From 83c92d1a375b70ab74d4597cfa01636f491275f1 Mon Sep 17 00:00:00 2001
From: Nathan TeBlunthuis <nathanteblunthuis@gmail.com>
Date: Tue, 22 Jul 2025 13:29:01 -0700
Subject: [PATCH] decrease moved paragraph detection cutoff to see if that
 fixes memory issue.

---
 src/wikiq/__init__.py | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/src/wikiq/__init__.py b/src/wikiq/__init__.py
index 5047658..9dcc64b 100755
--- a/src/wikiq/__init__.py
+++ b/src/wikiq/__init__.py
@@ -489,6 +489,12 @@ class WikiqParser:
 
                         persist_state = persistence.State()
 
+
+            if self.diff:
+                differ = pywikidiff2.pywikidiff2(
+                    numContextLines=1000000, moved_paragraph_detection_cutoff=2000
+                )
+
             while not on_last_batch:
                 # first loop: next_batch <- batch;
                 # second loop: next_batch <- batch; evaluate next_batch.
@@ -649,11 +655,6 @@ class WikiqParser:
                     last_text = last_rev_text
                     new_diffs = []
                     for text in row_buffer["text"]:
-
-                        differ = pywikidiff2.pywikidiff2(
-                            numContextLines=1000000, moved_paragraph_detection_cutoff=200000
-                        )
-
                         new_diffs.append(differ.inline_json_diff(last_text, text))
                         last_text = text
                     row_buffer["diff"] = [