Merge pull request #8078 from dotCooCoo/feat/text-import-character-sets

Text Import Options: Character Set offers the other documented encodings
This commit is contained in:
BFlat
2026-11-18 10:31:10 +07:00
committed by GitHub
40 changed files with 427 additions and 34 deletions
Generated
+1
View File
@@ -6775,6 +6775,7 @@ dependencies = [
"craft-stream-codecs",
"craft-xml",
"crc32fast",
"encoding_rs",
"flate2",
"hayro-ccitt",
"heic-rs",
+3
View File
@@ -59,6 +59,9 @@ chrono = { workspace = true }
craft-xml = { workspace = true }
# The compound file that holds a Word 97-2003 document placed as type (place/doc.rs).
cfb = "0.15"
# The Text Import Options character sets other than Unicode and ANSI (place/text.rs). Already in
# Cargo.lock (vectorcraft-eps), so this adds no new crate.
encoding_rs = { workspace = true }
kurbo = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
File diff suppressed because one or more lines are too long
+140 -23
View File
@@ -3,8 +3,8 @@
use serde_json::Value;
use super::super::utf16_order_without_mark;
use super::{Point, Rect, Result, bad, bool_or, fileio, shapes, str_param};
use super::super::{text_param, utf16_order_without_mark};
use super::{Point, Rect, Result, bad, fileio, shapes, switch_or};
/// Text files as `file.place` reports them (not a format `document.open` reads).
pub(super) const FORMAT: fileio::Format = fileio::Format {
@@ -22,13 +22,68 @@ pub(super) const FORMAT: fileio::Format = fileio::Format {
/// document may give.
pub(super) const MAX_TEXT: usize = 4 << 20;
/// A character set of Text Import Options (`text.characterSet`).
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
enum CharacterSet {
/// UTF-8, or UTF-16 with or without a byte-order mark ([`decode`]).
#[default]
Unicode,
/// The platform's 8-bit character set: Windows-1252, or Mac Roman on a Mac.
Ansi,
ShiftJis,
Gb2312,
ChineseBig5,
Cyrillic,
Gb18030,
Greek,
Turkish,
Baltic,
CentralEuropean,
}
/// Each character set by its `text.characterSet` value.
const CHARACTER_SETS: [(&str, CharacterSet); 11] = [
("unicode", CharacterSet::Unicode),
("ansi", CharacterSet::Ansi),
("shiftJis", CharacterSet::ShiftJis),
("gb2312", CharacterSet::Gb2312),
("chineseBig5", CharacterSet::ChineseBig5),
("cyrillic", CharacterSet::Cyrillic),
("gb18030", CharacterSet::Gb18030),
("greek", CharacterSet::Greek),
("turkish", CharacterSet::Turkish),
("baltic", CharacterSet::Baltic),
("centralEuropean", CharacterSet::CentralEuropean),
];
impl CharacterSet {
/// The Encoding Standard decoder of a set other than Unicode and ANSI, for a file from a Mac
/// when `mac`: GB2312 reads as GBK, Cyrillic as windows-1251 (x-mac-cyrillic on a Mac), and
/// Greek, Turkish, Baltic and Central European as windows-1253, 1254, 1257 and 1250 on both
/// platforms.
fn encoding(self, mac: bool) -> Option<&'static encoding_rs::Encoding> {
Some(match self {
Self::Unicode | Self::Ansi => return None,
Self::ShiftJis => encoding_rs::SHIFT_JIS,
Self::Gb2312 => encoding_rs::GBK,
Self::ChineseBig5 => encoding_rs::BIG5,
Self::Cyrillic if mac => encoding_rs::X_MAC_CYRILLIC,
Self::Cyrillic => encoding_rs::WINDOWS_1251,
Self::Gb18030 => encoding_rs::GB18030,
Self::Greek => encoding_rs::WINDOWS_1253,
Self::Turkish => encoding_rs::WINDOWS_1254,
Self::Baltic => encoding_rs::WINDOWS_1257,
Self::CentralEuropean => encoding_rs::WINDOWS_1250,
})
}
}
/// Text Import Options (`file.place`'s `text` param).
#[derive(Clone, Copy, Debug, Default, PartialEq)]
pub(super) struct TextOptions {
/// Decode as the platform's 8-bit character set (Windows-1252 or Mac Roman) instead of
/// Unicode.
ansi: bool,
/// The file comes from a Mac (its 8-bit character set is Mac Roman).
/// The character set the file's bytes are decoded as.
character_set: CharacterSet,
/// The file comes from a Mac (its ANSI set is Mac Roman, its Cyrillic set x-mac-cyrillic).
mac: bool,
/// Join the lines of each block of text (blank lines end paragraphs).
remove_line_returns: bool,
@@ -45,11 +100,13 @@ impl TextOptions {
if !t.is_object() {
return Err(bad(cmd, "text must be {characterSet?, platform?, removeLineReturns?, removeParagraphReturns?, replaceSpaces?}"));
}
let choice = |key: &str, values: [&str; 2]| match str_param(t, key) {
None => Ok(false),
Some(v) if v == values[0] => Ok(false),
Some(v) if v == values[1] => Ok(true),
Some(v) => Err(bad(cmd, format!("text.{key} `{v}`: use \"{}\" or \"{}\"", values[0], values[1]))),
// The index of `text[key]` in `values`; 0 when it is omitted or null.
let choice = |key: &str, values: &[&str]| -> Result<usize> {
let Some(v) = text_param(t, key, cmd)? else { return Ok(0) };
values.iter().position(|x| *x == v).ok_or_else(|| {
let (last, rest) = values.split_last().map_or(("", &[][..]), |(last, rest)| (*last, rest));
bad(cmd, format!("text.{key} `{v}`: use \"{}\" or \"{}\"", rest.join("\", \""), last))
})
};
let spaces_to_tab = match t.get("replaceSpaces") {
None | Some(Value::Null) => None,
@@ -58,11 +115,12 @@ impl TextOptions {
as usize,
),
};
let set = choice("characterSet", &CHARACTER_SETS.map(|(name, _)| name))?;
Ok(Self {
ansi: choice("characterSet", ["unicode", "ansi"])?,
mac: choice("platform", ["windows", "mac"])?,
remove_line_returns: bool_or(t, "removeLineReturns", false),
remove_paragraph_returns: bool_or(t, "removeParagraphReturns", false),
character_set: CHARACTER_SETS.get(set).map_or(CharacterSet::Unicode, |(_, s)| *s),
mac: choice("platform", &["windows", "mac"])? == 1,
remove_line_returns: switch_or(t, "removeLineReturns", false, cmd)?,
remove_paragraph_returns: switch_or(t, "removeParagraphReturns", false, cmd)?,
spaces_to_tab,
})
}
@@ -80,10 +138,15 @@ pub(super) fn import(bytes: &[u8], o: TextOptions, cmd: &str) -> Result<String>
/// `bytes` as text: Unicode (UTF-8, or UTF-16 with a byte-order mark, or without one when the
/// file has an even length, reads as valid UTF-16 with no NUL character in the byte order
/// [`utf16_order_without_mark`] gives; bytes that aren't UTF-8 are read as the platform's 8-bit
/// set), or the platform's 8-bit character set.
