RUBY-3357 Add static analysis

.github/workflows/codeql.yml

@@ -0,0 +1,77 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ "master" ]
+  pull_request:
+    branches: [ "master" ]
+  schedule:
+    - cron: '20 0 * * 0'
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: 'ubuntu-latest'
+    timeout-minutes: 360
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+        - language: ruby
+          build-mode: none
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v3
+      with:
+        languages: ${{ matrix.language }}
+        build-mode: ${{ matrix.build-mode }}
+        config: |
+          paths-ignore:
+            - .evergreen
+            - spec
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+    # If the analyze step fails for one of the languages you are analyzing with
+    # "We were unable to automatically build your code", modify the matrix above
+    # to set the build mode to "manual" for that language. Then modify this step
+    # to build your code.
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+    - if: matrix.build-mode == 'manual'
+      run: |
+        echo 'If you are using a "manual" build mode for one or more of the' \
+          'languages you are analyzing, replace this with the commands to build' \
+          'your code, for example:'
+        echo '  make bootstrap'
+        echo '  make release'
+        exit 1
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3
+      with:
+        category: "/language:${{matrix.language}}"

lib/mongo/socket/ssl.rb

@@ -287,7 +287,7 @@ def set_cert(context, options)
         # for instance, if there is no newline between two certificates
         # this code will extract them both but OpenSSL fails in this situation.
         if cert_text
-          certs = cert_text.scan(/-----BEGIN CERTIFICATE-----(?:.|\n)+?-----END CERTIFICATE-----/)
+          certs = extract_certs(cert_text)
           if certs.length > 1
             context.cert = OpenSSL::X509::Certificate.new(certs.shift)
             context.extra_chain_cert = certs.map do |cert|
@@ -390,6 +390,27 @@ def run_tls_context_hooks
           hook.call(@context)
         end
       end
+
+      BEGIN_CERT = "-----BEGIN CERTIFICATE-----"
+      END_CERT = "-----END CERTIFICATE-----"
+
+      # This was originally a scan + regex, but the regex was particularly
+      # inefficient and was flagged as a concern by static analysis.
+      def extract_certs(text)
+        [].tap do |list|
+          pos = 0
+
+          while (begin_idx = text.index(BEGIN_CERT, pos))
+            end_idx = text.index(END_CERT, begin_idx)
+            break unless end_idx
+
+            end_idx += END_CERT.length
+            list.push(text[begin_idx...end_idx])
+
+            pos = end_idx
+          end
+        end
+      end
     end
   end
 end