suggest:
- Replace with: “Rosa”
- Replace with: “R's”
- Replace with: “RV's”
@@ -561,8 +562,8 @@ Message: |
| ^~~~~ Did you mean to spell `Péter` this way?
Suggest:
- Replace with: “Peter”
- Replace with: “Patel”
- Replace with: “Pete”
- Replace with: “Pother”
- Replace with: “Paper”
@@ -599,9 +600,9 @@ Message: |
| ^~~~~~ Did you mean to spell `Parnas` this way?
163 | taking a cue from the relationship between other engineering and science
Suggest:
- Replace with: “Paras”
- Replace with: “Parkas”
- Replace with: “Parana's”
- Replace with: “Parr's”
- Replace with: “Patna's”
@@ -611,9 +612,9 @@ Message: |
182 | Newell and Herbert A. Simon argued in 1975,
| ^~~~~~ Did you mean to spell `Newell` this way?
Suggest:
- Replace with: “Newel”
- Replace with: “Newels”
- Replace with: “Jewell”
- Replace with: “Nell”
- Replace with: “Newel's”
@@ -623,9 +624,9 @@ Message: |
182 | Newell and Herbert A. Simon argued in 1975,
| ^~ Did you mean to spell `A.` this way?
Suggest:
- Replace with: “Ax”
- Replace with: “A”
- Replace with: “Ab”
- Replace with: “Ac”
@@ -665,8 +666,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Edsger` this way?
Suggest:
- Replace with: “Edger”
- Replace with: “Easter”
- Replace with: “Edgar”
- Replace with: “Eager”
- Replace with: “Edge”
@@ -701,7 +702,7 @@ Message: |
Suggest:
- Replace with: “Wagner”
- Replace with: “Wigner”
- Replace with: “Warner”
- Replace with: “Wager”
@@ -713,7 +714,7 @@ Message: |
Suggest:
- Replace with: “Deming's”
- Replace with: “Dennis's”
- Replace with: “Jennings's”
- Replace with: “Dancing's”
@@ -722,9 +723,9 @@ Message: |
216 | that they are theory, abstraction (modeling), and design. Amnon H. Eden
| ^~~~~ Did you mean to spell `Amnon` this way?
Suggest:
- Replace with: “Amnion”
- Replace with: “Anon”
- Replace with: “Aaron”
- Replace with: “Amnion”
- Replace with: “Amazon”
@@ -754,9 +755,9 @@ Message: |
216 | that they are theory, abstraction (modeling), and design. Amnon H. Eden
| ^~ Did you mean to spell `H.` this way?
Suggest:
- Replace with: “Ha”
- Replace with: “He”
- Replace with: “Hi”
- Replace with: “Ht”
@@ -777,8 +778,8 @@ Message: |
232 | Computing Sciences Accreditation Board—which is made up of representatives of
Suggest:
- Replace with: “Cab”
- Replace with: “CPA”
- Replace with: “CSON”
- Replace with: “Crab”
- Replace with: “Cad”
@@ -830,8 +831,8 @@ Message: |
| ^~~~ Did you mean to spell `CSAB` this way?
Suggest:
- Replace with: “Cab”
- Replace with: “CPA”
- Replace with: “CSON”
- Replace with: “Crab”
- Replace with: “Cad”
@@ -840,9 +841,9 @@ Message: |
252 | According to Peter Denning, the fundamental question underlying computer science
| ^~~~~~~ Did you mean to spell `Denning` this way?
Suggest:
- Replace with: “Denying”
- Replace with: “Penning”
- Replace with: “Dunning”
- Replace with: “Denting”
- Replace with: “Denying”
@@ -853,7 +854,7 @@ Message: |
Suggest:
- Replace with: “Nap”
- Replace with: “Nip”
- Replace with: “Nu”
- Replace with: “No”
@@ -947,7 +948,7 @@ Message: |
Suggest:
- Replace with: “Hi”
- Replace with: “Chi”
- Replace with: “CI”
- Replace with: “Sci”
@@ -959,7 +960,7 @@ Message: |
Suggest:
- Replace with: “Hi”
- Replace with: “Chi”
- Replace with: “CI”
- Replace with: “Sci”
@@ -977,9 +978,9 @@ Message: |
393 | term "architecture" in computer literature can be traced to the work of Lyle R.
| ^~ Did you mean to spell `R.` this way?