/// set), the platform's 8-bit character set, or another set's decoder
/// ([`CharacterSet::encoding`]), which reads a byte-order mark as ordinary bytes and a malformed
/// sequence as U+FFFD.
fn decode(bytes: &[u8], o: TextOptions) -> String {
if let Some(encoding) = o.character_set.encoding(o.mac) {
return encoding.decode_without_bom_handling(bytes).0.into_owned();
}
let eight_bit = |b: &[u8]| -> String { b.iter().map(|&c| if o.mac { mac_roman(c) } else { windows_1252(c) }).collect() };
if o.ansi {
if o.character_set == CharacterSet::Ansi {
return eight_bit(bytes);
}
let utf16 = |rest: &[u8], le: bool| {
@@ -278,22 +341,76 @@ mod tests {
assert_eq!(decode(&[0xFF, 0xFE, b'h', 0, 0xE9, 0], unicode), "hé", "UTF-16 LE");
assert_eq!(decode(&[0xFE, 0xFF, 0, b'h', 0x20, 0xAC], unicode), "h€", "UTF-16 BE");
assert_eq!(decode(&[b'c', b'a', b'f', 0xE9, 0x80], unicode), "café€", "not UTF-8: Windows-1252");
let ansi = TextOptions { ansi: true, ..TextOptions::default() };
let ansi = TextOptions { character_set: CharacterSet::Ansi, ..TextOptions::default() };
assert_eq!(decode(&[0x93, b'q', 0x94, 0xE9], ansi), "“q”é");
let mac = TextOptions { ansi: true, mac: true, ..TextOptions::default() };
let mac = TextOptions { character_set: CharacterSet::Ansi, mac: true, ..TextOptions::default() };
assert_eq!(decode(&[0xD2, b'q', 0xD3, 0x8E, 0xA5, 0xDB], mac), "“q”é•€");
}
/// The other character sets decode by their Encoding Standard decoders: the platform matters
/// for Cyrillic alone, a byte-order mark is read as ordinary bytes, and a malformed sequence
/// reads as U+FFFD.
#[test]
fn decodes_the_other_character_sets() {
let cases: [(CharacterSet, &[u8], &str); 9] = [
(CharacterSet::ShiftJis, &[0x93, 0xFA, 0x96, 0x7B], "日本"),
(CharacterSet::Gb2312, &[0xD6, 0xD0, 0xCE, 0xC4], "中文"),
(CharacterSet::ChineseBig5, &[0xA4, 0xA4, 0xA4, 0xE5], "中文"),
(CharacterSet::Cyrillic, &[0xCF, 0xF0, 0xE8, 0xE2, 0xE5, 0xF2], "Привет"),
(CharacterSet::Gb18030, &[0x95, 0x32, 0x82, 0x36], "\u{20000}"),
(CharacterSet::Greek, &[0xC5, 0xEB, 0xEB, 0xDC, 0xE4, 0xE1], "Ελλάδα"),
(CharacterSet::Turkish, &[0xDD, 0x73, 0x74], "İst"),
(CharacterSet::Baltic, &[0x52, 0xEE, 0x67, 0x61], "Rīga"),
(CharacterSet::CentralEuropean, &[0xA3, 0xF3, 0x64, 0x9F], "Łódź"),
];
for (set, bytes, text) in cases {
let windows = TextOptions { character_set: set, ..TextOptions::default() };
assert_eq!(decode(bytes, windows), text, "{set:?}");
if set != CharacterSet::Cyrillic {
assert_eq!(decode(bytes, TextOptions { mac: true, ..windows }), text, "{set:?} from a Mac");
}
}
let mac_cyrillic = TextOptions { character_set: CharacterSet::Cyrillic, mac: true, ..TextOptions::default() };
assert_eq!(decode(&[0x8F, 0xF0, 0xE8, 0xE2, 0xE5, 0xF2], mac_cyrillic), "Привет");
let shift_jis = TextOptions { character_set: CharacterSet::ShiftJis, ..TextOptions::default() };
assert_eq!(decode(&[0x82, 0x22], shift_jis), "\u{FFFD}\"", "a lead byte before ASCII");
assert_eq!(decode(&[b'a', 0x82], shift_jis), "a\u{FFFD}", "a lead byte at the end");
let central = TextOptions { character_set: CharacterSet::CentralEuropean, ..TextOptions::default() };
assert_eq!(decode(&[0xEF, 0xBB, 0xBF, b'A'], central), "A", "a UTF-8 byte-order mark is read as windows-1250");
assert_eq!(decode(&[0xFF, 0xFE, b'A', 0], shift_jis), "\u{FFFD}\u{FFFD}A\0", "a UTF-16 byte-order mark is read as Shift JIS");
}
#[test]
fn options_parse_and_reject_bad_values() {
let p = serde_json::json!({"text": {"characterSet": "ansi", "platform": "mac", "removeLineReturns": true, "replaceSpaces": 4}});
let o = TextOptions::parse(&p, "file.place").unwrap();
assert_eq!(o, TextOptions { ansi: true, mac: true, remove_line_returns: true, remove_paragraph_returns: false, spaces_to_tab: Some(4) });
assert_eq!(
o,
TextOptions {
character_set: CharacterSet::Ansi,
mac: true,
remove_line_returns: true,
remove_paragraph_returns: false,
spaces_to_tab: Some(4)
}
);
for (name, set) in CHARACTER_SETS {
let o = TextOptions::parse(&serde_json::json!({"text": {"characterSet": name}}), "file.place").unwrap();
assert_eq!(o.character_set, set, "{name}");
}
assert_eq!(TextOptions::parse(&serde_json::json!({}), "file.place").unwrap(), TextOptions::default());
for bad in
[serde_json::json!({"text": 3}), serde_json::json!({"text": {"platform": "amiga"}}), serde_json::json!({"text": {"replaceSpaces": 1}})]
{
for bad in [
serde_json::json!({"text": 3}),
serde_json::json!({"text": {"platform": "amiga"}}),
serde_json::json!({"text": {"replaceSpaces": 1}}),
serde_json::json!({"text": {"characterSet": 3}}),
serde_json::json!({"text": {"platform": true}}),
serde_json::json!({"text": {"removeLineReturns": "yes"}}),
serde_json::json!({"text": {"removeParagraphReturns": 1}}),
] {
assert!(TextOptions::parse(&bad, "file.place").is_err(), "{bad}");
}
let null = serde_json::json!({"text": {"characterSet": null, "platform": null, "removeLineReturns": null}});
assert_eq!(TextOptions::parse(&null, "file.place").unwrap(), TextOptions::default(), "null leaves the default");
}
}
+30
View File
@@ -135,6 +135,36 @@ fn text_files_report_and_queue_with_their_options() {
assert!(close(frame, Rect::new(50.0, 60.0, 130.0, 100.0)), "{frame:?}");
}
/// Text Import Options' other character sets place their text as area type, and an unknown
/// character set is refused with the list of sets and places nothing.
