GH-48199: [Python][Parquet] Expose existing Parquet C++ metadata about index_page and bloom_filter to Python

python/pyarrow/_parquet.pyx

@@ -474,8 +474,14 @@ cdef class ColumnChunkMetaData(_Weakrefable):
   has_dictionary_page: {self.has_dictionary_page}
   dictionary_page_offset: {self.dictionary_page_offset}
   data_page_offset: {self.data_page_offset}
+  has_index_page: {self.has_index_page}
+  index_page_offset: {self.index_page_offset}
+  has_bloom_filter: {self.has_bloom_filter}
+  bloom_filter_offset: {self.bloom_filter_offset}
   total_compressed_size: {self.total_compressed_size}
-  total_uncompressed_size: {self.total_uncompressed_size}"""
+  total_uncompressed_size: {self.total_uncompressed_size}
+  has_offset_index: {self.has_offset_index}
+  has_column_index: {self.has_column_index}"""
 
     def to_dict(self):
         """
@@ -506,8 +512,14 @@ cdef class ColumnChunkMetaData(_Weakrefable):
             has_dictionary_page=self.has_dictionary_page,
             dictionary_page_offset=self.dictionary_page_offset,
             data_page_offset=self.data_page_offset,
+            has_index_page=self.has_index_page,
+            index_page_offset=self.index_page_offset,
+            has_bloom_filter=self.has_bloom_filter,
+            bloom_filter_offset=self.bloom_filter_offset,
             total_compressed_size=self.total_compressed_size,
-            total_uncompressed_size=self.total_uncompressed_size
+            total_uncompressed_size=self.total_uncompressed_size,
+            has_offset_index=self.has_offset_index,
+            has_column_index=self.has_column_index
         )
         return d
 
@@ -627,13 +639,30 @@ cdef class ColumnChunkMetaData(_Weakrefable):
 
     @property
     def has_index_page(self):
-        """Not yet supported."""
-        raise NotImplementedError('not supported in parquet-cpp')
+        """Whether there is an index data present in the column chunk (bool)."""
+        return self.metadata.has_index_page()
 
     @property
     def index_page_offset(self):
-        """Not yet supported."""
-        raise NotImplementedError("parquet-cpp doesn't return valid values")
+        """Offset of index page relative to beginning of the file (int or None)."""
+        return self.metadata.index_page_offset() if self.has_index_page else None
+
+    @property
+    def has_bloom_filter(self):
+        """Whether there is a bloom filter present in the column chunk (bool)."""
+        return self.metadata.bloom_filter_offset().has_value()
+
+    @property
+    def bloom_filter_offset(self):
+        """Offset of bloom filter relative to beginning of the file (int or None)."""
+        offset = self.metadata.bloom_filter_offset()
+        return offset.value() if offset.has_value() else None
+
+    @property
+    def bloom_filter_length(self):
+        """Length of bloom filter (int or None)."""
+        length = self.metadata.bloom_filter_length()
+        return length.value() if length.has_value() else None
 
     @property
     def total_compressed_size(self):

python/pyarrow/includes/libparquet.pxd

@@ -364,9 +364,12 @@ cdef extern from "parquet/api/reader.h" namespace "parquet" nogil:
         const vector[ParquetEncoding]& encodings() const
         c_bool Equals(const CColumnChunkMetaData&) const
 
+        optional[int64_t] bloom_filter_offset() const
+        optional[int64_t] bloom_filter_length() const
         int64_t has_dictionary_page() const
         int64_t dictionary_page_offset() const
         int64_t data_page_offset() const
+        c_bool has_index_page() const
         int64_t index_page_offset() const
         int64_t total_compressed_size() const
         int64_t total_uncompressed_size() const

python/pyarrow/tests/parquet/test_metadata.py

@@ -139,10 +139,12 @@ def test_parquet_metadata_api():
     assert col_meta.data_page_offset > 0
     assert col_meta.total_compressed_size > 0
     assert col_meta.total_uncompressed_size > 0
-    with pytest.raises(NotImplementedError):
-        col_meta.has_index_page
-    with pytest.raises(NotImplementedError):
-        col_meta.index_page_offset
+    assert col_meta.has_index_page is False
+    assert col_meta.index_page_offset is None
+    assert col_meta.has_bloom_filter is False
+    assert col_meta.bloom_filter_offset is None
+    assert col_meta.has_offset_index is False
+    assert col_meta.has_column_index is False
 
 
 def test_parquet_metadata_lifetime(tempdir):
@@ -814,3 +816,31 @@ def msg(c):
 
     with pytest.raises(TypeError, match=msg("FileMetaData")):
         pq.FileMetaData()
+
+
+def test_column_metadata_with_bloom_filter(parquet_test_datadir):
+    metadata = pq.read_metadata(parquet_test_datadir /
+                                'data_index_bloom_encoding_with_length.parquet')
+    assert metadata.row_group(0).column(0).has_dictionary_page is True
+    assert metadata.row_group(0).column(0).dictionary_page_offset == 4
+    assert metadata.row_group(0).column(0).has_index_page is False
+    assert metadata.row_group(0).column(0).index_page_offset is None
+    assert metadata.row_group(0).column(0).has_bloom_filter is True
+    assert metadata.row_group(0).column(0).has_column_index is True
+    assert metadata.row_group(0).column(0).has_offset_index is True
+    assert metadata.row_group(0).column(0).bloom_filter_offset == 253
+    assert metadata.row_group(0).column(0).bloom_filter_length == 2064
+
+
+def test_column_metadata_with_index_page(parquet_test_datadir):
+    metadata = pq.read_metadata(parquet_test_datadir /
+                                'nan_in_stats.parquet')
+    assert metadata.row_group(0).column(0).has_dictionary_page is True
+    assert metadata.row_group(0).column(0).dictionary_page_offset == 4
+    assert metadata.row_group(0).column(0).has_index_page is True
+    assert metadata.row_group(0).column(0).index_page_offset == 0
+    assert metadata.row_group(0).column(0).has_bloom_filter is False
+    assert metadata.row_group(0).column(0).has_column_index is False
+    assert metadata.row_group(0).column(0).has_offset_index is False
+    assert metadata.row_group(0).column(0).bloom_filter_offset is None
+    assert metadata.row_group(0).column(0).bloom_filter_length is None