aleleba/pdfcraft
1
0
Fork 0
mirror of https://github.com/storytold/pdfcraft.git synced 2026-10-26 11:08:48 -06:00
Code Issues Packages Projects Releases Wiki Activity

Merge PR #2816: M10: running text is not a table row in Word, HTML and PowerPoint export (#2806)

Browse Source
This commit is contained in:
aiongg
2026-10-16 14:02:08 +00:00
parent a17794f170 f9db1e31fd
commit c2a634ec4c
2 changed files with 108 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/export/src/lib.rs
+106 -2
View File
@@ -114,6 +114,34 @@ const COL_TOL: f64 = 4.0;
/// its columns, so a hostile page laid out as a staircase of blocks would otherwise make
/// (blocks / 2)² cells.
const MAX_COLS: usize = 63;
/// Two blocks in a row this close (as a fraction of their font size) are one line of running
/// text that changed font or colour, such as a link inside a sentence, not two table cells.
const INLINE_GAP: f64 = 0.5;
/// How many blocks ending near a block's start are looked at to find the one it continues; a
/// page laid out so that many end at the same place stays quick.
const CONTINUATION_PROBE: usize = 64;
/// Per block, whether it continues another on the same line: it starts where that one ends (up to
/// [`INLINE_GAP`] later, or a point earlier for rounding), so it is the same line of text running
/// on (a link inside a sentence, a superscript), not a cell of its own.
fn continuations(blocks: &[Block]) -> Vec<bool> {
let mut by_end: Vec<(f64, usize)> = blocks.iter().enumerate().map(|(i, b)| (b.rect[2], i)).collect();
by_end.sort_by(|a, b| a.0.total_cmp(&b.0));
blocks
.iter()
.enumerate()
.map(|(bi, b)| {
let k = by_end.partition_point(|(end, _)| *end < b.rect[0] - INLINE_GAP * b.size);
by_end
.get(k..)
.unwrap_or_default()
.iter()
.take_while(|(end, _)| *end <= b.rect[0] + 1.0)
.take(CONTINUATION_PROBE)
.filter_map(|(_, ai)| blocks.get(*ai).filter(|_| *ai != bi))
.any(|a| a.rect[3].min(b.rect[3]) - a.rect[1].max(b.rect[1]) > 0.5 * (a.rect[3] - a.rect[1]).min(b.rect[3] - b.rect[1]))
})
.collect()
}
/// A cell is short: taller blocks are body text (or a multi-column layout), not table cells.
fn is_cell_like(b: &Block) -> bool {
(b.rect[3] - b.rect[1]) <= b.size * 5.0 && !b.text.trim().is_empty()
@@ -264,13 +292,20 @@ pub(crate) fn tables(blocks: &[Block]) -> (Vec<Table>, Vec<bool>) {
es.dedup_by(|a, b| (*a - *b).abs() <= COL_TOL);
es
};
let cont = continuations(blocks);
let qual: Vec<bool> = rows
.iter()
.map(|row| {
let mut cs: Vec<usize> = row.iter().map(|(c, _)| *c).collect();
// A block that continues another adds no column of its own, and the cells of a table row
// sit side by side: blocks that overlap are a paragraph's lines, not cells (#2806).
let cells: Vec<(usize, usize)> = row.iter().copied().filter(|(_, bi)| !cont.get(*bi).copied().unwrap_or(false)).collect();
let mut spans: Vec<[f64; 2]> = cells.iter().filter_map(|(_, bi)| blocks.get(*bi)).map(|b| [b.rect[0], b.rect[2]]).collect();
spans.sort_by(|a, b| a[0].total_cmp(&b[0]));
let apart = spans.windows(2).all(|w| w[1][0] >= w[0][1] - COL_TOL);
let mut cs: Vec<usize> = cells.iter().map(|(c, _)| *c).collect();
cs.sort_unstable();
cs.dedup();
cs.len() >= 2
apart && cs.len() >= 2
})
.collect();
let mut i = 0;
@@ -1186,6 +1221,75 @@ mod tests {
assert_eq!(grid_cols(&grid(64)), 0);
}
fn block(t: &str, x0: f64, y0: f64, x1: f64, y1: f64) -> Block {
Block { text: t.into(), rect: [x0, y0, x1, y1], size: 12.0, bold: false, italic: false, color: [0.0; 3], rotation: 0.0 }
}
/// #2806: a sentence whose link is set in another colour or font runs on as separate blocks
/// on one line. They are not table columns, even when several such lines share left edges.
