fix: bumped the glm version and adjusted the tests (#83)

* bumped the glm version and adjusted the tests Signed-off-by: Peter Staar <[email protected]> * updated the poetry lock Signed-off-by: Peter Staar <[email protected]> * fix hooks Signed-off-by: Michele Dolfi <[email protected]> * fixed the tests Signed-off-by: Peter Staar <[email protected]> * reformatted the code Signed-off-by: Peter Staar <[email protected]> * added the tests for tables Signed-off-by: Peter Staar <[email protected]> --------- Signed-off-by: Peter Staar <[email protected]> Signed-off-by: Michele Dolfi <[email protected]> Co-authored-by: Michele Dolfi <[email protected]>
DS4SD · Sep 18, 2024 · 442443a · 442443a
1 parent 8242bce
commit 442443a
Show file tree

Hide file tree

Showing 11 changed files with 406 additions and 361 deletions.
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -25,7 +25,7 @@ python = "^3.10"
 pydantic = "^2.0.0"
 docling-core = "^1.3.0"
 docling-ibm-models = "^1.2.0"
-deepsearch-glm = "^0.21.0"
+deepsearch-glm = "^0.21.1"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
 pydantic-settings = "^2.3.0"

diff --git a/tests/data/2203.01017v2.json b/tests/data/2203.01017v2.json
diff --git a/tests/data/2206.01062.json b/tests/data/2206.01062.json
diff --git a/tests/data/2305.03393v1-pg9.json b/tests/data/2305.03393v1-pg9.json
diff --git a/tests/data/2305.03393v1-pg9.pages.json b/tests/data/2305.03393v1-pg9.pages.json
diff --git a/tests/data/2305.03393v1.json b/tests/data/2305.03393v1.json
diff --git a/tests/data/redp5110.json b/tests/data/redp5110.json
diff --git a/tests/data/redp5110.pages.json b/tests/data/redp5110.pages.json
diff --git a/tests/data/redp5695.json b/tests/data/redp5695.json
diff --git a/tests/verify_utils.py b/tests/verify_utils.py
@@ -96,10 +96,17 @@ def verify_tables(doc_pred: DsDocument, doc_true: DsDocument):
         for i, row in enumerate(true_item.data):
             for j, col in enumerate(true_item.data[i]):
 
+                # print("true: ", true_item.data[i][j])
+                # print("pred: ", pred_item.data[i][j])
+
                 assert (
                     true_item.data[i][j].text == pred_item.data[i][j].text
                 ), "table-cell does not have the same text"
 
+                assert (
+                    true_item.data[i][j].obj_type == pred_item.data[i][j].obj_type
+                ), "table-cell does not have the same type"
+
     return True
 
 
@@ -156,9 +163,13 @@ def verify_conversion_result(
         ), f"Mismatch in PDF cell prediction for {input_path}"
 
         # assert verify_output(
-        #     doc_pred, doc_true
+        #    doc_pred, doc_true
         # ), f"Mismatch in JSON prediction for {input_path}"
 
+        assert verify_tables(
+            doc_pred, doc_true
+        ), f"verify_tables(doc_pred, doc_true) mismatch for {input_path}"
+
         assert verify_md(
             doc_pred_md, doc_true_md
         ), f"Mismatch in Markdown prediction for {input_path}"