mirror of
https://github.com/storytold/craft-libs.git
synced 2026-11-12 11:13:55 +00:00
Dylan M. Taylor
c516452b47
craft-rtf and craft-dxf each carried tables for DOS 437, 737, 850, 852 and 857 (and craft-rtf one for 866). They are now one set in craft-codepage, which takes craft-rtf's codepage module (Windows and Mac tables, OEM glyphs, font charsets) and craft-dxf's DOS tables. craft_rtf::codepage re-exports it unchanged; craft-dxf keeps its $DWGCODEPAGE names and Decoder and looks the DOS tables up there. Every byte of every code page either crate decodes is unchanged: the public decoders of both crates were dumped over all 256 bytes of each page (and the East Asian pairs) before and after, and the dumps are identical. craft-mime now reads the DOS pages by their IANA names (IBM437, cp850, ibm-852, 857...), which it read as UTF-8 before.
1338 lines
52 KiB
Rust
1338 lines
52 KiB
Rust
//! A standalone DXF tag reader and writer.
|
||
//!
|
||
//! DXF is a sequence of (group code, value) pairs. This crate parses ASCII and binary DXF into a
|
||
//! flat list of [`Tag`]s, splits them into sections and entities, and writes tags back. [`model`]
|
||
//! reads the tags as a drawing (header variables, tables, blocks, entities, objects); mapping
|
||
//! that onto an application's own document is left to the caller. Written from Autodesk's
|
||
//! published DXF Reference; depends on no other Craft crate. Moved from CADCraft's `cadcraft-dxf`.
|
||
#![deny(clippy::unwrap_used, clippy::expect_used, clippy::panic, clippy::unimplemented, clippy::todo, clippy::unreachable)]
|
||
#![forbid(unsafe_code)]
|
||
|
||
use std::io::Write as _;
|
||
|
||
pub mod model;
|
||
mod version;
|
||
pub use version::Version;
|
||
|
||
#[derive(Debug, thiserror::Error)]
|
||
pub enum DxfError {
|
||
#[error("not a DXF file")]
|
||
NotDxf,
|
||
#[error("line {line}: bad group code `{text}`")]
|
||
BadCode { line: usize, text: String },
|
||
#[error("unexpected end of file")]
|
||
Eof,
|
||
/// More group codes than [`MAX_TAGS`]: `tags` is the count found (or the count read when the
|
||
/// limit was reached), `limit` the maximum.
|
||
#[error("drawing too large: {tags} DXF group codes, more than the {limit} CADCraft reads (set CADCRAFT_MAX_DXF_TAGS to read more)")]
|
||
TooLarge { tags: usize, limit: usize },
|
||
/// The memory for `tags` group codes couldn't be had: an error, not the process ending.
|
||
#[error("not enough memory to read this drawing's {tags} DXF group codes")]
|
||
OutOfMemory { tags: usize },
|
||
}
|
||
|
||
pub type Result<T> = std::result::Result<T, DxfError>;
|
||
|
||
/// A typed group value.
|
||
#[derive(Clone, Debug, PartialEq)]
|
||
pub enum Value {
|
||
Str(String),
|
||
Real(f64),
|
||
Int(i64),
|
||
Bool(bool),
|
||
/// Binary chunk (310–319, 1004) as hex text.
|
||
Hex(String),
|
||
}
|
||
|
||
impl Value {
|
||
pub fn as_str(&self) -> String {
|
||
match self {
|
||
Value::Str(s) | Value::Hex(s) => s.clone(),
|
||
Value::Real(r) => format_real(*r),
|
||
Value::Int(i) => i.to_string(),
|
||
Value::Bool(b) => i64::from(*b).to_string(),
|
||
}
|
||
}
|
||
#[expect(
|
||
clippy::cast_precision_loss,
|
||
reason = "DXF numeric accessors intentionally convert integer values to f64, accepting precision loss beyond 2^53."
|
||
)]
|
||
pub fn as_f64(&self) -> f64 {
|
||
match self {
|
||
Value::Real(r) if r.is_finite() => *r,
|
||
Value::Int(i) => *i as f64,
|
||
Value::Str(s) => s.trim().parse::<f64>().ok().filter(|v| v.is_finite()).unwrap_or(0.0),
|
||
Value::Bool(b) => f64::from(u8::from(*b)),
|
||
_ => 0.0,
|
||
}
|
||
}
|
||
#[expect(clippy::cast_possible_truncation, reason = "DXF numeric accessors intentionally truncate finite real values to i64.")]
|
||
pub fn as_i64(&self) -> i64 {
|
||
match self {
|
||
Value::Int(i) => *i,
|
||
Value::Real(r) if r.is_finite() => *r as i64,
|
||
Value::Str(s) => {
|
||
s.trim().parse::<i64>().unwrap_or_else(|_| s.trim().parse::<f64>().ok().filter(|f| f.is_finite()).map_or(0, |f| f as i64))
|
||
}
|
||
Value::Bool(b) => i64::from(*b),
|
||
_ => 0,
|
||
}
|
||
}
|
||
}
|
||
|
||
#[derive(Clone, Debug, PartialEq)]
|
||
pub struct Tag {
|
||
pub code: i32,
|
||
pub value: Value,
|
||
}
|
||
|
||
impl Tag {
|
||
pub fn new(code: i32, value: Value) -> Self {
|
||
Tag { code, value }
|
||
}
|
||
pub fn s(code: i32, v: impl Into<String>) -> Self {
|
||
Tag { code, value: Value::Str(v.into()) }
|
||
}
|
||
pub fn f(code: i32, v: f64) -> Self {
|
||
Tag { code, value: Value::Real(if v.is_finite() { v } else { 0.0 }) }
|
||
}
|
||
pub fn i(code: i32, v: i64) -> Self {
|
||
Tag { code, value: Value::Int(v) }
|
||
}
|
||
pub fn str(&self) -> String {
|
||
self.value.as_str()
|
||
}
|
||
/// The value when it is text, without a copy.
|
||
pub fn str_ref(&self) -> Option<&str> {
|
||
match &self.value {
|
||
Value::Str(s) | Value::Hex(s) => Some(s),
|
||
_ => None,
|
||
}
|
||
}
|
||
pub fn f64(&self) -> f64 {
|
||
self.value.as_f64()
|
||
}
|
||
pub fn i64(&self) -> i64 {
|
||
self.value.as_i64()
|
||
}
|
||
}
|
||
|
||
/// The value type for a group code (DXF Reference, "Group Code Value Types").
|
||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||
pub enum Kind {
|
||
Str,
|
||
Real,
|
||
Int16,
|
||
Int32,
|
||
Int64,
|
||
Bool,
|
||
Hex,
|
||
}
|
||
|
||
pub fn kind_of(code: i32) -> Kind {
|
||
match code {
|
||
10..=59 | 110..=149 | 210..=239 | 460..=469 | 1010..=1059 => Kind::Real,
|
||
60..=79 | 170..=179 | 270..=289 | 370..=389 | 400..=409 | 1060..=1070 => Kind::Int16,
|
||
90..=99 | 420..=429 | 440..=449 | 450..=459 | 1071 => Kind::Int32,
|
||
160..=169 => Kind::Int64,
|
||
290..=299 => Kind::Bool,
|
||
310..=319 | 1004 => Kind::Hex,
|
||
_ => Kind::Str,
|
||
}
|
||
}
|
||
|
||
#[expect(clippy::cast_possible_truncation, reason = "DXF numeric parsing intentionally truncates finite real values to i64.")]
|
||
fn typed(code: i32, text: &str) -> Value {
|
||
let t = text.trim();
|
||
match kind_of(code) {
|
||
Kind::Real => t.parse::<f64>().ok().filter(|v| v.is_finite()).map_or(Value::Real(0.0), Value::Real),
|
||
Kind::Int16 | Kind::Int32 | Kind::Int64 => {
|
||
// A float spelling ("1e3", "12.0") is accepted when finite, clamped to what the
|
||
// group's width holds, signed or unsigned (files write 16-bit flags up to 65535, as
|
||
// the integer spelling reads them); NaN, inf and text become 0.
