Rename sts_synindex_external.R script to internal_to_external_staging.R

Dockerfile

@@ -29,4 +29,4 @@ RUN sed -i -e "s|\"<PERSONAL_ACCESS_TOKEN>\"|\"\${AWS_SYNAPSE_TOKEN}\"\n|g" \
 CMD R -e "q()" \
     && sed -i -e "s|\${AWS_SYNAPSE_TOKEN}|$AWS_SYNAPSE_TOKEN|g"\
     /root/.aws/config \
-    && Rscript /root/recover-parquet-external/sts_synindex_external.R
+    && Rscript /root/recover-parquet-external/scripts/main/internal_to_external_staging.R

README.md

@@ -85,7 +85,7 @@ git clone https://github.com/Sage-Bionetworks/recover-parquet-external.git
 2. Modify the parameters in the [config](config/config.yml) as needed
 3. Run [install_requirements.R](install_requirements.R)
 
-4. Run [sts_synindex_external.R](scripts/main/sts_synindex_external.R) to generate the external parquet datasets in the staging locations (S3 and Synapse).
+4. Run [internal_to_external_staging.R](scripts/main/internal_to_external_staging.R) to generate the external parquet datasets in the staging locations (S3 and Synapse).
 5. Once the datasets in the staging location have been validated, run [staging_to_archive.R](scripts/main/staging_to_archive.R) to generate the validated external parquet datasets in the date-tagged prod Archive locations (S3 and Synapse).
 6. As needed, run [archive-to-current.R](scripts/main/archive-to-current.R) to update the Current Freeze version of the external parquet data in the appropriate locations (S3 and Synapse).
 7. **(Optional)** Setup a scheduled job (AWS, cron, etc.) using the docker image to run the pipeline at a set frequency or when certain conditions are met

scripts/main/sts_synindex_external.R → scripts/main/internal_to_external_staging.R

@@ -219,7 +219,7 @@ if (nrow(synapse_fileview)>0) {
 
 # Index each file in Synapse
 latest_commit <- gh::gh("/repos/:owner/:repo/commits/main", owner = "Sage-Bionetworks", repo = "recover-parquet-external")
-latest_commit_this_file <- paste0(latest_commit$html_url %>% stringr::str_replace("commit", "blob"), "/scripts/main/sts_synindex_external.R")
+latest_commit_this_file <- paste0(latest_commit$html_url %>% stringr::str_replace("commit", "blob"), "/scripts/main/internal_to_external_staging.R")
 
 act <- synapser::Activity(name = "Indexing",
                           description = "Indexing external parquet datasets",