tris/recoll
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

rclocrtesseract: unquote tesseractcmd parameter and check existence.

Browse Source
This commit is contained in:
Jean-Francois Dockes 2020-09-23 19:50:49 +02:00
parent 0dd609cf1a
commit 8accec9b88
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/filters/rclocrtesseract.py
View File

@ -80,13 +80,19 @@ def ocrpossible(config, path):
global tesseractcmd global tesseractcmd
if not tesseractcmd: if not tesseractcmd:
config.setKeyDir(os.path.dirname(path)) config.setKeyDir(os.path.dirname(path))
tesseractcmd = config.getConfParam("tesseractcmd") # It is very tempting to quote this value, esp. on Windows where it
# will contain whitespace. There is no chance that an actual command
# line would have quotes, so unquote it.
tesseractcmd = config.getConfParam("tesseractcmd").strip('"')
if not tesseractcmd: if not tesseractcmd:
tesseractcmd = rclexecm.which("tesseract") tesseractcmd = rclexecm.which("tesseract")
if not tesseractcmd: if not tesseractcmd:
_deb("tesseractcmd not found") _deb("tesseractcmd not found")
return False return False
if not os.path.isfile(tesseractcmd):
_deb("tesseractcmd parameter [%s] is not a file" % tesseractcmd)
return False
# Check input format # Check input format
base,ext = os.path.splitext(path) base,ext = os.path.splitext(path)
ext = ext.lower() ext = ext.lower()