added docs and tests, style check

docs/en/interfaces/formats.md

@@ -74,6 +74,7 @@ The supported formats are:
 | [ArrowStream](#data-format-arrow-stream)                                                  | ✔    | ✔     |
 | [ORC](#data-format-orc)                                                                   | ✔    | ✔     |
 | [One](#data-format-one)                                                                   | ✔    | ✗     |
+| [Npy](#data-format-npy)                                                                   | ✔    | ✗     |
 | [RowBinary](#rowbinary)                                                                   | ✔    | ✔     |
 | [RowBinaryWithNames](#rowbinarywithnamesandtypes)                                         | ✔    | ✔     |
 | [RowBinaryWithNamesAndTypes](#rowbinarywithnamesandtypes)                                 | ✔    | ✔     |
@@ -2445,6 +2446,26 @@ Result:
 └──────────────┘
 ```
 
+## Npy {#data-format-npy}
+
+This function is designed to load a NumPy array from a .npy file into ClickHouse. The NumPy file format is a binary format used for efficiently storing arrays of numerical data. It stores all the top-level dimension objects as a separate column.
+
+**Example**
+
+Query:
+```sql
+SELECT *
+FROM file('example_array.npy', Npy)
+```
+
+Result:
+```
+┌─array─────────┐
+│ [[1],[2],[3]] │
+│ [[4],[5],[6]] │
+└───────────────┘
+```
+
 ## LineAsString {#lineasstring}
 
 In this format, every line of input data is interpreted as a single string value. This format can only be parsed for table with a single field of type [String](/docs/en/sql-reference/data-types/string.md). The remaining columns must be set to [DEFAULT](/docs/en/sql-reference/statements/create/table.md/#default) or [MATERIALIZED](/docs/en/sql-reference/statements/create/table.md/#materialized), or omitted.

src/Processors/Formats/Impl/NpyRowInputFormat.cpp

@@ -37,9 +37,8 @@ namespace DB
 namespace ErrorCodes
 {
     extern const int INCORRECT_DATA;
-    extern const int CANNOT_PARSE_ESCAPE_SEQUENCE;
-    extern const int CANNOT_READ_ALL_DATA;
-    extern const int CANNOT_PARSE_INPUT_ASSERTION_FAILED;
+    extern const int BAD_ARGUMENTS;
+    extern const int LOGICAL_ERROR;
 }
 
 
@@ -119,16 +118,21 @@ std::vector<int> parseShape(String shapeString)
     shapeString.erase(std::remove(shapeString.begin(), shapeString.end(), ')'), shapeString.end());
 
     // Use a string stream to extract integers
-    std::istringstream ss(shapeString);
-    int value;
-    char comma; // to handle commas between values
+    String value;
 
     std::vector<int> shape;
 
-    while (ss >> value) {
-        shape.push_back(value);
-        ss >> comma; // read the comma
+    size_t start = 0, end = 0;
+
+    while ((end = shapeString.find(',', start)) != std::string::npos)
+    {
+        shape.push_back(std::stoi(shapeString.substr(start, end - start)));
+        start = end + 1;
     }
+
+    // Add the last token (or the only token if no delimiter is found)
+    if (start != shapeString.length())
+        shape.push_back(std::stoi(shapeString.substr(start)));
     return shape;
 }
 

tests/queries/0_stateless/02895_npy_format.reference

@@ -0,0 +1,28 @@
+1
+2
+3
+1.1
+2.2
+3.3
+1
+a
+c
+1
+a
+c
+[1,2,3]
+[4,5,6]
+[1.1,2.22,3.33]
+[4.4,5.5,6.6]
+['a','b','c']
+['e','f','g']
+['a','b','c']
+['e','f','g']
+[1]
+[0]
+[1]
+[0]
+[0,0,0]
+[0,0,0]
+[[1,2],[3,4]]
+[[5,6],[7,8]]

tests/queries/0_stateless/02895_npy_format.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+# Tags: no-fasttest
+
+CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CURDIR"/../shell_config.sh
+
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/one_dim.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/one_dim_float.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/one_dim_str.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/one_dim_unicode.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/two_dim.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/two_dim_float.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/two_dim_str.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/two_dim_unicode.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/two_dim_bool.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/two_dim_null.npy')"
+$CLICKHOUSE_LOCAL -q "select * from file('$CURDIR/data_npy/three_dim.npy')"