first attempt at updating the schemas

Signed-off-by: Peter Staar <[email protected]>

docling_core/resources/schemas/generated/ccs_document_schema.json

@@ -1,5 +1,5 @@
 {
-  "title": "ExportedCCSDocument",
+  "title": "ExportedDocument",
   "type": "object",
   "properties": {
     "name": {
@@ -16,10 +16,10 @@
       "type": "string"
     },
     "description": {
-      "$ref": "#/definitions/CCSDocumentDescription"
+      "$ref": "#/definitions/DocumentDescription"
     },
     "file-info": {
-      "$ref": "#/definitions/CCSFileInfoObject"
+      "$ref": "#/definitions/FileInfoObject"
     },
     "main-text": {
       "title": "Main-Text",
@@ -274,8 +274,8 @@
         "date"
       ]
     },
-    "CCSDocumentDescription": {
-      "title": "CCSDocumentDescription",
+    "DocumentDescription": {
+      "title": "DocumentDescription",
       "type": "object",
       "properties": {
         "title": {
@@ -414,8 +414,8 @@
         "logs"
       ]
     },
-    "CCSFileInfoDescription": {
-      "title": "CCSFileInfoDescription",
+    "FileInfoDescription": {
+      "title": "FileInfoDescription",
       "type": "object",
       "properties": {
         "author": {
@@ -462,8 +462,8 @@
         "page"
       ]
     },
-    "CCSFileInfoObject": {
-      "title": "CCSFileInfoObject",
+    "FileInfoObject": {
+      "title": "FileInfoObject",
       "type": "object",
       "properties": {
         "filename": {
@@ -487,7 +487,7 @@
           "type": "string"
         },
         "description": {
-          "$ref": "#/definitions/CCSFileInfoDescription"
+          "$ref": "#/definitions/FileInfoDescription"
         },
         "page-hashes": {
           "title": "Page-Hashes",
@@ -1068,4 +1068,4 @@
       }
     }
   }
-}
+}

docling_core/resources/schemas/generated/minimal_document_schema_flat.json

@@ -12,7 +12,7 @@
       "type": "string"
     },
     "description": {
-      "title": "CCSDocumentDescription",
+      "title": "DocumentDescription",
       "type": "object",
       "properties": {
         "title": {
@@ -1126,4 +1126,4 @@
     "file-info",
     "main-text"
   ]
-}
+}

docling_core/search/meta.py

@@ -18,7 +18,7 @@
 
 
 class S3Path(BaseModel, extra="forbid"):
-    """The path details within a cloud object storage for CCS-parsed files."""
+    """The path details within a cloud object storage for Documents."""
 
     bucket: StrictStr
     prefix: StrictStr
@@ -30,7 +30,7 @@ def __hash__(self):
 
 
 class S3CcsData(BaseModel, extra="forbid"):
-    """The access details to a cloud object storage for CCS-parsed files."""
+    """The access details to a cloud object storage for Documents."""
 
     endpoint: StrictStr
     paths: UniqueList[S3Path] = Field(min_length=1)

docling_core/types/__init__.py

@@ -17,9 +17,9 @@
     Ref,
 )
 from docling_core.types.doc.document import (  # noqa
-    CCSDocumentDescription as DocumentDescription,
+    DocumentDescription as DocumentDescription,
 )
-from docling_core.types.doc.document import CCSFileInfoObject as FileInfoObject  # noqa
-from docling_core.types.doc.document import ExportedCCSDocument as Document  # noqa
+from docling_core.types.doc.document import FileInfoObject as FileInfoObject  # noqa
+from docling_core.types.doc.document import LayoutDocument as Document  # noqa
 from docling_core.types.gen.generic import Generic  # noqa
 from docling_core.types.rec.record import Record  # noqa

docling_core/types/base.py

@@ -122,7 +122,7 @@ class Log(AliasModel, extra="forbid"):
         json_schema_extra=es_field(type="keyword", ignore_above=8191),
     )
     agent: StrictStr = Field(
-        description="The Docling agent that performed the task, e.g., CCS or CXS.",
+        description="The Docling agent that performed the task.",
         json_schema_extra=es_field(type="keyword", ignore_above=8191),
     )
     type_: StrictStr = Field(

docling_core/types/doc/base.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: MIT
 #
 
-"""Define common models across CCS objects."""
+"""Define common models across Documents."""
 from typing import Annotated, Literal, Optional, Union
 
 from pydantic import BaseModel, Field, PositiveInt, StrictStr

docling_core/types/doc/doc_ann.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: MIT
 #
 
