add DocTags serialization, revert smiles to smi to prevent confusion with plural

Signed-off-by: Panos Vagenas <[email protected]>

Author: vagenas

docling_core/transforms/serializer/doctags.py

@@ -44,6 +44,7 @@
     PictureTabularChartData,
     ProvenanceItem,
     SectionHeaderItem,
+    TableData,
     TableItem,
     TextItem,
 )
@@ -233,13 +234,22 @@ def serialize(
                     ysize=params.ysize,
                 )
 
-            classifications = [
-                ann
-                for ann in item.annotations
-                if isinstance(ann, PictureClassificationData)
-            ]
-            if len(classifications) > 0:
+            # handle classification data
+            predicted_class: Optional[str] = None
+            if item.meta and item.meta.classification:
+                predicted_class = (
+                    item.meta.classification.get_main_prediction().class_name
+                )
+            elif (
+                classifications := [
+                    ann
+                    for ann in item.annotations
+                    if isinstance(ann, PictureClassificationData)
+                ]
+            ) and classifications[0].predicted_classes:
                 predicted_class = classifications[0].predicted_classes[0].class_name
+            if predicted_class:
+                body += DocumentToken.get_picture_classification_token(predicted_class)
                 if predicted_class in [
                     PictureClassificationLabel.PIE_CHART,
                     PictureClassificationLabel.BAR_CHART,
@@ -250,26 +260,31 @@ def serialize(
                     PictureClassificationLabel.HEATMAP,
                 ]:
                     is_chart = True
-                body += DocumentToken.get_picture_classification_token(predicted_class)
 
-            smiles_annotations = [
+            # handle molecule data
+            smi: Optional[str] = None
+            if item.meta and item.meta.molecule:
+                smi = item.meta.molecule.smi
+            elif smiles_annotations := [
                 ann for ann in item.annotations if isinstance(ann, PictureMoleculeData)
-            ]
-            if len(smiles_annotations) > 0:
-                body += _wrap(
-                    text=smiles_annotations[0].smi, wrap_tag=DocumentToken.SMILES.value
-                )
-
-            tabular_chart_annotations = [
+            ]:
+                smi = smiles_annotations[0].smi
+            if smi:
+                body += _wrap(text=smi, wrap_tag=DocumentToken.SMILES.value)
+
+            # handle tabular chart data
+            chart_data: Optional[TableData] = None
+            if item.meta and item.meta.tabular_chart:
+                chart_data = item.meta.tabular_chart.chart_data
+            elif tabular_chart_annotations := [
                 ann
                 for ann in item.annotations
                 if isinstance(ann, PictureTabularChartData)
-            ]
-            if len(tabular_chart_annotations) > 0:
+            ]:
+                chart_data = tabular_chart_annotations[0].chart_data
+            if chart_data and chart_data.table_cells:
                 temp_doc = DoclingDocument(name="temp")
-                temp_table = temp_doc.add_table(
-                    data=tabular_chart_annotations[0].chart_data
-                )
+                temp_table = temp_doc.add_table(data=chart_data)
                 otsl_content = temp_table.export_to_otsl(
                     temp_doc, add_cell_location=False
                 )

docling_core/transforms/serializer/html.py

@@ -865,7 +865,7 @@ def _serialize_meta_field(self, meta: BaseMeta, name: str) -> Optional[str]:
             elif isinstance(field_val, PictureClassificationMetaField):
                 txt = self._humanize_text(field_val.get_main_prediction().class_name)
             elif isinstance(field_val, MoleculeMetaField):
-                txt = field_val.smiles
+                txt = field_val.smi
             elif isinstance(field_val, TabularChartMetaField):
                 # suppressing tabular chart serialization
                 return None

docling_core/transforms/serializer/markdown.py

@@ -313,7 +313,7 @@ def _serialize_meta_field(
             elif isinstance(field_val, PictureClassificationMetaField):
                 txt = self._humanize_text(field_val.get_main_prediction().class_name)
             elif isinstance(field_val, MoleculeMetaField):
-                txt = field_val.smiles
+                txt = field_val.smi
             elif isinstance(field_val, TabularChartMetaField):
                 # suppressing tabular chart serialization
                 return None

docling_core/types/doc/document.py

@@ -1017,7 +1017,7 @@ class SummaryMetaField(BasePrediction):
     text: str
 
 
-# NOTE: should be manually kept in sync with top-level BaseMeta hierarchy fields
+# NOTE: must be manually kept in sync with top-level BaseMeta hierarchy fields
 class MetaFieldName(str, Enum):
     """Standard meta field names."""
 
@@ -1069,7 +1069,7 @@ def get_main_prediction(self) -> PictureClassificationPrediction:
 class MoleculeMetaField(BasePrediction):
     """Molecule metadata field."""
 
-    smiles: str = Field(description="The SMILES representation of the molecule.")
+    smi: str = Field(description="The SMILES representation of the molecule.")
 
 
 class TabularChartMetaField(BasePrediction):
@@ -1643,7 +1643,7 @@ def _migrate_annotations_to_meta(cls, data: Any) -> Any:
                     data["meta"].setdefault(
                         MetaFieldName.MOLECULE.value,
                         MoleculeMetaField(
-                            smiles=ann.smi,
+                            smi=ann.smi,
                             confidence=ann.confidence,
                             created_by=ann.provenance,
                             **{

docs/DoclingDocument.json

@@ -1421,14 +1421,14 @@
           ],
           "title": "Created By"
         },
-        "smiles": {
+        "smi": {
           "description": "The SMILES representation of the molecule.",
-          "title": "Smiles",
+          "title": "Smi",
           "type": "string"
         }
       },
       "required": [
-        "smiles"
+        "smi"
       ],
       "title": "MoleculeMetaField",
       "type": "object"

test/data/doc/dummy_doc_2_prec.yaml

@@ -107,7 +107,7 @@ pictures:
         - 1.0
       - - 1.0
         - 1.0
-      smiles: CC1=NNC(C2=CN3C=CN=C3C(CC3=CC(F)=CC(F)=C3)=N2)=N1
+      smi: CC1=NNC(C2=CN3C=CN=C3C(CC3=CC(F)=CC(F)=C3)=N2)=N1
   parent:
     $ref: '#/body'
   prov:

test/data/doc/dummy_doc_with_meta_modified.yaml

@@ -107,7 +107,7 @@ pictures:
         - 1.0
       - - 1.0
         - 1.0
-      smiles: CC1=NNC(C2=CN3C=CN=C3C(CC3=CC(F)=CC(F)=C3)=N2)=N1
+      smi: CC1=NNC(C2=CN3C=CN=C3C(CC3=CC(F)=CC(F)=C3)=N2)=N1
   parent:
     $ref: '#/body'
   prov: