docx: keep a paragraph's text alignment (#5498)

* docx: keep a paragraph's text alignment

w:textAlignment (ECMA-376 17.3.1.39) was not read, so a save dropped it. Word sizes a line by it when a
list's bullet is larger than the text: without it, those lines grow and every page after them moves.
ParaProps gains text_alignment, read and carried through styles, and written back after w:jc. Kept for
the file only; the layout does not use it yet.

* contributors: add entropybeater

---------

Co-authored-by: Brian <255903314+entropybeater@users.noreply.github.com>

crates/doc/src/props.rs

@@ -26,7 +26,9 @@ pub use char_props::{
     CharProps, CombineBrackets, DEFAULT_FONT_SIZE, EastAsianLayout, EmphasisMark, Highlight, Ligatures, NumChange, PropChange, Underline, VertAlign,
 };
 pub use color::{Rgb, TextColor};
-pub use para_props::{Align, Border, BorderStyle, Borders, LineSpacing, NumRef, ParaProps, TAB_POS_EPS, TabAlign, TabLeader, TabStop, TextFrame};
+pub use para_props::{
+    Align, Border, BorderStyle, Borders, LineSpacing, NumRef, ParaProps, TAB_POS_EPS, TabAlign, TabLeader, TabStop, TextAlignment, TextFrame,
+};
 pub use table_props::{
     CellPicture, CellProps, HeightRule, PictureRepeat, RowProps, TableFloat, TableLook, TableProps, TextDirection, TextVert, VAlign, VMerge,
     anchor_ooxml, valign_from_anchor,

crates/doc/src/props/para_props.rs

@@ -26,6 +26,40 @@ impl Align {
     }
 }
 
+/// Vertical alignment of characters of different sizes on a line (`w:textAlignment`,
+/// ECMA-376 §17.3.1.39).
+#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, Serialize, Deserialize)]
+#[serde(rename_all = "camelCase")]
+pub enum TextAlignment {
+    Auto,
+    Top,
+    Center,
+    Baseline,
+    Bottom,
+}
+
+impl TextAlignment {
+    pub fn ooxml(self) -> &'static str {
+        match self {
+            TextAlignment::Auto => "auto",
+            TextAlignment::Top => "top",
+            TextAlignment::Center => "center",
+            TextAlignment::Baseline => "baseline",
+            TextAlignment::Bottom => "bottom",
+        }
+    }
+    pub fn from_ooxml(s: &str) -> Option<TextAlignment> {
+        match s {
+            "auto" => Some(TextAlignment::Auto),
+            "top" => Some(TextAlignment::Top),
+            "center" => Some(TextAlignment::Center),
+            "baseline" => Some(TextAlignment::Baseline),
+            "bottom" => Some(TextAlignment::Bottom),
+            _ => None,
+        }
+    }
+}
+
 /// Line spacing rule.
 #[derive(Clone, Copy, Debug, PartialEq, Serialize, Deserialize)]
 #[serde(rename_all = "camelCase", tag = "rule", content = "value")]
@@ -398,6 +432,10 @@ pub struct ParaProps {
     /// `w:snapToGrid`: lines snap to the section's document grid. Unset = on.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub snap_to_grid: Option<bool>,
+    /// `w:textAlignment`: how characters of different sizes line up on a line. Kept for the
+    /// file (not laid out yet); Word sizes a line by it, so dropping it changes Word's pages.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub text_alignment: Option<TextAlignment>,
 }
 
 impl ParaProps {
@@ -418,7 +456,7 @@ impl ParaProps {
     }
 
     fn overlay_script_layout(&mut self, patch: &ParaProps) {
-        overlay_fields!(self, patch; bidi, kinsoku, word_wrap, overflow_punct, top_line_punct, auto_space_de, auto_space_dn);
+        overlay_fields!(self, patch; bidi, kinsoku, word_wrap, overflow_punct, top_line_punct, auto_space_de, auto_space_dn, text_alignment);
     }
     pub fn overlaid(mut self, patch: &ParaProps) -> ParaProps {
         self.overlay(patch);

crates/docx/src/read/props.rs

@@ -5,8 +5,8 @@ use std::collections::HashMap;
 use wordcraft_doc::para::cap_alt;
 use wordcraft_doc::props::{
     Align, Border, BorderStyle, Borders, CellProps, CharProps, CombineBrackets, EastAsianLayout, HeightRule, Highlight, LineSpacing, NumRef,
-    ParaProps, Rgb, RowProps, TabAlign, TabLeader, TabStop, TableFloat, TableLook, TableProps, TextColor, TextDirection, Underline, VAlign, VMerge,
-    VertAlign,
+    ParaProps, Rgb, RowProps, TabAlign, TabLeader, TabStop, TableFloat, TableLook, TableProps, TextAlignment, TextColor, TextDirection, Underline,
+    VAlign, VMerge, VertAlign,
 };
 use wordcraft_doc::section::{
     Columns, DocGrid, DocGridType, LineNumberRestart, LineNumbering, MAX_CHAR_SPACE, MAX_GRID_PITCH, NotePos, NoteProps, NoteRestart, NumFormat,
@@ -343,6 +343,7 @@ impl PropCtx {
                 "w:autoSpaceDE" => p.auto_space_de = Some(on_off(k)),
                 "w:autoSpaceDN" => p.auto_space_dn = Some(on_off(k)),
                 "w:snapToGrid" => p.snap_to_grid = Some(on_off(k)),
+                "w:textAlignment" => p.text_alignment = k.attr("w:val").and_then(TextAlignment::from_ooxml),
                 "w:framePr" => {
                     if let Some(kind @ ("drop" | "margin")) = k.attr("w:dropCap") {
                         p.drop_cap = Some(k.attr("w:lines").and_then(u32_of).unwrap_or(3).clamp(1, 10) as u8);

crates/docx/src/write/props.rs

@@ -287,6 +287,9 @@ pub fn ppr_inner(w: &mut W, p: &ParaProps, framed: bool, num_change: Option<&Cha
     if let Some(a) = p.align {
         w.val("w:jc", align_val(a));
     }
+    if let Some(t) = p.text_alignment {
+        w.val("w:textAlignment", t.ooxml());
+    }
     if let Some(l) = p.outline_level {
         w.val("w:outlineLvl", &n(l.min(9) as i64));
     }

crates/docx/tests/it/main.rs

@@ -33,6 +33,7 @@ mod section_page_number_type;
 mod section_text_direction;
 mod section_valign;
 mod settings_merge;
+mod text_alignment;
 mod text_boxes;
 mod toc_ranges;
 mod undefined_style;

crates/docx/tests/it/roundtrip.rs

@@ -7,7 +7,7 @@ use wordcraft_doc::numbering::ListKind;
 use wordcraft_doc::para::{Anchor, Float, FloatAlign, NoteKind, ShapeKind, Wrap};
 use wordcraft_doc::props::{
     Align, Border, BorderStyle, Borders, CharProps, HeightRule, Highlight, LineSpacing, NumRef, ParaProps, Rgb, RowProps, TabAlign, TabLeader,
-    TabStop, TableLook, TextColor, TextDirection, Underline, VAlign, VMerge, VertAlign,
+    TabStop, TableLook, TextAlignment, TextColor, TextDirection, Underline, VAlign, VMerge, VertAlign,
 };
 use wordcraft_doc::section::{Columns, DocGrid, DocGridType, LineNumberRestart, LineNumbering, NumFormat, PageVAlign, SectionProps, SectionStart};
 use wordcraft_doc::styles::{Style, StyleKind};
@@ -221,6 +221,7 @@ fn every_para_prop_round_trips() {
         num_change: None,
         fmt_change: None,
         snap_to_grid: Some(false),
+        text_alignment: Some(TextAlignment::Top),
     };
     let variants = [
         ParaProps { line_spacing: Some(LineSpacing::AtLeast(14.0)), indent_first: Some(24.0), align: Some(Align::Center), ..Default::default() },

crates/docx/tests/it/text_alignment.rs

@@ -0,0 +1,64 @@
+//! A paragraph's vertical text alignment (`w:textAlignment`, ECMA-376 Part 1 §17.3.1.39, values
+//! from ST_TextAlignment): read and written back as read, in the schema's place after `w:jc`.
+//! Word sizes a line by it when a list label is larger than the text, so a save that drops it
+//! moves every line after. Fixtures are hand-written from the spec.
+
+use std::io::{Read, Write};
+
+use wordcraft_doc::props::TextAlignment;
+
+fn docx(body: &str) -> Vec<u8> {
+    let root = r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>"#;
+    let doc = format!(
+        r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body>{body}</w:body></w:document>"#
+    );
+    let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+    for (name, bytes) in [("_rels/.rels", root.as_bytes()), ("word/document.xml", doc.as_bytes())] {
+        zw.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
+        zw.write_all(bytes).unwrap();
+    }
+    zw.finish().unwrap().into_inner()
+}
+
+fn document_xml(bytes: &[u8]) -> String {
+    let mut z = zip::ZipArchive::new(std::io::Cursor::new(bytes)).unwrap();
+    let mut s = String::new();
+    z.by_name("word/document.xml").unwrap().read_to_string(&mut s).unwrap();
+    s
+}
+
+#[test]
+fn text_alignment_is_written_back_as_read() {
+    let para = |ppr: &str, text: &str| format!(r#"<w:p><w:pPr>{ppr}</w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#);
+    let body = [
+        para(r#"<w:jc w:val="center"/><w:textAlignment w:val="top"/><w:outlineLvl w:val="1"/>"#, "A"),
+        para(r#"<w:textAlignment w:val="center"/>"#, "B"),
+        para(r#"<w:textAlignment w:val="baseline"/>"#, "C"),
+        para(r#"<w:textAlignment w:val="bottom"/>"#, "D"),
+        para(r#"<w:textAlignment w:val="auto"/>"#, "E"),
+        para(r#"<w:textAlignment w:val="sideways"/>"#, "F"),
+        para("", "G"),
+    ]
+    .concat();
+    let d = wordcraft_docx::read(&docx(&body)).unwrap();
+    let got: Vec<Option<TextAlignment>> = d.body.iter().filter_map(|b| b.as_para()).map(|p| p.props.text_alignment).collect();
+    let want = vec![
+        Some(TextAlignment::Top),
+        Some(TextAlignment::Center),
+        Some(TextAlignment::Baseline),
+        Some(TextAlignment::Bottom),
+        Some(TextAlignment::Auto),
+        None,
+        None,
+    ];
+    assert_eq!(got, want);
+    let out = wordcraft_docx::write(&d).unwrap();
+    let xml = document_xml(&out);
+    assert!(xml.contains(r#"<w:jc w:val="center"/><w:textAlignment w:val="top"/><w:outlineLvl w:val="1"/>"#), "{xml}");
+    for v in ["center", "baseline", "bottom", "auto"] {
+        assert_eq!(xml.matches(&format!(r#"<w:textAlignment w:val="{v}"/>"#)).count(), 1, "{v}: {xml}");
+    }
+    assert_eq!(xml.matches("w:textAlignment").count(), 5, "an unknown value and none write nothing: {xml}");
+    let back = wordcraft_docx::read(&out).unwrap();
+    assert_eq!(back.body.iter().filter_map(|b| b.as_para()).map(|p| p.props.text_alignment).collect::<Vec<_>>(), want);
+}