From: William A. Rowe Jr <wrowe@apache.org>
Date: Fri, 5 Apr 2002 04:22:45 +0000 (+0000)
Subject:   One for 2.0.34 - to fix the problem of utf-8 configuration files saved
X-Git-Tag: 2.0.35~22
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=95270aa043f94c5d9fc8528e4d6def97119638e0;p=apache

  One for 2.0.34 - to fix the problem of utf-8 configuration files saved
  from MeSsed up editors that believe zero byte joiner lead bytes signify
  a utf-8 file.  Someone point me at an RFC ... gheesh.

  FWIW; fixes bugs report 10125


git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/trunk@94446 13f79535-47bb-0310-9956-ffa450edef68
---

diff --git a/server/util.c b/server/util.c
index e66f291da5..86a3c9f302 100644
--- a/server/util.c
+++ b/server/util.c
@@ -916,6 +916,29 @@ AP_DECLARE(apr_status_t) ap_pcfg_openfile(ap_configfile_t **ret_cfg, apr_pool_t
         return APR_EBADF;
     }
 
+#ifdef WIN32
+    /* Some twisted character [no pun intended] at MS decided that a
+     * zero width joiner as the lead wide character would be ideal for
+     * describing Unicode text files.  This was further convoluted to
+     * another MSism that the same character mapped into utf-8, EF BB BF
+     * would signify utf-8 text files.
+     *
+     * Since MS configuration files are all protecting utf-8 encoded
+     * Unicode path, file and resource names, we already have the correct 
+     * WinNT encoding.  But at least eat the stupid three bytes up front.
+     */
+    {
+        unsigned char buf[4];
+        apr_size_t len = 3;
+        status = apr_file_read(file, buf, &len);
+        if ((status != APR_SUCCESS) || (len < 3) 
+              || memcmp(buf, "\xEF\xBB\xBF", 3) != 0) {
+            apr_off_t zero = 0;
+            apr_file_seek(file, APR_SET, &zero);
+        }
+    }
+#endif
+
     new_cfg = apr_palloc(p, sizeof(*new_cfg));
     new_cfg->param = file;
     new_cfg->name = apr_pstrdup(p, name);