|
||
let (lo, hi) = match kind_of(code) {
|
||
Kind::Int16 => (i64::from(i16::MIN), i64::from(u16::MAX)),
|
||
Kind::Int32 => (i64::from(i32::MIN), i64::from(u32::MAX)),
|
||
_ => (i64::MIN, i64::MAX),
|
||
};
|
||
t.parse::<i64>()
|
||
.map_or_else(|_| Value::Int(t.parse::<f64>().ok().filter(|f| f.is_finite()).map_or(0, |f| (f as i64).clamp(lo, hi))), Value::Int)
|
||
}
|
||
Kind::Bool => Value::Bool(t.parse::<i64>().unwrap_or(0) != 0),
|
||
Kind::Hex => Value::Hex(normalize_hex(t)),
|
||
Kind::Str => Value::Str(text.trim_end_matches(['\r', '\n']).to_string()),
|
||
}
|
||
}
|
||
|
||
const BINARY_SENTINEL: &[u8] = b"AutoCAD Binary DXF\r\n\x1a\0";
|
||
const UTF8_BOM: &[u8] = b"\xEF\xBB\xBF";
|
||
/// Most group codes read from one file by default. A `Tag` takes 40 bytes plus its text, so this
|
||
/// bounds the tag list to about 4 GB plus text. 50 million rejected large DWGs that converted fine
|
||
/// (a 172 MB drawing has 56 million, issue #1948). The file-size limits bound memory too: 512 MB
|
||
/// for a DXF opened directly, 1 GB for a DWG's DXF rendition. Set `CADCRAFT_MAX_DXF_TAGS` to
|
||
/// raise or lower it.
|
||
pub const MAX_TAGS: usize = 100_000_000;
|
||
|
||
/// Environment variable overriding [`MAX_TAGS`] (a positive integer).
|
||
pub const MAX_TAGS_ENV: &str = "CADCRAFT_MAX_DXF_TAGS";
|
||
|
||
/// The group-code limit in effect: [`MAX_TAGS_ENV`] when set to a positive integer, else
|
||
/// [`MAX_TAGS`].
|
||
pub fn max_tags() -> usize {
|
||
max_tags_from(std::env::var(MAX_TAGS_ENV).ok().as_deref())
|
||
}
|
||
|
||
fn max_tags_from(v: Option<&str>) -> usize {
|
||
v.and_then(|s| s.trim().replace('_', "").parse::<usize>().ok()).filter(|&n| n > 0).unwrap_or(MAX_TAGS)
|
||
}
|
||
|
||
mod codepage;
|
||
pub use codepage::decode_code_page;
|
||
|
||
/// Parse a DXF file (ASCII or binary).
|
||
///
|
||
/// # Errors
|
||
///
|
||
/// Returns an error for empty input, an invalid group code, an incomplete group-code/value pair,
|
||
/// truncated binary data, or more than [`MAX_TAGS`] group codes. For ASCII input, invalid numeric
|
||
/// text becomes `0.0` for real values or `0` for integer values, and an EOF tag is not required.
|
||
pub fn parse(bytes: &[u8]) -> Result<Vec<Tag>> {
|
||
parse_with_limit(bytes, max_tags())
|
||
}
|
||
|
||
/// [`parse`] for a file that may be cut short or damaged: an ASCII file is read up to the first
|
||
/// line that is no group code (or a last group code with no value), and what came before is
|
||
/// returned with the 1-based number of that line, so a caller can open what the file still holds
|
||
/// and say where it stops. `None` for a file read to its end. A truncated binary file, an empty
|
||
/// one, one damaged before its first group, and one over the limit are still errors.
|
||
///
|
||
/// # Errors
|
||
///
|
||
/// As [`parse`], except for damage after the first group of an ASCII file.
|
||
pub fn parse_recovering(bytes: &[u8]) -> Result<(Vec<Tag>, Option<usize>)> {
|
||
if let Some(body) = bytes.strip_prefix(BINARY_SENTINEL) {
|
||
return parse_binary_with_limit(body, max_tags()).map(|tags| (tags, None));
|
||
}
|
||
let bytes = bytes.strip_prefix(UTF8_BOM).unwrap_or(bytes);
|
||
let (tags, limit) = (count_ascii_pairs(bytes), max_tags());
|
||
if tags > limit {
|
||
return Err(DxfError::TooLarge { tags, limit });
|
||
}
|
||
ascii_tags(&codepage::decode_ascii_file(bytes), limit, tags, true)
|
||
}
|
||
|
||
/// The nonblank group-code/value pairs of an ASCII file (LF, CRLF and a lone CR each end a
|
||
/// line), up to EOF just as the parser stops there. Blank lines do not count.
|
||
fn count_ascii_pairs(bytes: &[u8]) -> usize {
|
||
let mut lines = byte_lines(bytes);
|
||
let mut tags = 0;
|
||
while let Some(code) = lines.next() {
|
||
let code = code.trim_ascii();
|
||
if code.is_empty() {
|
||
continue;
|
||
}
|
||
let Some(value) = lines.next() else { break };
|
||
tags += 1;
|
||
if code == b"0" && value.trim_ascii() == b"EOF" {
|
||
break;
|
||
}
|
||
}
|
||
tags
|
||
}
|
||
|
||
/// [`parse`] with an explicit group-code limit. For ASCII DXF the limit is checked up front from
|
||
/// the line count, before the text is decoded or any tag allocated, so an oversized file fails in
|
||
/// milliseconds instead of after it has filled memory.
|
||
///
|
||
/// # Errors
|
||
///
|
||
/// Returns an error for empty input, an invalid group code, an incomplete group-code/value pair,
|
||
/// truncated binary data, or more than `max_tags` group codes. For ASCII input, invalid numeric
|
||
/// text becomes `0.0` for real values or `0` for integer values, and an EOF tag is not required.
|
||
pub fn parse_with_limit(bytes: &[u8], max_tags: usize) -> Result<Vec<Tag>> {
|
||
if let Some(body) = bytes.strip_prefix(BINARY_SENTINEL) {
|
||
return parse_binary_with_limit(body, max_tags);
|
||
}
|
||
let bytes = bytes.strip_prefix(UTF8_BOM).unwrap_or(bytes);
|
||
// Counted first, before the text is decoded or any tag allocated.
|
||
let tags = count_ascii_pairs(bytes);
|
||
if tags > max_tags {
|
||
return Err(DxfError::TooLarge { tags, limit: max_tags });
|
||
}
|
||
parse_ascii_counted(&codepage::decode_ascii_file(bytes), max_tags, tags)
|
||
}
|
||
|
||
/// The four hex digits of a `\U+XXXX` escape starting at `chars[i]`, if there is one.
|
||
fn escape_at(chars: &[char], i: usize) -> Option<u32> {
|
||
if chars.get(i) != Some(&'\\') || chars.get(i + 1) != Some(&'U') || chars.get(i + 2) != Some(&'+') {
|
||
return None;
|
||
}
|
||
let hex = chars.get(i + 3..i + 7)?;
|
||
if !hex.iter().all(char::is_ascii_hexdigit) {
|
||
return None;
|
||
}
|
||
hex.iter().try_fold(0u32, |acc, c| Some(acc * 16 + c.to_digit(16)?))
|
||
}
|
||
|
||
/// The character of a `\M+nXXXX` escape starting at `chars[i]`, if there is one: `n` names a
|
||
/// double-byte code page and `XXXX` is the character's two bytes in hex.
|
||
pub fn mif_escape_at(chars: &[char], i: usize) -> Option<char> {
|
||
if chars.get(i) != Some(&'\\') || chars.get(i + 1) != Some(&'M') || chars.get(i + 2) != Some(&'+') {
|
||
return None;
|
||
}
|
||
let n = *chars.get(i + 3)?;
|
||
let hex = chars.get(i + 4..i + 8)?;
|
||
if !hex.iter().all(char::is_ascii_hexdigit) {
|
||
return None;
|
||
}
|
||
let code = hex.iter().try_fold(0u16, |acc, c| Some(acc * 16 + u16::try_from(c.to_digit(16)?).ok()?))?;
|
||
codepage::mif_char(n, code.to_be_bytes())
|
||
}
|
||
|
||
/// Unescape the `\U+XXXX` sequences pre-R2007 DXF uses for characters outside the file's code
|
||
/// page (four hex digits, one UTF-16 code unit; characters above U+FFFF are a surrogate pair of
|
||
/// escapes), and the `\M+nXXXX` sequences for double-byte East Asian characters. Malformed
|
||
/// escapes, unpaired surrogates and unknown `\M+` code pages are kept as literal text.
|
||
fn unescape_unicode(s: &str) -> String {
|
||
if !has_escape(s) {
|
||
return s.to_string();
|
||
}
|
||
unescape_found(s)
|
||
}
|
||
|
||
/// [`unescape_unicode`] for a string the caller owns: without escapes (nearly always) it is
|
||
/// returned as it is, with no copy.
|
||
fn unescape_owned(s: String) -> String {
|
||
if has_escape(&s) { unescape_found(&s) } else { s }
|
||
}
|
||
|
||
fn has_escape(s: &str) -> bool {
|
||
s.contains("\\U+") || s.contains("\\M+")
|
||
}
|
||
|
||
/// The longest escape: a surrogate pair of two `\U+XXXX` (14 characters).
|
||
const MAX_ESCAPE_CHARS: usize = 14;
|
||
|
||
fn unescape_found(s: &str) -> String {
|
||
let mut out = String::with_capacity(s.len());
|
||
let mut rest = s;
|
||
// Everything up to the next backslash is copied as it is; an escape is looked for in a window
|
||
// of the next few characters only, so no copy of the whole string (4 bytes a character) is made.
