Add offline live spell checking (Hunspell via spellbook)
Spelling is now checked live as you type, fully offline, using the pure-Rust `spellbook` crate to read Hunspell .aff/.dic dictionaries (no C libhunspell — the binary stays self-contained; ldd unchanged). - Canadian (en-CA, default) and British (en-GB) English dictionaries are compiled in; more languages are auto-discovered from system Hunspell folders and ~/.config/md-manuscript/dictionaries/. A "Spelling" row in the top bar toggles live checking and picks the dictionary. - Misspellings are underlined in red; right-clicking a word opens a menu of suggested corrections. A results-panel and one-click fixes work too. - Checks run on a background thread, debounced ~400ms after the last edit. Prose is extracted with pulldown-cmark so code spans, code blocks and link targets are skipped; ALL-CAPS initialisms are ignored. - LanguageTool still layers on top: when its results are fresh they own the underlines (spelling + grammar); once you edit, the offline checker resumes. The editor underlines, issues panel and fix-apply logic are now shared between the two sources. Bundled dictionaries are SCOWL-derived under a permissive license (kept in dictionaries/<lang>/license). Adds spell-check unit tests (tokenizer, code-block skipping, offset mapping, en-CA/en-GB spelling); 40 tests pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01N9kRuP7JvXoUGdNNeg5ZSs
This commit is contained in:
landon
Generated
+11
@@ -1858,6 +1858,7 @@ dependencies = [
|
|||||||
"rfd",
|
"rfd",
|
||||||
"serde",
|
"serde",
|
||||||
"serde_json",
|
"serde_json",
|
||||||
|
"spellbook",
|
||||||
"ureq",
|
"ureq",
|
||||||
"zip",
|
"zip",
|
||||||
]
|
]
|
||||||
@@ -3036,6 +3037,16 @@ dependencies = [
|
|||||||
"serde",
|
"serde",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
[[package]]
|
||||||
|
name = "spellbook"
|
||||||
|
version = "0.4.2"
|
||||||
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
|
checksum = "0d204abcbdf8e88729306a8d0ca01a79d8a49969fe1f84696909d6dbc4321c1a"
|
||||||
|
dependencies = [
|
||||||
|
"foldhash",
|
||||||
|
"hashbrown 0.17.1",
|
||||||
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "spirv"
|
name = "spirv"
|
||||||
version = "0.3.0+sdk-1.3.268.0"
|
version = "0.3.0+sdk-1.3.268.0"
|
||||||
|
|||||||
@@ -18,6 +18,9 @@ rfd = { version = "0.15", default-features = false, features = ["xdg-portal", "a
|
|||||||
# backend links statically (no new runtime .so deps), so both a plain-HTTP local
|
# backend links statically (no new runtime .so deps), so both a plain-HTTP local
|
||||||
# server and an HTTPS domain work.
|
# server and an HTTPS domain work.
|
||||||
ureq = { version = "2", default-features = false, features = ["tls"] }
|
ureq = { version = "2", default-features = false, features = ["tls"] }
|
||||||
|
# Pure-Rust reader of Hunspell .aff/.dic dictionaries for offline spell
|
||||||
|
# checking, so the binary stays self-contained (no C libhunspell to link).
|
||||||
|
spellbook = "0.4.2"
|
||||||
|
|
||||||
[profile.release]
|
[profile.release]
|
||||||
opt-level = 2
|
opt-level = 2
|
||||||
|
|||||||
@@ -110,9 +110,38 @@ The status bar shows a live **word count** for the current file, plus the net
|
|||||||
words added (or removed) to it since the current session started. The count
|
words added (or removed) to it since the current session started. The count
|
||||||
updates as you type, including unsaved edits.
|
updates as you type, including unsaved edits.
|
||||||
|
|
||||||
|
## Spelling (offline)
|
||||||
|
|
||||||
|
Spelling is checked **live as you type**, entirely offline — no server, no
|
||||||
|
network. Misspelled words get a red underline; **right-click** one for a menu of
|
||||||
|
suggested corrections (click a suggestion to apply it). It uses Hunspell
|
||||||
|
dictionaries read by the pure-Rust [`spellbook`](https://crates.io/crates/spellbook)
|
||||||
|
crate, so the binary stays self-contained.
|
||||||
|
|
||||||
|
* **Two dictionaries are built in** — Canadian English (`en-CA`, the default)
|
||||||
|
and British English (`en-GB`). Pick one from the **Dictionary** dropdown on
|
||||||
|
the *Spelling* row of the top bar; the choice is remembered.
|
||||||
|
* **More languages** are discovered automatically from the usual Hunspell
|
||||||
|
folders (`/usr/share/hunspell`, `/usr/share/myspell`, …) and from a per-user
|
||||||
|
folder, `~/.config/md-manuscript/dictionaries/`. Drop a matching
|
||||||
|
`xx_YY.aff` + `xx_YY.dic` pair in there (e.g. from your distro's
|
||||||
|
`hunspell-de-de` package) and it appears in the dropdown.
|
||||||
|
* **Untick “Check as I type”** on the Spelling row to turn the underlines off.
|
||||||
|
* Code spans, fenced/indented code blocks and link targets are skipped, and
|
||||||
|
ALL-CAPS initialisms (ODT, HTTP) are left alone, to cut false positives.
|
||||||
|
|
||||||
|
When you run a **LanguageTool** check (below), its richer spelling-and-grammar
|
||||||
|
results take over the underlines until you next edit the text — at which point
|
||||||
|
the live offline checker resumes. In other words, LanguageTool is used when it's
|
||||||
|
available and current; the offline checker is the always-on default.
|
||||||
|
|
||||||
|
The bundled dictionaries live under `dictionaries/` and are derived from
|
||||||
|
[SCOWL](http://wordlist.sourceforge.net/) under a permissive license (kept
|
||||||
|
alongside them in each `license` file).
|
||||||
|
|
||||||
## Grammar & spelling (LanguageTool)
|
## Grammar & spelling (LanguageTool)
|
||||||
|
|
||||||
The editor can check the current file against a
|
The editor can *additionally* check the current file against a
|
||||||
[LanguageTool](https://languagetool.org/) server — typically a **local
|
[LanguageTool](https://languagetool.org/) server — typically a **local
|
||||||
instance**, so your manuscript never leaves your machine.
|
instance**, so your manuscript never leaves your machine.
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,205 @@
|
|||||||
|
SET UTF-8
|
||||||
|
TRY esianrtolcdugmphbyfvkwzESIANRTOLCDUGMPHBYFVKWZ'
|
||||||
|
ICONV 1
|
||||||
|
ICONV ’ '
|
||||||
|
NOSUGGEST !
|
||||||
|
|
||||||
|
# ordinal numbers
|
||||||
|
COMPOUNDMIN 1
|
||||||
|
# only in compounds: 1th, 2th, 3th
|
||||||
|
ONLYINCOMPOUND c
|
||||||
|
# compound rules:
|
||||||
|
# 1. [0-9]*1[0-9]th (10th, 11th, 12th, 56714th, etc.)
|
||||||
|
# 2. [0-9]*[02-9](1st|2nd|3rd|[4-9]th) (21st, 22nd, 123rd, 1234th, etc.)
|
||||||
|
COMPOUNDRULE 2
|
||||||
|
COMPOUNDRULE n*1t
|
||||||
|
COMPOUNDRULE n*mp
|
||||||
|
WORDCHARS 0123456789
|
||||||
|
|
||||||
|
PFX A Y 1
|
||||||
|
PFX A 0 re .
|
||||||
|
|
||||||
|
PFX I Y 1
|
||||||
|
PFX I 0 in .
|
||||||
|
|
||||||
|
PFX U Y 1
|
||||||
|
PFX U 0 un .
|
||||||
|
|
||||||
|
PFX C Y 1
|
||||||
|
PFX C 0 de .
|
||||||
|
|
||||||
|
PFX E Y 1
|
||||||
|
PFX E 0 dis .
|
||||||
|
|
||||||
|
PFX F Y 1
|
||||||
|
PFX F 0 con .
|
||||||
|
|
||||||
|
PFX K Y 1
|
||||||
|
PFX K 0 pro .
|
||||||
|
|
||||||
|
SFX V N 2
|
||||||
|
SFX V e ive e
|
||||||
|
SFX V 0 ive [^e]
|
||||||
|
|
||||||
|
SFX N Y 3
|
||||||
|
SFX N e ion e
|
||||||
|
SFX N y ication y
|
||||||
|
SFX N 0 en [^ey]
|
||||||
|
|
||||||
|
SFX X Y 3
|
||||||
|
SFX X e ions e
|
||||||
|
SFX X y ications y
|
||||||
|
SFX X 0 ens [^ey]
|
||||||
|
|
||||||
|
SFX H N 2
|
||||||
|
SFX H y ieth y
|
||||||
|
SFX H 0 th [^y]
|
||||||
|
|
||||||
|
SFX Y Y 1
|
||||||
|
SFX Y 0 ly .
|
||||||
|
|
||||||
|
SFX G Y 2
|
||||||
|
SFX G e ing e
|
||||||
|
SFX G 0 ing [^e]
|
||||||
|
|
||||||
|
SFX J Y 2
|
||||||
|
SFX J e ings e
|
||||||
|
SFX J 0 ings [^e]
|
||||||
|
|
||||||
|
SFX D Y 4
|
||||||
|
SFX D 0 d e
|
||||||
|
SFX D y ied [^aeiou]y
|
||||||
|
SFX D 0 ed [^ey]
|
||||||
|
SFX D 0 ed [aeiou]y
|
||||||
|
|
||||||
|
SFX T N 4
|
||||||
|
SFX T 0 st e
|
||||||
|
SFX T y iest [^aeiou]y
|
||||||
|
SFX T 0 est [aeiou]y
|
||||||
|
SFX T 0 est [^ey]
|
||||||
|
|
||||||
|
SFX R Y 4
|
||||||
|
SFX R 0 r e
|
||||||
|
SFX R y ier [^aeiou]y
|
||||||
|
SFX R 0 er [aeiou]y
|
||||||
|
SFX R 0 er [^ey]
|
||||||
|
|
||||||
|
SFX Z Y 4
|
||||||
|
SFX Z 0 rs e
|
||||||
|
SFX Z y iers [^aeiou]y
|
||||||
|
SFX Z 0 ers [aeiou]y
|
||||||
|
SFX Z 0 ers [^ey]
|
||||||
|
|
||||||
|
SFX S Y 4
|
||||||
|
SFX S y ies [^aeiou]y
|
||||||
|
SFX S 0 s [aeiou]y
|
||||||
|
SFX S 0 es [sxzh]
|
||||||
|
SFX S 0 s [^sxzhy]
|
||||||
|
|
||||||
|
SFX P Y 3
|
||||||
|
SFX P y iness [^aeiou]y
|
||||||
|
SFX P 0 ness [aeiou]y
|
||||||
|
SFX P 0 ness [^y]
|
||||||
|
|
||||||
|
SFX M Y 1
|
||||||
|
SFX M 0 's .
|
||||||
|
|
||||||
|
SFX B Y 3
|
||||||
|
SFX B 0 able [^aeiou]
|
||||||
|
SFX B 0 able ee
|
||||||
|
SFX B e able [^aeiou]e
|
||||||
|
|
||||||
|
SFX L Y 1
|
||||||
|
SFX L 0 ment .
|
||||||
|
|
||||||
|
REP 90
|
||||||
|
REP a ei
|
||||||
|
REP ei a
|
||||||
|
REP a ey
|
||||||
|
REP ey a
|
||||||
|
REP ai ie
|
||||||
|
REP ie ai
|
||||||
|
REP alot a_lot
|
||||||
|
REP are air
|
||||||
|
REP are ear
|
||||||
|
REP are eir
|
||||||
|
REP air are
|
||||||
|
REP air ere
|
||||||
|
REP ere air
|
||||||
|
REP ere ear
|
||||||
|
REP ere eir
|
||||||
|
REP ear are
|
||||||
|
REP ear air
|
||||||
|
REP ear ere
|
||||||
|
REP eir are
|
||||||
|
REP eir ere
|
||||||
|
REP ch te
|
||||||
|
REP te ch
|
||||||
|
REP ch ti
|
||||||
|
REP ti ch
|
||||||
|
REP ch tu
|
||||||
|
REP tu ch
|
||||||
|
REP ch s
|
||||||
|
REP s ch
|
||||||
|
REP ch k
|
||||||
|
REP k ch
|
||||||
|
REP f ph
|
||||||
|
REP ph f
|
||||||
|
REP gh f
|
||||||
|
REP f gh
|
||||||
|
REP i igh
|
||||||
|
REP igh i
|
||||||
|
REP i uy
|
||||||
|
REP uy i
|
||||||
|
REP i ee
|
||||||
|
REP ee i
|
||||||
|
REP j di
|
||||||
|
REP di j
|
||||||
|
REP j gg
|
||||||
|
REP gg j
|
||||||
|
REP j ge
|
||||||
|
REP ge j
|
||||||
|
REP s ti
|
||||||
|
REP ti s
|
||||||
|
REP s ci
|
||||||
|
REP ci s
|
||||||
|
REP k cc
|
||||||
|
REP cc k
|
||||||
|
REP k qu
|
||||||
|
REP qu k
|
||||||
|
REP kw qu
|
||||||
|
REP o eau
|
||||||
|
REP eau o
|
||||||
|
REP o ew
|
||||||
|
REP ew o
|
||||||
|
REP oo ew
|
||||||
|
REP ew oo
|
||||||
|
REP ew ui
|
||||||
|
REP ui ew
|
||||||
|
REP oo ui
|
||||||
|
REP ui oo
|
||||||
|
REP ew u
|
||||||
|
REP u ew
|
||||||
|
REP oo u
|
||||||
|
REP u oo
|
||||||
|
REP u oe
|
||||||
|
REP oe u
|
||||||
|
REP u ieu
|
||||||
|
REP ieu u
|
||||||
|
REP ue ew
|
||||||
|
REP ew ue
|
||||||
|
REP uff ough
|
||||||
|
REP oo ieu
|
||||||
|
REP ieu oo
|
||||||
|
REP ier ear
|
||||||
|
REP ear ier
|
||||||
|
REP ear air
|
||||||
|
REP air ear
|
||||||
|
REP w qu
|
||||||
|
REP qu w
|
||||||
|
REP z ss
|
||||||
|
REP ss z
|
||||||
|
REP shun tion
|
||||||
|
REP shun sion
|
||||||
|
REP shun cion
|
||||||
|
REP size cise
|
||||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,347 @@
|
|||||||
|
en_CA Hunspell Dictionary
|
||||||
|
Version 2020.12.07
|
||||||
|
Mon Dec 7 20:14:35 2020 -0500 [5ef55f9]
|
||||||
|
http://wordlist.sourceforge.net
|
||||||
|
|
||||||
|
README file for English Hunspell dictionaries derived from SCOWL.
