Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

avoid false positives in regexes, and parse nested classes correctly 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1377953 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2012-08-28 02:53:39 +00:00
parent b4ca62c640
commit e82f5c2862
1 changed files with 16 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
dev-tools/scripts/checkJavaDocs.py
View File

@ -22,8 +22,9 @@ reHREF = re.compile('<a.*?>(.*?)</a>', re.IGNORECASE)
reMarkup = re.compile('<.*?>')
reDivBlock = re.compile('<div class="block">(.*?)</div>', re.IGNORECASE)
reCaption = re.compile('<caption><span>(.*?)</span>', re.IGNORECASE)
reTDLast = re.compile('<td class="colLast">.*<a href=".*#(.*?)">', re.IGNORECASE)
reColOne = re.compile('<td class="colOne">.*<a href=".*#(.*?)">', re.IGNORECASE)
reTDLastNested = re.compile('<td class="colLast"><code><strong><a href="[^>]*\.([^>]*?)\.html" title="class in[^>]*">', re.IGNORECASE)
reTDLast = re.compile('<td class="colLast"><code><strong><a href="[^>]*#([^>]*?)">', re.IGNORECASE)
reColOne = re.compile('<td class="colOne"><code><strong><a href="[^>]*#([^>]*?)">', re.IGNORECASE)
def cleanHTML(s):
s = reMarkup.sub('', s)
@ -50,18 +51,25 @@ def checkClass(fullPath):
if m is not None:
lastCaption = m.group(1)
#print(' caption %s' % lastCaption)
m = reTDLast.search(line)
m = reTDLastNested.search(line)
if m is not None:
# TODO: this is actually the link anchor for the method, which we must
# somehow defer and only later check if the list at that anchor does not contain
# the text 'specified by' (in which case its an overridden method from an external library)
# nested classes
lastItem = m.group(1)
#print(' item %s' % lastItem)
else:
m = reColOne.search(line)
m = reTDLast.search(line)
if m is not None:
# methods etc
# TODO: this is actually the link anchor for the method, which we must
# somehow defer and only later check if the list at that anchor does not contain
# the text 'specified by' (in which case its an overridden method from an external library)
lastItem = m.group(1)
#print(' item %s' % lastItem)
else:
# ctors etc
m = reColOne.search(line)
if m is not None:
lastItem = m.group(1)
#print(' item %s' % lastItem)
lineLower = line.strip().lower()