From acdcb05c58533923e6636fc80494ca66aebbc8a2 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sun, 10 Apr 2022 09:42:14 -0700
Subject: [PATCH 01/10] BUG: to_json incorrectly localizes tz-naive datetimes
 to UTC

---
 doc/source/whatsnew/v1.5.0.rst                |  1 +
 .../_libs/src/ujson/python/date_conversions.c | 31 +++++++++++++++++--
 pandas/_libs/src/ujson/python/objToJSON.c     | 29 ++++++++++++++++-
 .../tslibs/src/datetime/np_datetime_strings.c | 15 ++++-----
 .../tests/io/json/test_json_table_schema.py   | 14 ++++-----
 .../json/test_json_table_schema_ext_dtype.py  |  4 +--
 pandas/tests/io/json/test_pandas.py           | 31 ++++++++++++++++---
 7 files changed, 100 insertions(+), 25 deletions(-)

diff --git a/doc/source/whatsnew/v1.5.0.rst b/doc/source/whatsnew/v1.5.0.rst
index 73dc832e2007b..bd891e5a84d4f 100644
--- a/doc/source/whatsnew/v1.5.0.rst
+++ b/doc/source/whatsnew/v1.5.0.rst
@@ -563,6 +563,7 @@ I/O
 - Bug in Parquet roundtrip for Interval dtype with ``datetime64[ns]`` subtype (:issue:`45881`)
 - Bug in :func:`read_excel` when reading a ``.ods`` file with newlines between xml elements (:issue:`45598`)
 - Bug in :func:`read_parquet` when ``engine="fastparquet"`` where the file was not closed on error (:issue:`46555`)
+- Bug in :meth:`DataFrame.to_json`, :meth:`Series.to_json`, and :meth:`Index.to_json` where tz-aware datetimes were being incorrectly localized to UTC (:issue:`38760`)
 
 Period
 ^^^^^^
diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index 0744c6af74480..c11e4ed60541c 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -54,8 +54,8 @@ char *int64ToIso(int64_t value, NPY_DATETIMEUNIT base, size_t *len) {
         PyErr_NoMemory();
         return NULL;
     }
-
-    ret_code = make_iso_8601_datetime(&dts, result, *len, base);
+    ret_code = make_iso_8601_datetime(&dts, result, *len,
+                                      0 /* datetime64 is always naive */, base);
     if (ret_code != 0) {
         PyErr_SetString(PyExc_ValueError,
                         "Could not convert datetime value to string");
@@ -90,7 +90,32 @@ char *PyDateTimeToIso(PyObject *obj, NPY_DATETIMEUNIT base,
 
     *len = (size_t)get_datetime_iso_8601_strlen(0, base);
     char *result = PyObject_Malloc(*len);
-    ret = make_iso_8601_datetime(&dts, result, *len, base);
+    // Check to see if PyDateTime has a timezone.
+    // Don't convert to UTC if it doesn't.
+    int is_tz_aware = 0;
+    PyObject *tmp;
+    PyObject *offset;
+    if (PyObject_HasAttrString((PyObject*)obj, "tzinfo")) {
+        tmp = PyObject_GetAttrString(obj, "tzinfo");
+        if (tmp == NULL) {
+            return -1;
+        }
+        if (tmp == Py_None) {
+            Py_DECREF(tmp);
+        } else {
+            offset = PyObject_CallMethod(tmp, "utcoffset", "O", obj);
+            if (offset == NULL) {
+                Py_DECREF(tmp);
+                return -1;
+            }
+            Py_DECREF(tmp);
+            if (offset != Py_None) {
+                is_tz_aware = 1;
+            }
+            Py_DECREF(offset);
+        }
+    }
+    ret = make_iso_8601_datetime(&dts, result, *len, is_tz_aware, base);
 
     if (ret != 0) {
         PyErr_SetString(PyExc_ValueError,
diff --git a/pandas/_libs/src/ujson/python/objToJSON.c b/pandas/_libs/src/ujson/python/objToJSON.c
index c4609992342c3..8913da477ea92 100644
--- a/pandas/_libs/src/ujson/python/objToJSON.c
+++ b/pandas/_libs/src/ujson/python/objToJSON.c
@@ -221,8 +221,19 @@ static PyObject *get_values(PyObject *obj) {
         // The special cases to worry about are dt64tz and category[dt64tz].
         //  In both cases we want the UTC-localized datetime64 ndarray,
         //  without going through and object array of Timestamps.
+        if (PyObject_HasAttrString(obj, "tz")) {
+            PyObject *tz = PyObject_GetAttrString(obj, "tz");
+            if (tz != Py_None) {
+                // Go through object array if we have dt64tz, since tz info will
+                // be lost if values is used directly.
+                Py_DECREF(tz);
+                values = PyObject_CallMethod(obj, "__array__", NULL);
+                PyObject_Print(values, stdout, NULL);
+                return values;
+            }
+            Py_DECREF(tz);
+        }
         values = PyObject_GetAttrString(obj, "values");
-
         if (values == NULL) {
             // Clear so we can subsequently try another method
             PyErr_Clear();
@@ -707,6 +718,22 @@ void PdBlock_iterBegin(JSOBJ _obj, JSONTypeContext *tc) {
 