|
||||||
|
|
||||||
|
These dictionaries are created using the speller/make-hunspell-dict
|
||||||
|
script in SCOWL.
|
||||||
|
|
||||||
|
The following dictionaries are available:
|
||||||
|
|
||||||
|
en_US (American)
|
||||||
|
en_CA (Canadian)
|
||||||
|
en_GB-ise (British with "ise" spelling)
|
||||||
|
en_GB-ize (British with "ize" spelling)
|
||||||
|
en_AU (Australian)
|
||||||
|
|
||||||
|
en_US-large
|
||||||
|
en_CA-large
|
||||||
|
en_GB-large (with both "ise" and "ize" spelling)
|
||||||
|
en_AU-large
|
||||||
|
|
||||||
|
The normal (non-large) dictionaries correspond to SCOWL size 60 and,
|
||||||
|
to encourage consistent spelling, generally only include one spelling
|
||||||
|
variant for a word. The large dictionaries correspond to SCOWL size
|
||||||
|
70 and may include multiple spelling for a word when both variants are
|
||||||
|
considered almost equal. The larger dictionaries however (1) have not
|
||||||
|
been as carefully checked for errors as the normal dictionaries and
|
||||||
|
thus may contain misspelled or invalid words; and (2) contain
|
||||||
|
uncommon, yet valid, words that might cause problems as they are
|
||||||
|
likely to be misspellings of more common words (for example, "ort" and
|
||||||
|
"calender").
|
||||||
|
|
||||||
|
To get an idea of the difference in size, here are 25 random words
|
||||||
|
only found in the large dictionary for American English:
|
||||||
|
|
||||||
|
Bermejo Freyr's Guenevere Hatshepsut Nottinghamshire arrestment
|
||||||
|
crassitudes crural dogwatches errorless fetial flaxseeds godroon
|
||||||
|
incretion jalapeño's kelpie kishkes neuroglias pietisms pullulation
|
||||||
|
stemwinder stenoses syce thalassic zees
|
||||||
|
|
||||||
|
The en_US, en_CA and en_AU are the official dictionaries for Hunspell.
|
||||||
|
The en_GB and large dictionaries are made available on an experimental
|
||||||
|
basis. If you find them useful please send me a quick email at
|
||||||
|
kevina@gnu.org.
|
||||||
|
|
||||||
|
If none of these dictionaries suite you (for example, maybe you want
|
||||||
|
the normal dictionary that also includes common variants) additional
|
||||||
|
dictionaries can be generated at http://app.aspell.net/create or by
|
||||||
|
modifying speller/make-hunspell-dict in SCOWL. Please do let me know
|
||||||
|
if you end up publishing a customized dictionary.
|
||||||
|
|
||||||
|
If a word is not found in the dictionary or a word is there you think
|
||||||
|
shouldn't be, you can lookup the word up at http://app.aspell.net/lookup
|
||||||
|
to help determine why that is.
|
||||||
|
|
||||||
|
General comments on these list can be sent directly to me at
|
||||||
|
kevina@gnu.org or to the wordlist-devel mailing lists
|
||||||
|
(https://lists.sourceforge.net/lists/listinfo/wordlist-devel). If you
|
||||||
|
have specific issues with any of these dictionaries please file a bug
|
||||||
|
report at https://github.com/kevina/wordlist/issues.
|
||||||
|
|
||||||
|
IMPORTANT CHANGES INTRODUCED In 2016.11.20:
|
||||||
|
|
||||||
|
New Australian dictionaries thanks to the work of Benjamin Titze
|
||||||
|
(btitze@protonmail.ch).
|
||||||
|
|
||||||
|
IMPORTANT CHANGES INTRODUCED IN 2016.04.24:
|
||||||
|
|
||||||
|
The dictionaries are now in UTF-8 format instead of ISO-8859-1. This
|
||||||
|
was required to handle smart quotes correctly.
|
||||||
|
|
||||||
|
IMPORTANT CHANGES INTRODUCED IN 2016.01.19:
|
||||||
|
|
||||||
|
"SET UTF8" was changes to "SET UTF-8" in the affix file as some
|
||||||
|
versions of Hunspell do not recognize "UTF8".
|
||||||
|
|
||||||
|
ADDITIONAL NOTES:
|
||||||
|
|
||||||
|
The NOSUGGEST flag was added to certain taboo words. While I made an
|
||||||
|
honest attempt to flag the strongest taboo words with the NOSUGGEST
|
||||||
|
flag, I MAKE NO GUARANTEE THAT I FLAGGED EVERY POSSIBLE TABOO WORD.
|
||||||
|
The list was originally derived from Németh László, however I removed
|
||||||
|
some words which, while being considered taboo by some dictionaries,
|
||||||
|
are not really considered swear words in today's society.
|
||||||
|
|
||||||
|
COPYRIGHT, SOURCES, and CREDITS:
|
||||||
|
|
||||||
|
The English dictionaries come directly from SCOWL
|
||||||
|
and is thus under the same copyright of SCOWL. The affix file is
|
||||||
|
a heavily modified version of the original english.aff file which was
|
||||||
|
released as part of Geoff Kuenning's Ispell and as such is covered by
|
||||||
|
his BSD license. Part of SCOWL is also based on Ispell thus the
|
||||||
|
Ispell copyright is included with the SCOWL copyright.
|
||||||
|
|
||||||
|
The collective work is Copyright 2000-2018 by Kevin Atkinson as well
|
||||||
|
as any of the copyrights mentioned below:
|
||||||
|
|
||||||
|
Copyright 2000-2018 by Kevin Atkinson
|
||||||
|
|
||||||
|
Permission to use, copy, modify, distribute and sell these word
|
||||||
|
lists, the associated scripts, the output created from the scripts,
|
||||||
|
and its documentation for any purpose is hereby granted without fee,
|
||||||
|
provided that the above copyright notice appears in all copies and
|
||||||
|
that both that copyright notice and this permission notice appear in
|
||||||
|
supporting documentation. Kevin Atkinson makes no representations
|
||||||
|
about the suitability of this array for any purpose. It is provided
|
||||||
|
"as is" without express or implied warranty.
|
||||||
|
|
||||||
|
Alan Beale <biljir@pobox.com> also deserves special credit as he has,
|
||||||
|
in addition to providing the 12Dicts package and being a major
|
||||||
|
contributor to the ENABLE word list, given me an incredible amount of
|
||||||
|
feedback and created a number of special lists (those found in the
|
||||||
|
Supplement) in order to help improve the overall quality of SCOWL.
|
||||||
|
|
||||||
|
The 10 level includes the 1000 most common English words (according to
|
||||||
|
the Moby (TM) Words II [MWords] package), a subset of the 1000 most
|
||||||
|
common words on the Internet (again, according to Moby Words II), and
|
||||||
|
frequently class 16 from Brian Kelk's "UK English Wordlist
|
||||||
|
with Frequency Classification".
|
||||||
|
|
||||||
|
The MWords package was explicitly placed in the public domain:
|
||||||
|
|
||||||
|
The Moby lexicon project is complete and has
|
||||||
|
been place into the public domain. Use, sell,
|
||||||
|
rework, excerpt and use in any way on any platform.
|
||||||
|
|
||||||
|
Placing this material on internal or public servers is
|
||||||
|
also encouraged. The compiler is not aware of any
|
||||||
|
export restrictions so freely distribute world-wide.
|
||||||
|
|
||||||
|
You can verify the public domain status by contacting
|
||||||
|
|
||||||
|
Grady Ward
|
||||||
|
3449 Martha Ct.
|
||||||
|
Arcata, CA 95521-4884
|
||||||
|
|
||||||
|
grady@netcom.com
|
||||||
|
grady@northcoast.com
|
||||||
|
|
||||||
|
The "UK English Wordlist With Frequency Classification" is also in the
|
||||||
|
Public Domain:
|
||||||
|
|
||||||
|
Date: Sat, 08 Jul 2000 20:27:21 +0100
|
||||||
|
From: Brian Kelk <Brian.Kelk@cl.cam.ac.uk>
|
||||||
|
|
||||||
|
> I was wondering what the copyright status of your "UK English
|
||||||
|
> Wordlist With Frequency Classification" word list as it seems to
|
||||||
|
> be lacking any copyright notice.
|
||||||
|
|
||||||
|
There were many many sources in total, but any text marked
|
||||||
|
"copyright" was avoided. Locally-written documentation was one
|
||||||
|
source. An earlier version of the list resided in a filespace called
|
||||||
|
PUBLIC on the University mainframe, because it was considered public
|
||||||
|
domain.
|
||||||
|
|
||||||
|
Date: Tue, 11 Jul 2000 19:31:34 +0100
|
||||||
|
|
||||||
|
> So are you saying your word list is also in the public domain?
|
||||||
|
|
||||||
|
That is the intention.
|
||||||
|
|
||||||
|
The 20 level includes frequency classes 7-15 from Brian's word list.
|
||||||
|
|
||||||
|
The 35 level includes frequency classes 2-6 and words appearing in at
|
||||||
|
least 11 of 12 dictionaries as indicated in the 12Dicts package. All
|
||||||
|
words from the 12Dicts package have had likely inflections added via
|
||||||
|
my inflection database.
|
||||||
|
|
||||||
|
The 12Dicts package and Supplement is in the Public Domain.
|
||||||
|
|
||||||
|
The WordNet database, which was used in the creation of the
|
||||||
|
Inflections database, is under the following copyright:
|
||||||
|
|
||||||
|
This software and database is being provided to you, the LICENSEE,
|
||||||
|
by Princeton University under the following license. By obtaining,
|
||||||
|
using and/or copying this software and database, you agree that you
|
||||||
|
have read, understood, and will comply with these terms and
|
||||||
|
conditions.:
|
||||||
|
|
||||||
|
Permission to use, copy, modify and distribute this software and
|
||||||
|
database and its documentation for any purpose and without fee or
|
||||||
|
royalty is hereby granted, provided that you agree to comply with
|
||||||
|
the following copyright notice and statements, including the
|
||||||
|
disclaimer, and that the same appear on ALL copies of the software,
|
||||||
|
database and documentation, including modifications that you make
|
||||||
|
for internal use or for distribution.
|
||||||
|
|
||||||
|
WordNet 1.6 Copyright 1997 by Princeton University. All rights
|
||||||
|
reserved.
|
||||||
|
|
||||||
|
THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON
|
||||||
|
UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
|
||||||
|
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON
|
||||||
|
UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-
|
||||||
|
ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE
|
||||||
|
LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT INFRINGE ANY
|
||||||
|
THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS.
|
||||||
|
|
||||||
|
The name of Princeton University or Princeton may not be used in
|
||||||
|
advertising or publicity pertaining to distribution of the software
|
||||||
|
and/or database. Title to copyright in this software, database and
|
||||||
|
any associated documentation shall at all times remain with
|
||||||
|
Princeton University and LICENSEE agrees to preserve same.
|
||||||
|
|
||||||
|
The 40 level includes words from Alan's 3esl list found in version 4.0
|
||||||
|
of his 12dicts package. Like his other stuff the 3esl list is also in the
|
||||||
|
public domain.
|
||||||
|
|
||||||
|
The 50 level includes Brian's frequency class 1, words appearing
|
||||||
|
in at least 5 of 12 of the dictionaries as indicated in the 12Dicts
|
||||||
|
package, and uppercase words in at least 4 of the previous 12
|
||||||
|
dictionaries. A decent number of proper names is also included: The
|
||||||
|
top 1000 male, female, and Last names from the 1990 Census report; a
|
||||||
|
list of names sent to me by Alan Beale; and a few names that I added
|
||||||
|
myself. Finally a small list of abbreviations not commonly found in
|
||||||
|
other word lists is included.
|
||||||
|
|
||||||
|
The name files form the Census report is a government document which I
|
||||||
|
don't think can be copyrighted.
|
||||||
|
|
||||||
|
The file special-jargon.50 uses common.lst and word.lst from the
|
||||||
|
"Unofficial Jargon File Word Lists" which is derived from "The Jargon
|
||||||
|
File". All of which is in the Public Domain. This file also contain
|
||||||
|
a few extra UNIX terms which are found in the file "unix-terms" in the
|
||||||
|
special/ directory.
|
||||||
|
|
||||||
|
The 55 level includes words from Alan's 2of4brif list found in version
|
||||||
|
4.0 of his 12dicts package. Like his other stuff the 2of4brif is also
|
||||||
|
in the public domain.
|
||||||
|
|
||||||
|
The 60 level includes all words appearing in at least 2 of the 12
|
||||||
|
dictionaries as indicated by the 12Dicts package.
|
||||||
|
|
||||||
|
The 70 level includes Brian's frequency class 0 and the 74,550 common
|
||||||
|
dictionary words from the MWords package. The common dictionary words,
|
||||||
|
like those from the 12Dicts package, have had all likely inflections
|
||||||
|
added. The 70 level also included the 5desk list from version 4.0 of
|
||||||
|
the 12Dics package which is in the public domain.
|
||||||
|
|
||||||
|
The 80 level includes the ENABLE word list, all the lists in the
|
||||||
|
ENABLE supplement package (except for ABLE), the "UK Advanced Cryptics
|
||||||
|
Dictionary" (UKACD), the list of signature words from the YAWL package,
|
||||||
|
and the 10,196 places list from the MWords package.
|
||||||
|
|
||||||
|
The ENABLE package, mainted by M\Cooper <thegrendel@theriver.com>,
|
||||||
|
is in the Public Domain:
|
||||||
|
|
||||||
|
The ENABLE master word list, WORD.LST, is herewith formally released
|
||||||
|
into the Public Domain. Anyone is free to use it or distribute it in
|
||||||
|
any manner they see fit. No fee or registration is required for its
|
||||||
|
use nor are "contributions" solicited (if you feel you absolutely
|
||||||
|
must contribute something for your own peace of mind, the authors of
|
||||||
|
the ENABLE list ask that you make a donation on their behalf to your
|
||||||
|
favorite charity). This word list is our gift to the Scrabble
|
||||||
|
community, as an alternate to "official" word lists. Game designers
|
||||||
|
may feel free to incorporate the WORD.LST into their games. Please
|
||||||
|
mention the source and credit us as originators of the list. Note
|
||||||
|
that if you, as a game designer, use the WORD.LST in your product,
|
||||||
|
you may still copyright and protect your product, but you may *not*
|
||||||
|
legally copyright or in any way restrict redistribution of the
|
||||||
|
WORD.LST portion of your product. This *may* under law restrict your
|
||||||
|
rights to restrict your users' rights, but that is only fair.
|
||||||
|
|
||||||
|
UKACD, by J Ross Beresford <ross@bryson.demon.co.uk>, is under the
|
||||||
|
following copyright:
|
||||||
|
|
||||||
|
Copyright (c) J Ross Beresford 1993-1999. All Rights Reserved.
|
||||||
|
|
||||||
|
The following restriction is placed on the use of this publication:
|
||||||
|
if The UK Advanced Cryptics Dictionary is used in a software package
|
||||||
|
or redistributed in any form, the copyright notice must be
|
||||||
|
prominently displayed and the text of this document must be included
|
||||||
|
verbatim.
|
||||||
|
|
||||||
|
There are no other restrictions: I would like to see the list
|
||||||
|
distributed as widely as possible.
|
||||||
|
|
||||||
|
The 95 level includes the 354,984 single words, 256,772 compound
|
||||||
|
words, 4,946 female names and the 3,897 male names, and 21,986 names
|
||||||
|
from the MWords package, ABLE.LST from the ENABLE Supplement, and some
|
||||||
|
additional words found in my part-of-speech database that were not
|
||||||
|
found anywhere else.
|
||||||
|
|
||||||
|
Accent information was taken from UKACD.
|
||||||
|
|
||||||
|
The VarCon package was used to create the American, British, Canadian,
|
||||||
|
and Australian word list. It is under the following copyright:
|
||||||
|
|
||||||
|
Copyright 2000-2016 by Kevin Atkinson
|
||||||
|
|
||||||
|
Permission to use, copy, modify, distribute and sell this array, the
|
||||||
|
associated software, and its documentation for any purpose is hereby
|
||||||
|
granted without fee, provided that the above copyright notice appears
|
||||||
|
in all copies and that both that copyright notice and this permission
|
||||||
|
notice appear in supporting documentation. Kevin Atkinson makes no
|
||||||
|
representations about the suitability of this array for any
|
||||||
|
purpose. It is provided "as is" without express or implied warranty.
|
||||||
|
|
||||||
|
Copyright 2016 by Benjamin Titze
|
||||||
|
|
||||||
|
Permission to use, copy, modify, distribute and sell this array, the
|
||||||
|
associated software, and its documentation for any purpose is hereby
|
||||||
|
granted without fee, provided that the above copyright notice appears
|
||||||
|
in all copies and that both that copyright notice and this permission
|
||||||
|
notice appear in supporting documentation. Benjamin Titze makes no
|
||||||
|
representations about the suitability of this array for any
|
||||||
|
purpose. It is provided "as is" without express or implied warranty.
|
||||||
|
|
||||||
|
Since the original words lists come from the Ispell distribution:
|
||||||
|
|
||||||
|
Copyright 1993, Geoff Kuenning, Granada Hills, CA
|
||||||
|
All rights reserved.
|
||||||
|
|
||||||
|
Redistribution and use in source and binary forms, with or without
|
||||||
|
modification, are permitted provided that the following conditions
|
||||||
|
are met:
|
||||||
|
|
||||||
|
1. Redistributions of source code must retain the above copyright
|
||||||
|
notice, this list of conditions and the following disclaimer.
|
||||||
|
2. Redistributions in binary form must reproduce the above copyright
|
||||||
|
notice, this list of conditions and the following disclaimer in the
|
||||||
|
documentation and/or other materials provided with the distribution.
|
||||||
|
3. All modifications to the source code must be clearly marked as
|
||||||
|
such. Binary redistributions based on modified source code
|
||||||
|
must be clearly marked as modified versions in the documentation
|
||||||
|
and/or other materials provided with the distribution.
|
||||||
|
(clause 4 removed with permission from Geoff Kuenning)
|
||||||
|
5. The name of Geoff Kuenning may not be used to endorse or promote
|
||||||
|
products derived from this software without specific prior
|
||||||
|
written permission.
|
||||||
|
|
||||||
|
THIS SOFTWARE IS PROVIDED BY GEOFF KUENNING AND CONTRIBUTORS ``AS IS'' AND
|
||||||
|
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||||
|
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||||
|
ARE DISCLAIMED. IN NO EVENT SHALL GEOFF KUENNING OR CONTRIBUTORS BE LIABLE
|
||||||
|
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||||
|
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
||||||
|
OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||||
|
HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
||||||
|
LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
||||||
|
OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||||
|
SUCH DAMAGE.
|
||||||
|
|
||||||
|
Build Date: Mon Dec 7 20:19:28 EST 2020
|
||||||
|
Wordlist Command: mk-list --accents=strip en_CA 60
|
||||||
@@ -0,0 +1,205 @@
|
|||||||
|
SET UTF-8
|
||||||
|
TRY esianrtolcdugmphbyfvkwzESIANRTOLCDUGMPHBYFVKWZ'
|
||||||
|
ICONV 1
|
||||||
|
ICONV ’ '
|
||||||
|
NOSUGGEST !
|
||||||
|
|
||||||
|
# ordinal numbers
|
||||||
|
COMPOUNDMIN 1
|
||||||
|
# only in compounds: 1th, 2th, 3th
|
||||||
|
ONLYINCOMPOUND c
|
||||||
|
# compound rules:
|
||||||
|
# 1. [0-9]*1[0-9]th (10th, 11th, 12th, 56714th, etc.)
|
||||||
|
# 2. [0-9]*[02-9](1st|2nd|3rd|[4-9]th) (21st, 22nd, 123rd, 1234th, etc.)
|
||||||
|
COMPOUNDRULE 2
|
||||||
|
COMPOUNDRULE n*1t
|
||||||
|
COMPOUNDRULE n*mp
|
||||||
|
WORDCHARS 0123456789
|
||||||
|
|
||||||
|
PFX A Y 1
|
||||||
|
PFX A 0 re .
|
||||||
|
|
||||||
|
PFX I Y 1
|
||||||
|
PFX I 0 in .
|
||||||
|
|
||||||
|
PFX U Y 1
|
||||||
|
PFX U 0 un .
|
||||||
|
|
||||||
|
PFX C Y 1
|
||||||
|
PFX C 0 de .
|
||||||
|
|
||||||
|
PFX E Y 1
|
||||||
|
PFX E 0 dis .
|
||||||
|
|
||||||
|
PFX F Y 1
|
||||||
|
PFX F 0 con .
|
||||||
|
|
||||||
|
PFX K Y 1
|
||||||
|
PFX K 0 pro .
|
||||||
|
|
||||||
|
SFX V N 2
|
||||||
|
SFX V e ive e
|
||||||
|
SFX V 0 ive [^e]
|
||||||
|
|
||||||
|
SFX N Y 3
|
||||||
|
SFX N e ion e
|
||||||
|
SFX N y ication y
|
||||||
|
SFX N 0 en [^ey]
|
||||||
|
|
||||||
|
SFX X Y 3
|
||||||
|
SFX X e ions e
|
||||||
|
SFX X y ications y
|
||||||
|
SFX X 0 ens [^ey]
|
||||||
|
|
||||||
|
SFX H N 2
|
||||||
|
SFX H y ieth y
|
||||||
|
SFX H 0 th [^y]
|
||||||
|
|
||||||
|
SFX Y Y 1
|
||||||
|
SFX Y 0 ly .
|
||||||
|
|
||||||
|
SFX G Y 2
|
||||||
|
SFX G e ing e
|
||||||
|
SFX G 0 ing [^e]
|
||||||
|
|
||||||
|
SFX J Y 2
|
||||||
|
SFX J e ings e
|
||||||
|
SFX J 0 ings [^e]
|
||||||
|
|
||||||
|
SFX D Y 4
|
||||||
|
SFX D 0 d e
|
||||||
|
SFX D y ied [^aeiou]y
|
||||||
|
SFX D 0 ed [^ey]
|
||||||
|
SFX D 0 ed [aeiou]y
|
||||||
|
|
||||||
|
SFX T N 4
|
||||||
|
SFX T 0 st e
|
||||||
|
SFX T y iest [^aeiou]y
|
||||||
|
SFX T 0 est [aeiou]y
|
||||||
|
SFX T 0 est [^ey]
|
||||||
|
|
||||||
|
SFX R Y 4
|
||||||
|
SFX R 0 r e
|
||||||
|
SFX R y ier [^aeiou]y
|
||||||
|
SFX R 0 er [aeiou]y
|
||||||
|
SFX R 0 er [^ey]
|
||||||
|
|
||||||
|
SFX Z Y 4
|
||||||
|
SFX Z 0 rs e
|
||||||
|
SFX Z y iers [^aeiou]y
|
||||||
|
SFX Z 0 ers [aeiou]y
|
||||||
|
SFX Z 0 ers [^ey]
|
||||||
|
|
||||||
|
SFX S Y 4
|
||||||
|
SFX S y ies [^aeiou]y
|
||||||
|
SFX S 0 s [aeiou]y
|
||||||
|
SFX S 0 es [sxzh]
|
||||||
|
SFX S 0 s [^sxzhy]
|
||||||
|
|
||||||
|
SFX P Y 3
|
||||||
|
SFX P y iness [^aeiou]y
|
||||||
|
SFX P 0 ness [aeiou]y
|
||||||
|
SFX P 0 ness [^y]
|
||||||
|
|
||||||
|
SFX M Y 1
|
||||||
|
SFX M 0 's .
|
||||||
|
|
||||||
|
SFX B Y 3
|
||||||
|
SFX B 0 able [^aeiou]
|
||||||
|
SFX B 0 able ee
|
||||||
|
SFX B e able [^aeiou]e
|
||||||
|
|
||||||
|
SFX L Y 1
|
||||||
|
SFX L 0 ment .
|
||||||
|
|
||||||
|
REP 90
|
||||||
|
REP a ei
|
||||||
|
REP ei a
|
||||||
|
REP a ey
|
||||||
|
REP ey a
|
||||||
|
REP ai ie
|
||||||
|
REP ie ai
|
||||||
|
REP alot a_lot
|
||||||
|
REP are air
|
||||||
|
REP are ear
|
||||||
|
REP are eir
|
||||||
|
REP air are
|
||||||
|
REP air ere
|
||||||
|
REP ere air
|
||||||
|
REP ere ear
|
||||||
|
REP ere eir
|
||||||
|
REP ear are
|
||||||
|
REP ear air
|
||||||
|
REP ear ere
|
||||||
|
REP eir are
|
||||||
|
REP eir ere
|
||||||
|
REP ch te
|
||||||
|
REP te ch
|
||||||
|
REP ch ti
|
||||||
|
REP ti ch
|
||||||
|
REP ch tu
|
||||||
|
REP tu ch
|
||||||
|
REP ch s
|
||||||
|
REP s ch
|
||||||
|
REP ch k
|
||||||
|
REP k ch
|
||||||
|
REP f ph
|
||||||
|
REP ph f
|
||||||
|
REP gh f
|
||||||
|
REP f gh
|
||||||
|
REP i igh
|
||||||
|
REP igh i
|
||||||
|
REP i uy
|
||||||
|
REP uy i
|
||||||
|
REP i ee
|
||||||
|
REP ee i
|
||||||
|
REP j di
|
||||||
|
REP di j
|
||||||
|
REP j gg
|
||||||
|
REP gg j
|
||||||
|
REP j ge
|
||||||
|
REP ge j
|
||||||
|
REP s ti
|
||||||
|
REP ti s
|
||||||
|
REP s ci
|
||||||
|
REP ci s
|
||||||
|
REP k cc
|
||||||
|
REP cc k
|
||||||
|
REP k qu
|
||||||
|
REP qu k
|
||||||
|
REP kw qu
|
||||||
|
REP o eau
|
||||||
|
REP eau o
|
||||||
|
REP o ew
|
||||||
|
REP ew o
|
||||||
|
REP oo ew
|
||||||
|
REP ew oo
|
||||||
|
REP ew ui
|
||||||
|
REP ui ew
|
||||||
|
REP oo ui
|
||||||
|
REP ui oo
|
||||||
|
REP ew u
|
||||||
|
REP u ew
|
||||||
|
REP oo u
|
||||||
|
REP u oo
|
||||||
|
REP u oe
|
||||||
|
REP oe u
|
||||||
|
REP u ieu
|
||||||
|
REP ieu u
|
||||||
|
REP ue ew
|
||||||
|
REP ew ue
|
||||||
|
REP uff ough
|
||||||
|
REP oo ieu
|
||||||
|
REP ieu oo
|
||||||
|
REP ier ear
|
||||||
|
REP ear ier
|
||||||
|
REP ear air
|
||||||
|
REP air ear
|
||||||
|
REP w qu
|
||||||
|
REP qu w
|
||||||
|
REP z ss
|
||||||
|
REP ss z
|
||||||
|
REP shun tion
|
||||||
|
REP shun sion
|
||||||
|
REP shun cion
|
||||||
|
REP size cise
|
||||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,347 @@
|
|||||||
|
en_GB-ise Hunspell Dictionary
|
||||||
|
Version 2020.12.07
|
||||||
|
Mon Dec 7 20:14:35 2020 -0500 [5ef55f9]
|
||||||
|
http://wordlist.sourceforge.net
|
||||||
|
|
||||||
|
README file for English Hunspell dictionaries derived from SCOWL.
|
||||||
|
|
||||||
|
These dictionaries are created using the speller/make-hunspell-dict
|
||||||
|
script in SCOWL.
|
||||||
|
|
||||||
|
The following dictionaries are available:
|
||||||
|
|
||||||
|
en_US (American)
|
||||||
|
en_CA (Canadian)
|
||||||
|
en_GB-ise (British with "ise" spelling)
|
||||||
|
en_GB-ize (British with "ize" spelling)
|
||||||
|
en_AU (Australian)
|
||||||
|
|
||||||
|
en_US-large
|
||||||
|
en_CA-large
|
||||||
|
en_GB-large (with both "ise" and "ize" spelling)
|
||||||
|
en_AU-large
|
||||||
|
|
||||||
|
The normal (non-large) dictionaries correspond to SCOWL size 60 and,
|
||||||
|
to encourage consistent spelling, generally only include one spelling
|
||||||
|
variant for a word. The large dictionaries correspond to SCOWL size
|
||||||
|
70 and may include multiple spelling for a word when both variants are
|
||||||
|
considered almost equal. The larger dictionaries however (1) have not
|
||||||
|
been as carefully checked for errors as the normal dictionaries and
|
||||||
|
thus may contain misspelled or invalid words; and (2) contain
|
||||||
|
uncommon, yet valid, words that might cause problems as they are
|
||||||
|
likely to be misspellings of more common words (for example, "ort" and
|
||||||
|
"calender").
|
||||||
|
|
||||||
|
To get an idea of the difference in size, here are 25 random words
|
||||||
|
only found in the large dictionary for American English:
|
||||||
|
|
||||||
|
Bermejo Freyr's Guenevere Hatshepsut Nottinghamshire arrestment
|
||||||
|
crassitudes crural dogwatches errorless fetial flaxseeds godroon
|
||||||
|
incretion jalapeño's kelpie kishkes neuroglias pietisms pullulation
|
||||||
|
stemwinder stenoses syce thalassic zees
|
||||||
|
|
||||||
|
The en_US, en_CA and en_AU are the official dictionaries for Hunspell.
|
||||||
|
The en_GB and large dictionaries are made available on an experimental
|
||||||
|
basis. If you find them useful please send me a quick email at
|
||||||
|
kevina@gnu.org.
|
||||||
|
|
||||||
|
If none of these dictionaries suite you (for example, maybe you want
|
||||||
|
the normal dictionary that also includes common variants) additional
|
||||||
|
dictionaries can be generated at http://app.aspell.net/create or by
|
||||||
|
modifying speller/make-hunspell-dict in SCOWL. Please do let me know
|
||||||
|
if you end up publishing a customized dictionary.
|
||||||
|
|
||||||
|
If a word is not found in the dictionary or a word is there you think
|
||||||
|
shouldn't be, you can lookup the word up at http://app.aspell.net/lookup
|
||||||
|
to help determine why that is.
|
||||||
|
|
||||||
|
General comments on these list can be sent directly to me at
|
||||||
|
kevina@gnu.org or to the wordlist-devel mailing lists
|
||||||
|
(https://lists.sourceforge.net/lists/listinfo/wordlist-devel). If you
|
||||||
|
have specific issues with any of these dictionaries please file a bug
|
||||||
|
report at https://github.com/kevina/wordlist/issues.
|
||||||
|
|
||||||
|
IMPORTANT CHANGES INTRODUCED In 2016.11.20:
|
||||||
|
|
||||||
|
New Australian dictionaries thanks to the work of Benjamin Titze
|
||||||
|
(btitze@protonmail.ch).
|
||||||
|
|
||||||
|
IMPORTANT CHANGES INTRODUCED IN 2016.04.24:
|
||||||
|
|
||||||
|
The dictionaries are now in UTF-8 format instead of ISO-8859-1. This
|
||||||
|
was required to handle smart quotes correctly.
|
||||||
|
|
||||||
|
IMPORTANT CHANGES INTRODUCED IN 2016.01.19:
|
||||||
|
|
||||||
|
"SET UTF8" was changes to "SET UTF-8" in the affix file as some
|
||||||
|
versions of Hunspell do not recognize "UTF8".
|
||||||
|
|
||||||
|
ADDITIONAL NOTES:
|
||||||
|
|
||||||
|
The NOSUGGEST flag was added to certain taboo words. While I made an
|
||||||
|
honest attempt to flag the strongest taboo words with the NOSUGGEST
|
||||||
|
flag, I MAKE NO GUARANTEE THAT I FLAGGED EVERY POSSIBLE TABOO WORD.
|
||||||
|
The list was originally derived from Németh László, however I removed
|
||||||
|
some words which, while being considered taboo by some dictionaries,
|
||||||
|
are not really considered swear words in today's society.
|
||||||
|
|
||||||
|
COPYRIGHT, SOURCES, and CREDITS:
|
||||||
|
|
||||||
|
The English dictionaries come directly from SCOWL
|
||||||
|
and is thus under the same copyright of SCOWL. The affix file is
|
||||||
|
a heavily modified version of the original english.aff file which was
|
||||||
|
released as part of Geoff Kuenning's Ispell and as such is covered by
|
||||||
|
his BSD license. Part of SCOWL is also based on Ispell thus the
|
||||||
|
Ispell copyright is included with the SCOWL copyright.
|
||||||
|
|
||||||
|
The collective work is Copyright 2000-2018 by Kevin Atkinson as well
|
||||||
|
as any of the copyrights mentioned below:
|
||||||
|
|
||||||
|
Copyright 2000-2018 by Kevin Atkinson
|
||||||
|
|
||||||
|
Permission to use, copy, modify, distribute and sell these word
|
||||||
|
lists, the associated scripts, the output created from the scripts,
|
||||||
|
and its documentation for any purpose is hereby granted without fee,
|
||||||
|
provided that the above copyright notice appears in all copies and
|
||||||
|
that both that copyright notice and this permission notice appear in
|
||||||
|
supporting documentation. Kevin Atkinson makes no representations
|
||||||
|
about the suitability of this array for any purpose. It is provided
|
||||||
|
"as is" without express or implied warranty.
|
||||||
|
|
||||||
|
Alan Beale <biljir@pobox.com> also deserves special credit as he has,
|
||||||
|
in addition to providing the 12Dicts package and being a major
|
||||||
|
contributor to the ENABLE word list, given me an incredible amount of
|
||||||
|
feedback and created a number of special lists (those found in the
|
||||||
|
Supplement) in order to help improve the overall quality of SCOWL.
|
||||||
|
|
||||||
|
The 10 level includes the 1000 most common English words (according to
|
||||||
|
the Moby (TM) Words II [MWords] package), a subset of the 1000 most
|
||||||
|
common words on the Internet (again, according to Moby Words II), and
|
||||||
|
frequently class 16 from Brian Kelk's "UK English Wordlist
|
||||||
|
with Frequency Classification".
|
||||||
|
|
||||||
|
The MWords package was explicitly placed in the public domain:
|
||||||
|
|
||||||
|
The Moby lexicon project is complete and has
|
||||||
|
been place into the public domain. Use, sell,
|
||||||
|
rework, excerpt and use in any way on any platform.
|
||||||
|
|
||||||
|
Placing this material on internal or public servers is
|
||||||
|
also encouraged. The compiler is not aware of any
|
||||||
|
export restrictions so freely distribute world-wide.
|
||||||
|
|
||||||
|
You can verify the public domain status by contacting
|
||||||
|
|
||||||
|
Grady Ward
|
||||||
|
3449 Martha Ct.
|
||||||
|
Arcata, CA 95521-4884
|
||||||
|
|
||||||
|
grady@netcom.com
|
||||||
|
grady@northcoast.com
|
||||||
|
|
||||||
|
The "UK English Wordlist With Frequency Classification" is also in the
|
||||||
|
Public Domain:
|
||||||
|
|
||||||
|
Date: Sat, 08 Jul 2000 20:27:21 +0100
|
||||||
|
From: Brian Kelk <Brian.Kelk@cl.cam.ac.uk>
|
||||||
|
|
||||||
|
> I was wondering what the copyright status of your "UK English
|
||||||
|
> Wordlist With Frequency Classification" word list as it seems to
|
||||||
|
> be lacking any copyright notice.
|
||||||
|
|
||||||
|
There were many many sources in total, but any text marked
|
||||||
|
"copyright" was avoided. Locally-written documentation was one
|
||||||
|
source. An earlier version of the list resided in a filespace called
|
||||||
|
PUBLIC on the University mainframe, because it was considered public
|
||||||
|
domain.
|
||||||
|
|
||||||
|
Date: Tue, 11 Jul 2000 19:31:34 +0100
|
||||||
|
|
||||||
|
> So are you saying your word list is also in the public domain?
|
||||||
|
|
||||||
|
That is the intention.
|
||||||
|
|
||||||
|
The 20 level includes frequency classes 7-15 from Brian's word list.
|
||||||
|
|
||||||
|
The 35 level includes frequency classes 2-6 and words appearing in at
|
||||||
|
least 11 of 12 dictionaries as indicated in the 12Dicts package. All
|
||||||
|
words from the 12Dicts package have had likely inflections added via
|
||||||
|
my inflection database.
|
||||||
|
|
||||||
|
The 12Dicts package and Supplement is in the Public Domain.
|
||||||
|
|
||||||
|
The WordNet database, which was used in the creation of the
|
||||||
|
Inflections database, is under the following copyright:
|
||||||
|
|
||||||
|
This software and database is being provided to you, the LICENSEE,
|
||||||
|
by Princeton University under the following license. By obtaining,
|
||||||
|
using and/or copying this software and database, you agree that you
|
||||||
|
have read, understood, and will comply with these terms and
|
||||||
|
conditions.:
|
||||||
|
|
||||||
|
Permission to use, copy, modify and distribute this software and
|
||||||
|
database and its documentation for any purpose and without fee or
|
||||||
|
royalty is hereby granted, provided that you agree to comply with
|
||||||
|
the following copyright notice and statements, including the
|
||||||
|
disclaimer, and that the same appear on ALL copies of the software,
|
||||||
|
database and documentation, including modifications that you make
|
||||||
|
for internal use or for distribution.
|
||||||
|
|
||||||
|
WordNet 1.6 Copyright 1997 by Princeton University. All rights
|
||||||
|
reserved.
|
||||||
|
|
||||||
|
THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON
|
||||||
|
UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
|
||||||
|
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON
|
||||||
|
UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-
|
||||||
|
ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE
|
||||||
|
LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT INFRINGE ANY
|
||||||
|
THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS.
|
||||||
|
|
||||||
|
The name of Princeton University or Princeton may not be used in
|
||||||
|
advertising or publicity pertaining to distribution of the software
|
||||||
|
and/or database. Title to copyright in this software, database and
|
||||||
|
any associated documentation shall at all times remain with
|
||||||
|
Princeton University and LICENSEE agrees to preserve same.
|
||||||
|
|
||||||
|
The 40 level includes words from Alan's 3esl list found in version 4.0
|
||||||
|
of his 12dicts package. Like his other stuff the 3esl list is also in the
|
||||||
|
public domain.
|
||||||
|
|
||||||
|
The 50 level includes Brian's frequency class 1, words appearing
|
||||||
|
in at least 5 of 12 of the dictionaries as indicated in the 12Dicts
|
||||||
|
package, and uppercase words in at least 4 of the previous 12
|
||||||
|
dictionaries. A decent number of proper names is also included: The
|
||||||
|
top 1000 male, female, and Last names from the 1990 Census report; a
|
||||||
|
list of names sent to me by Alan Beale; and a few names that I added
|
||||||
|
myself. Finally a small list of abbreviations not commonly found in
|
||||||
|
other word lists is included.
|
||||||
|
|
||||||
|
The name files form the Census report is a government document which I
|
||||||
|
don't think can be copyrighted.
|
||||||
|
|
||||||
|
The file special-jargon.50 uses common.lst and word.lst from the
|
||||||
|
"Unofficial Jargon File Word Lists" which is derived from "The Jargon
|
||||||
|
File". All of which is in the Public Domain. This file also contain
|
||||||
|
a few extra UNIX terms which are found in the file "unix-terms" in the
|
||||||
|
special/ directory.
|
||||||
|
|
||||||
|
The 55 level includes words from Alan's 2of4brif list found in version
|
||||||
|
4.0 of his 12dicts package. Like his other stuff the 2of4brif is also
|
||||||
|
in the public domain.
|
||||||
|
|
||||||
|
The 60 level includes all words appearing in at least 2 of the 12
|
||||||
|
dictionaries as indicated by the 12Dicts package.
|
||||||
|
|
||||||
|
The 70 level includes Brian's frequency class 0 and the 74,550 common
|
||||||
|
dictionary words from the MWords package. The common dictionary words,
|
||||||
|
like those from the 12Dicts package, have had all likely inflections
|
||||||
|
added. The 70 level also included the 5desk list from version 4.0 of
|
||||||
|
the 12Dics package which is in the public domain.
|
||||||
|
|
||||||
|
The 80 level includes the ENABLE word list, all the lists in the
|
||||||
|
ENABLE supplement package (except for ABLE), the "UK Advanced Cryptics
|
||||||
|
Dictionary" (UKACD), the list of signature words from the YAWL package,
|
||||||
|
and the 10,196 places list from the MWords package.
|
||||||
|
|
||||||
|
The ENABLE package, mainted by M\Cooper <thegrendel@theriver.com>,
|
||||||
|
is in the Public Domain:
|
||||||
|
|
||||||
|
The ENABLE master word list, WORD.LST, is herewith formally released
|
||||||
|
into the Public Domain. Anyone is free to use it or distribute it in
|
||||||
|
any manner they see fit. No fee or registration is required for its
|
||||||
|
use nor are "contributions" solicited (if you feel you absolutely
|
||||||
|
must contribute something for your own peace of mind, the authors of
|
||||||
|
the ENABLE list ask that you make a donation on their behalf to your
|
||||||
|
favorite charity). This word list is our gift to the Scrabble
|
||||||
|
community, as an alternate to "official" word lists. Game designers
|
||||||
|
may feel free to incorporate the WORD.LST into their games. Please
|
||||||
|
mention the source and credit us as originators of the list. Note
|
||||||
|
that if you, as a game designer, use the WORD.LST in your product,
|
||||||
|
you may still copyright and protect your product, but you may *not*
|
||||||
|
legally copyright or in any way restrict redistribution of the
|
||||||
|
WORD.LST portion of your product. This *may* under law restrict your
|
||||||
|
rights to restrict your users' rights, but that is only fair.
|
||||||
|
|
||||||
|
UKACD, by J Ross Beresford <ross@bryson.demon.co.uk>, is under the
|
||||||
|
following copyright:
|
||||||
|
|
||||||
|
Copyright (c) J Ross Beresford 1993-1999. All Rights Reserved.
|
||||||
|
|
||||||
|
The following restriction is placed on the use of this publication:
|
||||||
|
if The UK Advanced Cryptics Dictionary is used in a software package
|
||||||
|
or redistributed in any form, the copyright notice must be
|
||||||
|
prominently displayed and the text of this document must be included
|
||||||
|
verbatim.
|
||||||
|
|
||||||
|
There are no other restrictions: I would like to see the list
|
||||||
|
distributed as widely as possible.
|
||||||
|
|
||||||
|
The 95 level includes the 354,984 single words, 256,772 compound
|
||||||
|
words, 4,946 female names and the 3,897 male names, and 21,986 names
|
||||||
|
from the MWords package, ABLE.LST from the ENABLE Supplement, and some
|
||||||
|
additional words found in my part-of-speech database that were not
|
||||||
|
found anywhere else.
|
||||||
|
|
||||||
|
Accent information was taken from UKACD.
|
||||||
|
|
||||||
|
The VarCon package was used to create the American, British, Canadian,
|
||||||
|
and Australian word list. It is under the following copyright:
|
||||||
|
|
||||||
|
Copyright 2000-2016 by Kevin Atkinson
|
||||||
|
|
||||||
|
Permission to use, copy, modify, distribute and sell this array, the
|
||||||
|
associated software, and its documentation for any purpose is hereby
|
||||||
|
granted without fee, provided that the above copyright notice appears
|
||||||
|
in all copies and that both that copyright notice and this permission
|
||||||
|
notice appear in supporting documentation. Kevin Atkinson makes no
|
||||||
|
representations about the suitability of this array for any
|
||||||
|
purpose. It is provided "as is" without express or implied warranty.
|
||||||
|
|
||||||
|
Copyright 2016 by Benjamin Titze
|
||||||
|
|
||||||
|
Permission to use, copy, modify, distribute and sell this array, the
|
||||||
|
associated software, and its documentation for any purpose is hereby
|
||||||
|
granted without fee, provided that the above copyright notice appears
|
||||||
|
in all copies and that both that copyright notice and this permission
|
||||||
|
notice appear in supporting documentation. Benjamin Titze makes no
|
||||||
|
representations about the suitability of this array for any
|
||||||
|
purpose. It is provided "as is" without express or implied warranty.
|
||||||
|
|
||||||
|
Since the original words lists come from the Ispell distribution:
|
||||||
|
|
||||||
|
Copyright 1993, Geoff Kuenning, Granada Hills, CA
|
||||||
|
All rights reserved.
|
||||||
|
|
||||||
|
Redistribution and use in source and binary forms, with or without
|
||||||
|
modification, are permitted provided that the following conditions
|
||||||
|
are met:
|
||||||
|
|
||||||
|
1. Redistributions of source code must retain the above copyright
|
||||||
|
notice, this list of conditions and the following disclaimer.
|
||||||
|
2. Redistributions in binary form must reproduce the above copyright
|
||||||
|
notice, this list of conditions and the following disclaimer in the
|
||||||
|
documentation and/or other materials provided with the distribution.
|
||||||
|
3. All modifications to the source code must be clearly marked as
|
||||||
|
such. Binary redistributions based on modified source code
|
||||||
|
must be clearly marked as modified versions in the documentation
|
||||||
|
and/or other materials provided with the distribution.
|
||||||
|
(clause 4 removed with permission from Geoff Kuenning)
|
||||||
|
5. The name of Geoff Kuenning may not be used to endorse or promote
|
||||||
|
products derived from this software without specific prior
|
||||||
|
written permission.
|
||||||
|
|
||||||
|
THIS SOFTWARE IS PROVIDED BY GEOFF KUENNING AND CONTRIBUTORS ``AS IS'' AND
|
||||||
|
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||||
|
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||||
|
ARE DISCLAIMED. IN NO EVENT SHALL GEOFF KUENNING OR CONTRIBUTORS BE LIABLE
|
||||||
|
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||||
|
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
||||||
|
OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||||
|
HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
||||||
|
LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
||||||
|
OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||||
|
SUCH DAMAGE.
|
||||||
|
|
||||||
|
Build Date: Mon Dec 7 20:19:30 EST 2020
|
||||||
|
Wordlist Command: mk-list --accents=strip en_GB-ise 60
|
||||||
+422
-58
@@ -5,12 +5,40 @@ use crate::order;
|
|||||||
use eframe::egui;
|
use eframe::egui;
|
||||||
use std::collections::HashMap;
|
use std::collections::HashMap;
|
||||||
use std::path::{Path, PathBuf};
|
use std::path::{Path, PathBuf};
|
||||||
|
use std::sync::Arc;
|
||||||
|
use std::time::{Duration, Instant};
|
||||||
|
|
||||||
/// Result of a background grammar check: the matches, or an error message.
|
/// Result of a background grammar check: the matches, or an error message.
|
||||||
type LtCheckResult = Result<Vec<crate::langtool::Match>, String>;
|
type LtCheckResult = Result<Vec<crate::langtool::Match>, String>;
|
||||||
/// Channel payload from a background check: the text that was checked, paired
|
/// Channel payload from a background check: the text that was checked, paired
|
||||||
/// with its result (so the app can confirm the buffer hasn't changed since).
|
/// with its result (so the app can confirm the buffer hasn't changed since).
|
||||||
type LtCheckMsg = (String, LtCheckResult);
|
type LtCheckMsg = (String, LtCheckResult);
|
||||||
|
/// Channel payload from a background spell check: the checked text and the
|
||||||
|
/// spelling matches found in it.
|
||||||
|
type SpellCheckMsg = (String, Vec<crate::langtool::Match>);
|
||||||
|
|
||||||
|
/// Which check currently owns the editor's underlines and the issues panel.
|
||||||
|
#[derive(Clone, Copy, PartialEq, Eq)]
|
||||||
|
enum IssueSource {
|
||||||
|
/// Fresh LanguageTool results for the current buffer (spelling + grammar).
|
||||||
|
LanguageTool,
|
||||||
|
/// Live offline spell-check results (spelling only).
|
||||||
|
Spell,
|
||||||
|
/// Nothing current to show.
|
||||||
|
None,
|
||||||
|
}
|
||||||
|
|
||||||
|
/// An owned snapshot of one issue for the results panel, decoupled from `self`
|
||||||
|
/// so the panel can render without holding a borrow across its click handling.
|
||||||
|
struct IssueItem {
|
||||||
|
/// Index of this item in the source match list (for applying a fix).
|
||||||
|
idx: usize,
|
||||||
|
/// The offending text.
|
||||||
|
snippet: String,
|
||||||
|
message: String,
|
||||||
|
spelling: bool,
|
||||||
|
replacements: Vec<String>,
|
||||||
|
}
|
||||||
|
|
||||||
pub struct App {
|
pub struct App {
|
||||||
config: Config,
|
config: Config,
|
||||||
@@ -86,6 +114,25 @@ pub struct App {
|
|||||||
find_focus: Option<bool>,
|
find_focus: Option<bool>,
|
||||||
/// Request the editor to scroll the active match into view next frame.
|
/// Request the editor to scroll the active match into view next frame.
|
||||||
find_scroll: bool,
|
find_scroll: bool,
|
||||||
|
/// The loaded offline spell-check dictionary (shared with the worker thread).
|
||||||
|
spell_dict: Option<Arc<spellbook::Dictionary>>,
|
||||||
|
/// Dictionaries available to choose from (bundled + discovered on disk).
|
||||||
|
spell_dicts: Vec<crate::spell::DictEntry>,
|
||||||
|
/// Live spelling matches and the buffer text they were computed against.
|
||||||
|
spell_matches: Vec<crate::langtool::Match>,
|
||||||
|
spell_checked_text: String,
|
||||||
|
/// Set when the buffer changed and a re-check is owed.
|
||||||
|
spell_dirty: bool,
|
||||||
|
/// When the buffer was last edited, for debouncing the live check. `None`
|
||||||
|
/// means "check as soon as possible" (e.g. right after opening a file).
|
||||||
|
spell_last_edit: Option<Instant>,
|
||||||
|
/// In-flight background spell check, if any.
|
||||||
|
spell_rx: Option<std::sync::mpsc::Receiver<SpellCheckMsg>>,
|
||||||
|
/// One-line status for the spell checker (dictionary name, count, or error).
|
||||||
|
spell_status: String,
|
||||||
|
/// Index (into the currently displayed matches) of the word a right-click
|
||||||
|
/// suggestion menu is open for, if any.
|
||||||
|
spell_menu: Option<usize>,
|
||||||
}
|
}
|
||||||
|
|
||||||
impl App {
|
impl App {
|
||||||
@@ -131,7 +178,17 @@ impl App {
|
|||||||
find_needs_refresh: false,
|
find_needs_refresh: false,
|
||||||
find_focus: None,
|
find_focus: None,
|
||||||
find_scroll: false,
|
find_scroll: false,
|
||||||
|
spell_dict: None,
|
||||||
|
spell_dicts: crate::spell::available(),
|
||||||
|
spell_matches: Vec::new(),
|
||||||
|
spell_checked_text: String::new(),
|
||||||
|
spell_dirty: true,
|
||||||
|
spell_last_edit: None,
|
||||||
|
spell_rx: None,
|
||||||
|
spell_status: String::new(),
|
||||||
|
spell_menu: None,
|
||||||
};
|
};
|
||||||
|
app.load_spell_dict();
|
||||||
app.open_workspace();
|
app.open_workspace();
|
||||||
app
|
app
|
||||||
}
|
}
|
||||||
@@ -295,6 +352,12 @@ impl App {
|
|||||||
self.find_matches.clear();
|
self.find_matches.clear();
|
||||||
self.find_active = 0;
|
self.find_active = 0;
|
||||||
self.find_needs_refresh = true;
|
self.find_needs_refresh = true;
|
||||||
|
// Re-run the live spell check on the newly loaded buffer immediately.
|
||||||
|
self.spell_matches.clear();
|
||||||
|
self.spell_checked_text.clear();
|
||||||
|
self.spell_dirty = true;
|
||||||
|
self.spell_last_edit = None;
|
||||||
|
self.spell_menu = None;
|
||||||
if let Some(name) = self.files.get(idx) {
|
if let Some(name) = self.files.get(idx) {
|
||||||
let path = self.path_for(name);
|
let path = self.path_for(name);
|
||||||
self.buffer = std::fs::read_to_string(&path).unwrap_or_default();
|
self.buffer = std::fs::read_to_string(&path).unwrap_or_default();
|
||||||
@@ -643,34 +706,223 @@ impl App {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Apply replacement `rep_idx` of match `match_idx` to the buffer, then shift
|
/// Apply a LanguageTool suggestion to the buffer, then shift the remaining
|
||||||
/// the remaining matches so their highlights stay valid.
|
/// matches so their highlights stay valid.
|
||||||
fn apply_replacement(&mut self, match_idx: usize, rep_idx: usize) {
|
fn apply_replacement(&mut self, match_idx: usize, rep_idx: usize) {
|
||||||
// Only safe while the buffer still matches what was checked.
|
// Only safe while the buffer still matches what was checked.
|
||||||
if self.buffer != self.lt_checked_text {
|
if self.buffer != self.lt_checked_text {
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
let Some(m) = self.lt_matches.get(match_idx).cloned() else {
|
if splice_fix(&mut self.buffer, &mut self.lt_matches, match_idx, rep_idx) {
|
||||||
return;
|
|
||||||
};
|
|
||||||
let Some(replacement) = m.replacements.get(rep_idx).cloned() else {
|
|
||||||
return;
|
|
||||||
};
|
|
||||||
if m.end > self.buffer.len() || !self.buffer.is_char_boundary(m.start) {
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
self.buffer.replace_range(m.start..m.end, &replacement);
|
|
||||||
self.dirty = true;
|
self.dirty = true;
|
||||||
|
self.find_needs_refresh = true;
|
||||||
self.lt_checked_text = self.buffer.clone();
|
self.lt_checked_text = self.buffer.clone();
|
||||||
|
|
||||||
// The applied match overlaps its own region, so it is dropped here too.
|
|
||||||
remap_matches(&mut self.lt_matches, m.start, m.end, replacement.len());
|
|
||||||
self.lt_status = match self.lt_matches.len() {
|
self.lt_status = match self.lt_matches.len() {
|
||||||
0 => "No issues remaining".to_string(),
|
0 => "No issues remaining".to_string(),
|
||||||
1 => "1 issue".to_string(),
|
1 => "1 issue".to_string(),
|
||||||
n => format!("{n} issues"),
|
n => format!("{n} issues"),
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Apply a spell-check suggestion to the buffer, keeping the remaining
|
||||||
|
/// misspelling underlines aligned.
|
||||||
|
fn apply_spell_fix(&mut self, match_idx: usize, rep_idx: usize) {
|
||||||
|
if self.buffer != self.spell_checked_text {
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
if splice_fix(&mut self.buffer, &mut self.spell_matches, match_idx, rep_idx) {
|
||||||
|
self.dirty = true;
|
||||||
|
self.find_needs_refresh = true;
|
||||||
|
// Keep these matches valid without forcing a full re-check.
|
||||||
|
self.spell_checked_text = self.buffer.clone();
|
||||||
|
self.spell_status = match self.spell_matches.len() {
|
||||||
|
0 => "No spelling issues".to_string(),
|
||||||
|
1 => "1 spelling issue".to_string(),
|
||||||
|
n => format!("{n} spelling issues"),
|
||||||
|
};
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Apply suggestion `rep_idx` of the match at `match_idx` from whichever
|
||||||
|
/// source currently owns the issues (LanguageTool or the spell checker).
|
||||||
|
fn apply_current_fix(&mut self, match_idx: usize, rep_idx: usize) {
|
||||||
|
match self.issue_source() {
|
||||||
|
IssueSource::LanguageTool => self.apply_replacement(match_idx, rep_idx),
|
||||||
|
IssueSource::Spell => self.apply_spell_fix(match_idx, rep_idx),
|
||||||
|
IssueSource::None => {}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// ---- Spell check (offline) ---------------------------------------------
|
||||||
|
|
||||||
|
/// (Re)load the dictionary named by `config.spell_language`, falling back to
|
||||||
|
/// the default and then to whatever is available. Resets the live results so
|
||||||
|
/// the buffer is re-checked against the new dictionary.
|
||||||
|
fn load_spell_dict(&mut self) {
|
||||||
|
let want = self.config.spell_language.clone();
|
||||||
|
let entry = self
|
||||||
|
.spell_dicts
|
||||||
|
.iter()
|
||||||
|
.find(|d| d.id == want)
|
||||||
|
.or_else(|| {
|
||||||
|
self.spell_dicts
|
||||||
|
.iter()
|
||||||
|
.find(|d| d.id == crate::spell::DEFAULT_LANGUAGE)
|
||||||
|
})
|
||||||
|
.or_else(|| self.spell_dicts.first())
|
||||||
|
.cloned();
|
||||||
|
|
||||||
|
match entry {
|
||||||
|
Some(e) => match e.load() {
|
||||||
|
Ok(dict) => {
|
||||||
|
self.spell_dict = Some(Arc::new(dict));
|
||||||
|
self.spell_status = format!("Dictionary: {}", e.id);
|
||||||
|
}
|
||||||
|
Err(err) => {
|
||||||
|
self.spell_dict = None;
|
||||||
|
self.spell_status = err;
|
||||||
|
}
|
||||||
|
},
|
||||||
|
None => {
|
||||||
|
self.spell_dict = None;
|
||||||
|
self.spell_status = "No spelling dictionary available".to_string();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
self.spell_matches.clear();
|
||||||
|
self.spell_checked_text.clear();
|
||||||
|
self.spell_dirty = true;
|
||||||
|
self.spell_last_edit = None;
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Switch the active dictionary and persist the choice.
