adding find algorithm (#1640)

* adding find

* add default value

README.md

@@ -300,6 +300,7 @@ But if you wish to select or exclude specific linters, we give you full control
 | **SSL_CERT_SECRET**                | `none`                          | SSL cert to add to the **Super-Linter** trust store. This is needed for users on `self-hosted` runners or need to inject the cert for security standards (ex. ${{ secrets.SSL_CERT }})                               |
 | **SQL_CONFIG_FILE**                | `.sql-config.json`              | Filename for [SQL-Lint configuration](https://sql-lint.readthedocs.io/en/latest/files/configuration.html) (ex: `sql-config.json` , `.config.json`)                                                                   |
 | **TYPESCRIPT_ES_CONFIG_FILE**      | `.eslintrc.yml`                 | Filename for [eslint configuration](https://eslint.org/docs/user-guide/configuring#configuration-file-formats) (ex: `.eslintrc.yml`, `.eslintrc.json`)                                                               |
+| **USE_FIND_ALGORITHM**             | `false`                         | By default, we use `git diff` to find all files in the workspace and what has been updated, this would enable the Linux `find` method instead to find all files to lint                                              |
 | **VALIDATE_ALL_CODEBASE**          | `true`                          | Will parse the entire repository and find all files to validate across all types. **NOTE:** When set to `false`, only **new** or **edited** files will be parsed for validation.                                     |
 | **VALIDATE_ANSIBLE**               | `true`                          | Flag to enable or disable the linting process of the Ansible language.                                                                                                                                               |
 | **VALIDATE_ARM**                   | `true`                          | Flag to enable or disable the linting process of the ARM language.                                                                                                                                                   |

lib/functions/buildFileList.sh

@@ -64,6 +64,8 @@ function BuildFileList() {
 
   debug "IGNORE_GITIGNORED_FILES: ${IGNORE_GITIGNORED_FILES}..."
 
+  debug "USE_FIND_ALGORITHM: ${USE_FIND_ALGORITHM}..."
+
   if [ "${VALIDATE_ALL_CODEBASE}" == "false" ] && [ "${TEST_CASE_RUN}" != "true" ]; then
     # Need to build a list of all files changed
     # This can be pulled from the GITHUB_EVENT_PATH payload
@@ -116,7 +118,6 @@ function BuildFileList() {
 
         DIFF_CMD="git -C ${GITHUB_WORKSPACE} diff --name-only ${DEFAULT_BRANCH}...${GITHUB_SHA} --diff-filter=d | xargs -I % sh -c 'echo \"${GITHUB_WORKSPACE}/%\"' 2>&1"
         GenerateFileDiff "$DIFF_CMD"
-
       fi
     else
       ################
@@ -131,6 +132,40 @@ function BuildFileList() {
       WORKSPACE_PATH="${GITHUB_WORKSPACE}/${TEST_CASE_FOLDER}"
     fi
 
+    #############################
+    # Use the find on all files #
+    #############################
+    if [ "${USE_FIND_ALGORITHM}" == 'true' ]; then
+      ################
+      # print header #
+      ################
+      debug "----------------------------------------------"
+      debug "Populating the file list with all the files in the ${WORKSPACE_PATH} workspace using FIND algorithm"
+      mapfile -t RAW_FILE_ARRAY < <(find "${WORKSPACE_PATH}" \
+        -not \( -path '*/\.git' -prune \) \
+        -not \( -path '*/\.pytest_cache' -prune \) \
+        -not \( -path '*/\.rbenv' -prune \) \
+        -not \( -path '*/\.terragrunt-cache' -prune \) \
+        -not \( -path '*/\.venv' -prune \) \
+        -not \( -path '*/\__pycache__' -prune \) \
+        -not \( -path '*/\node_modules' -prune \) \
+        -not -name ".DS_Store" \
+        -not -name "*.gif" \
+        -not -name "*.ico" \
+        -not -name "*.jpg" \
+        -not -name "*.jpeg" \
+        -not -name "*.pdf" \
+        -not -name "*.png" \
+        -not -name "*.webp" \
+        -not -name "*.woff" \
+        -not -name "*.woff2" \
+        -not -name "*.zip" \
+        -type f \
+        2>&1 | sort)
+    else
+      ##############################
+      # use the standard mechinism #
+      ##############################
       ################
       # print header #
       ################
@@ -139,6 +174,7 @@ function BuildFileList() {
       mapfile -t RAW_FILE_ARRAY < <(git -C "${WORKSPACE_PATH}" ls-tree -r --name-only HEAD | xargs -I % sh -c "echo ${WORKSPACE_PATH}/%" 2>&1)
       debug "RAW_FILE_ARRAY contents: ${RAW_FILE_ARRAY[*]}"
     fi
+  fi
 
   #######################
   # Load the error code #

lib/linter.sh

@@ -164,6 +164,8 @@ TYPESCRIPT_ES_FILE_NAME="${TYPESCRIPT_ES_CONFIG_FILE:-.eslintrc.yml}"
 # shellcheck disable=SC2034  # Variable is referenced indirectly
 TYPESCRIPT_STANDARD_FILE_NAME="${TYPESCRIPT_ES_CONFIG_FILE:-.eslintrc.yml}"
 # shellcheck disable=SC2034  # Variable is referenced indirectly
+USE_FIND_ALGORITHM="${USE_FIND_ALGORITHM:-false}"
+# shellcheck disable=SC2034  # Variable is referenced indirectly
 YAML_FILE_NAME="${YAML_CONFIG_FILE:-.yaml-lint.yml}"
 
 #################################################