From df1ba399056f6a598f111a8206f15a44c7196bf9 Mon Sep 17 00:00:00 2001
From: Yuming Long <63475068+yuming-long@users.noreply.github.com>
Date: Wed, 26 Jul 2023 16:55:35 -0400
Subject: [PATCH] Chore: add uns api repo unittests (#954)

* stage

* git clone

* ci ignore markdown file

* make install

* use env instead

* remove md

* add script

* wrong env value

* add note

* maybe don't rm

* no cd../

---------

Co-authored-by: cragwolfe <crag@unstructured.io>
---
 .github/workflows/ci.yml              | 47 +++++++++++++++++++++++++++
 CHANGELOG.md                          |  3 +-
 Makefile                              |  4 +++
 scripts/test-unstructured-api-unit.sh | 39 ++++++++++++++++++++++
 unstructured/__version__.py           |  2 +-
 5 files changed, 93 insertions(+), 2 deletions(-)
 create mode 100755 scripts/test-unstructured-api-unit.sh

diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 1cda04b60..22e410e12 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -220,6 +220,53 @@ jobs:
         make install-ingest-wikipedia
         ./test_unstructured_ingest/test-ingest.sh
 
+  test_unstructured_api_unit:
+    strategy:
+      matrix:
+        # NOTE(yuming): Unstructured API only use Python 3.8
+        python-version: ["3.8"]
+    runs-on: ubuntu-latest
+    env:
+      NLTK_DATA: ${{ github.workspace }}/nltk_data
+    needs: [setup, lint]
+    steps:
+    - uses: actions/checkout@v3
+    - uses: actions/cache/restore@v3
+      id: virtualenv-cache
+      with:
+        path: |
+          .venv
+          nltk_data
+        key: unstructured-${{ runner.os }}-${{ matrix.python-version }}-${{ env.GHA_CACHE_KEY_VERSION }}-${{ hashFiles('requirements/*.txt') }}
+    - name: Set up flag for running Unstructured API unit tests
+      run: |
+        # NOTE: Change env `SKIP_API_UNIT_FOR_BREAKING_CHANGE` to true if there is a breaking change in Unstructured repo that will break unstructured api unit tests
+        # TODO: Change env back to false once API unit tests is in sync with unstructured repo
+        echo "SKIP_API_UNIT_FOR_BREAKING_CHANGE=true" >> $GITHUB_ENV
+    - name: Set up Python ${{ matrix.python-version }}
+      if: env.SKIP_API_UNIT_FOR_BREAKING_CHANGE == 'false'
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Setup virtual environment (no cache hit)
+      if: steps.virtualenv-cache.outputs.cache-hit != 'true' &&  env.SKIP_API_UNIT_FOR_BREAKING_CHANGE == 'false'
+      run: |
+        python${{ matrix.python-version}} -m venv .venv
+        source .venv/bin/activate
+        mkdir "$NLTK_DATA"
+        make install-ci
+    - name: Test Unstructured API Unit
+      if: env.SKIP_API_UNIT_FOR_BREAKING_CHANGE == 'false'
+      run: |
+        source .venv/bin/activate
+        sudo apt-get update && sudo apt-get install --yes poppler-utils libreoffice
+        make install-pandoc
+        sudo add-apt-repository -y ppa:alex-p/tesseract-ocr5
+        sudo apt-get install -y tesseract-ocr tesseract-ocr-kor
+        tesseract --version
+        make install-nltk-models
+        make test-unstructured-api-unit
+
   changelog:
     runs-on: ubuntu-latest
     steps:
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 60921905d..8b90464c4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,7 +1,8 @@
-## 0.8.5-dev0
+## 0.8.5-dev1
 
 ### Enhancements
 
+* Adds optional Unstructured API unit tests in CI
 * Tracks last modified date for all document types.
 
 ### Features
diff --git a/Makefile b/Makefile
index a7cfb209f..097b9ccbc 100644
--- a/Makefile
+++ b/Makefile
@@ -177,6 +177,10 @@ export CI ?= false
 test:
 	PYTHONPATH=. CI=$(CI) pytest test_${PACKAGE_NAME} --cov=${PACKAGE_NAME} --cov-report term-missing
 
+.PHONY: test-unstructured-api-unit
+test-unstructured-api-unit:
+	scripts/test-unstructured-api-unit.sh
+
 ## check:                   runs linters (includes tests)
 .PHONY: check
 check: check-src check-tests check-version
diff --git a/scripts/test-unstructured-api-unit.sh b/scripts/test-unstructured-api-unit.sh
new file mode 100755
index 000000000..bf0718471
--- /dev/null
+++ b/scripts/test-unstructured-api-unit.sh
@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+cleanup() {
+    rm -rf unstructured-api
+}
+
+handle_error() {
+    cleanup
+    exit 1
+}
+
+# Remove the unstructured-api directory if it exists
+if [ -d "unstructured-api" ]; then
+    rm -rf unstructured-api
+fi
+
+# Clone the repository
+git clone https://github.com/Unstructured-IO/unstructured-api.git --depth 1
+
+# Install dependencies and project locally
+cd unstructured-api && make install && cd ../
+make install-project-local
+pip show unstructured | grep Version
+
+# Run tests and capture exit status
+(cd unstructured-api && make test)
+test_exit_status=$?
+
+# Check the exit status and handle errors
+if [ $test_exit_status -ne 0 ]; then
+    echo "Test failed, see the error message above."
+    handle_error
+fi
+
+cleanup
+
+echo "Test and cleanup completed successfully."
diff --git a/unstructured/__version__.py b/unstructured/__version__.py
index ac2543761..1b15eacd6 100644
--- a/unstructured/__version__.py
+++ b/unstructured/__version__.py
@@ -1 +1 @@
-__version__ = "0.8.5-dev0"  # pragma: no cover
+__version__ = "0.8.5-dev1"  # pragma: no cover