Clean up inspect-table and add Cdc action support #527
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,14 +1,17 @@ | ||
| use delta_kernel::actions::visitors::{ | ||
| AddVisitor, CdcVisitor, MetadataVisitor, ProtocolVisitor, RemoveVisitor, SetTransactionVisitor, | ||
| }; | ||
| use delta_kernel::actions::{ | ||
| get_log_schema, ADD_NAME, CDC_NAME, METADATA_NAME, PROTOCOL_NAME, REMOVE_NAME, | ||
| SET_TRANSACTION_NAME, | ||
| }; | ||
| use delta_kernel::engine::default::executor::tokio::TokioBackgroundExecutor; | ||
| use delta_kernel::engine::default::DefaultEngine; | ||
| use delta_kernel::engine_data::{GetData, TypedGetData}; | ||
| use delta_kernel::scan::state::{DvInfo, Stats}; | ||
| use delta_kernel::scan::ScanBuilder; | ||
| use delta_kernel::schema::{DataType, SchemaRef, StructField}; | ||
| use delta_kernel::{DataVisitor, DeltaResult, Error, Table}; | ||
|
|
||
| use std::collections::HashMap; | ||
| use std::process::ExitCode; | ||
|
|
@@ -40,9 +43,9 @@ enum Commands { | |
| ScanData, | ||
| /// Show each action from the log-segments | ||
| Actions { | ||
| /// Show the log in reverse order (default is log replay order -- newest first) | ||
| #[arg(short, long)] | ||
| oldest_first: bool, | ||
| }, | ||
| } | ||
|
|
||
|
|
@@ -58,23 +61,12 @@ fn main() -> ExitCode { | |
| } | ||
|
|
||
| enum Action { | ||
| Metadata(delta_kernel::actions::Metadata), | ||
| Protocol(delta_kernel::actions::Protocol), | ||
| Remove(delta_kernel::actions::Remove), | ||
| Add(delta_kernel::actions::Add), | ||
| SetTransaction(delta_kernel::actions::SetTransaction), | ||
| Cdc(delta_kernel::actions::Cdc), | ||
| } | ||
|
|
||
| fn fields_in(field: &StructField) -> usize { | ||
|
|
@@ -86,89 +78,88 @@ fn fields_in(field: &StructField) -> usize { | |
| } | ||
|
|
||
| struct LogVisitor { | ||
| actions: Vec<(Action, usize)>, | ||
| offsets: HashMap<&'static str, (usize, usize)>, | ||
| previous_rows_seen: usize, | ||
| } | ||
|
|
||
| impl LogVisitor { | ||
| fn new(log_schema: &'static SchemaRef) -> LogVisitor { | ||
| // Grab the start offset for each top-level column name, then compute the end offset by | ||
| // skipping the rest of the leaves for that column. | ||
| let mut start = 0; | ||
| let mut offsets = HashMap::new(); | ||
| for field in log_schema.fields() { | ||
| let end = start + fields_in(field); | ||
| offsets.insert(field.name.as_str(), (start, end)); | ||
| start = end; | ||
| } | ||
| LogVisitor { | ||
| actions: vec![], | ||
| offsets, | ||
| previous_rows_seen: 0, | ||
| } | ||
| } | ||
| } | ||
|
|
||
| impl DataVisitor for LogVisitor { | ||
| fn visit<'a>(&mut self, row_count: usize, getters: &[&'a dyn GetData<'a>]) -> DeltaResult<()> { | ||
| if getters.len() != 55 { | ||
| return Err(Error::InternalError(format!( | ||
| "Wrong number of LogVisitor getters: {}", | ||
| getters.len() | ||
| ))); | ||
| } | ||
| let (add_start, add_end) = self.offsets[&ADD_NAME]; | ||
| let (remove_start, remove_end) = self.offsets[&REMOVE_NAME]; | ||
| let (metadata_start, metadata_end) = self.offsets[&METADATA_NAME]; | ||
| let (protocol_start, protocol_end) = self.offsets[&PROTOCOL_NAME]; | ||
| let (set_transaction_start, set_transaction_end) = self.offsets[&SET_TRANSACTION_NAME]; | ||
| let (cdc_start, cdc_end) = self.offsets[&CDC_NAME]; | ||
| for i in 0..row_count { | ||
| let action = if let Some(path) = getters[add_start].get_opt(i, "add.path")? { | ||
| Action::Add(AddVisitor::visit_add( | ||
| i, | ||
| path, | ||
| &getters[add_start..add_end], | ||
| )?) | ||
| } else if let Some(path) = getters[remove_start].get_opt(i, "remove.path")? { | ||
| Action::Remove(RemoveVisitor::visit_remove( | ||
| i, | ||
| path, | ||
| &getters[remove_start..remove_end], | ||
| )?) | ||
| } else if let Some(id) = getters[metadata_start].get_opt(i, "metadata.id")? { | ||
| Action::Metadata(MetadataVisitor::visit_metadata( | ||
| i, | ||
| id, | ||
| &getters[metadata_start..metadata_end], | ||
| )?) | ||
| } else if let Some(min_reader_version) = | ||
| getters[protocol_start].get_opt(i, "protocol.min_reader_version")? | ||
| { | ||
| Action::Protocol(ProtocolVisitor::visit_protocol( | ||
| i, | ||
| min_reader_version, | ||
| &getters[protocol_start..protocol_end], | ||
| )?) | ||
| } else if let Some(app_id) = getters[set_transaction_start].get_opt(i, "txn.appId")? { | ||
| Action::SetTransaction(SetTransactionVisitor::visit_txn( | ||
| i, | ||
| app_id, | ||
| &getters[set_transaction_start..set_transaction_end], | ||
| )?) | ||
| } else if let Some(path) = getters[cdc_start].get_opt(i, "cdc.path")? { | ||
| Action::Cdc(CdcVisitor::visit_cdc( | ||
| i, | ||
| path, | ||
| &getters[cdc_start..cdc_end], | ||
| )?) | ||
| } else { | ||
| // TODO: Add CommitInfo support (tricky because all fields are optional) | ||
| continue; | ||
|
There was a problem hiding this comment. made #528 for commit info support |
||
| }; | ||
| self.actions.push((action, self.previous_rows_seen + i)); | ||
| } | ||
| self.previous_rows_seen += row_count; | ||
| Ok(()) | ||
|
|
@@ -214,7 +205,7 @@ fn try_main() -> DeltaResult<()> { | |
|
|
||
| let snapshot = table.snapshot(&engine, None)?; | ||
|
|
||
| match cli.command { | ||
| Commands::TableVersion => { | ||
| println!("Latest table version: {}", snapshot.version()); | ||
| } | ||
|
|
@@ -237,7 +228,7 @@ fn try_main() -> DeltaResult<()> { | |
| )?; | ||
| } | ||
| } | ||
| Commands::Actions { oldest_first } => { | ||
| let log_schema = get_log_schema(); | ||
| let actions = snapshot._log_segment().replay( | ||
| &engine, | ||
|
|
@@ -251,22 +242,17 @@ fn try_main() -> DeltaResult<()> { | |
| action?.0.extract(log_schema.clone(), &mut visitor)?; | ||
| } | ||
|
|
||
| if oldest_first { | ||
| visitor.actions.reverse(); | ||
| } | ||
| for (action, row) in visitor.actions.iter() { | ||
| match action { | ||
| Action::Metadata(md) => println!("\nAction {row}:\n{:#?}", md), | ||
| Action::Protocol(p) => println!("\nAction {row}:\n{:#?}", p), | ||
| Action::Remove(r) => println!("\nAction {row}:\n{:#?}", r), | ||
| Action::Add(a) => println!("\nAction {row}:\n{:#?}", a), | ||
| Action::SetTransaction(t) => println!("\nAction {row}:\n{:#?}", t), | ||
| Action::Cdc(c) => println!("\nAction {row}:\n{:#?}", c), | ||
| } | ||
| } | ||
| } | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Any reason for SchemaRef to be static?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Because rust is a bit silly, and you can't probe a
HashMap<String, _>with&str(there's aBorrow<str> for Stringbut noBorrow<&str> for String). So I'm storingHashMap<&'static str, _>instead, to avoid allocating a string for every map probe and/or adding a lifetime to the enclosing struct. I hit a similar issue withColumnNamebtw, but could solve that one by defining a suitable Borrow (can do that since it's a local trait).There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
wow you're right that is silly. TIL the difference between
strand&str👍that makes sense.
And we can't do this because Borrow is a foreign trait, and SchemaRef is a foreign struct (from inspect-table's perspective). While in the example, ColumnName was at least local.
Thanks @scovich!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Update: Turns out if I pass e.g.
offsets[ADD_NAME]instead ofoffsets[&ADD_NAME]then it works!