|
||||||
|
fn set_spell_language(&mut self, id: &str) {
|
||||||
|
if self.config.spell_language == id {
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
self.config.spell_language = id.to_string();
|
||||||
|
self.config.save();
|
||||||
|
self.load_spell_dict();
|
||||||
|
}
|
||||||
|
|
||||||
|
/// True when LanguageTool results describe the current buffer exactly (so
|
||||||
|
/// they, rather than the live spell checker, own the underlines).
|
||||||
|
fn lt_is_current(&self) -> bool {
|
||||||
|
!self.lt_checked_text.is_empty() && self.buffer == self.lt_checked_text
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Which check currently owns the issues shown in the editor and panel.
|
||||||
|
fn issue_source(&self) -> IssueSource {
|
||||||
|
if self.lt_is_current() {
|
||||||
|
IssueSource::LanguageTool
|
||||||
|
} else if self.config.spell_check
|
||||||
|
&& self.spell_dict.is_some()
|
||||||
|
&& self.buffer == self.spell_checked_text
|
||||||
|
{
|
||||||
|
IssueSource::Spell
|
||||||
|
} else {
|
||||||
|
IssueSource::None
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// The matches currently owning the editor's underlines (may be empty).
|
||||||
|
fn current_matches(&self) -> &[crate::langtool::Match] {
|
||||||
|
match self.issue_source() {
|
||||||
|
IssueSource::LanguageTool => &self.lt_matches,
|
||||||
|
IssueSource::Spell => &self.spell_matches,
|
||||||
|
IssueSource::None => &[],
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Index of the current match covering byte offset `byte`, if any.
|
||||||
|
fn match_index_at(&self, byte: usize) -> Option<usize> {
|
||||||
|
self.current_matches()
|
||||||
|
.iter()
|
||||||
|
.position(|m| byte >= m.start && byte < m.end)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// An owned snapshot of the current issues for the results panel.
|
||||||
|
fn issue_items(&self) -> (IssueSource, Vec<IssueItem>) {
|
||||||
|
let source = self.issue_source();
|
||||||
|
let (matches, checked) = match source {
|
||||||
|
IssueSource::LanguageTool => (&self.lt_matches, self.lt_checked_text.as_str()),
|
||||||
|
IssueSource::Spell => (&self.spell_matches, self.spell_checked_text.as_str()),
|
||||||
|
IssueSource::None => return (source, Vec::new()),
|
||||||
|
};
|
||||||
|
let items = matches
|
||||||
|
.iter()
|
||||||
|
.enumerate()
|
||||||
|
.map(|(idx, m)| IssueItem {
|
||||||
|
idx,
|
||||||
|
snippet: checked.get(m.start..m.end).unwrap_or("").to_string(),
|
||||||
|
message: m.message.clone(),
|
||||||
|
spelling: m.spelling,
|
||||||
|
replacements: m.replacements.clone(),
|
||||||
|
})
|
||||||
|
.collect();
|
||||||
|
(source, items)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// The status line for the spelling checker given a match count.
|
||||||
|
fn spell_count_status(n: usize) -> String {
|
||||||
|
match n {
|
||||||
|
0 => "No spelling issues".to_string(),
|
||||||
|
1 => "1 spelling issue".to_string(),
|
||||||
|
n => format!("{n} spelling issues"),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Pick up a finished background spell check.
|
||||||
|
fn poll_spell(&mut self) {
|
||||||
|
let received = self.spell_rx.as_ref().and_then(|rx| rx.try_recv().ok());
|
||||||
|
if let Some((text, matches)) = received {
|
||||||
|
self.spell_rx = None;
|
||||||
|
if self.spell_dict.is_some() {
|
||||||
|
self.spell_status = Self::spell_count_status(matches.len());
|
||||||
|
}
|
||||||
|
self.spell_matches = matches;
|
||||||
|
self.spell_checked_text = text;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Start a background spell check of the current buffer if one is due:
|
||||||
|
/// enabled, a dictionary loaded, a file open, the buffer changed, no check
|
||||||
|
/// already running, and the debounce interval elapsed since the last edit.
|
||||||
|
fn maybe_start_spell_check(&mut self, ctx: &egui::Context) {
|
||||||
|
if !self.config.spell_check || self.selected.is_none() || !self.spell_dirty {
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
// LanguageTool results already cover this exact buffer (spelling too), so
|
||||||
|
// don't spend effort on a spell pass that wouldn't be shown.
|
||||||
|
if self.lt_is_current() {
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
let Some(dict) = self.spell_dict.clone() else {
|
||||||
|
return;
|
||||||
|
};
|
||||||
|
if self.spell_rx.is_some() {
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
// Debounce so we don't re-check on every keystroke.
|
||||||
|
const DEBOUNCE: Duration = Duration::from_millis(400);
|
||||||
|
if let Some(edited) = self.spell_last_edit {
|
||||||
|
let elapsed = edited.elapsed();
|
||||||
|
if elapsed < DEBOUNCE {
|
||||||
|
ctx.request_repaint_after(DEBOUNCE - elapsed);
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
self.spell_dirty = false;
|
||||||
|
let text = self.buffer.clone();
|
||||||
|
let (tx, rx) = std::sync::mpsc::channel();
|
||||||
|
self.spell_rx = Some(rx);
|
||||||
|
let ctx = ctx.clone();
|
||||||
|
std::thread::spawn(move || {
|
||||||
|
let matches = crate::spell::check(&dict, &text);
|
||||||
|
let _ = tx.send((text, matches));
|
||||||
|
ctx.request_repaint();
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
// ---- Find / replace ----------------------------------------------------
|
// ---- Find / replace ----------------------------------------------------
|
||||||
|
|
||||||
@@ -903,6 +1155,47 @@ impl App {
|
|||||||
ui.label(egui::RichText::new(&self.lt_status).weak());
|
ui.label(egui::RichText::new(&self.lt_status).weak());
|
||||||
}
|
}
|
||||||
});
|
});
|
||||||
|
ui.add_space(2.0);
|
||||||
|
ui.horizontal(|ui| {
|
||||||
|
ui.label("Spelling:").on_hover_text(
|
||||||
|
"Offline spell check (Hunspell dictionaries). Underlines misspellings \
|
||||||
|
as you type when LanguageTool results aren't current; right-click a \
|
||||||
|
word for suggestions.",
|
||||||
|
);
|
||||||
|
if ui
|
||||||
|
.checkbox(&mut self.config.spell_check, "Check as I type")
|
||||||
|
.on_hover_text("Underline misspellings live using the dictionary below")
|
||||||
|
.changed()
|
||||||
|
{
|
||||||
|
self.config.save();
|
||||||
|
if self.config.spell_check {
|
||||||
|
// Re-check the current buffer straight away.
|
||||||
|
self.spell_dirty = true;
|
||||||
|
self.spell_last_edit = None;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
ui.label("Dictionary:");
|
||||||
|
let current = self.config.spell_language.clone();
|
||||||
|
let mut pick: Option<String> = None;
|
||||||
|
egui::ComboBox::from_id_salt("spell_dict")
|
||||||
|
.selected_text(current.clone())
|
||||||
|
.show_ui(ui, |ui| {
|
||||||
|
for d in &self.spell_dicts {
|
||||||
|
if ui
|
||||||
|
.selectable_label(current == d.id, &d.label)
|
||||||
|
.clicked()
|
||||||
|
{
|
||||||
|
pick = Some(d.id.clone());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
});
|
||||||
|
if let Some(id) = pick {
|
||||||
|
self.set_spell_language(&id);
|
||||||
|
}
|
||||||
|
if !self.spell_status.is_empty() {
|
||||||
|
ui.label(egui::RichText::new(&self.spell_status).weak());
|
||||||
|
}
|
||||||
|
});
|
||||||
ui.add_space(4.0);
|
ui.add_space(4.0);
|
||||||
});
|
});
|
||||||
|
|
||||||
@@ -1229,24 +1522,23 @@ impl App {
|
|||||||
self.show_settings = now_open;
|
self.show_settings = now_open;
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Bottom panel listing grammar/spelling issues with one-click fixes.
|
/// Bottom panel listing the current grammar/spelling issues with one-click
|
||||||
|
/// fixes. Shows LanguageTool results when they're fresh, otherwise the live
|
||||||
|
/// spell-check results.
|
||||||
fn lt_panel(&mut self, ctx: &egui::Context) {
|
fn lt_panel(&mut self, ctx: &egui::Context) {
|
||||||
|
let (source, items) = self.issue_items();
|
||||||
egui::TopBottomPanel::bottom("ltpanel")
|
egui::TopBottomPanel::bottom("ltpanel")
|
||||||
.resizable(true)
|
.resizable(true)
|
||||||
.default_height(190.0)
|
.default_height(190.0)
|
||||||
.show(ctx, |ui| {
|
.show(ctx, |ui| {
|
||||||
let stale = self.buffer != self.lt_checked_text;
|
let (title, status) = match source {
|
||||||
|
IssueSource::LanguageTool => ("Grammar & spelling", self.lt_status.clone()),
|
||||||
|
_ => ("Spelling", self.spell_status.clone()),
|
||||||
|
};
|
||||||
ui.horizontal(|ui| {
|
ui.horizontal(|ui| {
|
||||||
ui.label(egui::RichText::new("Grammar & spelling").strong());
|
ui.label(egui::RichText::new(title).strong());
|
||||||
if !self.lt_status.is_empty() {
|
if !status.is_empty() {
|
||||||
ui.label(egui::RichText::new(&self.lt_status).weak());
|
ui.label(egui::RichText::new(status).weak());
|
||||||
}
|
|
||||||
if stale && !self.lt_matches.is_empty() {
|
|
||||||
ui.label(
|
|
||||||
egui::RichText::new("· edited since check — re-check to apply fixes")
|
|
||||||
.weak()
|
|
||||||
.italics(),
|
|
||||||
);
|
|
||||||
}
|
}
|
||||||
ui.with_layout(egui::Layout::right_to_left(egui::Align::Center), |ui| {
|
ui.with_layout(egui::Layout::right_to_left(egui::Align::Center), |ui| {
|
||||||
if ui.button("Hide").clicked() {
|
if ui.button("Hide").clicked() {
|
||||||
@@ -1256,13 +1548,10 @@ impl App {
|
|||||||
});
|
});
|
||||||
ui.separator();
|
ui.separator();
|
||||||
|
|
||||||
if self.lt_matches.is_empty() {
|
if items.is_empty() {
|
||||||
|
let busy = self.lt_rx.is_some() || self.spell_rx.is_some();
|
||||||
ui.label(
|
ui.label(
|
||||||
egui::RichText::new(if self.lt_rx.is_some() {
|
egui::RichText::new(if busy { "Checking…" } else { "No issues to show." })
|
||||||
"Checking…"
|
|
||||||
} else {
|
|
||||||
"No issues to show."
|
|
||||||
})
|
|
||||||
.weak(),
|
.weak(),
|
||||||
);
|
);
|
||||||
return;
|
return;
|
||||||
@@ -1272,34 +1561,31 @@ impl App {
|
|||||||
egui::ScrollArea::vertical()
|
egui::ScrollArea::vertical()
|
||||||
.auto_shrink([false, false])
|
.auto_shrink([false, false])
|
||||||
.show(ui, |ui| {
|
.show(ui, |ui| {
|
||||||
for (i, m) in self.lt_matches.iter().enumerate() {
|
for item in &items {
|
||||||
ui.horizontal_wrapped(|ui| {
|
ui.horizontal_wrapped(|ui| {
|
||||||
let (dot, col) = if m.spelling {
|
let col = if item.spelling {
|
||||||
("●", egui::Color32::from_rgb(0xE0, 0x40, 0x40))
|
egui::Color32::from_rgb(0xE0, 0x40, 0x40)
|
||||||
} else {
|
} else {
|
||||||
("●", egui::Color32::from_rgb(0x3B, 0x82, 0xF6))
|
egui::Color32::from_rgb(0x3B, 0x82, 0xF6)
|
||||||
};
|
};
|
||||||
ui.label(egui::RichText::new(dot).color(col));
|
ui.label(egui::RichText::new("●").color(col));
|
||||||
if let Some(snippet) = self.lt_checked_text.get(m.start..m.end) {
|
if !item.snippet.is_empty() {
|
||||||
ui.label(
|
ui.label(
|
||||||
egui::RichText::new(format!("“{snippet}”")).strong(),
|
egui::RichText::new(format!("“{}”", item.snippet)).strong(),
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
ui.label(&m.message);
|
ui.label(&item.message);
|
||||||
});
|
});
|
||||||
ui.horizontal_wrapped(|ui| {
|
ui.horizontal_wrapped(|ui| {
|
||||||
ui.add_space(16.0);
|
ui.add_space(16.0);
|
||||||
if m.replacements.is_empty() {
|
if item.replacements.is_empty() {
|
||||||
ui.label(
|
ui.label(
|
||||||
egui::RichText::new("(no suggestion)").weak().italics(),
|
egui::RichText::new("(no suggestion)").weak().italics(),
|
||||||
);
|
);
|
||||||
} else {
|
} else {
|
||||||
for (j, rep) in m.replacements.iter().take(8).enumerate() {
|
for (j, rep) in item.replacements.iter().enumerate() {
|
||||||
if ui
|
if ui.button(egui::RichText::new(rep).small()).clicked() {
|
||||||
.add_enabled(!stale, egui::Button::new(rep).small())
|
apply = Some((item.idx, j));
|
||||||
.clicked()
|
|
||||||
{
|
|
||||||
apply = Some((i, j));
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -1309,7 +1595,7 @@ impl App {
|
|||||||
});
|
});
|
||||||
|
|
||||||
if let Some((i, j)) = apply {
|
if let Some((i, j)) = apply {
|
||||||
self.apply_replacement(i, j);
|
self.apply_current_fix(i, j);
|
||||||
}
|
}
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
@@ -1435,16 +1721,13 @@ impl App {
|
|||||||
// Editor text colour, brightened toward max contrast by the contrast slider.