-"""Models for annotations and predictions in CCS."""
+"""Models for annotations and predictions on Documents."""
 from typing import Any
 
 from pydantic import BaseModel

docling_core/types/doc/doc_ocr.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: MIT
 #
 
-"""Models for CCS objects with OCR."""
+"""Models for Document objects with OCR."""
 from typing import Any, Dict, List, Literal
 
 from pydantic import BaseModel, Field

docling_core/types/doc/doc_raw.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: MIT
 #
 
-"""Models for CCS objects in raw format."""
+"""Models for Document objects in raw format."""
 from typing import Any, List, Optional
 
 from pydantic import BaseModel, Field

docling_core/types/doc/document.py

@@ -54,7 +54,7 @@ class FileInfoDescription(BaseModel, extra="forbid"):
     creation_date: Optional[str] = None  # datetime
 
 
-class FileInfoObject(FileInfoObject, extra="forbid"):
+class LayoutFileInfoObject(FileInfoObject, extra="forbid"):
     """File info object."""
 
     num_pages: Optional[int] = Field(default=None, alias="#-pages")
@@ -260,7 +260,7 @@ class SimpleDocument(
         CollectionNameTypeT,
     ],
 ):
-    """Minimal model for a document."""
+    """Simple model for a document."""
 
     name: StrictStr = Field(alias="_name")
     obj_type: Optional[StrictStr] = Field("document", alias="type")
@@ -280,7 +280,7 @@ class SimpleDocument(
 
 
 class LayoutDocument(
-    MinimalDocument,
+    SimpleDocument,
     Generic[
         DescriptionAdvancedT,
         DescriptionAnalyticsT,
@@ -361,7 +361,12 @@ def export_to_markdown(
         delim: str = "\n\n",
         main_text_start: int = 0,
         main_text_stop: Optional[int] = None,
-        main_text_labels: Optional[List[str]] = ["title", "subtitle-level-1", "paragraph", "caption"]     
+        main_text_labels: list[str] = [
+            "title",
+            "subtitle-level-1",
+            "paragraph",
+            "caption",
+        ],
     ) -> str:
         r"""Serialize to Markdown.
 

test/data/json_schemas/base_log.json

@@ -18,7 +18,7 @@
       "x-es-type": "keyword"
     },
     "agent": {
-      "description": "The Docling agent that performed the task, e.g., CCS or CXS.",
+      "description": "The Docling agent that performed the task.",
       "title": "Agent",
       "type": "string",
       "x-es-ignore_above": 8191,
@@ -58,4 +58,4 @@
   ],
   "title": "Log",
   "type": "object"
-}
+}

test/test_base.py

@@ -20,7 +20,7 @@
     Log,
     StrictDateTime,
 )
-from docling_core.types.doc.document import CCSDocumentDescription
+from docling_core.types.doc.document import DocumentDescription
 from docling_core.types.rec.record import RecordDescription
 
 
@@ -215,11 +215,11 @@ def test_collection_document_info():
             "alias": ["patent"],
         },
     }
-    CCSDocumentDescription(**desc_dict)
+    DocumentDescription(**desc_dict)
 
     desc_dict["collection"]["type"] = "Record"
     with pytest.raises(ValidationError, match="collection.type"):
-        CCSDocumentDescription(**desc_dict)
+        DocumentDescription(**desc_dict)
 
 
 def test_collection_record_info():

test/test_doc_schema.py

@@ -18,23 +18,23 @@
     LanguageT,
 )
 from docling_core.types.doc.document import (
-    CCSDocument,
-    CCSDocumentDescription,
+    DocumentDescription,
+    LayoutDocument,
     Publication,
 )
 
 
 def test_ccs_document():
-    """Validate data with CCSDocument schema."""
+    """Validate data with Document schema."""
     for filename in glob.glob("test/data/doc/doc-*.json"):
         with open(filename) as file_obj:
             file_json = file_obj.read()
         try:
             # do not pass strict=True, since date input values are not an instance of datetime.
-            CCSDocument.model_validate_json(file_json)
+            LayoutDocument.model_validate_json(file_json)
             # try as well as dictionary
             doc = json.loads(file_json)
-            CCSDocument.model_validate(doc)
+            LayoutDocument.model_validate(doc)
         except ValidationError as e:
             print(f"Validation error in file {filename}:\n{e.json()}")
             raise
@@ -43,8 +43,8 @@ def test_ccs_document():
     try:
         with open("test/data/doc/error-1.json") as file_obj:
             file_json = file_obj.read()
-        CCSDocument.model_validate_json(file_json)
-        assert False, f"Data in file {filename} should be invalid for CCSDocument model"
+        LayoutDocument.model_validate_json(file_json)
+        assert False, f"Data in file {filename} should be invalid for Document model"
     except ValidationError as e:
         for error in e.errors():
             print(type(error))
@@ -58,15 +58,15 @@ def test_ccs_document():
         open("test/data/doc/error-2.json") as file_obj,
     ):
         file_json = file_obj.read()
-        CCSDocument.model_validate_json(file_json)
+        LayoutDocument.model_validate_json(file_json)
 
