test(wired_table_rec): Add issue #13 unit testing

Author: SWHL

.github/workflows/wired_table_rec.yml

@@ -27,7 +27,7 @@ jobs:
       - name: Unit testings
         run: |
           pip install -r requirements.txt
-          pip install pytest
+          pip install pytest beautifulsoup4
 
           wget https://github.com/RapidAI/TableStructureRec/releases/download/v0.0.0/wired_table_rec_models.zip
           unzip wired_table_rec_models.zip

demo_wired.py

@@ -2,12 +2,12 @@
 # @Author: SWHL
 # @Contact: [email protected]
 from pathlib import Path
-from wired_table_rec import WiredTableRecognition
 
+from wired_table_rec import WiredTableRecognition
 
 table_rec = WiredTableRecognition()
 
-img_path = "tests/test_files/wired/row_span.png"
+img_path = "tests/test_files/wired/squeeze_error.jpeg"
 table_str, elapse = table_rec(img_path)
 print(table_str)
 print(elapse)

tests/test_files/wired/squeeze_error.jpeg

@@ -5,6 +5,7 @@
 from pathlib import Path
 
 import pytest
+from bs4 import BeautifulSoup
 from rapidocr_onnxruntime import RapidOCR
 
 cur_dir = Path(__file__).resolve().parent
@@ -20,36 +21,35 @@
 ocr_engine = RapidOCR()
 
 
-@pytest.mark.parametrize(
-    "img_path, gt1, gt2",
-    [
-        ("table_recognition.jpg", 1245, "d colsp"),
-        ("table2.jpg", 924, "td><td "),
-        ("row_span.png", 312, "></td><"),
-    ],
-)
-def test_input_normal(img_path, gt1, gt2):
-    img_path = test_file_dir / img_path
+def get_td_nums(html: str) -> int:
+    soup = BeautifulSoup(html, "html.parser")
+    tds = soup.table.find_all("td")
+    return len(tds)
+
 
+def test_squeeze_bug():
+    img_path = test_file_dir / "squeeze_error.jpeg"
     ocr_result, _ = ocr_engine(img_path)
     table_str, _ = table_recog(str(img_path), ocr_result)
-
-    assert len(table_str) >= gt1
-    assert table_str[-53:-46] == gt2
+    td_nums = get_td_nums(table_str)
+    assert td_nums == 153
 
 
 @pytest.mark.parametrize(
-    "img_path, gt1, gt2",
+    "img_path, gt_td_nums, gt2",
     [
-        ("table_recognition.jpg", 1245, "d colsp"),
-        ("table2.jpg", 924, "td><td "),
-        ("row_span.png", 311, "></td><"),
+        ("table_recognition.jpg", 35, "d colsp"),
+        ("table2.jpg", 22, "td><td "),
+        ("row_span.png", 17, "></td><"),
     ],
 )
-def test_input_without_ocr(img_path, gt1, gt2):
+def test_input_normal(img_path, gt_td_nums, gt2):
     img_path = test_file_dir / img_path
 
-    table_str, _ = table_recog(str(img_path))
+    ocr_result, _ = ocr_engine(img_path)
+    table_str, _ = table_recog(str(img_path), ocr_result)
+    td_nums = get_td_nums(table_str)
 
-    assert len(table_str) >= gt1
+    assert td_nums == gt_td_nums
     assert table_str[-53:-46] == gt2
+

tests/test_wired.py

@@ -59,8 +59,7 @@ def __call__(
         except Exception:
             logging.warning(traceback.format_exc())
             return "", 0.0
-        else:
-            return table_str, elapse
+        return table_str, elapse
 
 
 def main():