Rename materialize_tree to materialize_table

Author: yoid2000

syndiffix/clustering/common.py

@@ -24,6 +24,7 @@ def __repr__(self) -> str:
 
 
 # Owner, Stitch columns, Derived columns
+# The total set of columns is Stitch+Derived.
 DerivedCluster = tuple[StitchOwner, list[ColumnId], list[ColumnId]]
 
 
@@ -35,6 +36,8 @@ class Clusters:
 
 TreeMaterializer = Callable[[Forest, list[ColumnId]], tuple[list[MicrodataRow], Combination]]
 
+TableMaterializer = Callable[[Forest, list[ColumnId]], tuple[list[MicrodataRow], Combination]]
+
 
 def microdata_row_to_row(microdata_row: MicrodataRow) -> Row:
     return tuple(value[MICRODATA_SYN_VALUE] for value in microdata_row)

syndiffix/clustering/stitching.py

@@ -360,15 +360,15 @@ def _do_patch(
 
 
 def _stitch(
-    materialize_tree: TreeMaterializer,
+    materialize_table: TableMaterializer,
     forest: Forest,
     metadata: StitchingMetadata,
     left: tuple[list[MicrodataRow], Combination],
     derived_cluster: DerivedCluster,
 ) -> tuple[list[MicrodataRow], Combination]:
     (_, stitch_columns, derived_columns) = derived_cluster
 
-    right = materialize_tree(forest, stitch_columns + derived_columns)
+    right = materialize_table(forest, stitch_columns + derived_columns)
 
     if len(stitch_columns) == 0:
         return _do_patch(forest.unsafe_rng, left, right)
@@ -377,12 +377,12 @@ def _stitch(
 
 
 def build_table(
-    materialize_tree: TreeMaterializer, forest: Forest, metadata: StitchingMetadata, clusters: Clusters
+    materialize_table: TableMaterializer, forest: Forest, metadata: StitchingMetadata, clusters: Clusters
 ) -> tuple[list[Row], Combination]:
-    acc = materialize_tree(forest, clusters.initial_cluster)
+    acc = materialize_table(forest, clusters.initial_cluster)
 
     for derived_cluster in clusters.derived_clusters:
-        acc = _stitch(materialize_tree, forest, metadata, acc, derived_cluster)
+        acc = _stitch(materialize_table, forest, metadata, acc, derived_cluster)
 
     rows, columns = acc
     return [microdata_row_to_row(row) for row in rows], columns

syndiffix/synthesizer.py

@@ -119,7 +119,7 @@ def __init__(
             converter.analyze_tree(self.forest.get_tree((ColumnId(col_id),)))
 
     def sample(self) -> pd.DataFrame:
-        def materialize_tree(forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
+        def materialize_table(forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
             combination = tuple(sorted(columns))
             tree = forest.get_tree(combination)
             buckets = harvest(tree, self.forest.derive_unsafe_rng())
@@ -134,7 +134,7 @@ def materialize_tree(forest: Forest, columns: list[ColumnId]) -> tuple[list[Micr
             )
 
         rows, root_combination = build_table(
-            materialize_tree,
+            materialize_table,
             self.forest,
             StitchingMetadata(self.column_is_integral, self.entropy_1dim),
             self.clusters,

tests/clustering/test_stitching.py

@@ -35,7 +35,7 @@ def test_stitching() -> None:
         (ColumnId(2), ColumnId(3)): _build_rows(col_c_right, col_d),
     }
 
-    def materialize_tree(_forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
+    def materialize_table(_forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
         combination = tuple(sorted(columns))
         return (microtables[combination], combination)
 
@@ -47,7 +47,7 @@ def materialize_tree(_forest: Forest, columns: list[ColumnId]) -> tuple[list[Mic
         ],
     )
 
-    rows, combination = build_table(materialize_tree, forest, _dummy_metadata(4), clusters)
+    rows, combination = build_table(materialize_table, forest, _dummy_metadata(4), clusters)
 
     assert combination == (0, 1, 2, 3)
     assert rows == [
@@ -67,7 +67,7 @@ def materialize_tree(_forest: Forest, columns: list[ColumnId]) -> tuple[list[Mic
 def test_empty_microtables() -> None:
     forest = load_forest("dummy.csv")
 
-    def materialize_tree(_forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
+    def materialize_table(_forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
         combination = tuple(sorted(columns))
         return ([], combination)
 
@@ -78,7 +78,7 @@ def materialize_tree(_forest: Forest, columns: list[ColumnId]) -> tuple[list[Mic
         ],
     )
 
-    rows, combination = build_table(materialize_tree, forest, _dummy_metadata(3), clusters)
+    rows, combination = build_table(materialize_table, forest, _dummy_metadata(3), clusters)
 
     assert combination == (0, 1, 2)
     assert rows == []
@@ -98,7 +98,7 @@ def test_patching() -> None:
         (ColumnId(3),): _build_rows(col_d),
     }
 
-    def materialize_tree(_forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
+    def materialize_table(_forest: Forest, columns: list[ColumnId]) -> tuple[list[MicrodataRow], Combination]:
         combination = tuple(sorted(columns))
         return (microtables[combination], combination)
 
@@ -110,7 +110,7 @@ def materialize_tree(_forest: Forest, columns: list[ColumnId]) -> tuple[list[Mic
         ],
     )
 
-    rows, combination = build_table(materialize_tree, forest, _dummy_metadata(4), clusters)
+    rows, combination = build_table(materialize_table, forest, _dummy_metadata(4), clusters)
 
     assert combination == (0, 1, 2, 3)
     assert rows == [