Suggest:
- Replace with: “Re”
- Replace with: “RI”
- Replace with: “Ra”
- Replace with: “Ru”
@@ -989,7 +990,7 @@ Message: |
| ^~ Did you mean to spell `P.` this way?
Suggest:
- Replace with: “Pa”
- Replace with: “Po”
- Replace with: “Pi”
- Replace with: “PE”
@@ -1002,7 +1003,7 @@ Message: |
Suggest:
- Replace with: “Petra”
- Replace with: “Perth”
- Replace with: “Perry”
- Replace with: “Pear”
@@ -1033,6 +1034,7 @@ Message: |
Suggest:
- Replace with: “Rapport”
- Replace with: “Rappaport”
- Replace with: “Rapports”
@@ -1041,9 +1043,9 @@ Message: |
439 | - Gottfried Wilhelm Leibniz's, George Boole's, Alan Turing's, Claude Shannon's,
| ^~~~~~~~~ Did you mean to spell `Gottfried` this way?
Suggest:
- Replace with: “Guttered”
- Replace with: “Lotteries”
- Replace with: “Notified”
- Replace with: “Pottered”
@@ -1063,9 +1065,9 @@ Message: |
| ^~ Did you mean to spell `de` this way?
445 | > "high-voltage/low-voltage", etc.).
Suggest:
- Replace with: “den”
- Replace with: “db”
- Replace with: “dc”
- Replace with: “dd”
@@ -1083,9 +1085,9 @@ Message: |
458 | - Corrado Böhm and Giuseppe Jacopini's insight: there are only three ways of
| ^~~~~~~ Did you mean to spell `Corrado` this way?
Suggest:
- Replace with: “Colorado”
- Replace with: “Conrad”
- Replace with: “Coronado”
- Replace with: “Comrade”
- Replace with: “Corral”
- Replace with: “Corridor”
@@ -1094,19 +1096,18 @@ Message: |
458 | - Corrado Böhm and Giuseppe Jacopini's insight: there are only three ways of
| ^~~~ Did you mean to spell `Böhm` this way?
Suggest:
- Replace with: “Baum”
- Replace with: “Bohr”
- Replace with: “Ohm”
- Replace with: “Bah”
- Replace with: “Baht”
- Replace with: “Beam”
Lint: Spelling (63 priority)
Message: |
458 | - Corrado Böhm and Giuseppe Jacopini's insight: there are only three ways of
| ^~~~~~~~~~ Did you mean to spell `Jacopini's` this way?
| ^~~~~~~~~~ Did you mean `Jacobin's`?
Suggest:
- Replace with: “Jacobin's”
- Replace with: “Jacobi's”
@@ -1136,7 +1137,7 @@ Message: |
Suggest:
- Replace with: “Boer's”
- Replace with: “Bohr's”
- Replace with: “Ohm's”
- Replace with: “Beam's”
@@ -1144,10 +1145,9 @@ Lint: Spelling (63 priority)
Message: |
467 | - repetition: WHILE such-and-such is the case, DO this. The three rules of
468 | Boehm's and Jacopini's insight can be further simplified with the use of
| ^~~~~~~~~~ Did you mean to spell `Jacopini's` this way?
| ^~~~~~~~~~ Did you mean `Jacobin's`?
Suggest:
- Replace with: “Jacobin's”
- Replace with: “Jacobi's”
@@ -1157,8 +1157,8 @@ Message: |
469 | goto (which means it is more elementary than structured programming).
| ^~~~ Did you mean to spell `goto` this way?