|
||
while let Some(at) = rest.find('\\') {
|
||
let (plain, tail) = rest.split_at(at);
|
||
out.push_str(plain);
|
||
let mut buf = ['\0'; MAX_ESCAPE_CHARS];
|
||
let mut n = 0;
|
||
for (slot, c) in buf.iter_mut().zip(tail.chars()) {
|
||
*slot = c;
|
||
n += 1;
|
||
}
|
||
let window = buf.get(..n).unwrap_or_default();
|
||
let (ch, used) = if let Some(ch) = mif_escape_at(window, 0) {
|
||
(Some(ch), 8)
|
||
} else if let Some(unit) = escape_at(window, 0) {
|
||
if let Some(ch) = char::from_u32(unit) {
|
||
(Some(ch), 7)
|
||
} else if (0xD800..0xDC00).contains(&unit)
|
||
&& let Some(low) = escape_at(window, 7).filter(|u| (0xDC00..0xE000).contains(u))
|
||
{
|
||
(char::from_u32(0x10000 + ((unit - 0xD800) << 10) + (low - 0xDC00)), 14)
|
||
} else {
|
||
(None, 0)
|
||
}
|
||
} else {
|
||
(None, 0)
|
||
};
|
||
match ch {
|
||
Some(ch) => {
|
||
out.push(ch);
|
||
// Every escape character is ASCII, so `used` characters are `used` bytes.
|
||
rest = tail.get(used..).unwrap_or_default();
|
||
}
|
||
None => {
|
||
out.push('\\');
|
||
rest = tail.get(1..).unwrap_or_default();
|
||
}
|
||
}
|
||
}
|
||
out.push_str(rest);
|
||
out
|
||
}
|
||
|
||
/// The lines of an ASCII DXF text: LF, CRLF and a lone CR (old Mac files) all end a line, like
|
||
/// [`str::lines`] otherwise (no empty line after a final terminator).
|
||
fn ascii_lines(text: &str) -> impl Iterator<Item = &str> {
|
||
let mut rest = text;
|
||
std::iter::from_fn(move || {
|
||
if rest.is_empty() {
|
||
return None;
|
||
}
|
||
let end = rest.find(['\r', '\n']).unwrap_or(rest.len());
|
||
let line = rest.get(..end).unwrap_or_default();
|
||
let after = rest.get(end..).unwrap_or_default();
|
||
rest = after.strip_prefix("\r\n").or_else(|| after.strip_prefix(['\r', '\n'])).unwrap_or(after);
|
||
Some(line)
|
||
})
|
||
}
|
||
|
||
/// Byte-level twin of [`ascii_lines`] for the up-front limit check, so the count matches the parser.
|
||
fn byte_lines(mut rest: &[u8]) -> impl Iterator<Item = &[u8]> {
|
||
std::iter::from_fn(move || {
|
||
if rest.is_empty() {
|
||
return None;
|
||
}
|
||
let end = rest.iter().position(|&b| b == b'\r' || b == b'\n').unwrap_or(rest.len());
|
||
let line = &rest[..end];
|
||
let after = &rest[end..];
|
||
rest = match after {
|
||
[b'\r', b'\n', tail @ ..] | [b'\r' | b'\n', tail @ ..] => tail,
|
||
_ => after,
|
||
};
|
||
Some(line)
|
||
})
|
||
}
|
||
|
||
/// Parse ASCII DXF text into typed tags.
|
||
///
|
||
/// # Errors
|
||
///
|
||
/// Returns an error for empty input, an invalid group code, an incomplete group-code/value pair,
|
||
/// or too many tags. Invalid numeric text becomes `0.0` for real values or `0` for integer values.
|
||
/// A complete tag stream does not require an EOF tag.
|
||
pub fn parse_ascii(text: &str) -> Result<Vec<Tag>> {
|
||
parse_ascii_counted(text, max_tags(), 0)
|
||
}
|
||
|
||
/// [`parse_ascii`] of a file known to hold `expected` group codes. Their list is reserved first,
|
||
/// with an allocation that can fail: where the system refuses that much memory, opening the file
|
||
/// is an error instead of the end of the app. Growing the list instead could also briefly take
|
||
/// half as much again.
|
||
fn parse_ascii_counted(text: &str, max_tags: usize, expected: usize) -> Result<Vec<Tag>> {
|
||
ascii_tags(text, max_tags, expected, false).map(|(tags, _)| tags)
|
||
}
|
||
|
||
/// The tags of ASCII DXF text. With `recover`, a line that is no group code, or a group code
|
||
/// with no value after it, ends the reading instead of failing it: the tags before it are
|
||
/// returned with the 1-based number of that line.
|
||
#[allow(clippy::while_let_loop)]
|
||
fn ascii_tags(text: &str, max_tags: usize, expected: usize, recover: bool) -> Result<(Vec<Tag>, Option<usize>)> {
|
||
let mut tags = Vec::new();
|
||
tags.try_reserve_exact(expected.min(max_tags)).map_err(|_| DxfError::OutOfMemory { tags: expected })?;
|
||
let mut lines = ascii_lines(text.strip_prefix('\u{feff}').unwrap_or(text)).enumerate();
|
||
let mut damaged = None;
|
||
loop {
|
||
let Some((ln, code_line)) = lines.next() else { break };
|
||
let ct = code_line.trim();
|
||
if ct.is_empty() {
|
||
continue;
|
||
}
|
||
let Ok(code) = ct.parse::<i32>() else {
|
||
if recover && !tags.is_empty() {
|
||
damaged = Some(ln + 1);
|
||
break;
|
||
}
|
||
return Err(DxfError::BadCode { line: ln + 1, text: ct.chars().take(40).collect() });
|
||
};
|
||
let Some((_, val)) = lines.next() else {
|
||
if recover && !tags.is_empty() {
|
||
damaged = Some(ln + 1);
|
||
break;
|
||
}
|
||
return Err(DxfError::Eof);
|
||
};
|
||
let v = match typed(code, val) {
|
||
// Only text with a backslash can hold an escape; the rest moves in as it is.
|
||
Value::Str(s) => Value::Str(unescape_owned(s)),
|
||
o => o,
|
||
};
|
||
let eof = code == 0 && matches!(&v, Value::Str(s) if s.trim_end() == "EOF");
|
||
tags.push(Tag { code, value: v });
|
||
if tags.len() > max_tags {
|
||
return Err(DxfError::TooLarge { tags: tags.len(), limit: max_tags });
|
||
}
|
||
if eof {
|
||
break;
|
||
}
|
||
}
|
||
if tags.is_empty() {
|
||
return Err(DxfError::NotDxf);
|
||
}
|
||
Ok((tags, damaged))
|
||
}
|
||
|
||
struct Cur<'a> {
|
||
b: &'a [u8],
|
||
p: usize,
|
||
}
|
||
|
||
impl<'a> Cur<'a> {
|
||
fn take(&mut self, n: usize) -> Result<&[u8]> {
|
||
let end = self.p.checked_add(n).ok_or(DxfError::Eof)?;
|
||
let s = self.b.get(self.p..end).ok_or(DxfError::Eof)?;
|
||
self.p = end;
|
||
Ok(s)
|
||
}
|
||
fn u8(&mut self) -> Result<u8> {
|
||
Ok(*self.take(1)?.first().ok_or(DxfError::Eof)?)
|
||
}
|
||
fn i16(&mut self) -> Result<i16> {
|
||
let s = self.take(2)?;
|
||
Ok(i16::from_le_bytes([s[0], s[1]]))
|
||
}
|
||
fn i32(&mut self) -> Result<i32> {
|
||
let s = self.take(4)?;
|
||
Ok(i32::from_le_bytes([s[0], s[1], s[2], s[3]]))
|
||
}
|
||
fn i64(&mut self) -> Result<i64> {
|
||
let s = self.take(8)?;
|
||
let mut a = [0u8; 8];
|
||
a.copy_from_slice(s);
|
||
Ok(i64::from_le_bytes(a))
|
||
}
|
||
fn f64(&mut self) -> Result<f64> {
|
||
let s = self.take(8)?;
|
||
let mut a = [0u8; 8];
|
||
a.copy_from_slice(s);
|
||
Ok(f64::from_le_bytes(a))
|
||
}
|
||
/// The bytes of a zero-terminated string (without the zero), decoded by the caller.
|
||
fn cstr(&mut self) -> Result<&'a [u8]> {
|
||
let rest = self.b.get(self.p..).unwrap_or(&[]);
|
||
let len = rest.iter().position(|&b| b == 0).ok_or(DxfError::Eof)?;
|
||
self.p += len + 1;
|
||
Ok(rest.get(..len).unwrap_or(&[]))
|
||
}
|
||
}
|
||
|
||
const HEX_DIGITS: &[u8; 16] = b"0123456789ABCDEF";
|
||
|
||
/// Binary DXF, the body after the sentinel: R13+ (2-byte group codes) or R12 and earlier (1-byte
|
||
/// group codes, where 255 is followed by a 2-byte code).
