9.1.2

- Fix duplicate detection for normalized aggregate reports in Elasticsearch/OpenSearch (PR #666 fixes issue #665)
Fix duplicate detection for normalized aggregate reports in Elasticsearch/OpenSearch (#666 )
2026-03-07 07:11:24 +00:00 · 2026-03-06 13:41:33 -05:00 · 2026-03-06 13:21:54 -05:00
4 changed files with 11 additions and 5 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,11 @@
 # Changelog

+## 9.1.2
+
+### Fixes
+
+- Fix duplicate detection for normalized aggregate reports in Elasticsearch/OpenSearch (PR #666 fixes issue #665)
+
 ## 9.1.1

 ### Fixes
--- a/parsedmarc/constants.py
+++ b/parsedmarc/constants.py
@@ -1,3 +1,3 @@
-__version__ = "9.1.1"
+__version__ = "9.1.2"

 USER_AGENT = f"parsedmarc/{__version__}"
--- a/parsedmarc/elastic.py
+++ b/parsedmarc/elastic.py
@@ -413,8 +413,8 @@ def save_aggregate_report_to_elasticsearch(
    org_name_query = Q(dict(match_phrase=dict(org_name=org_name)))  # type: ignore
    report_id_query = Q(dict(match_phrase=dict(report_id=report_id)))  # pyright: ignore[reportArgumentType]
    domain_query = Q(dict(match_phrase={"published_policy.domain": domain}))  # pyright: ignore[reportArgumentType]
-    begin_date_query = Q(dict(match=dict(date_begin=begin_date)))  # pyright: ignore[reportArgumentType]
-    end_date_query = Q(dict(match=dict(date_end=end_date)))  # pyright: ignore[reportArgumentType]
+    begin_date_query = Q(dict(range=dict(date_begin=dict(gte=begin_date))))  # pyright: ignore[reportArgumentType]
+    end_date_query = Q(dict(range=dict(date_end=dict(lte=end_date))))  # pyright: ignore[reportArgumentType]

    if index_suffix is not None:
        search_index = "dmarc_aggregate_{0}*".format(index_suffix)
--- a/parsedmarc/opensearch.py
+++ b/parsedmarc/opensearch.py
@@ -413,8 +413,8 @@ def save_aggregate_report_to_opensearch(
    org_name_query = Q(dict(match_phrase=dict(org_name=org_name)))
    report_id_query = Q(dict(match_phrase=dict(report_id=report_id)))
    domain_query = Q(dict(match_phrase={"published_policy.domain": domain}))
-    begin_date_query = Q(dict(match=dict(date_begin=begin_date)))
-    end_date_query = Q(dict(match=dict(date_end=end_date)))
+    begin_date_query = Q(dict(range=dict(date_begin=dict(gte=begin_date))))
+    end_date_query = Q(dict(range=dict(date_end=dict(lte=end_date))))

    if index_suffix is not None:
        search_index = "dmarc_aggregate_{0}*".format(index_suffix)