     for (i = 0; i < PyObject_Length(arrays); i++) {
         array = PyList_GET_ITEM(arrays, i);
+        // tz information is lost when dt64tz is converted
+        // to numpy arrays.
+        // TODO(lithomas1): Patch column_arrays(actually values_for_json)
+        // to return EAs instead of casting to object
+        if (PyArray_TYPE((PyArrayObject *)array) == NPY_DATETIME) {
+            PyObject *mgr = PyObject_GetAttrString(obj, "_mgr");
+            PyObject *dtarr = PyObject_CallMethod(mgr, "iget_values", "n", i);
+            PyObject *tz = PyObject_GetAttrString(dtarr, "tz");
+            if (tz != Py_None) {
+                // we have a timezone, use an object array of Timestamp
+                array = PyObject_CallMethod(dtarr, "__array__", NULL);
+            }
+            Py_DECREF(mgr);
+            Py_DECREF(dtarr);
+            Py_DECREF(tz);
+        }
         if (!array) {
             GET_TC(tc)->iterNext = NpyArr_iterNextNone;
             goto ARR_RET;
diff --git a/pandas/_libs/tslibs/src/datetime/np_datetime_strings.c b/pandas/_libs/tslibs/src/datetime/np_datetime_strings.c
index 847e84b21c06c..8e05c5c9b98e3 100644
--- a/pandas/_libs/tslibs/src/datetime/np_datetime_strings.c
+++ b/pandas/_libs/tslibs/src/datetime/np_datetime_strings.c
@@ -605,7 +605,7 @@ int get_datetime_iso_8601_strlen(int local, NPY_DATETIMEUNIT base) {
  *  string was too short).
  */
 int make_iso_8601_datetime(npy_datetimestruct *dts, char *outstr, int outlen,
-                           NPY_DATETIMEUNIT base) {
+                           int utc, NPY_DATETIMEUNIT base) {
     char *substr = outstr;
     int sublen = outlen;
     int tmplen;
@@ -884,13 +884,14 @@ int make_iso_8601_datetime(npy_datetimestruct *dts, char *outstr, int outlen,
 
 add_time_zone:
     /* UTC "Zulu" time */
-    if (sublen < 1) {
-        goto string_too_short;
+    if (utc) {
+        if (sublen < 1) {
+            goto string_too_short;
+        }
+        substr[0] = 'Z';
+        substr += 1;
+        sublen -= 1;
     }
-    substr[0] = 'Z';
-    substr += 1;
-    sublen -= 1;
-
     /* Add a NULL terminator, and return */
     if (sublen > 0) {
         substr[0] = '\0';
diff --git a/pandas/tests/io/json/test_json_table_schema.py b/pandas/tests/io/json/test_json_table_schema.py
index a2fd8d2cbbf04..c90ac2fb3b813 100644
--- a/pandas/tests/io/json/test_json_table_schema.py
+++ b/pandas/tests/io/json/test_json_table_schema.py
@@ -301,7 +301,7 @@ def test_to_json(self, df_table):
                     ("idx", 0),
                     ("A", 1),
                     ("B", "a"),
-                    ("C", "2016-01-01T00:00:00.000Z"),
+                    ("C", "2016-01-01T00:00:00.000"),
                     ("D", "P0DT1H0M0S"),
                     ("E", "a"),
                     ("F", "a"),
@@ -314,7 +314,7 @@ def test_to_json(self, df_table):
                     ("idx", 1),
                     ("A", 2),
                     ("B", "b"),
-                    ("C", "2016-01-02T00:00:00.000Z"),
+                    ("C", "2016-01-02T00:00:00.000"),
                     ("D", "P0DT1H1M0S"),
                     ("E", "b"),
                     ("F", "b"),
@@ -327,7 +327,7 @@ def test_to_json(self, df_table):
                     ("idx", 2),
                     ("A", 3),
                     ("B", "c"),
-                    ("C", "2016-01-03T00:00:00.000Z"),
+                    ("C", "2016-01-03T00:00:00.000"),
                     ("D", "P0DT1H2M0S"),
                     ("E", "c"),
                     ("F", "c"),
@@ -340,7 +340,7 @@ def test_to_json(self, df_table):
                     ("idx", 3),
                     ("A", 4),
                     ("B", "c"),
-                    ("C", "2016-01-04T00:00:00.000Z"),
+                    ("C", "2016-01-04T00:00:00.000"),
                     ("D", "P0DT1H3M0S"),
                     ("E", "c"),
                     ("F", "c"),
@@ -397,8 +397,8 @@ def test_to_json_period_index(self):
 
         schema = {"fields": fields, "primaryKey": ["index"]}
         data = [
-            OrderedDict([("index", "2015-11-01T00:00:00.000Z"), ("values", 1)]),
-            OrderedDict([("index", "2016-02-01T00:00:00.000Z"), ("values", 1)]),
+            OrderedDict([("index", "2015-11-01T00:00:00.000"), ("values", 1)]),
+            OrderedDict([("index", "2016-02-01T00:00:00.000"), ("values", 1)]),
         ]
         expected = OrderedDict([("schema", schema), ("data", data)])
 
@@ -635,7 +635,7 @@ def test_timestamp_in_columns(self):
         )
         result = df.to_json(orient="table")
         js = json.loads(result)
-        assert js["schema"]["fields"][1]["name"] == "2016-01-01T00:00:00.000Z"
+        assert js["schema"]["fields"][1]["name"] == "2016-01-01T00:00:00.000"
         assert js["schema"]["fields"][2]["name"] == "P0DT0H0M10S"
 