#[test]
fn text_files_place_in_the_other_character_sets() {
let mut s = session();
let cases: [(&str, &str, &[u8], &str); 11] = [
("shiftJis", "windows", &[0x93, 0xFA, 0x96, 0x7B], "日本"),
("gb2312", "windows", &[0xD6, 0xD0, 0xCE, 0xC4], "中文"),
("chineseBig5", "mac", &[0xA4, 0xA4, 0xA4, 0xE5], "中文"),
("cyrillic", "windows", &[0xCF, 0xF0, 0xE8, 0xE2, 0xE5, 0xF2], "Привет"),
("cyrillic", "mac", &[0x8F, 0xF0, 0xE8, 0xE2, 0xE5, 0xF2], "Привет"),
("gb18030", "windows", &[0x95, 0x32, 0x82, 0x36], "\u{20000}"),
("greek", "windows", &[0xC5, 0xEB, 0xEB, 0xDC, 0xE4, 0xE1], "Ελλάδα"),
("turkish", "mac", &[0xDD, 0x73, 0x74], "İst"),
("baltic", "windows", &[0x52, 0xEE, 0x67, 0x61], "Rīga"),
("centralEuropean", "windows", &[0xA3, 0xF3, 0x64, 0x9F, b'\r', b'\n', 0xA3], "Łódź\nŁ"),
("shiftJis", "windows", &[0x82, 0x22], "\u{FFFD}\""),
];
for (set, platform, bytes, text) in cases {
let r = place_text(&mut s, bytes, json!({"text": {"characterSet": set, "platform": platform}}));
assert_eq!(placed(&s, &r).0, text, "{set} on {platform}");
}
let undo = s.doc().unwrap().history.undo.len();
let bad = json!({"name": "a.txt", "dataBase64": "YQ==", "text": {"characterSet": "latin9"}});
let err = s.execute("file.place", &bad).unwrap_err().to_string();
let list = r#""unicode", "ansi", "shiftJis", "gb2312", "chineseBig5", "cyrillic", "gb18030", "greek", "turkish", "baltic" or "centralEuropean""#;
assert!(err.contains(&format!("text.characterSet `latin9`: use {list}")), "{err}");
assert_eq!(s.doc().unwrap().history.undo.len(), undo, "nothing placed");
}
/// An RTF file with a font table, a color table, a bold run, an italic run, a superscript and a
/// centered, indented second paragraph.
const LETTER_RTF: &str = concat!(
+4 -2
View File
@@ -17,7 +17,9 @@ proptest! {
fn any_bytes_place_as_text_without_panics(
bytes in prop::collection::vec(prop_oneof![any::<u8>(), Just(b'\r'), Just(b'\n'), Just(b' ')], 0..400),
bom in prop::sample::select(vec![&b""[..], b"\xEF\xBB\xBF", b"\xFF\xFE", b"\xFE\xFF"]),
ansi in any::<bool>(),
set in prop::sample::select(vec![
"unicode", "ansi", "shiftJis", "gb2312", "chineseBig5", "cyrillic", "gb18030", "greek", "turkish", "baltic", "centralEuropean",
]),
mac in any::<bool>(),
lines in any::<bool>(),
paras in any::<bool>(),
@@ -31,7 +33,7 @@ proptest! {
let mut s = vectorcraft_engine::Session::new();
s.execute("file.new", &json!({"width": 100, "height": 100})).unwrap();
let text = json!({
"characterSet": if ansi { "ansi" } else { "unicode" },
"characterSet": set,
"platform": if mac { "mac" } else { "windows" },
"removeLineReturns": lines,
"removeParagraphReturns": paras,
+52 -3
View File
@@ -3,7 +3,7 @@
//! places it as area type (`file.place` with `text`) and remembers the options: the next text file
//! starts from them, and is placed with them when Show Import Options is off.
//!
//! Fields: `platform` (`windows` | `mac`), `characterSet` (`unicode` | `ansi`),
//! Fields: `platform` (`windows` | `mac`), `characterSet` (one of [`CHARACTER_SETS`]),
//! `removeLineReturns`, `removeParagraphReturns`, `replaceSpaces` (on or off), `spaces` (how many
//! spaces make a tab, 2–100), and `__params` (the `file.place` params naming the file).
@@ -22,6 +22,21 @@ pub(super) const SPEC: DialogSpec =
/// The label column of the Encoding rows.
const LABEL: f32 = 104.0;
/// The Character Set choices: `file.place`'s `text.characterSet` value and the menu label.
const CHARACTER_SETS: [(&str, &str); 11] = [
("unicode", "Unicode"),
("ansi", "ANSI"),
("shiftJis", "Shift JIS"),
("gb2312", "GB2312"),
("chineseBig5", "Chinese Big 5"),
("cyrillic", "Cyrillic"),
("gb18030", "GB18030"),
("greek", "Greek"),
("turkish", "Turkish"),
("baltic", "Baltic"),
("centralEuropean", "Central European"),
];
/// Is the file `p` names (`path` or `name`) a text file?
pub fn is_text(p: &Value) -> bool {
let name = p.get("path").or_else(|| p.get("name")).and_then(Value::as_str).unwrap_or_default();
@@ -41,7 +56,8 @@ pub fn open(app: &mut VectorcraftApp, params: &Value) -> Value {
"__params": params,
});
let last = &app.ui.text_import;
for (k, wanted) in [("platform", ["windows", "mac"]), ("characterSet", ["unicode", "ansi"])] {
let sets = CHARACTER_SETS.map(|(value, _)| value);
for (k, wanted) in [("platform", &["windows", "mac"][..]), ("characterSet", &sets[..])] {
if let Some(v) = last.get(k).and_then(Value::as_str).filter(|v| wanted.contains(v)) {
fields[k] = json!(v);
}
@@ -68,7 +84,7 @@ pub fn last_options(app: &VectorcraftApp) -> Value {
fn body(_: &mut VectorcraftApp, ui: &mut egui::Ui, d: &mut Dialog) -> bool {
widgets::subheader(ui, tl!("Encoding"));
form::choice(ui, d, "platform", tl!("Platform:"), (LABEL, 180.0), &[("windows", "Windows"), ("mac", "Mac")]);
form::choice(ui, d, "characterSet", tl!("Character Set:"), (LABEL, 180.0), &[("unicode", "Unicode"), ("ansi", "ANSI")]);
form::choice(ui, d, "characterSet", tl!("Character Set:"), (LABEL, 180.0), &CHARACTER_SETS);
ui.add_space(10.0);
widgets::subheader(ui, tl!("Line Breaks"));
for (key, label) in
@@ -166,6 +182,39 @@ mod tests {
assert_eq!(st.history.undo.len(), 1);
}
/// Every character set is a choice: one confirmed last comes back on the next text file and
/// decodes it, an unknown remembered value falls back to Unicode, and with Show Import Options
/// off the remembered set is the one the file is placed with.
