Rewrite/cleanup/tests of URI normalization:

- uri.c: rewrite of xmlNormalizeURIPath from Paul D. Smith
- test/URI/smith.uri result/URI/smith.uri Makefile.am:
  added the new tests for URI normalization
- testURI.c: fixed stoopid bugs
- result/VC/OneID3 result/VC/UniqueElementTypeDeclaration:
  the URI in the error messages are now properly normalized
Daniel

ChangeLog

@@ -1,3 +1,12 @@
+Fri Feb  2 18:04:35 CET 2001 Daniel Veillard <Daniel.Veillard@imag.fr>
+
+	* uri.c: rewrite of xmlNormalizeURIPath from Paul D. Smith
+	* test/URI/smith.uri result/URI/smith.uri Makefile.am:
+	  added the new tests for URI normalization
+	* testURI.c: fixed stoopid bugs
+	* result/VC/OneID3 result/VC/UniqueElementTypeDeclaration:
+	  the URI in the error messages are now properly normalized
+
 Fri Feb  2 09:18:53 CET 2001 Daniel Veillard <Daniel.Veillard@imag.fr>
 
 	* uri.c: applied Marc Sanfacon's patch for xmlNormalizeURIPath

Makefile.am

@@ -237,6 +237,19 @@ URItests : testURI
 	      diff $(srcdir)/result/URI/$$name result.$$name ; \
 	      rm result.$$name ; \
 	  fi ; fi ; done)
+	@(for i in $(srcdir)/test/URI/*.uri ; do \
+	  name=`basename $$i`; \
+	  if [ ! -d $$i ] ; then \
+	  if [ ! -f $(srcdir)/result/URI/$$name ] ; then \
+	      echo New test file $$name ; \
+	      $(top_builddir)/testURI < $$i > $(srcdir)/result/URI/$$name ; \
+	  else \
+	      echo Testing $$name ; \
+	      $(top_builddir)/testURI < $$i > result.$$name ; \
+	      grep "MORY ALLO" .memdump  | grep -v "MEMORY ALLOCATED : 0";\
+	      diff $(srcdir)/result/URI/$$name result.$$name ; \
+	      rm result.$$name ; \
+	  fi ; fi ; done)
 
 XPathtests : testXPath
 	@echo "##"

aclocal.m4

@@ -620,31 +620,35 @@ esac
 ])
 
 # AC_LIBLTDL_CONVENIENCE[(dir)] - sets LIBLTDL to the link flags for
-# the libltdl convenience library, adds --enable-ltdl-convenience to
+# the libltdl convenience library and INCLTDL to the include flags for
-# the configure arguments.  Note that LIBLTDL is not AC_SUBSTed, nor
+# the libltdl header and adds --enable-ltdl-convenience to the
-# is AC_CONFIG_SUBDIRS called.  If DIR is not provided, it is assumed
+# configure arguments.  Note that LIBLTDL and INCLTDL are not
-# to be `${top_builddir}/libltdl'.  Make sure you start DIR with
+# AC_SUBSTed, nor is AC_CONFIG_SUBDIRS called.  If DIR is not
-# '${top_builddir}/' (note the single quotes!) if your package is not
+# provided, it is assumed to be `libltdl'.  LIBLTDL will be prefixed
-# flat, and, if you're not using automake, define top_builddir as
+# with '${top_builddir}/' and INCLTDL will be prefixed with
-# appropriate in the Makefiles.
+# '${top_srcdir}/' (note the single quotes!).  If your package is not
+# flat and you're not using automake, define top_builddir and
+# top_srcdir appropriately in the Makefiles.
 AC_DEFUN(AC_LIBLTDL_CONVENIENCE, [AC_BEFORE([$0],[AC_LIBTOOL_SETUP])dnl
   case "$enable_ltdl_convenience" in
   no) AC_MSG_ERROR([this package needs a convenience libltdl]) ;;
   "") enable_ltdl_convenience=yes
       ac_configure_args="$ac_configure_args --enable-ltdl-convenience" ;;
   esac
-  LIBLTDL=ifelse($#,1,$1,['${top_builddir}/libltdl'])/libltdlc.la
+  LIBLTDL='${top_builddir}/'ifelse($#,1,[$1],['libltdl'])/libltdlc.la
-  INCLTDL=ifelse($#,1,-I$1,['-I${top_builddir}/libltdl'])
+  INCLTDL='-I${top_srcdir}/'ifelse($#,1,[$1],['libltdl'])
 ])
 
 # AC_LIBLTDL_INSTALLABLE[(dir)] - sets LIBLTDL to the link flags for
-# the libltdl installable library, and adds --enable-ltdl-install to
+# the libltdl installable library and INCLTDL to the include flags for
-# the configure arguments.  Note that LIBLTDL is not AC_SUBSTed, nor
+# the libltdl header and adds --enable-ltdl-install to the configure
-# is AC_CONFIG_SUBDIRS called.  If DIR is not provided, it is assumed
+# arguments.  Note that LIBLTDL and INCLTDL are not AC_SUBSTed, nor is
-# to be `${top_builddir}/libltdl'.  Make sure you start DIR with
+# AC_CONFIG_SUBDIRS called.  If DIR is not provided and an installed
-# '${top_builddir}/' (note the single quotes!) if your package is not
+# libltdl is not found, it is assumed to be `libltdl'.  LIBLTDL will
-# flat, and, if you're not using automake, define top_builddir as
+# be prefixed with '${top_builddir}/' and INCLTDL will be prefixed
-# appropriate in the Makefiles.
+# with '${top_srcdir}/' (note the single quotes!).  If your package is
+# not flat and you're not using automake, define top_builddir and
+# top_srcdir appropriately in the Makefiles.
 # In the future, this macro may have to be called after AC_PROG_LIBTOOL.
 AC_DEFUN(AC_LIBLTDL_INSTALLABLE, [AC_BEFORE([$0],[AC_LIBTOOL_SETUP])dnl
   AC_CHECK_LIB(ltdl, main,
@@ -657,8 +661,8 @@ AC_DEFUN(AC_LIBLTDL_INSTALLABLE, [AC_BEFORE([$0],[AC_LIBTOOL_SETUP])dnl
   ])
   if test x"$enable_ltdl_install" = x"yes"; then
     ac_configure_args="$ac_configure_args --enable-ltdl-install"
-    LIBLTDL=ifelse($#,1,$1,['${top_builddir}/libltdl'])/libltdl.la
+    LIBLTDL='${top_builddir}/'ifelse($#,1,[$1],['libltdl'])/libltdl.la
-    INCLTDL=ifelse($#,1,-I$1,['-I${top_builddir}/libltdl'])
+    INCLTDL='-I${top_srcdir}/'ifelse($#,1,[$1],['libltdl'])
   else
     ac_configure_args="$ac_configure_args --enable-ltdl-install=no"
     LIBLTDL="-lltdl"

result/URI/smith.uri

@@ -0,0 +1,15 @@
+/bar
+bar
+bar
+bar
+baz
+
+foo/
+foo
+foo
+../foo./
+../foo/
+/foo
+../foo
+../../foo
+../../../foo

result/VC/OneID3

@@ -1,3 +1,3 @@
-./test/VC/dtds/doc.dtd:2: validity error: Element doc has ID attributes defined in the internal and external subset : val
+test/VC/dtds/doc.dtd:2: validity error: Element doc has ID attributes defined in the internal and external subset : val
 <!ATTLIST doc val ID #IMPLIED>
                              ^

result/VC/UniqueElementTypeDeclaration

@@ -1,3 +1,3 @@
-./test/VC/dtds/a.dtd:1: validity error: Redefinition of element a
+test/VC/dtds/a.dtd:1: validity error: Redefinition of element a
 <!ELEMENT a (#PCDATA | b | c)*>
                               ^

test/URI/smith.uri

@@ -0,0 +1,15 @@
+/foo/../bar
+foo/../bar
+./foo/../bar
+foo/./../bar
+foo/bar/.././../baz
+foo/..
+foo/bar/..
+./foo
+././foo
+.././foo./
+.././foo/.
+/foo
+../foo
+../../foo
+../../../foo

testURI.c

@@ -27,11 +27,8 @@ int main(int argc, char **argv) {
     const char *base = NULL;
     xmlChar *composite;
 
-    if (argv[arg] == NULL) {
+    if ((argv[arg] != NULL) &&
-	printf("Usage: %s [-base URI] URI ...\n", argv[0]);
+	((!strcmp(argv[arg], "-base")) || (!strcmp(argv[arg], "--base")))) {
-	exit(0);
-    }
-    if ((!strcmp(argv[arg], "-base")) || (!strcmp(argv[arg], "--base"))) {
 	arg++;
 	base = argv[arg];
 	if (base != NULL)
@@ -64,6 +61,7 @@ int main(int argc, char **argv) {
 		if (ret != 0)
 		    printf("%s : error %d\n", str, ret);
 		else {
+		    xmlNormalizeURIPath(uri->path);
 		    xmlPrintURI(stdout, uri);
 		    printf("\n");
 		}
@@ -99,5 +97,5 @@ int main(int argc, char **argv) {
     }
     xmlFreeURI(uri);
     xmlMemoryDump();
-    exit(0);
+    return(0);
 }

uri.c

@@ -606,6 +606,7 @@ xmlFreeURI(xmlURIPtr uri) {
  *									*
  ************************************************************************/
 
