Fix conflicts

.github/workflows/tests.yml

@@ -28,7 +28,11 @@ jobs:
       - name: Run benchmark test
         run: |
           poetry run python benchmarks/overall.py benchmark_data/pdfs benchmark_data/references report.json
-          poetry run python scripts/verify_benchmark_scores.py report.json
+          poetry run python scripts/verify_benchmark_scores.py report.json --type marker
+      - name: Run table benchmark
+        run: |
+          poetry run python benchmarks/table.py tables.json
+          poetry run python scripts/verify_benchmark_scores.py report.json --type table
         
           
 

marker/output.py

@@ -3,7 +3,7 @@ import json
 
 
 def get_subfolder_path(out_folder, fname):
-    subfolder_name = fname.split(".")[0]
+    subfolder_name = fname.rsplit('.', 1)[0]
     subfolder_path = os.path.join(out_folder, subfolder_name)
     return subfolder_path
 

scripts/verify_benchmark_scores.py

@@ -9,12 +9,25 @@ def verify_scores(file_path):
     multicolcnn_score = data["marker"]["files"]["multicolcnn.pdf"]["score"]
     switch_trans_score = data["marker"]["files"]["switch_trans.pdf"]["score"]
 
-    if multicolcnn_score <= 0.39 or switch_trans_score <= 0.4:
+    if multicolcnn_score <= 0.37 or switch_trans_score <= 0.4:
         raise ValueError("One or more scores are below the required threshold of 0.4")
 
 
+def verify_table_scores(file_path):
+    with open(file_path, 'r') as file:
+        data = json.load(file)
+
+    avg = sum([r["score"] for r in data]) / len(data)
+    if avg < 0.7:
+        raise ValueError("Average score is below the required threshold of 0.7")
+
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Verify benchmark scores")
     parser.add_argument("file_path", type=str, help="Path to the json file")
+    parser.add_argument("--type", type=str, help="Type of file to verify", default="marker")
     args = parser.parse_args()
-    verify_scores(args.file_path)
+    if args.type == "marker":
+        verify_scores(args.file_path)
+    elif args.type == "table":
+        verify_table_scores(args.file_path)

signatures/version1/cla.json

@@ -0,0 +1,52 @@
+{
+  "signedContributors": [
+    {
+      "name": "korakot",
+      "id": 3155646,
+      "comment_id": 2143359366,
+      "created_at": "2024-06-01T08:25:52Z",
+      "repoId": 712111618,
+      "pullRequestNo": 161
+    },
+    {
+      "name": "tosaddler",
+      "id": 13705399,
+      "comment_id": 2144014410,
+      "created_at": "2024-06-02T20:40:52Z",
+      "repoId": 712111618,
+      "pullRequestNo": 165
+    },
+    {
+      "name": "q2333gh",
+      "id": 32679742,
+      "comment_id": 2156122900,
+      "created_at": "2024-06-08T18:01:39Z",
+      "repoId": 712111618,
+      "pullRequestNo": 176
+    },
+    {
+      "name": "q2333gh",
+      "id": 32679742,
+      "comment_id": 2156614334,
+      "created_at": "2024-06-09T13:48:49Z",
+      "repoId": 712111618,
+      "pullRequestNo": 176
+    },
+    {
+      "name": "aniketinamdar",
+      "id": 79044809,
+      "comment_id": 2157453610,
+      "created_at": "2024-06-10T06:43:39Z",
+      "repoId": 712111618,
+      "pullRequestNo": 179
+    },
+    {
+      "name": "Zxilly",
+      "id": 31370133,
+      "comment_id": 2295163597,
+      "created_at": "2024-08-18T07:44:04Z",
+      "repoId": 712111618,
+      "pullRequestNo": 257
+    }
+  ]
+}