|
||
///
|
||
/// # Errors
|
||
///
|
||
/// Returns an error for an empty or malformed file, an unexpected end of file, or too many tags.
|
||
pub fn parse_binary(b: &[u8]) -> Result<Vec<Tag>> {
|
||
parse_binary_with_limit(b, max_tags())
|
||
}
|
||
|
||
/// Whether a binary DXF body uses the pre-R13 layout with 1-byte group codes, told from its first
|
||
/// tag: R13+ starts with a 2-byte code (`00 00` for the usual `0 SECTION`, `E7 03` for a 999
|
||
/// comment), the old layout with a 1-byte `00` followed by the string's first character, or with
|
||
/// the 255 escape and a code that needs it (255 to 1071; an R13+ file whose first group is code 255
|
||
/// has the string's first character there instead).
|
||
fn legacy_binary_layout(b: &[u8]) -> bool {
|
||
match b {
|
||
[0, next, ..] => *next != 0,
|
||
[255, lo, hi, ..] => (255..=1071).contains(&u16::from_le_bytes([*lo, *hi])),
|
||
_ => false,
|
||
}
|
||
}
|
||
|
||
fn parse_binary_with_limit(b: &[u8], max_tags: usize) -> Result<Vec<Tag>> {
|
||
let mut text = codepage::BinaryText::default();
|
||
let tags = parse_binary_pass(b, max_tags, &mut text)?;
|
||
if !text.needs_code_page_pass() {
|
||
return Ok(tags);
|
||
}
|
||
// The first pass's tags go before the second pass runs: both held at once would double
|
||
// the peak near the tag limit.
|
||
drop(tags);
|
||
parse_binary_pass(b, max_tags, &mut codepage::BinaryText::code_page_pass())
|
||
}
|
||
|
||
fn parse_binary_pass(b: &[u8], max_tags: usize, text: &mut codepage::BinaryText) -> Result<Vec<Tag>> {
|
||
let mut c = Cur { b, p: 0 };
|
||
let mut tags = Vec::new();
|
||
let legacy = legacy_binary_layout(b);
|
||
while c.p < b.len() {
|
||
// 255 escapes a 2-byte code only in the 1-byte layout; in R13+ it is an ordinary code.
|
||
let code = if legacy {
|
||
match c.u8()? {
|
||
255 => i32::from(c.i16()?),
|
||
x => i32::from(x),
|
||
}
|
||
} else {
|
||
i32::from(c.i16()?)
|
||
};
|
||
let v = match kind_of(code) {
|
||
Kind::Str => Value::Str(unescape_unicode(&text.string(code, c.cstr()?))),
|
||
Kind::Real => Value::Real(Some(c.f64()?).filter(|v| v.is_finite()).unwrap_or(0.0)),
|
||
Kind::Int16 => Value::Int(i64::from(c.i16()?)),
|
||
Kind::Int32 => Value::Int(i64::from(c.i32()?)),
|
||
Kind::Int64 => Value::Int(c.i64()?),
|
||
Kind::Bool => Value::Bool(c.u8()? != 0),
|
||
Kind::Hex => {
|
||
let n = usize::from(c.u8()?);
|
||
let bytes = c.take(n)?;
|
||
let mut s = String::with_capacity(n * 2);
|
||
for &x in bytes {
|
||
s.push(char::from(HEX_DIGITS[usize::from(x >> 4)]));
|
||
s.push(char::from(HEX_DIGITS[usize::from(x & 15)]));
|
||
}
|
||
Value::Hex(s)
|
||
}
|
||
};
|
||
let eof = code == 0 && matches!(&v, Value::Str(s) if s.trim_end() == "EOF");
|
||
tags.push(Tag { code, value: v });
|
||
if tags.len() > max_tags {
|
||
return Err(DxfError::TooLarge { tags: tags.len(), limit: max_tags });
|
||
}
|
||
if eof {
|
||
break;
|
||
}
|
||
}
|
||
if tags.is_empty() {
|
||
return Err(DxfError::NotDxf);
|
||
}
|
||
Ok(tags)
|
||
}
|
||
|
||
/// Format a real the way DXF writers usually do (shortest round-trip, with a decimal point).
|
||
pub fn format_real(v: f64) -> String {
|
||
let mut out = Vec::new();
|
||
push_real(&mut out, v);
|
||
// What `push_real` writes is ASCII.
|
||
String::from_utf8(out).unwrap_or_default()
|
||
}
|
||
|
||
/// [`format_real`] appended to `out`, without a string of its own (a large drawing writes
|
||
/// millions of reals).
|
||
fn push_real(out: &mut Vec<u8>, v: f64) {
|
||
if !v.is_finite() {
|
||
out.extend_from_slice(b"0.0");
|
||
return;
|
||
}
|
||
// Very large and very small values in exponent form, as AutoCAD writes them (`1.0E+20`):
|
||
// plain digits would run to hundreds of characters.
|
||
let a = v.abs();
|
||
if a != 0.0 && !(1e-10..1e16).contains(&a) {
|
||
let e = format!("{v:E}");
|
||
let (m, x) = e.split_once('E').unwrap_or((&e, "0"));
|
||
let x: i32 = x.parse().unwrap_or(0);
|
||
let point = if m.contains('.') { "" } else { ".0" };
|
||
let _ = write!(out, "{m}{point}E{}{:02}", if x < 0 { '-' } else { '+' }, x.abs());
|
||
return;
|
||
}
|
||
let start = out.len();
|
||
let _ = write!(out, "{v}");
|
||
// A finite real in this range prints as an optional sign, digits and an optional point.
|
||
if !out.get(start..).is_some_and(|s| s.contains(&b'.')) {
|
||
out.extend_from_slice(b".0");
|
||
}
|
||
}
|
||
|
||
/// A group code right-aligned to three characters and its line end, as `write!("{:>3}\r\n")`
|
||
/// writes it, without the formatting machinery for the codes DXF has (0 to 9999).
|
||
fn push_code(out: &mut Vec<u8>, code: i32) {
|
||
match u16::try_from(code) {
|
||
Ok(c) if c < 10_000 => {
|
||
let digits = [c / 1000, c / 100 % 10, c / 10 % 10, c % 10].map(|d| b'0' + u8::try_from(d % 10).unwrap_or(0));
|
||
// The significant digits (at least one), padded to three.
|
||
let first = digits.iter().position(|&d| d != b'0').unwrap_or(3);
|
||
for _ in 1..first {
|
||
out.push(b' ');
|
||
}
|
||
out.extend_from_slice(digits.get(first..).unwrap_or_default());
|
||
out.extend_from_slice(b"\r\n");
|
||
}
|
||
_ => {
|
||
let _ = write!(out, "{code:>3}\r\n");
|
||
}
|
||
}
|
||
}
|
||
|
||
/// Most characters one string group holds: longer text is split over several groups (MTEXT
|
||
/// contents, field codes).
|
||
pub const MAX_STRING_CHARS: usize = 250;
|
||
|
||
/// `s` split into strings of at most [`MAX_STRING_CHARS`] characters, in order; none for an
|
||
/// empty string.
|
||
pub fn string_groups(s: &str) -> Vec<String> {
|
||
let mut out = Vec::new();
|
||
let mut cur = String::new();
|
||
let mut n = 0;
|
||
for c in s.chars() {
|
||
if n == MAX_STRING_CHARS {
|
||
out.push(std::mem::take(&mut cur));
|
||
n = 0;
|
||
}
|
||
cur.push(c);
|
||
n += 1;
|
||
}
|
||
if !cur.is_empty() {
|
||
out.push(cur);
|
||
}
|
||
out
|
||
}
|
||
|
||
/// Write tags as ASCII DXF (CRLF line ends, codes right-aligned to 3 as is conventional).
|
||
///
|
||
/// The output is pure ASCII: non-ASCII characters in strings are written as `\U+XXXX` escapes,
|
||
/// the pre-R2007 convention, so it is correct whatever `$DWGCODEPAGE` the header declares.
|
||
pub fn write_ascii(tags: &[Tag]) -> String {
|
||
write_ascii_as(tags, false)
|
||
}
|
||
|
||
/// Write tags as ASCII DXF with text in UTF-8 (`utf8`, the R2007+ convention: non-ASCII
|
||
/// characters as they are) or escaped as `\U+XXXX` (older versions, see [`write_ascii`]). Line
|
||
/// breaks inside strings become spaces either way.
|
||
pub fn write_ascii_as(tags: &[Tag], utf8: bool) -> String {
|
||
let bytes = ascii(tags, if utf8 { Strings::Utf8 } else { Strings::Escaped(None) });
|
||
// Both forms are UTF-8 (the escaped one is ASCII).
