gridcraft/crates/engine/src/cmd/data/tools.rs

use super::*;

// ---------------------------------------------------------------- tools

pub(super) fn remove_duplicates(s: &mut Session, p: &Json) -> Result<Json> {
    let (sheet, r) = data_target(s, p, "data.removeDuplicates")?;
    let d = s.doc()?;
    let sh = d.wb.sheet(sheet).ok_or(EngineError::NoDocument)?;
    // Rows and columns past the data are blank: only the part with data is compared (whole
    // columns compared a million blank rows and reported them as removed duplicates).
    let r = sh.used_range().and_then(|u| r.intersection(&u)).unwrap_or(RangeRef::cell(r.start));
    let header = bool_param(p, "header").unwrap_or_else(|| guess_header(&d.wb, sh, r));
    let cols: Vec<u32> = p
        .get("columns")
        .and_then(Json::as_array)
        .map(|a| a.iter().filter_map(|c| col_param(Some(c), r.start.col)).collect())
        .unwrap_or_else(|| (r.start.col..=r.end.col).collect());
    // With no column to compare, every row key is empty: the first row would survive and every
    // other row would be deleted as a duplicate. A column outside the range compares data the
    // user didn't select. Excel refuses both.
    if cols.is_empty() || cols.iter().any(|c| !(r.start.col..=r.end.col).contains(c)) {
        return Err(bad("data.removeDuplicates", "`columns` must name at least one column of the range"));
    }
    let start = r.start.row + header as u32;
    let mut removed = 0;
    edit(s, |cx| {
        let Some(sh) = cx.wb.sheet(sheet) else { return Ok(()) };
        let mut seen = std::collections::HashSet::new();
        let mut keep: Vec<u32> = Vec::new();
        // Cells are compared by the text they show, as in Excel: the same date in two formats
        // isn't a duplicate, while 1.01 and 1.02 shown as 1.0 are.
        let shown = |c: CellRef| crate::display::format(&sh.value(c), cx.wb.styles.get(sh.style_id(c)).num_fmt.as_str(), &cx.wb).text;
        for row in start..=r.end.row {
            let key: Vec<String> = cols.iter().map(|c| shown(CellRef::new(row, *c)).to_lowercase()).collect();
            if seen.insert(key) {
                keep.push(row);
            } else {
                removed += 1;
            }
        }
        let pictures: Vec<_> = keep
            .iter()
            .enumerate()
            .flat_map(|(i, row)| {
                (r.start.col..=r.end.col)
                    .filter_map(move |col| sh.cell_pictures.get(&CellRef::new(*row, col)).map(|p| (CellRef::new(start + i as u32, col), p.clone())))
            })
            .collect();
        // Rows a filter keeps are compacted to `start + i`, so the notes and hyperlinks that
        // describe them move with them; the ones on removed rows are dropped with the row.
        let notes: Vec<_> = keep
            .iter()
            .enumerate()
            .flat_map(|(i, row)| {
                (r.start.col..=r.end.col)
                    .filter_map(move |col| sh.comments.get(&CellRef::new(*row, col)).map(|cm| (CellRef::new(start + i as u32, col), cm.clone())))
            })
            .collect();
        let links: Vec<_> = keep
            .iter()
            .enumerate()
            .flat_map(|(i, row)| {
                (r.start.col..=r.end.col)
                    .filter_map(move |col| sh.hyperlinks.get(&CellRef::new(*row, col)).map(|h| (CellRef::new(start + i as u32, col), h.clone())))
            })
            .collect();
        let rows: Vec<Vec<Option<Cell>>> =
            keep.iter().map(|row| (r.start.col..=r.end.col).map(|c| sh.cell(CellRef::new(*row, c)).cloned()).collect()).collect();
        let shm = cx.sheet_mut(sheet)?;
        for row in start..=r.end.row {
            for c in r.start.col..=r.end.col {
                shm.remove_cell(CellRef::new(row, c));
            }
        }
        for row in start..=r.end.row {
            for c in r.start.col..=r.end.col {
                let at = CellRef::new(row, c);
                shm.comments.remove(&at);
                shm.hyperlinks.remove(&at);
            }
        }
        for (i, cells) in rows.into_iter().enumerate() {
            for (j, cell) in cells.into_iter().enumerate() {
                if let Some(cell) = cell {
                    shm.set_cell(CellRef::new(start + i as u32, r.start.col + j as u32), cell);
                }
            }
        }
        shm.cell_pictures.extend(pictures);
        for (at, cm) in notes {
            shm.comments.insert(at, cm);
        }
        for (at, h) in links {
            shm.hyperlinks.insert(at, h);
        }
        for c in RangeRef::new(CellRef::new(start, r.start.col), r.end).iter() {
            cx.changed.push((sheet, c));
        }
        Ok(())
    })?;
    let remaining = (r.end.row + 1 - start) as usize - removed;
    Ok(json!({"removed": removed, "remaining": remaining}))
}

