Fix for table.insert(..., pk=..., ignore=True), closes #554

docs/changelog.rst

@@ -11,6 +11,7 @@ Unreleased
 
 - JSON output from the command-line tool no longer escapes non-ASCII characters, so ``sqlite-utils data.db "select '日本語' as text"`` now outputs ``[{"text": "日本語"}]``. This matches how values were already stored by ``insert`` and how CSV/TSV output already behaved. A new ``--ascii`` option restores the previous behavior of escaping non-ASCII characters, for output destinations that cannot handle UTF-8 - see :ref:`cli_query_json_ascii`. The option is available on the ``query``, ``rows``, ``search``, ``tables``, ``views``, ``triggers``, ``indexes`` and ``memory`` commands. The ``convert --multi --dry-run`` preview and ``plugins`` output also no longer escape non-ASCII characters. (:issue:`625`)
 - ``table.insert_all(..., pk=...)`` now raises ``InvalidColumns`` if ``pk=`` names columns that do not exist in an existing table. Previously this behaved inconsistently, with single-row inserts raising a ``KeyError`` while other row counts succeeded. (:issue:`732`)
+- Fixed an ``IndexError`` from ``table.insert(..., pk=..., ignore=True)`` when an ignored insert followed writes to another table on the same connection. ``last_pk`` is now populated from the explicit primary key value instead of looking up a stale ``lastrowid``. (:issue:`554`)
 
 .. _v4_0rc3:
 

sqlite_utils/db.py

@@ -4386,18 +4386,54 @@ class Table(Queryable):
         if num_records_processed == 1:
             # For an insert we need to use result.lastrowid
             if not upsert and result is not None:
-                self.last_rowid = result.lastrowid
-                if (hash_id or pk) and self.last_rowid:
-                    # Set self.last_pk to the pk(s) for that rowid
-                    row = list(self.rows_where("rowid = ?", [self.last_rowid]))[0]
-                    if hash_id:
-                        self.last_pk = row[hash_id]
-                    elif isinstance(pk, str):
-                        self.last_pk = row[resolve_casing(pk, row)]
+                ignored_insert = ignore and result.rowcount == 0
+                if ignored_insert:
+                    if list_mode:
+                        first_record_list = cast(Sequence[Any], first_record)
+                        if hash_id:
+                            pass
+                        elif isinstance(pk, str):
+                            pk_index = column_names.index(
+                                resolve_casing(pk, column_names)
+                            )
+                            self.last_pk = first_record_list[pk_index]
+                        elif pk:
+                            self.last_pk = tuple(
+                                first_record_list[
+                                    column_names.index(resolve_casing(p, column_names))
+                                ]
+                                for p in pk
+                            )
                     else:
-                        self.last_pk = tuple(row[resolve_casing(p, row)] for p in pk)
+                        first_record_dict = cast(Dict[str, Any], first_record)
+                        if hash_id:
+                            self.last_pk = hash_record(
+                                first_record_dict, hash_id_columns
+                            )
+                        elif isinstance(pk, str):
+                            self.last_pk = first_record_dict[
+                                resolve_casing(pk, first_record_dict)
+                            ]
+                        elif pk:
+                            self.last_pk = tuple(
+                                first_record_dict[resolve_casing(p, first_record_dict)]
+                                for p in pk
+                            )
                 else:
-                    self.last_pk = self.last_rowid
+                    self.last_rowid = result.lastrowid
+                    if (hash_id or pk) and self.last_rowid:
+                        # Set self.last_pk to the pk(s) for that rowid
+                        row = list(self.rows_where("rowid = ?", [self.last_rowid]))[0]
+                        if hash_id:
+                            self.last_pk = row[hash_id]
+                        elif isinstance(pk, str):
+                            self.last_pk = row[resolve_casing(pk, row)]
+                        else:
+                            self.last_pk = tuple(
+                                row[resolve_casing(p, row)] for p in pk
+                            )
+                    else:
+                        self.last_pk = self.last_rowid
             else:
                 # For an upsert use first_record from earlier
                 if list_mode:

tests/test_create.py

@@ -953,6 +953,24 @@ def test_insert_ignore(fresh_db):
     assert rows == [{"id": 1, "bar": 2}]
 
 
+def test_insert_ignore_with_pk_after_other_table_insert(fresh_db):
+    # https://github.com/simonw/sqlite-utils/issues/554
+    user = {"id": "abc", "name": "david"}
+
+    fresh_db["users"].insert(user, pk="id")
+    fresh_db["comments"].insert_all(
+        [
+            {"id": "def", "text": "ok"},
+            {"id": "ghi", "text": "great"},
+        ],
+    )
+
+    table = fresh_db["users"].insert(user, pk="id", ignore=True)
+
+    assert table.last_pk == "abc"
+    assert list(fresh_db["users"].rows) == [user]
+
+
 def test_insert_hash_id(fresh_db):
     dogs = fresh_db["dogs"]
     id = dogs.insert({"name": "Cleo", "twitter": "cleopaws"}, hash_id="id").last_pk