@ai-matrx/content-ir 0.19.8 → 0.19.9

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.19.9
+### Unreleased
+
+- `/source` **A table ends where GFM ends it (verify-RC-B4 round 9):** `continuesTable` / `findTableEnd` end a table at an HTML block start (all seven CommonMark 4.6 conditions — `<script`/`<pre`/`<style`/`<textarea`, `<!--`, `<?`, `<!X`, `<![CDATA[`, a block tag name, or any other complete tag alone on its line such as `</artifact>`) and at indented code: a line 4+ columns past the table's container. New `startsHtmlBlock`, `lineIndent`, `tableContainerIndent` (the content column of the list item a table sits in); `continuesTable(line, containerIndent = 0)`. A lone `|` is a row (one empty cell) — `rowCells("|")` is `[""]`, no longer `[]`. Since 0.19.4 an HTML line or an indented line after a table was read as a table row. Shared vectors gain `tableEnds` (30 cases, each judged against remark-gfm in matrx-frontend); the Python twin moved with them.
+- `/source` **A table never opens on a lazy continuation line (verify-RC-B4 round 9):** `opensTable` / `tableStartsAt` / `findTableStart` refuse a header that lazily continues a list item's or a block quote's paragraph (no blank line above, not indented to the item's content column, or missing the quote's `>`) — GFM reads it as paragraph text (`- item` then `| a | b |` is no table). Vectors gain `tableStarts` (15 cases, judged against remark-gfm).
+
 ## 0.19.8
 
 Automatic changed-only republish (docs/metadata drift since the last tag — see

package/dist/index.cjs

@@ -7687,14 +7687,61 @@ function rowCells(line) {
   const cells = splitRowSegments(line).map((cell) => cell.trim());
   if (cells.length > 1 && cells[0] === "") cells.shift();
   if (cells.length > 1 && cells[cells.length - 1] === "") cells.pop();
-  else if (cells.length === 1 && cells[0] === "") cells.pop();
+  else if (cells.length === 1 && cells[0] === "" && !line.includes("|")) cells.pop();
   return cells;
 }
 function unescapeCellPipes(cell) {
   return cell.replace(/\\\|/g, "|");
 }
 var BLOCK_START = /^(?:[-+*](?:\s|$)|\d{1,9}[.)](?:\s|$)|>|#{1,6}(?:\s|$)|(?:-\s*){3,}$|(?:\*\s*){3,}$|(?:_\s*){3,}$)/;
-var startsBlock = (trimmed) => BLOCK_START.test(trimmed) || opensStrictFence(trimmed);
+var startsBlock = (trimmed) => BLOCK_START.test(trimmed) || opensStrictFence(trimmed) || startsHtmlBlock(trimmed);
+var HTML_RAW = /^<(?:script|pre|style|textarea)(?:[\s>]|$)/i;
+var HTML_COMMENT_ETC = /^(?:<!--|<\?|<![A-Za-z]|<!\[CDATA\[)/;
+var HTML_BLOCK_NAMES = "address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h[1-6]|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|search|section|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul";
+var HTML_BLOCK_TAG = new RegExp(`^</?(?:${HTML_BLOCK_NAMES})(?:[\\s>]|/>|$)`, "i");
+var ATTRIBUTE = `\\s+[A-Za-z_:][A-Za-z0-9_.:-]*(?:\\s*=\\s*(?:[^\\s"'=<>\`]+|'[^']*'|"[^"]*"))?`;
+var HTML_COMPLETE_TAG = new RegExp(`^(?:<[A-Za-z][A-Za-z0-9-]*(?:${ATTRIBUTE})*\\s*/?>|</[A-Za-z][A-Za-z0-9-]*\\s*>)\\s*$`);
+function startsHtmlBlock(trimmed) {
+  if (!trimmed.startsWith("<")) return false;
+  return HTML_RAW.test(trimmed) || HTML_COMMENT_ETC.test(trimmed) || HTML_BLOCK_TAG.test(trimmed) || HTML_COMPLETE_TAG.test(trimmed);
+}
+function lineIndent(line) {
+  let column = 0;
+  for (const ch of line) {
+    if (ch === " ") column += 1;
+    else if (ch === "	") column += 4 - column % 4;
+    else break;
+  }
+  return column;
+}
+var LIST_MARKER = /^([ \t]*)([-+*]|\d{1,9}[.)])([ \t]+|$)/;
+function markerContentColumn(marker) {
+  const markerEnd = lineIndent(marker[1] ?? "") + (marker[2] ?? "").length;
+  const gap = marker[3] ? lineIndent(" ".repeat(markerEnd) + marker[3]) - markerEnd : 1;
+  return markerEnd + (gap >= 1 && gap <= 4 ? gap : 1);
+}
+function tableContainerIndent(lines, start) {
+  return tableContainerIndentOf(lines, start, false);
+}
+function tableContainerIndentOf(lines, start, ownItem) {
+  const own = ownItem ? LIST_MARKER.exec(lines[start] ?? "") : null;
+  if (own) return markerContentColumn(own);
+  const header = lineIndent(lines[start] ?? "");
+  if (header === 0) return 0;
+  for (let k = start - 1; k >= 0; k -= 1) {
+    const line = lines[k] ?? "";
+    if (!line.trim()) continue;
+    const indent = lineIndent(line);
+    const marker = LIST_MARKER.exec(line);
+    if (marker && indent < header) {
+      const content = markerContentColumn(marker);
+      if (content <= header) return content;
+      continue;
+    }
+    if (indent === 0) return 0;
+  }
+  return 0;
+}
 var DELIMITER_CELL = /^:?-+:?$/;
 function isGfmDelimiterRow(line) {
   const trimmed = line.trim();
@@ -7713,14 +7760,42 @@ function startsPipelessTable(header, delimiter) {
   if (delimiter === void 0 || !isGfmDelimiterRow(delimiter)) return false;
   return rowCells(head).length === rowCells(delimiter.trim()).length;
 }
-function continuesTable(line) {
+function continuesTable(line, containerIndent = 0) {
   const trimmed = line.trim();
   if (!trimmed) return false;
+  if (lineIndent(line) - containerIndent >= 4) return false;
   return trimmed.startsWith("|") || !startsBlock(trimmed);
 }
 function opensTable(lines, index) {
   const line = lines[index] ?? "";
-  return isPipeLedRow(line) || startsPipelessTable(line, lines[index + 1]);
+  if (!isPipeLedRow(line) && !startsPipelessTable(line, lines[index + 1])) return false;
+  return !isLazyContinuation(lines, index);
+}
+var QUOTE_LINE = /^ {0,3}>/;
+var THEMATIC_BREAK = /^(?:(?:-[ \t]*){3,}|(?:\*[ \t]*){3,}|(?:_[ \t]*){3,})$/;
+var breaksParagraph = (trimmed) => /^#{1,6}(?:\s|$)/.test(trimmed) || THEMATIC_BREAK.test(trimmed) || opensStrictFence(trimmed) || startsHtmlBlock(trimmed);
+function isLazyContinuation(lines, index) {
+  const header = lines[index] ?? "";
+  let first = -1;
+  for (let k = index - 1; k >= 0; k -= 1) {
+    const line = lines[k] ?? "";
+    const trimmed = line.trim();
+    if (!trimmed) break;
+    if (breaksParagraph(trimmed)) break;
+    const marker = LIST_MARKER.exec(line);
+    if (marker) {
+      const rest = line.slice(marker[0].length).trim();
+      if (!rest || breaksParagraph(rest)) break;
+      first = k;
+      break;
+    }
+    first = k;
+    if (QUOTE_LINE.test(line)) break;
+  }
+  if (first < 0) return false;
+  const start = lines[first] ?? "";
+  if (QUOTE_LINE.test(start)) return !QUOTE_LINE.test(header);
+  return lineIndent(header) < tableContainerIndentOf(lines, first, true);
 }
 function tableStartsAt(lines, index) {
   return opensTable(lines, index) && isGfmDelimiterRow(lines[index + 1] ?? "");
@@ -7730,8 +7805,9 @@ function findTableStart(lines, from = 0) {
   return -1;
 }
 function findTableEnd(lines, start) {
+  const container = tableContainerIndent(lines, start);
   let end = Math.min(lines.length, start + 2);
-  while (end < lines.length && continuesTable(lines[end] ?? "")) end += 1;
+  while (end < lines.length && continuesTable(lines[end] ?? "", container)) end += 1;
   return end;
 }
 
@@ -7847,6 +7923,7 @@ exports.kindSchemaToJsonSchema = kindSchemaToJsonSchema;
 exports.kindSchemaToStorage = kindSchemaToStorage;
 exports.kindVerdictOf = kindVerdictOf;
 exports.legacyShellUses = legacyShellUses;
+exports.lineIndent = lineIndent;
 exports.listIslands = listIslands;
 exports.looksLikeDirectiveHead = looksLikeDirectiveHead;
 exports.looksLikeDisplayMath = looksLikeDisplayMath;
@@ -7895,9 +7972,11 @@ exports.singleDollarMathEnd = singleDollarMathEnd;
 exports.spliceSave = spliceSave;
 exports.splitRowSegments = splitRowSegments;
 exports.splitsSurrogatePair = splitsSurrogatePair;
+exports.startsHtmlBlock = startsHtmlBlock;
 exports.startsPipelessTable = startsPipelessTable;
 exports.storageToKindSchema = storageToKindSchema;
 exports.stripKindDeep = stripKindDeep;
+exports.tableContainerIndent = tableContainerIndent;
 exports.tableStartsAt = tableStartsAt;
 exports.titleCaseToken = titleCaseToken;
 exports.toCodePointOffset = toCodePointOffset;