     @pytest.mark.parametrize(
diff --git a/pandas/tests/io/json/test_json_table_schema_ext_dtype.py b/pandas/tests/io/json/test_json_table_schema_ext_dtype.py
index f6aa16ff0ce38..08b182ced4915 100644
--- a/pandas/tests/io/json/test_json_table_schema_ext_dtype.py
+++ b/pandas/tests/io/json/test_json_table_schema_ext_dtype.py
@@ -151,7 +151,7 @@ def test_build_date_series(self):
         expected = OrderedDict(
             [
                 ("schema", schema),
-                ("data", [OrderedDict([("id", 0), ("a", "2021-10-10T00:00:00.000Z")])]),
+                ("data", [OrderedDict([("id", 0), ("a", "2021-10-10T00:00:00.000")])]),
             ]
         )
 
@@ -256,7 +256,7 @@ def test_to_json(self):
             OrderedDict(
                 [
                     ("idx", 0),
-                    ("A", "2021-10-10T00:00:00.000Z"),
+                    ("A", "2021-10-10T00:00:00.000"),
                     ("B", 10.0),
                     ("C", "pandas"),
                     ("D", 10),
diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py
index 985d9e47ea7bd..76f711dc058d3 100644
--- a/pandas/tests/io/json/test_pandas.py
+++ b/pandas/tests/io/json/test_pandas.py
@@ -822,7 +822,7 @@ def test_date_index_and_values(self, date_format, as_object, date_typ):
             expected = '{"1577836800000":1577836800000,"null":null}'
         else:
             expected = (
-                '{"2020-01-01T00:00:00.000Z":"2020-01-01T00:00:00.000Z","null":null}'
+                '{"2020-01-01T00:00:00.000":"2020-01-01T00:00:00.000","null":null}'
             )
 
         if as_object:
@@ -875,8 +875,6 @@ def test_date_format_frame(self, date, date_unit, datetime_frame):
             json = df.to_json(date_format="iso")
         result = read_json(json)
         expected = df.copy()
-        expected.index = expected.index.tz_localize("UTC")
-        expected["date"] = expected["date"].dt.tz_localize("UTC")
         tm.assert_frame_equal(result, expected)
 
     def test_date_format_frame_raises(self, datetime_frame):
@@ -905,8 +903,6 @@ def test_date_format_series(self, date, date_unit, datetime_series):
             json = ts.to_json(date_format="iso")
         result = read_json(json, typ="series")
         expected = ts.copy()
-        expected.index = expected.index.tz_localize("UTC")
-        expected = expected.dt.tz_localize("UTC")
         tm.assert_series_equal(result, expected)
 
     def test_date_format_series_raises(self, datetime_series):
@@ -1192,6 +1188,16 @@ def test_tz_is_utc(self, ts):
         dt = ts.to_pydatetime()
         assert dumps(dt, iso_dates=True) == exp
 
+    def test_tz_is_naive(self):
+        from pandas.io.json import dumps
+
+        ts = Timestamp("2013-01-10 05:00:00")
+        exp = '"2013-01-10T05:00:00.000"'
+
+        assert dumps(ts, iso_dates=True) == exp
+        dt = ts.to_pydatetime()
+        assert dumps(dt, iso_dates=True) == exp
+
     @pytest.mark.parametrize(
         "tz_range",
         [
@@ -1217,6 +1223,21 @@ def test_tz_range_is_utc(self, tz_range):
         result = dumps(df, iso_dates=True)
         assert result == dfexp
 
+    def test_tz_range_is_naive(self):
+        from pandas.io.json import dumps
+
+        tz_range = pd.date_range("2013-01-01 05:00:00", periods=2)
+
+        exp = '["2013-01-01T05:00:00.000","2013-01-02T05:00:00.000"]'
+        dfexp = '{"DT":{"0":"2013-01-01T05:00:00.000", "1":"2013-01-02T05:00:00.000"}}'
+
+        assert dumps(tz_range, iso_dates=True) == exp
+        dti = DatetimeIndex(tz_range)
+        assert dumps(dti, iso_dates=True) == exp
+        df = DataFrame({"DT": dti})
+        result = dumps(df, iso_dates=True)
+        assert result == dfexp
+
     def test_read_inline_jsonl(self):
         # GH9180
         result = read_json('{"a": 1, "b": 2}\n{"b":2, "a" :1}\n', lines=True)

From 9652002184613ac116ca71dc2b1ba503467dcff0 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sun, 10 Apr 2022 11:54:38 -0700
Subject: [PATCH 02/10] fix warnings?

---
 pandas/_libs/src/ujson/python/date_conversions.c       | 2 +-
 pandas/_libs/tslibs/src/datetime/np_datetime_strings.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index c11e4ed60541c..791dc71dc6d67 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -98,7 +98,7 @@ char *PyDateTimeToIso(PyObject *obj, NPY_DATETIMEUNIT base,
     if (PyObject_HasAttrString((PyObject*)obj, "tzinfo")) {
         tmp = PyObject_GetAttrString(obj, "tzinfo");
         if (tmp == NULL) {
-            return -1;
+            return NULL;
         }
         if (tmp == Py_None) {
             Py_DECREF(tmp);
diff --git a/pandas/_libs/tslibs/src/datetime/np_datetime_strings.h b/pandas/_libs/tslibs/src/datetime/np_datetime_strings.h
index 200a71ff0c2b7..e0b3e8c8b9d91 100644
--- a/pandas/_libs/tslibs/src/datetime/np_datetime_strings.h
+++ b/pandas/_libs/tslibs/src/datetime/np_datetime_strings.h
@@ -78,7 +78,7 @@ get_datetime_iso_8601_strlen(int local, NPY_DATETIMEUNIT base);
  */
 int
 make_iso_8601_datetime(npy_datetimestruct *dts, char *outstr, int outlen,
-                       NPY_DATETIMEUNIT base);
+                       int utc, NPY_DATETIMEUNIT base);
 
 /*
  * Converts an pandas_timedeltastruct to an ISO 8601 string.

