fix: update all test cases again

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

poetry.lock

@@ -887,7 +887,7 @@ chunking = ["semchunk (>=2.2.0,<3.0.0)", "transformers (>=4.34.0,<5.0.0)"]
 type = "git"
 url = "ssh://git@github.com/DS4SD/docling-core.git"
 reference = "cau/add-content-layer"
-resolved_reference = "4c19ae7f7fb128a12173c50a9ab376114f70a689"
+resolved_reference = "ae3748b1f2e526698c1ed136cec7dc0502f28209"
 
 [[package]]
 name = "docling-ibm-models"

tests/data/groundtruth/docling_v2/elife-56337.xml.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "elife-56337",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/example_01.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "example_01",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_02.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "example_02",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_03.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "example_03",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_04.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "example_04",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_05.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "example_05",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/ipa20180000016.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "ipa20180000016.xml",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/ipa20200022300.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "ipa20200022300.xml",
   "origin": {
     "mimetype": "application/xml",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "lorem_ipsum",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/pa20010031492.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "pa20010031492.xml",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/pftaps057006474.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "pftaps057006474.txt",
   "origin": {
     "mimetype": "text/plain",

tests/data/groundtruth/docling_v2/pg06442728.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "pg06442728.xml",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/pntd.0008301.xml.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "pntd.0008301",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/pone.0234687.xml.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "pone.0234687",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "powerpoint_sample",
   "origin": {
     "mimetype": "application/vnd.ms-powerpoint",

tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "powerpoint_with_image",
   "origin": {
     "mimetype": "application/vnd.ms-powerpoint",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "tablecell",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/test-01.xlsx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "test-01",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "test_emf_docx",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/unit_test_01.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "unit_test_01",
   "origin": {
     "mimetype": "text/html",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "unit_test_headers",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "unit_test_headers_numbered",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "unit_test_lists",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/wiki_duck.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "wiki_duck",
   "origin": {
     "mimetype": "text/html",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "word_sample",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

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

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "name": "word_tables",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data_scanned/groundtruth/docling_v2/ocr_test.json

@@ -1 +1 @@
-{"schema_name": "DoclingDocument", "version": "1.0.0", "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": 69.6796646118164, "t": 764.9216918945312, "r": 504.87200927734375, "b": 689.012451171875, "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"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}
+{"schema_name": "DoclingDocument", "version": "1.1.0", "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": 69.6796646118164, "t": 764.9216918945312, "r": 504.87200927734375, "b": 689.012451171875, "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"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}