Suggest:
- Replace with: “got”
- Replace with: “goo”
- Replace with: “got”
- Replace with: “goths”

24
harper-core/tests/text/linters/Difficult sentences.snap.yml
View File

@@ -23,7 +23,7 @@ Message: |
Suggest:
- Replace with: “armor”
- Replace with: “amour”
- Replace with: “armory”
- Replace with: “arbor”
@@ -42,8 +42,9 @@ Message: |
88 | By Chabad, it's different. (with, among)
| ^~~~~~ Did you mean to spell `Chabad` this way?
Suggest:
- Replace with: “Canad”
- Replace with: “Chiba”
- Replace with: “Cabal”
- Replace with: “Chad”
- Replace with: “Charade”
@@ -163,8 +164,8 @@ Message: |
| ^~~~~~ Did you mean to spell `favour` this way?
Suggest:
- Replace with: “favor”
- Replace with: “famous”
- Replace with: “flavor”
- Replace with: “flour”
@@ -213,8 +214,9 @@ Message: |
310 | Ponsonby-Smythe hit a thumping on drive.
| ^~~~~~~~ Did you mean to spell `Ponsonby` this way?
Suggest:
- Replace with: “Jonson's”
- Replace with: “Jonson”
- Replace with: “Poison”
- Replace with: “Poison's”
- Replace with: “Poisoned”
@@ -224,8 +226,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Smythe` this way?
Suggest:
- Replace with: “Scythe”
- Replace with: “Myth”
- Replace with: “Myths”
- Replace with: “Smith”
- Replace with: “Smiths”
@@ -306,11 +308,9 @@ Suggest:
Lint: Spelling (63 priority)
Message: |
358 | Smith scored again on twelve minutes, doubling Mudchester Rovers' lead.
| ^~~~~~~~~~ Did you mean to spell `Mudchester` this way?
| ^~~~~~~~~~ Did you mean `Manchester`?
Suggest:
- Replace with: “Manchester”
- Replace with: “Rochester”
- Replace with: “Winchester”
@@ -343,7 +343,7 @@ Message: |
Suggest:
- Replace with: “Pa”
- Replace with: “Par”
- Replace with: “Pre”
- Replace with: “Pi”

101
harper-core/tests/text/linters/Part-of-speech tagging.snap.yml
View File

@@ -27,9 +27,9 @@ Message: |
| ^~~ Did you mean to spell `PoS` this way?
9 | POST), also called grammatical tagging is the process of marking up a word in a
Suggest:
- Replace with: “PBS”
- Replace with: “PMS”
- Replace with: “POS”
- Replace with: “Pod”
- Replace with: “Poi”
- Replace with: “Pol”
@@ -52,7 +52,7 @@ Message: |
Suggest:
- Replace with: “Brillo's”
- Replace with: “Bill's”
- Replace with: “Trill's”
- Replace with: “Drill's”
@@ -76,9 +76,9 @@ Message: |
49 | tags. For example, NN for singular common nouns, NNS for plural common nouns, NP
| ^~ Did you mean to spell `NN` this way?
Suggest:
- Replace with: “Nun”
- Replace with: “No”
- Replace with: “Non”
- Replace with: “Na”
- Replace with: “Nu”
@@ -89,8 +89,8 @@ Message: |
50 | for singular proper nouns (see the POS tags used in the Brown Corpus). Other
Suggest:
- Replace with: “NES”
- Replace with: “Ens”
- Replace with: “INS”
- Replace with: “Nos”
- Replace with: “Nuns”
@@ -102,7 +102,7 @@ Message: |
Suggest:
- Replace with: “Nap”
- Replace with: “Nip”
- Replace with: “Nu”
- Replace with: “No”
@@ -112,9 +112,9 @@ Message: |
56 | Koine Greek (DeRose 1990) has used over 1,000 parts of speech and found that
| ^~~~~ Did you mean to spell `Koine` this way?
