aboutsummaryrefslogtreecommitdiffstats
path: root/python/grobid_tool.py
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2019-12-18 14:52:41 -0800
committerBryan Newbold <bnewbold@archive.org>2019-12-18 14:52:43 -0800
commit0ea8bfb3485bc4db5cb7a17397d6c37f407a65b4 (patch)
tree6a421ced28f7cd947dd09215e90811a83e8b3171 /python/grobid_tool.py
parent59776d4175faa3d0b7ff5f25456620b2a84d738e (diff)
downloadsandcrawler-0ea8bfb3485bc4db5cb7a17397d6c37f407a65b4.tar.gz
sandcrawler-0ea8bfb3485bc4db5cb7a17397d6c37f407a65b4.zip
refactor: improve argparse usage
use ArgumentDefaultsHelpFormatter and add help messages to all sub-commands
Diffstat (limited to 'python/grobid_tool.py')
-rwxr-xr-xpython/grobid_tool.py12
1 files changed, 8 insertions, 4 deletions
diff --git a/python/grobid_tool.py b/python/grobid_tool.py
index f21d088..a8d5120 100755
--- a/python/grobid_tool.py
+++ b/python/grobid_tool.py
@@ -50,7 +50,8 @@ def run_extract_zipfile(args):
pusher.run()
def main():
- parser = argparse.ArgumentParser()
+ parser = argparse.ArgumentParser(
+ formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--kafka-mode',
action='store_true',
help="send output to Kafka (not stdout)")
@@ -68,19 +69,22 @@ def main():
help="GROBID API host/port")
subparsers = parser.add_subparsers()
- sub_extract_json = subparsers.add_parser('extract-json')
+ sub_extract_json = subparsers.add_parser('extract-json',
+ help="for each JSON line with CDX info, fetches PDF and does GROBID extraction")
sub_extract_json.set_defaults(func=run_extract_json)
sub_extract_json.add_argument('json_file',
help="JSON file to import from (or '-' for stdin)",
type=argparse.FileType('r'))
- sub_extract_cdx = subparsers.add_parser('extract-cdx')
+ sub_extract_cdx = subparsers.add_parser('extract-cdx',
+ help="for each CDX line, fetches PDF and does GROBID extraction")
sub_extract_cdx.set_defaults(func=run_extract_cdx)
sub_extract_cdx.add_argument('cdx_file',
help="CDX file to import from (or '-' for stdin)",
type=argparse.FileType('r'))
- sub_extract_zipfile = subparsers.add_parser('extract-zipfile')
+ sub_extract_zipfile = subparsers.add_parser('extract-zipfile',
+ help="opens zipfile, iterates over PDF files inside and does GROBID extract for each")
sub_extract_zipfile.set_defaults(func=run_extract_zipfile)
sub_extract_zipfile.add_argument('zip_file',
help="zipfile with PDFs to extract",