qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-07 19:05:13 +02:00
Code Issues Releases Wiki Activity

ADD os path join and unique hashname

Browse source
This commit is contained in:
JKamlah 2019-11-15 19:17:32 +01:00
parent eb70510271
commit 4ae2425e5a
2 changed files with 7 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
qurator/dinglehopper/cli.py
View file

@ -44,13 +44,13 @@ def gen_diff_report(gt_things, ocr_things, css_prefix, joiner, none, align):
def delete_tempcache():
# Delete all tempfiles and the directory (if empty)
tempdir = tempfile.gettempdir() + "/dinglehopper/"
tempdir = os.path.join(tempfile.gettempdir(), "dinglehopper/")
if os.path.exists(tempdir):
tempfiles = glob.glob(tempdir+"*.np*")
for tempfilename in tempfiles:
os.remove(tempfilename)
if not os.listdir(tempdir):
shutil.rmtree(os.path.normpath(tempdir))
shutil.rmtree(tempdir)
def process(gt, ocr, report_prefix):

9
qurator/dinglehopper/edit_distance.py
View file

@ -23,11 +23,12 @@ def levenshtein_matrix(seq1, seq2, tempcache=True):
strings, e.g. lists of grapheme clusters or lists of word strings.
"""
if tempcache:
hashname = hashlib.sha1(("".join(seq1) + "".join(seq2)).encode("utf-8")).hexdigest()
tempdir = os.path.normpath(tempfile.gettempdir() + "/dinglehopper/")
hashseq1 = hashlib.sha1(("؟".join(seq1)).encode("utf-8")).hexdigest()
hashseq2 = hashlib.sha1(("؟".join(seq2)).encode("utf-8")).hexdigest()
tempdir = os.path.join(tempfile.gettempdir(), "dinglehopper/")
if not os.path.exists(tempdir):
os.makedirs(tempdir + "/dinglehopper/")
tempfilename = os.path.normpath(tempdir + "/" + hashname + ".npy")
os.makedirs(tempdir)
tempfilename = os.path.join(tempdir, hashseq1 + "." + hashseq2 + ".npy")
if os.path.exists(tempfilename):
return np.load(tempfilename)