Suggest:
- Replace with: “Kine”
- Replace with: “Kline”
- Replace with: “Kane”
- Replace with: “Kine”
- Replace with: “Kin”
@@ -125,8 +125,8 @@ Message: |
| ^~~~~~ Did you mean to spell `DeRose` this way?
Suggest:
- Replace with: “Depose”
- Replace with: “Defoe”
- Replace with: “Denise”
- Replace with: “Debase”
- Replace with: “Decode”
@@ -157,9 +157,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Ncmsan` this way?
60 | Type = common, Gender = masculine, Number = singular, Case = accusative, Animate
Suggest:
- Replace with: “Nissan”
- Replace with: “Nisan”
- Replace with: “Nampa”
- Replace with: “Nissan”
@@ -169,9 +168,9 @@ Message: |
64 | Penn tag set, developed in the Penn Treebank project. It is largely similar to
| ^~~~~~~~ Did you mean to spell `Treebank` this way?
Suggest:
- Replace with: “Freeman”
- Replace with: “Reembark”
- Replace with: “Debank”
- Replace with: “Tie back”
- Replace with: “Tieback”
- Replace with: “Traceback”
@@ -191,8 +190,8 @@ Message: |
76 | al. have proposed a "universal" tag set, with 12 categories (for example, no
Suggest:
- Replace with: “Petrol”
- Replace with: “Pedro”
- Replace with: “Peron”
- Replace with: “Patrol”
- Replace with: “Patron”
@@ -258,6 +257,10 @@ Lint: Spelling (63 priority)
Message: |
105 | later part-of-speech tagging systems, such as CLAWS and VOLSUNGA. However, by
| ^~~~~~~~ Did you mean to spell `VOLSUNGA` this way?
Suggest:
- Replace with: “Volcanic”
- Replace with: “Volcano”
- Replace with: “Voltage”
@@ -280,9 +283,9 @@ Message: |
| ^~~~ Did you mean to spell `HMMs` this way?
120 | to disambiguate parts of speech, when working to tag the Lancaster-Oslo-Bergen
Suggest:
- Replace with: “Hems”
- Replace with: “Hams”
- Replace with: “HMO's”
- Replace with: “Hems”
- Replace with: “Hums”
@@ -291,9 +294,9 @@ Message: |
121 | Corpus of British English. HMMs involve counting cases (such as from the Brown
| ^~~~ Did you mean to spell `HMMs` this way?
Suggest:
- Replace with: “Hems”
- Replace with: “Hams”
- Replace with: “HMO's”
- Replace with: “Hems”
- Replace with: “Hums”
@@ -302,9 +305,9 @@ Message: |
129 | More advanced ("higher-order") HMMs learn the probabilities not only of pairs
| ^~~~ Did you mean to spell `HMMs` this way?
Suggest:
- Replace with: “Hems”
- Replace with: “Hams”
- Replace with: “HMO's”
- Replace with: “Hems”
- Replace with: “Hums”
@@ -328,9 +331,9 @@ Message: |
141 | Eugene Charniak points out in Statistical techniques for natural language
| ^~~~~~~~ Did you mean to spell `Charniak` this way?
Suggest:
- Replace with: “Carina”
- Replace with: “Carnap”
- Replace with: “Chadian”
- Replace with: “Cardiac”
- Replace with: “Carnal”
- Replace with: “Carnival”
@@ -362,9 +365,9 @@ Message: |
153 | HMMs underlie the functioning of stochastic taggers and are used in various
| ^~~~ Did you mean to spell `HMMs` this way?
Suggest:
- Replace with: “Hems”
- Replace with: “Hams”
- Replace with: “HMO's”
- Replace with: “Hems”
- Replace with: “Hums”
@@ -374,8 +377,8 @@ Message: |
| ^~~~~~ Did you mean to spell `DeRose` this way?
Suggest:
- Replace with: “Depose”
- Replace with: “Defoe”
- Replace with: “Denise”
- Replace with: “Debase”
- Replace with: “Decode”
@@ -397,8 +400,8 @@ Message: |
| ^~~~~~~ Did you mean to spell `Viterbi` this way?