|
||
String::from_utf8(bytes).unwrap_or_else(|e| String::from_utf8_lossy(e.as_bytes()).into_owned())
|
||
}
|
||
|
||
/// Write tags as pre-R2007 ASCII DXF with text in the code page `code_page` names (a
|
||
/// `$DWGCODEPAGE` value such as `ANSI_1252`), as the DXF Reference describes for those versions:
|
||
/// a character the code page has is written as its bytes, any other as a `\U+XXXX` escape. A
|
||
/// code page this crate doesn't know, `ASCII`, and `UTF8`/`UNICODE` (not a pre-2007 code page)
|
||
/// give [`write_ascii`]'s pure ASCII output. So does a file whose code page bytes happen to be
|
||
/// valid UTF-8 (`СІ` in ANSI_1251 is D1 B2, U+0472), since readers, ours included, take an ASCII
|
||
/// DXF that is valid UTF-8 as UTF-8.
|
||
pub fn write_ascii_in(tags: &[Tag], code_page: &str) -> Vec<u8> {
|
||
let bytes = write_ascii_in_page(tags, code_page);
|
||
if !bytes.is_ascii() && std::str::from_utf8(&bytes).is_ok() {
|
||
return ascii(tags, Strings::Escaped(None));
|
||
}
|
||
bytes
|
||
}
|
||
|
||
/// [`write_ascii_in`] without its fallback to pure ASCII: the text is in the code page even when
|
||
/// its bytes happen to be valid UTF-8. For a reader that decodes a pre-2007 DXF by the
|
||
/// `$DWGCODEPAGE` it declares and never guesses UTF-8, as the DWG bridge's acadrust does. A code
|
||
/// page this crate doesn't know, `ASCII`, and `UTF8`/`UNICODE` still give pure ASCII.
|
||
pub fn write_ascii_in_page(tags: &[Tag], code_page: &str) -> Vec<u8> {
|
||
ascii(tags, Strings::Escaped(codepage::encoder(code_page)))
|
||
}
|
||
|
||
/// How a writer stores string values.
|
||
#[derive(Clone, Copy)]
|
||
enum Strings {
|
||
/// As they are (R2007+).
|
||
Utf8,
|
||
/// ASCII as it is, other characters in this code page when it has them, otherwise as
|
||
/// `\U+XXXX` escapes (before R2007).
|
||
Escaped(Option<codepage::Decoder>),
|
||
}
|
||
|
||
fn ascii(tags: &[Tag], strings: Strings) -> Vec<u8> {
|
||
let mut out = Vec::with_capacity(tags.len() * 16);
|
||
for t in tags {
|
||
push_code(&mut out, t.code);
|
||
match &t.value {
|
||
// Most text has no line breaks or backslashes and is ASCII (or goes out as UTF-8):
|
||
// copied as it is. A code page may write an ASCII character another way, so text
|
||
// for one takes the long path.
|
||
Value::Str(s)
|
||
if !s.contains(['\r', '\n', '\\'])
|
||
&& (matches!(strings, Strings::Utf8) || (matches!(strings, Strings::Escaped(None)) && s.is_ascii())) =>
|
||
{
|
||
out.extend_from_slice(s.as_bytes());
|
||
}
|
||
Value::Str(s) => push_string(s, strings, &mut out),
|
||
Value::Real(r) => push_real(&mut out, *r),
|
||
Value::Int(i) => {
|
||
let _ = write!(out, "{i}");
|
||
}
|
||
Value::Bool(b) => out.push(if *b { b'1' } else { b'0' }),
|
||
Value::Hex(h) => {
|
||
// The DXF Reference limits a binary chunk line to 254 hex digits (127 bytes);
|
||
// longer data continues in further groups of the same code. Only hex digits are
|
||
// written, so a hostile value can't inject tags.
|
||
let digits = normalize_hex(h);
|
||
let mut chunks: Vec<&str> = digits.as_bytes().chunks(254).map(|c| std::str::from_utf8(c).unwrap_or_default()).collect();
|
||
if chunks.is_empty() {
|
||
chunks.push("");
|
||
}
|
||
for (n, chunk) in chunks.into_iter().enumerate() {
|
||
if n > 0 {
|
||
let _ = write!(out, "\r\n{:>3}\r\n", t.code);
|
||
}
|
||
out.extend_from_slice(chunk.as_bytes());
|
||
}
|
||
}
|
||
}
|
||
out.extend_from_slice(b"\r\n");
|
||
}
|
||
out
|
||
}
|
||
|
||
/// Write tags as binary DXF (DXF Reference, "Binary DXF Files", R13+ layout): the sentinel,
|
||
/// then per tag a 2-byte little-endian group code and the value in the binary form of the code's
|
||
/// [`Kind`]: a zero-terminated string, an 8-byte real, a 2-, 4- or 8-byte integer, a 1-byte
|
||
/// boolean, or a binary chunk (one length byte, then up to 255 bytes; longer data is split into
|
||
/// several groups of the same code). Strings are UTF-8 when `utf8` (R2007+), otherwise escaped as
|
||
/// in [`write_ascii`]. A tag's value is converted to its code's kind, so a number written as text
|
||
/// is stored as a number; a code outside the 16-bit range is skipped.
|
||
pub fn write_binary(tags: &[Tag], utf8: bool) -> Vec<u8> {
|
||
binary(tags, if utf8 { Strings::Utf8 } else { Strings::Escaped(None) })
|
||
}
|
||
|
||
/// Write tags as pre-R2007 binary DXF with text in the code page `code_page` names, as
|
||
/// [`write_ascii_in`] does.
|
||
pub fn write_binary_in(tags: &[Tag], code_page: &str) -> Vec<u8> {
|
||
binary(tags, Strings::Escaped(codepage::encoder(code_page)))
|
||
}
|
||
|
||
fn binary(tags: &[Tag], strings: Strings) -> Vec<u8> {
|
||
let mut out = Vec::with_capacity(BINARY_SENTINEL.len() + tags.len() * 12);
|
||
out.extend_from_slice(BINARY_SENTINEL);
|
||
for t in tags {
|
||
let Ok(code) = i16::try_from(t.code) else { continue };
|
||
let code_bytes = code.to_le_bytes();
|
||
match kind_of(t.code) {
|
||
Kind::Str => {
|
||
out.extend_from_slice(&code_bytes);
|
||
let s = match &t.value {
|
||
Value::Str(s) => s.clone(),
|
||
v => v.as_str(),
|
||
};
|
||
let mut text = Vec::with_capacity(s.len());
|
||
push_string(&s, strings, &mut text);
|
||
out.extend(text.into_iter().filter(|&b| b != 0));
|
||
out.push(0);
|
||
}
|
||
Kind::Real => {
|
||
out.extend_from_slice(&code_bytes);
|
||
out.extend_from_slice(&t.value.as_f64().to_le_bytes());
|
||
}
|
||
Kind::Int16 => {
|
||
out.extend_from_slice(&code_bytes);
|
||
out.extend_from_slice(&wrap_i16(t.value.as_i64()));
|
||
}
|
||
Kind::Int32 => {
|
||
out.extend_from_slice(&code_bytes);
|
||
out.extend_from_slice(&wrap_i32(t.value.as_i64()));
|
||
}
|
||
Kind::Int64 => {
|
||
out.extend_from_slice(&code_bytes);
|
||
out.extend_from_slice(&t.value.as_i64().to_le_bytes());
|
||
}
|
||
Kind::Bool => {
|
||
out.extend_from_slice(&code_bytes);
|
||
out.push(u8::from(t.value.as_i64() != 0));
|
||
}
|
||
Kind::Hex => {
|
||
let bytes = hex_bytes(&t.value.as_str());
|
||
// An empty chunk is still one group, as in ASCII.
|
||
let mut chunks: Vec<&[u8]> = bytes.chunks(255).collect();
|
||
if chunks.is_empty() {
|
||
chunks.push(&[]);
|
||
}
|
||
for chunk in chunks {
|
||
out.extend_from_slice(&code_bytes);
|
||
out.push(u8::try_from(chunk.len()).unwrap_or(u8::MAX));
|
||
out.extend_from_slice(chunk);
|
||
}
|
||
}
|
||
}
|
||
}
|
||
out
|
||
}
|
||
|
||
/// Hex text cleaned up: only the hex digits are kept, and an odd trailing digit is padded with
|
||
/// `0` (so the bytes before it are never shifted). Used by the reader and both writers.
|
||
fn normalize_hex(s: &str) -> String {
|
||
let mut out: String = s.chars().filter(char::is_ascii_hexdigit).collect();
|
||
if out.len() % 2 == 1 {
|
||
out.push('0');
|
||
}
|
||
out
|
||
}
|
||
|
||
/// The bytes of hex text, two digits each (see [`normalize_hex`]).
