Merge pull request #986 from dt-yy/dev

update ci

.github/workflows/cli.yml

@@ -3,13 +3,6 @@
 
 name: mineru
 on:
-  push:
-    branches:
-      - "master"
-      - "dev"
-    paths-ignore:
-      - "cmds/**"
-      - "**.md"
   pull_request:
     branches:
       - "master"

.github/workflows/daily.yml

@@ -23,6 +23,7 @@ jobs:
         source activate mineru
         conda env list
         pip show coverage
+        git checkout "dev"
         # cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
         cd $GITHUB_WORKSPACE && python tests/clean_coverage.py      
         cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/  --cov-report html --cov-report term-missing

.github/workflows/huigui.yml

@@ -10,7 +10,6 @@ on:
     paths-ignore:
       - "cmds/**"
       - "**.md"
-  workflow_dispatch:
 jobs:
   cli-test:
     if: github.repository == 'opendatalab/MinerU'

tests/retry_env.sh

@@ -8,6 +8,9 @@ while true; do
     #python -m pip install -r requirements-qa.txt
     python -m pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple
     python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+    pip install modelscope
+    wget https://gitee.com/myhloli/MinerU/raw/master/scripts/download_models.py -O download_models.py
+    python download_models.py
     exit_code=$?
     if [ $exit_code -eq 0 ]; then
         echo "test.sh 成功执行！"

tests/test_cli/conftest.py

@@ -8,10 +8,3 @@ def clear_gpu_memory():
     torch.cuda.empty_cache()
     print("GPU memory cleared.")
 
-@pytest.hookimpl(tryfirst=True, hookwrapper=True)
-def pytest_runtest_teardown(item, nextitem):
-    '''
-    clear GPU memory after each test
-    '''
-    yield
-    clear_gpu_memory()
\ No newline at end of file

tests/test_cli/lib/common.py

@@ -3,6 +3,15 @@ import os
 import shutil
 import re
 import json
+import torch
+
+def clear_gpu_memory():
+    '''
+    clear GPU memory
+    '''
+    torch.cuda.empty_cache()
+    print("GPU memory cleared.")
+
 def check_shell(cmd):
     """shell successful."""
     res = os.system(cmd)
@@ -10,11 +19,12 @@ def check_shell(cmd):
 
 def update_config_file(file_path, key, value):
     """update config file."""
-    with open(file_path, 'r', encoding="utf-8") as f:
-        config  = json.loads(f.read())
+    with open(file_path, 'r', encoding="utf-8") as fr:
+        config  = json.loads(fr.read())
     config[key] = value
-    with open(file_path, 'w', encoding="utf-8") as f:
-        f.write(json.dumps(config))
+        # 保存修改后的内容
+    with open(file_path, 'w', encoding='utf-8') as fw:
+        json.dump(config, fw, ensure_ascii=False, indent=4)
 
 def cli_count_folders_and_check_contents(file_path):
     """" count cli files."""
@@ -33,6 +43,7 @@ def sdk_count_folders_and_check_contents(file_path):
         exit(1)
 
 
+
 def delete_file(path):
     """delete file."""
     if not os.path.exists(path):

tests/test_cli/test_cli_sdk.py

@@ -13,10 +13,19 @@ model_config.__use_inside_model__ = True
 pdf_res_path = conf.conf['pdf_res_path']
 code_path = conf.conf['code_path']
 pdf_dev_path = conf.conf['pdf_dev_path']
-
+magic_pdf_config = "/home/quyuan/magic-pdf.json"
 
 class TestCli:
     """test cli."""
+    @pytest.fixture(autouse=True)
+    def setup(self):
+        """
+        init
+        """
+        common.clear_gpu_memory()
+        common.update_config_file(magic_pdf_config, "device-mode", "cuda")
+        # 这里可以添加任何前置操作
+        yield
 
     @pytest.mark.P0
     def test_pdf_auto_sdk(self):
@@ -291,22 +300,32 @@ class TestCli:
     def test_local_magic_pdf_open_st_table(self):
         """magic pdf cli open st table."""
         time.sleep(2)
-        pre_cmd = "cp ~/magic_pdf_st.json ~/magic-pdf.json"
-        print (pre_cmd)
-        os.system(pre_cmd)
+        #pre_cmd = "cp ~/magic_pdf_st.json ~/magic-pdf.json"
+        value = {
+        "model": "struct_eqtable",
+        "enable": True,
+        "max_time": 400
+        }   
+        common.update_config_file(magic_pdf_config, "table-config", value)
         pdf_path = os.path.join(pdf_dev_path, "pdf", "test_rearch_report.pdf")
         common.delete_file(pdf_res_path)
         cli_cmd = "magic-pdf -p %s -o %s" % (pdf_path, pdf_res_path)
         os.system(cli_cmd)
-        res = common.check_latex_table_exists(os.path.join(pdf_res_path, "test_rearch_report", "auto", "test_rearch_report.md"))
+        res = common.check_html_table_exists(os.path.join(pdf_res_path, "test_rearch_report", "auto", "test_rearch_report.md"))
         assert res is True
   
