Add huq data file

.github/workflows/deploy-dev.yml

@@ -60,13 +60,12 @@ jobs:
 
       - name: Get current data
         run: |
-          # cp my-deploy-key deploy-key
           umask 077
           echo "${{ secrets.DEPLOY_KEY }}" > deploy-key
+          echo "${{ secrets.DEPLOY_KEY_HUQ }}" > deploy-key-huq
           eval $(ssh-agent -s)
-          ssh-add deploy-key
-          # ssh-add -l
-          pipenv run dvc update -R data/
+          ssh-add deploy-key deploy-key-huq          
+          pipenv run dvc update data/*.dvc
 
       - name: Run pipelines
         run: |

CONTRIBUTING.md

@@ -66,7 +66,7 @@ will not get the latest data from the remote repository, but will fetch the data
 contained in the commit (md5 hash) referenced in the `.dvc` file.
 
 ```sh
-dvc pull data/published.dvc data/metadata.dvc
+dvc pull -R data/
 ```
 
 If you wish to update to the latest available data, you can run `dvc update`.
@@ -75,7 +75,7 @@ consistent with the `rev` (i.e. branch name) specified in that file (or the
 default branch if that's not specified).
 
 ```sh
-dvc update data/published.dvc data/metadata.dvc
+dvc update -R data/
 ```
 
 These commands will need to be run in an environment where dvc is available. The
@@ -135,3 +135,22 @@ ensure that no leakage takes place.
    to create a `.gitignore` file in the same folder as the page with the a
    general exclusion of `/_data/*`. Exceptions can be added if needed. Once the
    data is approved for publication, this file can be removed.
+
+
+## DVC Remote access
+
+Remote files are loaded from git repos as follows:
+
+```sh
+dvc import -o TARGET_PATH [email protected]:GIT_ORG/GIT_REPO REPO_PATH
+```
+
+> _e.g._ to import data from the `data` directory of the **bradford-2025**
+> repo **my-repo** into the `data/my-data` directory, run the following command
+>
+> ```sh
+> dvc import -o data/my-data [email protected]:bradford-2025/huq-data data 
+> ```
+
+If the repo is private, you will need to have permission to access this data
+via your GitHub account, or will need to provide a deploy key for the repository.

data/.gitignore

@@ -1,3 +1,4 @@
 /processed
 /metadata
 /published
+/huq

data/huq.dvc

@@ -0,0 +1,14 @@
+md5: fad6aa01733a27dbc7e9d908507a9099
+frozen: true
+deps:
+- path: data
+  repo:
+    url: [email protected]:bradford-2025/huq-data
+    rev_lock: 2999e53ca3df0a3e996b76c0c887c9f0b09b85f5
+    rev: main
+outs:
+- md5: 0bcdbf567b2597907e08168965ba01b9.dir
+  size: 7713
+  nfiles: 2
+  hash: md5
+  path: huq

data/metadata.dvc

@@ -1,14 +1,14 @@
-md5: d749518ed517221f70e7d7e609288746
+md5: f881c9ce0905bbfe7bf109d6d4be5a22
 frozen: true
 deps:
 - path: data/metadata/processed/
   repo:
     url: [email protected]:bradford-2025/open-data-pipelines
     rev: main
-    rev_lock: 1ff0179bfcf6c70c54b747750a1aa1d93748ec03
+    rev_lock: f0e342c6aa999ff4f44f94f97e9b2de2163b714c
 outs:
-- md5: bc4b2dd906cc820e657cfe8947e39773.dir
-  size: 9007
+- md5: ccda40852fb7c10e98af94d25f9388b9.dir
+  size: 8995
   nfiles: 7
   hash: md5
   path: metadata

data/published.dvc

@@ -1,14 +1,14 @@
-md5: 6e83378430c5bf96cff3cf5b1e47c992
+md5: 2d1e4a0fb8e9a428cb92698074e949eb
 frozen: true
 deps:
 - path: data/processed/
   repo:
     url: [email protected]:bradford-2025/open-data-pipelines
     rev: main
-    rev_lock: 1ff0179bfcf6c70c54b747750a1aa1d93748ec03
+    rev_lock: f0e342c6aa999ff4f44f94f97e9b2de2163b714c
 outs:
-- md5: cc2a14445e52b2845322da0e59505b3f.dir
-  size: 169708
+- md5: 14509e7ade4dffedd0e1368960a978f7.dir
+  size: 169787
   nfiles: 7
   hash: md5
   path: published

deno.json

@@ -10,8 +10,8 @@
     "dev": "LUME_DRAFTS=true deno task lume -s",
     "build:dev": "LUME_DRAFTS=true deno task lume --location https://dev.open-innovations.org/bradford-2025-data/",
     "deploy:dev": "rsync --info=STATS2 --recursive --delete --rsh=\"sshpass -e ssh -o StrictHostKeyChecking=no -l $SSH_USER\" --rsync-path \"sudo -u www-data rsync\" _site/ $SSH_HOST:$SSH_PATH",
-    "data:pull": "pipenv run dvc pull data/published.dvc data/metadata.dvc",
-    "data:update": "pipenv run dvc update data/published.dvc data/metadata.dvc",
+    "data:pull": "pipenv run dvc pull data/*.dvc",
+    "data:update": "pipenv run dvc update data/*.dvc",
     "data:pipeline": "pipenv run dvc repro pipelines/dvc.yaml",
     "build:full": "deno task data:update && deno task data:pipeline && deno task build"
   },