|
||
fn hex_bytes(s: &str) -> Vec<u8> {
|
||
let digits: Vec<u8> = normalize_hex(s).bytes().filter_map(|b| char::from(b).to_digit(16).and_then(|d| u8::try_from(d).ok())).collect();
|
||
digits.as_chunks::<2>().0.iter().map(|[hi, lo]| (hi << 4) | lo).collect()
|
||
}
|
||
|
||
/// A 16- or 32-bit integer for binary DXF: values that fit the unsigned width wrap into the
|
||
/// signed one (65535 is -1, as writers that store unsigned flags expect); anything else clamps.
|
||
fn wrap_i16(v: i64) -> [u8; 2] {
|
||
match u16::try_from(v) {
|
||
Ok(u) => u.to_le_bytes(),
|
||
Err(_) => i16::try_from(v.clamp(i64::from(i16::MIN), i64::from(i16::MAX))).unwrap_or_default().to_le_bytes(),
|
||
}
|
||
}
|
||
|
||
fn wrap_i32(v: i64) -> [u8; 4] {
|
||
match u32::try_from(v) {
|
||
Ok(u) => u.to_le_bytes(),
|
||
Err(_) => i32::try_from(v.clamp(i64::from(i32::MIN), i64::from(i32::MAX))).unwrap_or_default().to_le_bytes(),
|
||
}
|
||
}
|
||
|
||
/// Whether `bytes` are a binary DXF file (they start with the binary sentinel).
|
||
pub fn is_binary(bytes: &[u8]) -> bool {
|
||
bytes.starts_with(BINARY_SENTINEL)
|
||
}
|
||
|
||
/// A string value as `strings` stores it. Line breaks become spaces. Before R2007 the text is
|
||
/// in the `$DWGCODEPAGE` code page: ASCII stays as it is, a character the code page has becomes
|
||
/// its bytes, and every other one `\U+XXXX` (a surrogate pair of escapes above U+FFFF). Without
|
||
/// a code page the result is ASCII, so it is valid in any code page. In every form a backslash
|
||
/// that would start a `\U+` or `\M+` sequence is written as `\U+005C`, so the reader gives back
|
||
/// the literal text (#2050). So is a double-byte character whose trail byte is 0x5C (`\`) in that
|
||
/// place, such as Shift-JIS `表` or Big5 `許`: CADCraft decodes the code page before it looks for
|
||
/// escapes, but a reader that looks first would take that byte and the `U+` after it for one.
|
||
fn push_string(s: &str, strings: Strings, out: &mut Vec<u8>) {
|
||
let chars: Vec<char> = s.chars().collect();
|
||
let escape_at = |j: usize| matches!(chars.get(j), Some('U' | 'M')) && chars.get(j + 1) == Some(&'+');
|
||
for (i, &c) in chars.iter().enumerate() {
|
||
match (c, strings) {
|
||
('\r' | '\n', _) => out.push(b' '),
|
||
('\\', _) if escape_at(i + 1) => {
|
||
out.extend_from_slice(b"\\U+005C");
|
||
}
|
||
(c, Strings::Utf8) => out.extend_from_slice(c.encode_utf8(&mut [0; 4]).as_bytes()),
|
||
(c, Strings::Escaped(Some(d))) if d.shadows_ascii(c) => {
|
||
let _ = write!(out, "\\U+{:04X}", u32::from(c));
|
||
}
|
||
(c, _) if c.is_ascii() => out.extend_from_slice(c.encode_utf8(&mut [0; 4]).as_bytes()),
|
||
(c, Strings::Escaped(Some(d))) if code_page_bytes(c, d, escape_at(i + 1), out) => {}
|
||
(c, Strings::Escaped(_)) => {
|
||
let mut units = [0u16; 2];
|
||
for u in c.encode_utf16(&mut units) {
|
||
let _ = write!(out, "\\U+{u:04X}");
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
/// `c` in the code page `d`, if it has it, unless it is a double-byte character whose trail byte
|
||
/// is 0x5C and an escape's `U+` or `M+` follows (`before_escape`): see [`push_string`].
|
||
fn code_page_bytes(c: char, d: codepage::Decoder, before_escape: bool, out: &mut Vec<u8>) -> bool {
|
||
let start = out.len();
|
||
if !codepage::encode_char(c, d, out) {
|
||
return false;
|
||
}
|
||
if before_escape && out.len() - start > 1 && out.last() == Some(&b'\\') {
|
||
out.truncate(start);
|
||
return false;
|
||
}
|
||
true
|
||
}
|
||
|
||
/// A section: `0 SECTION / 2 NAME ... 0 ENDSEC`.
|
||
#[derive(Clone, Debug, Default)]
|
||
pub struct Section {
|
||
pub name: String,
|
||
pub tags: Vec<Tag>,
|
||
}
|
||
|
||
/// Split a tag stream into sections.
|
||
pub fn sections(tags: &[Tag]) -> Vec<Section> {
|
||
section_slices(tags).into_iter().map(|s| Section { name: s.name.to_string(), tags: s.tags.to_vec() }).collect()
|
||
}
|
||
|
||
/// A section borrowed from the tag stream it was split from: [`Section`] without the copy.
|
||
#[derive(Clone, Copy, Debug)]
|
||
pub struct SectionRef<'a> {
|
||
pub name: &'a str,
|
||
pub tags: &'a [Tag],
|
||
}
|
||
|
||
/// [`sections`] without copying the tags: each section is a slice of `tags`. A large file's tags
|
||
/// take gigabytes (40 bytes a tag, 25 million tags in a 0.5 GB DXF), so a reader that holds the
|
||
/// stream while it reads the sections should take them this way.
|
||
pub fn section_slices(tags: &[Tag]) -> Vec<SectionRef<'_>> {
|
||
let is = |t: &Tag, word: &str| t.code == 0 && t.str_ref().is_some_and(|s| s.trim_end() == word);
|
||
let mut out = Vec::new();
|
||
let mut i = 0;
|
||
while i < tags.len() {
|
||
if tags.get(i).is_some_and(|t| is(t, "SECTION")) {
|
||
let name = tags.get(i + 1).filter(|t| t.code == 2).and_then(Tag::str_ref).unwrap_or_default().trim_end();
|
||
let start = i + 2;
|
||
let mut j = start;
|
||
// A section cut short has no ENDSEC: the EOF is not one of its records.
|
||
while j < tags.len() && !tags.get(j).is_some_and(|t| is(t, "ENDSEC") || is(t, "EOF")) {
|
||
j += 1;
|
||
}
|
||
out.push(SectionRef { name, tags: tags.get(start..j).unwrap_or(&[]) });
|
||
i = j + 1;
|
||
} else {
|
||
i += 1;
|
||
}
|
||
}
|
||
out
|
||
}
|
||
|
||
/// Split a run of tags into records starting at each code-0 tag: (type, tags after the 0).
|
||
pub fn records(tags: &[Tag]) -> Vec<(String, Vec<Tag>)> {
|
||
record_slices(tags).into_iter().map(|(kind, tags)| (kind, tags.to_vec())).collect()
|
||
}
|
||
|
||
/// [`records`] without copying the tags: each record's tags are a slice of `tags`.
|
||
pub fn record_slices(tags: &[Tag]) -> Vec<(String, &[Tag])> {
|
||
let starts: Vec<usize> = tags.iter().enumerate().filter(|(_, t)| t.code == 0).map(|(i, _)| i).collect();
|
||
starts
|
||
.iter()
|
||
.enumerate()
|
||
.map(|(n, &i)| {
|
||
let end = starts.get(n + 1).copied().unwrap_or(tags.len());
|
||
(tags.get(i).map(Tag::str).unwrap_or_default(), tags.get(i + 1..end).unwrap_or(&[]))
|
||
})
|
||
.collect()
|
||
}
|
||
|
||
#[cfg(test)]
|
||
mod tests {
|
||
use super::*;
|
||
|
||
/// The writer's own code and real formatting gives the text `format!` gave.
