From a5dee767d1d67f604956c9b66e3dcd1773e674d6 Mon Sep 17 00:00:00 2001
From: David Michaels <david_michaels@hms.harvard.edu>
Date: Mon, 6 May 2024 16:31:25 -0400
Subject: [PATCH] minor updates from pr-305 feedback

---
 dcicutils/file_utils.py | 20 ++++++++++++++-----
 dcicutils/http_utils.py | 44 ++++++++++++++++++++++++-----------------
 pyproject.toml          |  2 +-
 3 files changed, 42 insertions(+), 24 deletions(-)

diff --git a/dcicutils/file_utils.py b/dcicutils/file_utils.py
index 60c62f1ac..defad2da5 100644
--- a/dcicutils/file_utils.py
+++ b/dcicutils/file_utils.py
@@ -104,21 +104,25 @@ def normalize_path(value: Union[str, pathlib.Path], absolute: bool = False, expa
     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
 
 
diff --git a/dcicutils/http_utils.py b/dcicutils/http_utils.py
index 9ccf743c5..a82da78bd 100644
--- a/dcicutils/http_utils.py
+++ b/dcicutils/http_utils.py
@@ -8,24 +8,32 @@
 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.
+    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.
     """
-    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)
+        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)
diff --git a/pyproject.toml b/pyproject.toml
index 2cc997a12..da8d34ecb 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dcicutils"
-version = "8.8.4.1b24"  # 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"