Merge pull request #71 from paradigmxyz/undo_last_two

revert 2 commits for refactor merge, will add back in exponential backoff code after merging refactor

Cargo.toml

@@ -33,7 +33,6 @@ governor = "0.5.1"
 hex = "0.4.3"
 indexmap = "2.0.0"
 indicatif = "0.17.5"
-lazy_static = "1.4.0"
 polars = { version = "0.32.1", features = [
     "parquet",
     "string_encoding",

README.md

@@ -90,13 +90,12 @@ Many `cryo` cli options will affect output schemas by adding/removing columns or
 #### Schema Design Guide
 
 An attempt is made to ensure that the dataset schemas conform to a common set of design guidelines:
-- By default, rows should contain enough information in their columns to be order-able (unless the rows do not have an intrinsic order)
+- By default, rows should contain enough information be order-able
 - Columns should be named by their JSON-RPC or ethers.rs defaults, except in cases where a much more explicit name is available
 - To make joins across tables easier, a given piece of information should use the same datatype and column name across tables when possible
 - Large ints such as `u256` should allow multiple conversions. A `value` column of type `u256` should allow: `value_binary`, `value_string`, `value_f32`, `value_f64`, `value_u32`, `value_u64`, and `value_d128`
 - By default, columns related to non-identifying cryptographic signatures are omitted by default. For example, `state_root` of a block or `v`/`r`/`s` of a transaction
 - Integer values that can never be negative should be stored as unsigned integers
-- Every table should allow an optional `chain_id` column so that data from multiple chains can be easily stored in the same table.
 
 Standard types across tables:
 - `block_number`: `u32`

crates/cli/src/args.rs

@@ -78,14 +78,6 @@ pub struct Args {
     #[arg(short('l'), long, value_name = "limit", help_heading = "Acquisition Options")]
     pub requests_per_second: Option<u32>,
 
-    /// Specify max retries on provider errors
-    #[arg(long, default_value_t = 5, value_name = "R", help_heading = "Acquisition Options")]
-    pub max_retries: u32,
-
-    /// Specify initial backoff for retry strategy (ms)
-    #[arg(long, default_value_t = 500, value_name = "B", help_heading = "Acquisition Options")]
-    pub initial_backoff: u64,
-
     /// Global number of concurrent requests
     #[arg(long, value_name = "M", help_heading = "Acquisition Options")]
     pub max_concurrent_requests: Option<u64>,
@@ -155,37 +147,9 @@ pub struct Args {
     #[arg(long, help_heading = "Output Options")]
     pub no_report: bool,
 
-    /// Address
-    #[arg(long, help_heading = "Dataset-specific Options", num_args(1..))]
-    pub address: Option<Vec<String>>,
-
-    /// To Address
-    #[arg(long, help_heading = "Dataset-specific Options", num_args(1..), value_name="TO")]
-    pub to_address: Option<Vec<String>>,
-
-    /// From Address
-    #[arg(long, help_heading = "Dataset-specific Options", num_args(1..), value_name="FROM")]
-    pub from_address: Option<Vec<String>>,
-
-    /// [eth_calls] Call data to use for eth_calls
-    #[arg(long, help_heading = "Dataset-specific Options", num_args(1..))]
-    pub call_data: Option<Vec<String>>,
-
-    /// [eth_calls] Function to use for eth_calls
-    #[arg(long, help_heading = "Dataset-specific Options", num_args(1..))]
-    pub function: Option<Vec<String>>,
-
-    /// [eth_calls] Inputs to use for eth_calls
-    #[arg(long, help_heading = "Dataset-specific Options", num_args(1..))]
-    pub inputs: Option<Vec<String>>,
-
-    /// [slots] Slots
-    #[arg(long, help_heading = "Dataset-specific Options", num_args(1..))]
-    pub slots: Option<Vec<String>>,
-
     /// [logs] filter logs by contract address
     #[arg(long, help_heading = "Dataset-specific Options")]
-    pub contract: Option<Vec<String>>,
+    pub contract: Option<String>,
 
     /// [logs] filter logs by topic0
     #[arg(long, visible_alias = "event", help_heading = "Dataset-specific Options")]
@@ -206,14 +170,14 @@ pub struct Args {
     /// [logs] Blocks per request
     #[arg(
         long,
-        value_name = "SIZE",
+        value_name = "BLOCKS",
         default_value_t = 1,
         help_heading = "Dataset-specific Options"
     )]
     pub inner_request_size: u64,
 
     /// [logs] event signature to parse
-    #[arg(long, value_name = "SIGNATURE", help_heading = "Dataset-specific Options")]
+    #[arg(long, help_heading = "Dataset-specific Options")]
     pub event_signature: Option<String>,
 }
 

crates/cli/src/parse/blocks.rs

@@ -1,8 +1,7 @@
 use ethers::prelude::*;
 use polars::prelude::*;
-use std::collections::HashMap;
 
-use cryo_freeze::{BlockChunk, Chunk, ChunkData, Datatype, Fetcher, ParseError, Subchunk, Table};
+use cryo_freeze::{BlockChunk, Chunk, ChunkData, Fetcher, ParseError, Subchunk};
 
 use crate::args::Args;
 
@@ -124,15 +123,8 @@ async fn postprocess_block_chunks<P: JsonRpcClient>(
 pub(crate) async fn get_default_block_chunks<P: JsonRpcClient>(
     args: &Args,
     fetcher: Arc<Fetcher<P>>,
-    schemas: &HashMap<Datatype, Table>,
 ) -> Result<Vec<(Chunk, Option<String>)>, ParseError> {
-    let default_blocks = schemas
-        .keys()
-        .map(|datatype| datatype.dataset().default_blocks())
-        .find(|blocks| !blocks.is_none())
-        .unwrap_or(Some("0:latest".to_string()))
-        .unwrap();
-    let block_chunks = parse_block_inputs(&default_blocks, &fetcher).await?;
+    let block_chunks = parse_block_inputs(&String::from(r"0:latest"), &fetcher).await?;
     postprocess_block_chunks(block_chunks, args, fetcher).await
 }
 

crates/cli/src/parse/mod.rs

@@ -1,11 +1,12 @@
 mod args;
 mod blocks;
 mod file_output;
-mod parse_utils;
 mod query;
-mod schemas;
 mod source;
 mod transactions;
 
 pub use args::*;
-use schemas::*;
+// use blocks::*;
+// use file_output::*;
+// use query::*;
+// use source::*;