From 9001cab926605dd5ebf5493a8a4f734cf1612437 Mon Sep 17 00:00:00 2001
From: Olof Olsson <olof.olsson@snd.gu.se>
Date: Sun, 17 Sep 2023 16:26:16 +0200
Subject: [PATCH] wip: add checks for dir and list option

#4 --list-ony flag will skip download
---
 README.md           |  8 +++++++-
 daget/__main__.py   | 30 ++++++++++++++++++------------
 daget/exceptions.py |  1 -
 daget/utils.py      |  4 ++--
 pyproject.toml      |  4 ++--
 5 files changed, 29 insertions(+), 18 deletions(-)

diff --git a/README.md b/README.md
index 8676832..bda9d68 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,8 @@
 
 Simple utility to download datasets from data respositories.
 
+The goal of this project is to explore machine readable metadata and learn more about writing python packages.
+
 ⚠️ __script is in early development and needs testing__ ⚠️ 
 
 ## Installation
@@ -32,6 +34,10 @@ or short form doi:
 ## Semi-suported respositories 
 * Figshare - https://su.figshare.com & https://figshare.scilifelab.se (more testing needed)
 
+## Alternatives
+
+* [datahugger](https://github.com/J535D165/datahugger/) - wider repository suport
+
 ## Improve the script
 
 Adding suport for additional repositories requires test cases and investigation arround how to get file metadata from the landing page.
@@ -41,6 +47,6 @@ Please help by testing and reporting [issues](https://github.com/borsna/daget/is
 ## TODO
 
 - [ ] Add error handling
-- [ ] Check empty destination directory
+- [x] Check empty destination directory
 - [ ] Improve documentation
 - [x] Package script for pip
diff --git a/daget/__main__.py b/daget/__main__.py
index 70c01bc..41b1822 100755
--- a/daget/__main__.py
+++ b/daget/__main__.py
@@ -15,29 +15,35 @@ def main():
 
   parser.add_argument('url', help="URL/DOI to the dataset")
   parser.add_argument('destination', help="Full or relative path to destination directory") 
+  parser.add_argument("--list-only", action="store_true", help="Skip download")
 
   args = parser.parse_args()
 
-  desitnation = os.path.realpath(args.destination)
-
-  if not os.path.exists(desitnation):
-    os.makedirs(desitnation)
-
-  print("destination:  ", desitnation)
-
+  # get doi/url and resolve to landing page
   try:
     url = get_redirect_url(args.url)
   except ResolveError as err:
-    print(bcolors.FAIL, "error resolving ", args.url, bcolors.ENDC)
+    print(bcolors.FAIL, f'error resolving {args.url}', bcolors.ENDC)
     exit(1)
   
-  print("landing page: ", url)
+  print(f'landing page: {url}')
+
+  # get desitnation directory and create directory
+  desitnation = os.path.realpath(args.destination)
+
+  if not os.path.exists(desitnation):
+    os.makedirs(desitnation)
+  else:
+    if len(os.listdir(desitnation)) != 0:
+      print(bcolors.FAIL, f'{desitnation} must be a empty directory or new directory path', bcolors.ENDC)
+      exit(1)
+
+  print(f'destination: {desitnation}')
 
   files = get_file_list_from_repo(url)
 
   total_size = 0
 
-  print(bcolors.BOLD, "size", "\t", "path", bcolors.ENDC)
   for file in files:
     total_size += file['size']
     print(bcolors.OKBLUE, size_as_string(file['size']).strip(), bcolors.ENDC, file['name'])
@@ -46,8 +52,8 @@ def main():
     
     if not os.path.exists(file_dir):
       os.makedirs(file_dir)
-
-    download_file(file['url'], file_path)
+    if(not args.list_only):
+      download_file(file['url'], file_path)
 
   print(bcolors.OKGREEN, bcolors.BOLD, size_as_string(total_size), bcolors.ENDC, "downloaded ")
 
diff --git a/daget/exceptions.py b/daget/exceptions.py
index 8858511..87ec07d 100644
--- a/daget/exceptions.py
+++ b/daget/exceptions.py
@@ -1,6 +1,5 @@
 class ResolveError(ValueError):
     pass
 
-
 class RepoError(Exception):
     pass
\ No newline at end of file
diff --git a/daget/utils.py b/daget/utils.py
index 9001be9..9f94551 100644
--- a/daget/utils.py
+++ b/daget/utils.py
@@ -1,5 +1,5 @@
 import urllib, urllib.error
-from exceptions import RepoError, ResolveError
+from daget.exceptions import RepoError, ResolveError
 
 
 def get_redirect_url(url):
@@ -14,7 +14,7 @@ def get_redirect_url(url):
     r = urllib.request.urlopen(url)
     return r.geturl()
   except urllib.error.HTTPError:
-    raise ResolveError("url not found") 
+    raise ResolveError(f"{url} not found") 
   
 def download_file(url, target):
   opener = urllib.request.build_opener()
diff --git a/pyproject.toml b/pyproject.toml
index cb3e28e..b5aea0d 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "daget"
-version = "0.3"
+version = "0.4"
 description = "Download dataset via DOI or landing page url"
 authors = [
     { name = "Olof Olsson", email = "borsna@gmail.com" }
@@ -20,7 +20,7 @@ dependencies = ["requests"]
 requires-python = ">=3.6"
 
 [project.scripts]
-datahugger = "daget.__main__:main"
+daget = "daget.__main__:main"
 
 [build-system]
 requires = ["setuptools>=61.0"]