Skip to content

Implement table captions in tree-sitter grammar #45

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 14, 2025
Merged

Implement table captions in tree-sitter grammar #45

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2e3bf51
Implement table captions in tree-sitter grammar
cscheid Oct 14, 2025
3727cc3
remove test that tries too much
cscheid Oct 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions crates/quarto-markdown-pandoc/src/pandoc/treesitter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -712,6 +712,7 @@ fn native_visitor<T: Write>(
}
"pipe_table_delimiter_row" => process_pipe_table_delimiter_row(children, context),
"pipe_table_cell" => process_pipe_table_cell(node, children, context),
"table_caption" => PandocNativeIntermediate::IntermediateInlines(native_inlines(children)),
"pipe_table" => process_pipe_table(node, children, context),
"setext_h1_underline" => PandocNativeIntermediate::IntermediateSetextHeadingLevel(1),
"setext_h2_underline" => PandocNativeIntermediate::IntermediateSetextHeadingLevel(2),
Expand Down
28 changes: 24 additions & 4 deletions crates/quarto-markdown-pandoc/src/pandoc/treesitter_utils/pipe_table.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,6 +151,7 @@ pub fn process_pipe_table(
let mut header: Option<Row> = None;
let mut colspec: Vec<ColSpec> = Vec::new();
let mut rows: Vec<Row> = Vec::new();
let mut caption_inlines: Option<Inlines> = None;
for (node, child) in children {
if node == "block_continuation" {
continue; // skip block continuation nodes
Expand Down Expand Up @@ -179,6 +180,12 @@ pub fn process_pipe_table(
} else {
panic!("Expected Row in pipe_table_row, got {:?}", child);
}
} else if node == "table_caption" {
if let PandocNativeIntermediate::IntermediateInlines(inlines) = child {
caption_inlines = Some(inlines);
} else {
panic!("Expected Inlines in table_caption, got {:?}", child);
}
} else {
panic!("Unexpected node in pipe_table: {}", node);
}
Expand All @@ -204,12 +211,25 @@ pub fn process_pipe_table(
(vec![header.unwrap()], rows)
};

PandocNativeIntermediate::IntermediateBlock(Block::Table(Table {
attr,
caption: Caption {
// Construct caption from caption_inlines if present
let caption = if let Some(inlines) = caption_inlines {
Caption {
short: None,
long: Some(vec![Block::Plain(Plain {
content: inlines,
source_info: node_source_info_with_context(node, context),
})]),
}
} else {
Caption {
short: None,
long: None,
},
}
};

PandocNativeIntermediate::IntermediateBlock(Block::Table(Table {
attr,
caption,
colspec,
head: TableHead {
attr: empty_attr(),
Expand Down
1 change: 1 addition & 0 deletions crates/quarto-markdown-pandoc/src/pandoc/treesitter_utils/postprocess.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,6 +259,7 @@ fn transform_definition_list_div(div: Div) -> Block {
})
}


/// Apply post-processing transformations to the Pandoc AST
pub fn postprocess(doc: Pandoc) -> Result<Pandoc, Vec<String>> {
let mut errors = Vec::new();
Expand Down
6 changes: 6 additions & 0 deletions crates/quarto-markdown-pandoc/tests/snapshots/native/table-caption.qmd
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
| Name | Age |
|-------|-----|
| Alice | 30 |
| Bob | 25 |

: Sample table caption
1 change: 1 addition & 0 deletions crates/quarto-markdown-pandoc/tests/snapshots/native/table-caption.qmd.snapshot
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
[ Table ( "" , [] , [] ) (Caption Nothing [ Plain [Str "Sample", Space, Str "table", Space, Str "caption"] ]) [(AlignDefault, ColWidthDefault), (AlignDefault, ColWidthDefault)] (TableHead ( "" , [] , [] ) [Row ( "" , [] , [] ) [Cell ( "" , [] , [] ) AlignDefault (RowSpan 1) (ColSpan 1) [Plain [Str "Name"]] , Cell ( "" , [] , [] ) AlignDefault (RowSpan 1) (ColSpan 1) [Plain [Str "Age"]] ] ]) [TableBody ( "" , [] , [] ) (RowHeadColumns 0) [] [Row ( "" , [] , [] ) [Cell ( "" , [] , [] ) AlignDefault (RowSpan 1) (ColSpan 1) [Plain [Str "Alice"]] , Cell ( "" , [] , [] ) AlignDefault (RowSpan 1) (ColSpan 1) [Plain [Str "30"]] ] , Row ( "" , [] , [] ) [Cell ( "" , [] , [] ) AlignDefault (RowSpan 1) (ColSpan 1) [Plain [Str "Bob"]] , Cell ( "" , [] , [] ) AlignDefault (RowSpan 1) (ColSpan 1) [Plain [Str "25"]] ] ]] (TableFoot ( "" , [] , [] ) [] ) ]
18 changes: 17 additions & 1 deletion crates/tree-sitter-qmd/tree-sitter-markdown/grammar.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -355,7 +355,7 @@ module.exports = grammar({
),
// Some symbols get parsed as single tokens so that html blocks get detected properly
_code_line: $ => prec.right(repeat1(choice($._word, $._display_math_state_track_marker, $._inline_math_state_track_marker, $._whitespace, common.punctuation_without($, [])))),

