#3166: a web page's table keeps its characters, its shown text and its header formats

Addresses CodeRabbit review on #3223:
- "Decode HTML before parsing its cells": a page in Windows-1252 read as
  lossy UTF-8, so "Café" lost its é. The page is now decoded as a CSV is
  (BOM, UTF-8, else Windows-1252/1256); decode_text is exported for it.
- "Keep visible cell text when csv_as_text is enabled": opened as text, a
  cell with x:num took the recorded number ("4,50" became "4.5"). The
  recorded number is used only when values are read.
- "Preserve the imported format when styling a header": a date in a <th>
  lost its date format when made bold and centred. Header styling now
  builds on the style the CSV reader gave the cell.

Test: a_web_page_table_keeps_its_characters_text_and_header_formats.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

crates/engine/src/io.rs

@@ -355,7 +355,8 @@ fn part_too_large_message(name: &str, part: &str, size: u64) -> String {
 /// header cells (`<th>`) are bold and centred, and the sheet takes the name the page gives it
 /// (`<x:Name>`) or the file's. `None` when the bytes aren't such a page.
 fn read_html_table(name: &str, kind: Option<FileKind>, bytes: &[u8], csv_as_text: bool) -> Option<Result<(Workbook, Vec<String>)>> {
-    let text = String::from_utf8_lossy(bytes);
+    // Decoded as a CSV is (BOM, UTF-8, else Windows-1252/1256), so a legacy page keeps its letters.
+    let text = gridcraft_xlsx::decode_text(bytes);
     let head: String = text.trim_start_matches('\u{feff}').trim_start().chars().take(16).collect::<String>().to_ascii_lowercase();
     if !["<!doctype html", "<html", "<table", "<head", "<body", "<meta"].iter().any(|t| head.starts_with(t)) {
         return None;
@@ -370,7 +371,9 @@ fn read_html_table(name: &str, kind: Option<FileKind>, bytes: &[u8], csv_as_text
         let fields: Vec<String> = row
             .iter()
             .map(|cell| {
-                let field = match cell.num {
+                // The number the page recorded (`x:num`) only when values are read; as text, the
+                // cell keeps the text it shows.
+                let field = match cell.num.filter(|_| !csv_as_text) {
                     Some(n) => gridcraft_core::number_to_text(n),
                     None => cell.text.split_whitespace().collect::<Vec<_>>().join(" "),
                 };
@@ -384,17 +387,24 @@ fn read_html_table(name: &str, kind: Option<FileKind>, bytes: &[u8], csv_as_text
     let read = gridcraft_xlsx::read_csv_with_report(tsv.as_bytes(), &opts).map_err(|e| EngineError::Other(e.to_string()));
     Some(read.map(|(mut wb, report)| {
         wb.csv_delimiter = None;
-        let header_style = wb.styles.derive(gridcraft_model::StyleId::DEFAULT, |st| {
-            st.font.bold = true;
-            st.align.h = gridcraft_model::HAlign::Center;
-        });
-        if let Some(sh) = wb.sheet_mut(0) {
-            for (r, row) in rows.iter().enumerate() {
-                for (c, cell) in row.iter().enumerate() {
-                    if cell.header && !cell.text.trim().is_empty() {
-                        sh.set_style(CellRef::new(r as u32, c as u32), header_style);
-                    }
-                }
+        // Header cells are bold and centred on top of the style the CSV reader gave them, so a
+        // date in a header keeps its date format.
+        let headers: Vec<CellRef> = rows
+            .iter()
+            .enumerate()
+            .flat_map(|(r, row)| row.iter().enumerate().filter(|(_, cell)| cell.header && !cell.text.trim().is_empty()).map(move |(c, _)| CellRef::new(r as u32, c as u32)))
+            .collect();
+        let mut bold: std::collections::HashMap<gridcraft_model::StyleId, gridcraft_model::StyleId> = std::collections::HashMap::new();
+        for at in headers {
+            let Some(base) = wb.sheet(0).map(|sh| sh.style_id(at)) else { continue };
+            let id = *bold.entry(base).or_insert_with(|| {
+                wb.styles.derive(base, |st| {
+                    st.font.bold = true;
+                    st.align.h = gridcraft_model::HAlign::Center;
+                })
+            });
+            if let Some(sh) = wb.sheet_mut(0) {
+                sh.set_style(at, id);
             }
         }
         let page_name = find_between(&text, "<x:Name>", "</x:Name>").map(|n| crate::clip_html::normalized(n.trim()));

crates/engine/src/io/tests.rs

@@ -636,3 +636,23 @@ fn a_web_page_saved_as_xls_opens_its_table() {
     let (wb, _) = open_bytes("notes.csv", b"<b>,1\nx,2\n").unwrap();
     assert_eq!(wb.sheet(0).unwrap().value(CellRef::parse("B2").unwrap()), gridcraft_core::Value::number(2.0));
 }
+
+#[test]
+fn a_web_page_table_keeps_its_characters_text_and_header_formats() {
+    // A page saved in Windows-1252 keeps its accented letters (it read as replacement characters).
+    let mut page = b"<html><body><table><tr><th>Caf".to_vec();
+    page.push(0xE9);
+    page.extend_from_slice(b"</th><th>2024-01-15</th></tr><tr><td>Plum</td><td x:num=\"4.5\">4,50</td></tr></table></body></html>");
+    let (wb, _) = open_bytes("menu.xls", &page).unwrap();
+    let sh = wb.sheet(0).unwrap();
+    assert_eq!(sh.value(CellRef::parse("A1").unwrap()), gridcraft_core::Value::text("Café"));
+    // A date in a header cell stays a date, bold and centred (its format was replaced).
+    let b1 = wb.styles.get(sh.style_id(CellRef::parse("B1").unwrap()));
+    assert!(matches!(sh.value(CellRef::parse("B1").unwrap()), gridcraft_core::Value::Number(_)));
+    assert!(b1.font.bold && b1.align.h == gridcraft_model::HAlign::Center);
+    assert_ne!(b1.num_fmt.as_str(), "General", "the date keeps its date format");
+    assert_eq!(sh.value(CellRef::parse("B2").unwrap()), gridcraft_core::Value::number(4.5));
+    // Opened as text, a cell keeps the text it shows, not the number the page recorded for it.
+    let (wb, _) = open_bytes_with("menu.xls", &page, None, true).unwrap();
+    assert_eq!(wb.sheet(0).unwrap().value(CellRef::parse("B2").unwrap()), gridcraft_core::Value::text("4,50"));
+}

crates/xlsx/src/lib.rs

@@ -47,7 +47,7 @@ use gridcraft_core::DateSystem;
 use gridcraft_model::Workbook;
 
 pub use crypto::{DecryptError, check_encryption, decrypt};
-pub use csv::{MAX_CSV_BYTES, read_csv, read_csv_with_report, write_csv, write_csv_limited};
+pub use csv::{MAX_CSV_BYTES, decode_text, read_csv, read_csv_with_report, write_csv, write_csv_limited};
 pub use ods::read_ods;
 pub use package::MAX_PART;
 pub use passthrough::rebase_links;