[REVIEW] Switch engine=cudf to the new JSON reader

docs/cudf/source/user_guide/io/read-json.md

@@ -19,14 +19,14 @@ each object corresponds to a row.
     {"a": "v2", "b": 7},
     {"a": "v3", "b": 5}
 ]'''
->>> df_records = cudf.read_json(j, engine='cudf_experimental')
+>>> df_records = cudf.read_json(j, engine='cudf')
 
 >>> j = '\n'.join([
 ...     '{"a": "v1", "b": 12}',
 ...     '{"a": "v2", "b": 7}',
 ...     '{"a": "v3", "b": 5}'
 ... ])
->>> df_lines = cudf.read_json(j, lines=True, engine='cudf_experimental')
+>>> df_lines = cudf.read_json(j, lines=True, engine='cudf')
 
 >>> df_lines
     a   b
@@ -49,7 +49,7 @@ reading nested JSON data.
     {"list": [0,1,2], "struct": {"k":"v1"}},
     {"list": [3,4,5], "struct": {"k":"v2"}}
 ]'''
->>> df = cudf.read_json(j, engine='cudf_experimental')
+>>> df = cudf.read_json(j, engine='cudf')
 >>> df
         list       struct
 0  [0, 1, 2]  {'k': 'v1'}
@@ -61,7 +61,7 @@ reading nested JSON data.
 ...     '{"a": [{"k": 0}], "b": {"k": [0, 1], "m": 5}}',
 ...     '{"a": [{"k": 1}, {"k": 2}], "b": {"k": [2, 3], "m": 6}}',
 ... ])
->>> df = cudf.read_json(j, lines=True, engine='cudf_experimental')
+>>> df = cudf.read_json(j, lines=True, engine='cudf')
 >>> df
                       a                      b
 0            [{'k': 0}]  {'k': [0, 1], 'm': 5}
@@ -97,7 +97,7 @@ should be adjacent, as shown in the following example.
 ...         j,
 ...         lines=True,
 ...         byte_range=(chunk_size * x, chunk_size),
-...         engine='cudf_experimental'
+...         engine='cudf'
 ...     )
 ...     data.append(d)
 >>> df = cudf.concat(data)
@@ -115,7 +115,7 @@ raw strings, or file-like objects, as well as iterables of these sources.
 >>> j1 = '{"id":0}\n{"id":1}\n'
 >>> j2 = '{"id":2}\n{"id":3}\n'
 
->>> df = cudf.read_json([j1, j2], lines=True, engine='cudf_experimental')
+>>> df = cudf.read_json([j1, j2], lines=True, engine='cudf')
 ```
 
 ## Unpacking list and struct data
@@ -133,7 +133,7 @@ following example demonstrates how to extract data from a struct column.
 ...    '{"x": "Jakarta", "y": {"country": "Indonesia", "iso2": "ID"}}',
 ...    '{"x": "Shanghai", "y": {"country": "China", "iso2": "CN"}}'
 ... ])
->>> df = cudf.read_json(j, lines=True, engine='cudf_experimental')
+>>> df = cudf.read_json(j, lines=True, engine='cudf')
 >>> df = df.drop(columns='y').join(df['y'].struct.explode())
 >>> df
           x    country iso2
@@ -156,7 +156,7 @@ list column.
 ...    '{"name": "New Bedford, MA", "coord": [41.63, -70.93]}'
 ... ])
 
->>> df = cudf.read_json(j, lines=True, engine='cudf_experimental')
+>>> df = cudf.read_json(j, lines=True, engine='cudf')
 >>> df['latitude'] = df['coord'].list.get(0)
 >>> df['longitude'] = df['coord'].list.get(1)
 >>> df = df.drop(columns='coord')
@@ -181,7 +181,7 @@ the parent dataframe.
 ...    '{"product": "shirts", "ratings": [3, 4]}'
 ... ])
 
->>> df = cudf.read_json(j, lines=True, engine='cudf_experimental')
+>>> df = cudf.read_json(j, lines=True, engine='cudf')
 >>> df = df.drop(columns='ratings').join(df['ratings'].explode())
 >>> df
   product  ratings
@@ -217,7 +217,7 @@ reads a JSON object as a single line and then extracts the
 }'''
 
 # first read the JSON object with line=True
->>> df = cudf.read_json(j, lines=True, engine='cudf_experimental')
+>>> df = cudf.read_json(j, lines=True, engine='cudf')
 >>> df
              metadata                                            records
 0  {'vehicle': 'car'}  [{'id': 0, 'distance': 1.2}, {'id': 1, 'distan...

python/cudf/cudf/_lib/json.pyx

@@ -31,7 +31,7 @@ cpdef read_json(object filepaths_or_buffers,
                 bool lines,
                 object compression,
                 object byte_range,
-                bool experimental,
+                bool legacy,
                 bool keep_quotes):
     """
     Cython function to call into libcudf API, see `read_json`.
@@ -71,6 +71,8 @@ cpdef read_json(object filepaths_or_buffers,
             c_compression = cudf_io_types.compression_type.GZIP
         elif compression == 'bz2':
             c_compression = cudf_io_types.compression_type.BZIP2
+        elif compression == 'zip':
+            c_compression = cudf_io_types.compression_type.ZIP
         else:
             c_compression = cudf_io_types.compression_type.AUTO
     else:
@@ -99,7 +101,7 @@ cpdef read_json(object filepaths_or_buffers,
         .lines(c_lines)
         .byte_range_offset(c_range_offset)
         .byte_range_size(c_range_size)
-        .legacy(not experimental)
+        .legacy(legacy)
         .build()
     )
     if is_list_like_dtypes:

python/cudf/cudf/io/json.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2019-2022, NVIDIA CORPORATION.
+# Copyright (c) 2019-2023, NVIDIA CORPORATION.
 
 import warnings
 from collections import abc
@@ -37,16 +37,31 @@ def read_json(
             f"or a bool, or None. Got {type(dtype)}"
         )
 
-    if engine == "cudf" and not lines:
+    if engine == "cudf_experimental":
+        raise ValueError(
+            "engine='cudf_experimental' support has been removed, "
+            "use `engine='cudf'`"
+        )
+
+    if engine == "cudf_legacy":
+        # TODO: Deprecated in 23.02, please
+        # give some time until `cudf_legacy`
+        # support can be removed completely.
+        warnings.warn(
+            "engine='cudf_legacy' is a deprecated engine."
+            "This will be removed in a future release."
+            "Please switch to using engine='cudf'.",
+            FutureWarning,
+        )
+    if engine == "cudf_legacy" and not lines:
         raise ValueError(f"{engine} engine only supports JSON Lines format")
-    if engine != "cudf_experimental" and keep_quotes:
+    if engine != "cudf" and keep_quotes:
         raise ValueError(
-            "keep_quotes='True' is supported only with"
-            " engine='cudf_experimental'"
+            "keep_quotes='True' is supported only with engine='cudf'"
         )
     if engine == "auto":
         engine = "cudf" if lines else "pandas"
-    if engine == "cudf" or engine == "cudf_experimental":
+    if engine == "cudf_legacy" or engine == "cudf":
         if dtype is None:
             dtype = True
 
@@ -97,7 +112,7 @@ def read_json(
             lines,
             compression,
             byte_range,
-            engine == "cudf_experimental",
+            engine == "cudf_legacy",
             keep_quotes,
         )
     else: