Updates contributing and PR checks

.github/CONTRIBUTING.md

@@ -19,7 +19,7 @@
 You can add, edit or remove entries by opening a pull request.
 
 All data is stored in [`awesome-privacy.yml`](https://github.com/Lissy93/awesome-privacy/blob/main/awesome-privacy.yml).
-If you're adding, editing or removing a listing - **this is the only file you need to edit**.
+If you're adding, editing or removing a listing - **this is the only file you need to edit**. Don't edit the README directly, as this is auto-generated from the YAML file.
 
 ### Process
 
@@ -74,12 +74,11 @@ Usually these entries go within the "Notable Mentions" section instead._
 
 Your pull request must follow these requirements. Failure to do so, might result in it being closed.
 
-- Do not edit the README directly when adding / editing a listing
+- Do not edit the README directly when adding / editing a listing (it's auto-generated!)
 - Ensure your PR is not a duplicate, search for existing / previous submissions first
-- You must respond to any comments or requests for changes in a timely manner, 48-hours maximum
+- You must respond to any comments or requests for changes in a timely manner, 14 days maximum
 - Write short but descriptive git commit messages, under 50 characters. This must be in the format of `Adds [software-name] to [section-name]`. Your PR will be rejected if you name it `Updates README.md`
 - Only include a single addition / amendment / removal, per pull request
-- If your pull request contains multiple commits, you must squash them first
 - You must complete each of the sections in the pull request template. Do not delete it!
 - Where applicable, include links to supporting material for your addition: git repo, docs, recent security audits, etc. This will make researching it much easier for reviewers
 - While adding new software to the list, don't make your entry read like an advert. Be objective, and include drawbacks as well as strengths
@@ -90,8 +89,8 @@ Your pull request must follow these requirements. Failure to do so, might result
 - You must adhere to the Contributor Covenant Code of Conduct
 - Don't open a Draft / WIP pull request while you work on the guidelines. A pull request should be 100% ready and should adhere to all the above guidelines when you open it
 - Your changes must be correctly spelled, and with good grammar
-- Your changes must be correctly formatted, in valid markdown
-- The addition title must be a link the project, and in bold
+- Your changes must be correctly formatted, in valid yaml and markdown
+- The addition title must be a link the project
 - The addition description must be no less than 50, and no more than 250 characters, keep it clear and to the point
 
 ---
@@ -103,8 +102,6 @@ This file may look a bit daunting to start with, but don't worry - it's pretty s
 
