Skip to content

DesignCraft: An open-source page and layout design editor written by scratch in pure Rust

I: place Excel workbooks as tables

Brandon Thomasdd68539cb069
diff --git a/ROADMAP.md b/ROADMAP.md
index 150140083..ff642f582 100644
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -51,6 +51,7 @@ DesignCraft aims at full Adobe InDesign parity — and to be better: faster, ope
- File ▸ Print Booklet (`file.printBooklet`): saddle-stitch or 2-up consecutive printer spreads as PDF, padded with blanks, with a gap between pages.
- Edit ▸ Transparency Blend Space (`edit.transparencyBlendSpace`; RGB for web/mobile documents; IDML TransparencyPreference) — stored; compositing is still RGB on screen and in PDF.
- High Contrast interface theme (fifth Interface Color Theme: black chrome, white text, yellow selection).
+- Place Excel workbooks (.xlsx): the first worksheet's used range becomes a table (shared/inline strings, numbers, booleans).
- Drag and drop text editing: drag selected text to move it (Alt copies) with its formatting (`text.release`).
- Image Import Options: place any page of a multi-page PDF (`file.place {pdfPage}`; the app asks which page), shown on screen and embedded as that page in PDF export.
- Define Lists: named numbered lists that continue across stories in page order (`list.define`, paragraph `listName` / `startAt`), round-tripped through IDML; `null` in `type.para` / `type.char` now removes an override.
diff --git a/apps/designcraft-web/src/web.rs b/apps/designcraft-web/src/web.rs
index 90b54bcaa..fc7f2d4ed 100644
--- a/apps/designcraft-web/src/web.rs
+++ b/apps/designcraft-web/src/web.rs
@@ -5,7 +5,8 @@ use designcraft_ui_egui::{DesignApp, Inbox, Services};
use wasm_bindgen::JsCast as _;
const DOC_EXTS: &[&str] = &["designcraft", "idml"];
-const IMAGE_EXTS: &[&str] = &["png", "jpg", "jpeg", "gif", "webp", "tif", "tiff", "bmp", "psd", "svg", "pdf", "ai", "txt", "docx", "rtf", "md"];
+const IMAGE_EXTS: &[&str] =
+ &["png", "jpg", "jpeg", "gif", "webp", "tif", "tiff", "bmp", "psd", "svg", "pdf", "ai", "txt", "docx", "rtf", "md", "xlsx"];
const CANVAS_ID: &str = "designcraft_canvas";
const LOADING_ID: &str = "designcraft_loading";
diff --git a/apps/designcraft/src/main.rs b/apps/designcraft/src/main.rs
index 6c4582981..a1d753c6a 100644
--- a/apps/designcraft/src/main.rs
+++ b/apps/designcraft/src/main.rs
@@ -86,10 +86,10 @@ fn services() -> Services {
} else if purpose == "place" {
d.add_filter(
"Graphics and text",
- &["png", "jpg", "jpeg", "gif", "webp", "tif", "tiff", "bmp", "psd", "svg", "pdf", "ai", "txt", "docx", "rtf", "md"],
+ &["png", "jpg", "jpeg", "gif", "webp", "tif", "tiff", "bmp", "psd", "svg", "pdf", "ai", "txt", "docx", "rtf", "md", "xlsx"],
)
.add_filter("Graphics", &["png", "jpg", "jpeg", "gif", "webp", "tif", "tiff", "bmp", "psd", "svg", "pdf", "ai"])
- .add_filter("Text (Word, RTF, plain)", &["docx", "rtf", "txt", "md"])
+ .add_filter("Text (Word, RTF, plain, Excel)", &["docx", "rtf", "txt", "md", "xlsx"])
} else {
d.add_filter("DesignCraft or IDML", &["designcraft", "idml"])
.add_filter("DesignCraft", &["designcraft"])
diff --git a/crates/engine/src/cmd/file.rs b/crates/engine/src/cmd/file.rs
index 616f0ae32..14e798cff 100644
--- a/crates/engine/src/cmd/file.rs
+++ b/crates/engine/src/cmd/file.rs
@@ -77,7 +77,7 @@ pub fn specs() -> Vec<CommandSpec> {
"Place…",
["File"],
Some("Cmd+D"),
- "{path?|base64?, name?, frame?: id (place into), spread?, x?, y?, width?, pdfPage?: n (1-based, Image Import Options)} — places an image (into the selected empty frame if any); text files (.txt, .docx, .rtf, .md) go into the insertion point, the selected frame or a new frame on `page`/`rect` — {autoflow?: adds pages with threaded frames until the text fits, removeStyles?}",
+ "{path?|base64?, name?, frame?: id (place into), spread?, x?, y?, width?, pdfPage?: n (1-based, Image Import Options)} — places an image (into the selected empty frame if any); text files (.txt, .docx, .rtf, .md) and Excel workbooks (.xlsx, as a table) go into the insertion point, the selected frame or a new frame on `page`/`rect` — {autoflow?: adds pages with threaded frames until the text fits, removeStyles?}",
has_doc,
file_place
),
diff --git a/crates/textimport/src/docx.rs b/crates/textimport/src/docx.rs
index a7f2139b2..048529574 100644
--- a/crates/textimport/src/docx.rs
+++ b/crates/textimport/src/docx.rs
@@ -11,8 +11,8 @@ use crate::{ImportError, Imported, ImportedStyle};
/// A minimal element tree (local names, attributes by local name).