|
// Editor text colour, brightened toward max contrast by the contrast slider.
|
||||||
let text_color = editor_text_color(ui.visuals(), self.config.editor_text_contrast);
|
let text_color = editor_text_color(ui.visuals(), self.config.editor_text_contrast);
|
||||||
|
|
||||||
// Underline grammar/spelling matches, but only while the buffer still
|
// Underline whichever check currently owns the buffer's issues
|
||||||
// equals the text they were computed against (edits invalidate offsets).
|
// (LanguageTool when fresh, otherwise the live spell checker).
|
||||||
let ranges: Vec<(usize, usize, bool)> = if self.buffer == self.lt_checked_text {
|
let ranges: Vec<(usize, usize, bool)> = self
|
||||||
self.lt_matches
|
.current_matches()
|
||||||
.iter()
|
.iter()
|
||||||
.map(|m| (m.start, m.end, m.spelling))
|
.map(|m| (m.start, m.end, m.spelling))
|
||||||
.collect()
|
.collect();
|
||||||
} else {
|
|
||||||
Vec::new()
|
|
||||||
};
|
|
||||||
|
|
||||||
// Search-match highlights (all matches shaded, the active one stronger).
|
// Search-match highlights (all matches shaded, the active one stronger).
|
||||||
let find_ranges: Vec<(usize, usize)> = if self.show_find {
|
let find_ranges: Vec<(usize, usize)> = if self.show_find {
|
||||||
@@ -1482,8 +1765,11 @@ impl App {
|
|||||||
.show(ui);
|
.show(ui);
|
||||||
if output.response.changed() {
|
if output.response.changed() {
|
||||||
self.dirty = true;
|
self.dirty = true;
|
||||||
// The buffer changed, so any search matches are now stale.
|
// The buffer changed, so search matches and the live spell
|
||||||
|
// check both need refreshing (the latter debounced).
|
||||||
self.find_needs_refresh = true;
|
self.find_needs_refresh = true;
|
||||||
|
self.spell_dirty = true;
|
||||||
|
self.spell_last_edit = Some(Instant::now());
|
||||||
}
|
}
|
||||||
// Markdown formatting hotkeys, applied to the current selection
|
// Markdown formatting hotkeys, applied to the current selection
|
||||||
// while the editor is focused (Ctrl/Cmd + B / I / E / K, and
|
// while the editor is focused (Ctrl/Cmd + B / I / E / K, and
|
||||||
@@ -1524,6 +1810,55 @@ impl App {
|
|||||||
}
|
}
|
||||||
self.find_scroll = false;
|
self.find_scroll = false;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Right-click a misspelling → a menu of suggested corrections.
|
||||||
|
if output.response.secondary_clicked() {
|
||||||
|
self.spell_menu = output.response.interact_pointer_pos().and_then(|pos| {
|
||||||
|
let local = pos - output.galley_pos;
|
||||||
|
let cursor = output.galley.cursor_from_pos(local);
|
||||||
|
let byte = char_to_byte(&self.buffer, cursor.ccursor.index);
|
||||||
|
self.match_index_at(byte)
|
||||||
|
});
|
||||||
|
}
|
||||||
|
// Snapshot the target's suggestions (owned) so the menu closure
|
||||||
|
// doesn't borrow self; compute them on demand if the background
|
||||||
|
// check hadn't produced any for this word.
|
||||||
|
let menu: Option<(usize, Vec<String>)> = self.spell_menu.and_then(|i| {
|
||||||
|
let m = self.current_matches().get(i)?;
|
||||||
|
let mut reps = m.replacements.clone();
|
||||||
|
if reps.is_empty() {
|
||||||
|
if let (Some(dict), Some(word)) =
|
||||||
|
(&self.spell_dict, self.buffer.get(m.start..m.end))
|
||||||
|
{
|
||||||
|
reps = crate::spell::suggestions(dict, word);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Some((i, reps))
|
||||||
|
});
|
||||||
|
let mut chosen: Option<(usize, usize)> = None;
|
||||||
|
output.response.context_menu(|ui| {
|
||||||
|
match &menu {
|
||||||
|
Some((i, reps)) if !reps.is_empty() => {
|
||||||
|
ui.label(egui::RichText::new("Suggestions").strong());
|
||||||
|
for (j, rep) in reps.iter().enumerate() {
|
||||||
|
if ui.button(rep).clicked() {
|
||||||
|
chosen = Some((*i, j));
|
||||||
|
ui.close_menu();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Some(_) => {
|
||||||
|
ui.label(egui::RichText::new("No suggestions").weak());
|
||||||
|
}
|
||||||
|
None => {
|
||||||
|
ui.label(egui::RichText::new("No spelling issue here").weak());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
});
|
||||||
|
if let Some((i, j)) = chosen {
|
||||||
|
self.apply_current_fix(i, j);
|
||||||
|
self.spell_menu = None;
|
||||||
|
}
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1690,6 +2025,8 @@ impl eframe::App for App {
|
|||||||
|
|
||||||
self.poll_lt();
|
self.poll_lt();
|
||||||
self.poll_settings_test();
|
self.poll_settings_test();
|
||||||
|
self.poll_spell();
|
||||||
|
self.maybe_start_spell_check(ctx);
|
||||||
|
|
||||||
self.menu_bar(ctx);
|
self.menu_bar(ctx);
|
||||||
self.top_bar(ctx);
|
self.top_bar(ctx);
|
||||||
@@ -2180,6 +2517,33 @@ fn resolve_chapter_title(
|
|||||||
.unwrap_or_else(|| format!("{:0width$}.", index + 1, width = pad_width))
|
.unwrap_or_else(|| format!("{:0width$}.", index + 1, width = pad_width))
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// Apply suggestion `rep_idx` of `matches[match_idx]` to `buffer` in place and
|
||||||
|
/// remap the remaining matches. Returns whether a replacement was made (false if
|
||||||
|
/// the indices are out of range or the match's bounds aren't valid boundaries).
|
||||||
|
fn splice_fix(
|
||||||
|
buffer: &mut String,
|
||||||
|
matches: &mut Vec<crate::langtool::Match>,
|
||||||
|
match_idx: usize,
|
||||||
|
rep_idx: usize,
|
||||||
|
) -> bool {
|
||||||
|
let Some(m) = matches.get(match_idx).cloned() else {
|
||||||
|
return false;
|
||||||
|
};
|
||||||
|
let Some(replacement) = m.replacements.get(rep_idx).cloned() else {
|
||||||
|
return false;
|
||||||
|
};
|
||||||
|
if m.end > buffer.len()
|
||||||
|
|| !buffer.is_char_boundary(m.start)
|
||||||
|
|| !buffer.is_char_boundary(m.end)
|
||||||
|
{
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
buffer.replace_range(m.start..m.end, &replacement);
|
||||||
|
// The applied match overlaps its own region, so it is dropped here too.
|
||||||
|
remap_matches(matches, m.start, m.end, replacement.len());
|
||||||
|
true
|
||||||
|
}
|
||||||
|
|
||||||
/// Re-position matches after the byte range `[s, e)` was replaced with `new_len`
|
/// Re-position matches after the byte range `[s, e)` was replaced with `new_len`
|
||||||
/// bytes. Matches that overlapped the edited region (including the one that was
|
/// bytes. Matches that overlapped the edited region (including the one that was
|
||||||
/// just applied) are dropped; matches entirely after it are shifted by the
|
/// just applied) are dropped; matches entirely after it are shifted by the
|
||||||
|
|||||||
@@ -45,6 +45,24 @@ pub struct Config {
|
|||||||
/// Language passed to LanguageTool (`auto` to detect, or a code like `en-US`).
|
/// Language passed to LanguageTool (`auto` to detect, or a code like `en-US`).
|
||||||
#[serde(default = "default_languagetool_language")]
|
#[serde(default = "default_languagetool_language")]
|
||||||
pub languagetool_language: String,
|
pub languagetool_language: String,
|
||||||
|
/// Whether the offline (Hunspell) live spell checker underlines misspellings
|
||||||
|
/// as you type. Used whenever LanguageTool results aren't current.
|
||||||
|
#[serde(default = "default_spell_check")]
|
||||||
|
pub spell_check: bool,
|
||||||
|
/// Id of the spell-check dictionary to use (e.g. `en-CA`, `en_GB`), matching
|
||||||
|
/// a [`crate::spell::DictEntry::id`].
|
||||||
|
#[serde(default = "default_spell_language")]
|
||||||
|
pub spell_language: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Live spell checking is on by default.
|
||||||
|
pub fn default_spell_check() -> bool {
|
||||||
|
true
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Default dictionary: the built-in Canadian English one.
|
||||||
|
pub fn default_spell_language() -> String {
|
||||||
|
crate::spell::DEFAULT_LANGUAGE.to_string()
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Default scheme: plain HTTP, matching a local server.
|
/// Default scheme: plain HTTP, matching a local server.
|
||||||
@@ -89,6 +107,8 @@ impl Default for Config {
|
|||||||
languagetool_port: default_languagetool_port(),
|
languagetool_port: default_languagetool_port(),
|
||||||
languagetool_token: String::new(),
|
languagetool_token: String::new(),
|
||||||
languagetool_language: default_languagetool_language(),
|
languagetool_language: default_languagetool_language(),
|
||||||
|
spell_check: default_spell_check(),
|
||||||
|
spell_language: default_spell_language(),
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
+13
-4
@@ -140,12 +140,21 @@ fn cheatsheet_body(ui: &mut egui::Ui) {
|
|||||||
blank to export the whole file. Comments are removed everywhere.",
|
blank to export the whole file. Comments are removed everywhere.",
|
||||||
);
|
);
|
||||||
|
|
||||||
section(ui, "Grammar & spelling");
|
section(ui, "Spelling & grammar");
|
||||||
body(
|
body(
|
||||||
ui,
|
ui,
|
||||||
"Press ✓ Check (or the Grammar panel) to run the current file through your \
|
"Spelling is checked live and offline: misspellings are underlined in red \
|
||||||
LanguageTool server — configure it in Settings ▸ LanguageTool. Spelling issues \
|
as you type — right-click a word for correction suggestions. Choose the \
|
||||||
are underlined in red, grammar/style in blue.",
|
dictionary (Canadian or British English are built in) on the Spelling row \
|
||||||
|
of the top bar, or drop more Hunspell .aff/.dic files in \
|
||||||
|
~/.config/md-manuscript/dictionaries/.",
|
||||||
|
);
|
||||||
|
note(
|
||||||
|
ui,
|
||||||
|
"For grammar and style too, press ✓ Check to run the file through a \
|
||||||
|
LanguageTool server (configure it in Settings ▸ LanguageTool). Its results \
|
||||||
|
(grammar in blue, spelling in red) take over until you edit again, then the \
|
||||||
|
offline spell check resumes.",
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -10,6 +10,7 @@ mod langtool;
|
|||||||
mod odt;
|
mod odt;
|
||||||
mod order;
|
mod order;
|
||||||
mod preprocess;
|
mod preprocess;
|
||||||
|
mod spell;
|
||||||
|
|
||||||
use eframe::egui;
|
use eframe::egui;
|
||||||
|
|
||||||
|
|||||||
+392
@@ -0,0 +1,392 @@
|
|||||||
|
//! Offline spell checking with [`spellbook`], a pure-Rust reader of Hunspell
|
||||||
|
//! `.aff`/`.dic` dictionaries (so the binary stays self-contained — no C
|
||||||
|
//! `libhunspell` to link against).
|
||||||
|
//!
|
||||||
|
//! Two dictionaries are compiled into the program (Canadian and British
|
||||||
|
//! English); additional Hunspell dictionaries are discovered at runtime from
|
||||||
|
//! the usual system folders and a per-user folder. The checker walks the prose
|
||||||
|
//! of a markdown buffer (skipping code spans, code blocks and link targets via
|
||||||
|
//! `pulldown-cmark`) and reports each unknown word as a spelling
|
||||||
|
//! [`Match`](crate::langtool::Match), reusing the same type LanguageTool
|
||||||
|
//! produces so the editor's underlines, results panel and one-click fixes work
|
||||||
|
//! unchanged.
|
||||||
|
|
||||||
|
use crate::langtool::Match;
|
||||||
|
use spellbook::Dictionary;
|
||||||
|
use std::collections::HashMap;
|
||||||
|
use std::path::PathBuf;
|
||||||
|
|
||||||
|
// --- Bundled dictionaries (SCOWL-derived, permissive license; see the files
|
||||||
|
// under `dictionaries/<lang>/license`) --------------------------------------
|
||||||
|
|
||||||
|
const EN_CA_AFF: &str = include_str!("../dictionaries/en-CA/index.aff");
|
||||||
|
const EN_CA_DIC: &str = include_str!("../dictionaries/en-CA/index.dic");
|
||||||
|
const EN_GB_AFF: &str = include_str!("../dictionaries/en-GB/index.aff");
|
||||||
|
const EN_GB_DIC: &str = include_str!("../dictionaries/en-GB/index.dic");
|
||||||
|
|
||||||
|
/// The language id selected by default when none is configured.
|
||||||
|
pub const DEFAULT_LANGUAGE: &str = "en-CA";
|
||||||
|
|
||||||
|
/// A dictionary the app can load, either compiled in or found on disk.
|
||||||
|
#[derive(Debug, Clone)]
|
||||||
|
pub struct DictEntry {
|
||||||
|
/// Stable identifier stored in the config (e.g. `en-CA`, `en_GB`, `de_DE`).
|
||||||
|
pub id: String,
|
||||||
|
/// Human-readable label for the picker.
|
||||||
|
pub label: String,
|
||||||
|
kind: DictKind,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Debug, Clone)]
|
||||||
|
enum DictKind {
|
||||||
|
/// Compiled into the binary.
|
||||||
|
Bundled {
|
||||||
|
aff: &'static str,
|
||||||
|
dic: &'static str,
|
||||||
|
},
|
||||||
|
/// A pair of files on disk (`<stem>.aff` + `<stem>.dic`).
|
||||||
|
Files { aff: PathBuf, dic: PathBuf },
|
||||||
|
}
|
||||||
|
|
||||||
|
impl DictEntry {
|
||||||
|
/// Read and parse this dictionary into a usable [`Dictionary`].
