Don't detect types on JSON input to memory, closes #283

sqlite_utils/cli.py

@@ -1241,9 +1241,9 @@ def memory(
             csv_path = pathlib.Path(path)
             csv_table = csv_path.stem
             csv_fp = csv_path.open("rb")
-        rows = rows_from_file(csv_fp, format=format, encoding=encoding)
+        rows, format_used = rows_from_file(csv_fp, format=format, encoding=encoding)
         tracker = None
-        if not no_detect_types:
+        if format_used in (Format.CSV, Format.TSV) and not no_detect_types:
             tracker = TypeTracker()
             rows = tracker.wrap(rows)
         db[csv_table].insert_all(rows, alter=True)

sqlite_utils/utils.py

@@ -155,15 +155,18 @@ def rows_from_file(
             decoded = [decoded]
         if not isinstance(decoded, list):
             raise RowsFromFileBadJSON("JSON must be a list or a dictionary")
-        yield from decoded
+        return decoded, Format.JSON
     elif format == Format.NL:
-        yield from (json.loads(line) for line in fp if line.strip())
+        return (json.loads(line) for line in fp if line.strip()), Format.NL
     elif format == Format.CSV:
         decoded_fp = io.TextIOWrapper(fp, encoding=encoding or "utf-8-sig")
-        yield from csv.DictReader(decoded_fp, dialect=dialect)
+        return csv.DictReader(decoded_fp, dialect=dialect), Format.CSV
     elif format == Format.TSV:
-        yield from rows_from_file(
+        return (
-            fp, format=Format.CSV, dialect=csv.excel_tab, encoding=encoding
+            rows_from_file(
+                fp, format=Format.CSV, dialect=csv.excel_tab, encoding=encoding
+            )[0],
+            Format.TSV,
         )
     elif format is None:
         # Detect the format, then call this recursively
@@ -171,12 +174,12 @@ def rows_from_file(
         first_bytes = buffered.peek(2048).strip()
         if first_bytes.startswith(b"[") or first_bytes.startswith(b"{"):
             # TODO: Detect newline-JSON
-            yield from rows_from_file(buffered, format=Format.JSON)
+            return rows_from_file(buffered, format=Format.JSON)
         else:
             dialect = csv.Sniffer().sniff(
                 first_bytes.decode(encoding or "utf-8-sig", "ignore")
             )
-            yield from rows_from_file(
+            return rows_from_file(
                 buffered, format=Format.CSV, dialect=dialect, encoding=encoding
             )
     else:
@@ -215,14 +218,14 @@ class ValueTracker:
         try:
             int(value)
             return True
-        except ValueError:
+        except (ValueError, TypeError):
             return False
 
     def test_float(self, value):
         try:
             float(value)
             return True
-        except ValueError:
+        except (ValueError, TypeError):
             return False
 
     def __repr__(self):

tests/test_cli_memory.py

@@ -64,7 +64,7 @@ def test_memory_tsv(tmpdir, use_stdin):
 
 @pytest.mark.parametrize("use_stdin", (True, False))
 def test_memory_json(tmpdir, use_stdin):
-    data = '[{"name": "Bants"}, {"name": "Dori", "age": 1}]'
+    data = '[{"name": "Bants"}, {"name": "Dori", "age": 1, "nested": {"nest": 1}}]'
     if use_stdin:
         input = data
         path = "stdin:json"
@@ -82,8 +82,8 @@ def test_memory_json(tmpdir, use_stdin):
     )
     assert result.exit_code == 0, result.output
     assert json.loads(result.output.strip()) == [
-        {"rowid": 1, "name": "Bants", "age": None},
+        {"name": "Bants", "age": None, "nested": None},
-        {"rowid": 2, "name": "Dori", "age": 1},
+        {"name": "Dori", "age": 1, "nested": '{"nest": 1}'},
     ]
 
 
@@ -107,8 +107,8 @@ def test_memory_json_nl(tmpdir, use_stdin):
     )
     assert result.exit_code == 0, result.output
     assert json.loads(result.output.strip()) == [
-        {"rowid": 1, "name": "Bants"},
+        {"name": "Bants"},
-        {"rowid": 2, "name": "Dori"},
+        {"name": "Dori"},
     ]