From 16332fce4663aacebf37bf23456bc0c247c240df Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sun, 10 Apr 2022 12:33:12 -0700
Subject: [PATCH 03/10] actually fix warnings

---
 pandas/_libs/src/ujson/python/date_conversions.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index 791dc71dc6d67..f1e4a2fddb81d 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -106,7 +106,7 @@ char *PyDateTimeToIso(PyObject *obj, NPY_DATETIMEUNIT base,
             offset = PyObject_CallMethod(tmp, "utcoffset", "O", obj);
             if (offset == NULL) {
                 Py_DECREF(tmp);
-                return -1;
+                return NULL;
             }
             Py_DECREF(tmp);
             if (offset != Py_None) {

From aa6444c9fc361c1d7f2ed45627c7c8f73e5ec79c Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sun, 10 Apr 2022 15:20:52 -0700
Subject: [PATCH 04/10] Update objToJSON.c

---
 pandas/_libs/src/ujson/python/objToJSON.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/pandas/_libs/src/ujson/python/objToJSON.c b/pandas/_libs/src/ujson/python/objToJSON.c
index 8913da477ea92..c027c386527fe 100644
--- a/pandas/_libs/src/ujson/python/objToJSON.c
+++ b/pandas/_libs/src/ujson/python/objToJSON.c
@@ -228,7 +228,6 @@ static PyObject *get_values(PyObject *obj) {
                 // be lost if values is used directly.
                 Py_DECREF(tz);
                 values = PyObject_CallMethod(obj, "__array__", NULL);
-                PyObject_Print(values, stdout, NULL);
                 return values;
             }
             Py_DECREF(tz);

From 94ad92a69e11305e40fafd416d4529fa5900d165 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Mon, 11 Apr 2022 07:03:36 -0700
Subject: [PATCH 05/10] fix formatting(and test)

---
 pandas/tests/io/json/test_pandas.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py
index 76f711dc058d3..51bcf85af8821 100644
--- a/pandas/tests/io/json/test_pandas.py
+++ b/pandas/tests/io/json/test_pandas.py
@@ -1229,7 +1229,7 @@ def test_tz_range_is_naive(self):
         tz_range = pd.date_range("2013-01-01 05:00:00", periods=2)
 
         exp = '["2013-01-01T05:00:00.000","2013-01-02T05:00:00.000"]'
-        dfexp = '{"DT":{"0":"2013-01-01T05:00:00.000", "1":"2013-01-02T05:00:00.000"}}'
+        dfexp = '{"DT":{"0":"2013-01-01T05:00:00.000","1":"2013-01-02T05:00:00.000"}}'
 
         assert dumps(tz_range, iso_dates=True) == exp
         dti = DatetimeIndex(tz_range)

From ab895dc0781bda95083aa6cea33cd72c88d48477 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Sat, 16 Apr 2022 08:07:47 -0700
Subject: [PATCH 06/10] Address code comments

---
 .../_libs/src/ujson/python/date_conversions.c | 25 +-----
 pandas/_libs/src/ujson/python/objToJSON.c     | 16 ----
 .../_libs/tslibs/src/datetime/np_datetime.c   | 90 +++++++++++--------
 .../_libs/tslibs/src/datetime/np_datetime.h   |  2 +
 pandas/core/internals/blocks.py               |  8 +-
 5 files changed, 63 insertions(+), 78 deletions(-)

diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index f1e4a2fddb81d..993e0e89562cc 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -93,27 +93,10 @@ char *PyDateTimeToIso(PyObject *obj, NPY_DATETIMEUNIT base,
     // Check to see if PyDateTime has a timezone.
     // Don't convert to UTC if it doesn't.
     int is_tz_aware = 0;
-    PyObject *tmp;
-    PyObject *offset;
-    if (PyObject_HasAttrString((PyObject*)obj, "tzinfo")) {
-        tmp = PyObject_GetAttrString(obj, "tzinfo");
-        if (tmp == NULL) {
-            return NULL;
-        }
-        if (tmp == Py_None) {
-            Py_DECREF(tmp);
-        } else {
-            offset = PyObject_CallMethod(tmp, "utcoffset", "O", obj);
-            if (offset == NULL) {
-                Py_DECREF(tmp);
-                return NULL;
-            }
-            Py_DECREF(tmp);
-            if (offset != Py_None) {
-                is_tz_aware = 1;
-            }
-            Py_DECREF(offset);
-        }
+    PyObject *offset = extract_utc_offset(obj);
+    if (offset != NULL) {
+        is_tz_aware = 1;
+        Py_DECREF(offset);
     }
     ret = make_iso_8601_datetime(&dts, result, *len, is_tz_aware, base);
 
diff --git a/pandas/_libs/src/ujson/python/objToJSON.c b/pandas/_libs/src/ujson/python/objToJSON.c
index c027c386527fe..7de47749e500c 100644
--- a/pandas/_libs/src/ujson/python/objToJSON.c
+++ b/pandas/_libs/src/ujson/python/objToJSON.c
@@ -717,22 +717,6 @@ void PdBlock_iterBegin(JSOBJ _obj, JSONTypeContext *tc) {
 