#[test]
fn a_remembered_character_set_comes_back_and_places_the_file() {
let mut app = VectorcraftApp::new(Session::new(), Default::default());
app.run("file.new", json!({"width": 300, "height": 200})).unwrap();
let file = json!({"name": "notes.txt", "dataBase64": vectorcraft_format::base64_encode(&[0x93, 0xFA, 0x96, 0x7B])});
app.ui.text_import = json!({"characterSet": "shiftJis", "platform": "windows"});
app.run("file.place", file.clone()).unwrap();
assert_eq!(app.ui.dialog.as_ref().map(|d| d.str("characterSet")).as_deref(), Some("shiftJis"));
assert!(frame(&mut app).contains("Shift JIS"), "the remembered set is shown");
let r = super::super::confirm(&mut app).unwrap();
let st = app.session.doc().unwrap();
let n = st.doc.node(vectorcraft_engine::doc::NodeId(r["ids"][0].as_u64().unwrap())).unwrap();
let NodeKind::Text(t) = &n.kind else { panic!("type") };
assert_eq!(t.plain_text(), "日本");
assert_eq!(last_options(&app)["characterSet"], "shiftJis", "remembered for Show Import Options off");
app.ui.text_import = json!({"characterSet": "latin9"});
app.run("file.place", file).unwrap();
assert_eq!(app.ui.dialog.as_ref().map(|d| d.str("characterSet")).as_deref(), Some("unicode"));
let values: Vec<&str> = CHARACTER_SETS.iter().map(|(v, _)| *v).collect();
let labels: Vec<&str> = CHARACTER_SETS.iter().map(|(_, l)| *l).collect();
assert_eq!(
values,
["unicode", "ansi", "shiftJis", "gb2312", "chineseBig5", "cyrillic", "gb18030", "greek", "turkish", "baltic", "centralEuropean"]
);
assert_eq!(
labels,
["Unicode", "ANSI", "Shift JIS", "GB2312", "Chinese Big 5", "Cyrillic", "GB18030", "Greek", "Turkish", "Baltic", "Central European"]
);
}
/// A text file dropped on a canvas is placed by the dialog's OK in the document it was dropped
/// on, even when another document became active meanwhile.
#[test]
+6
View File
@@ -408,6 +408,12 @@ font-technology Variable Променливи
Character Alignment Подравняване на знаците
Character / Paragraph Знак / Абзац
Character Rotation Въртене на знак
Chinese Big 5 Китайски Big 5
Cyrillic Кирилица
Greek Гръцки
Turkish Турски
Baltic Балтийски
Central European Централноевропейски
Character Set: Набор от знаци:
Character Style Стил на знак
Character Style Options Опции за стил на знак
Can't render this file because it is too large.
+6
View File
@@ -3326,6 +3326,12 @@ antiAlias Sharp Oštro
LF (macOS, Linux) LF (macOS, Linux)
CRLF (Windows) CRLF (Windows)
Text Export Options Opcije izvoza teksta
Chinese Big 5 Kineski Big 5
Cyrillic Ćirilica
Greek Grčki
Turkish Turski
Baltic Baltički
Central European Srednjoevropski
Character Set: Skup znakova:
Join the lines of each paragraph Spoji redove svakog pasusa
Line Breaks Prelomi reda
Can't render this file because it contains an unexpected character in line 2 and column 73.
+7
View File
@@ -685,6 +685,12 @@ antiAlias Sharp Nítid
Character options Opcions de caràcter
Paragraph options Opcions de paràgraf
Character Rotation Rotació de caràcters
Chinese Big 5 Xinès Big 5
Cyrillic Ciríl·lic
Greek Grec
Turkish Turc
Baltic Bàltic
Central European Centreeuropeu
Character Set: Joc de caràcters:
Character Style Estil de caràcter
Character Style Options Opcions de l’estil de caràcter
@@ -8258,3 +8264,4 @@ breakText Glyphs Glifs
@msg A joint does not close by {gap} pt. Una unió no es tanca per {gap} pt.
@msg Two panels pass through each other. Dos panells es travessen l’un a l’altre.
@msg composer must be "singleLine", "everyLine", "standardSingleLine" or "standardEveryLine" composer ha de ser "singleLine", "everyLine", "standardSingleLine" o "standardEveryLine"
@msg text.{key} `{v}`: use "{_1}" or "{_2}" text.{key} `{v}`: utilitzeu "{_1}" o "{_2}"
Can't render this file because it contains an unexpected character in line 2 and column 73.
+6
View File
@@ -3414,6 +3414,12 @@ antiAlias Sharp Ostré
LF (macOS, Linux) LF (macOS, Linux)
CRLF (Windows) CRLF (Windows)
Text Export Options Možnosti exportu textu
Chinese Big 5 Čínština Big 5
Cyrillic Cyrilice
Greek Řečtina
Turkish Turečtina
Baltic Baltské jazyky
Central European Středoevropské jazyky
Character Set: Znaková sada:
Join the lines of each paragraph Spojit řádky každého odstavce
Line Breaks Zalomení řádků
Can't render this file because it is too large.
+6
View File
@@ -5873,6 +5873,12 @@ antiAlias Sharp Skarp
LF (macOS, Linux) LF (macOS, Linux)
CRLF (Windows) CRLF (Windows)
Text Export Options Indstillinger for teksteksport
Chinese Big 5 Kinesisk Big 5
Cyrillic Kyrillisk
Greek Græsk
Turkish Tyrkisk
Baltic Baltisk
Central European Centraleuropæisk
Character Set: Tegnsæt:
Join the lines of each paragraph Forbind linjerne i hvert afsnit
Line Breaks Linjeskift
Can't render this file because it is too large.
+6
View File
@@ -402,6 +402,12 @@ font-technology Variable Variabel
Character Alignment Zeichenausrichtung
Character / Paragraph Zeichen / Absatz
Character Rotation Zeichendrehung
Chinese Big 5 Chinesisch Big 5
Cyrillic Kyrillisch
Greek Griechisch
Turkish Türkisch
Baltic Baltisch
Central European Mitteleuropäisch
Character Set: Zeichensatz:
Character Style Zeichenformat
Character Style Options Zeichenformatoptionen
Can't render this file because it is too large.
+7
View File
@@ -398,6 +398,12 @@ font-technology Variable Μεταβλητές
Character Alignment Στοίχιση χαρακτήρων
Character / Paragraph Χαρακτήρας / Παράγραφος
Character Rotation Περιστροφή χαρακτήρων
Chinese Big 5 Κινεζικά Big 5
Cyrillic Κυριλλικά
Greek Ελληνικά
Turkish Τουρκικά
Baltic Βαλτικά
Central European Κεντρικής Ευρώπης
Character Set: Σύνολο χαρακτήρων:
Character Style Στυλ χαρακτήρων
Character Style Options Επιλογές στυλ χαρακτήρων
@@ -8232,3 +8238,4 @@ breakText Glyphs Γλύφοι
@msg A joint does not close by {gap} pt. Μια ένωση δεν κλείνει κατά {gap} pt.
@msg Two panels pass through each other. Δύο πάνελ διαπερνούν το ένα το άλλο.
@msg composer must be "singleLine", "everyLine", "standardSingleLine" or "standardEveryLine" το composer πρέπει να είναι "singleLine", "everyLine", "standardSingleLine" ή "standardEveryLine"
@msg text.{key} `{v}`: use "{_1}" or "{_2}" text.{key} `{v}`: χρησιμοποιήστε "{_1}" ή "{_2}"
Can't render this file because it is too large.
+7
View File
@@ -425,6 +425,12 @@ font-technology Variable Variables
Character Alignment Alineación de caracteres
Character / Paragraph Carácter / Párrafo
Character Rotation Rotación de caracteres
Chinese Big 5 Chino Big 5
Cyrillic Cirílico
Greek Griego
Turkish Turco
Baltic Báltico
Central European Centroeuropeo
Character Set: Juego de caracteres:
Character Style Estilo de carácter
Character Style Options Opciones de estilo de carácter
@@ -8219,3 +8225,4 @@ breakText Glyphs Glifos
@msg A joint does not close by {gap} pt. Una unión no cierra por {gap} pt.
@msg Two panels pass through each other. Dos paneles se atraviesan entre sí.
@msg composer must be "singleLine", "everyLine", "standardSingleLine" or "standardEveryLine" composer debe ser "singleLine", "everyLine", "standardSingleLine" o "standardEveryLine"
@msg text.{key} `{v}`: use "{_1}" or "{_2}" text.{key} `{v}`: use "{_1}" o "{_2}"
Can't render this file because it contains an unexpected character in line 2 and column 73.
+7
View File
@@ -3361,6 +3361,12 @@ antiAlias Sharp Terävä
LF (macOS, Linux) LF (macOS, Linux)
CRLF (Windows) CRLF (Windows)
Text Export Options Tekstin vientiasetukset
Chinese Big 5 Kiina Big 5
Cyrillic Kyrillinen
Greek Kreikka
Turkish Turkki
Baltic Balttilainen
Central European Keskieurooppalainen
Character Set: Merkistö:
Join the lines of each paragraph Yhdistä kunkin kappaleen rivit
Line Breaks Rivinvaihdot
@@ -8315,3 +8321,4 @@ breakText Glyphs Merkit
@msg A joint does not close by {gap} pt. Liitos ei sulkeudu, rako {gap} pt.
@msg Two panels pass through each other. Kaksi paneelia kulkee toistensa läpi.
@msg composer must be "singleLine", "everyLine", "standardSingleLine" or "standardEveryLine" composer on oltava "singleLine", "everyLine", "standardSingleLine" tai "standardEveryLine"
@msg text.{key} `{v}`: use "{_1}" or "{_2}" text.{key} `{v}`: käytä arvoa "{_1}" tai "{_2}"
Can't render this file because it contains an unexpected character in line 2 and column 73.
+6
View File
@@ -426,6 +426,12 @@ font-technology Variable Variables
Character Alignment Alignement des caractères
Character / Paragraph Caractère / Paragraphe
Character Rotation Rotation des caractères
Chinese Big 5 Chinois Big 5
Cyrillic Cyrillique
Greek Grec
Turkish Turc
Baltic Balte
Central European Europe centrale
Character Set: Jeu de caractères :
Character Style Style de caractère
Character Style Options Options de style de caractère
Can't render this file because it is too large.
+5
View File
@@ -542,6 +542,11 @@
Character Color અક્ષર રંગ
Character Direction અક્ષર દિશા
Character Rotation અક્ષર પરિભ્રમણ
Chinese Big 5 ચાઇનીઝ Big 5
Cyrillic સિરિલિક
Greek ગ્રીક
Baltic બાલ્ટિક
Central European મધ્ય યુરોપિયન
Character Set: અક્ષર સેટ:
Character Style Options અક્ષર સ્ટાઇલ વિકલ્પો
Character Styles અક્ષર સ્ટાઇલ
Can't render this file because it contains an unexpected character in line 72 and column 5.
+5
View File
@@ -801,6 +801,11 @@ antiAlias Sharp शार्प
Character Direction कैरेक्टर दिशा
Character options कैरेक्टर ऑप्शन्स
Character Rotation कैरेक्टर रोटेशन
Chinese Big 5 चीनी Big 5
Cyrillic सिरिलिक
Greek ग्रीक
Baltic बाल्टिक
Central European मध्य यूरोपीय
Character Set: कैरेक्टर सेट:
Character Style कैरेक्टर स्टाइल
Character Style Options कैरेक्टर स्टाइल ऑप्शन्स
Can't render this file because it is too large.
+6
View File
@@ -584,6 +584,12 @@ font-technology Variable Változó
Character options Karakterbeállítások
Paragraph options Bekezdésbeállítások
Character Rotation Karakterforgatás
Chinese Big 5 Kínai Big 5
Cyrillic Cirill
Greek Görög
Turkish Török
Baltic Balti
Central European Közép-európai
Character Set: Karakterkészlet:
Character Style Karakterstílus
Character Style Options Karakterstílus beállításai
Can't render this file because it is too large.
+6
View File
@@ -3105,6 +3105,12 @@ antiAlias Sharp Tajam
LF (macOS, Linux) LF (macOS, Linux)
CRLF (Windows) CRLF (Windows)
Text Export Options Opsi ekspor teks
Chinese Big 5 Tionghoa Big 5
Cyrillic Sirilik
Greek Yunani
Turkish Turki
Baltic Baltik
Central European Eropa Tengah
Character Set: Set karakter:
Join the lines of each paragraph Gabungkan baris setiap paragraf
Line Breaks Pemisah baris
Can't render this file because it contains an unexpected character in line 2528 and column 5.
