feat(ocr): auto-detect rotated pages in Tesseract (#1167)

* 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>
2025-12-09 05:08:14 +00:00 · 2025-05-21 18:12:33 +02:00
parent 90875247e5
commit 45265bf8b1
96 changed files with 9864 additions and 5258 deletions
--- a/tests/data/webp/groundtruth/docling_v2/webp-test.doctags.txt
+++ b/tests/data/webp/groundtruth/docling_v2/webp-test.doctags.txt
@@ -1,2 +1,2 @@
-<doctag><text><loc_58><loc_44><loc_426><loc_91>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
+<doctag><text><loc_60><loc_46><loc_424><loc_91>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
 </doctag>
--- a/tests/data/webp/groundtruth/docling_v2/webp-test.json
+++ b/tests/data/webp/groundtruth/docling_v2/webp-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": "webp-test",
+  "origin": {
+    "mimetype": "application/pdf",
+    "binary_hash": 16115062463007057787,
+    "filename": "webp-test.webp",
+    "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": 238.19302423176944,
+            "t": 2570.0959833241664,
+            "r": 1696.0985546594009,
+            "b": 2315.204273887442,
+            "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": 2000.0,
+        "height": 2829.0
+      },
+      "image": null,
+      "page_no": 1
+    }
+  }
+}
--- a/tests/data/webp/groundtruth/docling_v2/webp-test.pages.json
+++ b/tests/data/webp/groundtruth/docling_v2/webp-test.pages.json