diff --git a/.gitignore b/.gitignore index 30f02d1c5af28706cb5c6e661bbaba59c5bf937e..a87719155a81c2d1398130f803674726ec831865 100644 --- a/.gitignore +++ b/.gitignore @@ -1,6 +1,8 @@ __pycache__ .tox +.eggs .coverage *cache.db *.egg-info .docker/cert +src/caosadvancedtools/version.py diff --git a/src/caosadvancedtools/crawler.py b/src/caosadvancedtools/crawler.py index 7c4ae658c60a363e4d4ecfff0780acf1213b011f..e1d9901c60620b2d858f5f8bb54d346d1e87fe8d 100644 --- a/src/caosadvancedtools/crawler.py +++ b/src/caosadvancedtools/crawler.py @@ -224,8 +224,8 @@ class Crawler(object): msg = ("The crawler has no matching rules for and is thus " "ignoring:\n{}".format(item)) - logging.warning(msg, extra={"identifier": str(item), - 'category': "matches"}) + logger.warning(msg, extra={"identifier": str(item), + 'category': "matches"}) if len(matches[idx]) > 1: msg = ("Attention: More than one matching cfood!\n" @@ -233,8 +233,8 @@ class Crawler(object): + "\tRecordTypes:\t" + ", ".join( matches[idx])+"\n") - logging.warning(msg, extra={"identifier": str(item), - 'category': "matches"}) + logger.warning(msg, extra={"identifier": str(item), + 'category': "matches"}) def cached_find_identifiables(self, identifiables): if self.use_cache: diff --git a/src/caosadvancedtools/table_importer.py b/src/caosadvancedtools/table_importer.py index 4ade13bd7495d1509041e4f005bd08f7ab34896a..6fb4a28f17420df901ad33a2bbe57fbd63dfc190 100755 --- a/src/caosadvancedtools/table_importer.py +++ b/src/caosadvancedtools/table_importer.py @@ -75,7 +75,8 @@ class TSV_Importer(object): class XLS_Importer(object): - def __init__(self, converters, obligatory_columns=[], unique_columns=[]): + + def __init__(self, converters, obligatory_columns=None, unique_columns=None): """ converters: dict with column names as keys and converter functions as values @@ -89,8 +90,8 @@ class XLS_Importer(object): """ self.sup = SuppressKnown() self.required_columns = list(converters.keys()) - self.obligatory_columns = obligatory_columns - self.unique_columns = unique_columns + self.obligatory_columns = [] if obligatory_columns is None else obligatory_columns + self.unique_columns = [] if unique_columns is None else unique_columns self.converters = converters def read_xls(self, filename): @@ -161,9 +162,9 @@ class XLS_Importer(object): df = df.copy() uniques = [] - for index, row in df.iterrows(): - element = tuple(row.loc[key] for key in self.unique_columns) - + subtable = df[list(self.unique_columns)] + for index, row in subtable.iterrows(): + element = tuple(row) if element in uniques: errmsg = ( "The {}. row contains the values '{}'.\nThis value "