fix(docx): split multiple OMML equations into separate formula items

docling/backend/msword_backend.py

@@ -906,21 +906,56 @@ def _handle_equations_in_text(self, element, text):
         only_texts = []
         only_equations = []
         texts_and_equations = []
-        for subt in element.iter():
-            tag_name = etree.QName(subt).localname
-            if tag_name == "t" and "math" not in subt.tag:
-                if isinstance(subt.text, str):
-                    only_texts.append(subt.text)
-                    texts_and_equations.append(subt.text)
-            elif "oMath" in subt.tag and "oMathPara" not in subt.tag:
-                latex_equation = str(oMath2Latex(subt)).strip()
-                if len(latex_equation) > 0:
-                    only_equations.append(
-                        self.equation_bookends.format(EQ=latex_equation)
-                    )
-                    texts_and_equations.append(
-                        self.equation_bookends.format(EQ=latex_equation)
-                    )
+
+        # Collect oMath elements and text runs from the paragraph.
+        # Use direct children iteration first; fall back to deep iteration
+        # only if no oMath elements are found at the direct level.
+        direct_omaths = [
+            child
+            for child in element
+            if "oMath" in child.tag and "oMathPara" not in child.tag
+        ]
+
+        if direct_omaths:
+            # Iterate direct children to preserve sibling order and avoid
+            # processing nested oMath descendants of an already-converted node.
+            for child in element:
+                tag_name = etree.QName(child).localname
+                if "oMath" in child.tag and "oMathPara" not in child.tag:
+                    latex_equation = str(oMath2Latex(child)).strip()
+                    if len(latex_equation) > 0:
+                        only_equations.append(
+                            self.equation_bookends.format(EQ=latex_equation)
+                        )
+                        texts_and_equations.append(
+                            self.equation_bookends.format(EQ=latex_equation)
+                        )
+                else:
+                    # Collect text from non-math children (e.g. <w:r> runs)
+                    for t_elem in child.iter():
+                        t_tag = etree.QName(t_elem).localname
+                        if t_tag == "t" and "math" not in t_elem.tag:
+                            if isinstance(t_elem.text, str):
+                                only_texts.append(t_elem.text)
+                                texts_and_equations.append(t_elem.text)
+        else:
+            # Original deep-iteration fallback for nested oMath (e.g.
+            # inside oMathPara or other wrapper elements).
+            for subt in element.iter():
+                tag_name = etree.QName(subt).localname
+                if tag_name == "t" and "math" not in subt.tag:
+                    if isinstance(subt.text, str):
+                        only_texts.append(subt.text)
+                        texts_and_equations.append(subt.text)
+                elif "oMath" in subt.tag and "oMathPara" not in subt.tag:
+                    latex_equation = str(oMath2Latex(subt)).strip()
+                    if len(latex_equation) > 0:
+                        only_equations.append(
+                            self.equation_bookends.format(EQ=latex_equation)
+                        )
+                        texts_and_equations.append(
+                            self.equation_bookends.format(EQ=latex_equation)
+                        )
 
         if len(only_equations) < 1:
             return text, []
@@ -1055,15 +1090,28 @@ def _handle_text_elements(
             if (paragraph.text is None or len(paragraph.text.strip()) == 0) and len(
                 text
             ) > 0:
-                # Standalone equation
+                # Standalone equation(s) — emit each as a separate formula
                 level = self._get_level()
-                t1 = doc.add_text(
-                    label=DocItemLabel.FORMULA,
-                    parent=self.parents[level - 1],
-                    text=text.replace("<eq>", "").replace("</eq>", ""),
-                    content_layer=self.content_layer,
-                )
-                elem_ref.append(t1.get_ref())
+                parent = self.parents[level - 1]
+                if len(equations) > 1:
+                    for eq in equations:
+                        eq_text = eq.replace("<eq>", "").replace("</eq>", "").strip()
+                        if len(eq_text) > 0:
+                            t1 = doc.add_text(
+                                label=DocItemLabel.FORMULA,
+                                parent=parent,
+                                text=eq_text,
+                                content_layer=self.content_layer,
+                            )
+                            elem_ref.append(t1.get_ref())
+                else:
+                    t1 = doc.add_text(
+                        label=DocItemLabel.FORMULA,
+                        parent=parent,
+                        text=text.replace("<eq>", "").replace("</eq>", ""),
+                        content_layer=self.content_layer,
+                    )
+                    elem_ref.append(t1.get_ref())
             else:
                 # Inline equation
                 level = self._get_level()

tests/data/groundtruth/docling_v2/omml_multi_equation_paragraph.docx.itxt

@@ -0,0 +1,7 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: section: group header-0
+    item-2 at level 2: section_header: Issue 3: Concatenated equation blocks
+      item-3 at level 3: text: The paragraph below contains thr ... ts are siblings inside a single <w:p>.
+      item-4 at level 3: formula: a=b
+      item-5 at level 3: formula: c=d
+      item-6 at level 3: formula: e=f

tests/data/groundtruth/docling_v2/omml_multi_equation_paragraph.docx.json

@@ -0,0 +1,132 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.9.0",
+  "name": "omml_multi_equation_paragraph",
+  "origin": {
+    "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    "binary_hash": 17520448227351822398,
+    "filename": "omml_multi_equation_paragraph.docx"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/groups/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/0"
+        }
+      ],
+      "content_layer": "body",
+      "name": "header-0",
+      "label": "section"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/texts/2"
+        },
+        {
+          "$ref": "#/texts/3"
+        },
+        {
+          "$ref": "#/texts/4"
+        }
+      ],
+      "content_layer": "body",
+      "label": "section_header",
+      "prov": [],
+      "orig": "Issue 3: Concatenated equation blocks",
+      "text": "Issue 3: Concatenated equation blocks",
+      "level": 1
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "The paragraph below contains three separate <m:oMath> elements.\nExpected: three separate $$ blocks ($$a = b$$, $$c = d$$, $$e = f$$)\nDocling produces: one $$ block with all equations concatenated.\n\nAll three <m:oMath> elements are siblings inside a single <w:p>.",
+      "text": "The paragraph below contains three separate <m:oMath> elements.\nExpected: three separate $$ blocks ($$a = b$$, $$c = d$$, $$e = f$$)\nDocling produces: one $$ block with all equations concatenated.\n\nAll three <m:oMath> elements are siblings inside a single <w:p>.",
+      "formatting": {
+        "bold": false,
+        "italic": false,
+        "underline": false,
+        "strikethrough": false,
+        "script": "baseline"
+      }
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "formula",
+      "prov": [],
+      "orig": "a=b",
+      "text": "a=b"
+    },
+    {
+      "self_ref": "#/texts/3",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "formula",
+      "prov": [],
+      "orig": "c=d",
+      "text": "c=d"
+    },
+    {
+      "self_ref": "#/texts/4",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "formula",
+      "prov": [],
+      "orig": "e=f",
+      "text": "e=f"
+    }
+  ],
+  "pictures": [],
+  "tables": [],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {}
+}

tests/data/groundtruth/docling_v2/omml_multi_equation_paragraph.docx.md

@@ -0,0 +1,13 @@
+## Issue 3: Concatenated equation blocks
+
+The paragraph below contains three separate <m:oMath> elements.
+Expected: three separate $$ blocks ($$a = b$$, $$c = d$$, $$e = f$$)
+Docling produces: one $$ block with all equations concatenated.
+
+All three <m:oMath> elements are siblings inside a single <w:p>.
+
+$$a=b$$
+
+$$c=d$$
+
+$$e=f$$