From bb93d57055f58944289f0061f0dd9c4a91de4bf8 Mon Sep 17 00:00:00 2001
From: L4XB <lukas.buck@e-mail.de>
Date: Sat, 17 Oct 2026 15:38:54 +0200
Subject: [PATCH] Read a single-column CSV file as one column when detecting
 the format

rows_from_file() sniffed the CSV dialect with no delimiters= list, so
csv.Sniffer considered every character. A single-column file then either
had no consistent candidate (csv.Error: Could not determine delimiter) or
was split on a letter that repeats on each line: a column of URLs came out
as {"ur": "https://examp", "": "e.com/a"}.

Format detection now sniffs for a comma, a semicolon, a tab or a pipe,
and reads a file with none of them as plain CSV.

Closes #907
---
 sqlite_utils/utils.py        | 16 +++++++++++++++-
 tests/test_cli_memory.py     | 11 +++++++++++
 tests/test_rows_from_file.py | 19 +++++++++++++++++++
 3 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/sqlite_utils/utils.py b/sqlite_utils/utils.py
index 91fd24ddd..24d32024c 100644
--- a/sqlite_utils/utils.py
+++ b/sqlite_utils/utils.py
@@ -285,6 +285,20 @@ def _extra_key_strategy(
             yield row_out
 
 
+# Delimiters rows_from_file() looks for when it detects the format. Without a list
+# csv.Sniffer takes any character that repeats on the sampled lines, so a single-column
+# file was split on a letter, or raised "Could not determine delimiter".
+_SNIFF_DELIMITERS = ",;\t|"
+
+
+def _sniff_csv_dialect(sample: str) -> type[csv.Dialect]:
+    try:
+        return csv.Sniffer().sniff(sample, delimiters=_SNIFF_DELIMITERS)
+    except csv.Error:
+        # None of them: a single-column file, read as plain CSV
+        return csv.excel
+
+
 def rows_from_file(
     fp: BinaryIO,
     format: Format | None = None,
@@ -389,7 +403,7 @@ class Format(enum.Enum):
             with buffered:
                 return rows_from_file(buffered, format=Format.JSON)
         else:
-            dialect = csv.Sniffer().sniff(
+            dialect = _sniff_csv_dialect(
                 first_bytes.decode(encoding or "utf-8-sig", "ignore")
             )
             rows, _ = rows_from_file(
diff --git a/tests/test_cli_memory.py b/tests/test_cli_memory.py
index 445f50b0f..6d4212681 100644
--- a/tests/test_cli_memory.py
+++ b/tests/test_cli_memory.py
@@ -157,6 +157,17 @@ def test_memory_csv_encoding(tmpdir, use_stdin):
     }
 
 
+def test_memory_csv_single_column(tmpdir):
+    csv_path = str(tmpdir / "names.csv")
+    with open(csv_path, "w") as fp:
+        fp.write("name\nAnn\nBob\n")
+    result = CliRunner().invoke(
+        cli.cli, ["memory", csv_path, "select * from names", "--nl"]
+    )
+    assert result.exit_code == 0, result.output
+    assert result.output.strip() == '{"name": "Ann"}\n{"name": "Bob"}'
+
+
 def test_memory_csv_headers_only(tmpdir):
     csv_path = str(tmpdir / "headers_only.csv")
     with open(csv_path, "w") as fp:
diff --git a/tests/test_rows_from_file.py b/tests/test_rows_from_file.py
index a8e7f9d76..d5666bcde 100644
--- a/tests/test_rows_from_file.py
+++ b/tests/test_rows_from_file.py
@@ -11,6 +11,7 @@
     "input,expected_format",
     (
         (b"id,name\n1,Cleo", Format.CSV),
+        (b"id;name\n1;Cleo", Format.CSV),
         (b"id\tname\n1\tCleo", Format.TSV),
         (b'[{"id": "1", "name": "Cleo"}]', Format.JSON),
     ),
@@ -22,6 +23,24 @@ def test_rows_from_file_detect_format(input, expected_format):
     assert rows_list == [{"id": "1", "name": "Cleo"}]
 
 
+@pytest.mark.parametrize(
+    "input,expected",
+    (
+        # csv.Sniffer could not determine a delimiter for this one
+        (b"name\nAnn\nBob\n", [{"name": "Ann"}, {"name": "Bob"}]),
+        # and took "l", which every line holds twice, for this one
+        (
+            b"url\nhttps://example.com/a\nhttps://example.org/b\n",
+            [{"url": "https://example.com/a"}, {"url": "https://example.org/b"}],
+        ),
+    ),
+)
+def test_rows_from_file_detect_format_single_column(input, expected):
+    rows, format = rows_from_file(BytesIO(input))
+    assert format == Format.CSV
+    assert list(rows) == expected
+
+
 @pytest.mark.parametrize("input", (b"", b" \n\t"))
 def test_rows_from_file_empty_input(input):
     rows, format = rows_from_file(BytesIO(input))