fix: properly deserialize percent-encoded file paths of Remove action…

…s, to make sure tombstone and file paths match (delta-io#2035)

Percent-encoded file paths of Remove actions were not properly
deserialized, and when compared to active file paths, the paths didn't
match, which caused tombstones to be recognized as active files (be kept
in the state)

<!---
For example:

- closes delta-io#106
--->

<!---
Share links to useful documentation
--->

---------

Co-authored-by: Igor Borodin <[email protected]>
Co-authored-by: Ion Koutsouris <[email protected]>
Co-authored-by: R. Tyler Croy <[email protected]>

rust/src/table/state.rs

@@ -429,8 +429,10 @@ impl DeltaTableState {
 
 #[cfg(test)]
 mod tests {
+
     use super::*;
     use pretty_assertions::assert_eq;
+    use serde_json::json;
 
     #[test]
     fn state_round_trip() {
@@ -489,4 +491,34 @@ mod tests {
         assert_eq!(2, *state.app_transaction_version().get("abc").unwrap());
         assert_eq!(1, *state.app_transaction_version().get("xyz").unwrap());
     }
+
+    #[test]
+    fn test_merging_deserialized_special_tombstones_and_files_paths() {
+        let add = serde_json::from_value(json!({
+            "path": "x=A%252FA/part-00016-94175338-2acc-40c2-a68a-d08ba677975f.c000.snappy.parquet",
+            "partitionValues": {"x": "A/A"},
+            "size": 460,
+            "modificationTime": 1631873480,
+            "dataChange": true
+        }))
+        .unwrap();
+
+        let remove = serde_json::from_value(json!({
+            "path": "x=A%252FA/part-00016-94175338-2acc-40c2-a68a-d08ba677975f.c000.snappy.parquet",
+            "deletionTimestamp": 1631873481,
+            "partitionValues": {"x": "A/A"},
+            "size": 460,
+            "modificationTime": 1631873481,
+            "dataChange": true
+        }))
+        .unwrap();
+
+        let state = DeltaTableState::from_actions(vec![Action::add(add)], 0).unwrap();
+        let state_next = DeltaTableState::from_actions(vec![Action::remove(remove)], 1).unwrap();
+
+        let mut merged_state = state.clone();
+        merged_state.merge(state_next, true, true);
+
+        assert_eq!(merged_state.files().len(), 0);
+    }
 }

rust/tests/data/simple_table_features/_delta_log/00000000000000000000.json

@@ -0,0 +1,9 @@
+{"commitInfo":{"timestamp":1587968586154,"operation":"WRITE","operationParameters":{"mode":"ErrorIfExists","partitionBy":"[]"},"isBlindAppend":true}}
+{"protocol":{"minReaderVersion":5,"minWriterVersion":7,"readerFeatures": ["columnMapping","blahabl","deletionVectors","timestampNtz","v2Checkpoint"],"writerFeatures": ["appendOnly","invariants", "checkConstraints", "changeDataFeed","generatedColumns","columnMapping","identityColumns","deletionVectors","rowTracking","timestampNtz","domainMetadata","v2Checkpoint","icebergCompatV1"]}}
+{"metaData":{"id":"5fba94ed-9794-4965-ba6e-6ee3c0d22af9","format":{"provider":"parquet","options":{}},"schemaString":"{\"type\":\"struct\",\"fields\":[{\"name\":\"id\",\"type\":\"long\",\"nullable\":true,\"metadata\":{}}]}","partitionColumns":[],"configuration":{},"createdTime":1587968585495}}
+{"add":{"path":"part-00000-a72b1fb3-f2df-41fe-a8f0-e65b746382dd-c000.snappy.parquet","partitionValues":{},"size":262,"modificationTime":1587968586000,"dataChange":true}}
+{"add":{"path":"part-00001-c506e79a-0bf8-4e2b-a42b-9731b2e490ae-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968586000,"dataChange":true}}
+{"add":{"path":"part-00003-508ae4aa-801c-4c2c-a923-f6f89930a5c1-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968586000,"dataChange":true}}
+{"add":{"path":"part-00004-80938522-09c0-420c-861f-5a649e3d9674-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968586000,"dataChange":true}}
+{"add":{"path":"part-00006-63ce9deb-bc0f-482d-b9a1-7e717b67f294-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968586000,"dataChange":true}}
+{"add":{"path":"part-00007-94f725e2-3963-4b00-9e83-e31021a93cf9-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968586000,"dataChange":true}}

rust/tests/data/simple_table_features/_delta_log/00000000000000000001.json

@@ -0,0 +1,27 @@
+{"commitInfo":{"timestamp":1587968596254,"operation":"MERGE","operationParameters":{"predicate":"(oldData.`id` = newData.`id`)"},"readVersion":0,"isBlindAppend":false}}
+{"remove":{"path":"part-00006-63ce9deb-bc0f-482d-b9a1-7e717b67f294-c000.snappy.parquet","deletionTimestamp":1587968596250,"dataChange":true}}
+{"remove":{"path":"part-00001-c506e79a-0bf8-4e2b-a42b-9731b2e490ae-c000.snappy.parquet","deletionTimestamp":1587968596253,"dataChange":true}}
+{"remove":{"path":"part-00007-94f725e2-3963-4b00-9e83-e31021a93cf9-c000.snappy.parquet","deletionTimestamp":1587968596253,"dataChange":true}}
+{"remove":{"path":"part-00003-508ae4aa-801c-4c2c-a923-f6f89930a5c1-c000.snappy.parquet","deletionTimestamp":1587968596253,"dataChange":true}}
+{"remove":{"path":"part-00004-80938522-09c0-420c-861f-5a649e3d9674-c000.snappy.parquet","deletionTimestamp":1587968596253,"dataChange":true}}
+{"add":{"path":"part-00000-a922ea3b-ffc2-4ca1-9074-a278c24c4449-c000.snappy.parquet","partitionValues":{},"size":262,"modificationTime":1587968595000,"dataChange":true}}
+{"add":{"path":"part-00004-95c9bc2c-ac85-4581-b3cc-84502b0c314f-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00005-94a0861b-6455-4bd9-a080-73e02491c643-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00011-42f838f9-a911-40af-98f5-2fccfa1b123f-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00045-332fe409-7705-45b1-8d34-a0018cf73b70-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00049-d3095817-de74-49c1-a888-81565a40161d-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00058-b462c4cb-0c48-4148-8475-e21d2a2935f8-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00068-90650739-6a8e-492b-9403-53e33b3778ac-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00069-c78b4dd8-f955-4643-816f-cbd30a3f8c1b-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00077-2fcb1c7c-5390-48ee-93f6-0acf11199a0d-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00107-3f6c2aa0-fc28-4f4c-be15-135e15b398f4-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00112-07fd790a-11dc-4fde-9acd-623e740be992-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00116-bc66759e-6381-4f34-8cd4-6688aad8585d-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00121-d8bc3e53-d2f2-48ce-9909-78da7294ffbd-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00128-b31c3b81-24da-4a90-a8b4-578c9e9a218d-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00140-e9b1971d-d708-43fb-b07f-975d2226b800-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00143-03ceb88e-5283-4193-aa43-993cdf937fd3-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00150-ec6643fc-4963-4871-9613-f5ad1940b689-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00154-4630673a-5227-48fb-a03d-e356fcd1564a-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00164-bf40481c-4afd-4c02-befa-90f056c2d77a-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}
+{"add":{"path":"part-00190-8ac0ae67-fb1d-461d-a3d3-8dc112766ff5-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968596000,"dataChange":true}}

rust/tests/data/simple_table_features/_delta_log/00000000000000000002.json

@@ -0,0 +1,29 @@
+{"commitInfo":{"timestamp":1587968604143,"operation":"WRITE","operationParameters":{"mode":"Overwrite","partitionBy":"[]"},"readVersion":1,"isBlindAppend":false}}
+{"add":{"path":"part-00000-c1777d7d-89d9-4790-b38a-6ee7e24456b1-c000.snappy.parquet","partitionValues":{},"size":262,"modificationTime":1587968602000,"dataChange":true}}
+{"add":{"path":"part-00001-7891c33d-cedc-47c3-88a6-abcfb049d3b4-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968602000,"dataChange":true}}
+{"add":{"path":"part-00003-53f42606-6cda-4f13-8d07-599a21197296-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968602000,"dataChange":true}}
+{"add":{"path":"part-00004-315835fe-fb44-4562-98f6-5e6cfa3ae45d-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968602000,"dataChange":true}}
+{"add":{"path":"part-00006-46f2ff20-eb5d-4dda-8498-7bfb2940713b-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968602000,"dataChange":true}}
+{"add":{"path":"part-00007-3a0e4727-de0d-41b6-81ef-5223cf40f025-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968602000,"dataChange":true}}
+{"remove":{"path":"part-00004-95c9bc2c-ac85-4581-b3cc-84502b0c314f-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00107-3f6c2aa0-fc28-4f4c-be15-135e15b398f4-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00011-42f838f9-a911-40af-98f5-2fccfa1b123f-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00190-8ac0ae67-fb1d-461d-a3d3-8dc112766ff5-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00121-d8bc3e53-d2f2-48ce-9909-78da7294ffbd-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00005-94a0861b-6455-4bd9-a080-73e02491c643-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00077-2fcb1c7c-5390-48ee-93f6-0acf11199a0d-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00112-07fd790a-11dc-4fde-9acd-623e740be992-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00128-b31c3b81-24da-4a90-a8b4-578c9e9a218d-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00000-a922ea3b-ffc2-4ca1-9074-a278c24c4449-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00068-90650739-6a8e-492b-9403-53e33b3778ac-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00164-bf40481c-4afd-4c02-befa-90f056c2d77a-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00045-332fe409-7705-45b1-8d34-a0018cf73b70-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00058-b462c4cb-0c48-4148-8475-e21d2a2935f8-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00140-e9b1971d-d708-43fb-b07f-975d2226b800-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00116-bc66759e-6381-4f34-8cd4-6688aad8585d-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00069-c78b4dd8-f955-4643-816f-cbd30a3f8c1b-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00154-4630673a-5227-48fb-a03d-e356fcd1564a-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00150-ec6643fc-4963-4871-9613-f5ad1940b689-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00049-d3095817-de74-49c1-a888-81565a40161d-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00000-a72b1fb3-f2df-41fe-a8f0-e65b746382dd-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}
+{"remove":{"path":"part-00143-03ceb88e-5283-4193-aa43-993cdf937fd3-c000.snappy.parquet","deletionTimestamp":1587968604143,"dataChange":true}}

rust/tests/data/simple_table_features/_delta_log/00000000000000000003.json

@@ -0,0 +1,5 @@
+{"commitInfo":{"timestamp":1587968614187,"operation":"UPDATE","operationParameters":{"predicate":"((id#697L % cast(2 as bigint)) = cast(0 as bigint))"},"readVersion":2,"isBlindAppend":false}}
+{"remove":{"path":"part-00003-53f42606-6cda-4f13-8d07-599a21197296-c000.snappy.parquet","deletionTimestamp":1587968614096,"dataChange":true}}
+{"remove":{"path":"part-00006-46f2ff20-eb5d-4dda-8498-7bfb2940713b-c000.snappy.parquet","deletionTimestamp":1587968614096,"dataChange":true}}
+{"add":{"path":"part-00000-f17fcbf5-e0dc-40ba-adae-ce66d1fcaef6-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968614000,"dataChange":true}}
+{"add":{"path":"part-00001-bb70d2ba-c196-4df2-9c85-f34969ad3aa9-c000.snappy.parquet","partitionValues":{},"size":429,"modificationTime":1587968614000,"dataChange":true}}

rust/tests/data/simple_table_features/_delta_log/00000000000000000004.json

@@ -0,0 +1,4 @@
+{"commitInfo":{"timestamp":1587968626537,"operation":"DELETE","operationParameters":{"predicate":"[\"((`id` % CAST(2 AS BIGINT)) = CAST(0 AS BIGINT))\"]"},"readVersion":3,"isBlindAppend":false}}
+{"remove":{"path":"part-00001-bb70d2ba-c196-4df2-9c85-f34969ad3aa9-c000.snappy.parquet","deletionTimestamp":1587968626536,"dataChange":true}}
+{"remove":{"path":"part-00000-f17fcbf5-e0dc-40ba-adae-ce66d1fcaef6-c000.snappy.parquet","deletionTimestamp":1587968626536,"dataChange":true}}
+{"add":{"path":"part-00000-2befed33-c358-4768-a43c-3eda0d2a499d-c000.snappy.parquet","partitionValues":{},"size":262,"modificationTime":1587968626000,"dataChange":true}}