|
||
#[test]
|
||
fn fast_code_and_real_formatting_match_format() {
|
||
for code in [-1_000_000, -10, -1, 0, 1, 9, 10, 42, 99, 100, 330, 999, 1000, 1071, 9999, 10_000, 65_535, 1_000_000] {
|
||
let mut s = Vec::new();
|
||
push_code(&mut s, code);
|
||
assert_eq!(String::from_utf8(s).unwrap(), format!("{code:>3}\r\n"), "{code}");
|
||
}
|
||
let old = |v: f64| {
|
||
if !v.is_finite() {
|
||
return "0.0".to_string();
|
||
}
|
||
let a = v.abs();
|
||
if a != 0.0 && !(1e-10..1e16).contains(&a) {
|
||
let e = format!("{v:E}");
|
||
let (m, x) = e.split_once('E').unwrap_or((&e, "0"));
|
||
let x: i32 = x.parse().unwrap_or(0);
|
||
let m = if m.contains('.') { m.to_string() } else { format!("{m}.0") };
|
||
return format!("{m}E{}{:02}", if x < 0 { '-' } else { '+' }, x.abs());
|
||
}
|
||
let s = format!("{v}");
|
||
if s.contains('.') { s } else { format!("{s}.0") }
|
||
};
|
||
for v in [
|
||
0.0,
|
||
-0.0,
|
||
1.0,
|
||
-1.0,
|
||
0.1,
|
||
1.5e-7,
|
||
123456789.0,
|
||
1e15,
|
||
1e16,
|
||
1e21,
|
||
1e300,
|
||
-1e-300,
|
||
1e-10,
|
||
9e-11,
|
||
f64::MAX,
|
||
f64::MIN_POSITIVE,
|
||
f64::NAN,
|
||
f64::INFINITY,
|
||
] {
|
||
assert_eq!(format_real(v), old(v), "{v}");
|
||
}
|
||
let tags = [
|
||
Tag::f(10, 2.0),
|
||
Tag::i(70, -3),
|
||
Tag::new(290, Value::Bool(true)),
|
||
Tag::s(1, "a\r\nb"),
|
||
Tag::s(1, "é"),
|
||
Tag::s(1, "plain"),
|
||
Tag::s(1, "a\\U+0041"),
|
||
];
|
||
assert_eq!(
|
||
write_ascii_as(&tags, true),
|
||
" 10\r\n2.0\r\n 70\r\n-3\r\n290\r\n1\r\n 1\r\na b\r\n 1\r\né\r\n 1\r\nplain\r\n 1\r\na\\U+005CU+0041\r\n"
|
||
);
|
||
assert_eq!(write_ascii_as(&tags, false).lines().nth(9), Some("\\U+00E9"));
|
||
// A code page that writes an ASCII character another way still does.
|
||
let yen = [Tag::s(1, "a\\b~")];
|
||
assert_eq!(write_ascii_in_page(¥, "ANSI_932"), ascii_slow(¥, "ANSI_932"));
|
||
}
|
||
|
||
/// What the writer gave before the fast path: every string through `push_string`.
|
||
fn ascii_slow(tags: &[Tag], code_page: &str) -> Vec<u8> {
|
||
let mut out = Vec::new();
|
||
for t in tags {
|
||
let _ = write!(out, "{:>3}\r\n", t.code);
|
||
push_string(&t.str(), Strings::Escaped(codepage::encoder(code_page)), &mut out);
|
||
out.extend_from_slice(b"\r\n");
|
||
}
|
||
out
|
||
}
|
||
|
||
#[test]
|
||
fn literal_escape_text_roundtrips() {
|
||
for utf8 in [false, true] {
|
||
for text in ["\\U+00E9", "\\M+183A4F", "a\\nb \\P", "\\\\U+00E9", "\\U+005C"] {
|
||
let tags = vec![Tag::s(8, text)];
|
||
let back = parse_ascii(&write_ascii_as(&tags, utf8)).unwrap();
|
||
assert_eq!(back, tags, "utf8={utf8} {text}");
|
||
let back = parse_binary(&write_binary(&tags, utf8)).unwrap();
|
||
assert_eq!(back[1..], tags[..], "binary utf8={utf8} {text}");
|
||
}
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn blank_lines_do_not_consume_group_code_limit() {
|
||
let tags = parse_with_limit(b"0\nEOF\n\n\n", 1).expect("one group code should fit a limit of one");
|
||
assert_eq!(tags, vec![Tag::s(0, "EOF")]);
|
||
}
|
||
|
||
#[test]
|
||
fn ascii_roundtrip() {
|
||
let tags = vec![
|
||
Tag::s(0, "SECTION"),
|
||
Tag::s(2, "ENTITIES"),
|
||
Tag::s(0, "LINE"),
|
||
Tag::s(8, "0"),
|
||
Tag::f(10, 1.5),
|
||
Tag::f(20, 2.0),
|
||
Tag::i(62, 1),
|
||
Tag::s(0, "ENDSEC"),
|
||
Tag::s(0, "EOF"),
|
||
];
|
||
let text = write_ascii(&tags);
|
||
let back = parse(text.as_bytes()).unwrap();
|
||
assert_eq!(back, tags);
|
||
let secs = sections(&back);
|
||
assert_eq!(secs.len(), 1);
|
||
assert_eq!(secs[0].name, "ENTITIES");
|
||
let recs = records(&secs[0].tags);
|
||
assert_eq!(recs[0].0, "LINE");
|
||
assert_eq!(recs[0].1.len(), 4);
|
||
}
|
||
|
||
#[test]
|
||
fn binary_parse() {
|
||
let mut b = BINARY_SENTINEL.to_vec();
|
||
let push_str = |b: &mut Vec<u8>, code: i16, s: &str| {
|
||
b.extend_from_slice(&code.to_le_bytes());
|
||
b.extend_from_slice(s.as_bytes());
|
||
b.push(0);
|
||
};
|
||
push_str(&mut b, 0, "LINE");
|
||
b.extend_from_slice(&10i16.to_le_bytes());
|
||
b.extend_from_slice(&3.25f64.to_le_bytes());
|
||
b.extend_from_slice(&62i16.to_le_bytes());
|
||
b.extend_from_slice(&5i16.to_le_bytes());
|
||
push_str(&mut b, 0, "EOF");
|
||
let tags = parse(&b).unwrap();
|
||
assert_eq!(tags[1], Tag::f(10, 3.25));
|
||
assert_eq!(tags[2], Tag::i(62, 5));
|
||
}
|
||
|
||
/// A pre-R13 binary body: 1-byte group codes, 255 escaping a 2-byte code (1001 here).
|
||
fn r12_binary() -> Vec<u8> {
|
||
let mut b = BINARY_SENTINEL.to_vec();
|
||
let push_str = |b: &mut Vec<u8>, code: u8, s: &str| {
|
||
b.push(code);
|
||
b.extend_from_slice(s.as_bytes());
|
||
b.push(0);
|
||
};
|
||
push_str(&mut b, 0, "SECTION");
|
||
push_str(&mut b, 2, "ENTITIES");
|
||
push_str(&mut b, 0, "LINE");
|
||
push_str(&mut b, 8, "RAILROAD");
|
||
b.push(10);
|
||
b.extend_from_slice(&3.25f64.to_le_bytes());
|
||
b.push(62);
|
||
b.extend_from_slice(&5i16.to_le_bytes());
|
||
b.push(255);
|
||
b.extend_from_slice(&1001i16.to_le_bytes());
|
||
b.extend_from_slice(b"APP\0");
|
||
push_str(&mut b, 0, "ENDSEC");
|
||
push_str(&mut b, 0, "EOF");
|
||
b
|
||
}
|
||
|
||
#[test]
|
||
fn r12_binary_parse() {
|
||
let tags = parse(&r12_binary()).unwrap();
|
||
assert_eq!(tags[0], Tag::s(0, "SECTION"));
|
||
assert_eq!(tags[3], Tag::s(8, "RAILROAD"));
|
||
assert_eq!(tags[4], Tag::f(10, 3.25));
|
||
assert_eq!(tags[5], Tag::i(62, 5));
|
||
assert_eq!(tags[6], Tag::s(1001, "APP"));
|
||
assert_eq!(tags.last(), Some(&Tag::s(0, "EOF")));
|
||
}
|
||
|
||
#[test]
|
||
fn r13_binary_code_255_is_ordinary() {
|
||
let mut b = BINARY_SENTINEL.to_vec();
|
||
for (code, s) in [(0i16, "LINE"), (255, "x"), (0, "EOF")] {
|
||
b.extend_from_slice(&code.to_le_bytes());
|
||
b.extend_from_slice(s.as_bytes());
|
||
b.push(0);
|
||
}
|
||
let tags = parse(&b).unwrap();
|
||
assert_eq!(tags.get(1).map(|t| t.code), Some(255));
|
||
assert_eq!(tags.len(), 3);
|
||
}
|
||
|
||
#[test]
|
||
fn binary_layout_detection() {
|
||
assert!(legacy_binary_layout(b"\0SECTION\0"));
|
||
assert!(legacy_binary_layout(&[255, 0xE7, 0x03]));
|
||
assert!(!legacy_binary_layout(b"\0\0SECTION\0"));
|
||
assert!(!legacy_binary_layout(&[0xE7, 0x03, b'x', 0]));
|
||
assert!(!legacy_binary_layout(b""));
|
||
assert!(!legacy_binary_layout(&[0]));
|
||
// R13+ code 255 with the string "x": not the escape
|
||
assert!(!legacy_binary_layout(&[255, 0, b'x', 0]));
|
||
assert!(!legacy_binary_layout(&[255, 0xE7]));
|
||
}
|
||
|
||
#[test]
|
||
fn truncated_r12_binary_never_panics() {
|
||
let b = r12_binary();
|
||
for n in BINARY_SENTINEL.len()..b.len() {
|
||
let _ = parse(b.get(..n).unwrap_or(&[]));
|
||
}
|
||
let mut cut = BINARY_SENTINEL.to_vec();
|
||
cut.extend_from_slice(&[0, b'S', 0, 255, 0x10]);
|
||
assert!(parse(&cut).is_err());
|
||
}
|
||
|
||
#[test]
|
||
fn borrowed_sections_and_records_match_the_copies() {
|
||
let text = "999\nstray\n 0\nSECTION\n 2\nHEADER\n 9\n$ACADVER\n 1\nAC1015\n 0\nENDSEC\n 0\nSECTION\n 2\nENTITIES\n 5\n1A\n 0\nLINE\n 8\n0\n 10\n1.5\n 0\nCIRCLE\n 40\n2.0\n 0\nENDSEC\n 0\nEOF\n";
|
||
let tags = parse(text.as_bytes()).unwrap();
|
||
let (copies, slices) = (sections(&tags), section_slices(&tags));
|
||
assert_eq!(slices.iter().map(|s| s.name).collect::<Vec<_>>(), ["HEADER", "ENTITIES"]);
|
||
assert_eq!(copies.len(), slices.len());
|
||
for (c, s) in copies.iter().zip(&slices) {
|
||
assert_eq!(c.name, s.name);
|
||
assert_eq!(c.tags.as_slice(), s.tags);
|
||
let (rc, rs) = (records(&c.tags), record_slices(s.tags));
|
||
assert_eq!(rc.len(), rs.len());
|
||
for ((kc, tc), (ks, ts)) in rc.iter().zip(&rs) {
|
||
assert_eq!((kc, tc.as_slice()), (ks, *ts));
|
||
}
|
||
}
|
||
// Tags before the first record start none, as in `records`.