#[derive(Debug, Default, Clone)]
-struct El {
- name: String,
+pub(crate) struct El {
+ pub(crate) name: String,
attrs: Vec<(String, String)>,
kids: Vec<Node>,
}
@@ -24,16 +24,16 @@ enum Node {
}
impl El {
- fn attr(&self, k: &str) -> Option<&str> {
+ pub(crate) fn attr(&self, k: &str) -> Option<&str> {
self.attrs.iter().find(|(n, _)| n == k).map(|(_, v)| v.as_str())
}
- fn els(&self) -> impl Iterator<Item = &El> {
+ pub(crate) fn els(&self) -> impl Iterator<Item = &El> {
self.kids.iter().filter_map(|n| if let Node::El(e) = n { Some(e) } else { None })
}
- fn child(&self, name: &str) -> Option<&El> {
+ pub(crate) fn child(&self, name: &str) -> Option<&El> {
self.els().find(|e| e.name == name)
}
- fn text(&self) -> String {
+ pub(crate) fn text(&self) -> String {
self.kids
.iter()
.map(|n| match n {
@@ -56,7 +56,7 @@ fn local(n: &[u8]) -> String {
s.rsplit(':').next().unwrap_or(&s).to_string()
}
-fn parse(xml: &str) -> Result<El, ImportError> {
+pub(crate) fn parse(xml: &str) -> Result<El, ImportError> {
let mut r = quick_xml::Reader::from_str(xml);
let mut stack: Vec<El> = vec![El::default()];
loop {
@@ -125,7 +125,7 @@ fn parse(xml: &str) -> Result<El, ImportError> {
Ok(root.kids.drain(..).find_map(|n| if let Node::El(e) = n { Some(e) } else { None }).unwrap_or_default())
}
-fn part(zip: &mut zip::ZipArchive<std::io::Cursor<&[u8]>>, name: &str) -> Option<String> {
+pub(crate) fn part(zip: &mut zip::ZipArchive<std::io::Cursor<&[u8]>>, name: &str) -> Option<String> {
let mut f = zip.by_name(name).ok()?;
let mut s = String::new();
f.read_to_string(&mut s).ok()?;
diff --git a/crates/textimport/src/lib.rs b/crates/textimport/src/lib.rs
index b45653ae1..55527decf 100644
--- a/crates/textimport/src/lib.rs
+++ b/crates/textimport/src/lib.rs
@@ -10,6 +10,7 @@
mod docx;
pub mod export;
mod rtf;
+mod xlsx;
use designcraft_doc::{CharAttrs, ParaAttrs, Story};
@@ -50,12 +51,15 @@ impl std::fmt::Display for ImportError {
/// Text files this crate reads, by extension.
pub fn is_text_file(name: &str) -> bool {
let l = name.to_ascii_lowercase();
- l.ends_with(".txt") || l.ends_with(".text") || l.ends_with(".md") || l.ends_with(".docx") || l.ends_with(".rtf")
+ l.ends_with(".txt") || l.ends_with(".text") || l.ends_with(".md") || l.ends_with(".docx") || l.ends_with(".rtf") || l.ends_with(".xlsx")
}
/// Import `bytes` (format from the file name, else sniffed).
pub fn import(name: &str, bytes: &[u8]) -> Result<Imported, ImportError> {
let l = name.to_ascii_lowercase();
+ if l.ends_with(".xlsx") {
+ return xlsx::import(bytes);
+ }
if l.ends_with(".docx") || bytes.starts_with(b"PK\x03\x04") {
return docx::import(bytes);
}
diff --git a/crates/textimport/src/xlsx.rs b/crates/textimport/src/xlsx.rs
new file mode 100644
index 000000000..f6d0c80a5
--- /dev/null
+++ b/crates/textimport/src/xlsx.rs
@@ -0,0 +1,138 @@
+//! Excel workbooks (`.xlsx`) → a story holding one table: the first worksheet's used range, cell
+//! values as shown text (shared and inline strings, numbers, booleans).
+
+use designcraft_doc::{CharFormat, ParaFormat, Story, StoryId, Table};
+
+use crate::docx::{El, parse, part};
+use crate::{ImportError, Imported};
+
+/// "B12" → (row 11, column 1).
+fn cell_ref(r: &str) -> Option<(usize, usize)> {
+ let letters: String = r.chars().take_while(|c| c.is_ascii_alphabetic()).collect();
+ let row: usize = r[letters.len()..].parse().ok()?;
+ let col = letters.chars().try_fold(0usize, |acc, c| Some(acc * 26 + (c.to_ascii_uppercase() as u8).checked_sub(b'A')? as usize + 1))?;
+ Some((row.checked_sub(1)?, col.checked_sub(1)?))
+}
+
+/// The worksheet part of the first sheet (workbook order), via the workbook relationships.
+fn first_sheet(zip: &mut zip::ZipArchive<std::io::Cursor<&[u8]>>) -> Option<String> {
+ let wb = parse(&part(zip, "xl/workbook.xml")?).ok()?;
+ let rid = wb.child("sheets")?.els().find(|e| e.name == "sheet")?.attr("id")?.to_string();
+ let rels = parse(&part(zip, "xl/_rels/workbook.xml.rels")?).ok()?;
+ let target = rels.els().find(|r| r.attr("Id") == Some(rid.as_str()))?.attr("Target")?.trim_start_matches('/').to_string();
+ Some(if target.starts_with("xl/") { target } else { format!("xl/{target}") })
+}
+
+fn value(c: &El, shared: &[String]) -> String {
+ let v = || c.child("v").map(El::text).unwrap_or_default();
+ match c.attr("t") {
+ Some("s") => v().trim().parse::<usize>().ok().and_then(|i| shared.get(i).cloned()).unwrap_or_default(),
+ Some("inlineStr") => c.child("is").map(El::text).unwrap_or_default(),
+ Some("b") => {
+ if v().trim() == "1" {
+ "TRUE".into()
+ } else {
+ "FALSE".into()
+ }
+ }
+ _ => {
+ let raw = v();
+ // Whole numbers without the trailing ".0" Excel never shows.
+ match raw.trim().parse::<f64>() {
+ Ok(f) if f.fract() == 0.0 && f.abs() < 1e15 => format!("{}", f as i64),
+ Ok(f) => format!("{}", (f * 1e10).round() / 1e10),
+ Err(_) => raw,
+ }
+ }
+ }
+}
+
+pub fn import(bytes: &[u8]) -> Result<Imported, ImportError> {
+ let mut zip = zip::ZipArchive::new(std::io::Cursor::new(bytes)).map_err(|e| ImportError::Corrupt(e.to_string()))?;
+ let sheet_part = first_sheet(&mut zip).unwrap_or_else(|| "xl/worksheets/sheet1.xml".into());
+ let sheet = parse(&part(&mut zip, &sheet_part).ok_or_else(|| ImportError::Corrupt(format!("no {sheet_part} (not an Excel workbook)")))?)?;
+ let shared: Vec<String> = part(&mut zip, "xl/sharedStrings.xml")
+ .map(|x| parse(&x))
+ .transpose()?
+ .map(|sst| sst.els().filter(|e| e.name == "si").map(El::text).collect())
+ .unwrap_or_default();
+ let mut cells: Vec<((usize, usize), String)> = Vec::new();
+ if let Some(data) = sheet.child("sheetData") {
+ for (ri, row) in data.els().filter(|e| e.name == "row").enumerate() {
+ for (ci, c) in row.els().filter(|e| e.name == "c").enumerate() {
+ let at = c.attr("r").and_then(cell_ref).unwrap_or((ri, ci));
+ let v = value(c, &shared);
+ if !v.is_empty() {
+ cells.push((at, v));
+ }
+ }
+ }
+ }
+ let mut warnings = Vec::new();
+ if cells.is_empty() {
+ warnings.push("the worksheet is empty".into());
+ }
+ // The used range, from the first used row/column.
