mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-15 20:34:36 +00:00
mtlcl410andClaude Opus 5.5
122a155126
An engine test converts files without a binary comment and with a 2.0 header, saves them through Session::save_bytes and verifies the reopened bytes; the preflight test adds a good version with a short comment, and a good header that conversion leaves alone. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Pq7HyDBXygTf7jcqdsjcfn
72 lines
2.9 KiB
Rust
72 lines
2.9 KiB
Rust
//! PDF/A-2 6.1.2, the file header: the file starts at its first byte with `%PDF-1.n`, `n` from 0
|
|
//! to 7, and an end-of-line marker; the next line is a comment, `%` and at least four bytes each
|
|
//! above 127, which marks the file as binary (ISO 32000-1 7.5.2).
|
|
//!
|
|
//! A document whose next save rewrites it in full is judged by the header that save writes: the
|
|
//! version it keeps, followed by the writer's own binary comment.
|
|
|
|
use pdfcraft_cos::Document;
|
|
|
|
/// What the header of `doc`, as it will be saved, breaks of 6.1.2.
|
|
#[derive(Debug, Default, PartialEq, Eq)]
|
|
pub(crate) struct Header {
|
|
/// The first line isn't `%PDF-1.0` to `%PDF-1.7` at the start of the file.
|
|
pub(crate) version: bool,
|
|
/// The second line isn't a comment of at least four bytes above 127.
|
|
pub(crate) comment: bool,
|
|
}
|
|
|
|
/// What the header of `doc` breaks of 6.1.2: as stored, or, when the next save rewrites the
|
|
/// file, as that save will write it.
|
|
pub(crate) fn check(doc: &Document) -> Header {
|
|
if doc.full_save_required() || doc.encryption_changed() {
|
|
let written = doc.version().get(..3).unwrap_or_default();
|
|
return Header { version: !allowed(written.as_bytes()), comment: false };
|
|
}
|
|
let data = doc.bytes();
|
|
let Some(rest) = data.strip_prefix(b"%PDF-") else { return Header { version: true, comment: false } };
|
|
let version = rest.get(..3).unwrap_or_default();
|
|
let Some(rest) = rest.get(3..).and_then(eol) else {
|
|
return Header { version: true, comment: !binary_comment(after_line(rest)) };
|
|
};
|
|
Header { version: !allowed(version), comment: !binary_comment(rest) }
|
|
}
|
|
|
|
/// Whether a version is `1.0` to `1.7`.
|
|
fn allowed(version: &[u8]) -> bool {
|
|
matches!(version, [b'1', b'.', b'0'..=b'7'])
|
|
}
|
|
|
|
/// What follows an end-of-line marker (CR, LF or CR LF) at the start of `data`.
|
|
fn eol(data: &[u8]) -> Option<&[u8]> {
|
|
match data {
|
|
[b'\r', b'\n', rest @ ..] | [b'\r', rest @ ..] | [b'\n', rest @ ..] => Some(rest),
|
|
_ => None,
|
|
}
|
|
}
|
|
|
|
/// What follows the first end-of-line marker in `data`, or nothing.
|
|
fn after_line(data: &[u8]) -> &[u8] {
|
|
let end = data.iter().position(|&b| b == b'\r' || b == b'\n').unwrap_or(data.len());
|
|
data.get(end..).and_then(eol).unwrap_or_default()
|
|
}
|
|
|
|
/// Whether `data` starts with `%` and four bytes above 127.
|
|
fn binary_comment(data: &[u8]) -> bool {
|
|
matches!(data, [b'%', a, b, c, d, ..] if [a, b, c, d].iter().all(|&&x| x > 127))
|
|
}
|
|
|
|
/// Makes the next save of `doc` write a header 6.1.2 allows, when the current one breaks it:
|
|
/// a full save, at version 1.7 when the version kept isn't 1.0 to 1.7. What it fixed, if anything.
|
|
pub(crate) fn rewrite(doc: &mut Document) -> Option<String> {
|
|
let header = check(doc);
|
|
if !header.version && !header.comment {
|
|
return None;
|
|
}
|
|
if !allowed(doc.version().as_bytes().get(..3).unwrap_or_default()) {
|
|
doc.set_version("1.7");
|
|
}
|
|
doc.require_full_save();
|
|
Some("Rewrote the file header".into())
|
|
}
|