change github workflows to require test to pass before docs

.github/workflows/build.yml

@@ -0,0 +1,22 @@
+name: build
+on:
+  push:
+    branches: [ "main" ]
+  workflow_dispatch:
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+  call-workflow1:
+    name: tests
+    uses: ./.github/workflows/test.yml
+  call-workflow2:
+    needs: call-workflow1
+    name: docs
+    uses: ./.github/workflows/docs.yml
+  print:
+    needs: [call-workflow1]
+    runs-on: ubuntu-latest
+    steps:
+       - run: echo "${{ needs.call-workflow1 }}"

.github/workflows/docs.yml

@@ -1,13 +1,6 @@
-name: website
+name: docs
 
-# build the documentation whenever there are new commits on main
-on:
-  push:
-    branches:
-      - main
-    # Alternative: only build for tags.
-    # tags:
-    #   - '*'
+on: workflow_call
 
 # security: restrict permissions for CI jobs.
 permissions:

.github/workflows/test.yml

@@ -1,6 +1,6 @@
 name: tests
 
-on: [push]
+on: workflow_call
 
 jobs:
   build:

src/sciterra/vectorization/preprocessing.py

@@ -2,7 +2,11 @@
 
 import spacy
 
-nlp = spacy.load("en_core_web_sm")
+model = "en_core_web_sm"
+try:
+    nlp = spacy.load(model)
+except OSError:
+    raise OSError(f"Can't find model '{model}'; make sure you have run 'python3 -m spacy download {model}'!")
 
 # Another off the shelf simple tokenizer
 from gensim.utils import simple_preprocess