chdb 3.1.2__cp39-cp39-macosx_10_15_x86_64.whl → 3.3.0__cp39-cp39-macosx_10_15_x86_64.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', '1', '2')
+chdb_version = ('3', '3', '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

@@ -4,7 +4,7 @@ import warnings
 
 import chdb
 from ..state import sqlitelike as chdb_stateful
-
+from ..state.sqlitelike import StreamingResult
 
 g_session = None
 g_session_path = None
@@ -120,3 +120,16 @@ Eg: conn = connect(f"db_path?verbose&log-level=test")"""
 
     # alias sql = query
     sql = query
+
+    def send_query(self, sql, fmt="CSV") -> StreamingResult:
+        """
+        Execute a streaming query.
+        """
+        if fmt == "Debug":
+            warnings.warn(
+                """Debug format is not supported in Session.query
+Please try use parameters in connection string instead:
+Eg: conn = connect(f"db_path?verbose&log-level=test")"""
+            )
+            fmt = "CSV"
+        return self._conn.send_query(sql, fmt)

chdb/state/sqlitelike.py

@@ -40,6 +40,57 @@ def to_df(r):
     return t.to_pandas(use_threads=True)
 
 
+class StreamingResult:
+    def __init__(self, c_result, conn, result_func):
+        self._result = c_result
+        self._result_func = result_func
+        self._conn = conn
+        self._exhausted = False
+
+    def fetch(self):
+        """Fetch next chunk of streaming results"""
+        if self._exhausted:
+            return None
+
+        try:
+            result = self._conn.streaming_fetch_result(self._result)
+            if result is None or result.rows_read() == 0:
+                self._exhausted = True
+                return None
+            return self._result_func(result)
+        except Exception as e:
+            self._exhausted = True
+            raise RuntimeError(f"Streaming query failed: {str(e)}") from e
+
+    def __iter__(self):
+        return self
+
+    def __next__(self):
+        if self._exhausted:
+            raise StopIteration
+
+        chunk = self.fetch()
+        if chunk is None:
+            self._exhausted = True
+            raise StopIteration
+
+        return chunk
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        pass
+
+    def cancel(self):
+        self._exhausted = True
+
+        try:
+            self._conn.streaming_cancel_query(self._result)
+        except Exception as e:
+            raise RuntimeError(f"Failed to cancel streaming query: {str(e)}") from e
+
+
 class Connection:
     def __init__(self, connection_string: str):
         # print("Connection", connection_string)
@@ -59,6 +110,15 @@ class Connection:
         result = self._conn.query(query, format)
         return result_func(result)
 
+    def send_query(self, query: str, format: str = "CSV") -> StreamingResult:
+        lower_output_format = format.lower()
+        result_func = _process_result_format_funs.get(lower_output_format, lambda x: x)
+        if lower_output_format in _arrow_format:
+            format = "Arrow"
+
+        c_stream_result = self._conn.send_query(query, format)
+        return StreamingResult(c_stream_result, self._conn, result_func)
+
     def close(self) -> None:
         # print("close")
         if self._cursor:

{chdb-3.1.2.dist-info → chdb-3.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chdb
-Version: 3.1.2
+Version: 3.3.0
 Summary: chDB is an in-process SQL OLAP Engine powered by ClickHouse
 Home-page: https://github.com/chdb-io/chdb
 Author: auxten
@@ -54,11 +54,11 @@ Dynamic: requires-python
 
 
 > 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)
@@ -96,6 +96,44 @@ python3 -m chdb "SELECT 1,'abc'" Pretty
 ### Data Input
 The following methods are available to access on-disk and in-memory data formats:
 
