Small fixes for dedoc library (#441)

ispras · May 21, 2024 · ebb7593 · ebb7593
1 parent 29a0c0d
commit ebb7593
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -6,6 +6,7 @@
 [![GitHub release](https://img.shields.io/github/release/ispras/dedoc.svg)](https://github.com/ispras/dedoc/releases/)
 [![Demo dedoc-readme.hf.space](https://img.shields.io/website-up-down-green-red/https/huggingface.co/spaces/dedoc/README.svg)](https://dedoc-readme.hf.space)
 [![Docker Hub](https://img.shields.io/docker/pulls/dedocproject/dedoc.svg)](https://hub.docker.com/r/dedocproject/dedoc/ "Docker Pulls")
+[![CI tests](https://github.com/ispras/dedoc/workflows/CI/badge.svg)](https://github.com/ispras/dedoc/actions)
 
 ![Dedoc](https://github.com/ispras/dedoc/raw/master/dedoc_logo.png)
 

diff --git a/dedoc/readers/article_reader/article_reader.py b/dedoc/readers/article_reader/article_reader.py
@@ -34,7 +34,6 @@ def __init__(self, config: Optional[dict] = None) -> None:
             self.grobid_url = f"http://{os.environ.get('GROBID_HOST', 'localhost')}:{os.environ.get('GROBID_PORT', '8070')}"
         self.url = f"{self.grobid_url}/api/processFulltextDocument"
         self.grobid_is_alive = False
-        self.__update_grobid_alive(self.grobid_url, max_attempts=self.config.get("grobid_max_connection_attempts", 3))
 
     def read(self, file_path: str, parameters: Optional[dict] = None) -> UnstructuredDocument:
         """
@@ -91,7 +90,7 @@ def can_read(self, file_path: Optional[str] = None, mime: Optional[str] = None,
         if get_param_document_type(parameters) != "article":
             return False
 
-        self.__update_grobid_alive(self.grobid_url, max_attempts=1)
+        self.__update_grobid_alive(self.grobid_url, max_attempts=self.config.get("grobid_max_connection_attempts", 3))
         if not self.grobid_is_alive:
             return False
 

diff --git a/dedoc/utils/parameter_utils.py b/dedoc/utils/parameter_utils.py
@@ -175,6 +175,6 @@ def get_param_attachments_dir(parameters: Optional[dict], file_path: str) -> str
     parameters = {} if parameters is None else parameters
 
     attachments_dir = parameters.get("attachments_dir", None)
-    attachments_dir = default_dir if attachments_dir is None else attachments_dir
+    attachments_dir = attachments_dir if attachments_dir else default_dir
     os.makedirs(attachments_dir, exist_ok=True)
     return attachments_dir