From 2ebdd5e4ca1b3230e7c59c9deeeb23349944a5a7 Mon Sep 17 00:00:00 2001
From: Wes McKinney <wesm+git@apache.org>
Date: Tue, 11 Feb 2020 23:51:28 -0600
Subject: [PATCH] Add Python unit test to verify that field_id's are correctly
 filtered through to the Arrow schema in Python

---
 python/pyarrow/tests/test_parquet.py | 49 +++++++++++++++++++++++++---
 python/pyarrow/types.pxi             |  4 +++
 2 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/python/pyarrow/tests/test_parquet.py b/python/pyarrow/tests/test_parquet.py
index c8f555e5ef954..f045855b4dcd8 100644
--- a/python/pyarrow/tests/test_parquet.py
+++ b/python/pyarrow/tests/test_parquet.py
@@ -3251,6 +3251,13 @@ def test_categorical_order_survives_roundtrip():
     tm.assert_frame_equal(result, df)
 
 
+def _simple_table_write_read(table):
+    bio = pa.BufferOutputStream()
+    pq.write_table(table, bio)
+    contents = bio.getvalue()
+    return pq.read_table(pa.BufferReader(contents))
+
+
 def test_dictionary_array_automatically_read():
     # ARROW-3246
 
@@ -3269,16 +3276,50 @@ def test_dictionary_array_automatically_read():
                                                      dict_values))
 
     table = pa.table([pa.chunked_array(chunks)], names=['f0'])
+    result = _simple_table_write_read(table)
+
+    assert_tables_equal(result, table)
+
+    # The only key in the metadata was the Arrow schema key
+    assert result.schema.metadata is None
+
+
+def test_field_id_metadata():
+    # ARROW-7080
+    table = pa.table([pa.array([1], type='int32'),
+                      pa.array([[]], type=pa.list_(pa.int32())),
+                      pa.array([b'boo'], type='binary')],
+                     ['f0', 'f1', 'f2'])
 
     bio = pa.BufferOutputStream()
     pq.write_table(table, bio)
     contents = bio.getvalue()
-    result = pq.read_table(pa.BufferReader(contents))
 
-    assert_tables_equal(result, table)
+    pf = pq.ParquetFile(pa.BufferReader(contents))
+    schema = pf.schema_arrow
 
-    # The only key in the metadata was the Arrow schema key
-    assert result.schema.metadata is None
+    # Expected Parquet schema for reference
+    #
+    # required group field_id=0 schema {
+    #   optional int32 field_id=1 f0;
+    #   optional group field_id=2 f1 (List) {
+    #     repeated group field_id=3 list {
+    #       optional int32 field_id=4 item;
+    #     }
+    #   }
+    #   optional binary field_id=5 f2;
+    # }
+
+    field_name = b'PARQUET::field_id'
+    assert schema[0].metadata[field_name] == b'1'
+
+    list_field = schema[1]
+    assert list_field.metadata[field_name] == b'2'
+
+    list_item_field = list_field.type.value_field
+    assert list_item_field.metadata[field_name] == b'4'
+
+    assert schema[2].metadata[field_name] == b'5'
 
 
 @pytest.mark.pandas
diff --git a/python/pyarrow/types.pxi b/python/pyarrow/types.pxi
index 1099d43841835..c63051d129b20 100644
--- a/python/pyarrow/types.pxi
+++ b/python/pyarrow/types.pxi
@@ -253,6 +253,10 @@ cdef class ListType(DataType):
     def __reduce__(self):
         return list_, (self.value_type,)
 
+    @property
+    def value_field(self):
+        return pyarrow_wrap_field(self.list_type.value_field())
+
     @property
     def value_type(self):
         """