chore: format JSON test files to enable comparison (#1511)

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

tests/data_scanned/groundtruth/docling_v1/ocr_test.json

@@ -1 +1,83 @@
-{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "ocr_test.pdf", "filename-prov": null, "document-hash": "80f38f5b87a84870681556176a9622186fd200dd32c5557be9e0c0af05b8bc61", "#-pages": 1, "collection-name": null, "description": null, "page-hashes": [{"hash": "14d896dc8bcb7ee7c08c0347eb6be8dcb92a3782501992f1ea14d2e58077d4e3", "model": "default", "page": 1}]}, "main-text": [{"prov": [{"bbox": [69.0, 688.5883585611979, 506.6666666666667, 767.2550252278646], "page": 1, "span": [0, 94], "__ref_s3_data": null}], "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "type": "paragraph", "payload": null, "name": "Text", "font": null}], "figures": [], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 841.9216918945312, "page": 1, "width": 595.201171875}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null}
+{
+  "_name": "",
+  "type": "pdf-document",
+  "description": {
+    "title": null,
+    "abstract": null,
+    "authors": null,
+    "affiliations": null,
+    "subjects": null,
+    "keywords": null,
+    "publication_date": null,
+    "languages": null,
+    "license": null,
+    "publishers": null,
+    "url_refs": null,
+    "references": null,
+    "publication": null,
+    "reference_count": null,
+    "citation_count": null,
+    "citation_date": null,
+    "advanced": null,
+    "analytics": null,
+    "logs": [],
+    "collection": null,
+    "acquisition": null
+  },
+  "file-info": {
+    "filename": "ocr_test.pdf",
+    "filename-prov": null,
+    "document-hash": "80f38f5b87a84870681556176a9622186fd200dd32c5557be9e0c0af05b8bc61",
+    "#-pages": 1,
+    "collection-name": null,
+    "description": null,
+    "page-hashes": [
+      {
+        "hash": "14d896dc8bcb7ee7c08c0347eb6be8dcb92a3782501992f1ea14d2e58077d4e3",
+        "model": "default",
+        "page": 1
+      }
+    ]
+  },
+  "main-text": [
+    {
+      "prov": [
+        {
+          "bbox": [
+            69.0,
+            688.5883585611979,
+            506.6666666666667,
+            767.2550252278646
+          ],
+          "page": 1,
+          "span": [
+            0,
+            94
+          ],
+          "__ref_s3_data": null
+        }
+      ],
+      "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package",
+      "type": "paragraph",
+      "payload": null,
+      "name": "Text",
+      "font": null
+    }
+  ],
+  "figures": [],
+  "tables": [],
+  "bitmaps": null,
+  "equations": [],
+  "footnotes": [],
+  "page-dimensions": [
+    {
+      "height": 841.9216918945312,
+      "page": 1,
+      "width": 595.201171875
+    }
+  ],
+  "page-footers": [],
+  "page-headers": [],
+  "_s3_data": null,
+  "identifiers": null
+}

tests/data_scanned/groundtruth/docling_v2/ocr_test.json

@@ -1 +1,77 @@
-{"schema_name": "DoclingDocument", "version": "1.3.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.0, "t": 767.2550252278646, "r": 506.6666666666667, "b": 688.5883585611979, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "formatting": null, "hyperlink": null}], "pictures": [], "tables": [], "key_value_items": [], "form_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.3.0",
+  "name": "ocr_test",
+  "origin": {
+    "mimetype": "application/pdf",
+    "binary_hash": 14853448746796404529,
+    "filename": "ocr_test.pdf",
+    "uri": null
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "parent": null,
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "parent": null,
+    "children": [
+      {
+        "cref": "#/texts/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "cref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [
+        {
+          "page_no": 1,
+          "bbox": {
+            "l": 69.0,
+            "t": 767.2550252278646,
+            "r": 506.6666666666667,
+            "b": 688.5883585611979,
+            "coord_origin": "BOTTOMLEFT"
+          },
+          "charspan": [
+            0,
+            94
+          ]
+        }
+      ],
+      "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package",
+      "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package",
+      "formatting": null,
+      "hyperlink": null
+    }
+  ],
+  "pictures": [],
+  "tables": [],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {
+    "1": {
+      "size": {
+        "width": 595.201171875,
+        "height": 841.9216918945312
+      },
+      "image": null,
+      "page_no": 1
+    }
+  }
+}

tests/verify_utils.py

@@ -293,6 +293,7 @@ def verify_conversion_result_v1(
     generate: bool = False,
     ocr_engine: Optional[str] = None,
     fuzzy: bool = False,
+    indent: int = 2,
 ):
     PageList = TypeAdapter(List[Page])
 
@@ -323,11 +324,13 @@ def verify_conversion_result_v1(
     if generate:  # only used when re-generating truth
         pages_path.parent.mkdir(parents=True, exist_ok=True)
         with open(pages_path, "w") as fw:
-            fw.write(json.dumps(doc_pred_pages, default=pydantic_encoder))
+            fw.write(
+                json.dumps(doc_pred_pages, default=pydantic_encoder, indent=indent)
+            )
 
         json_path.parent.mkdir(parents=True, exist_ok=True)
         with open(json_path, "w") as fw:
-            fw.write(json.dumps(doc_pred, default=pydantic_encoder))
+            fw.write(json.dumps(doc_pred, default=pydantic_encoder, indent=indent))
 
         md_path.parent.mkdir(parents=True, exist_ok=True)
         with open(md_path, "w") as fw:
@@ -377,6 +380,7 @@ def verify_conversion_result_v2(
     generate: bool = False,
     ocr_engine: Optional[str] = None,
     fuzzy: bool = False,
+    indent: int = 2,
 ):
     PageList = TypeAdapter(List[Page])
 
@@ -405,11 +409,13 @@ def verify_conversion_result_v2(
     if generate:  # only used when re-generating truth
         pages_path.parent.mkdir(parents=True, exist_ok=True)
         with open(pages_path, "w") as fw:
-            fw.write(json.dumps(doc_pred_pages, default=pydantic_encoder))
+            fw.write(
+                json.dumps(doc_pred_pages, default=pydantic_encoder, indent=indent)
+            )
 
         json_path.parent.mkdir(parents=True, exist_ok=True)
         with open(json_path, "w") as fw:
-            fw.write(json.dumps(doc_pred, default=pydantic_encoder))
+            fw.write(json.dumps(doc_pred, default=pydantic_encoder, indent=indent))
 
         md_path.parent.mkdir(parents=True, exist_ok=True)
         with open(md_path, "w") as fw: