Merge branch '27918-prefix-code-search' into 'master'

Remove partial word matching from code search

See merge request gitlab-org/gitlab!32771

doc/development/elasticsearch.md

@@ -54,7 +54,7 @@ Please see the `sha_tokenizer` explanation later below for an example.
 
 #### `code_analyzer`
 
-Used when indexing a blob's filename and content. Uses the `whitespace` tokenizer and the filters: [`code`](#code), [`edgeNGram_filter`](#edgengram_filter), `lowercase`, and `asciifolding`
+Used when indexing a blob's filename and content. Uses the `whitespace` tokenizer and the filters: [`code`](#code), `lowercase`, and `asciifolding`
 
 The `whitespace` tokenizer was selected in order to have more control over how tokens are split. For example the string `Foo::bar(4)` needs to generate tokens like `Foo` and `bar(4)` in order to be properly searched.
 

ee/changelogs/unreleased/27918-prefix-code-search.yml

+---
+title: Remove partial word matching from code search
+merge_request: 32771
+author:
+type: changed

ee/lib/elastic/latest/config.rb

@@ -35,7 +35,7 @@ module Elastic
               code_analyzer: {
                 type: 'custom',
                 tokenizer: 'whitespace',
-                filter: %w(code edgeNGram_filter lowercase asciifolding)
+                filter: %w(code lowercase asciifolding)
               },
               code_search_analyzer: {
                 type: 'custom',
@@ -60,11 +60,6 @@ module Elastic
                   '\.([^.]+)(?=\.|\s|\Z)', # separate terms on periods
                   '\/?([^\/]+)(?=\/|\b)' # separate path terms (like/this/one)
                 ]
-              },
-              edgeNGram_filter: {
-                type: 'edgeNGram',
-                min_gram: 2,
-                max_gram: 40
               }
             },
             tokenizer: {

ee/spec/lib/gitlab/elastic/search_results_spec.rb

@@ -537,7 +537,15 @@ describe Gitlab::Elastic::SearchResults, :elastic, :sidekiq_might_not_need_inlin
       blobs = results.objects('blobs')
 
       expect(blobs.first.data).to include('def')
-      expect(results.blobs_count).to eq 7
+      expect(results.blobs_count).to eq 5
+    end
+
+    it 'finds blobs by prefix search' do
+      results = described_class.new(user, 'defau*', limit_project_ids)
+      blobs = results.objects('blobs')
+
+      expect(blobs.first.data).to include('default')
+      expect(results.blobs_count).to eq 3
     end
 
     it 'finds blobs from public projects only' do
@@ -547,13 +555,13 @@ describe Gitlab::Elastic::SearchResults, :elastic, :sidekiq_might_not_need_inlin
       ensure_elasticsearch_index!
 
       results = described_class.new(user, 'def', [project_1.id])
-      expect(results.blobs_count).to eq 7
+      expect(results.blobs_count).to eq 5
       result_project_ids = results.objects('blobs').map(&:project_id)
       expect(result_project_ids.uniq).to eq([project_1.id])
 
       results = described_class.new(user, 'def', [project_1.id, project_2.id])
 
-      expect(results.blobs_count).to eq 14
+      expect(results.blobs_count).to eq 10
     end
 
     it 'returns zero when blobs are not found' do
@@ -580,7 +588,8 @@ describe Gitlab::Elastic::SearchResults, :elastic, :sidekiq_might_not_need_inlin
         expect(search_for('write')).to include('test.txt')
       end
 
-      it 'find by first two words' do
+      # Re-enable after fixing https://gitlab.com/gitlab-org/gitlab/-/issues/10693#note_349683299
+      xit 'find by first two words' do
         expect(search_for('writeString')).to include('test.txt')
       end
 
@@ -591,6 +600,10 @@ describe Gitlab::Elastic::SearchResults, :elastic, :sidekiq_might_not_need_inlin
       it 'find by exact match' do
         expect(search_for('writeStringToFile')).to include('test.txt')
       end
+
+      it 'find by prefix search' do
+        expect(search_for('writeStr*')).to include('test.txt')
+      end
     end
 
     context 'Searches special characters' do

ee/spec/requests/api/search_spec.rb

@@ -129,7 +129,7 @@ describe API::Search do
 
       context 'filters' do
         it 'by filename' do
-          get api("/projects/#{project.id}/search", user), params: { scope: 'blobs', search: 'mon filename:PROCESS.md' }
+          get api("/projects/#{project.id}/search", user), params: { scope: 'blobs', search: 'mon* filename:PROCESS.md' }
 
           expect(response).to have_gitlab_http_status(:ok)
           expect(json_response.size).to eq(1)
@@ -137,7 +137,7 @@ describe API::Search do
         end
 
         it 'by path' do
-          get api("/projects/#{project.id}/search", user), params: { scope: 'blobs', search: 'mon path:markdown' }
+          get api("/projects/#{project.id}/search", user), params: { scope: 'blobs', search: 'mon* path:markdown' }
 
           expect(response).to have_gitlab_http_status(:ok)
           expect(json_response.size).to eq(1)
@@ -147,7 +147,7 @@ describe API::Search do
         end
 
         it 'by extension' do
-          get api("/projects/#{project.id}/search", user), params: { scope: 'blobs', search: 'mon extension:md' }
+          get api("/projects/#{project.id}/search", user), params: { scope: 'blobs', search: 'mon* extension:md' }
 
           expect(response).to have_gitlab_http_status(:ok)
           expect(json_response.size).to eq(3)