#[test]
fn a_link_inside_a_sentence_is_not_a_table_column() {
let blue = |t: &str, x0: f64, y0: f64, x1: f64, y1: f64| Block { color: [0.02, 0.388, 0.757], ..block(t, x0, y0, x1, y1) };
let p = Page {
width: 612.0,
height: 792.0,
blocks: vec![
block("6.3. 2. All content shown at", 121.7, 710.3, 272.0, 724.9),
blue("http", 273.5, 710.3, 294.1, 724.9),
blue("s", 294.1, 709.8, 298.8, 725.8),
blue("://women", 298.8, 710.3, 348.0, 724.9),
blue("g", 348.1, 709.8, 353.7, 725.8),
blue("randprix.fide.com", 353.7, 710.3, 443.2, 724.9),
block("shall be reviewed and approved by the Press Officer.", 164.3, 622.5, 533.1, 724.9),
block("6.3. 3. The Organiser shall warrant that", 121.7, 601.8, 345.1, 616.5),
blue("https://womengrandprix.fide.com", 350.2, 601.3, 519.9, 617.4),
block("is managed in a professional way and furthermore that it is capable of", 164.3, 557.9, 533.0, 616.5),
block("6. 3. 4. The Press Officer shall report to the FIDE Head of PR.", 121.7, 516.6, 530.3, 551.9),
block("conducted during a WGP tournament.", 164.3, 502.0, 352.5, 516.6),
],
images: Vec::new(),
};
let h = html(std::slice::from_ref(&p), "Regulations");
assert!(!h.contains("<table>"), "running text became a table: {h}");
for b in &p.blocks {
assert!(h.contains(&b.text), "{} was lost: {h}", b.text);
}
}
/// #2806: lines that each run on into a link starting at the same place are sentences, not a
/// two-column table, even three in a row.
#[test]
fn sentences_that_run_on_into_links_are_not_a_table() {
let blue = |t: &str, x0: f64, y0: f64, x1: f64, y1: f64| Block { color: [0.02, 0.388, 0.757], ..block(t, x0, y0, x1, y1) };
let mut blocks = Vec::new();
for (n, lead) in ["Rules are published at", "Pairings are posted at", "Results are listed at"].iter().enumerate() {
let y = 700.0 - 16.0 * n as f64;
blocks.push(block(lead, 72.0, y, 211.0, y + 12.0));
blocks.push(blue("https://example.org/event", 212.5, y, 360.0, y + 12.0));
}
let p = Page { width: 612.0, height: 792.0, blocks, images: Vec::new() };
let h = html(std::slice::from_ref(&p), "Event");
assert!(!h.contains("<table>"), "sentences became a table: {h}");
assert_eq!(h.matches("https://example.org/event").count(), 3, "{h}");
}
/// #2806: a superscript right after a number ("1" "st") continues its cell; the prize table
/// around it stays a table.
#[test]
fn a_superscript_beside_a_number_keeps_its_table() {
let mut blocks = vec![block("PLACE", 100.0, 700.0, 140.0, 712.0), block("PRIZE (euros)", 300.0, 700.0, 380.0, 712.0)];
for (n, (row, sup)) in [("1", "st"), ("2", "nd"), ("3", "rd"), ("4", "th")].iter().enumerate() {
let y = 680.0 - 20.0 * n as f64;
blocks.push(block(row, 100.0, y, 106.0, y + 12.0));
blocks.push(Block { size: 8.0, ..block(sup, 106.0, y + 5.0, 113.0, y + 13.0) });
blocks.push(block(&format!("{},000", 30 - 5 * n), 300.0, y, 340.0, y + 12.0));
}
let p = Page { width: 612.0, height: 792.0, blocks, images: Vec::new() };
let h = html(std::slice::from_ref(&p), "Prizes");
assert!(h.contains("<table>"), "the prize table was lost: {h}");
assert!(h.contains("30,000") && h.contains("15,000"), "{h}");
}
#[test]
fn two_column_body_text_is_not_mistaken_for_a_table() {
let para = |t: &str, x: f64, y: f64| Block {
parity/acrobat-features.toml
+2 -2
View File
@@ -6976,8 +6976,8 @@ milestone = "M10"
status = "partial"
commands = ["export.docx"]
tools = ["doc_export_office"]
evidence = ["crates/export/src/lib.rs::word_does_not_invent_borders_for_aligned_invoice_fields", "crates/export/src/lib.rs::word_overlap_does_not_consume_invoice_body_space", "crates/export/src/lib.rs::word_keeps_a_page_with_a_clear_image_and_big_title_in_flow", "crates/export/src/lib.rs::word_rotated_pages_keep_separate_page_sizes_and_unique_shapes", "crates/engine/src/tests.rs::office_export_positions_follow_the_displayed_crop_rotation_and_units", "crates/automation/tests/automation.rs::exporting_an_invoice_to_word_keeps_the_watermark_out_of_flow", "crates/export/src/lib.rs::docx_is_a_word_package", "crates/export/src/lib.rs::text_colour_survives_every_format", "crates/engine/src/tests.rs::exporting_office_files_keeps_text_colour", "crates/export/src/lib.rs::grid_text_becomes_a_real_table_in_every_format", "crates/export/src/lib.rs::word_opens_text_with_control_characters_and_long_pages", "crates/engine/src/tests.rs::exporting_office_files_keeps_images", "crates/automation/tests/automation.rs::exporting_to_word_html_and_rtf", "crates/ui-egui/tests/compare.rs::export_to_word_html_and_rtf"]
