Added 'linklint' scons target

git-svn-id: https://svn.berlios.de/svnroot/repos/senf/trunk@432 270642c3-0616-0410-b53a-bc976706d245

diff --git a/SConstruct b/SConstruct
index bcfdd21..449ab7c 100644 (file)
--- a/SConstruct
+++ b/SConstruct
@@ -62,6 +62,7 @@ install_all  Install SENF into $PREFIX
 deb          Build debian source and binary package
 debsrc       Build debian source package
 debbin       Build debian binary package
+linklint     Check links of doxygen documentation with 'linklint'
 """)
 
 if os.environ.get('debian_build'):
@@ -144,3 +145,14 @@ env.Clean('all', [ os.path.join(path,f)
                    for path, subdirs, files in os.walk('.')
                    for pattern in env['CLEAN_PATTERNS']
                    for f in fnmatch.filter(files,pattern) ])
+
+env.AlwaysBuild(env.Alias('linklint', [ 'all_docs' ], [
+    'rm -rf linklint',
+    'linklint -doc linklint -net -limit 99999999 `find -type d -name html -printf "/%P/@ "`',
+    '[ -r linklint/errorX.html ] && python linklint_addnames.py <linklint/errorX.html >linklint/errorX.html.new',
+    '[ -r linklint/errorX.html.new ] && mv linklint/errorX.html.new linklint/errorX.html',
+    '[ -r linklint/errorAX.html ] && python linklint_addnames.py <linklint/errorAX.html >linklint/errorAX.html.new',
+    '[ -r linklint/errorAX.html.new ] && mv linklint/errorAX.html.new linklint/errorAX.html',
+    '@echo -e "\\nLokal link check results: linklint/index.html"',
+    '@echo -e "Remote link check results: linklint/urlindex.html\\n"'
+]))

diff --git a/linklint_addnames.py b/linklint_addnames.py
new file mode 100644 (file)
index 0000000..d8bb8c5
--- /dev/null
+++ b/linklint_addnames.py
@@ -0,0 +1,85 @@
+#!/usr/bin/python
+
+import HTMLParser, re, sys, os.path
+
+class ScanLinks(HTMLParser.HTMLParser):
+
+    def __init__(self, target, base):
+        HTMLParser.HTMLParser.__init__(self)
+        self._target = target
+        self._base = base
+        self._collect = False
+        self._data = ""
+        self._value = ""
+
+    def startCollect(self):
+        self._collect = True
+        self._data = ""
+
+    def endCollect(self):
+        self._collect = False
+        return self._data
+
+    def collecting(self):
+        return self._collect
+
+    def handle_starttag(self,tag,attrs):
+        m = getattr(self,'_s_'+tag.upper(),None)
+        if m:
+            m(attrs)
+
+    def handle_endtag(self,tag):
+        m = getattr(self,'_e_'+tag.upper(),None)
+        if m:
+            m()
+
+    def handle_data(self,data):
+        if self._collect:
+            self._data += data
+
+    def handle_charref(self,name):
+        self.handle_data(name)
+
+    def handle_entityref(self,name):
+        self.handle_data(name)
+
+    def value(self):
+        return self._value
+
+    ###########################################################################
+
+    SCHEME_RE=re.compile("[a-z]+:")
+
+    def _s_A(self,attrs):
+        attrs = dict(attrs)
+        url = attrs.get('href')
+        if url and not self.SCHEME_RE.match(url):
+            if '#' in self._target:
+                p = os.path.abspath(os.path.join(self._base,url))
+            else:
+                p = os.path.abspath(os.path.join(self._base,url.split('#')[0]))
+            if  p == self._target:
+                self.startCollect()
+        
+    def _e_A(self):
+        if self.collecting():
+            self._value = self.endCollect()
+
+WS_RE=re.compile("\\s+")
+
+def linkName(target,f):
+    scanner = ScanLinks(target,os.path.split(os.path.abspath(f))[0])
+    scanner.feed(file(f).read())
+    return WS_RE.sub(' ',scanner.value().strip())
+
+process = 0
+target = 0
+for line in sys.stdin:
+    if line.startswith('<a href='):
+        target = line.split(':')[1]
+        target = target[2:].split('"')[0]
+    elif line.startswith('    <a href='):
+        f = line.split(':')[1]
+        f = f[2:].split('"')[0]
+        line = '%s (%s)</a>\n'  % (line[:-5], linkName(target,f))
+    sys.stdout.write(line)