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

python preview filter: avoid printing spurious encoding value

Browse Source
This commit is contained in:
Jean-Francois Dockes 2022-07-31 21:58:03 +02:00
parent 70723a5280
commit 9b06d05be7
1 changed files with 13 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/filters/rclpython.py
View File

@ -51,6 +51,12 @@ _css_classes = {
_TEXT: 'text', _TEXT: 'text',
} }
# python3.8 token.py sends an ENCODING token which we ignore
try:
token_encoding_type = token.ENCODING
except:
token_encoding_type = 62
_HTML_HEADER = """\ _HTML_HEADER = """\
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
"http://www.w3.org/TR/html4/loose.dtd"> "http://www.w3.org/TR/html4/loose.dtd">
@ -146,17 +152,21 @@ class Parser:
def __call__(self, toktype, toktext, startpos, endpos, line): def __call__(self, toktype, toktext, startpos, endpos, line):
""" Token handler. """ Token handler.
""" """
srow, scol = startpos
erow, ecol = endpos
if 0: if 0:
print("type %s %s text %s start %s %s end %s %s<br>\n" % \ print("type %s %s text %s start %s %s end %s %s<br>\n" % \
(toktype, token.tok_name[toktype], toktext, \ (toktype, token.tok_name[toktype], toktext, \
srow, scol,erow,ecol)) srow, scol,erow,ecol), file=sys.stderr)
srow, scol = startpos
erow, ecol = endpos
# calculate new positions # calculate new positions
oldpos = self.pos oldpos = self.pos
newpos = self.lines[srow] + scol newpos = self.lines[srow] + scol
self.pos = newpos + len(toktext) self.pos = newpos + len(toktext)
if toktype == token_encoding_type:
return
# handle newlines # handle newlines
if toktype in [token.NEWLINE, tokenize.NL]: if toktype in [token.NEWLINE, tokenize.NL]:
self.out.write(b'\n') self.out.write(b'\n')