notes = "Flowing Word document: paragraphs, Heading 1/2 from larger text, bold/italic, text colour (fill as sRGB; gray/CMYK converted naively, colour spaces via cs/sc read as black), borderless detected tables with spans/empty cells, per-page sections/sizes, and positioned editable text/artwork only for pages with rotated text or text overlapped by an image or watermark-sized text, other pages flowing with inline images (#773); synthetic invoice regression; the emitted package validates with Open XML SDK 2.20 (Office 2010 schema). Word/LibreOffice rendering of the positioned output remains unverified. Pictures on positioned pages are DrawingML anchors behind the text (a VML rectangle with an image showed no picture, #1936; not yet opened in Word); a Word file embeds at most 1000 pictures and 512 MiB of them. The earlier flowing output was checked with macOS textutil and opened in Microsoft Word (Windows). Characters XML forbids are dropped; the page size stays within Word's 22 in. Not yet: exact font matching, vector rules, arbitrary paint-order/transparency, colour per run within a paragraph, general exact layout fidelity."
evidence = ["crates/export/src/lib.rs::word_does_not_invent_borders_for_aligned_invoice_fields", "crates/export/src/lib.rs::word_overlap_does_not_consume_invoice_body_space", "crates/export/src/lib.rs::word_keeps_a_page_with_a_clear_image_and_big_title_in_flow", "crates/export/src/lib.rs::word_rotated_pages_keep_separate_page_sizes_and_unique_shapes", "crates/engine/src/tests.rs::office_export_positions_follow_the_displayed_crop_rotation_and_units", "crates/automation/tests/automation.rs::exporting_an_invoice_to_word_keeps_the_watermark_out_of_flow", "crates/export/src/lib.rs::docx_is_a_word_package", "crates/export/src/lib.rs::text_colour_survives_every_format", "crates/engine/src/tests.rs::exporting_office_files_keeps_text_colour", "crates/export/src/lib.rs::grid_text_becomes_a_real_table_in_every_format", "crates/export/src/lib.rs::a_link_inside_a_sentence_is_not_a_table_column", "crates/export/src/lib.rs::sentences_that_run_on_into_links_are_not_a_table", "crates/export/src/lib.rs::a_superscript_beside_a_number_keeps_its_table", "crates/export/src/lib.rs::word_opens_text_with_control_characters_and_long_pages", "crates/engine/src/tests.rs::exporting_office_files_keeps_images", "crates/automation/tests/automation.rs::exporting_to_word_html_and_rtf", "crates/ui-egui/tests/compare.rs::export_to_word_html_and_rtf"]
notes = "Flowing Word document: paragraphs, Heading 1/2 from larger text, bold/italic, text colour (fill as sRGB; gray/CMYK converted naively, colour spaces via cs/sc read as black), borderless detected tables with spans/empty cells (a row whose blocks run on into each other, such as a link or superscript inside a sentence, or overlap, as a paragraph's lines do, is text and not a table row, #2806), per-page sections/sizes, and positioned editable text/artwork only for pages with rotated text or text overlapped by an image or watermark-sized text, other pages flowing with inline images (#773); synthetic invoice regression; the emitted package validates with Open XML SDK 2.20 (Office 2010 schema). Word/LibreOffice rendering of the positioned output remains unverified. Pictures on positioned pages are DrawingML anchors behind the text (a VML rectangle with an image showed no picture, #1936; not yet opened in Word); a Word file embeds at most 1000 pictures and 512 MiB of them. The earlier flowing output was checked with macOS textutil and opened in Microsoft Word (Windows). Characters XML forbids are dropped; the page size stays within Word's 22 in. Not yet: exact font matching, vector rules, arbitrary paint-order/transparency, colour per run within a paragraph, general exact layout fidelity."
[[feature]]
id = "create.export-rtf"