sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2024-12-26 18:44:18 +00:00
Code Issues Projects Releases Wiki Activity

Use more descriptive argument names then i and o (now: input and output)

Browse Source
This commit is contained in:
Patrick Jentsch 2021-03-18 10:32:55 +01:00
parent 41f70da8eb
commit e78f667438
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
hocrtotei
View File

@ -9,8 +9,8 @@ import re
import xml.etree.ElementTree as ET import xml.etree.ElementTree as ET
parser = ArgumentParser(description='Convert hOCR to TEI XML.') parser = ArgumentParser(description='Convert hOCR to TEI XML.')
parser.add_argument('i', metavar='Path to hOCR input file') parser.add_argument('input', metavar='Path to hOCR input file')
parser.add_argument('o', metavar='Path to TEI output file') parser.add_argument('output', metavar='Path to TEI output file')
args = parser.parse_args() args = parser.parse_args()
tei = '' tei = ''
@ -31,7 +31,7 @@ tei += ' </teiHeader>\n'
tei += ' <text>\n' tei += ' <text>\n'
tei += ' <body>\n' tei += ' <body>\n'
# Conversion start # Conversion start
hocr = ET.parse(args.i) hocr = ET.parse(args.input)
for page in hocr.findall('.//*[@class="ocr_page"]'): for page in hocr.findall('.//*[@class="ocr_page"]'):
page_properties = page.attrib.get('title') page_properties = page.attrib.get('title')
facsimile = re.search(r'image \"(.*?)\"', page_properties).group(1) facsimile = re.search(r'image \"(.*?)\"', page_properties).group(1)
@ -53,5 +53,5 @@ tei += ' </body>\n'
tei += ' </text>\n' tei += ' </text>\n'
tei += '</TEI>\n' tei += '</TEI>\n'
with open(args.o, 'w') as tei_file: with open(args.output, 'w') as tei_file:
tei_file.write(tei) tei_file.write(tei)