keep github.tsv sorted

Author: pdurbin

.githooks/pre-commit

@@ -0,0 +1,5 @@
+#!/bin/sh
+if git diff --cached --name-only | grep -q '^github\.tsv$'; then
+  scripts/check-sorted.sh --fix
+  git add github.tsv
+fi

.github/workflows/check-sorted.yml

@@ -0,0 +1,13 @@
+name: Check github.tsv is sorted
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  check-sorted:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Verify github.tsv is sorted
+        run: scripts/check-sorted.sh

CONTRIBUTING.md

@@ -26,3 +26,9 @@ Finally, issue the following commands to download JSON files about each project
 A file called `data.tsv` should result, representing the data you just downloaded. Again, it should look something like the tsv file described above or the one at http://dx.doi.org/10.7910/DVN/TJCLKP .
 
 If you have any trouble with the commands above or have any ideas for this project, please open a GitHub issue. Pull request are also very welcome!
+
+## Keeping github.tsv sorted
+
+After cloning, run this once to enable the pre-commit hook that keeps `github.tsv` sorted:
+
+    git config core.hooksPath .githooks

github.tsv

@@ -64,9 +64,9 @@ https://github.com/DRSC-FG/gene2function
 https://github.com/farhat-lab/gentb-site
 https://github.com/fasrc/helmod
 https://github.com/FilteredPush/event_date_qc
-https://github.com/FilteredPush/sci_name_qc
-https://github.com/FilteredPush/geo_ref_qc
 https://github.com/FilteredPush/FP-KurationServices
+https://github.com/FilteredPush/geo_ref_qc
+https://github.com/FilteredPush/sci_name_qc
 https://github.com/glue-viz/glue
 https://github.com/harvard-dce/canvas-docker
 https://github.com/harvard-dce/dce_lti
@@ -110,7 +110,6 @@ https://github.com/HarvardOpenData/propublica-data
 https://github.com/HarvardPL/shill
 https://github.com/HarvardX/edx_course_templater
 https://github.com/HarvardX/studio-advanced
-https://github.com/HBRGTech/daisy
 https://github.com/hbctraining/Intro-to-bulk-RNAseq
 https://github.com/hbctraining/Intro-to-DGE
 https://github.com/hbctraining/Intro-to-peak-analysis
@@ -122,6 +121,7 @@ https://github.com/hbctraining/Pseudobulk-for-scRNAseq
 https://github.com/hbctraining/Shell-for-bioinformatics
 https://github.com/hbctraining/Tools-for-reproducible-research
 https://github.com/hbctraining/Training-modules
+https://github.com/HBRGTech/daisy
 https://github.com/hms-dbmi/scde
 https://github.com/hms-dbmi/UpSetR
 https://github.com/hms-dbmi/viv
@@ -161,7 +161,7 @@ https://github.com/OpenSDP/nearly-unique-stata
 https://github.com/OpenSDP/OpenSDPsynthR
 https://github.com/OpenSDP/template-r
 https://github.com/OpenSDP/template-stata
-https://github.com/Slicer/Slicer
 https://github.com/penzance/canvas_python_sdk
 https://github.com/penzance/harvard-data-tools
 https://github.com/refinery-platform/refinery-platform
+https://github.com/Slicer/Slicer

scripts/check-sorted.sh

@@ -0,0 +1,16 @@
+#!/bin/sh
+# Usage: check-sorted.sh [--fix]
+# Checks that github.tsv is sorted (case-insensitive, header preserved).
+# With --fix, sorts it in place.
+file=github.tsv
+sorted=$({ head -1 "$file"; tail -n +2 "$file" | sort -f; })
+if [ "$sorted" = "$(cat "$file")" ]; then
+  exit 0
+fi
+if [ "$1" = "--fix" ]; then
+  printf '%s\n' "$sorted" > "$file"
+  echo "Sorted $file"
+else
+  echo "$file is not sorted. Run: scripts/check-sorted.sh --fix"
+  exit 1
+fi