     for (i = 0; i < PyObject_Length(arrays); i++) {
         array = PyList_GET_ITEM(arrays, i);
-        // tz information is lost when dt64tz is converted
-        // to numpy arrays.
-        // TODO(lithomas1): Patch column_arrays(actually values_for_json)
-        // to return EAs instead of casting to object
-        if (PyArray_TYPE((PyArrayObject *)array) == NPY_DATETIME) {
-            PyObject *mgr = PyObject_GetAttrString(obj, "_mgr");
-            PyObject *dtarr = PyObject_CallMethod(mgr, "iget_values", "n", i);
-            PyObject *tz = PyObject_GetAttrString(dtarr, "tz");
-            if (tz != Py_None) {
-                // we have a timezone, use an object array of Timestamp
-                array = PyObject_CallMethod(dtarr, "__array__", NULL);
-            }
-            Py_DECREF(mgr);
-            Py_DECREF(dtarr);
-            Py_DECREF(tz);
-        }
         if (!array) {
             GET_TC(tc)->iterNext = NpyArr_iterNextNone;
             goto ARR_RET;
diff --git a/pandas/_libs/tslibs/src/datetime/np_datetime.c b/pandas/_libs/tslibs/src/datetime/np_datetime.c
index f5400cf8da4df..4ce0b57ea985a 100644
--- a/pandas/_libs/tslibs/src/datetime/np_datetime.c
+++ b/pandas/_libs/tslibs/src/datetime/np_datetime.c
@@ -331,6 +331,34 @@ int cmp_npy_datetimestruct(const npy_datetimestruct *a,
 
     return 0;
 }
+/*
+* Returns the offset from utc of the timezone.
+* If the passed object is timezone naive, or if extraction
+* of the offset fails, NULL is returned.
+*
+* NOTE: This function is not vendored from numpy.
+*/
+PyObject *extract_utc_offset(PyObject *obj) {
+    if (PyObject_HasAttrString(obj, "tzinfo")) {
+        PyObject *tmp = PyObject_GetAttrString(obj, "tzinfo");
+        if (tmp == NULL) {
+            return NULL;
+        }
+        if (tmp != Py_None) {
+            PyObject *offset = PyObject_CallMethod(tmp, "utcoffset", "O", obj);
+            if (offset == NULL) {
+                Py_DECREF(tmp);
+                return NULL;
+            }
+            if (offset != Py_None) {
+                return offset;
+            }
+            Py_DECREF(offset);
+        }
+        Py_DECREF(tmp);
+    }
+    return NULL;
+}
 
 /*
  *
@@ -376,54 +404,38 @@ int convert_pydatetime_to_datetimestruct(PyObject *dtobj,
     out->sec = PyLong_AsLong(PyObject_GetAttrString(obj, "second"));
     out->us = PyLong_AsLong(PyObject_GetAttrString(obj, "microsecond"));
 
+    PyObject *offset = extract_utc_offset(obj);
     /* Apply the time zone offset if datetime obj is tz-aware */
-    if (PyObject_HasAttrString((PyObject*)obj, "tzinfo")) {
-        tmp = PyObject_GetAttrString(obj, "tzinfo");
+    if (offset != NULL) {
+        PyObject *tmp_int;
+        int seconds_offset, minutes_offset;
+        /*
+         * The timedelta should have a function "total_seconds"
+         * which contains the value we want.
+         */
+        tmp = PyObject_CallMethod(offset, "total_seconds", "");
+        Py_DECREF(offset);
         if (tmp == NULL) {
             return -1;
         }
-        if (tmp == Py_None) {
-            Py_DECREF(tmp);
-        } else {
-            PyObject *offset;
-            PyObject *tmp_int;
-            int seconds_offset, minutes_offset;
-
-            /* The utcoffset function should return a timedelta */
-            offset = PyObject_CallMethod(tmp, "utcoffset", "O", obj);
-            if (offset == NULL) {
-                Py_DECREF(tmp);
-                return -1;
-            }
+        tmp_int = PyNumber_Long(tmp);
+        if (tmp_int == NULL) {
             Py_DECREF(tmp);
-
-            /*
-             * The timedelta should have a function "total_seconds"
-             * which contains the value we want.
-             */
-            tmp = PyObject_CallMethod(offset, "total_seconds", "");
-            if (tmp == NULL) {
-                return -1;
-            }
-            tmp_int = PyNumber_Long(tmp);
-            if (tmp_int == NULL) {
-                Py_DECREF(tmp);
-                return -1;
-            }
-            seconds_offset = PyLong_AsLong(tmp_int);
-            if (seconds_offset == -1 && PyErr_Occurred()) {
-                Py_DECREF(tmp_int);
-                Py_DECREF(tmp);
-                return -1;
-            }
+            return -1;
+        }
+        seconds_offset = PyLong_AsLong(tmp_int);
+        if (seconds_offset == -1 && PyErr_Occurred()) {
             Py_DECREF(tmp_int);
             Py_DECREF(tmp);
+            return -1;
+        }
+        Py_DECREF(tmp_int);
+        Py_DECREF(tmp);
 
-            /* Convert to a minutes offset and apply it */
-            minutes_offset = seconds_offset / 60;
+        /* Convert to a minutes offset and apply it */
+        minutes_offset = seconds_offset / 60;
 
-            add_minutes_to_datetimestruct(out, -minutes_offset);
-        }
+        add_minutes_to_datetimestruct(out, -minutes_offset);
     }
 
     return 0;
diff --git a/pandas/_libs/tslibs/src/datetime/np_datetime.h b/pandas/_libs/tslibs/src/datetime/np_datetime.h
index 065f09a6d93b5..6ab915e517cfb 100644
--- a/pandas/_libs/tslibs/src/datetime/np_datetime.h
+++ b/pandas/_libs/tslibs/src/datetime/np_datetime.h
@@ -48,6 +48,8 @@ extern const npy_datetimestruct _M_MAX_DTS;
 // stuff pandas needs
 // ----------------------------------------------------------------------------
 
