XPUB
/
OuNuPo
6
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updated erase & replace python script with sort function

Browse Source
master^2
nberting 7 years ago
parent cc9c5b39ac
commit 9e1f618b68
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File

4
src/erase_leastcommon.py
Unescape Escape View File

@ -46,8 +46,8 @@ def filternone(word_raw):
x = -1 x = -1
leastcommon_list = [] leastcommon_list = []
allwords = [] allwords = []
scanimg = glob.glob('images-tiff/*.tiff') scanimg = sorted(glob.glob('images-tiff/*.tiff'))
hocr = glob.glob('hocr/*.html') hocr = sorted(glob.glob('hocr/*.html'))
maximum = 20 / len(scanimg) # this helps the script remove words in a way that is proportional to number of pages scanned maximum = 20 / len(scanimg) # this helps the script remove words in a way that is proportional to number of pages scanned
# loop through every image in scanimg folder # loop through every image in scanimg folder

4
src/replace_leastcommon.py
Unescape Escape View File

@ -63,8 +63,8 @@ def filternone(word_raw):
x = -1 x = -1
leastcommon_list = [] leastcommon_list = []
allwords = [] allwords = []
scanimg = glob.glob('images-tiff/*.tiff') scanimg = sorted(glob.glob('images-tiff/*.tiff'))
hocr = glob.glob('hocr/*.html') hocr = sorted(glob.glob('hocr/*.html'))
num = 0 num = 0
maximum = 20 / len(scanimg) # this helps the script remove words in a way that is proportional to number of pages scanned maximum = 20 / len(scanimg) # this helps the script remove words in a way that is proportional to number of pages scanned

Write Preview
Loading…
Cancel
Save