From 60f431e3657c8c760dd24353f9408e6af0bd8a58 Mon Sep 17 00:00:00 2001
From: thodson-usgs <thodson@usgs.gov>
Date: Wed, 27 May 2026 17:38:00 -0500
Subject: [PATCH] perf(waterdata): emit compact CQL2 JSON to halve POST chunk
 count

monitoring-locations is the one service that POSTs a CQL2 body (it doesn't
support comma-separated multi-value GET). The body was pretty-printed via
json.dumps(indent=4), ~39 B/value, so it counted ~2x against both the
server's ~8 KB request-size cap and the chunk planner's byte budget. The
tightest separators (~17 B/value) roughly double how many ids fit per
sub-request, halving the chunk count and API requests for large id lists:

  n_ids   indent=4   compact
    500       4          2
   1000       8          4
   5000      32         16

Live check: a 500-id query returns all 500 rows in 2 sub-requests (was 4).
The WAF body limit (403) is empirically ~8.2-8.4 KB, so 8000-byte compact
bodies stay safely under it. Locked in with a compactness assertion on the
monitoring-locations POST test.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 dataretrieval/waterdata/utils.py | 14 ++++++++++++--
 tests/waterdata_test.py          |  7 +++++++
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/dataretrieval/waterdata/utils.py b/dataretrieval/waterdata/utils.py
index 9a2be2c4..475998ca 100644
--- a/dataretrieval/waterdata/utils.py
+++ b/dataretrieval/waterdata/utils.py
@@ -321,7 +321,17 @@ def _cql2_param(args: dict[str, Any]) -> str:
     Returns
     -------
     str
-        JSON string representation of the CQL2 query.
+        Compact JSON string representation of the CQL2 query.
+
+    Notes
+    -----
+    Serialized with the tightest separators (no indentation or
+    whitespace). The body counts against the server's ~8 KB request-size
+    limit and against :func:`chunking._request_bytes` when planning
+    chunks, so every saved byte fits more values per POST: compact
+    encoding roughly halves the per-value cost versus pretty-printing,
+    which roughly doubles how many monitoring-location ids fit in one
+    sub-request and so halves the chunk count for large id lists.
     """
     filters = []
     for key, values in args.items():
@@ -329,7 +339,7 @@ def _cql2_param(args: dict[str, Any]) -> str:
 
     query = {"op": "and", "args": filters}
 
-    return json.dumps(query, indent=4)
+    return json.dumps(query, separators=(",", ":"))
 
 
 def _default_headers():
diff --git a/tests/waterdata_test.py b/tests/waterdata_test.py
index 9e0d4c70..c3836534 100644
--- a/tests/waterdata_test.py
+++ b/tests/waterdata_test.py
@@ -158,6 +158,13 @@ def test_construct_api_requests_monitoring_locations_post():
     assert req.method == "POST"
     assert req.headers["Content-Type"] == "application/query-cql-json"
 
+    # Body is serialized compactly (tight separators, no whitespace): the
+    # body counts against the server's ~8 KB request-size cap and the
+    # chunk planner's byte budget, so pretty-printing would needlessly
+    # halve how many ids fit per sub-request and double the chunk count.
+    raw = req.content.decode()
+    assert "\n" not in raw and ", " not in raw and ": " not in raw
+
     body = json.loads(req.content)
     # Top-level shape: AND over a list of per-param predicates.
     assert body["op"] == "and"