From e0f6b934603045c2a69611a806b2dfadc8ac95b5 Mon Sep 17 00:00:00 2001 From: Roy Crihfield Date: Fri, 1 Sep 2023 17:39:26 +0800 Subject: [PATCH] update docs --- README.md | 12 ++++++------ scripts/README.md | 20 ++++++++++---------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index f4b09e8..327bad9 100644 --- a/README.md +++ b/README.md @@ -125,8 +125,8 @@ Config format: * Combine output from multiple workers and copy to post-processed output directory: ```bash - # public.blocks - cat {output_dir,output_dir/*}/public.blocks.csv > output_dir/processed_output/combined-public.blocks.csv + # ipld.blocks + cat {output_dir,output_dir/*}/ipld.blocks.csv > output_dir/processed_output/combined-ipld.blocks.csv # eth.state_cids cat output_dir/*/eth.state_cids.csv > output_dir/processed_output/combined-eth.state_cids.csv @@ -144,8 +144,8 @@ Config format: * De-duplicate data: ```bash - # public.blocks - sort -u output_dir/processed_output/combined-public.blocks.csv -o output_dir/processed_output/deduped-combined-public.blocks.csv + # ipld.blocks + sort -u output_dir/processed_output/combined-ipld.blocks.csv -o output_dir/processed_output/deduped-combined-ipld.blocks.csv # eth.header_cids sort -u output_dir/processed_output/eth.header_cids.csv -o output_dir/processed_output/deduped-eth.header_cids.csv @@ -171,8 +171,8 @@ Config format: # public.nodes COPY public.nodes FROM '/output_dir/processed_output/public.nodes.csv' CSV; - # public.blocks - COPY public.blocks FROM '/output_dir/processed_output/deduped-combined-public.blocks.csv' CSV; + # ipld.blocks + COPY ipld.blocks FROM '/output_dir/processed_output/deduped-combined-ipld.blocks.csv' CSV; # eth.header_cids COPY eth.header_cids FROM '/output_dir/processed_output/deduped-eth.header_cids.csv' CSV; diff --git a/scripts/README.md b/scripts/README.md index a0f0f43..392f0af 100644 --- a/scripts/README.md +++ b/scripts/README.md @@ -2,13 +2,13 @@ * For a given table in the `ipld-eth-db` schema, we know the number of columns to be expected in each row in the data dump: - | Table | Expected columns | - | ----------------- |:----------------:| - | public.nodes | 5 | - | public.blocks | 3 | - | eth.header_cids | 16 | - | eth.state_cids | 8 | - | eth.storage_cids | 9 | + | Table | Expected columns | + |--------------------|:----------------:| + | `public.nodes` | 5 | + | `ipld.blocks` | 3 | + | `eth.header_cids` | 16 | + | `eth.state_cids` | 8 | + | `eth.storage_cids` | 9 | ### Find Bad Data @@ -29,7 +29,7 @@ ```bash ./scripts/find-bad-rows.sh -i eth.state_cids.csv -c 8 -o res.txt -d true ``` - + Output: ``` @@ -40,7 +40,7 @@ ```bash ./scripts/find-bad-rows.sh -i public.nodes.csv -c 5 -o res.txt -d true - ./scripts/find-bad-rows.sh -i public.blocks.csv -c 3 -o res.txt -d true + ./scripts/find-bad-rows.sh -i ipld.blocks.csv -c 3 -o res.txt -d true ./scripts/find-bad-rows.sh -i eth.header_cids.csv -c 16 -o res.txt -d true ./scripts/find-bad-rows.sh -i eth.state_cids.csv -c 8 -o res.txt -d true ./scripts/find-bad-rows.sh -i eth.storage_cids.csv -c 9 -o res.txt -d true @@ -66,7 +66,7 @@ ```bash ./scripts/filter-bad-rows.sh -i public.nodes.csv -c 5 -o cleaned-public.nodes.csv - ./scripts/filter-bad-rows.sh -i public.blocks.csv -c 3 -o cleaned-public.blocks.csv + ./scripts/filter-bad-rows.sh -i ipld.blocks.csv -c 3 -o cleaned-ipld.blocks.csv ./scripts/filter-bad-rows.sh -i eth.header_cids.csv -c 16 -o cleaned-eth.header_cids.csv ./scripts/filter-bad-rows.sh -i eth.state_cids.csv -c 8 -o cleaned-eth.state_cids.csv ./scripts/filter-bad-rows.sh -i eth.storage_cids.csv -c 9 -o cleaned-eth.storage_cids.csv