+PyObject *extract_utc_offset(PyObject *obj);
+
 int convert_pydatetime_to_datetimestruct(PyObject *dtobj,
                                          npy_datetimestruct *out);
 
diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py
index 26569b571724d..c8430a9266ea5 100644
--- a/pandas/core/internals/blocks.py
+++ b/pandas/core/internals/blocks.py
@@ -1974,8 +1974,6 @@ class DatetimeLikeBlock(NDArrayBackedExtensionBlock):
     values: DatetimeArray | TimedeltaArray
 
     def values_for_json(self) -> np.ndarray:
-        # special casing datetimetz to avoid conversion through
-        #  object dtype
         return self.values._ndarray
 
 
@@ -1989,6 +1987,12 @@ class DatetimeTZBlock(DatetimeLikeBlock):
     _validate_ndim = True
     _can_consolidate = False
 
+    def values_for_json(self) -> np.ndarray:
+        # force dt64tz to go through object dtype
+        # tz info will be lost when converting to
+        # dt64 which is naive
+        return self.values.astype(object)
+
 
 class ObjectBlock(NumpyBlock):
     __slots__ = ()

From 075e7ca45ae0467faaf0f7ebad5959e051122dbc Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Tue, 19 Apr 2022 20:10:26 -0700
Subject: [PATCH 07/10] address comments

---
 doc/source/whatsnew/v1.5.0.rst                   | 15 +++++++++++----
 pandas/_libs/src/ujson/python/date_conversions.c |  4 ++--
 pandas/tests/io/json/test_pandas.py              | 12 +++++++++---
 3 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/doc/source/whatsnew/v1.5.0.rst b/doc/source/whatsnew/v1.5.0.rst
index bd891e5a84d4f..da32396fcbb6e 100644
--- a/doc/source/whatsnew/v1.5.0.rst
+++ b/doc/source/whatsnew/v1.5.0.rst
@@ -175,10 +175,17 @@ Styler
 
 - Fix showing "None" as ylabel in :meth:`Series.plot` when not setting ylabel (:issue:`46129`)
 
-.. _whatsnew_150.notable_bug_fixes.notable_bug_fix2:
+.. _whatsnew_150.notable_bug_fixes.to_json_incorrectly_localizing_naive_timestamps:
 
-notable_bug_fix2
-^^^^^^^^^^^^^^^^
+Serializing tz-naive Timestamps with to_json() with ``iso_dates=True``
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+:meth:`DataFrame.to_json`, :meth:`Series.to_json`, and :meth:`Index.to_json`
+would incorrectly localize DatetimeArrays/DatetimeIndexes with tz-naive Timestamps
+to UTC. (:issue:`38760`)
+
+Note that this patch does not fix the localization of tz-aware Timestamps to UTC
+upon serialization. (Related issue :issue:`12997`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_150.api_breaking:
@@ -563,7 +570,7 @@ I/O
 - Bug in Parquet roundtrip for Interval dtype with ``datetime64[ns]`` subtype (:issue:`45881`)
 - Bug in :func:`read_excel` when reading a ``.ods`` file with newlines between xml elements (:issue:`45598`)
 - Bug in :func:`read_parquet` when ``engine="fastparquet"`` where the file was not closed on error (:issue:`46555`)
-- Bug in :meth:`DataFrame.to_json`, :meth:`Series.to_json`, and :meth:`Index.to_json` where tz-aware datetimes were being incorrectly localized to UTC (:issue:`38760`)
+-
 
 Period
 ^^^^^^
diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index 993e0e89562cc..53673da6aa93c 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -54,8 +54,8 @@ char *int64ToIso(int64_t value, NPY_DATETIMEUNIT base, size_t *len) {
         PyErr_NoMemory();
         return NULL;
     }
-    ret_code = make_iso_8601_datetime(&dts, result, *len,
-                                      0 /* datetime64 is always naive */, base);
+    // datetime64 is always naive
+    ret_code = make_iso_8601_datetime(&dts, result, *len, 0, base);
     if (ret_code != 0) {
         PyErr_SetString(PyExc_ValueError,
                         "Could not convert datetime value to string");
diff --git a/pandas/tests/io/json/test_pandas.py b/pandas/tests/io/json/test_pandas.py
index 51bcf85af8821..576d99f25e25c 100644
--- a/pandas/tests/io/json/test_pandas.py
+++ b/pandas/tests/io/json/test_pandas.py
@@ -1218,25 +1218,31 @@ def test_tz_range_is_utc(self, tz_range):
 
         assert dumps(tz_range, iso_dates=True) == exp
         dti = DatetimeIndex(tz_range)
+        # Ensure datetimes in object array are serialized correctly
+        # in addition to the normal DTI case
         assert dumps(dti, iso_dates=True) == exp
+        assert dumps(dti.astype(object), iso_dates=True) == exp
         df = DataFrame({"DT": dti})
         result = dumps(df, iso_dates=True)
         assert result == dfexp
+        assert dumps(df.astype({"DT": object}), iso_dates=True)
 
     def test_tz_range_is_naive(self):
         from pandas.io.json import dumps
 
-        tz_range = pd.date_range("2013-01-01 05:00:00", periods=2)
+        dti = pd.date_range("2013-01-01 05:00:00", periods=2)
 
         exp = '["2013-01-01T05:00:00.000","2013-01-02T05:00:00.000"]'
         dfexp = '{"DT":{"0":"2013-01-01T05:00:00.000","1":"2013-01-02T05:00:00.000"}}'
 
