45265bf8b1
* fix(ocr): tesseract support mis-oriented documents Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): update missing test data Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): rotate image to the natural orientation before layout prediction Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): move bounding bow rotation util to orientation.py Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): refactor rotation utilities Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): revert layout updates Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): update e2e OCR test data Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * fix(ocr): avoid to swallow tesseract errors causing orientation detection failures Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): revert layout updates Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com> * chore(ocr): update e2e OCR test data * chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrCliModel` * chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrModel` * chore(ocr): default `TesseractOcrCliModel._is_auto` to `False` * fix(ocr): fix `TesseractOcrCliModel._is_auto` computation * chore(ocr): improve logging in case of OSD failure in `TesseractOcrCliModel` and `TesseractOcrModel` --------- Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>
619 lines
12 KiB
JSON
Vendored
619 lines
12 KiB
JSON
Vendored
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.3.0",
|
|
"name": "unit_test_formatting",
|
|
"origin": {
|
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
|
"binary_hash": 16380079676357958448,
|
|
"filename": "unit_test_formatting.docx"
|
|
},
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"content_layer": "furniture",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
},
|
|
{
|
|
"$ref": "#/texts/4"
|
|
},
|
|
{
|
|
"$ref": "#/groups/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/12"
|
|
},
|
|
{
|
|
"$ref": "#/groups/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/23"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [
|
|
{
|
|
"self_ref": "#/groups/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/5"
|
|
},
|
|
{
|
|
"$ref": "#/texts/6"
|
|
},
|
|
{
|
|
"$ref": "#/texts/7"
|
|
},
|
|
{
|
|
"$ref": "#/texts/8"
|
|
},
|
|
{
|
|
"$ref": "#/texts/9"
|
|
},
|
|
{
|
|
"$ref": "#/texts/10"
|
|
},
|
|
{
|
|
"$ref": "#/texts/11"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/13"
|
|
},
|
|
{
|
|
"$ref": "#/texts/14"
|
|
},
|
|
{
|
|
"$ref": "#/texts/15"
|
|
},
|
|
{
|
|
"$ref": "#/groups/2"
|
|
},
|
|
{
|
|
"$ref": "#/groups/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/2",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/16"
|
|
},
|
|
{
|
|
"$ref": "#/texts/17"
|
|
},
|
|
{
|
|
"$ref": "#/texts/18"
|
|
},
|
|
{
|
|
"$ref": "#/texts/19"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/3",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/4"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/4",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/20"
|
|
},
|
|
{
|
|
"$ref": "#/texts/21"
|
|
},
|
|
{
|
|
"$ref": "#/texts/22"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "group",
|
|
"label": "inline"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "italic",
|
|
"text": "italic",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": true,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "bold",
|
|
"text": "bold",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "underline",
|
|
"text": "underline",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": true,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "hyperlink",
|
|
"text": "hyperlink",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"hyperlink": "https:/github.com/DS4SD/docling"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "italic and bold hyperlink",
|
|
"text": "italic and bold hyperlink",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": true,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"hyperlink": "https:/github.com/DS4SD/docling"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/5",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Normal",
|
|
"text": "Normal",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/6",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "italic",
|
|
"text": "italic",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": true,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/7",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "bold",
|
|
"text": "bold",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/8",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "underline",
|
|
"text": "underline",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": true,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/9",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "and",
|
|
"text": "and",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/10",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "hyperlink",
|
|
"text": "hyperlink",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"hyperlink": "https:/github.com/DS4SD/docling"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/11",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "on the same line",
|
|
"text": "on the same line",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
}
|
|
},
|
|
{
|
|
"self_ref": "#/texts/12",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/13",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Italic bullet 1",
|
|
"text": "Italic bullet 1",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": true,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/14",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Bold bullet 2",
|
|
"text": "Bold bullet 2",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/15",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Underline bullet 3",
|
|
"text": "Underline bullet 3",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": true,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/16",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Some",
|
|
"text": "Some",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/17",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "italic",
|
|
"text": "italic",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": true,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/18",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "bold",
|
|
"text": "bold",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/19",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "underline",
|
|
"text": "underline",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": true,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/20",
|
|
"parent": {
|
|
"$ref": "#/groups/4"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Nested",
|
|
"text": "Nested",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/21",
|
|
"parent": {
|
|
"$ref": "#/groups/4"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "italic",
|
|
"text": "italic",
|
|
"formatting": {
|
|
"bold": false,
|
|
"italic": true,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/22",
|
|
"parent": {
|
|
"$ref": "#/groups/4"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "bold",
|
|
"text": "bold",
|
|
"formatting": {
|
|
"bold": true,
|
|
"italic": false,
|
|
"underline": false,
|
|
"strikethrough": false
|
|
},
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/23",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [],
|
|
"key_value_items": [],
|
|
"form_items": [],
|
|
"pages": {}
|
|
} |