 ### Top-Level Structure
 
-
-
 ```mermaid
 ---
 title: Class Diagram

lib/checks/check-additions.py

@@ -35,6 +35,22 @@ OPENSOURCE_MSG = (
     f" [Requirements]({CONTRIBUTING}#requirements)."
     " Please ensure that this is justified in your PR body."
 )
+DUPLICATE_NAME_MSG = (
+    "A service named `{name}` already exists (in {location})."
+    " If this is a different service, please clarify in your PR description"
+)
+DUPLICATE_URL_MSG = (
+    "The URL `{url}` is already associated with `{existing}`."
+    " Please check this isn't a duplicate submission"
+)
+DESC_LENGTH_MSG = (
+    "Description length ({length} chars) is outside the recommended 50\u2013250"
+    f" character range. Please see our [Contributing Guidelines]({CONTRIBUTING}#description)"
+)
+OPENSOURCE_GITHUB_MSG = (
+    "You marked this service as open source but didn't include a `github` field."
+    " Please add the repository link"
+)
 
 
 def load_json(path):
@@ -81,7 +97,7 @@ def check_required_fields(diff, head):
     for svc in diff.get("services", {}).get("added", []):
         fields = svc.get("fields", {})
         for f in REQUIRED_FIELDS:
-            if not fields.get(f):
+            if fields.get(f) is None:
                 missing.add(f)
     for svc in diff.get("services", {}).get("modified", []):
         if not head:
@@ -92,7 +108,7 @@ def check_required_fields(diff, head):
         )
         if fields:
             for f in REQUIRED_FIELDS:
-                if f in changed and not fields.get(f):
+                if f in changed and fields.get(f) is None:
                     missing.add(f)
     if missing:
         names = ", ".join(f"`{f}`" for f in sorted(missing))
@@ -133,6 +149,75 @@ def check_single_entry(diff):
     return None
 
 
+def build_name_index(head):
+    """Build {lowercase_name: "category > section"} from all services."""
+    index = {}
+    if not head:
+        return index
+    for cat in head.get("categories", []):
+        cn = cat.get("name", "")
+        for sec in cat.get("sections", []):
+            sn = sec.get("name", "")
+            for svc in sec.get("services", []):
+                name = svc.get("name", "").lower().strip()
+                if name:
+                    index[name] = f"{cn} > {sn}"
+    return index
+
+
+def build_url_index(head):
+    """Build {url: service_name} from all services, skipping empty URLs."""
+    index = {}
+    if not head:
+        return index
+    for cat in head.get("categories", []):
+        for sec in cat.get("sections", []):
+            for svc in sec.get("services", []):
+                url = svc.get("url", "")
+                if url:
+                    index[url] = svc.get("name", "")
+    return index
+
+
+def check_duplicate_name(diff, name_index):
+    """Return a finding if an added service name already exists in the YAML."""
+    for svc in diff.get("services", {}).get("added", []):
+        name = svc.get("fields", {}).get("name", "").lower().strip()
+        if name and name in name_index:
+            return DUPLICATE_NAME_MSG.format(
+                name=svc["fields"]["name"], location=name_index[name],
+            )
+    return None
+
+
+def check_duplicate_url(diff, url_index):
+    """Return a finding if an added service URL already exists in the YAML."""
+    for svc in diff.get("services", {}).get("added", []):
+        url = svc.get("fields", {}).get("url", "")
+        if url and url in url_index:
+            return DUPLICATE_URL_MSG.format(url=url, existing=url_index[url])
+    return None
+
+
+def check_description_length(diff):
+    """Return a finding if an added service description is outside 50-250 chars."""
+    for svc in diff.get("services", {}).get("added", []):
+        desc = svc.get("fields", {}).get("description", "")
+        length = len(desc)
+        if length < 50 or length > 250:
+            return DESC_LENGTH_MSG.format(length=length)
+    return None
+
+
+def check_opensource_github(diff):
+    """Return a finding if an added service is open source but has no github field."""
+    for svc in diff.get("services", {}).get("added", []):
+        fields = svc.get("fields", {})
+        if fields.get("openSource") is True and not fields.get("github"):
+            return OPENSOURCE_GITHUB_MSG
+    return None
+
+
 def main():
     findings = []
     try:
@@ -158,6 +243,25 @@ def main():
             finding = check_open_source(diff)
             if finding:
                 findings.append(finding)
+
+            name_index = build_name_index(head)
+            url_index = build_url_index(head)
+
+            finding = check_duplicate_name(diff, name_index)
+            if finding:
+                findings.append(finding)
+
+            finding = check_duplicate_url(diff, url_index)
+            if finding:
+                findings.append(finding)
+
+            finding = check_description_length(diff)
+            if finding:
+                findings.append(finding)
+
+            finding = check_opensource_github(diff)
+            if finding:
+                findings.append(finding)
     except Exception:
         pass
 

lib/checks/check-project.py

@@ -126,21 +126,31 @@ def get_services(diff, key):
 
 
 def check_links(diff, head):
-    """Return LINK_MSG if any service URL is unreachable."""
+    """Return LINK_MSG if any service URL or icon URL is unreachable."""
     for svc in get_services(diff, "added"):
-        url = svc.get("fields", {}).get("url")
+        fields = svc.get("fields", {})
+        url = fields.get("url")
         if url and not check_url(url):
             return LINK_MSG
+        icon = fields.get("icon")
+        if icon and not check_url(icon):
+            return LINK_MSG
     for svc in get_services(diff, "modified"):
-        if "url" not in svc.get("changed_fields", []):
+        changed = svc.get("changed_fields", [])
+        if "url" not in changed and "icon" not in changed:
             continue
         head_svc = find_service_in_head(
             head, svc["category"], svc["section"], svc["service"]
         )
         if head_svc:
-            url = head_svc.get("url")
-            if url and not check_url(url):
-                return LINK_MSG
+            if "url" in changed:
+                url = head_svc.get("url")
+                if url and not check_url(url):
+                    return LINK_MSG
+            if "icon" in changed:
+                icon = head_svc.get("icon")
+                if icon and not check_url(icon):
+                    return LINK_MSG
     return None
 
 

lib/checks/check-yaml-diff.py

@@ -187,16 +187,18 @@ def main():
     write_github_output("has_service_changes", str(bool(added or removed or modified)).lower())
     write_step_summary(diff_result)
 
-    svc_count = len(added) + len(removed) + len(modified)
-    if svc_count > 1:
-        print(red(f"Single-entry rule violation: {svc_count} service changes found."), file=sys.stderr)
+    added_count = len(added)
+    if added_count > 1:
+        print(red(f"Single-entry rule violation: {added_count} service additions found."), file=sys.stderr)
         sys.exit(EXIT_RULE_VIOLATION)
-    if svc_count == 0 and len(sections) > 1:
+    if added_count == 0 and len(sections) > 1:
         print(red(f"Single-entry rule violation: {len(sections)} section changes found."), file=sys.stderr)
         sys.exit(EXIT_RULE_VIOLATION)
 
-    print(green(f"Single-entry rule passed. {svc_count} service, "
-                f"{len(sections)} section, {len(categories)} category change(s)."))
+    total = len(added) + len(removed) + len(modified)
+    print(green(f"Single-entry rule passed. {total} service "
+                f"({added_count} added), {len(sections)} section, "
+                f"{len(categories)} category change(s)."))
     sys.exit(EXIT_PASS)