Suggest:
- Replace with: “Vite's”
- Replace with: “Verdi”
- Replace with: “Vite”
- Replace with: “Verb”
- Replace with: “Veteran”
@@ -408,8 +411,8 @@ Message: |
| ^~~~~~ Did you mean to spell `DeRose` this way?
Suggest:
- Replace with: “Depose”
- Replace with: “Defoe”
- Replace with: “Denise”
- Replace with: “Debase”
- Replace with: “Decode”
@@ -434,7 +437,7 @@ Message: |
Suggest:
- Replace with: “Defoe's”
- Replace with: “Denise's”
- Replace with: “Repose's”
- Replace with: “Demise's”
@@ -458,7 +461,7 @@ Message: |
Suggest:
- Replace with: “Defoe's”
- Replace with: “Denise's”
- Replace with: “Repose's”
- Replace with: “Demise's”
@@ -484,8 +487,8 @@ Message: |
201 | algorithm, Brill tagger, Constraint Grammar, and the Baum-Welch algorithm (also
Suggest:
- Replace with: “Vite's”
- Replace with: “Verdi”
- Replace with: “Vite”
- Replace with: “Verb”
- Replace with: “Veteran”
@@ -496,8 +499,8 @@ Message: |
202 | known as the forward-backward algorithm). Hidden Markov model and visible Markov
Suggest:
- Replace with: “Welsh”
- Replace with: “Belch”
- Replace with: “Walsh”
- Replace with: “Wench”
- Replace with: “Watch”
@@ -507,8 +510,8 @@ Message: |
| ^~~~~~~ Did you mean to spell `Viterbi` this way?
Suggest:
- Replace with: “Vite's”
- Replace with: “Verdi”
- Replace with: “Vite”
- Replace with: “Verb”
- Replace with: “Veteran”
@@ -518,8 +521,8 @@ Message: |
| ^~~ Did you mean to spell `SVM` this way?
Suggest:
- Replace with: “Sim”
- Replace with: “Sum”
- Replace with: “SCM”
- Replace with: “SVG”
@@ -529,9 +532,9 @@ Message: |
| ^~~~~~~~ Did you mean to spell `Treebank` this way?
214 | so the results are directly comparable. However, many significant taggers are
Suggest:
- Replace with: “Freeman”
- Replace with: “Reembark”
- Replace with: “Debank”
- Replace with: “Tie back”
- Replace with: “Tieback”
- Replace with: “Traceback”

42
harper-core/tests/text/linters/Spell.US.snap.yml
View File

@@ -5,6 +5,7 @@ Message: |
Suggest:
- Replace with: “Afterward”
- Replace with: “Afterwords”
- Replace with: “Afterword's”
@@ -14,8 +15,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Centre` this way?
Suggest:
- Replace with: “Center”
- Replace with: “Entire”
- Replace with: “Entry”
- Replace with: “Censure”
- Replace with: “Cent”
@@ -25,8 +26,8 @@ Message: |
| ^~~~~~~~ Did you mean to spell `Labelled` this way?
Suggest:
- Replace with: “Labeled”
- Replace with: “Belled”
- Replace with: “Rebelled”
- Replace with: “Labeler”
- Replace with: “Labelless”
@@ -36,7 +37,8 @@ Message: |
| ^~~~~~~ Did you mean to spell `Flavour` this way?
Suggest:
- Replace with: “Flavor”
- Replace with: “Cavour”
- Replace with: “Favor”
- Replace with: “Flour”
@@ -46,8 +48,8 @@ Message: |
| ^~~~~~~~ Did you mean to spell `Favoured` this way?
Suggest:
- Replace with: “Favored”
- Replace with: “Devoured”
- Replace with: “Savored”
- Replace with: “Flavored”
- Replace with: “Floured”
@@ -57,8 +59,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Honour` this way?
