feat: add magic-pdf-dev case

.github/workflows/cli.yml

@@ -37,7 +37,8 @@ jobs:
       run: |
         echo $GITHUB_WORKSPACE && sh tests/retry_env.sh
     - name: unit test
-      run: |        
+      run: | 
+        cd $GITHUB_WORKSPACE && python tests/clean_coverage.py
         cd $GITHUB_WORKSPACE && export PYTHONPATH=. && coverage run -m  pytest  tests/test_unit.py --cov=magic_pdf/ --cov-report term-missing --cov-report html
         cd $GITHUB_WORKSPACE && python tests/get_coverage.py
     - name: cli test

tests/clean_covrage.py

+"""
+clean coverage
+"""
+import os
+import shutil
+
+def delete_file(path):
+    """delete file."""
+    if not os.path.exists(path):
+        if os.path.isfile(path):
+            try:
+                os.remove(path)
+                print(f"File '{path}' deleted.")
+            except TypeError as e:
+                print(f"Error deleting file '{path}': {e}")
+    elif os.path.isdir(path):
+        try:
+            shutil.rmtree(path)
+            print(f"Directory '{path}' and its contents deleted.")
+        except TypeError as e:
+            print(f"Error deleting directory '{path}': {e}")
+
+if __name__ == "__main__":
+    delete_file("htmlcov")
\ No newline at end of file

tests/get_coverage.py

@@ -2,7 +2,7 @@
 get cov
 """
 from bs4 import BeautifulSoup
-
+import shutil
 def get_covrage():
     """get covrage"""
     # 发送请求获取网页内容

tests/test_cli/test_cli_sdk.py

@@ -182,7 +182,7 @@ class TestCli:
     def test_pdf_dev_cli_local_jsonl_txt(self):
         """magic_pdf_dev cli local txt."""
         jsonl_path = os.path.join(pdf_dev_path, 'line1.jsonl')
-        cmd = 'magic-pdf-dev --jsonl %s -m %s' % (jsonl_path, "txt")
+        cmd = 'magic-pdf-dev --jsonl %s --method %s' % (jsonl_path, "txt")
         logging.info(cmd)
         os.system(cmd)
 
@@ -191,7 +191,7 @@ class TestCli:
     def test_pdf_dev_cli_local_jsonl_ocr(self):
         """magic_pdf_dev cli local ocr."""
         jsonl_path = os.path.join(pdf_dev_path, 'line1.jsonl')
-        cmd = 'magic-pdf-dev --jsonl %s -m %s' % (jsonl_path, 'ocr')
+        cmd = 'magic-pdf-dev --jsonl %s --method %s' % (jsonl_path, 'ocr')
         logging.info(cmd)
         os.system(cmd)
 
@@ -199,7 +199,7 @@ class TestCli:
     def test_pdf_dev_cli_local_jsonl_auto(self):
         """magic_pdf_dev cli local auto."""
         jsonl_path = os.path.join(pdf_dev_path, 'line1.jsonl')
-        cmd = 'magic-pdf-dev --jsonl %s -m %s' % (jsonl_path, 'auto')
+        cmd = 'magic-pdf-dev --jsonl %s --method %s' % (jsonl_path, 'auto')
         logging.info(cmd)
         os.system(cmd)
 
@@ -207,7 +207,7 @@ class TestCli:
     def test_pdf_dev_cli_s3_jsonl_txt(self):
         """magic_pdf_dev cli s3 txt."""
         jsonl_path = os.path.join(pdf_dev_path, 'line1.jsonl')
-        cmd = 'magic-pdf-dev --jsonl %s -m %s' % (jsonl_path, "txt")
+        cmd = 'magic-pdf-dev --jsonl %s --method %s' % (jsonl_path, "txt")
         logging.info(cmd)
         os.system(cmd)
 
@@ -216,7 +216,7 @@ class TestCli:
     def test_pdf_dev_cli_s3_jsonl_ocr(self):
         """magic_pdf_dev cli s3 ocr."""
         jsonl_path = os.path.join(pdf_dev_path, 'line1.jsonl')
-        cmd = 'magic-pdf-dev --jsonl %s -m %s' % (jsonl_path, 'ocr')
+        cmd = 'magic-pdf-dev --jsonl %s --method %s' % (jsonl_path, 'ocr')
         logging.info(cmd)
         os.system(cmd)
 
@@ -229,5 +229,26 @@ class TestCli:
         os.system(cmd)
 
 
+    @pytest.mark.P1
+    def test_pdf_dev_cli_pdf_json_auto(self):
+        """magic_pdf_dev cli pdf+json auto."""
+        json_path = os.path.join(pdf_dev_path, 'test_model.json')
+        pdf_path = os.path.join(pdf_dev_path, 'pdf', 'research_report_1f978cd81fb7260c8f7644039ec2c054.pdf')
+        cmd = 'magic-pdf-dev --pdf %s --json %s --method %s' % (pdf_path, json_path, 'auto')
+        logging.info(cmd)
+        os.system(cmd)
+    
+    @pytest.mark.P1
+    def test_pdf_dev_cli_pdf_json_ocr(self):
+        """magic_pdf_dev cli pdf+json ocr."""
+        json_path = os.path.join(pdf_dev_path, 'test_model.json')
+        pdf_path = os.path.join(pdf_dev_path, 'pdf', 'research_report_1f978cd81fb7260c8f7644039ec2c054.pdf')
+        cmd = 'magic-pdf-dev --pdf %s --json %s --method %s' % (pdf_path, json_path, 'auto')
+        logging.info(cmd)
+        os.system(cmd)
+
+
+
+
 if __name__ == '__main__':
     pytest.main()