     @pytest.mark.P1
-    def test_local_magic_pdf_open_html_table(self):
-        """magic pdf cli open html table."""
+    def test_local_magic_pdf_open_tablemaster_cuda(self):
+        """magic pdf cli open table master html table cuda mode."""
         time.sleep(2)
-        pre_cmd = "cp ~/magic_pdf_html.json ~/magic-pdf.json"
-        os.system(pre_cmd)
+        #pre_cmd = "cp ~/magic_pdf_html.json ~/magic-pdf.json"
+        #os.system(pre_cmd)
+        value = {
+        "model": "tablemaster",
+        "enable": True,
+        "max_time": 400
+        }   
+        common.update_config_file(magic_pdf_config, "table-config", value)
         pdf_path = os.path.join(pdf_dev_path, "pdf", "test_rearch_report.pdf")
         common.delete_file(pdf_res_path)
         cli_cmd = "magic-pdf -p %s -o %s" % (pdf_path, pdf_res_path)
@@ -315,24 +334,88 @@ class TestCli:
         assert res is True
     
     @pytest.mark.P1
-    def test_magic_pdf_close_html_table_cpu(self):
-        """magic pdf cli close html table cpu mode."""
+    def test_local_magic_pdf_open_rapidai_table(self):
+        """magic pdf cli open rapid ai table."""
         time.sleep(2)
-        pre_cmd = "cp ~/magic_pdf_html_table_cpu.json ~/magic-pdf.json"
-        os.system(pre_cmd)
+        #pre_cmd = "cp ~/magic_pdf_html.json ~/magic-pdf.json"
+        #os.system(pre_cmd)
+        value = {
+        "model": "rapid_table",
+        "enable": True,
+        "max_time": 400
+        }   
+        common.update_config_file(magic_pdf_config, "table-config", value)
         pdf_path = os.path.join(pdf_dev_path, "pdf", "test_rearch_report.pdf")
         common.delete_file(pdf_res_path)
         cli_cmd = "magic-pdf -p %s -o %s" % (pdf_path, pdf_res_path)
         os.system(cli_cmd)
         res = common.check_html_table_exists(os.path.join(pdf_res_path, "test_rearch_report", "auto", "test_rearch_report.md"))
-        assert res is  True
+        assert res is True
+    
+    
+    @pytest.mark.P1
+    def test_local_magic_pdf_doclayout_yolo(self):
+        """magic pdf cli open doclyaout yolo."""
+        time.sleep(2)
+        #pre_cmd = "cp ~/magic_pdf_html.json ~/magic-pdf.json"
+        #os.system(pre_cmd)
+        value = {
+        "model": "doclayout_yolo"
+        }   
+        common.update_config_file(magic_pdf_config, "layout-config", value)
+        pdf_path = os.path.join(pdf_dev_path, "pdf", "test_rearch_report.pdf")
+        common.delete_file(pdf_res_path)
+        cli_cmd = "magic-pdf -p %s -o %s" % (pdf_path, pdf_res_path)
+        os.system(cli_cmd)
+        common.cli_count_folders_and_check_contents(os.path.join(pdf_res_path, "test_rearch_report", "auto"))
+
+    @pytest.mark.P1
+    def test_local_magic_pdf_layoutlmv3_yolo(self):
+        """magic pdf cli open layoutlmv3."""
+        time.sleep(2)
+        value = {
+        "model": "layoutlmv3"
+        }   
+        common.update_config_file(magic_pdf_config, "layout-config", value)
+        pdf_path = os.path.join(pdf_dev_path, "pdf", "test_rearch_report.pdf")
+        common.delete_file(pdf_res_path)
+        cli_cmd = "magic-pdf -p %s -o %s" % (pdf_path, pdf_res_path)
+        os.system(cli_cmd)
+        common.cli_count_folders_and_check_contents(os.path.join(pdf_res_path, "test_rearch_report", "auto"))
+        #res = common.check_html_table_exists(os.path.join(pdf_res_path, "test_rearch_report", "auto", "test_rearch_report.md"))
+
+    @pytest.mark.P1
+    def test_magic_pdf_cpu(self):
+        """magic pdf cli cpu mode."""
+        time.sleep(2)
+        #pre_cmd = "cp ~/magic_pdf_html_table_cpu.json ~/magic-pdf.json"
+        #os.system(pre_cmd)
+        value = {
+        "model": "tablemaster",
+        "enable": False,
+        "max_time": 400
+        }   
+        common.update_config_file(magic_pdf_config, "table-config", value)
+        common.update_config_file(magic_pdf_config, "device-mode", "cpu")
+        pdf_path = os.path.join(pdf_dev_path, "pdf", "test_rearch_report.pdf")
+        common.delete_file(pdf_res_path)
+        cli_cmd = "magic-pdf -p %s -o %s" % (pdf_path, pdf_res_path)
+        os.system(cli_cmd)
+        common.cli_count_folders_and_check_contents(os.path.join(pdf_res_path, "test_rearch_report", "auto"))
+
 
     @pytest.mark.P1
     def test_local_magic_pdf_close_html_table(self):
         """magic pdf cli close table."""
         time.sleep(2)
-        pre_cmd = "cp ~/magic_pdf_close_table.json ~/magic-pdf.json"
-        os.system(pre_cmd)
+        #pre_cmd = "cp ~/magic_pdf_close_table.json ~/magic-pdf.json"
+        #os.system(pre_cmd)
+        value = {
+        "model": "tablemaster",
+        "enable": False,
+        "max_time": 400
+        }   
+        common.update_config_file(magic_pdf_config, "table-config", value)
         pdf_path = os.path.join(pdf_dev_path, "pdf", "test_rearch_report.pdf")
         common.delete_file(pdf_res_path)
         cli_cmd = "magic-pdf -p %s -o %s" % (pdf_path, pdf_res_path)