+<details>
+    <summary><h4>🗂️ Connection based API (recommended)</h4></summary>
+
+```python
+import chdb
+
+# Create a connection (in-memory by default)
+conn = chdb.connect(":memory:")
+# Or use file-based: conn = chdb.connect("test.db")
+
+# Create a cursor
+cur = conn.cursor()
+
+# Execute queries
+cur.execute("SELECT number, toString(number) as str FROM system.numbers LIMIT 3")
+
+# Fetch data in different ways
+print(cur.fetchone())    # Single row: (0, '0')
+print(cur.fetchmany(2))  # Multiple rows: ((1, '1'), (2, '2'))
+
+# Get column information
+print(cur.column_names())  # ['number', 'str']
+print(cur.column_types())  # ['UInt64', 'String']
+
+# Use the cursor as an iterator
+cur.execute("SELECT number FROM system.numbers LIMIT 3")
+for row in cur:
+    print(row)
+
+# Always close resources when done
+cur.close()
+conn.close()
+```
+
+For more details, see [examples/connect.py](examples/connect.py).
+</details>
+
+
 <details>
     <summary><h4>🗂️ Query On File</h4> (Parquet, CSV, JSON, Arrow, ORC and 60+)</summary>
 
@@ -111,7 +149,7 @@ 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
@@ -136,6 +174,8 @@ 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>
 
@@ -221,6 +261,56 @@ see also: [test_udf.py](tests/test_udf.py).
 </details>
 
 
+<details>
+    <summary><h4>🗂️ Streaming Query</h4></summary>
+
+Process large datasets with constant memory usage through chunked streaming.
+
+```python
+from chdb import session as chs
+
+sess = chs.Session()
+
+# Example 1: Basic example of using streaming query
+rows_cnt = 0
+with sess.send_query("SELECT * FROM numbers(200000)", "CSV") as stream_result:
+    for chunk in stream_result:
+        rows_cnt += chunk.rows_read()
+
+print(rows_cnt) # 200000
+
+# Example 2: Manual iteration with fetch()
+rows_cnt = 0
+stream_result = sess.send_query("SELECT * FROM numbers(200000)", "CSV")
+while True:
+    chunk = stream_result.fetch()
+    if chunk is None:
+        break
+    rows_cnt += chunk.rows_read()
+
+print(rows_cnt) # 200000
+
+# Example 3: Early cancellation demo
+rows_cnt = 0
+stream_result = sess.send_query("SELECT * FROM numbers(200000)", "CSV")
+while True:
+    chunk = stream_result.fetch()
+    if chunk is None:
+        break
+    if rows_cnt > 0:
+        stream_result.cancel()
+        break
+    rows_cnt += chunk.rows_read()
+
+print(rows_cnt) # 65409
+
+sess.close()
+```
+
+For more details, see [test_streaming_query.py](tests/test_streaming_query.py).
+</details>
+
+
 <details>
     <summary><h4>🗂️ Python Table Engine</h4></summary>
 
