dataverse-utils 0.22.1__tar.gz → 0.22.3__tar.gz

{dataverse_utils-0.22.1 → dataverse_utils-0.22.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataverse-utils
-Version: 0.22.1
+Version: 0.22.3
 Summary: Utilities for the Dataverse data respository system
 License: MIT
 License-File: LICENCE.md

{dataverse_utils-0.22.1 → dataverse_utils-0.22.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dataverse-utils"
-version = "0.22.1"
+version = "0.22.3"
 description = "Utilities for the Dataverse data respository system"
 authors = [
     {name = "Paul Lesack",email = "paul.lesack@ubc.ca"}

{dataverse_utils-0.22.1 → dataverse_utils-0.22.3}/src/dataverse_utils/__init__.py

@@ -7,7 +7,7 @@ import pathlib
 import sys
 from dataverse_utils.dataverse_utils import *
 
-VERSION = (0, 22, 1)
+VERSION = (0, 22, '3a1')
 __version__ = '.'.join([str(x) for x in VERSION])
 
 USERAGENT = (f'dataverse_utils/v{__version__} ({sys.platform.capitalize()}); '

{dataverse_utils-0.22.1 → dataverse_utils-0.22.3}/src/dataverse_utils/collections.py

@@ -16,6 +16,7 @@ import traceback
 import warnings
 
 import bs4
+import charset_normalizer as cn
 import markdown_pdf
 import markdownify
 import pyreadstat
@@ -290,8 +291,10 @@ class StudyMetadata(dict):
                            f'Offending JSON: {self.study_meta}') from e
         self.__files = None
         self.__all_files = None
-        self.index = {f"{_['versionNumber']}.{_['versionMinorNumber']}": n
-                 for n, _ in enumerate(self.all_versions['data'])}
+        #self.index = {f"{_['versionNumber']}.{_['versionMinorNumber']}": n
+        #         for n, _ in enumerate(self.all_versions['data'])}
+        #self.index = {_: n for _, n in enumerate(self.versions)}
+        self.index = dict(enumerate(self.versions))
 
     def __obtain_metadata(self):
         '''
@@ -347,7 +350,10 @@ class StudyMetadata(dict):
             for field in v['fields']:
                 tmp.update(self.extract_field_metadata(field))
         tmp.update(self.__extract_licence_info(chunk))
-        tmp['versionStatement'] = f"{chunk['versionNumber']}.{chunk['versionMinorNumber']}"
+        if chunk.get('versionNumber'):
+            tmp['versionStatement'] = f"{chunk['versionNumber']}.{chunk['versionMinorNumber']}"
+        else:
+            tmp['versionStatement'] = f"{chunk.get('versionState', '')}"
         return tmp
 
     def extract_field_metadata(self, field):
@@ -440,8 +446,15 @@ class StudyMetadata(dict):
         '''
         Return a *list* of formatted version strings
         '''
-        return [f"{_['versionNumber']}.{_['versionMinorNumber']}"
-                         for _ in self.all_versions['data']]
+        out = []
+        for _ in self.all_versions['data']:
+            if _.get('versionNumber'):
+                out.append(f"{_['versionNumber']}.{_['versionMinorNumber']}")
+            else:
+                out.append(_['versionState'])
+        #return [f"{_['versionNumber']}.{_['versionMinorNumber']}"
+        #                 for _ in self.all_versions['data']]
+        return out
 
     @property
     def files(self)->list:
@@ -468,10 +481,8 @@ class StudyMetadata(dict):
                 filelist = self.extract_files(_.get('files', []))
                 for oldfile in filelist:
                     oldfile.update({k:v for k,v in _.items() if k in add_fields})
-                    version_statement = {'versionStatement':
-                                             f'{_["versionNumber"]}.{_["versionMinorNumber"]}'}
-                    oldfile.update(version_statement)
-                #all_files.extend(self.extract_files_2(_.get('files', [])))
+                    vs = _.get('versionNumber', _.get('versionState', ''))
+                    oldfile.update({'versionStatement' : vs})
                 all_files.extend(filelist)
             self.__all_files = all_files
         return self.__all_files
@@ -904,7 +915,8 @@ class ReadmeCreator:
                    'Country':'Country(ies)',
                    'State':'State(s)',
                    'City':'City(ies)',
-                   'Geographic Unit':'Geographic unit(s)'}
+                   'Geographic Unit':'Geographic unit(s)',
+                   'State(s)ment' : 'Statement'}
         for k, v in fixthese.items():
             wordsp = wordsp.replace(k, v)
         return wordsp.strip()
@@ -1250,6 +1262,14 @@ class FileAnalysis(dict):
         self.update(outmeta)
         return
 
+    def get_encoding(self, fpath):
+        '''
+        Return the encoding of a file so that pandas
+        won't crash. Hopefully.
+
+        fpath : str
+            file path
+        '''
 
     def generic_metadata(self, ext)->None:
         '''
@@ -1265,14 +1285,20 @@ class FileAnalysis(dict):
         #    data = pd.read_csv(self.__whichfile, sep='\t')
         #else:
         #    data = pd.read_csv(self.__whichfile)
-
+        encme = {'.tsv': {'sep': '\t'},
+                 '.csv': {}}
+        if ext.lower() in encme:
+            with open(self.__whichfile, 'rb') as f:
+                encoding = {'encoding':'utf-8'}
+                encoding.update({'encoding':cn.detect(f.read()).get('encoding', 'utf-8')})
+                encme[ext.lower()].update(encoding)
         lookuptable ={'.tsv': {'func': pd.read_csv,
-                                'kwargs' : {'sep':'\t'}},
-                        '.csv': {'func' : pd.read_csv},
-                        '.rda': {'func' : pyreadr.read_r},
+                                'kwargs' : encme['.tsv']},
+                      '.csv': {'func' : pd.read_csv, 'kwargs' : encme['.csv']},
+                      '.rda': {'func' : pyreadr.read_r},
                        '.rdata':{'func' : pyreadr.read_r}}
         data = lookuptable[ext]['func'](self.__whichfile,
-                                              **lookuptable[ext].get('kwargs', {}))
+                                                  **lookuptable[ext].get('kwargs', {}))
         if ext  in ['.rda', '.rdata']:
             data = data[None] #why pyreadr why
         outmeta = {}

{dataverse_utils-0.22.1 → dataverse_utils-0.22.3}/src/dataverse_utils/scripts/dv_collection_info.py

@@ -207,7 +207,7 @@ def main():
     else:
         try:
             all_studies = [dvc.StudyMetadata(url=args.url, pid=args.pid, key=args.key)]
-        except dataverse_utils.collections.MetadataError as e:
+        except (KeyError, dataverse_utils.collections.MetadataError) as e:
             print(e, file=sys.stderr)
             sys.exit()
     #if 'all' in [x.lower() for x in args.fields] and args.collection:

{dataverse_utils-0.22.1 → dataverse_utils-0.22.3}/src/dataverse_utils/scripts/dv_readme_creator.py

@@ -36,7 +36,7 @@ def parse() -> argparse.ArgumentParser():
                               'Defaults to "borealisdata.ca"'))
     parser.add_argument('-p', '--pid',
                         help=('Persistent ID of study (ie, doi or hdl). '
-                              'format: doi: doi:12.2345/PRE/ZYX9876'),
+                              'eg: doi:12.2345/PRE/ZYX9876'),
                         type=str,
                         required=True)
     parser.add_argument('-k', '--key', required=True,