+ let (r0, c0) = cells.iter().fold((usize::MAX, usize::MAX), |(r, c), ((a, b), _)| (r.min(*a), c.min(*b)));
+ let (r1, c1) = cells.iter().fold((0, 0), |(r, c), ((a, b), _)| (r.max(*a), c.max(*b)));
+ let mut rows: Vec<Vec<String>> = if cells.is_empty() { vec![vec![String::new()]] } else { vec![vec![String::new(); c1 - c0 + 1]; r1 - r0 + 1] };
+ for ((r, c), v) in cells {
+ rows[r - r0][c - c0] = v;
+ }
+ const MAX_CELLS: usize = 100_000;
+ if rows.len() * rows[0].len() > MAX_CELLS {
+ let keep = (MAX_CELLS / rows[0].len()).max(1);
+ warnings.push(format!("only the first {keep} rows were placed"));
+ rows.truncate(keep);
+ }
+ let mut story = Story::new(StoryId(0));
+ let width = 72.0 * rows[0].len() as f64;
+ let t = Table::from_strings(1, &rows, width, &ParaFormat::default(), &CharFormat::default());
+ story.insert_table(0, t);
+ Ok(Imported { story, para_styles: vec![], char_styles: vec![], warnings })
+}
+
+#[cfg(test)]
+mod tests {
+ use std::io::Write;
+
+ use super::*;
+
+ fn workbook() -> Vec<u8> {
+ let mut buf = std::io::Cursor::new(Vec::new());
+ {
+ let mut z = zip::ZipWriter::new(&mut buf);
+ let o = zip::write::SimpleFileOptions::default();
+ for (name, body) in [
+ (
+ "xl/workbook.xml",
+ r#"<workbook xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"><sheets><sheet name="Prices" sheetId="1" r:id="rId1"/></sheets></workbook>"#,
+ ),
+ (
+ "xl/_rels/workbook.xml.rels",
+ r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="x" Target="worksheets/sheet1.xml"/></Relationships>"#,
+ ),
+ ("xl/sharedStrings.xml", r#"<sst><si><t>Item</t></si><si><t>Price</t></si><si><r><t>Te</t></r><r><t>a</t></r></si></sst>"#),
+ (
+ "xl/worksheets/sheet1.xml",
+ r#"<worksheet><sheetData><row r="2"><c r="B2" t="s"><v>0</v></c><c r="C2" t="s"><v>1</v></c></row><row r="3"><c r="B3" t="s"><v>2</v></c><c r="C3"><v>3.5</v></c></row><row r="4"><c r="B4" t="inlineStr"><is><t>Cake</t></is></c><c r="C4"><v>12.0</v></c></row></sheetData></worksheet>"#,
+ ),
+ ] {
+ z.start_file(name, o).unwrap();
+ z.write_all(body.as_bytes()).unwrap();
+ }
+ z.finish().unwrap();
+ }
+ buf.into_inner()
+ }
+
+ #[test]
+ fn first_sheet_used_range_becomes_a_table() {
+ let imp = import(&workbook()).unwrap();
+ let t = imp.story.tables.values().next().expect("a table");
+ assert_eq!((t.nrows(), t.ncols()), (3, 2), "the used range B2:C4");
+ let cell = |r, c| t.cell(r, c).unwrap().text.text.clone();
+ assert_eq!([cell(0, 0), cell(0, 1), cell(1, 0), cell(1, 1), cell(2, 0), cell(2, 1)], ["Item", "Price", "Tea", "3.5", "Cake", "12"]);
+ assert_eq!(cell_ref("AA10"), Some((9, 26)));
+ }
+}
diff --git a/docs/parity.md b/docs/parity.md
index 1b60b89b3..cb57ad02a 100644
--- a/docs/parity.md
+++ b/docs/parity.md
@@ -11,7 +11,7 @@ Each row of the InDesign feature catalogue is scored **D** (done), **P** (partia
|---|---|---|---|---|---|
| P0 | 102 | 99 | 3 | 0 | 99% |
| P1 | 97 | 75 | 21 | 1 | 88% |
-| P2 | 76 | 20 | 13 | 43 | 35% |
+| P2 | 76 | 21 | 13 | 42 | 36% |
| Area | Parity |
|---|---|
@@ -26,7 +26,7 @@ Each row of the InDesign feature catalogue is scored **D** (done), **P** (partia
| Type & text frames | 92% |
| Typography | 88% |
| Styles | 92% |
-| Tables | 88% |
+| Tables | 92% |
| Long documents | 88% |
| Interactivity & digital | 45% |
| Output & production | 75% |
@@ -258,7 +258,7 @@ Open P0 items: Preferences, Vector/page formats (PDF/AI/SVG/EPS place), Export t
| Tables | Overset cells | P1 | D |
| Tables | Tables spanning frames | P1 | D |
| Tables | Sort table rows | P2 | D |
-| Tables | Excel import | P2 | M |
+| Tables | Excel import | P2 | D |
| Tables | Drag to move rows/columns | P2 | M |
| Long documents | Table of contents | P1 | D |
| Long documents | Index | P2 | D |