mirror of
https://github.com/storytold/wordcraft.git
synced 2026-10-30 13:27:27 -06:00
Federico Olivares
56b0ff7760
Maintainer review on #3562: - words() keeps combining marks with the word they follow, so a word typed decomposed (NFD, `tambie\u{301}n`) is one word with its own byte range; is_correct_in_with and suggest_in look it up composed (NFC), so it is checked like `también` in every language (unicode-normalization, MIT/Apache) - the Spanish missing-¿/¡ rule skips marks in web and e-mail addresses (`Ver https://example.com/?`), and punctuation inside an address or a word (`example.com`, `https:`, `10:30`) no longer starts the sentence the opening mark is offered for; a mark ending an address still ends a sentence - Spanish repeated-word check matches composed and decomposed spellings - regressions: check_text with the Spanish fixture and NFC/NFD equivalents (acceptance and ranges), words() and composed(), URLs ending in /? beside ordinary questions CodeRabbit review: Session::region_spanish takes the ISO 639-2 `spa` as Spanish, so a `spa-MX` region writes es-MX documents.
18 lines
479 B
TOML
18 lines
479 B
TOML
[package]
|
|
name = "wordcraft-proof"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
description = "WordCraft proofing per language: spelling, suggestions, grammar checks and hyphenation for English (public-domain word list) and Polish (installed Hunspell dictionary, TeX patterns)"
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[dependencies]
|
|
log = { workspace = true }
|
|
miniz_oxide = "0.8"
|
|
unicode-normalization = "0.1"
|
|
|
|
[dev-dependencies]
|
|
proptest = { workspace = true }
|