Merge branch 'fixbug/editor_pdf' into 'mgx_ops'

fixbug: async Editor.read

See merge request pub/MetaGPT!293

metagpt/tools/libs/editor.py

@@ -11,7 +11,7 @@ from metagpt.const import DEFAULT_WORKSPACE_ROOT
 from metagpt.logs import logger
 from metagpt.tools.tool_registry import register_tool
 from metagpt.utils import read_docx
-from metagpt.utils.common import aread_bin, awrite_bin, run_coroutine_sync
+from metagpt.utils.common import aread_bin, awrite_bin
 from metagpt.utils.repo_to_markdown import is_text_file
 from metagpt.utils.report import EditorReporter
 
@@ -45,13 +45,13 @@ class Editor:
         # self.resource.report(path, "path")
         return f"The writing/coding the of the file {os.path.basename(path)}' is now completed. The file '{os.path.basename(path)}' has been successfully created."
 
-    def read(self, path: str) -> FileBlock:
+    async def read(self, path: str) -> FileBlock:
         """Read the whole content of a file. Using absolute paths as the argument for specifying the file location."""
-        is_text, mime_type = run_coroutine_sync(is_text_file, path)
+        is_text, mime_type = await is_text_file(path)
         if is_text:
             lines = self._read_text(path)
         elif mime_type == "application/pdf":
-            lines = self._read_pdf(path)
+            lines = await self._read_pdf(path)
         elif mime_type in {
             "application/msword",
             "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -59,7 +59,7 @@ class Editor:
             "application/vnd.openxmlformats-officedocument.wordprocessingml.template",
             "application/vnd.ms-word.template.macroEnabled.12",
         }:
-            lines = self._read_docx(path)
+            lines = await self._read_docx(path)
         else:
             return FileBlock(file_path=str(path), block_content="")
         self.resource.report(str(path), "path")
@@ -225,8 +225,8 @@ class Editor:
         return lines
 
     @staticmethod
-    def _read_pdf(path: Union[str, Path]) -> List[str]:
-        result = run_coroutine_sync(Editor._omniparse_read_file, path)
+    async def _read_pdf(path: Union[str, Path]) -> List[str]:
+        result = await Editor._omniparse_read_file(path)
         if result:
             return result
 
@@ -237,8 +237,8 @@ class Editor:
         return [i.text for i in lines]
 
     @staticmethod
-    def _read_docx(path: Union[str, Path]) -> List[str]:
-        result = run_coroutine_sync(Editor._omniparse_read_file, path)
+    async def _read_docx(path: Union[str, Path]) -> List[str]:
+        result = await Editor._omniparse_read_file(path)
         if result:
             return result
         return read_docx(str(path))

metagpt/utils/common.py

@@ -12,7 +12,6 @@
 from __future__ import annotations
 
 import ast
-import asyncio
 import base64
 import contextlib
 import csv
@@ -1054,32 +1053,6 @@ def tool2name(cls, methods: List[str], entry) -> Dict[str, Any]:
     return mappings
 
 
-def run_coroutine_sync(coroutine, *args, **kwargs):
-    """
-    Runs a coroutine function synchronously by encapsulating its invocation as a non-coroutine function call.
-
-    Args:
-        coroutine: The coroutine function to be encapsulated.
-        *args: Positional arguments to be passed to the coroutine.
-        **kwargs: Keyword arguments to be passed to the coroutine.
-
-    Returns:
-        The return value of the coroutine.
-    """
-    try:
-        loop = asyncio.get_running_loop()
-    except RuntimeError:  # No running event loop
-        loop = None
-
-    if loop and loop.is_running():
-        # The event loop is already running
-        future = asyncio.run_coroutine_threadsafe(coroutine(*args, **kwargs), loop)
-        return future.result()
-    else:
-        # The event loop is not running
-        return asyncio.run(coroutine(*args, **kwargs))
-
-
 def log_time(method):
     """A time-consuming decorator for printing execution duration."""
 

tests/metagpt/tools/libs/test_editor.py

@@ -141,9 +141,10 @@ def test_new_content_format_issue(test_file):
         TEST_DATA_PATH / "movie/trailer.mp4",
     ],
 )
-def test_read_files(filename):
+@pytest.mark.asyncio
+async def test_read_files(filename):
     editor = Editor()
-    file_block = editor.read(filename)
+    file_block = await editor.read(filename)
     assert file_block
     assert file_block.file_path
     if filename.suffix not in [".png", ".mp3", ".mp4"]: