chdb 3.2.0__cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl → 3.4.0__cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

chdb/__init__.py

@@ -19,7 +19,7 @@ _process_result_format_funs = {
 # UDF script path will be f"{g_udf_path}/{func_name}.py"
 g_udf_path = ""
 
-chdb_version = ('3', '2', '0')
+chdb_version = ('3', '4', '0')
 if sys.version_info[:2] >= (3, 7):
     # get the path of the current file
     current_path = os.path.dirname(os.path.abspath(__file__))

chdb/session/state.py

@@ -1,5 +1,3 @@
-import tempfile
-import shutil
 import warnings
 
 import chdb
@@ -51,11 +49,9 @@ class Session:
             )
             g_session.close()
             g_session_path = None
-        if path is None or ":memory:" in path:
-            self._cleanup = True
-            self._path = tempfile.mkdtemp()
+        if path is None:
+            self._path = ":memory:"
         else:
-            self._cleanup = False
             self._path = path
         if chdb.g_udf_path != "":
             self._udf_path = chdb.g_udf_path
@@ -84,8 +80,6 @@ class Session:
         self.close()
 
     def close(self):
-        if self._cleanup:
-            self.cleanup()
         if self._conn is not None:
             self._conn.close()
             self._conn = None
@@ -95,13 +89,7 @@ class Session:
 
     def cleanup(self):
         try:
-            if self._conn is not None:
-                self._conn.close()
-                self._conn = None
-            shutil.rmtree(self._path)
-            global g_session, g_session_path
-            g_session = None
-            g_session_path = None
+            self.close()
         except:  # noqa
             pass
 

{chdb-3.2.0.dist-info → chdb-3.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chdb
-Version: 3.2.0
+Version: 3.4.0
 Summary: chDB is an in-process SQL OLAP Engine powered by ClickHouse
 Home-page: https://github.com/chdb-io/chdb
 Author: auxten
@@ -51,11 +51,11 @@ Requires-Dist: pandas >=2.0.0
 
 
 > chDB is an in-process SQL OLAP Engine powered by ClickHouse  [^1]
-> For more details: [The birth of chDB](https://auxten.com/the-birth-of-chdb/) 
+> For more details: [The birth of chDB](https://auxten.com/the-birth-of-chdb/)
 
 
 ## Features
-     
+
 * In-process SQL OLAP Engine, powered by ClickHouse
 * No need to install ClickHouse
 * Minimized data copy from C++ to Python with [python memoryview](https://docs.python.org/3/c-api/memoryview.html)
@@ -146,7 +146,7 @@ res = chdb.query('select version()', 'Pretty'); print(res)
 # See more data type format in tests/format_output.py
 res = chdb.query('select * from file("data.parquet", Parquet)', 'JSON'); print(res)
 res = chdb.query('select * from file("data.csv", CSV)', 'CSV');  print(res)
-print(f"SQL read {res.rows_read()} rows, {res.bytes_read()} bytes, elapsed {res.elapsed()} seconds")
+print(f"SQL read {res.rows_read()} rows, {res.bytes_read()} bytes, storage read {res.storage_rows_read()} rows, {res.storage_bytes_read()} bytes, elapsed {res.elapsed()} seconds")
 ```
 
 ### Pandas dataframe output
@@ -171,6 +171,8 @@ ret_tbl = cdf.query(sql="select * from __tbl1__ t1 join __tbl2__ t2 on t1.a = t2
 print(ret_tbl)
 # Query on the DataFrame Table
 print(ret_tbl.query('select b, sum(a) from __table__ group by b'))
+# Pandas DataFrames are automatically registered as temporary tables in ClickHouse
+chdb.query("SELECT * FROM Python(df1) t1 JOIN Python(df2) t2 ON t1.a = t2.c").show()
 ```
 </details>
 
