Add localwebroot configuration option.

config/linkcheckerrc

@@ -159,6 +159,15 @@
 # The memory dump only works if the python-meliae package is installed.
 # Otherwise a warning is printed to install it.
 #debugmemory=0
+# When checking absolute URLs inside local files, the given root directory
+# is used as base URL.
+# Note that the given directory must have URL syntax, so it must use a slash
+# to join directories instead of a backslash.
+# And the given directory must end with a slash.
+# Unix example:
+#localwebroot=/var/www/
+# Windows example:
+#localwebroot=/C|/public_html/
 
 
 ##################### filtering options ##########################

doc/changelog.txt

@@ -10,6 +10,9 @@ Changes:
   directives of the form "<? ?>".
   Prevents false errors when checking local PHP files.
   Closes: SF bug #3532763
+- checking: Allow configuration of local webroot directory to
+  enable checking of local HTML files with absolute URLs.
+  Closes: SF bug #3533203
 
 Features:
 - installation: Support RPM building with cx_Freeze.

doc/de/linkcheckerrc.5

@@ -120,6 +120,17 @@ ist. Andernfalls wird eine Warnung angezeigt mit dem Hinweis dieses Paket zu
 installieren.
 .br
 Kommandozeilenoption: keine
+.TP 
+\fBlocalwebroot=\fP\fISTRING\fP
+Beim Prüfen von absoluten URLs in lokalen Dateien wird das angegebene
+Wurzelverzeichnis als Basis\-URL benutzt.
+.br
+Beachten Sie dass das angegebene Verzeichnis in URL\-Syntax sein muss,
+d.h. es muss einen normalen statt einen umgekehrten Schrägstrich zum
+Aneinanderfügen von Verzeichnissen benutzen. Und das angegebene Verzeichnis
+muss mit einem Schrägstrich enden.
+.br
+Kommandozeilenoption: keine
 .SS [filtering]
 .TP 
 \fBignore=\fP\fIREGEX\fP (MULTILINE)

doc/en/linkcheckerrc.5

@@ -113,6 +113,16 @@ The memory dump only works if the python-meliae package is installed.
 Otherwise a warning is printed to install it.
 .br
 Command line option: none
+.TP
+\fBlocalwebroot=\fP\fISTRING\fP
+When checking absolute URLs inside local files, the given root directory
+is used as base URL.
+.br
+Note that the given directory must have URL syntax, so it must use a slash
+to join directories instead of a backslash.
+And the given directory must end with a slash.
+.br
+Command line option: none
 .SS \fB[filtering]\fP
 .TP
 \fBignore=\fP\fIREGEX\fP (MULTILINE)

linkcheck/checker/fileurl.py

@@ -298,3 +298,13 @@ class FileUrl (urlbase.UrlBase):
                 # remove last filename to make directory internal
                 url = url[:i+1]
         return re.escape(url)
+
+    def add_url (self, url, line=0, column=0, name=u"", base=None):
+        """If a local webroot directory is configured, replace absolute URLs
+        with it. After that queue the URL data for checking."""
+        webroot = self.aggregate.config["localwebroot"]
+        if webroot and url and url.startswith(u"/"):
+            url = webroot + url[1:]
+            log.debug(LOG_CHECK, "Applied local webroot `%s' to `%s'.",
+                webroot, url)
+        super(FileUrl, self).add_url(url, line=line, column=column, name=name, base=base)

linkcheck/configuration/__init__.py

@@ -193,6 +193,7 @@ class Configuration (dict):
         self["clamavconf"] = clamav.canonical_clamav_conf()
         self["useragent"] = UserAgent
         self["debugmemory"] = False
+        self["localwebroot"] = None
         from ..logger import Loggers
         self.loggers = dict(**Loggers)
 

linkcheck/configuration/confparse.py

@@ -153,6 +153,8 @@ class LCConfigParser (ConfigParser.RawConfigParser, object):
                 self.getboolean(section, "cookies")
         if self.has_option(section, "cookiefile"):
             self.config['cookiefile'] = self.get(section, 'cookiefile')
+        if self.has_option(section, "localwebroot"):
+            self.config['localwebroot'] = self.get(section, 'localwebroot')
 
     def read_authentication_config (self):
         """Read configuration options in section "authentication"."""