diff --git a/lib/linguist/repository.rb b/lib/linguist/repository.rb
index 39eead6a34..6ef697f07b 100644
--- a/lib/linguist/repository.rb
+++ b/lib/linguist/repository.rb
@@ -10,10 +10,12 @@ module Linguist
   class Repository
     attr_reader :repository
 
+    MAX_TREE_SIZE = 100_000
+
     # Public: Create a new Repository based on the stats of
     # an existing one
-    def self.incremental(repo, commit_oid, old_commit_oid, old_stats)
-      repo = self.new(repo, commit_oid)
+    def self.incremental(repo, commit_oid, old_commit_oid, old_stats, max_tree_size = MAX_TREE_SIZE)
+      repo = self.new(repo, commit_oid, max_tree_size)
       repo.load_existing_stats(old_commit_oid, old_stats)
       repo
     end
@@ -24,11 +26,13 @@ def self.incremental(repo, commit_oid, old_commit_oid, old_stats)
     # repo - a Rugged::Repository object
     # commit_oid - the sha1 of the commit that will be analyzed;
     #              this is usually the master branch
+    # max_tree_size - the maximum tree size to consider for analysis (default: MAX_TREE_SIZE)
     #
     # Returns a Repository
-    def initialize(repo, commit_oid)
+    def initialize(repo, commit_oid, max_tree_size = MAX_TREE_SIZE)
       @repository = repo
       @commit_oid = commit_oid
+      @max_tree_size = max_tree_size
 
       @old_commit_oid = nil
       @old_stats = nil
@@ -129,10 +133,8 @@ def current_tree
     end
 
     protected
-    MAX_TREE_SIZE = 100_000
-
     def compute_stats(old_commit_oid, cache = nil)
-      return {} if current_tree.count_recursive(MAX_TREE_SIZE) >= MAX_TREE_SIZE
+      return {} if current_tree.count_recursive(@max_tree_size) >= @max_tree_size
 
       old_tree = old_commit_oid && Rugged::Commit.lookup(repository, old_commit_oid).tree
       read_index
diff --git a/test/test_repository.rb b/test/test_repository.rb
index 9a6e503980..2dcfdfce01 100644
--- a/test/test_repository.rb
+++ b/test/test_repository.rb
@@ -87,8 +87,8 @@ def test_commit_with_git_attributes_data
 
     # With some .gitattributes data
     attr_commit = '7ee006cbcb2d7261f9e648510a684ee9ac64126b'
-    # It's incremental but should bust the cache
-    new_repo = Linguist::Repository.incremental(rugged_repository, attr_commit, old_commit, old_repo.cache)
+    # It's incremental but now is scanning more data and should bust the cache
+    new_repo = Linguist::Repository.incremental(rugged_repository, attr_commit, old_commit, old_repo.cache, 350_000)
 
     assert new_repo.breakdown_by_file["Java"].include?("lib/linguist.rb")
   end