// the gymnastics around `:` in _line exist to make the parser reject paragraphs that start with a colon.
// Those are technically valid in Markdown, but disallowing them here makes it possible to detect an
// accidentally-continued paragraph with a colon that should have been a fenced div marker.
Expand All @@ -375,8 +375,24 @@ module.exports = grammar({
$.pipe_table_delimiter_row,
repeat(seq($._pipe_table_newline, optional($.pipe_table_row))),
choice($._newline, $._eof),
optional($.table_caption),
)),

// Table caption: blank line followed by ": caption text"
// This is a Pandoc extension for table captions
table_caption: $ => prec(1, seq(
$._blank_line,
':',
optional(seq(
optional($._whitespace),
alias($._table_caption_line, $.inline)
)),
choice($._newline, $._eof),
)),

// Caption line content - similar to _line but only used in table_caption context
_table_caption_line: $ => prec.right(repeat1(choice($._word, $._display_math_state_track_marker, $._inline_math_state_track_marker, $._whitespace, common.punctuation_without($, [])))),

_pipe_table_newline: $ => seq(
$._pipe_table_line_ending,
optional($.block_continuation)
Expand Down
254 changes: 254 additions & 0 deletions crates/tree-sitter-qmd/tree-sitter-markdown/src/grammar.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4722,10 +4722,264 @@
"name": "_eof"
}
]
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "table_caption"
},
{
"type": "BLANK"
}
]
}
]
}
},
"table_caption": {
"type": "PREC",
"value": 1,
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "_blank_line"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "CHOICE",
"members": [
{
"type": "SEQ",
"members": [
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "_whitespace"
},
{
"type": "BLANK"
}
]
},
{
"type": "ALIAS",
"content": {
"type": "SYMBOL",
"name": "_table_caption_line"
},
"named": true,
"value": "inline"
}
]
},
{
"type": "BLANK"
}
]
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "_newline"
},
{
"type": "SYMBOL",
"name": "_eof"
}
]
}
]
}
},
"_table_caption_line": {
"type": "PREC_RIGHT",
"value": 0,
"content": {
"type": "REPEAT1",
"content": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "_word"
},
{
"type": "SYMBOL",
"name": "_display_math_state_track_marker"
},
{
"type": "SYMBOL",
"name": "_inline_math_state_track_marker"
},
{
"type": "SYMBOL",
"name": "_whitespace"
},
{
"type": "SEQ",
"members": [
{
"type": "CHOICE",
"members": [
{
"type": "STRING",
"value": "!"
},
{
"type": "STRING",
"value": "\""
},
{
"type": "STRING",
"value": "#"
},
{
"type": "STRING",
"value": "$"
},
{
"type": "STRING",
"value": "%"
},
{
"type": "STRING",
"value": "&"
},
{
"type": "STRING",
"value": "'"
},
{
"type": "STRING",
"value": "("
},
{
"type": "STRING",
"value": ")"
},
{
"type": "STRING",
"value": "*"
},
{
"type": "STRING",
"value": "+"
},
{
"type": "STRING",
"value": ","
},
{
"type": "STRING",
"value": "-"
},
{
"type": "STRING",
"value": "."
},
{
"type": "STRING",
"value": "/"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "STRING",
"value": ";"
},
{
"type": "STRING",
"value": "<"
},
{
"type": "STRING",
"value": "="
},
{
"type": "STRING",
"value": ">"
},
{
"type": "STRING",
"value": "?"
},
{
"type": "STRING",
"value": "@"
},
{
"type": "STRING",
"value": "["
},
{
"type": "STRING",
"value": "\\"
},
{
"type": "STRING",
"value": "]"
},
{
"type": "STRING",
"value": "^"
},
{
"type": "STRING",
"value": "_"
},
{
"type": "STRING",
"value": "`"
},
{
"type": "STRING",
"value": "{"
},
{
"type": "STRING",
"value": "|"
},
{
"type": "STRING",
"value": "}"
},
{
"type": "STRING",
"value": "~"
}
]
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "_last_token_punctuation"
},
{
"type": "BLANK"
}
]
}
]
}
]
}
}
},
"_pipe_table_newline": {
"type": "SEQ",
"members": [
Expand Down
Loading