Merge branch 'main' into 558-implement-es-relevance-decay

freelawproject · Dec 30, 2024 · c1e2acd · c1e2acd
2 parents b40a747 + cb012e8
commit c1e2acd
Show file tree

Hide file tree

Showing 6 changed files with 38 additions and 3 deletions.
diff --git a/cl/lib/tests.py b/cl/lib/tests.py
@@ -1157,16 +1157,31 @@ def test_check_and_sanitize_queries_bad_syntax(self) -> None:
                 "output": True,
                 "sanitized": "This is unbalanced",
             },
+            {
+                "input_str": "This is “unbalanced",
+                "output": True,
+                "sanitized": "This is unbalanced",
+            },
             {
                 "input_str": 'This is "unbalanced""',
                 "output": True,
                 "sanitized": 'This is "unbalanced"',
             },
+            {
+                "input_str": "This is “unbalanced””",
+                "output": True,
+                "sanitized": 'This is "unbalanced"',
+            },
             {
                 "input_str": 'This "is" unbalanced"',
                 "output": True,
                 "sanitized": 'This "is" unbalanced',
             },
+            {
+                "input_str": 'This "is” unbalanced"',
+                "output": True,
+                "sanitized": 'This "is" unbalanced',
+            },
             {
                 "input_str": 'This "is" unbalanced"""',
                 "output": True,

diff --git a/cl/lib/utils.py b/cl/lib/utils.py
@@ -249,6 +249,8 @@ def cleanup_main_query(query_string: str) -> str:
     """
     inside_a_phrase = False
     cleaned_items = []
+    # Replace smart quotes with standard double quotes for consistency.
+    query_string = re.sub(r"[“”]", '"', query_string)
     for item in re.split(r'([^a-zA-Z0-9_\-^~":]+)', query_string):
         if not item:
             continue
@@ -330,8 +332,8 @@ def check_unbalanced_quotes(query: str) -> bool:
     :param query: The input query string
     :return: True if the query contains unbalanced quotes. Otherwise False
     """
-    quotes_count = query.count('"')
-    return quotes_count % 2 != 0
+    all_quotes = re.findall(r"[“”\"]", query)
+    return len(all_quotes) % 2 != 0
 
 
 def remove_last_symbol_occurrence(
@@ -382,6 +384,8 @@ def sanitize_unbalanced_quotes(query: str) -> str:
     :param query: The input query string
     :return: The sanitized query string, after removing unbalanced quotes.
     """
+    # Replace smart quotes with standard double quotes for consistency.
+    query = re.sub(r"[“”]", '"', query)
     quotes_count = query.count('"')
     while quotes_count % 2 != 0:
         query, quotes_count = remove_last_symbol_occurrence(

diff --git a/cl/opinion_page/templates/includes/authorities_list.html b/cl/opinion_page/templates/includes/authorities_list.html
@@ -3,7 +3,14 @@
 <ul>
   {% for authority in authorities %}
   <li>
-    {{ authority.depth }} reference{{ authority.depth|pluralize }} to
+    {% if docket %}
+    <a href="/?type=r&q=docket_id%3A{{ docket.pk }}%20AND%20cites%3A({{ authority.cited_opinion.cluster.sub_opinions.all|OR_join }})">
+    {% endif %}
+      {{ authority.depth }} reference{{ authority.depth|pluralize }}
+    {% if docket %}
+    </a>
+    {% endif %}
+    to
     <a href="{{ authority.cited_opinion.cluster.get_absolute_url }}{% querystring %}" {% if authority.blocked %}rel="nofollow" {% endif %}>
       {{ authority.cited_opinion.cluster.caption|safe|v_wrapper }}
     </a>

diff --git a/cl/scrapers/management/commands/clone_from_cl.py b/cl/scrapers/management/commands/clone_from_cl.py
@@ -37,6 +37,11 @@
 manage.py clone_from_cl --type people_db.Person --id 4173 --clone-person-positions
 manage.py clone_from_cl --type search.Docket --id 5377675 --clone-person-positions
 
+Note: for cloned Opinion Clusters to appear in docket authorities pages, use the
+`find_citations_and_parantheticals_for_recap_documents` method in the Django shell.
+You can pass all RECAPDocument IDs, for example:
+`RECAPDocument.objects.values_list('pk', flat=True)`, or only a subset if needed.
+
 This is still work in progress, some data is not cloned yet.
 """
 

diff --git a/cl/search/tests/tests.py b/cl/search/tests/tests.py
@@ -940,6 +940,8 @@ def test_query_cleanup_function(self) -> None:
                 "12-9238 happy Gilmore",
                 'docketNumber:"12-9238"~1 happy Gilmore',
             ),
+            ("“ping tree” leads", '"ping tree" leads'),
+            ('"this is” a “test"', '"this is" a "test"'),
             ("1chicken NUGGET", '"1chicken" NUGGET'),
             (
                 "We can drive her home with 1headlight",

diff --git a/cl/settings/third_party/rest_framework.py b/cl/settings/third_party/rest_framework.py
@@ -29,6 +29,8 @@
     "OVERRIDE_THROTTLE_RATES": {
         # Throttling down.
         # Multiple accounts
+        "api_1": "1/hour",
+        "api_2": "1/hour",
         "api_account_1": "1/hour",
         "api_account_2": "1/hour",
         "api_account_3": "1/hour",