From 53babe65b15b7ee0ca48739fff78a38412349e38 Mon Sep 17 00:00:00 2001
From: Jamie Lentin <jm@lentin.co.uk>
Date: Fri, 29 May 2026 15:45:52 +0000
Subject: [PATCH 1/2] dvc: Don't track data/js_output, always regenerate

The .gz files in data/js_output/ aren't stable, so we can't use them in
as part of a pipeline, as we'll constantly regenerate and upload new
ones.

Instead, mark the stage as always_changed, meaning it'll get re-run
even on repro --pull.
---
 dvc.lock | 6 ------
 dvc.yaml | 3 +--
 2 files changed, 1 insertion(+), 8 deletions(-)

diff --git a/dvc.lock b/dvc.lock
index a94607e..cc7581b 100644
--- a/dvc.lock
+++ b/dvc.lock
@@ -262,12 +262,6 @@ stages:
       md5: 81dfa9c3747bbe94c57161cc8e22d5c9.dir
       size: 1158499655
       nfiles: 7
-    outs:
-    - path: data/js_output/
-      hash: md5
-      md5: 9782411b79a64d6da09afacae2f3f047.dir
-      size: 8297912
-      nfiles: 6
   discover_latest_wikidata_dump_url:
     cmd: discover_latest_wikidata_dump_url > 
       data/Wiki/wd_JSON/latest-all-json-bz2-url.txt
diff --git a/dvc.yaml b/dvc.yaml
index 6e2a357..94480a2 100644
--- a/dvc.yaml
+++ b/dvc.yaml
@@ -197,5 +197,4 @@ stages:
       - make_js_treefiles --outdir data/js_output
     deps:
       - data/output_files/
-    outs:
-      - data/js_output/
+    always_changed: true

From 2b95e00bc7d09cb9983a79baa3bee750e6ad44f5 Mon Sep 17 00:00:00 2001
From: Jamie Lentin <jm@lentin.co.uk>
Date: Fri, 29 May 2026 16:15:03 +0000
Subject: [PATCH 2/2] .github: Freeze make_js_treefiles before checking status

make_js_treefiles is always_changed, so unless we ignore it the test
will always fail,
---
 .github/workflows/tests.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index f78dba0..26dd334 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -43,6 +43,7 @@ jobs:
           [ -n "${{ secrets.DVC_SECRET_ACCESS_KEY }}" ] || { echo "DVC_SECRET_ACCESS_KEY secret is not set"; exit 1; }
           dvc remote modify onezoom-r2 access_key_id ${{ secrets.DVC_ACCESS_KEY_ID }}
           dvc remote modify onezoom-r2 secret_access_key ${{ secrets.DVC_SECRET_ACCESS_KEY }}
+          dvc freeze make_js_treefiles
           dvc repro --allow-missing --dry | tee /dev/stderr | grep -q "Data and pipelines are up to date."
           if dvc data status --not-in-remote | grep -q "Not in remote"; then exit 1; fi
   test: