From c1b26eed03f60c3e317550053a3832b7ad62e588 Mon Sep 17 00:00:00 2001
From: Simon Willison <swillison@gmail.com>
Date: Wed, 22 Sep 2021 13:45:37 -0700
Subject: [PATCH] sqlite-utils memory handles files with same filename, closes
 #325

---
 docs/cli.rst             |  4 ++++
 sqlite_utils/cli.py      |  8 +++++++-
 tests/test_cli_memory.py | 24 ++++++++++++++++++++++++
 3 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/docs/cli.rst b/docs/cli.rst
index 0cc20dd..d2a4d84 100644
--- a/docs/cli.rst
+++ b/docs/cli.rst
@@ -281,6 +281,10 @@ The in-memory tables will be named after the files without their extensions. The
 
     $ sqlite-utils memory example.csv "select * from t"
 
+If two files have the same name they will be assigned a numeric suffix::
+
+    $ sqlite-utils memory foo/data.csv bar/data.csv "select * from data_2"
+
 To read from standard input, use either ``-`` or ``stdin`` as the filename - then use ``stdin`` or ``t`` or ``t1`` as the table name::
 
     $ cat example.csv | sqlite-utils memory - "select * from stdin"
diff --git a/sqlite_utils/cli.py b/sqlite_utils/cli.py
index 5217965..b29314e 100644
--- a/sqlite_utils/cli.py
+++ b/sqlite_utils/cli.py
@@ -1275,6 +1275,7 @@ def memory(
     if (dump or save or schema or analyze) and not paths:
         paths = [sql]
         sql = None
+    stem_counts = {}
     for i, path in enumerate(paths):
         # Path may have a :format suffix
         if ":" in path and path.rsplit(":", 1)[-1].upper() in Format.__members__:
@@ -1287,7 +1288,12 @@ def memory(
             csv_table = "stdin"
         else:
             csv_path = pathlib.Path(path)
-            csv_table = csv_path.stem
+            stem = csv_path.stem
+            if stem_counts.get(stem):
+                csv_table = "{}_{}".format(stem, stem_counts[stem])
+            else:
+                csv_table = stem
+            stem_counts[stem] = stem_counts.get(stem, 1) + 1
             csv_fp = csv_path.open("rb")
         rows, format_used = rows_from_file(csv_fp, format=format, encoding=encoding)
         tracker = None
diff --git a/tests/test_cli_memory.py b/tests/test_cli_memory.py
index 08566e3..a8b3a18 100644
--- a/tests/test_cli_memory.py
+++ b/tests/test_cli_memory.py
@@ -241,3 +241,27 @@ def test_memory_analyze():
         "  Blank rows: 0\n\n"
         "  Distinct values: 2\n\n"
     )
+
+
+def test_memory_two_files_with_same_stem(tmpdir):
+    (tmpdir / "one").mkdir()
+    (tmpdir / "two").mkdir()
+    one = tmpdir / "one" / "data.csv"
+    two = tmpdir / "two" / "data.csv"
+    one.write_text("id,name\n1,Cleo\n2,Bants", encoding="utf-8")
+    two.write_text("id,name\n3,Blue\n4,Lila", encoding="utf-8")
+    result = CliRunner().invoke(cli.cli, ["memory", str(one), str(two), "", "--schema"])
+    assert result.exit_code == 0
+    assert result.output == (
+        'CREATE TABLE "data" (\n'
+        "   [id] INTEGER,\n"
+        "   [name] TEXT\n"
+        ");\n"
+        "CREATE VIEW t1 AS select * from [data];\n"
+        "CREATE VIEW t AS select * from [data];\n"
+        'CREATE TABLE "data_2" (\n'
+        "   [id] INTEGER,\n"
+        "   [name] TEXT\n"
+        ");\n"
+        "CREATE VIEW t2 AS select * from [data_2];\n"
+    )