Suggest:
- Replace with: “Honor”
- Replace with: “Concur”
- Replace with: “Contour”
- Replace with: “Hour”
- Replace with: “Honer”
@@ -67,18 +69,19 @@ Message: |
15 | - Grey.
| ^~~~ Did you mean to spell `Grey` this way?
Suggest:
- Replace with: “Gray”
- Replace with: “Grew”
- Replace with: “Gorey”
- Replace with: “Greg”
- Replace with: “Trey”
Lint: Spelling (63 priority)
Message: |
16 | - Quarrelled.
| ^~~~~~~~~~ Did you mean `Quarreled`?
| ^~~~~~~~~~ Did you mean to spell `Quarrelled` this way?
Suggest:
- Replace with: “Quarreled”
- Replace with: “Quarreler”
@@ -94,18 +97,21 @@ Suggest:
Lint: Spelling (63 priority)
Message: |
18 | - Recognised.
| ^~~~~~~~~~ Did you mean `Recognized`?
| ^~~~~~~~~~ Did you mean to spell `Recognised` this way?
Suggest:
- Replace with: “Recognized”
- Replace with: “Recognize”
- Replace with: “Recognizer”
Lint: Spelling (63 priority)
Message: |
19 | - Neighbour.
| ^~~~~~~~~ Did you mean `Neighbor`?
| ^~~~~~~~~ Did you mean to spell `Neighbour` this way?
Suggest:
- Replace with: “Neighbor”
- Replace with: “Neighbors”
@@ -135,17 +141,19 @@ Message: |
| ^~~~~~~ Did you mean to spell `Theatre` this way?
Suggest:
- Replace with: “Theater”
- Replace with: “Sheathe”
- Replace with: “Heater”
- Replace with: “There”
- Replace with: “They're”
Lint: Spelling (63 priority)
Message: |
23 | - Analyse.
| ^~~~~~~ Did you mean `Analyze`?
| ^~~~~~~ Did you mean to spell `Analyse` this way?
Suggest:
- Replace with: “Analyze”
- Replace with: “Analyst”
- Replace with: “Analysis”

4
harper-core/tests/text/linters/Spell.snap.yml
View File

@@ -89,8 +89,8 @@ Message: |
| ^~~~~~ Did you mean to spell `centre` this way?
Suggest:
- Replace with: “center”
- Replace with: “central”
- Replace with: “censure”
- Replace with: “cent”
@@ -110,9 +110,9 @@ Message: |
13 | At the centre of the theatre I dropped a litre of coke.
| ^~~~~ Did you mean to spell `litre` this way?
Suggest:
- Replace with: “liter”
- Replace with: “lithe”
- Replace with: “lire”
- Replace with: “lite”

52
harper-core/tests/text/linters/The Constitution of the United States.snap.yml
View File

@@ -20,8 +20,8 @@ Message: |
7 | promote the general Welfare, and secure the Blessings of Liberty to ourselves
Suggest:
- Replace with: “defense”
- Replace with: “defended”
- Replace with: “defect”
- Replace with: “decency”
- Replace with: “deface”
@@ -41,9 +41,9 @@ Message: |
11 | ## Article. I.
| ^~ Did you mean to spell `I.` this way?
Suggest:
- Replace with: “In”
- Replace with: “I”
- Replace with: “Id”
- Replace with: “IC”
- Replace with: “If”
@@ -351,8 +351,8 @@ Message: |
125 | Regulations, except as to the Places of chusing Senators.
| ^~~~~~~ Did you mean to spell `chusing` this way?
Suggest:
- Replace with: “chasing”
- Replace with: “causing”
- Replace with: “chasing”
- Replace with: “casing”
@@ -386,9 +386,10 @@ Lint: Spelling (63 priority)
Message: |
139 | Each House may determine the Rules of its Proceedings, punish its Members for
140 | disorderly Behaviour, and, with the Concurrence of two thirds, expel a Member.
| ^~~~~~~~~ Did you mean `Behavior`?
| ^~~~~~~~~ Did you mean to spell `Behaviour` this way?