|
||
assert_eq!(record_slices(slices[1].tags).iter().map(|(k, _)| k.as_str()).collect::<Vec<_>>(), ["LINE", "CIRCLE"]);
|
||
assert_eq!(slices[1].tags[0].str_ref(), Some("1A"));
|
||
assert_eq!(Tag::f(10, 1.5).str_ref(), None);
|
||
}
|
||
|
||
#[test]
|
||
fn huge_and_tiny_reals_in_exponent_form() {
|
||
// Plain digits would run to hundreds of characters; the value reads back exactly.
|
||
assert_eq!(format_real(1e20), "1.0E+20");
|
||
assert_eq!(format_real(-2.5e-12), "-2.5E-12");
|
||
assert_eq!(format_real(0.5), "0.5");
|
||
assert_eq!(format_real(12.0), "12.0");
|
||
for v in [f64::MAX, -f64::MAX, 1e308, f64::MIN_POSITIVE, 5e-324, 1.2345678901234567e16] {
|
||
let s = format_real(v);
|
||
assert!(s.len() < 32, "{s}");
|
||
assert_eq!(s.parse::<f64>().ok(), Some(v), "{s}");
|
||
// and through the writer and the reader
|
||
let back = parse(write_ascii(&[Tag::f(10, v), Tag::s(0, "EOF")]).as_bytes()).unwrap();
|
||
assert_eq!(back[0], Tag::f(10, v));
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn long_strings_split_into_250_character_groups() {
|
||
assert!(string_groups("").is_empty());
|
||
assert_eq!(string_groups("abc"), ["abc"]);
|
||
let s = "é".repeat(251);
|
||
let g = string_groups(&s);
|
||
assert_eq!(g.iter().map(|x| x.chars().count()).collect::<Vec<_>>(), [250, 1]);
|
||
assert_eq!(g.concat(), s);
|
||
assert_eq!(string_groups(&"x".repeat(500)).len(), 2);
|
||
}
|
||
|
||
#[test]
|
||
fn malformed_inputs() {
|
||
assert!(parse(b"").is_err());
|
||
assert!(parse(b"abc\nxyz\n").is_err());
|
||
assert!(parse(b"0\n").is_err());
|
||
let mut b = BINARY_SENTINEL.to_vec();
|
||
b.extend_from_slice(&10i16.to_le_bytes());
|
||
b.extend_from_slice(&[1, 2, 3]);
|
||
assert!(parse(&b).is_err());
|
||
// Bad numbers become 0 rather than failing.
|
||
let t = parse(b"10\nnotanumber\n0\nEOF\n").unwrap();
|
||
assert!(t[0].f64().abs() < f64::EPSILON);
|
||
}
|
||
|
||
#[test]
|
||
fn unicode_escapes_and_latin1() {
|
||
let t = parse(b"1\nCaf\\U+00E9\n0\nEOF\n").unwrap();
|
||
assert_eq!(t[0].str(), "Café");
|
||
let t = parse(b"1\nCaf\xe9\n0\nEOF\n").unwrap();
|
||
assert_eq!(t[0].str(), "Café");
|
||
}
|
||
|
||
#[test]
|
||
fn surrogate_pair_escapes() {
|
||
let t = parse(b"1\n\\U+D83D\\U+DE00 \\u+56fe\\U+53f7\n0\nEOF\n").unwrap();
|
||
assert_eq!(t[0].str(), "😀 \\u+56fe号");
|
||
}
|
||
|
||
#[test]
|
||
fn hostile_escapes_stay_literal() {
|
||
for s in [
|
||
"\\U+",
|
||
"\\U",
|
||
"\\",
|
||
"a\\U+ZZZZ",
|
||
"\\U+12",
|
||
"\\U+D800",
|
||
"\\U+DC00",
|
||
"\\U+D800\\U+0041",
|
||
"\\U+D83D\\U+DE",
|
||
"\\U++123",
|
||
"\\U+-123",
|
||
"x\\U+12\u{e9}4",
|
||
] {
|
||
let t = parse(format!("1\n{s}\n0\nEOF\n").as_bytes()).unwrap();
|
||
let expect = if s == "\\U+D800\\U+0041" { "\\U+D800A" } else { s };
|
||
assert_eq!(t[0].str(), expect, "{s:?}");
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn writes_non_ascii_as_escapes() {
|
||
let tags = vec![Tag::s(1, "图号 Ä°ø 😀\r\nend"), Tag::s(1000, "Ø"), Tag::s(0, "EOF")];
|
||
let text = write_ascii(&tags);
|
||
assert!(text.is_ascii());
|
||
assert!(text.contains("\\U+56FE\\U+53F7 \\U+00C4\\U+00B0\\U+00F8 \\U+D83D\\U+DE00 end\r\n"));
|
||
let back = parse(text.as_bytes()).unwrap();
|
||
assert_eq!(back[0].str(), "图号 Ä°ø 😀 end");
|
||
assert_eq!(back[1].str(), "Ø");
|
||
}
|
||
|
||
#[test]
|
||
fn binary_strings_unescape() {
|
||
let mut b = BINARY_SENTINEL.to_vec();
|
||
b.extend_from_slice(&1i16.to_le_bytes());
|
||
b.extend_from_slice(b"\\U+56FE\\U+53F7\0");
|
||
b.extend_from_slice(&0i16.to_le_bytes());
|
||
b.extend_from_slice(b"EOF\0");
|
||
assert_eq!(parse(&b).unwrap()[0].str(), "图号");
|
||
}
|
||
}
|
||
|
||
#[cfg(test)]
|
||
mod limit_tests {
|
||
use super::*;
|
||
|
||
#[test]
|
||
fn tag_limit_defaults_and_env_override() {
|
||
assert_eq!(max_tags_from(None), MAX_TAGS);
|
||
assert_eq!(max_tags_from(Some("")), MAX_TAGS);
|
||
assert_eq!(max_tags_from(Some("0")), MAX_TAGS);
|
||
assert_eq!(max_tags_from(Some("abc")), MAX_TAGS);
|
||
assert_eq!(max_tags_from(Some(" 400_000_000 ")), 400_000_000);
|
||
// Issue #1948: the default must admit a DXF rendition well above 50 million group codes.
|
||
const { assert!(MAX_TAGS >= 100_000_000) };
|
||
}
|
||
|
||
#[test]
|
||
fn the_tag_list_is_reserved_once_and_a_refusal_is_an_error() {
|
||
let tags = parse_ascii_counted("0\nSECTION\n0\nENDSEC\n0\nEOF\n", MAX_TAGS, 3).unwrap();
|
||
assert_eq!((tags.len(), tags.capacity()), (3, 3));
|
||
let e = parse_ascii_counted("0\nEOF\n", usize::MAX, usize::MAX).unwrap_err();
|
||
assert!(matches!(e, DxfError::OutOfMemory { .. }), "{e}");
|
||
}
|
||
}
|