supporting spaces in column names for csv files

georgia-tech-db · Nov 24, 2023 · 4017bef · 4017bef
1 parent 69b39b8
commit 4017bef
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 3 deletions.
diff --git a/evadb/parser/lark_visitor/_common_clauses_ids.py b/evadb/parser/lark_visitor/_common_clauses_ids.py
@@ -43,6 +43,11 @@ def full_id(self, tree):
             return (self.visit(tree.children[0]), self.visit(tree.children[1]))
 
     def uid(self, tree):
+        if (hasattr(tree.children[0],"type") and tree.children[0].type == "REVERSE_QUOTE_ID"):
+            # tree.children[0].value = tree.children[0].value.replace("`","")
+            temp = str(tree.children[0]).replace("`","")
+            tree.children[0].type = "simple_id"
+            return temp
         return self.visit(tree.children[0])
 
     def full_column_name(self, tree):

diff --git a/test/integration_tests/short/test_load_executor.py b/test/integration_tests/short/test_load_executor.py
@@ -84,7 +84,7 @@ def test_should_load_csv_in_table(self):
 
             CREATE TABLE IF NOT EXISTS MyVideoCSV (
                 id INTEGER UNIQUE,
-                frame_id INTEGER,
+                `frame_id` INTEGER,
                 video_id INTEGER,
                 dataset_name TEXT(30),
                 label TEXT(30),
@@ -100,7 +100,7 @@ def test_should_load_csv_in_table(self):
         execute_query_fetch_all(self.evadb, load_query)
 
         # execute a select query
-        select_query = """SELECT id, frame_id, video_id,
+        select_query = """SELECT id, `frame_id`, video_id,
                           dataset_name, label, bbox,
                           object_id
                           FROM MyVideoCSV;"""

diff --git a/test/util.py b/test/util.py
@@ -304,7 +304,7 @@ def create_sample_csv(num_frames=NUM_FRAMES):
             random_coords = 200 + 300 * np.random.random(4)
             sample_meta[index] = {
                 "id": index,
-                "frame_id": frame_id,
+                "frame id": frame_id,
                 "video_id": video_id,
                 "dataset_name": "test_dataset",
                 "label": sample_labels[np.random.choice(len(sample_labels))],