0ct0pu5/wesnoth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

When a spelling exception occurs, report the non-case-smashed token.

Browse source
This commit is contained in:
Eric S. Raymond 2008-11-03 07:41:08 +00:00
parent c279bd6ba1
commit 53d2b62b88
1 changed files with 29 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
data/tools/wmllint
View file

@ -1169,13 +1169,16 @@ def spellcheck(fn, d):
(key, prefix, value, comment) = parse_attribute(nav.text)
if "no spellcheck" in comment:
continue
# Strip off translation marks
if value.startswith("_"):
value = value[1:].strip()
# Remove line continuations, they interfere with string-stripping
# Strip off line continuations, they interfere with string-stripping
value = value.strip()
if value.endswith("+"):
value = value[:-1].rstrip()
# Strip off string quotes
value = string_strip(value)
# Discard extraneous stuff
value = value.replace("...", " ")
value = value.replace("''", "")
value = value.replace("female^", " ")
@ -1183,48 +1186,49 @@ def spellcheck(fn, d):
if '<' in value:
value = re.sub("<[^>]+>text='([^']*)'<[^>]+>", r"\1", value)
value = re.sub("<[0-9,]+>", "", value)
value = value.lower()
# Fold continued lines
value = re.sub(r'" *\+\s*_ *"', "", value)
for token in value.split():
if d.check(token):
lowered = token.lower()
if d.check(lowered):
continue
while token and token[0] in " \t(`@*'%_":
token = token[1:]
while token and token[-1] in "_-*').,:;?!& \t":
token = token[:-1]
if not token or token.startswith("$") or token[0].isdigit():
while lowered and lowered[0] in " \t(`@*'%_":
lowered = lowered[1:]
while lowered and lowered[-1] in "_-*').,:;?!& \t":
lowered = lowered[:-1]
if not lowered or lowered.startswith("$") or lowered[0].isdigit():
continue
token = string_strip(token)
if token and d.check(token):
lowered = string_strip(lowered)
if lowered and d.check(lowered):
continue
elif token.endswith("'s") and d.check(token[:-2]):
elif lowered.endswith("'s") and d.check(lowered[:-2]):
continue
elif token.endswith("s'") and d.check(token[:-2]):
elif lowered.endswith("s'") and d.check(lowered[:-2]):
continue
if "-" in token:
parts = token.split("-")
if "-" in lowered:
parts = lowered.split("-")
if filter(lambda w: not w or d.check(w), parts) == parts:
continue
if re.match("[+-][0-9]", token):
if re.match("[+-][0-9]", lowered):
continue
# Match various onomatopoetic exclamations of variable form
if re.match("hm+", token):
if re.match("hm+", lowered):
continue
if re.match("a+[ur]*g+h*", token):
if re.match("a+[ur]*g+h*", lowered):
continue
if re.match("(mu)?ha(ha)*", token):
if re.match("(mu)?ha(ha)*", lowered):
continue
if re.match("ah+", token):
if re.match("ah+", lowered):
continue
if re.match("no+", token):
if re.match("no+", lowered):
continue
if re.match("no+", token):
if re.match("no+", lowered):
continue
if re.match("um+", token):
if re.match("um+", lowered):
continue
if re.match("aw+", token):
if re.match("aw+", lowered):
continue
if re.match("o+h+", token):
if re.match("o+h+", lowered):
continue
print nav.whereami(), 'possible misspelling "%s"' % token
# Take exceptions from name, id, and type fields
@ -1438,7 +1442,7 @@ if __name__ == '__main__':
sys.stderr.write("wmllint: internal error on %s\n" % fn)
(exc_type, exc_value, exc_traceback) = sys.exc_info()
raise exc_type, exc_value, exc_traceback
if not clean and not revert and future:
if not clean and not revert:
# Consistency-check everything we got from the file scans
consistency_check()
# Attempt a spell-check