Add basic backend validation for selectLinks (#2510)

Follow-up to #2152 

Related to #2487

This PR provides very basic validation of the `config.selectLinks`
argument on workflow creation and update. Namely, it checks that:
- `config.selectLinks` is not an empty array
- Each entry consists of two non-empty text sequences separated by `->`

At this point we're not validating the actual CSS selector on the
backend, though we could add that down the road.

Tests have been added accordingly.

Co-authored-by: Ilya Kreymer <[email protected]>

Author: tw4l

backend/btrixcloud/crawlconfigs.py

@@ -233,6 +233,8 @@ async def add_crawl_config(
                 exclude = [exclude]
             validate_regexes(exclude)
 
+        self._validate_link_selectors(config_in.config.selectLinks)
+
         if config_in.config.customBehaviors:
             for url in config_in.config.customBehaviors:
                 self._validate_custom_behavior_url_syntax(url)
@@ -297,6 +299,24 @@ async def add_crawl_config(
             execMinutesQuotaReached=exec_mins_quota_reached,
         )
 
+    def _validate_link_selectors(self, link_selectors: List[str]):
+        """Validate link selectors
+
+        Ensure at least one link selector is set and that all the link slectors passed
+        follow expected syntax: selector->attribute/property.
+
+        We don't yet check the validity of the CSS selector itself.
+        """
+        if not link_selectors:
+            raise HTTPException(status_code=400, detail="invalid_link_selector")
+
+        for link_selector in link_selectors:
+            parts = link_selector.split("->")
+            if not len(parts) == 2:
+                raise HTTPException(status_code=400, detail="invalid_link_selector")
+            if not parts[0] or not parts[1]:
+                raise HTTPException(status_code=400, detail="invalid_link_selector")
+
     def _validate_custom_behavior_url_syntax(self, url: str) -> Tuple[bool, List[str]]:
         """Validate custom behaviors are valid URLs after removing custom git syntax"""
         git_prefix = "git+"
@@ -379,6 +399,9 @@ async def update_crawl_config(
                 exclude = [exclude]
             validate_regexes(exclude)
 
+        if update.config and update.config.selectLinks is not None:
+            self._validate_link_selectors(update.config.selectLinks)
+
         if update.config and update.config.customBehaviors:
             for url in update.config.customBehaviors:
                 self._validate_custom_behavior_url_syntax(url)

backend/test/test_crawlconfigs.py

@@ -172,6 +172,24 @@ def test_update_config_invalid_exclude_regex(
     assert r.status_code == 400
     assert r.json()["detail"] == "invalid_regex"
 
+def test_update_config_invalid_link_selector(
+    crawler_auth_headers, default_org_id, sample_crawl_data
+):
+    r = requests.patch(
+        f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/{cid}/",
+        headers=crawler_auth_headers,
+        json={"config": {"selectLinks": []}},
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"] == "invalid_link_selector"
+
+    r = requests.patch(
+        f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/{cid}/",
+        headers=crawler_auth_headers,
+        json={"config": {"selectLinks": ["a[href]->href", "->href"]}},
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"] == "invalid_link_selector"
 
 def test_verify_default_select_links(
     crawler_auth_headers, default_org_id, sample_crawl_data
@@ -545,6 +563,28 @@ def test_add_crawl_config_invalid_exclude_regex(
     assert r.json()["detail"] == "invalid_regex"
 
 
+def test_add_crawl_config_invalid_link_selectors(
+    crawler_auth_headers, default_org_id, sample_crawl_data
+):
+    sample_crawl_data["config"]["selectLinks"] = []
+    r = requests.post(
+        f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/",
+        headers=crawler_auth_headers,
+        json=sample_crawl_data,
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"] == "invalid_link_selector"
+
+    sample_crawl_data["config"]["selectLinks"] = ["a[href]->href", "->href"]
+    r = requests.post(
+        f"{API_PREFIX}/orgs/{default_org_id}/crawlconfigs/",
+        headers=crawler_auth_headers,
+        json=sample_crawl_data,
+    )
+    assert r.status_code == 400
+    assert r.json()["detail"] == "invalid_link_selector"
+
+
 def test_add_crawl_config_custom_behaviors_invalid_url(
     crawler_auth_headers, default_org_id, sample_crawl_data
 ):

frontend/src/features/crawl-workflows/custom-behaviors-table-row.ts

@@ -77,7 +77,7 @@ const errorFor: Record<ValidationErrorCode, string> = {
 };
 
 const inputStyle = [
-  tw`[--sl-input-background-color-hover:transparent] [--sl-input-background-color:transparent] [--sl-input-border-color-hover:transparent] [--sl-input-border-radius-medium:0] [--sl-input-spacing-medium:var(--sl-spacing-small)]`,
+  tw`[--sl-input-border-radius-medium:0] [--sl-input-spacing-medium:var(--sl-spacing-small)] [--sl-input-background-color-hover:transparent] [--sl-input-background-color:transparent] [--sl-input-border-color-hover:transparent]`,
   tw`data-[valid]:[--sl-input-border-color:transparent]`,
   tw`part-[form-control-help-text]:mx-1 part-[form-control-help-text]:mb-1`,
 ];