@@ -318,10 +320,19 @@ df = pd.DataFrame(
     {
         "a": [1, 2, 3, 4, 5, 6],
         "b": ["tom", "jerry", "auxten", "tom", "jerry", "auxten"],
+        "dict_col": [
+            {'id': 1, 'tags': ['urgent', 'important'], 'metadata': {'created': '2024-01-01'}},
+            {'id': 2, 'tags': ['normal'], 'metadata': {'created': '2024-02-01'}},
+            {'id': 3, 'name': 'tom'},
+            {'id': 4, 'value': '100'},
+            {'id': 5, 'value': 101},
+            {'id': 6, 'value': 102},
+        ],
     }
 )
 
 chdb.query("SELECT b, sum(a) FROM Python(df) GROUP BY b ORDER BY b").show()
+chdb.query("SELECT dict_col.id FROM Python(df) WHERE dict_col.value='100'").show()
 ```
 
 ### Query on Arrow Table
@@ -333,12 +344,19 @@ arrow_table = pa.table(
     {
         "a": [1, 2, 3, 4, 5, 6],
         "b": ["tom", "jerry", "auxten", "tom", "jerry", "auxten"],
+        "dict_col": [
+            {'id': 1, 'value': 'tom'},
+            {'id': 2, 'value': 'jerry'},
+            {'id': 3, 'value': 'auxten'},
+            {'id': 4, 'value': 'tom'},
+            {'id': 5, 'value': 'jerry'},
+            {'id': 6, 'value': 'auxten'},
+        ],
     }
 )
 
-chdb.query(
-    "SELECT b, sum(a) FROM Python(arrow_table) GROUP BY b ORDER BY b", "debug"
-).show()
+chdb.query("SELECT b, sum(a) FROM Python(arrow_table) GROUP BY b ORDER BY b").show()
+chdb.query("SELECT dict_col.id FROM Python(arrow_table) WHERE dict_col.value='tom'").show()
 ```
 
 ### Query on chdb.PyReader class instance
@@ -362,24 +380,79 @@ class myReader(chdb.PyReader):
     def read(self, col_names, count):
         print("Python func read", col_names, count, self.cursor)
         if self.cursor >= len(self.data["a"]):
+            self.cursor = 0
             return []
         block = [self.data[col] for col in col_names]
         self.cursor += len(block[0])
         return block
 
+    def get_schema(self):
+        return [
+            ("a", "int"),
+            ("b", "str"),
+            ("dict_col", "json")
+        ]
+
 reader = myReader(
     {
         "a": [1, 2, 3, 4, 5, 6],
         "b": ["tom", "jerry", "auxten", "tom", "jerry", "auxten"],
+        "dict_col": [
+            {'id': 1, 'tags': ['urgent', 'important'], 'metadata': {'created': '2024-01-01'}},
+            {'id': 2, 'tags': ['normal'], 'metadata': {'created': '2024-02-01'}},
+            {'id': 3, 'name': 'tom'},
+            {'id': 4, 'value': '100'},
+            {'id': 5, 'value': 101},
+            {'id': 6, 'value': 102}
+        ],
     }
 )
 