-        assert dumps(tz_range, iso_dates=True) == exp
-        dti = DatetimeIndex(tz_range)
+        # Ensure datetimes in object array are serialized correctly
+        # in addition to the normal DTI case
         assert dumps(dti, iso_dates=True) == exp
+        assert dumps(dti.astype(object), iso_dates=True) == exp
         df = DataFrame({"DT": dti})
         result = dumps(df, iso_dates=True)
         assert result == dfexp
+        assert dumps(df.astype({"DT": object}), iso_dates=True)
 
     def test_read_inline_jsonl(self):
         # GH9180

From ca3316d3c263873a9524d510f430b8272234ffb0 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Tue, 26 Apr 2022 20:14:36 -0700
Subject: [PATCH 08/10] address more comments

---
 doc/source/whatsnew/v1.5.0.rst                | 30 ++++++
 .../_libs/src/ujson/python/date_conversions.c | 12 ++-
 .../_libs/tslibs/src/datetime/np_datetime.c   | 97 ++++++++++---------
 3 files changed, 89 insertions(+), 50 deletions(-)

diff --git a/doc/source/whatsnew/v1.5.0.rst b/doc/source/whatsnew/v1.5.0.rst
index da32396fcbb6e..8eb73cd3f40c0 100644
--- a/doc/source/whatsnew/v1.5.0.rst
+++ b/doc/source/whatsnew/v1.5.0.rst
@@ -187,6 +187,36 @@ to UTC. (:issue:`38760`)
 Note that this patch does not fix the localization of tz-aware Timestamps to UTC
 upon serialization. (Related issue :issue:`12997`)
 
+*Old Behavior*
+
+.. ipython:: python
+
+    index = pd.date_range(
+        start='2020-12-28 00:00:00',
+        end='2020-12-28 02:00:00',
+        freq='1H',
+    )
+    a = pd.Series(
+        data=range(3),
+        index=index,
+    )
+
+.. code-block:: ipython
+
+    In [4]: a.to_json(date_format='iso')
+    Out[4]: '{"2020-12-28T00:00:00.000Z":0,"2020-12-28T01:00:00.000Z":1,"2020-12-28T02:00:00.000Z":2}'
+
+    In [5]: pd.read_json(a.to_json(date_format='iso'), typ="series").index == a.index
+    Out[5]: array([False, False, False])
+
+*New Behavior*
+
+.. ipython:: python
+
+    a.to_json(date_format='iso')
+    # Roundtripping now works
+    pd.read_json(a.to_json(date_format='iso'), typ="series").index == a.index
+
 .. ---------------------------------------------------------------------------
 .. _whatsnew_150.api_breaking:
 
diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index 53673da6aa93c..6bc75590c1feb 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -93,10 +93,14 @@ char *PyDateTimeToIso(PyObject *obj, NPY_DATETIMEUNIT base,
     // Check to see if PyDateTime has a timezone.
     // Don't convert to UTC if it doesn't.
     int is_tz_aware = 0;
-    PyObject *offset = extract_utc_offset(obj);
-    if (offset != NULL) {
-        is_tz_aware = 1;
-        Py_DECREF(offset);
+    if (PyObject_HasAttrString(obj, "tzinfo")) {
+        PyObject *offset = extract_utc_offset(obj);
+        if (offset != NULL) {
+            if (offset != Py_None) {
+                is_tz_aware = 1;
+            }
+            Py_DECREF(offset);
+        }
     }
     ret = make_iso_8601_datetime(&dts, result, *len, is_tz_aware, base);
 
diff --git a/pandas/_libs/tslibs/src/datetime/np_datetime.c b/pandas/_libs/tslibs/src/datetime/np_datetime.c
index 4ce0b57ea985a..c5ff7219264e2 100644
--- a/pandas/_libs/tslibs/src/datetime/np_datetime.c
+++ b/pandas/_libs/tslibs/src/datetime/np_datetime.c
@@ -332,32 +332,31 @@ int cmp_npy_datetimestruct(const npy_datetimestruct *a,
     return 0;
 }
 /*
-* Returns the offset from utc of the timezone.
-* If the passed object is timezone naive, or if extraction
-* of the offset fails, NULL is returned.
+* Returns the offset from utc of the timezone as a timedelta.
+* The caller is responsible for ensuring that the tzinfo
+* attribute exists on the datetime object.
+*
+* If the passed object is timezone naive, Py_None is returned.
+* If extraction of the offset fails, NULL is returned.
 *
 * NOTE: This function is not vendored from numpy.
 */
 PyObject *extract_utc_offset(PyObject *obj) {
-    if (PyObject_HasAttrString(obj, "tzinfo")) {
-        PyObject *tmp = PyObject_GetAttrString(obj, "tzinfo");
-        if (tmp == NULL) {
+    PyObject *tmp = PyObject_GetAttrString(obj, "tzinfo");
+    if (tmp == NULL) {
+        return NULL;
+    }
+    if (tmp != Py_None) {
+        PyObject *offset = PyObject_CallMethod(tmp, "utcoffset", "O", obj);
+        if (offset == NULL) {
+            Py_DECREF(tmp);
             return NULL;
         }
-        if (tmp != Py_None) {
-            PyObject *offset = PyObject_CallMethod(tmp, "utcoffset", "O", obj);
-            if (offset == NULL) {
-                Py_DECREF(tmp);
-                return NULL;
-            }
-            if (offset != Py_None) {
-                return offset;
-            }
-            Py_DECREF(offset);
+        if (offset != Py_None) {
+            return offset;
         }
-        Py_DECREF(tmp);
     }
-    return NULL;
+    return tmp;
 }
 