|
||||||
|
pub fn load(&self) -> Result<Dictionary, String> {
|
||||||
|
match &self.kind {
|
||||||
|
DictKind::Bundled { aff, dic } => Dictionary::new(aff, dic)
|
||||||
|
.map_err(|e| format!("Could not parse the built-in {} dictionary: {e}", self.id)),
|
||||||
|
DictKind::Files { aff, dic } => {
|
||||||
|
let aff_text = std::fs::read_to_string(aff)
|
||||||
|
.map_err(|e| format!("Cannot read {}: {e}", aff.display()))?;
|
||||||
|
let dic_text = std::fs::read_to_string(dic)
|
||||||
|
.map_err(|e| format!("Cannot read {}: {e}", dic.display()))?;
|
||||||
|
Dictionary::new(&aff_text, &dic_text)
|
||||||
|
.map_err(|e| format!("Could not parse {}: {e}", dic.display()))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// The list of dictionaries available to the app: the two bundled English
|
||||||
|
/// variants first, then any others discovered on disk (deduplicated by id),
|
||||||
|
/// sorted by label.
|
||||||
|
pub fn available() -> Vec<DictEntry> {
|
||||||
|
let mut entries = vec![
|
||||||
|
DictEntry {
|
||||||
|
id: "en-CA".to_string(),
|
||||||
|
label: "English (Canada) — built-in".to_string(),
|
||||||
|
kind: DictKind::Bundled {
|
||||||
|
aff: EN_CA_AFF,
|
||||||
|
dic: EN_CA_DIC,
|
||||||
|
},
|
||||||
|
},
|
||||||
|
DictEntry {
|
||||||
|
id: "en-GB".to_string(),
|
||||||
|
label: "English (UK) — built-in".to_string(),
|
||||||
|
kind: DictKind::Bundled {
|
||||||
|
aff: EN_GB_AFF,
|
||||||
|
dic: EN_GB_DIC,
|
||||||
|
},
|
||||||
|
},
|
||||||
|
];
|
||||||
|
|
||||||
|
for dir in search_dirs() {
|
||||||
|
let Ok(read) = std::fs::read_dir(&dir) else {
|
||||||
|
continue;
|
||||||
|
};
|
||||||
|
for entry in read.flatten() {
|
||||||
|
let path = entry.path();
|
||||||
|
if path.extension().and_then(|e| e.to_str()) != Some("dic") {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
let Some(stem) = path.file_stem().and_then(|s| s.to_str()) else {
|
||||||
|
continue;
|
||||||
|
};
|
||||||
|
let aff = path.with_extension("aff");
|
||||||
|
if !aff.exists() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
// Don't shadow a bundled entry (or an earlier directory's copy).
|
||||||
|
if entries.iter().any(|e| e.id == stem) {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
entries.push(DictEntry {
|
||||||
|
id: stem.to_string(),
|
||||||
|
label: format!("{stem} ({})", dir.display()),
|
||||||
|
kind: DictKind::Files { aff, dic: path },
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
entries.sort_by(|a, b| a.label.cmp(&b.label));
|
||||||
|
entries
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Directories scanned for extra `.aff`/`.dic` pairs, most specific last so a
|
||||||
|
/// user copy can be preferred. Missing directories are simply skipped.
|
||||||
|
fn search_dirs() -> Vec<PathBuf> {
|
||||||
|
let mut dirs = vec![
|
||||||
|
PathBuf::from("/usr/share/hunspell"),
|
||||||
|
PathBuf::from("/usr/share/myspell"),
|
||||||
|
PathBuf::from("/usr/share/myspell/dicts"),
|
||||||
|
PathBuf::from("/usr/local/share/hunspell"),
|
||||||
|
];
|
||||||
|
if let Some(data) = dirs::data_dir() {
|
||||||
|
dirs.push(data.join("hunspell"));
|
||||||
|
}
|
||||||
|
if let Some(config) = dirs::config_dir() {
|
||||||
|
dirs.push(config.join("md-manuscript").join("dictionaries"));
|
||||||
|
}
|
||||||
|
dirs
|
||||||
|
}
|
||||||
|
|
||||||
|
/// How many distinct misspellings we compute suggestions for per check. Beyond
|
||||||
|
/// this the words are still underlined but carry no suggestions (a right-click
|
||||||
|
/// falls back to computing them on demand). Keeps a document full of unknown
|
||||||
|
/// words — names, invented terms — from stalling the background check.
|
||||||
|
const MAX_SUGGEST_WORDS: usize = 250;
|
||||||
|
|
||||||
|
/// Spell-check the prose in `text`, returning a spelling [`Match`] for every
|
||||||
|
/// unknown word (byte offsets into `text`, best suggestions first).
|
||||||
|
pub fn check(dict: &Dictionary, text: &str) -> Vec<Match> {
|
||||||
|
let mut out = Vec::new();
|
||||||
|
let mut cache: HashMap<&str, Vec<String>> = HashMap::new();
|
||||||
|
let mut suggested = 0usize;
|
||||||
|
|
||||||
|
for (offset, word) in prose_words(text) {
|
||||||
|
if should_skip(word) || dict.check(word) {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
let replacements = if let Some(cached) = cache.get(word) {
|
||||||
|
cached.clone()
|
||||||
|
} else if suggested < MAX_SUGGEST_WORDS {
|
||||||
|
let sugg = suggestions(dict, word);
|
||||||
|
suggested += 1;
|
||||||
|
cache.insert(word, sugg.clone());
|
||||||
|
sugg
|
||||||
|
} else {
|
||||||
|
Vec::new()
|
||||||
|
};
|
||||||
|
out.push(Match {
|
||||||
|
start: offset,
|
||||||
|
end: offset + word.len(),
|
||||||
|
message: format!("“{word}” may be misspelled"),
|
||||||
|
replacements,
|
||||||
|
spelling: true,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
out
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Suggestions for a single word (best first, capped), for on-demand use.
|
||||||
|
pub fn suggestions(dict: &Dictionary, word: &str) -> Vec<String> {
|
||||||
|
let mut sugg = Vec::new();
|
||||||
|
dict.suggest(word, &mut sugg);
|
||||||
|
sugg.truncate(8);
|
||||||
|
sugg
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Whether a token should not be checked: too short, an all-caps initialism, or
|
||||||
|
/// containing no alphabetic character.
|
||||||
|
fn should_skip(word: &str) -> bool {
|
||||||
|
let mut letters = 0usize;
|
||||||
|
let mut all_upper = true;
|
||||||
|
for ch in word.chars() {
|
||||||
|
if ch.is_alphabetic() {
|
||||||
|
letters += 1;
|
||||||
|
if !ch.is_uppercase() {
|
||||||
|
all_upper = false;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if letters < 2 {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
// Skip ALL-CAPS tokens (acronyms/initialisms like ODT, HTTP, NASA).
|
||||||
|
all_upper
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Extract the checkable prose words of a markdown buffer as `(byte_offset,
|
||||||
|
/// word)` pairs. Code spans, fenced/indented code blocks and link/image targets
|
||||||
|
/// are excluded (they arrive as non-`Text` events), and surrounding apostrophes
|
||||||
|
/// are trimmed so contractions like `don't` stay intact but `'quoted'` doesn't
|
||||||
|
/// keep its quotes.
|
||||||
|
fn prose_words(text: &str) -> Vec<(usize, &str)> {
|
||||||
|
use pulldown_cmark::{Event, Options, Parser, Tag, TagEnd};
|
||||||
|
let mut words = Vec::new();
|
||||||
|
let mut in_code_block = false;
|
||||||
|
let parser = Parser::new_ext(text, Options::ENABLE_STRIKETHROUGH).into_offset_iter();
|
||||||
|
for (event, range) in parser {
|
||||||
|
match event {
|
||||||
|
// Fenced/indented code-block *content* arrives as Text events, so
|
||||||
|
// suppress tokenizing while inside one. (Inline code is Event::Code.)
|
||||||
|
Event::Start(Tag::CodeBlock(_)) => in_code_block = true,
|
||||||
|
Event::End(TagEnd::CodeBlock) => in_code_block = false,
|
||||||
|
Event::Text(_) if !in_code_block => {
|
||||||
|
// Use the source slice (not the decoded Cow) so offsets are exact.
|
||||||
|
tokenize(range.start, &text[range.clone()], &mut words);
|
||||||
|
}
|
||||||
|
_ => {}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
words
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Split a run of prose into words, pushing `(absolute_byte_offset, word)`.
|
||||||
|
fn tokenize<'a>(base: usize, s: &'a str, out: &mut Vec<(usize, &'a str)>) {
|
||||||
|
let is_word = |c: char| c.is_alphabetic() || c == '\'' || c == '’';
|
||||||
|
let mut start: Option<usize> = None;
|
||||||
|
for (idx, ch) in s.char_indices() {
|
||||||
|
match (start, is_word(ch)) {
|
||||||
|
(None, true) => start = Some(idx),
|
||||||
|
(Some(st), false) => {
|
||||||
|
push_word(base, s, st, idx, out);
|
||||||
|
start = None;
|
||||||
|
}
|
||||||
|
_ => {}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if let Some(st) = start {
|
||||||
|
push_word(base, s, st, s.len(), out);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Trim leading/trailing apostrophes from `s[st..en]` and, if anything remains,
|
||||||
|
/// push it with its absolute byte offset.
|
||||||
|
fn push_word<'a>(base: usize, s: &'a str, st: usize, en: usize, out: &mut Vec<(usize, &'a str)>) {
|
||||||
|
let raw = &s[st..en];
|
||||||
|
let quote = |c: char| c == '\'' || c == '’';
|
||||||
|
let trimmed = raw.trim_matches(quote);
|
||||||
|
if trimmed.is_empty() {
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
let lead = raw.len() - raw.trim_start_matches(quote).len();
|
||||||
|
out.push((base + st + lead, trimmed));
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg(test)]
|
||||||
|
mod tests {
|
||||||
|
use super::*;
|
||||||
|
|
||||||
|
fn en_ca() -> Dictionary {
|
||||||
|
DictEntry {
|
||||||
|
id: "en-CA".to_string(),
|
||||||
|
label: String::new(),
|
||||||
|
kind: DictKind::Bundled {
|
||||||
|
aff: EN_CA_AFF,
|
||||||
|
dic: EN_CA_DIC,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
.load()
|
||||||
|
.expect("bundled en-CA dictionary parses")
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn bundled_dictionaries_are_listed_and_parse() {
|
||||||
|
let list = available();
|
||||||
|
for id in ["en-CA", "en-GB"] {
|
||||||
|
let entry = list
|
||||||
|
.iter()
|
||||||
|
.find(|d| d.id == id)
|
||||||
|
.unwrap_or_else(|| panic!("{id} should be available"));
|
||||||
|
entry
|
||||||
|
.load()
|
||||||
|
.unwrap_or_else(|e| panic!("bundled {id} should parse: {e}"));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn en_gb_prefers_british_spelling() {
|
||||||
|
let dict = available()
|
||||||
|
.into_iter()
|
||||||
|
.find(|d| d.id == "en-GB")
|
||||||
|
.unwrap()
|
||||||
|
.load()
|
||||||
|
.unwrap();
|
||||||
|
// "realise" is British; "color" (American) is not en-GB.
|
||||||
|
assert!(check(&dict, "realise").is_empty());
|
||||||
|
assert_eq!(check(&dict, "color").len(), 1);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn tokenizer_yields_prose_words_with_offsets() {
|
||||||
|
let text = "The cat sat.";
|
||||||
|
let mut words = Vec::new();
|
||||||
|
tokenize(0, text, &mut words);
|
||||||
|
assert_eq!(words, vec![(0, "The"), (4, "cat"), (8, "sat")]);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn tokenizer_keeps_contractions_but_trims_quotes() {
|
||||||
|
let text = "don't 'quoted'";
|
||||||
|
let mut words = Vec::new();
|
||||||
|
tokenize(0, text, &mut words);
|
||||||
|
assert_eq!(words, vec![(0, "don't"), (7, "quoted")]);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn prose_words_skip_code_spans_and_blocks() {
|
||||||
|
// Inline code and a fenced block must not be tokenized.
|
||||||
|
let text = "real word `codeword` end\n\n```\nblockword\n```\n";
|
||||||
|
let words = prose_words(text);
|
||||||
|
let found: Vec<&str> = words.iter().map(|(_, w)| *w).collect();
|
||||||
|
assert!(found.contains(&"real"));
|
||||||
|
assert!(found.contains(&"word"));
|
||||||
|
assert!(found.contains(&"end"));
|
||||||
|
assert!(!found.contains(&"codeword"));
|
||||||
|
assert!(!found.contains(&"blockword"));
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn should_skip_short_and_allcaps() {
|
||||||
|
assert!(should_skip("a")); // too short
|
||||||
|
assert!(should_skip("ODT")); // acronym
|
||||||
|
assert!(should_skip("HTTP"));
|
||||||
|
assert!(!should_skip("word"));
|
||||||
|
assert!(!should_skip("The")); // initial cap is fine
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn check_flags_misspellings_with_correct_offsets() {
|
||||||
|
let dict = en_ca();
|
||||||
|
let text = "The quikc brown fox.";
|
||||||
|
let matches = check(&dict, text);
|
||||||
|
assert_eq!(matches.len(), 1, "only 'quikc' is misspelled");
|
||||||
|
let m = &matches[0];
|
||||||
|
assert_eq!(&text[m.start..m.end], "quikc");
|
||||||
|
assert!(m.spelling);
|
||||||
|
// spellbook should suggest the obvious correction.
|
||||||
|
assert!(
|
||||||
|
m.replacements.iter().any(|r| r == "quick"),
|
||||||
|
"expected 'quick' among suggestions, got {:?}",
|
||||||
|
m.replacements
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn check_respects_canadian_spelling() {
|
||||||
|
let dict = en_ca();
|
||||||
|
// "colour" is correct in en-CA; "color" is not.
|
||||||
|
assert!(check(&dict, "colour").is_empty());
|
||||||
|
assert_eq!(check(&dict, "color").len(), 1);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn check_offsets_survive_multibyte_prose() {
|
||||||
|
let dict = en_ca();
|
||||||
|
// The é is two bytes; a misspelling after it must still map to the right
|
||||||
|
// bytes (whether or not "café" itself is in the dictionary).
|
||||||
|
let text = "café qmzxk";
|
||||||
|
let matches = check(&dict, text);
|
||||||
|
let target = matches
|
||||||
|
.iter()
|
||||||
|
.find(|m| text.get(m.start..m.end) == Some("qmzxk"));
|
||||||
|
assert!(
|
||||||
|
target.is_some(),
|
||||||
|
"expected a match slicing to 'qmzxk', got {:?}",
|
||||||
|
matches
|
||||||
|
.iter()
|
||||||
|
.map(|m| &text[m.start..m.end])
|
||||||
|
.collect::<Vec<_>>()
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user