+6
View File
@@ -427,6 +427,12 @@ font-technology Variable Variabili
Character Alignment Allineamento caratteri
Character / Paragraph Carattere / Paragrafo
Character Rotation Rotazione caratteri
Chinese Big 5 Cinese Big 5
Cyrillic Cirillico
Greek Greco
Turkish Turco
Baltic Baltico
Central European Centroeuropeo
Character Set: Set di caratteri:
Character Style Stile carattere
Character Style Options Opzioni stile carattere
Can't render this file because it is too large.
+6
View File
@@ -1265,6 +1265,12 @@ antiAlias Sharp シャープ
Channel チャンネル
Character / Paragraph 文字/段落
Character Rotation 文字回転
Chinese Big 5 中国語 Big 5
Cyrillic キリル文字
Greek ギリシャ語
Turkish トルコ語
Baltic バルト言語
Central European 中央ヨーロッパ言語
Character Set: 文字セット:
Character Style Options 文字スタイルオプション
Check Links リンクを確認
Can't render this file because it is too large.
+5
View File
@@ -5189,6 +5189,11 @@ antiAlias Sharp მკვეთრი
Encoding: კოდირება:
Line Endings: სტრიქონის დაბოლოებები:
Text Export Options ტექსტის ექსპორტის პარამეტრები
Chinese Big 5 ჩინური Big 5
Cyrillic კირილიცა
Greek ბერძნული
Baltic ბალტიური
Central European ცენტრალურევროპული
Character Set: სიმბოლოთა ნაკრები:
Join the lines of each paragraph თითოეული აბზაცის სტრიქონების შეერთება
Line Breaks სტრიქონის წყვეტები
Can't render this file because it is too large.
+6
View File
@@ -1255,6 +1255,12 @@ antiAlias Sharp 날카롭게
Channel 채널
Character / Paragraph 문자 / 단락
Character Rotation 문자 회전
Chinese Big 5 중국어 Big 5
Cyrillic 키릴 자모
Greek 그리스어
Turkish 터키어
Baltic 발트어
Central European 중앙 유럽어
Character Set: 문자 집합:
Character Style Options 문자 스타일 옵션
Check Links 링크 확인
Can't render this file because it is too large.
+6
View File
@@ -3748,6 +3748,12 @@ antiAlias Sharp Scherp
LF (macOS, Linux) LF (macOS, Linux)
CRLF (Windows) CRLF (Windows)
Text Export Options Opties tekstexport
Chinese Big 5 Chinees Big 5
Cyrillic Cyrillisch
Greek Grieks
Turkish Turks
Baltic Baltisch
Central European Centraal-Europees
Character Set: Tekenset:
Join the lines of each paragraph De regels van elke alinea samenvoegen
Line Breaks Regeleinden
Can't render this file because it is too large.
+6
View File
@@ -3295,6 +3295,12 @@ antiAlias Sharp Ostre
Encoding: Kodowanie:
Line Endings: Znaki końca wiersza:
Text Export Options Opcje eksportu tekstu
Chinese Big 5 Chiński Big 5
Cyrillic Cyrylica
Greek Grecki
Turkish Turecki
Baltic Bałtycki
Central European Środkowoeuropejski
Character Set: Zestaw znaków:
Join the lines of each paragraph Połącz wiersze każdego akapitu
Line Breaks Podziały wierszy
Can't render this file because it is too large.
+6
View File
@@ -394,6 +394,12 @@ antiAlias Sharp Nítido
Character Alignment Alinhamento de Caracteres
Character / Paragraph Caractere / Parágrafo
Character Rotation Rotação de Caractere
Chinese Big 5 Chinês Big 5
Cyrillic Cirílico
Greek Grego
Turkish Turco
Baltic Báltico
Central European Europa Central
Character Set: Conjunto de Caracteres:
Character Style Options Opções de Estilo de Caractere
Character Styles Estilos de Caractere
Can't render this file because it is too large.
+6
View File
@@ -423,6 +423,12 @@ font-technology Variable Вариативные
Character Alignment Выравнивание символов
Character / Paragraph Символ / Абзац
Character Rotation Поворот символов
Chinese Big 5 Китайская Big 5
Cyrillic Кириллица
Greek Греческая
Turkish Турецкая
Baltic Балтийская
Central European Центральноевропейская
Character Set: Набор символов:
Character Style Стиль символа
Character Style Options Параметры стиля символа
Can't render this file because it is too large.
+5
View File
@@ -415,6 +415,11 @@ font-technology Variable Variabla
Character Alignment Teckenjustering
Character / Paragraph Tecken / stycke
Character Rotation Teckenrotation
Chinese Big 5 Kinesisk Big 5
Cyrillic Kyrillisk
Greek Grekisk
Baltic Baltisk
Central European Centraleuropeisk
Character Set: Teckenuppsättning:
Character Style Teckenstil
Character Style Options Alternativ för teckenstil
Can't render this file because it is too large.
+16
View File
@@ -617,6 +617,22 @@ fn monitor_profile_labels_are_in_complete_catalogs() {
}
}
/// Text Import Options' Character Set choices that name a script or a region (Shift JIS, GB2312
/// and GB18030 are names of their own), and the error for an unknown character set.
#[test]
fn text_import_character_sets_are_in_complete_catalogs() {
for lang in LANGUAGES.iter().filter(|lang| lang.complete_menus) {
for label in ["Chinese Big 5", "Cyrillic", "Greek", "Turkish", "Baltic", "Central European"] {
assert!(lang.catalog().plain(label).is_some(), "{} is missing {label}", lang.code);
}
}
let unknown = r#"text.characterSet `x`: use "unicode", "ansi", "shiftJis", "gb2312", "chineseBig5", "cyrillic", "gb18030", "greek", "turkish", "baltic" or "centralEuropean""#;
for code in COMPLETE_MESSAGES {
let lang = Lang::from_code(code).expect("registered");
assert_ne!(message(lang, unknown), unknown, "{code}");
}
}
/// The Control bar panel menu's items, its groups of options and the edges, and the label of the
/// command that turns a group on or off.
#[test]
+6
View File
@@ -408,6 +408,12 @@ font-technology Variable Değişken
Character Alignment Karakter Hizalaması
Character / Paragraph Karakter / Paragraf
Character Rotation Karakter Rotasyonu
Chinese Big 5 Çince Big 5
Cyrillic Kiril
Greek Yunanca
Turkish Türkçe
Baltic Baltık
Central European Orta Avrupa
Character Set: Karakter Seti:
Character Style Karakter Stili
Character Style Options Karakter Stili Seçenekleri
Can't render this file because it is too large.
+6
View File
@@ -421,6 +421,12 @@ font-technology Variable Варіативні
Character Alignment Вирівнювання символів
Character / Paragraph Символ / Абзац
Character Rotation Поворот символів
Chinese Big 5 Китайська Big 5
Cyrillic Кирилиця
Greek Грецька
Turkish Турецька
Baltic Балтійська
Central European Центральноєвропейська
Character Set: Набір символів:
Character Style Стиль символу
Character Style Options Параметри стилю символу
Can't render this file because it is too large.
+7
View File
@@ -500,6 +500,12 @@ font-technology Variable Biến thiên
Character options Tùy chọn ký tự
Paragraph options Tùy chọn đoạn văn
Character Rotation Xoay ký tự
Chinese Big 5 Tiếng Trung Big 5
Cyrillic Chữ Kirin
Greek Tiếng Hy Lạp
Turkish Tiếng Thổ Nhĩ Kỳ
Baltic Vùng Baltic
Central European Trung Âu
Character Set: Bộ ký tự:
Character Style Kiểu ký tự
Character Style Options Tùy chọn kiểu ký tự
@@ -7895,3 +7901,4 @@ breakText Glyphs Glyph
@msg {width} × {height} pixels is too large for Targa (at most 65535 pixels a side): lower the resolution {width} × {height} điểm ảnh quá lớn cho Targa (tối đa 65535 điểm ảnh mỗi cạnh): hãy giảm độ phân giải
@msg {w} × {h} pixels is too large for PSD (at most {MAX_SIDE} pixels a side): lower the resolution {w} × {h} điểm ảnh quá lớn cho PSD (tối đa {MAX_SIDE} điểm ảnh mỗi cạnh): hãy giảm độ phân giải
@msg composer must be "singleLine", "everyLine", "standardSingleLine" or "standardEveryLine" composer phải là "singleLine", "everyLine", "standardSingleLine" hoặc "standardEveryLine"
@msg text.{key} `{v}`: use "{_1}" or "{_2}" text.{key} `{v}`: hãy dùng "{_1}" hoặc "{_2}"
Can't render this file because it contains an unexpected character in line 206 and column 5.
+6
View File
@@ -374,6 +374,12 @@ antiAlias Sharp 锐利
Character Alignment 字符对齐
Character / Paragraph 字符/段落
Character Rotation 字符旋转
Chinese Big 5 繁体中文 Big 5
Cyrillic 西里尔文
Greek 希腊文
Turkish 土耳其文
Baltic 波罗的海文
Central European 中欧文
Character Set: 字符集:
Character Style 字符样式
Character Style Options 字符样式选项
Can't render this file because it is too large.
+6
View File
@@ -389,6 +389,12 @@ font-technology Variable 可變
Character / Paragraph 字元/段落
Character Alignment 字元對齊
Character Rotation 字元旋轉
Chinese Big 5 繁體中文 Big 5
Cyrillic 西里爾文
Greek 希臘文
Turkish 土耳其文
Baltic 波羅的海文
Central European 中歐文
Character Set: 字元集:
Character Style 字元樣式
Character Style Options 字元樣式選項
Can't render this file because it is too large.
+1 -1
View File
@@ -738,7 +738,7 @@ folder, then opens the dialog searching it. The web shows a status line instead
disabled there.
Text Import Options: placing a `.txt` file through the app (`file.place` with a file and no `text` options, the Place
dialog, a drop) opens the `textImport` dialog (fields `platform`: `windows`/`mac`, `characterSet`: `unicode`/`ansi`,
dialog, a drop) opens the `textImport` dialog (fields `platform`: `windows`/`mac`, `characterSet`: a `text.characterSet` value,
`removeLineReturns`, `removeParagraphReturns`, `replaceSpaces`, `spaces`). `ui.dialog.confirm` places the file as area
type with those options (`file.place {text: {…}}`).
+1 -1
View File
@@ -336,7 +336,7 @@ Gradient meshes in the editing data keep each point's own color where a patch's
| Pixar PXR | open, place (legacy) | yes (any set of the R, G, B and A channels in 8 or 12 bits, dumped or run-length encoded, in tiles; R alone is gray; alpha matted to black or unassociated) | no | recognized by its magic number; 12-bit samples are clamped to 0.0 to 1.0; null tiles are transparent with A and black without; the offsets aren't read, and the image takes the default resolution; a file cut short, with header values or packets the format doesn't define, or past the pixel allowance is refused with a message; tested on synthetic files only; tests in `crates/engine/src/cmd/fileio/tests_pxrread.rs` and `crates/engine/tests/import_fuzz.rs` |
| FreeHand `.fh*` | open (legacy) | no | no | |
| CorelDRAW `.cdr` | open | no | no | |
| Text `.txt` | place, export | place (Text Import Options) | yes | |
| Text `.txt` | place, export | place (Text Import Options) | yes | place reads Unicode and ANSI, and Shift JIS, GB2312, Chinese Big 5, Cyrillic, GB18030, Greek, Turkish, Baltic and Central European through the WHATWG Encoding Standard's decoders (VectorCraft's own mapping); `tests/textimport.rs`, `place/text.rs`; fuzzed (`text_import_fuzz.rs`) |
| RTF `.rtf` | place | place (area type with fonts, size, bold, italic, underline, strikethrough, caps, superscript and subscript, color, alignment, indents and paragraph spacing) | no | `tests/textimport.rs`, `place/rtf.rs`; fuzzed (`text_import_fuzz.rs`); `\'hh` bytes read as Windows-1252 or Mac Roman only |
| Word `.docx` | place | place (area type with the document's styles and its fonts, size, bold, italic, underline, strikethrough, caps, superscript and subscript, color, alignment, indents and paragraph spacing) | no | `tests/textimport.rs`, `place/docx.rs`; fuzzed (`text_import_fuzz.rs`); list numbers, pictures and text boxes are left out |
| Word `.doc` | place | place (area type with the same formatting as `.docx`, from the style sheet's styles and direct formatting; Word 97 and later) | no | `tests/textimport.rs`, `place/doc.rs`; fuzzed (`text_import_fuzz.rs`); pictures, headers, footers, notes, comments and text boxes are left out with a warning; encrypted and fast-saved documents are refused |
+8 -3
View File
@@ -8509,10 +8509,15 @@ the document; so does `object.expand`.