@@ -233,10 +323,19 @@ 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
@@ -248,12 +347,19 @@ 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
@@ -277,24 +383,79 @@ 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-3.1.2.dist-info → chdb-3.3.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
-chdb/__init__.py,sha256=Wb4a4CPgJ0j44kDuehkwITZV9Q6QOqyUmxA5PM6BbYk,3762
+chdb/__init__.py,sha256=KsqKKRN2T2Rspn94XwwtR45fT5viF5h6KUJ7JIETo1w,3762
 chdb/__main__.py,sha256=xNNtDY38d973YM5dlxiIazcqqKhXJSpNb7JflyyrXGE,1185
-chdb/_chdb.cpython-39-darwin.so,sha256=HtRrZzYGC5GBZqY0SSkvKnd3PNz7GQjzMV8QUeiZMiA,422085256
+chdb/_chdb.cpython-39-darwin.so,sha256=-IrhrMdI1OnciveQnl9jK7QzxTptb4biBLFIVa9brtc,422309072
 chdb/rwabc.py,sha256=tbiwCrXirfrfx46wCJxS64yvFe6pVWIPGdSuvrAL5Ys,2102
 chdb/dataframe/__init__.py,sha256=1_mrZZiJwqBTnH_P8_FCbbYXIWWY5sxnaFpe3-tDLF4,680
 chdb/dataframe/query.py,sha256=ggvE8A5vtabFg9gSTp99S7LCrnIEwbWtb-PtJVT8Ct0,12759
@@ -13,16 +13,16 @@ chdb/dbapi/times.py,sha256=_qXgDaYwsHntvpIKSKXp1rrYIgtq6Z9pLyLnO2XNoL0,360
 chdb/dbapi/constants/FIELD_TYPE.py,sha256=ytFzgAnGmb9hvdsBlnK68qdZv_a6jYFIXT6VSAb60z8,370
 chdb/dbapi/constants/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chdb/session/__init__.py,sha256=fCUROZ5L1-92o2lcASiWJpFu-80-kDoSrNfouLEmLg8,50
-chdb/session/state.py,sha256=nx9KlqZyPTHAflToXCJVRBUSMjJFvyh6x2akP7Gc7h0,4360
+chdb/session/state.py,sha256=UtObxVuyNgeqFkTXVHtmOknR90Pe1dEzbOpKFDBYOkg,4845
 chdb/state/__init__.py,sha256=RVUIWDqDi7gte4Os7Mz1wPXFyFpdHT_p1klJC7QtluI,55
-chdb/state/sqlitelike.py,sha256=6Y57vnf7LnA0KnpByKQq7PkEkEEOKK-ExaHQLb1bedQ,10498
+chdb/state/sqlitelike.py,sha256=v0xh9jWirHzhDVq26C2213LxfaDbRulSAhSHaTiZ24c,12283
 chdb/udf/__init__.py,sha256=qSMaPEre7w1pYz8uJ-iZtuu8wYOUNRcI_8UNuaOymGE,80
 chdb/udf/udf.py,sha256=z0A1RmyZrx55bykpvvS-LpVt1lMrQOexjvU5zxCdCSA,3935
 chdb/utils/__init__.py,sha256=tXRcwBRGW2YQNBZWV4Mitw5QlCu_qlSRCjllw15XHbs,171
 chdb/utils/trace.py,sha256=W-pvDoKlnzq6H_7FiWjr5_teN40UNE4E5--zbUrjOIc,2511
 chdb/utils/types.py,sha256=MGLFIjoDvu7Uc2Wy8EDY60jjue66HmMPxbhrujjrZxQ,7530
-chdb-3.1.2.dist-info/licenses/LICENSE.txt,sha256=isYVtNCO5910aj6e9bJJ6kQceivkLqsMlFSNYwzGGKI,11366
-chdb-3.1.2.dist-info/METADATA,sha256=cr0z9tTvWd_9_cckipHt8UBVZ0FBVOarA_6CTYwDxjA,19512
-chdb-3.1.2.dist-info/WHEEL,sha256=frmk8uyyRBGmQ11xC4icmh-xoy3HnCVGUtquUWdhsEY,109
-chdb-3.1.2.dist-info/top_level.txt,sha256=se0Jj0A2-ijfMW51hIjiuNyDJPqy5xJU1G8a_IEdllI,11
-chdb-3.1.2.dist-info/RECORD,,
+chdb-3.3.0.dist-info/licenses/LICENSE.txt,sha256=isYVtNCO5910aj6e9bJJ6kQceivkLqsMlFSNYwzGGKI,11366
+chdb-3.3.0.dist-info/METADATA,sha256=fRAJ-SRLZW1U7SpJeiGr2S7rKJyesMCGoQPpcPc6U1s,24690
+chdb-3.3.0.dist-info/WHEEL,sha256=rhBzRBb5NVgz08EmkbnoZQLYki4NZ37t5Zn8NZLHrUo,109
+chdb-3.3.0.dist-info/top_level.txt,sha256=se0Jj0A2-ijfMW51hIjiuNyDJPqy5xJU1G8a_IEdllI,11
+chdb-3.3.0.dist-info/RECORD,,

{chdb-3.1.2.dist-info → chdb-3.3.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: false
 Tag: cp39-cp39-macosx_10_15_x86_64