Suggest:
- Replace with: “Behavior”
- Replace with: “Behaviors”
@@ -583,8 +584,8 @@ Message: |
204 | general Welfare of the United States; but all Duties, Imposts and Excises shall
Suggest:
- Replace with: “Defense”
- Replace with: “Terence”
- Replace with: “Geofence”
- Replace with: “Decency”
- Replace with: “Deface”
@@ -612,8 +613,9 @@ Message: |
229 | 9. To define and punish Piracies and Felonies committed on the high Seas, and
| ^~~~~~~~ Did you mean to spell `Piracies` this way?
Suggest:
- Replace with: “Curacies”
- Replace with: “Miracles”
- Replace with: “Piracy's”
- Replace with: “Papacies”
- Replace with: “Pirates”
@@ -624,7 +626,8 @@ Message: |
| ^~~~~~~~ Did you mean to spell `Offences` this way?
Suggest:
- Replace with: “Offenses”
- Replace with: “Fences”
- Replace with: “Offense's”
- Replace with: “Offender”
@@ -826,10 +829,12 @@ Suggest:
Lint: Spelling (63 priority)
Message: |
315 | United States; and all such Laws shall be subject to the Revision and Controul
| ^~~~~~~~ Did you mean `Control`?
| ^~~~~~~~ Did you mean to spell `Controul` this way?
316 | of the Congress.
Suggest:
- Replace with: “Control”
- Replace with: “Contour”
- Replace with: “Contrail”
@@ -994,8 +999,8 @@ Message: |
| ^~~~~~~ Did you mean to spell `chusing` this way?
384 | which they shall give their Votes; which Day shall be the same throughout the
Suggest:
- Replace with: “chasing”
- Replace with: “causing”
- Replace with: “chasing”
- Replace with: “casing”
@@ -1350,7 +1355,8 @@ Message: |
482 | States, except in Cases of Impeachment.
Suggest:
- Replace with: “Offenses”
- Replace with: “Fences”
- Replace with: “Offense's”
- Replace with: “Offender”
@@ -1413,10 +1419,11 @@ Lint: Spelling (63 priority)
Message: |
525 | time ordain and establish. The Judges, both of the supreme and inferior Courts,
526 | shall hold their Offices during good Behaviour, and shall, at stated Times,
| ^~~~~~~~~ Did you mean `Behavior`?
| ^~~~~~~~~ Did you mean to spell `Behaviour` this way?
527 | receive for their Services, a Compensation, which shall not be diminished
Suggest:
- Replace with: “Behavior”
- Replace with: “Behaviors”
@@ -1615,8 +1622,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Labour` this way?
Suggest:
- Replace with: “Labor”
- Replace with: “About”
- Replace with: “Amour”
- Replace with: “Laborer”
- Replace with: “Layout”
@@ -1627,8 +1634,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Labour` this way?
Suggest:
- Replace with: “Labor”
- Replace with: “About”
- Replace with: “Amour”
- Replace with: “Laborer”
- Replace with: “Layout”
@@ -1639,8 +1646,8 @@ Message: |
| ^~~~~~ Did you mean to spell `Labour` this way?
Suggest:
- Replace with: “Labor”
- Replace with: “About”
- Replace with: “Amour”
- Replace with: “Laborer”
- Replace with: “Layout”
@@ -1726,7 +1733,7 @@ Message: |
Suggest:
- Replace with: “Vi”
- Replace with: “Va”
- Replace with: “Vs.”
- Replace with: “Vb”
@@ -1819,6 +1826,7 @@ Message: |
715 | fifteenth Line of the first Page. The Words "is tried" being interlined between
Suggest:
- Replace with: “Erasure”
- Replace with: “Erasures”
- Replace with: “Azure”

747
harper-core/tests/text/linters/The Great Gatsby.snap.yml
View File

File diff suppressed because it is too large Load Diff