```
Placing a text file (`.txt`) sets it as area type: `file.place {path | name+dataBase64, text?: {characterSet?:
"unicode" | "ansi", platform?: "windows" | "mac", removeLineReturns?, removeParagraphReturns?, replaceSpaces?: n}}`
"unicode" | "ansi" | "shiftJis" | "gb2312" | "chineseBig5" | "cyrillic" | "gb18030" | "greek" | "turkish" | "baltic" |
"centralEuropean", platform?: "windows" | "mac", removeLineReturns?, removeParagraphReturns?, replaceSpaces?: n}}`
(Text Import Options). Unicode reads UTF-8, or UTF-16 with a byte-order mark; ANSI reads Windows-1252 (Mac Roman on
`mac`). Unicode reads a file without a byte-order mark as UTF-16 by the rule `dataset.import` uses: at least half of
its two-byte units hold a NUL byte, in the byte order that reads a line break, or for a file with one line, big-endian
`mac`). The other sets use the WHATWG Encoding Standard's decoders: `shiftJis` Shift_JIS, `gb2312` GBK, `chineseBig5`
Big5, `cyrillic` windows-1251 (x-mac-cyrillic on `mac`), `gb18030` gb18030, and `greek`, `turkish`, `baltic` and
`centralEuropean` windows-1253, 1254, 1257 and 1250 on both platforms. They read a byte-order mark as ordinary bytes
and a malformed sequence as U+FFFD. An unknown set, or an option of the wrong type (`characterSet: 3`,
`removeLineReturns: "yes"`), is an error, and nothing is placed. Unicode reads a file without a byte-order mark as
UTF-16 by the rule `dataset.import` uses: at least half of its two-byte units hold a NUL byte, in the byte order that reads a line break, or for a file with one line, big-endian
when more of its units start with a NUL byte than end with one, and little-endian otherwise. Any other file is read as
UTF-8, else as the platform's 8-bit set: one with fewer NUL bytes, one with an odd length, one where both byte orders
read a line break, and one that isn't valid UTF-16 in that order or holds a NUL character. `removeLineReturns` joins
+1
View File
@@ -2107,6 +2107,7 @@ Moved from the ROADMAP's "Shipped so far" on 2026-10-10. Update it when a featur
- The place cursor keeps an encrypted PDF, `.ai` or `.ait` file, at a letter page's size (VectorCraft's own size) and without a thumbnail, and a click or drag on it asks for its password, with the Place dialog's Show Import Options on or off; such a file was left out of the cursor before (`crates/engine/src/tests/place.rs`, `crates/ui-egui/src/tests/place.rs`).
- File › Place with Bounding Box (`file.place {crop: "bounding"}`) measures the art that shows, with its strokes and effects, as an export does: hidden objects, guides and template layers do not count, a group whose only part on the page or artboard is hidden is not placed, and symbol instances are measured by their art, for `at`, `rect`, the place cursor and `file.place.info` (`crates/engine/src/tests/place.rs`).
- The Place dialog has a Show Import Options checkbox after Link, Template and Replace ([Place multiple files in a document](https://helpx.adobe.com/illustrator/desktop/add-and-import-files/import-other-file-types/place-multiple-files-in-a-document.html)). On (VectorCraft's default, saved with the preferences), each PDF, DXF or text file asks for its import options before it is placed, also in the place cursor; off (`file.place {showImportOptions: false}`), it is placed with the options last confirmed for its format, and only an encrypted PDF asks, for its password. Text Import Options now starts from the options confirmed last (`crates/ui-egui/src/tests/place.rs`).
- Text Import Options' Character Set offers Shift JIS, GB2312, Chinese Big 5, Cyrillic, GB18030, Greek, Turkish, Baltic and Central European beside Unicode and ANSI, the plain-text encodings [the help page](https://helpx.adobe.com/illustrator/desktop/add-and-import-files/import-other-file-types/import-and-export-text.html) lists for placed text. `file.place {text: {characterSet}}` decodes each with its WHATWG Encoding Standard decoder. The mapping is VectorCraft's own: GB2312 reads as GBK, Cyrillic as windows-1251 (x-mac-cyrillic with `platform: "mac"`), and Greek, Turkish, Baltic and Central European as windows-1253, 1254, 1257 and 1250 on both platforms. A byte-order mark is read as ordinary bytes, a malformed sequence as U+FFFD, and the last set confirmed is remembered (`crates/engine/src/tests/textimport.rs`, `crates/ui-egui/src/dialogs/text_import.rs`).
- A Shift-click with the loaded place cursor opens the current file's import options (text, DXF, PDF page or embedded PSD) and OK places it at the click, with Show Import Options on or off and for a cursor loaded by `file.place.queue` ([Place multiple files](https://web.archive.org/web/20210601162814/https://helpx.adobe.com/pdf/illustrator_reference.pdf)). VectorCraft's own rules: a file without such a dialog places as a click does, Cancel leaves the file unplaced, a Shift-drag places at the dragged size, and headless the Shift-click places as a click (`crates/tools/src/place.rs`, `crates/engine/src/tests/place.rs`, `crates/ui-egui/src/tests/place.rs`).
- Separations Preview shows placed and embedded raster images on the visible plates, as it shows vector art (#4153): an RGB image's pixels are separated into process inks with the proof setup's intent, a CMYK image shows its own inks, a hidden plate's ink leaves the image, and with one plate visible the image shows that plate's ink as a grey. Raster images carry no spot ink, so a spot plate shown alone shows them as paper; a colorized image shows its color's plates. Emoji and other bitmap glyphs follow the same rule. The plate-filtered pixels and their reduced-size copies are kept apart from the image's own pixels, for each set of visible plates, proof setup and color settings, and with the preview off nothing changes. Evidence: `tests::colorize::separations_preview_shows_an_rgb_images_process_inks`, `separations_preview_shows_a_cmyk_images_own_inks`, `separations_preview_keeps_an_images_pixels_per_plate_set`. Print preview fidelity remains the open gap, so scores and hours are unchanged.
- Desktop print transport uses `craft-print` for CUPS and modern Windows. Sheet composition, copies, separations and colour management remain in VectorCraft. The Print dialog's Media list also carries the Japanese papers — JIS B4 257 × 364 mm, JIS B5 182 × 257 mm and JIS B6 128 × 182 mm beside the ISO B4/B5 (250 × 353 and 176 × 250 mm, kept so settings and presets saved before them keep their paper), and はがき 100 × 148 mm, 往復はがき 148 × 200 mm, 封筒 長形3号 120 × 235 mm, 長形4号 90 × 225 mm, 角形2号 240 × 332 mm, 角形3号 216 × 277 mm and 四六判 127 × 188 mm; the JSON id or the dialog label names a paper, any case and spacing (`B5 (JIS)` or `b5jis`) (`crates/pdf/src/print/settings.rs`, `crates/pdf/src/tests/print.rs`). The print-preview and physical-device fidelity gaps remain, so print scores and hours are unchanged.