adulau/napkin-text-analysis
1
0
Fork 0
mirror of https://github.com/adulau/napkin-text-analysis.git synced 2024-11-22 01:47:06 +00:00
Code Issues Projects Releases Packages Wiki Activity

chg: [args] add an option to force the language

Browse source
This commit is contained in:
Alexandre Dulaunoy 2020-10-01 23:06:39 +02:00
parent 3a09abc80c
commit 3d71d9288e
Signed by: adulau
GPG key ID: 09E2CD4944E6CBCD
1 changed files with 7 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
bin/napkin.py
View file

@ -14,6 +14,8 @@ parser.add_argument('-f', help="file to analyse")
parser.add_argument('-t', help="maximum value for the top list (default is 100) -1 is no limit", default=100) parser.add_argument('-t', help="maximum value for the top list (default is 100) -1 is no limit", default=100)
parser.add_argument('-s', help="display the overall statistics (default is False)", default=False, action='store_true') parser.add_argument('-s', help="display the overall statistics (default is False)", default=False, action='store_true')
parser.add_argument('-o', help="output format (default is csv), json", default="csv") parser.add_argument('-o', help="output format (default is csv), json", default="csv")
parser.add_argument("-l", help="language used for the analysis (default is en)", default="en")
args = parser.parse_args() args = parser.parse_args()
if args.f is None: if args.f is None:
parser.print_help() parser.print_help()
@ -27,7 +29,11 @@ except:
print("Redis database on port 6380 is not running...", file=sys.stderr) print("Redis database on port 6380 is not running...", file=sys.stderr)
sys.exit() sys.exit()
nlp = spacy.load("en_core_web_md") if args.l == "fr":
nlp = spacy.load("fr_core_news_md")
else:
nlp = spacy.load("en_core_web_md")
nlp.add_pipe(LanguageDetector(), name='language_detector', last=True) nlp.add_pipe(LanguageDetector(), name='language_detector', last=True)
nlp.max_length = 2000000 nlp.max_length = 2000000