     # check doc-error-3 is invalid for wrong types in citation_count and reference_count
     with (
         pytest.raises(ValidationError, match="count"),
         open("test/data/doc/error-3.json") as file_obj,
     ):
         file_json = file_obj.read()
-        CCSDocument.model_validate_json(file_json)
+        LayoutDocument.model_validate_json(file_json)
 
 
 def test_publication_journal():
@@ -89,44 +89,44 @@ def test_description_advanced_t():
         desc = json.load(file_obj)["description"]
 
     # without advanced
-    CCSDocumentDescription.model_validate(desc)
+    DocumentDescription.model_validate(desc)
 
     # any dictionary is valid, since it is not parametrized
-    CCSDocumentDescription(**desc, advanced={"serial": "CXS12345"})
-    CCSDocumentDescription(**desc, advanced={0: "CXS12345"})
+    DocumentDescription(**desc, advanced={"serial": "CXS12345"})
+    DocumentDescription(**desc, advanced={0: "CXS12345"})
     with pytest.raises(
         ValidationError, match="should be a valid dictionary or instance of BaseModel"
     ):
-        CCSDocumentDescription(**desc, advanced=False)
+        DocumentDescription(**desc, advanced=False)
 
     class MyAdvanced(BaseModel):
         serial: str
         comment: Optional[str] = None
 
     # with a model and bound specification
     adv_inst = MyAdvanced(serial="CXS12345", comment="public document")
-    CCSDocumentDescription(**desc, advanced=adv_inst)
+    DocumentDescription(**desc, advanced=adv_inst)
     with pytest.raises(ValidationError, match="Field required"):
-        CCSDocumentDescription(**desc, advanced=MyAdvanced(comment="public document"))
+        DocumentDescription(**desc, advanced=MyAdvanced(comment="public document"))
 
     # with a model and generic type specification
     advanced = MyAdvanced(serial="CXS12345", comment="public document")
-    CCSDocumentDescription[
+    DocumentDescription[
         MyAdvanced,
         DescriptionAnalyticsT,
         IdentifierTypeT,
         LanguageT,
         CollectionNameTypeT,
     ](**desc)
-    CCSDocumentDescription[
+    DocumentDescription[
         MyAdvanced,
         DescriptionAnalyticsT,
         IdentifierTypeT,
         LanguageT,
         CollectionNameTypeT,
     ](**desc, advanced=adv_inst)
     with pytest.raises(ValidationError, match="Field required"):
-        CCSDocumentDescription[
+        DocumentDescription[
             MyAdvanced,
             DescriptionAnalyticsT,
             IdentifierTypeT,
@@ -135,7 +135,7 @@ class MyAdvanced(BaseModel):
         ](**desc, advanced={})
 
     # deriving a new type
-    MyDocument = CCSDocumentDescription[
+    MyDocument = DocumentDescription[
         MyAdvanced,
         DescriptionAnalyticsT,
         IdentifierTypeT,

test/test_doc_schema_extractor.py

@@ -8,11 +8,11 @@
 
 from pydantic import ValidationError
 
-from docling_core.types.doc.document import CCSDocument
+from docling_core.types.doc.document import LayoutDocument
 
 
 def test_ccs_document_update():
-    """Validate data with CCSDocument extract."""
+    """Validate data with Document extract."""
     filename = "test/data/doc/ext-1.json"
     try:
         with open(filename) as f:
@@ -21,7 +21,7 @@ def test_ccs_document_update():
                 if "$ref" in item:
                     assert False, f"$ref should not be in file {filename}"
 
-            doc = CCSDocument.model_validate(raw_doc)
+            doc = LayoutDocument.model_validate(raw_doc)
 
             if doc.description.abstract:
                 assert False, f"Abstract should not be present"