+#if 0
 /**
  * xmlNormalizeURIPath:
  * @path:  pointer to the path string
@@ -739,6 +740,184 @@ xmlNormalizeURIPath(char *path) {
     }
     return(0);
 }
+#else
+/**
+ * xmlNormalizeURIPath:
+ * @path:  pointer to the path string
+ *
+ * Applies the 5 normalization steps to a path string--that is, RFC 2396
+ * Section 5.2, steps 6.c through 6.g.
+ *
+ * Normalization occurs directly on the string, no new allocation is done
+ *
+ * Returns 0 or an error code
+ */
+int
+xmlNormalizeURIPath(char *path) {
+    char *cur, *out;
+
+    if (path == NULL)
+	return(-1);
+
+    /* Skip all initial "/" chars.  We want to get to the beginning of the
+     * first non-empty segment.
+     */
+    cur = path;
+    while (cur[0] == '/')
+      ++cur;
+    if (cur[0] == '\0')
+      return(0);
+
+    /* Keep everything we've seen so far.  */
+    out = cur;
+
+    /*
+     * Analyze each segment in sequence for cases (c) and (d).
+     */
+    while (cur[0] != '\0') {
+	/*
+	 * c) All occurrences of "./", where "." is a complete path segment,
+	 *    are removed from the buffer string.
+	 */
+	if ((cur[0] == '.') && (cur[1] == '/')) {
+	    cur += 2;
+	    continue;
+	}
+
+	/*
+	 * d) If the buffer string ends with "." as a complete path segment,
+	 *    that "." is removed.
+	 */
+	if ((cur[0] == '.') && (cur[1] == '\0'))
+	    break;
+
+	/* Otherwise keep the segment.  */
+	while (cur[0] != '/') {
+            if (cur[0] == '\0')
+              goto done_cd;
+	    (out++)[0] = (cur++)[0];
+	}
+        (out++)[0] = (cur++)[0];
+    }
+ done_cd:
+    out[0] = '\0';
+
+    /* Reset to the beginning of the first segment for the next sequence.  */
+    cur = path;
+    while (cur[0] == '/')
+      ++cur;
+    if (cur[0] == '\0')
+	return(0);
+
+    /*
+     * Analyze each segment in sequence for cases (e) and (f).
+     *
+     * e) All occurrences of "<segment>/../", where <segment> is a
+     *    complete path segment not equal to "..", are removed from the
+     *    buffer string.  Removal of these path segments is performed
+     *    iteratively, removing the leftmost matching pattern on each
+     *    iteration, until no matching pattern remains.
+     *
+     * f) If the buffer string ends with "<segment>/..", where <segment>
+     *    is a complete path segment not equal to "..", that
+     *    "<segment>/.." is removed.
+     *
+     * To satisfy the "iterative" clause in (e), we need to collapse the
+     * string every time we find something that needs to be removed.  Thus,
+     * we don't need to keep two pointers into the string: we only need a
+     * "current position" pointer.
+     */
+    while (1) {
+        char *segp;
+
+        /* At the beginning of each iteration of this loop, "cur" points to
+         * the first character of the segment we want to examine.
+         */
+
+        /* Find the end of the current segment.  */
+        segp = cur;
+        while ((segp[0] != '/') && (segp[0] != '\0'))
+          ++segp;
+
+        /* If this is the last segment, we're done (we need at least two
+         * segments to meet the criteria for the (e) and (f) cases).
+         */
+        if (segp[0] == '\0')
+          break;
+
+        /* If the first segment is "..", or if the next segment _isn't_ "..",
+         * keep this segment and try the next one.
+         */
+        ++segp;
+        if (((cur[0] == '.') && (cur[1] == '.') && (segp == cur+3))
+            || ((segp[0] != '.') || (segp[1] != '.')
+                || ((segp[2] != '/') && (segp[2] != '\0')))) {
+          cur = segp;
+          continue;
+        }
+
+        /* If we get here, remove this segment and the next one and back up
+         * to the previous segment (if there is one), to implement the
+         * "iteratively" clause.  It's pretty much impossible to back up
+         * while maintaining two pointers into the buffer, so just compact
+         * the whole buffer now.
+         */
+
+        /* If this is the end of the buffer, we're done.  */
+        if (segp[2] == '\0') {
+          cur[0] = '\0';
+          break;
+        }
+        strcpy(cur, segp + 3);
+
+        /* If there are no previous segments, then keep going from here.  */
+        segp = cur;
+        while ((segp > path) && ((--segp)[0] == '/'))
+          ;
+        if (segp == path)
+          continue;
+
+        /* "segp" is pointing to the end of a previous segment; find it's
+         * start.  We need to back up to the previous segment and start
+         * over with that to handle things like "foo/bar/../..".  If we
+         * don't do this, then on the first pass we'll remove the "bar/..",
+         * but be pointing at the second ".." so we won't realize we can also
+         * remove the "foo/..".
+         */
+        cur = segp;
+        while ((cur > path) && (cur[-1] != '/'))
+          --cur;
+    }
+    out[0] = '\0';
+
+    /*
+     * g) If the resulting buffer string still begins with one or more
+     *    complete path segments of "..", then the reference is
+     *    considered to be in error. Implementations may handle this
+     *    error by retaining these components in the resolved path (i.e.,
+     *    treating them as part of the final URI), by removing them from
+     *    the resolved path (i.e., discarding relative levels above the
+     *    root), or by avoiding traversal of the reference.
+     *
+     * We discard them from the final path.
+     */
+    if (path[0] == '/') {
+      cur = path;
+      while ((cur[1] == '.') && (cur[2] == '.')
+             && ((cur[3] == '/') || (cur[3] == '\0')))
+	cur += 3;
+
+      if (cur != path) {
+	out = path;
+	while (cur[0] != '\0')
+          (out++)[0] = (cur++)[0];
+	out[0] = 0;
+      }
+    }
+
+    return(0);
+}
+#endif
 
 /**
  * xmlURIUnescapeString: