Merge branch 'sherlock-project:master' into code-sandbox

Author: manjushsh

.github/workflows/validate_modified_targets.yml

@@ -17,38 +17,57 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v5
         with:
+          # Checkout the base branch but fetch all history to avoid a second fetch call
           ref: ${{ github.base_ref }}
-          fetch-depth: 1
+          fetch-depth: 0
 
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: '3.13'
+          python-version: "3.13"
 
       - name: Install Poetry
         uses: abatilo/actions-poetry@v4
         with:
-          poetry-version: 'latest'
+          poetry-version: "latest"
 
       - name: Install dependencies
         run: |
           poetry install --no-interaction --with dev
 
-      - name: Drop in place updated manifest from base
+      - name: Prepare JSON versions for comparison
         run: |
-          cp sherlock_project/resources/data.json data.json.base
-          git fetch origin pull/${{ github.event.pull_request.number }}/head:pr --depth=1
-          git show pr:sherlock_project/resources/data.json > sherlock_project/resources/data.json
-          cp sherlock_project/resources/data.json data.json.head
+          # Fetch only the PR's branch head (single network call in this step)
+          git fetch origin pull/${{ github.event.pull_request.number }}/head:pr
+
+          # Find the merge-base commit between the target branch and the PR branch
+          MERGE_BASE=$(git merge-base origin/${{ github.base_ref }} pr)
+          echo "Comparing PR head against merge-base commit: $MERGE_BASE"
+
+          # Safely extract the file from the PR's head and the merge-base commit
+          git show pr:sherlock_project/resources/data.json > data.json.head
+          git show $MERGE_BASE:sherlock_project/resources/data.json > data.json.base
+
+          # CRITICAL FIX: Overwrite the checked-out data.json with the one from the PR
+          # This ensures that pytest runs against the new, updated file.
+          cp data.json.head sherlock_project/resources/data.json
 
       - name: Discover modified targets
         id: discover-modified
         run: |
           CHANGED=$(
             python - <<'EOF'
           import json
-          with open("data.json.base") as f: base = json.load(f)
-          with open("data.json.head") as f: head = json.load(f)
+          import sys
+          try:
+              with open("data.json.base") as f: base = json.load(f)
+              with open("data.json.head") as f: head = json.load(f)
+          except FileNotFoundError as e:
+              print(f"Error: Could not find {e.filename}", file=sys.stderr)
+              sys.exit(1)
+          except json.JSONDecodeError as e:
+              print(f"Error: Could not decode JSON from a file - {e}", file=sys.stderr)
+              sys.exit(1)
 
           changed = []
           for k, v in head.items():
@@ -63,6 +82,8 @@ jobs:
           echo -e ">>> Changed targets: \n$(echo $CHANGED | tr ',' '\n')"
           echo "changed_targets=$CHANGED" >> "$GITHUB_OUTPUT"
 
+      # --- The rest of the steps below are unchanged ---
+
       - name: Validate modified targets
         if: steps.discover-modified.outputs.changed_targets != ''
         continue-on-error: true

sherlock_project/resources/data.json

@@ -259,7 +259,8 @@
     "username_claimed": "blue"
   },
   "Blitz Tactics": {
-    "errorType": "status_code",
+    "errorMsg": "That page doesn't exist",
+    "errorType": "message",
     "url": "https://blitztactics.com/{}",
     "urlMain": "https://blitztactics.com/",
     "username_claimed": "Lance5500"
@@ -278,6 +279,7 @@
     "urlMain": "https://bsky.app/",
     "username_claimed": "mcuban"
   },
+
   "BongaCams": {
     "errorType": "status_code",
     "isNSFW": true,
@@ -2333,6 +2335,12 @@
     "urlMain": "https://discourse.wicg.io/",
     "username_claimed": "stefano"
   },
+  "Wakatime": {
+    "errorType": "status_code",
+    "url": "https://wakatime.com/@{}",
+    "urlMain": "https://wakatime.com/",
+    "username_claimed": "blue"
+  },
   "Warrior Forum": {
     "errorType": "status_code",
     "url": "https://www.warriorforum.com/members/{}.html",
@@ -2877,13 +2885,6 @@
     "urlMain": "https://znanylekarz.pl",
     "username_claimed": "janusz-nowak"
   },
-  "Bluesky": {
-    "errorType": "status_code",
-    "url": "https://bsky.app/profile/{}.bsky.social",
-    "urlProbe": "https://public.api.bsky.app/xrpc/app.bsky.actor.getProfile?actor={}.bsky.social",
-    "urlMain": "https://bsky.app/",
-    "username_claimed": "mcuban"
-  },
   "Platzi": {
     "errorType": "status_code",
     "errorCode": 404,