-chdb.query(
-    "SELECT b, sum(a) FROM Python(reader) GROUP BY b ORDER BY b"
-).show()
+chdb.query("SELECT b, sum(a) FROM Python(reader) GROUP BY b ORDER BY b").show()
+chdb.query("SELECT dict_col.id FROM Python(reader) WHERE dict_col.value='100'").show()
 ```
 
-see also: [test_query_py.py](tests/test_query_py.py).
+see also: [test_query_py.py](tests/test_query_py.py) and [test_query_json.py](tests/test_query_json.py).
+
+### JSON Type Inference
+
+chDB automatically converts Python dictionary objects to ClickHouse JSON types from these sources:
+
+1. **Pandas DataFrame**
+    - Columns with `object` dtype are sampled (default 10,000 rows) to detect JSON structures.
+    - Control sampling via SQL settings:
+      ```sql
+      SET pandas_analyze_sample = 10000  -- Default sampling
+      SET pandas_analyze_sample = 0      -- Force String type
+      SET pandas_analyze_sample = -1     -- Force JSON type
+      ```
+    - Columns are converted to `String` if sampling finds non-dictionary values.
+
+2. **Arrow Table**
+    - `struct` type columns are automatically mapped to JSON columns.
+    - Nested structures preserve type information.
+
+3. **chdb.PyReader**
+    - Implement custom schema mapping in `get_schema()`:
+      ```python
+      def get_schema(self):
+          return [
+              ("c1", "JSON"),  # Explicit JSON mapping
+              ("c2", "String")
+          ]
+      ```
+    - Column types declared as "JSON" will bypass auto-detection.
+
+When converting Python dictionary objects to JSON columns:
+
+1. **Nested Structures**
+    - Recursively process nested dictionaries, lists, tuples and NumPy arrays.
+
+2. **Primitive Types**
+    - Automatic type recognition for basic types such as integers, floats, strings, and booleans, and more.
+
+3. **Complex Objects**
+    - Non-primitive types will be converted to strings.
 
 ### Limitations
 

{chdb-3.2.0.dist-info → chdb-3.4.0.dist-info}/RECORD

@@ -1,9 +1,9 @@
 chdb/__main__.py,sha256=xNNtDY38d973YM5dlxiIazcqqKhXJSpNb7JflyyrXGE,1185
-chdb/__init__.py,sha256=yuWj0i3_5-uBRZCyZMBKIiBR1MmjEyAjcuxKTm076jI,3762
-chdb/_chdb.cpython-38-aarch64-linux-gnu.so,sha256=p6q6ZujWMVJL1w2bFECrDzmf69T2tDXH7BYbjmtGEQQ,533414320
+chdb/__init__.py,sha256=pNYyLRqm2s5hG1rPhVLECZXvJQ60EGPt_OC88W90j0w,3762
+chdb/_chdb.cpython-38-aarch64-linux-gnu.so,sha256=jWd7xJeE74xK21ep7dDeYMtYrEW-VVzxYN4HgQf8PiY,568828616
 chdb/rwabc.py,sha256=tbiwCrXirfrfx46wCJxS64yvFe6pVWIPGdSuvrAL5Ys,2102
 chdb/session/__init__.py,sha256=fCUROZ5L1-92o2lcASiWJpFu-80-kDoSrNfouLEmLg8,50
-chdb/session/state.py,sha256=UtObxVuyNgeqFkTXVHtmOknR90Pe1dEzbOpKFDBYOkg,4845
+chdb/session/state.py,sha256=m7K9zZtoMQTlh-pfmSyJV38pAe6eHNTPtOvlHYrImhA,4436
 chdb/dataframe/__init__.py,sha256=1_mrZZiJwqBTnH_P8_FCbbYXIWWY5sxnaFpe3-tDLF4,680
 chdb/dataframe/query.py,sha256=ggvE8A5vtabFg9gSTp99S7LCrnIEwbWtb-PtJVT8Ct0,12759
 chdb/utils/__init__.py,sha256=tXRcwBRGW2YQNBZWV4Mitw5QlCu_qlSRCjllw15XHbs,171
@@ -21,8 +21,8 @@ chdb/dbapi/constants/FIELD_TYPE.py,sha256=ytFzgAnGmb9hvdsBlnK68qdZv_a6jYFIXT6VSA
 chdb/dbapi/constants/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chdb/state/__init__.py,sha256=RVUIWDqDi7gte4Os7Mz1wPXFyFpdHT_p1klJC7QtluI,55
 chdb/state/sqlitelike.py,sha256=v0xh9jWirHzhDVq26C2213LxfaDbRulSAhSHaTiZ24c,12283
-chdb-3.2.0.dist-info/RECORD,,
-chdb-3.2.0.dist-info/LICENSE.txt,sha256=isYVtNCO5910aj6e9bJJ6kQceivkLqsMlFSNYwzGGKI,11366
-chdb-3.2.0.dist-info/WHEEL,sha256=kTTaziUGh4IgOXqp-kkEc0J_ej7kOw0CdWocYU-1ZR0,149
-chdb-3.2.0.dist-info/METADATA,sha256=SPZ4Gn_IrMBxh3-zVDXQpQejpUV33SdEAVdqGarSLJ8,21517
-chdb-3.2.0.dist-info/top_level.txt,sha256=se0Jj0A2-ijfMW51hIjiuNyDJPqy5xJU1G8a_IEdllI,11
+chdb-3.4.0.dist-info/RECORD,,
+chdb-3.4.0.dist-info/LICENSE.txt,sha256=isYVtNCO5910aj6e9bJJ6kQceivkLqsMlFSNYwzGGKI,11366
+chdb-3.4.0.dist-info/WHEEL,sha256=kTTaziUGh4IgOXqp-kkEc0J_ej7kOw0CdWocYU-1ZR0,149
+chdb-3.4.0.dist-info/METADATA,sha256=niEMQj5RD1T34yBzfkJzW9K4gziEvAnITAuzNN10AIs,24622
+chdb-3.4.0.dist-info/top_level.txt,sha256=se0Jj0A2-ijfMW51hIjiuNyDJPqy5xJU1G8a_IEdllI,11