Initial setup (#1)

prepare initial version

Co-authored-by: Dinakar <26552821+dinakar29@users.noreply.github.com>
Co-authored-by: KlaudiaBB <51341892+KlaudiaBB@users.noreply.github.com>

.github/workflows/CODEOWNERS

@@ -0,0 +1 @@
+*   @insightsengineering/idr

.github/workflows/ISSUE_TEMPLATE.md

@@ -0,0 +1 @@
+<!-- Hello! Please describe your issue -->

.github/workflows/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1 @@
+<!-- Thank you for your contribution! Please describe your PR -->

.github/workflows/linter.yaml

@@ -0,0 +1,31 @@
+---
+name: SuperLinter
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+
+jobs:
+  lint:
+    name: Lint Code Base
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+
+      - name: Lint Code Base
+        uses: github/super-linter/slim@v4
+        env:
+          VALIDATE_ALL_CODEBASE: false
+          DEFAULT_BRANCH: main
+          VALIDATE_R: true
+          VALIDATE_YAML: true
+          VALIDATE_BASH_EXEC: true
+          VALIDATE_DOCKERFILE_HADOLINT: true
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/test-action.yaml

@@ -0,0 +1,100 @@
+---
+name: Test 🧪
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test-action:
+    runs-on: ubuntu-latest
+    name: Test action 🎬
+    strategy:
+      fail-fast: false
+      matrix:
+        reports:
+          - path: "nothing.txt"
+            configuration-file: "default"
+            configuration-data: ""
+            output: "auto"
+            lang-models: ""
+          - path: "fake_no.txt"
+            configuration-file: "default"
+            configuration-data: ""
+            output: "auto"
+            lang-models: ""
+          - path: "3_types.txt"
+            configuration-file: "default"
+            configuration-data: ""
+            output: "auto"
+            lang-models: ""
+          - path: "nothing.txt"
+            configuration-file: "limited"
+            configuration-data: ""
+            output: "auto"
+            lang-models: ""
+          - path: "fake_no.txt"
+            configuration-file: "limited"
+            configuration-data: ""
+            output: "auto"
+            lang-models: ""
+          - path: "3_types.txt"
+            configuration-file: "limited"
+            configuration-data: ""
+            output: "standard"
+            lang-models: ""
+          - path: "3_types.txt"
+            configuration-file: "limited"
+            configuration-data: ""
+            output: "github"
+            lang-models: ""
+          - path: "3_types.txt"
+            configuration-file: "limited"
+            configuration-data: ""
+            output: "colored"
+            lang-models: ""
+          - path: "3_types.txt"
+            configuration-file: "limited"
+            configuration-data: ""
+            output: "parsable"
+            lang-models: ""
+          - path: "3_types.txt"
+            configuration-file: "ignored-use-data-content"
+            configuration-data: |2
+              entities:
+                - PERSON
+            output: "auto"
+            lang-models: ""
+          - path: "."
+            configuration-file: "limited"
+            configuration-data: ""
+            output: "github"
+            lang-models: ""
+          - path: "fake_no.txt"
+            configuration-file: "none"
+            configuration-data: |2
+              language: en
+              entities:
+                - CREDIT_CARD
+                - PERSON
+            output: "parsable"
+            lang-models: |
+              pl_core_news_sm
+              pl_core_news_lg
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v2
+
+      - name: Run test on ${{ matrix.reports.path }} 🏃‍♀️
+        uses: ./
+        with:
+          path: ./fixtures/${{ matrix.reports.path }}
+          configuration-file: ${{ matrix.reports.configuration-file }}
+          configuration-data: ${{ matrix.reports.configuration-data }}
+          output: ${{ matrix.reports.output }}
+          lang-models: ${{ matrix.reports.lang-models }}

.gitignore

@@ -0,0 +1,2 @@
+
+.presidio-output.txt

README.md

@@ -1,2 +1,162 @@
-# presidio-action
+# Presidio Action
+
 Github Actions that analyze Text for PII Entities with Microsoft Presidio framework.
+
+## Author
+
+Insights Engineering
+
+## Inputs
+
+* `path`:
+
+    _Description_: Path to verify
+
+    _Required_: `false`
+
+    _Default_: "."
+
+* `configuration-file`:
+
+    _Description_: Path to configuration file or predefined configuration (default, limited)
+
+    _Required_: `false`
+
+    _Default_: "default"
+
+* `configuration-data`:
+
+    _Description_: Simple configuration data directly in yaml format
+
+    _Required_: `false`
+
+    _Default_: ""
+
+* `output`:
+
+    _Description_: Format of an output
+
+    _Required_: `false`
+
+    _Default_: "auto"
+
+* `publish`:
+
+    _Description_: Publish result in PR comment
+
+    _Required_: `false`
+
+    _Default_: "true"
+
+* `upload`:
+
+    _Description_: Upload result as an artifact
+
+    _Required_: `false`
+
+    _Default_: "true"
+
+* `presidio-cli-version`:
+
+    _Description_: Presidio cli version - a version of presidio-cli used in action.
+
+    _Required_: `false`
+
+    _Default_: "1.0.0"
+
+## Outputs
+
+An output depends on the `output` parameter:
+
+The default format is `auto`.
+
+Available formats:
+
+* standard - standard output format
+
+```shell
+tests/conftest.py
+  34:58     0.85     PERSON
+  37:33     0.85     PERSON
+```
+
+* github - similar to diff function in github
+
+```shell
+::group::tests/conftest.py
+::0.85 file=tests/conftest.py,line=34,col=58::34:58 [PERSON] 
+::0.85 file=tests/conftest.py,line=37,col=33::37:33 [PERSON] 
+::endgroup::
+```
+
+* colored - standard output format but with colors
+
+* parsable - easy to parse automaticaly
+
+```shell
+{"entity_type": "PERSON", "start": 57, "end": 62, "score": 0.85, "analysis_explanation": null}
+{"entity_type": "PERSON", "start": 32, "end": 37, "score": 0.85, "analysis_explanation": null}
+```
+
+* auto - default format, switches automatically between those 2 modes:
+  * github, if run on github - environment variables `GITHUB_ACTIONS` and `GITHUB_WORKFLOW` are set
+  * colored, otherwise
+
+## How it works
+
+Presidio action uses [presidio-cli](https://pypi.org/project/presidio-cli/)
+based on presidio-analyzer from [Microsoft Presidio framework](https://github.com/microsoft/presidio)
+to check code against undesirable types of data such as 'EMAIL_ADDRESS' or 'PHONE_NUMBER' inside application's code.
+
+For more information please see a full [list of supported entities](https://microsoft.github.io/presidio/supported_entities/).
+
+## Usage
+
+Example usage:
+
+```yaml
+---
+name: Presidio check
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  presidio-action:
+    runs-on: ubuntu-latest
+    name: Presidio check
+
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v2
+
+      - name: Produce the presidio report
+        uses: insightsengineering/presidio-action@v1
+        # all parameters below are optional
+        with:
+          # path to project.
+          # if project does not have a specific 'my-project' path,
+          # '.' - current folder is a default value
+          path: "my-project"
+          # configuration-file - path to file with specific configuration
+          # or use one of predefined files: 
+          #   - default - `conf/default.yaml` file from action, check default list of entities
+          #                and ignore content of `.git` folder
+          #   - limited - `conf/limited.yaml` file from action, check only PERSON, EMAIL_ADDRESS and CREDIT_CARD
+          #                and ignore `.git` folder and *.cfg files
+          configuration-file: "my-project/conf/my-presidio-config.yaml"
+          # configuration-data - content of configuration in raw yaml format.
+          # Give possibility to prepare own configuration without adding file to project
+          # any value in this field will block usage of configuration file
+          configuration-data: |
+            entities:
+              - PERSON
+          # output - specify one of output formats
+          output: "parsable"
+
+```