dcicutils 8.8.4.1b22__tar.gz → 8.8.4.1b26__tar.gz

{dcicutils-8.8.4.1b22 → dcicutils-8.8.4.1b26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcicutils
-Version: 8.8.4.1b22
+Version: 8.8.4.1b26
 Summary: Utility package for interacting with the 4DN Data Portal and other 4DN resources
 Home-page: https://github.com/4dn-dcic/utils
 License: MIT

{dcicutils-8.8.4.1b22 → dcicutils-8.8.4.1b26}/dcicutils/file_utils.py

@@ -79,15 +79,15 @@ def search_for_file(file: str,
     return None if single is True else []
 
 
-def normalize_path(value: Union[str, pathlib.Path], absolute: bool = False, home: Optional[bool] = None) -> str:
+def normalize_path(value: Union[str, pathlib.Path], absolute: bool = False, expand_home: Optional[bool] = None) -> str:
     """
     Normalizes the given path value and returns the result; does things like remove redundant
     consecutive directory separators and redundant parent paths. If the given absolute argument
-    is True than converts the path to an absolute path. If the given home argument is True and
-    if the path can reasonably be represented with a home directory indicator (i.e. "~"), then
-    converts it to such. If the home argument is False and path starts with the home directory
-    indicator then expands it to the actual (absolute) home path. If the given value is not
-    actually even a string (or pathlib.Path) then returns an empty string.
+    is True than converts the path to an absolute path. If the given expand_home argument is False
+    and if the path can reasonably be represented with a home directory indicator (i.e. "~"), then
+    converts it to such. If the expand_home argument is True and path starts with the home directory
+    indicator (i.e. "~") then expands it to the actual (absolute) home path of the caller. If the
+    given path value is not actually even a string (or pathlib.Path) then returns an empty string.
     """
     if isinstance(value, pathlib.Path):
         value = str(value)
@@ -95,30 +95,34 @@ def normalize_path(value: Union[str, pathlib.Path], absolute: bool = False, home
         return ""
     if not (value := value.strip()) or not (value := os.path.normpath(value)):
         return ""
-    if home is False:
+    if expand_home is True:
         value = os.path.expanduser(value)
-    elif (home is True) and (os.name == "posix") and value.startswith(home := HOME_DIRECTORY + os.sep):
+    elif (expand_home is False) and (os.name == "posix") and value.startswith(home := HOME_DIRECTORY + os.sep):
         value = "~/" + value[len(home):]
     if absolute is True:
         value = os.path.abspath(value)
     return value
 
 
-def get_file_size(file: str) -> Optional[int]:
+def get_file_size(file: str, raise_exception: bool = True) -> Optional[int]:
     try:
         return os.path.getsize(file) if isinstance(file, str) else None
     except Exception:
+        if raise_exception is True:
+            raise
         return None
 
 
-def get_file_modified_datetime(file: str) -> Optional[datetime]:
+def get_file_modified_datetime(file: str, raise_exception: bool = True) -> Optional[datetime]:
     try:
         return datetime.fromtimestamp(os.path.getmtime(file)) if isinstance(file, str) else None
     except Exception:
+        if raise_exception is True:
+            raise
         return None
 
 
-def are_files_equal(filea: str, fileb: str) -> bool:
+def are_files_equal(filea: str, fileb: str, raise_exception: bool = True) -> bool:
     """
     Returns True iff the contents of the two given files are exactly the same.
     """
@@ -135,10 +139,12 @@ def are_files_equal(filea: str, fileb: str) -> bool:
                         break
         return True
     except Exception:
+        if raise_exception is True:
+            raise
         return False
 
 
-def compute_file_md5(file: str) -> str:
+def compute_file_md5(file: str, raise_exception: bool = True) -> str:
     """
     Returns the md5 checksum for the given file.
     """
@@ -151,10 +157,12 @@ def compute_file_md5(file: str) -> str:
                 md5.update(chunk)
         return md5.hexdigest()
     except Exception:
+        if raise_exception is True:
+            raise
         return ""
 
 
-def compute_file_etag(file: str) -> Optional[str]:
+def compute_file_etag(file: str, raise_exception: bool = True) -> Optional[str]:
     """
     Returns the AWS S3 "etag" for the given file; this value is md5-like but
     not the same as a normal md5. We use this to compare that a file in S3
@@ -164,6 +172,8 @@ def compute_file_etag(file: str) -> Optional[str]:
         with io.open(file, "rb") as f:
             return _compute_file_etag(f)
     except Exception:
+        if raise_exception is True:
+            raise
         return None
 
 

dcicutils-8.8.4.1b26/dcicutils/http_utils.py

@@ -0,0 +1,39 @@
+from contextlib import contextmanager
+import requests
+from typing import Callable, Optional
+from dcicutils.tmpfile_utils import temporary_file
+
+
+@contextmanager
+def download(url: str, suffix: Optional[str] = None, binary: bool = True,
+             progress: Optional[Callable] = None) -> Optional[str]:
+    """
+    Context manager to download the given URL into a temporary file and yields the file
+    path to it. An optional file suffix may be specified for this temporary file name.
+    Defaults to binary file mode; if not desired then pass False as the binary argument.
+    """
+    with temporary_file(suffix=suffix) as file:
+        download_to(url, file, binary=binary, progress=progress)
+        yield file
+
+
+def download_to(url: str, file: str, binary: bool = True, progress: Optional[Callable] = None) -> None:
+    """
+    Download the given URL into the given file. Defaults to binary
+    file mode; if not desired then pass False as the binary argument.
+    """
+    if not callable(progress):
+        progress = None
+    response = requests.get(url, stream=True)
+    if progress:
+        nbytes = 0
+        nbytes_total = None
+        if isinstance(content_length := response.headers.get("Content-Length"), str) and content_length.isdigit():
+            nbytes_total = int(content_length)
+    with open(file, "wb" if binary is True else "w") as f:
+        for chunk in response.iter_content(chunk_size=8192):
+            if chunk:
+                f.write(chunk)
+            if progress:
+                nbytes += len(chunk)
+                progress(nbytes, nbytes_total)

{dcicutils-8.8.4.1b22 → dcicutils-8.8.4.1b26}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dcicutils"
-version = "8.8.4.1b22"  # TODO: To become 8.8.5
+version = "8.8.4.1b26"  # TODO: To become 8.8.5
 description = "Utility package for interacting with the 4DN Data Portal and other 4DN resources"
 authors = ["4DN-DCIC Team <support@4dnucleome.org>"]
 license = "MIT"

dcicutils-8.8.4.1b22/dcicutils/http_utils.py

@@ -1,31 +0,0 @@
-from contextlib import contextmanager
-import requests
-from typing import Callable, Optional
-from dcicutils.tmpfile_utils import temporary_file
-
-
-@contextmanager
-def download(url: str, suffix: Optional[str] = None, binary: bool = True,
-             progress: Optional[Callable] = None) -> Optional[str]:
-    """
-    Context manager to ownload the given URL into a temporary file and yields the file
-    path to it. An optional file suffix may be specified. Defaults to binary file mode;
-    if this is not desired then pass False as the binary argument.
-    """
-    if not callable(progress):
-        progress = None
-    with temporary_file(suffix=suffix) as file:
-        response = requests.get(url, stream=True)
-        if progress:
-            nbytes = 0
-            nbytes_total = None
-            if isinstance(content_length := response.headers.get("Content-Length"), str) and content_length.isdigit():
-                nbytes_total = int(content_length)
-        with open(file, "wb" if binary is True else "w") as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                if chunk:
-                    f.write(chunk)
-                if progress:
-                    nbytes += len(chunk)
-                    progress(nbytes, nbytes_total)
-        yield file