 /*
@@ -404,38 +403,44 @@ int convert_pydatetime_to_datetimestruct(PyObject *dtobj,
     out->sec = PyLong_AsLong(PyObject_GetAttrString(obj, "second"));
     out->us = PyLong_AsLong(PyObject_GetAttrString(obj, "microsecond"));
 
-    PyObject *offset = extract_utc_offset(obj);
-    /* Apply the time zone offset if datetime obj is tz-aware */
-    if (offset != NULL) {
-        PyObject *tmp_int;
-        int seconds_offset, minutes_offset;
-        /*
-         * The timedelta should have a function "total_seconds"
-         * which contains the value we want.
-         */
-        tmp = PyObject_CallMethod(offset, "total_seconds", "");
-        Py_DECREF(offset);
-        if (tmp == NULL) {
-            return -1;
-        }
-        tmp_int = PyNumber_Long(tmp);
-        if (tmp_int == NULL) {
-            Py_DECREF(tmp);
-            return -1;
-        }
-        seconds_offset = PyLong_AsLong(tmp_int);
-        if (seconds_offset == -1 && PyErr_Occurred()) {
+    if (PyObject_HasAttrString(obj, "tzinfo")) {
+        PyObject *offset = extract_utc_offset(obj);
+        /* Apply the time zone offset if datetime obj is tz-aware */
+        if (offset != NULL) {
+            if (offset == Py_None) {
+                Py_DECREF(offset);
+                return 0;
+            }
+            PyObject *tmp_int;
+            int seconds_offset, minutes_offset;
+            /*
+             * The timedelta should have a function "total_seconds"
+             * which contains the value we want.
+             */
+            tmp = PyObject_CallMethod(offset, "total_seconds", "");
+            Py_DECREF(offset);
+            if (tmp == NULL) {
+                return -1;
+            }
+            tmp_int = PyNumber_Long(tmp);
+            if (tmp_int == NULL) {
+                Py_DECREF(tmp);
+                return -1;
+            }
+            seconds_offset = PyLong_AsLong(tmp_int);
+            if (seconds_offset == -1 && PyErr_Occurred()) {
+                Py_DECREF(tmp_int);
+                Py_DECREF(tmp);
+                return -1;
+            }
             Py_DECREF(tmp_int);
             Py_DECREF(tmp);
-            return -1;
-        }
-        Py_DECREF(tmp_int);
-        Py_DECREF(tmp);
 
-        /* Convert to a minutes offset and apply it */
-        minutes_offset = seconds_offset / 60;
+            /* Convert to a minutes offset and apply it */
+            minutes_offset = seconds_offset / 60;
 
-        add_minutes_to_datetimestruct(out, -minutes_offset);
+            add_minutes_to_datetimestruct(out, -minutes_offset);
+        }
     }
 
     return 0;

From fe90bb3ed19f49b969c7cddb3b6ccd6ea41dc6b9 Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Fri, 29 Apr 2022 20:47:42 -0700
Subject: [PATCH 09/10] address comments

---
 pandas/_libs/src/ujson/python/date_conversions.c | 9 ++++-----
 pandas/_libs/tslibs/src/datetime/np_datetime.c   | 4 +---
 2 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index 6bc75590c1feb..7aee0b0195712 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -95,12 +95,11 @@ char *PyDateTimeToIso(PyObject *obj, NPY_DATETIMEUNIT base,
     int is_tz_aware = 0;
     if (PyObject_HasAttrString(obj, "tzinfo")) {
         PyObject *offset = extract_utc_offset(obj);
-        if (offset != NULL) {
-            if (offset != Py_None) {
-                is_tz_aware = 1;
-            }
-            Py_DECREF(offset);
+        if (offset == NULL) {
+            return NULL;
         }
+        is_tz_aware = offset != Py_None;
+        Py_DECREF(offset);
     }
     ret = make_iso_8601_datetime(&dts, result, *len, is_tz_aware, base);
 
diff --git a/pandas/_libs/tslibs/src/datetime/np_datetime.c b/pandas/_libs/tslibs/src/datetime/np_datetime.c
index c5ff7219264e2..9029f9ae14b34 100644
--- a/pandas/_libs/tslibs/src/datetime/np_datetime.c
+++ b/pandas/_libs/tslibs/src/datetime/np_datetime.c
@@ -352,9 +352,7 @@ PyObject *extract_utc_offset(PyObject *obj) {
             Py_DECREF(tmp);
             return NULL;
         }
-        if (offset != Py_None) {
-            return offset;
-        }
+        return offset;
     }
     return tmp;
 }

From 65f321b07cf66e865790172a7ab3ddf9396e9d3e Mon Sep 17 00:00:00 2001
From: Thomas Li <47963215+lithomas1@users.noreply.github.com>
Date: Tue, 3 May 2022 08:07:12 -0700
Subject: [PATCH 10/10] fix memleak

---
 pandas/_libs/src/ujson/python/date_conversions.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/pandas/_libs/src/ujson/python/date_conversions.c b/pandas/_libs/src/ujson/python/date_conversions.c
index 7aee0b0195712..86cb68f869cb0 100644
--- a/pandas/_libs/src/ujson/python/date_conversions.c
+++ b/pandas/_libs/src/ujson/python/date_conversions.c
@@ -96,6 +96,7 @@ char *PyDateTimeToIso(PyObject *obj, NPY_DATETIMEUNIT base,
     if (PyObject_HasAttrString(obj, "tzinfo")) {
         PyObject *offset = extract_utc_offset(obj);
         if (offset == NULL) {
+            PyObject_Free(result);
             return NULL;
         }
         is_tz_aware = offset != Py_None;