pub(super) fn text_to_columns(s: &mut Session, p: &Json) -> Result<Json> {
    let r = target_range(s, p)?;
    let sheet = target_sheet(s, p)?;
    let mut delims: Vec<char> = p
        .get("delimiters")
        .and_then(Json::as_array)
        .map(|a| a.iter().filter_map(|d| d.as_str().and_then(|x| x.chars().next())).collect())
        .unwrap_or_else(|| vec!['\t']);
    if let Some(o) = str_param(p, "other").and_then(|o| o.chars().next()) {
        delims.push(o);
    }
    let fixed: Option<Vec<usize>> =
        p.get("fixedWidths").and_then(Json::as_array).map(|a| a.iter().filter_map(|x| x.as_u64().map(|v| v as usize)).collect());
    let consecutive = bool_param(p, "treatConsecutive").unwrap_or(false);
    let quote = str_param(p, "textQualifier").and_then(|q| q.chars().next()).unwrap_or('"');
    let dest = cell_param_on(s, p, "destination", sheet)?.unwrap_or(r.start);
    edit(s, |cx| {
        let Some(sh) = cx.wb.sheet(sheet) else { return Ok(()) };
        let mut out: Vec<(CellRef, String)> = Vec::new();
        for (i, row) in (r.start.row..=r.end.row).enumerate() {
            let text = sh.value(CellRef::new(row, r.start.col)).display();
            let parts: Vec<String> = match &fixed {
                Some(w) => {
                    let chars: Vec<char> = text.chars().collect();
                    let mut cuts = vec![0];
                    let mut breaks: Vec<usize> = w.iter().copied().filter(|x| *x > 0 && *x < chars.len()).collect();
                    breaks.sort_unstable();
                    breaks.dedup();
                    cuts.extend(breaks);
                    cuts.push(chars.len());
                    cuts.windows(2)
                        .map(|p| chars.get(p[0]..p[1]).map(|s| s.iter().collect::<String>().trim().to_string()).unwrap_or_default())
                        .collect()
                }
                None => split_delimited(&text, &delims, consecutive, quote),
            };
            for (j, part) in parts.into_iter().enumerate() {
                out.push((CellRef::new(dest.row + i as u32, dest.col + j as u32), part));
            }
        }
        for (c, t) in out {
            let cell = crate::cmd::edit::input_to_cell(&t, sheet, c, &mut cx.wb).unwrap_or(None);
            let shm = cx.sheet_mut(sheet)?;
            match cell {
                Some(x) => shm.set_cell(c, x),
                None => {
                    shm.remove_cell(c);
                }
            }
            cx.changed.push((sheet, c));
        }
        Ok(())
    })?;
    ok()
}

pub(super) fn split_delimited(text: &str, delims: &[char], consecutive: bool, quote: char) -> Vec<String> {
    let mut out = Vec::new();
    let mut cur = String::new();
    let mut in_q = false;
    let mut last_delim = false;
    let mut chars = text.chars().peekable();
    while let Some(c) = chars.next() {
        if c == quote {
            if in_q && chars.peek() == Some(&quote) {
                cur.push(quote);
                chars.next();
            } else {
                in_q = !in_q;
            }
            continue;
        }
        if !in_q && delims.contains(&c) {
            if consecutive && last_delim {
                continue;
            }
            out.push(std::mem::take(&mut cur));
            last_delim = true;
            continue;
        }
        last_delim = false;
        cur.push(c);
    }
    out.push(cur);
    out
}