From 6027f3ea6939a399aeef2578fca17efec0e539df Mon Sep 17 00:00:00 2001
From: Simon Willison <swillison@gmail.com>
Date: Sun, 21 May 2023 10:19:16 -0700
Subject: [PATCH] No need to show common values if everything is null

Closes #547
---
 sqlite_utils/cli.py          |  8 +++++---
 sqlite_utils/db.py           | 24 ++++++++++++++----------
 tests/test_analyze_tables.py | 26 +++++++++++++++++++++++++-
 3 files changed, 44 insertions(+), 14 deletions(-)

diff --git a/sqlite_utils/cli.py b/sqlite_utils/cli.py
index 0c91a8f..46af7ae 100644
--- a/sqlite_utils/cli.py
+++ b/sqlite_utils/cli.py
@@ -2691,9 +2691,11 @@ def _analyze(db, tables, columns, save, common_limit=10, no_most=False, no_least
             db["_analyze_tables_"].insert(
                 column_details._asdict(), pk=("table", "column"), replace=True
             )
-        most_common_rendered = _render_common(
-            "\n\n  Most common:", column_details.most_common
-        )
+        most_common_rendered = ""
+        if column_details.num_null != column_details.total_rows:
+            most_common_rendered = _render_common(
+                "\n\n  Most common:", column_details.most_common
+            )
         least_common_rendered = _render_common(
             "\n\n  Least common:", column_details.least_common
         )
diff --git a/sqlite_utils/db.py b/sqlite_utils/db.py
index 850a3ae..997c2a5 100644
--- a/sqlite_utils/db.py
+++ b/sqlite_utils/db.py
@@ -3470,18 +3470,22 @@ class Table(Queryable):
             most_common_results = [(truncate(value), total_rows)]
         elif num_distinct != total_rows:
             if most_common:
-                most_common_results = [
-                    (truncate(r[0]), r[1])
-                    for r in db.execute(
-                        "select [{}], count(*) from [{}] group by [{}] order by count(*) desc, [{}] limit {}".format(
-                            column, table, column, column, common_limit
-                        )
-                    ).fetchall()
-                ]
-                most_common_results.sort(key=lambda p: (p[1], p[0]), reverse=True)
+                # Optimization - if all rows are null, don't run this query
+                if num_null == total_rows:
+                    most_common_results = [(None, total_rows)]
+                else:
+                    most_common_results = [
+                        (truncate(r[0]), r[1])
+                        for r in db.execute(
+                            "select [{}], count(*) from [{}] group by [{}] order by count(*) desc, [{}] limit {}".format(
+                                column, table, column, column, common_limit
+                            )
+                        ).fetchall()
+                    ]
+                    most_common_results.sort(key=lambda p: (p[1], p[0]), reverse=True)
             if least_common:
                 if num_distinct <= common_limit:
-                    # No need to run the query if it will just return the results in revers order
+                    # No need to run the query if it will just return the results in reverse order
                     least_common_results = None
                 else:
                     least_common_results = [
diff --git a/tests/test_analyze_tables.py b/tests/test_analyze_tables.py
index a3e4e2f..f4559ff 100644
--- a/tests/test_analyze_tables.py
+++ b/tests/test_analyze_tables.py
@@ -40,6 +40,7 @@ def big_db_to_analyze_path(tmpdir):
             to_insert.append(
                 {
                     "category": category,
+                    "all_null": None,
                 }
             )
     db["stuff"].insert_all(to_insert)
@@ -233,7 +234,15 @@ def test_analyze_table_save(db_to_analyze_path):
 def test_analyze_table_save_no_most_no_least_options(
     no_most, no_least, big_db_to_analyze_path
 ):
-    args = ["analyze-tables", big_db_to_analyze_path, "--save", "--common-limit", "2"]
+    args = [
+        "analyze-tables",
+        big_db_to_analyze_path,
+        "--save",
+        "--common-limit",
+        "2",
+        "--column",
+        "category",
+    ]
     if no_most:
         args.append("--no-most")
     if no_least:
@@ -257,3 +266,18 @@ def test_analyze_table_save_no_most_no_least_options(
         expected["least_common"] = '[["D", 10], ["C", 20]]'
 
     assert rows == [expected]
+
+
+def test_analyze_table_column_all_nulls(big_db_to_analyze_path):
+    result = CliRunner().invoke(
+        cli.cli,
+        ["analyze-tables", big_db_to_analyze_path, "stuff", "--column", "all_null"],
+    )
+    assert result.exit_code == 0
+    assert result.output == (
+        "stuff.all_null: (1/1)\n\n  Total rows: 100\n"
+        "  Null rows: 100\n"
+        "  Blank rows: 0\n"
+        "\n"
+        "  Distinct values: 0\n\n"
+    )