md-manuscript/src/app/spelling.rs

//! Offline spell checking: loading a bundled or system Hunspell dictionary,
//! running checks in the background, and applying a correction.

use super::*;

impl App {
    /// Apply a spell-check suggestion to the buffer, keeping the remaining
    /// misspelling underlines aligned.
    pub(super) fn apply_spell_fix(&mut self, match_idx: usize, rep_idx: usize) -> bool {
        if self.buffer != self.spell_checked_text {
            return false;
        }
        if !splice_fix(&mut self.buffer, &mut self.spell_matches, match_idx, rep_idx) {
            return false;
        }
        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"),
        };
        true
    }

    // ---- 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.
    pub(super) 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.
    pub(super) 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();
    }

    /// The status line for the spelling checker given a match count.
    pub(super) 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.
    pub(super) 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;
            self.spell_matches = matches;
            self.spell_checked_text = text;
            // Words the user waved away stay quiet across re-checks.
            drop_dismissed(
                &mut self.spell_matches,
                &self.spell_checked_text,
                &self.dismissed,
            );
            if self.spell_dict.is_some() {
                self.spell_status = Self::spell_count_status(self.spell_matches.len());
            }
        }
    }

    /// 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.
    pub(super) 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 extra = self.wordlist.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, &extra, &text);
            let _ = tx.send((text, matches));
            ctx.request_repaint();
        });
    }

    // ---- The project word list ---------------------------------------------

    /// Accept `word` from now on: add it to the workspace's word list, persist
    /// it, and drop the underlines it was causing without waiting for a
    /// re-check.
    pub(super) fn add_to_dictionary(&mut self, word: &str) {
        let word = word.trim().to_string();
        if word.is_empty() {
            return;
        }
        if !self.wordlist.insert(&word) {
            self.spell_status = format!("“{word}” is already in the word list");
            return;
        }
        self.persist_wordlist();
        self.drop_accepted_matches();
        self.spell_status = format!("Added “{word}” — {}", Self::spell_count_status(
            self.spell_matches.len()
        ));
    }

    /// Stop accepting `word`, so it is flagged again.
    pub(super) fn remove_from_dictionary(&mut self, word: &str) {
        if self.wordlist.remove(word) {
            self.persist_wordlist();
            // The word has to be found again, which needs a full pass.
            self.spell_dirty = true;
            self.spell_last_edit = None;
            self.spell_status = format!("Removed “{word}” from the word list");
        }
    }

    pub(super) fn persist_wordlist(&mut self) {
        if let Err(e) = crate::spell::write_wordlist(self.workspace(), &self.wordlist) {
            self.status = format!("Could not save the word list: {e}");
        }
    }

    /// Clear the matches the word list now accepts, so an added word stops being
    /// underlined immediately rather than after the next debounce.
    fn drop_accepted_matches(&mut self) {
        let text = self.spell_checked_text.clone();
        let list = self.wordlist.clone();
        self.spell_matches.retain(|m| {
            text.get(m.start..m.end)
                .is_none_or(|w| !list.accepts(w))
        });
        self.spell_menu = None;
    }

    /// The project's character folder, looked for beside the workspace and then
    /// up through its ancestors — in a snowflake project the workspace is
    /// `05-First Draft` and the sheets are its sibling `03-Story-Bible`.
    pub(super) fn characters_dir(&self) -> Option<PathBuf> {
        /// How far up to look before giving up; deep enough for the layout,
        /// shallow enough not to wander into the home directory.
        const MAX_UP: usize = 3;
        let mut dir = Some(self.workspace());
        for _ in 0..=MAX_UP {
            let current = dir?;
            if let Ok(read) = std::fs::read_dir(current) {
                for entry in read.flatten() {
                    let name = entry.file_name();
                    let Some(name) = name.to_str() else { continue };
                    if crate::spell::is_characters_dir(name) && entry.path().is_dir() {
                        return Some(entry.path());
                    }
                }
            }
            dir = current.parent();
        }
        None
    }

    /// Add every name found in the project's character sheets to the word list.
    /// Returns how many were new, or an error message.
    pub(super) fn harvest_character_names(&mut self) -> Result<usize, String> {
        let dir = self
            .characters_dir()
            .ok_or_else(|| "No character folder found near this workspace".to_string())?;
        let mut added = 0usize;
        let mut sheets = 0usize;
        for path in markdown_files_under(&dir) {
            let Ok(text) = std::fs::read_to_string(&path) else {
                continue;
            };
            sheets += 1;
            for name in crate::spell::names_from_sheet(&text) {
                if self.wordlist.insert(&name) {
                    added += 1;
                }
            }
        }
        if sheets == 0 {
            return Err(format!("No character sheets in {}", dir.display()));
        }
        if added > 0 {
            self.persist_wordlist();
            self.drop_accepted_matches();
        }
        Ok(added)
    }
    /// The workspace's word list: what the checker accepts on top of the
    /// dictionary, where it came from, and how to take a word back out.
    pub(super) fn wordlist_window(&mut self, ctx: &egui::Context) {
        let mut open = self.show_wordlist;
        let mut close = false;
        let mut remove: Option<String> = None;
        let mut harvest = false;

        egui::Window::new("Word list")
            .open(&mut open)
            .resizable(true)
            .collapsible(false)
            .default_width(360.0)
            .show(ctx, |ui| {
                ui.label(
                    egui::RichText::new(
                        "Names and invented terms the spell checker accepts. Saved in \
                         the workspace as wordlist.json, so it is committed with the \
                         manuscript.",
                    )
                    .small()
                    .weak(),
                );
                ui.add_space(4.0);

                ui.horizontal(|ui| {
                    ui.add(
                        egui::TextEdit::singleline(&mut self.wordlist_input)
                            .hint_text("add a word")
                            .desired_width(200.0),
                    );
                    if ui.button("＋ Add").clicked() {
                        let word = self.wordlist_input.trim().to_string();
                        if !word.is_empty() {
                            self.add_to_dictionary(&word);
                            self.wordlist_input.clear();
                        }
                    }
                });

                let found = self.characters_dir();
                ui.horizontal(|ui| {
                    if ui
                        .add_enabled(found.is_some(), egui::Button::new("👤 Add character names"))
                        .on_hover_text(match &found {
                            Some(dir) => format!("Read the sheets in {}", dir.display()),
                            None => "No character folder found near this workspace".to_string(),
                        })
                        .clicked()
                    {
                        harvest = true;
                    }
                });

                ui.separator();
                ui.label(
                    egui::RichText::new(format!("{} word(s)", self.wordlist.len())).strong(),
                );
                egui::ScrollArea::vertical()
                    .auto_shrink([false, true])
                    .max_height(260.0)
                    .show(ui, |ui| {
                        if self.wordlist.is_empty() {
                            ui.label(
                                egui::RichText::new(
                                    "Nothing yet — right-click a underlined word in the \
                                     editor to add it.",
                                )
                                .weak(),
                            );
                        }
                        for word in self.wordlist.words() {
                            ui.horizontal(|ui| {
                                if ui
                                    .small_button("✖")
                                    .on_hover_text("Flag this word again")
                                    .clicked()
                                {
                                    remove = Some(word.clone());
                                }
                                ui.label(word);
                            });
                        }
                    });

                ui.separator();
                if ui.button("Close").clicked() {
                    close = true;
                }
            });

        if let Some(word) = remove {
            self.remove_from_dictionary(&word);
        }
        if harvest {
            self.spell_status = match self.harvest_character_names() {
                Ok(0) => "No new names in the character sheets".to_string(),
                Ok(n) => format!("Added {n} name(s) from the character sheets"),
                Err(e) => format!("✖ {e}"),
            };
        }
        self.show_wordlist = open && !close;
    }
}

/// Every `*.md` file at or below `dir`, one level of nesting at a time. Project
/// folders group their files into subfolders — character sheets into
/// `main_characters`, the outline into `scene_breakdown` — so a flat read of the
/// top level would miss all of them.
pub(super) fn markdown_files_under(dir: &Path) -> Vec<PathBuf> {
    let mut out = Vec::new();
    let mut stack = vec![dir.to_path_buf()];
    // A guard against a symlink pointing back up the tree.
    let mut budget = 512usize;
    while let Some(current) = stack.pop() {
        let Ok(read) = std::fs::read_dir(&current) else {
            continue;
        };
        for entry in read.flatten() {
            if budget == 0 {
                return out;
            }
            budget -= 1;
            let path = entry.path();
            if path.is_dir() {
                stack.push(path);
            } else if path
                .extension()
                .is_some_and(|e| e.eq_ignore_ascii_case("md"))
            {
                out.push(path);
            }
        }
    }
    out.sort();
    out
}